diff options
1074 files changed, 21646 insertions, 10645 deletions
@@ -126,6 +126,8 @@ Greg Kroah-Hartman <gregkh@suse.de> Greg Kroah-Hartman <greg@kroah.com> Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com> Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com> +Guo Ren <guoren@kernel.org> <guoren@linux.alibaba.com> +Guo Ren <guoren@kernel.org> <ren_guo@c-sky.com> Gustavo Padovan <gustavo@las.ic.unicamp.br> Gustavo Padovan <padovan@profusion.mobi> Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org> diff --git a/Documentation/admin-guide/blockdev/drbd/figures.rst b/Documentation/admin-guide/blockdev/drbd/figures.rst index bd9a4901fe46..9f73253ea353 100644 --- a/Documentation/admin-guide/blockdev/drbd/figures.rst +++ b/Documentation/admin-guide/blockdev/drbd/figures.rst @@ -25,6 +25,6 @@ Sub graphs of DRBD's state transitions :alt: disk-states-8.dot :align: center -.. kernel-figure:: node-states-8.dot - :alt: node-states-8.dot +.. kernel-figure:: peer-states-8.dot + :alt: peer-states-8.dot :align: center diff --git a/Documentation/admin-guide/blockdev/drbd/node-states-8.dot b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot index bfa54e1f8016..6dc3954954d6 100644 --- a/Documentation/admin-guide/blockdev/drbd/node-states-8.dot +++ b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot @@ -1,8 +1,3 @@ -digraph node_states { - Secondary -> Primary [ label = "ioctl_set_state()" ] - Primary -> Secondary [ label = "ioctl_set_state()" ] -} - digraph peer_states { Secondary -> Primary [ label = "recv state packet" ] Primary -> Secondary [ label = "recv state packet" ] diff --git a/Documentation/arm64/pointer-authentication.rst b/Documentation/arm64/pointer-authentication.rst index f127666ea3a8..e5dad2e40aa8 100644 --- a/Documentation/arm64/pointer-authentication.rst +++ b/Documentation/arm64/pointer-authentication.rst @@ -53,11 +53,10 @@ The number of bits that the PAC occupies in a pointer is 55 minus the virtual address size configured by the kernel. For example, with a virtual address size of 48, the PAC is 7 bits wide. -Recent versions of GCC can compile code with APIAKey-based return -address protection when passed the -msign-return-address option. This -uses instructions in the HINT space (unless -march=armv8.3-a or higher -is also passed), and such code can run on systems without the pointer -authentication extension. +When ARM64_PTR_AUTH_KERNEL is selected, the kernel will be compiled +with HINT space pointer authentication instructions protecting +function returns. Kernels built with this option will work on hardware +with or without pointer authentication support. In addition to exec(), keys can also be reinitialized to random values using the PR_PAC_RESET_KEYS prctl. A bitmask of PR_PAC_APIAKEY, diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index d0ec40d00c28..1ebf4c5c7ddc 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -3,7 +3,7 @@ BPF Type Format (BTF) ===================== 1. Introduction -*************** +=============== BTF (BPF Type Format) is the metadata format which encodes the debug info related to BPF program/map. The name BTF was used initially to describe data @@ -30,7 +30,7 @@ sections are discussed in details in :ref:`BTF_Type_String`. .. _BTF_Type_String: 2. BTF Type and String Encoding -******************************* +=============================== The file ``include/uapi/linux/btf.h`` provides high-level definition of how types/strings are encoded. @@ -57,13 +57,13 @@ little-endian target. The ``btf_header`` is designed to be extensible with generated. 2.1 String Encoding -=================== +------------------- The first string in the string section must be a null string. The rest of string table is a concatenation of other null-terminated strings. 2.2 Type Encoding -================= +----------------- The type id ``0`` is reserved for ``void`` type. The type section is parsed sequentially and type id is assigned to each recognized type starting from id @@ -504,7 +504,7 @@ valid index (starting from 0) pointing to a member or an argument. * ``type``: the type with ``btf_type_tag`` attribute 3. BTF Kernel API -***************** +================= The following bpf syscall command involves BTF: * BPF_BTF_LOAD: load a blob of BTF data into kernel @@ -547,14 +547,14 @@ The workflow typically looks like: 3.1 BPF_BTF_LOAD -================ +---------------- Load a blob of BTF data into kernel. A blob of data, described in :ref:`BTF_Type_String`, can be directly loaded into the kernel. A ``btf_fd`` is returned to a userspace. 3.2 BPF_MAP_CREATE -================== +------------------ A map can be created with ``btf_fd`` and specified key/value type id.:: @@ -581,7 +581,7 @@ automatically. .. _BPF_Prog_Load: 3.3 BPF_PROG_LOAD -================= +----------------- During prog_load, func_info and line_info can be passed to kernel with proper values for the following attributes: @@ -631,7 +631,7 @@ For line_info, the line number and column number are defined as below: #define BPF_LINE_INFO_LINE_COL(line_col) ((line_col) & 0x3ff) 3.4 BPF_{PROG,MAP}_GET_NEXT_ID -============================== +------------------------------ In kernel, every loaded program, map or btf has a unique id. The id won't change during the lifetime of a program, map, or btf. @@ -641,13 +641,13 @@ each command, to user space, for bpf program or maps, respectively, so an inspection tool can inspect all programs and maps. 3.5 BPF_{PROG,MAP}_GET_FD_BY_ID -=============================== +------------------------------- An introspection tool cannot use id to get details about program or maps. A file descriptor needs to be obtained first for reference-counting purpose. 3.6 BPF_OBJ_GET_INFO_BY_FD -========================== +-------------------------- Once a program/map fd is acquired, an introspection tool can get the detailed information from kernel about this fd, some of which are BTF-related. For @@ -656,7 +656,7 @@ example, ``bpf_map_info`` returns ``btf_id`` and key/value type ids. bpf byte codes, and jited_line_info. 3.7 BPF_BTF_GET_FD_BY_ID -======================== +------------------------ With ``btf_id`` obtained in ``bpf_map_info`` and ``bpf_prog_info``, bpf syscall command BPF_BTF_GET_FD_BY_ID can retrieve a btf fd. Then, with @@ -668,10 +668,10 @@ tool has full btf knowledge and is able to pretty print map key/values, dump func signatures and line info, along with byte/jit codes. 4. ELF File Format Interface -**************************** +============================ 4.1 .BTF section -================ +---------------- The .BTF section contains type and string data. The format of this section is same as the one describe in :ref:`BTF_Type_String`. @@ -679,7 +679,7 @@ same as the one describe in :ref:`BTF_Type_String`. .. _BTF_Ext_Section: 4.2 .BTF.ext section -==================== +-------------------- The .BTF.ext section encodes func_info and line_info which needs loader manipulation before loading into the kernel. @@ -743,7 +743,7 @@ bpf_insn``. For ELF API, the ``insn_off`` is the byte offset from the beginning of section (``btf_ext_info_sec->sec_name_off``). 4.2 .BTF_ids section -==================== +-------------------- The .BTF_ids section encodes BTF ID values that are used within the kernel. @@ -804,10 +804,10 @@ All the BTF ID lists and sets are compiled in the .BTF_ids section and resolved during the linking phase of kernel build by ``resolve_btfids`` tool. 5. Using BTF -************ +============ 5.1 bpftool map pretty print -============================ +---------------------------- With BTF, the map key/value can be printed based on fields rather than simply raw bytes. This is especially valuable for large structure or if your data @@ -849,7 +849,7 @@ bpftool is able to pretty print like below: ] 5.2 bpftool prog dump -===================== +--------------------- The following is an example showing how func_info and line_info can help prog dump with better kernel symbol names, function prototypes and line @@ -883,7 +883,7 @@ information.:: [...] 5.3 Verifier Log -================ +---------------- The following is an example of how line_info can help debugging verification failure.:: @@ -909,7 +909,7 @@ failure.:: R2 offset is outside of the packet 6. BTF Generation -***************** +================= You need latest pahole @@ -1016,6 +1016,6 @@ format.:: .long 8206 # Line 8 Col 14 7. Testing -********** +========== Kernel bpf selftest `test_btf.c` provides extensive set of BTF-related tests. diff --git a/Documentation/bpf/faq.rst b/Documentation/bpf/faq.rst new file mode 100644 index 000000000000..a622602ce9ad --- /dev/null +++ b/Documentation/bpf/faq.rst @@ -0,0 +1,11 @@ +================================ +Frequently asked questions (FAQ) +================================ + +Two sets of Questions and Answers (Q&A) are maintained. + +.. toctree:: + :maxdepth: 1 + + bpf_design_QA + bpf_devel_QA diff --git a/Documentation/bpf/helpers.rst b/Documentation/bpf/helpers.rst new file mode 100644 index 000000000000..c4ee0cc20dec --- /dev/null +++ b/Documentation/bpf/helpers.rst @@ -0,0 +1,7 @@ +Helper functions +================ + +* `bpf-helpers(7)`_ maintains a list of helpers available to eBPF programs. + +.. Links +.. _bpf-helpers(7): https://man7.org/linux/man-pages/man7/bpf-helpers.7.html
\ No newline at end of file diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index 610450f59e05..91ba5a62026b 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -5,104 +5,32 @@ BPF Documentation This directory contains documentation for the BPF (Berkeley Packet Filter) facility, with a focus on the extended BPF version (eBPF). -This kernel side documentation is still work in progress. The main -textual documentation is (for historical reasons) described in -:ref:`networking-filter`, which describe both classical and extended -BPF instruction-set. +This kernel side documentation is still work in progress. The Cilium project also maintains a `BPF and XDP Reference Guide`_ that goes into great technical depth about the BPF Architecture. -libbpf -====== - -Documentation/bpf/libbpf/index.rst is a userspace library for loading and interacting with bpf programs. - -BPF Type Format (BTF) -===================== - .. toctree:: :maxdepth: 1 + instruction-set + verifier + libbpf/index btf - - -Frequently asked questions (FAQ) -================================ - -Two sets of Questions and Answers (Q&A) are maintained. - -.. toctree:: - :maxdepth: 1 - - bpf_design_QA - bpf_devel_QA - -Syscall API -=========== - -The primary info for the bpf syscall is available in the `man-pages`_ -for `bpf(2)`_. For more information about the userspace API, see -Documentation/userspace-api/ebpf/index.rst. - -Helper functions -================ - -* `bpf-helpers(7)`_ maintains a list of helpers available to eBPF programs. - - -Program types -============= - -.. toctree:: - :maxdepth: 1 - - prog_cgroup_sockopt - prog_cgroup_sysctl - prog_flow_dissector - bpf_lsm - prog_sk_lookup - - -Map types -========= - -.. toctree:: - :maxdepth: 1 - - map_cgroup_storage - - -Testing and debugging BPF -========================= - -.. toctree:: - :maxdepth: 1 - - drgn - s390 - - -Licensing -========= - -.. toctree:: - :maxdepth: 1 - + faq + syscall_api + helpers + programs + maps bpf_licensing + test_debug + other +.. only:: subproject and html -Other -===== - -.. toctree:: - :maxdepth: 1 + Indices + ======= - ringbuf - llvm_reloc + * :ref:`genindex` .. Links: -.. _networking-filter: ../networking/filter.rst -.. _man-pages: https://www.kernel.org/doc/man-pages/ -.. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html -.. _bpf-helpers(7): https://man7.org/linux/man-pages/man7/bpf-helpers.7.html .. _BPF and XDP Reference Guide: https://docs.cilium.io/en/latest/bpf/ diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/instruction-set.rst new file mode 100644 index 000000000000..fa7cba59031e --- /dev/null +++ b/Documentation/bpf/instruction-set.rst @@ -0,0 +1,467 @@ + +==================== +eBPF Instruction Set +==================== + +eBPF is designed to be JITed with one to one mapping, which can also open up +the possibility for GCC/LLVM compilers to generate optimized eBPF code through +an eBPF backend that performs almost as fast as natively compiled code. + +Some core changes of the eBPF format from classic BPF: + +- Number of registers increase from 2 to 10: + + The old format had two registers A and X, and a hidden frame pointer. The + new layout extends this to be 10 internal registers and a read-only frame + pointer. Since 64-bit CPUs are passing arguments to functions via registers + the number of args from eBPF program to in-kernel function is restricted + to 5 and one register is used to accept return value from an in-kernel + function. Natively, x86_64 passes first 6 arguments in registers, aarch64/ + sparcv9/mips64 have 7 - 8 registers for arguments; x86_64 has 6 callee saved + registers, and aarch64/sparcv9/mips64 have 11 or more callee saved registers. + + Therefore, eBPF calling convention is defined as: + + * R0 - return value from in-kernel function, and exit value for eBPF program + * R1 - R5 - arguments from eBPF program to in-kernel function + * R6 - R9 - callee saved registers that in-kernel function will preserve + * R10 - read-only frame pointer to access stack + + Thus, all eBPF registers map one to one to HW registers on x86_64, aarch64, + etc, and eBPF calling convention maps directly to ABIs used by the kernel on + 64-bit architectures. + + On 32-bit architectures JIT may map programs that use only 32-bit arithmetic + and may let more complex programs to be interpreted. + + R0 - R5 are scratch registers and eBPF program needs spill/fill them if + necessary across calls. Note that there is only one eBPF program (== one + eBPF main routine) and it cannot call other eBPF functions, it can only + call predefined in-kernel functions, though. + +- Register width increases from 32-bit to 64-bit: + + Still, the semantics of the original 32-bit ALU operations are preserved + via 32-bit subregisters. All eBPF registers are 64-bit with 32-bit lower + subregisters that zero-extend into 64-bit if they are being written to. + That behavior maps directly to x86_64 and arm64 subregister definition, but + makes other JITs more difficult. + + 32-bit architectures run 64-bit eBPF programs via interpreter. + Their JITs may convert BPF programs that only use 32-bit subregisters into + native instruction set and let the rest being interpreted. + + Operation is 64-bit, because on 64-bit architectures, pointers are also + 64-bit wide, and we want to pass 64-bit values in/out of kernel functions, + so 32-bit eBPF registers would otherwise require to define register-pair + ABI, thus, there won't be able to use a direct eBPF register to HW register + mapping and JIT would need to do combine/split/move operations for every + register in and out of the function, which is complex, bug prone and slow. + Another reason is the use of atomic 64-bit counters. + +- Conditional jt/jf targets replaced with jt/fall-through: + + While the original design has constructs such as ``if (cond) jump_true; + else jump_false;``, they are being replaced into alternative constructs like + ``if (cond) jump_true; /* else fall-through */``. + +- Introduces bpf_call insn and register passing convention for zero overhead + calls from/to other kernel functions: + + Before an in-kernel function call, the eBPF program needs to + place function arguments into R1 to R5 registers to satisfy calling + convention, then the interpreter will take them from registers and pass + to in-kernel function. If R1 - R5 registers are mapped to CPU registers + that are used for argument passing on given architecture, the JIT compiler + doesn't need to emit extra moves. Function arguments will be in the correct + registers and BPF_CALL instruction will be JITed as single 'call' HW + instruction. This calling convention was picked to cover common call + situations without performance penalty. + + After an in-kernel function call, R1 - R5 are reset to unreadable and R0 has + a return value of the function. Since R6 - R9 are callee saved, their state + is preserved across the call. + + For example, consider three C functions:: + + u64 f1() { return (*_f2)(1); } + u64 f2(u64 a) { return f3(a + 1, a); } + u64 f3(u64 a, u64 b) { return a - b; } + + GCC can compile f1, f3 into x86_64:: + + f1: + movl $1, %edi + movq _f2(%rip), %rax + jmp *%rax + f3: + movq %rdi, %rax + subq %rsi, %rax + ret + + Function f2 in eBPF may look like:: + + f2: + bpf_mov R2, R1 + bpf_add R1, 1 + bpf_call f3 + bpf_exit + + If f2 is JITed and the pointer stored to ``_f2``. The calls f1 -> f2 -> f3 and + returns will be seamless. Without JIT, __bpf_prog_run() interpreter needs to + be used to call into f2. + + For practical reasons all eBPF programs have only one argument 'ctx' which is + already placed into R1 (e.g. on __bpf_prog_run() startup) and the programs + can call kernel functions with up to 5 arguments. Calls with 6 or more arguments + are currently not supported, but these restrictions can be lifted if necessary + in the future. + + On 64-bit architectures all register map to HW registers one to one. For + example, x86_64 JIT compiler can map them as ... + + :: + + R0 - rax + R1 - rdi + R2 - rsi + R3 - rdx + R4 - rcx + R5 - r8 + R6 - rbx + R7 - r13 + R8 - r14 + R9 - r15 + R10 - rbp + + ... since x86_64 ABI mandates rdi, rsi, rdx, rcx, r8, r9 for argument passing + and rbx, r12 - r15 are callee saved. + + Then the following eBPF pseudo-program:: + + bpf_mov R6, R1 /* save ctx */ + bpf_mov R2, 2 + bpf_mov R3, 3 + bpf_mov R4, 4 + bpf_mov R5, 5 + bpf_call foo + bpf_mov R7, R0 /* save foo() return value */ + bpf_mov R1, R6 /* restore ctx for next call */ + bpf_mov R2, 6 + bpf_mov R3, 7 + bpf_mov R4, 8 + bpf_mov R5, 9 + bpf_call bar + bpf_add R0, R7 + bpf_exit + + After JIT to x86_64 may look like:: + + push %rbp + mov %rsp,%rbp + sub $0x228,%rsp + mov %rbx,-0x228(%rbp) + mov %r13,-0x220(%rbp) + mov %rdi,%rbx + mov $0x2,%esi + mov $0x3,%edx + mov $0x4,%ecx + mov $0x5,%r8d + callq foo + mov %rax,%r13 + mov %rbx,%rdi + mov $0x6,%esi + mov $0x7,%edx + mov $0x8,%ecx + mov $0x9,%r8d + callq bar + add %r13,%rax + mov -0x228(%rbp),%rbx + mov -0x220(%rbp),%r13 + leaveq + retq + + Which is in this example equivalent in C to:: + + u64 bpf_filter(u64 ctx) + { + return foo(ctx, 2, 3, 4, 5) + bar(ctx, 6, 7, 8, 9); + } + + In-kernel functions foo() and bar() with prototype: u64 (*)(u64 arg1, u64 + arg2, u64 arg3, u64 arg4, u64 arg5); will receive arguments in proper + registers and place their return value into ``%rax`` which is R0 in eBPF. + Prologue and epilogue are emitted by JIT and are implicit in the + interpreter. R0-R5 are scratch registers, so eBPF program needs to preserve + them across the calls as defined by calling convention. + + For example the following program is invalid:: + + bpf_mov R1, 1 + bpf_call foo + bpf_mov R0, R1 + bpf_exit + + After the call the registers R1-R5 contain junk values and cannot be read. + An in-kernel `eBPF verifier`_ is used to validate eBPF programs. + +Also in the new design, eBPF is limited to 4096 insns, which means that any +program will terminate quickly and will only call a fixed number of kernel +functions. Original BPF and eBPF are two operand instructions, +which helps to do one-to-one mapping between eBPF insn and x86 insn during JIT. + +The input context pointer for invoking the interpreter function is generic, +its content is defined by a specific use case. For seccomp register R1 points +to seccomp_data, for converted BPF filters R1 points to a skb. + +A program, that is translated internally consists of the following elements:: + + op:16, jt:8, jf:8, k:32 ==> op:8, dst_reg:4, src_reg:4, off:16, imm:32 + +So far 87 eBPF instructions were implemented. 8-bit 'op' opcode field +has room for new instructions. Some of them may use 16/24/32 byte encoding. New +instructions must be multiple of 8 bytes to preserve backward compatibility. + +eBPF is a general purpose RISC instruction set. Not every register and +every instruction are used during translation from original BPF to eBPF. +For example, socket filters are not using ``exclusive add`` instruction, but +tracing filters may do to maintain counters of events, for example. Register R9 +is not used by socket filters either, but more complex filters may be running +out of registers and would have to resort to spill/fill to stack. + +eBPF can be used as a generic assembler for last step performance +optimizations, socket filters and seccomp are using it as assembler. Tracing +filters may use it as assembler to generate code from kernel. In kernel usage +may not be bounded by security considerations, since generated eBPF code +may be optimizing internal code path and not being exposed to the user space. +Safety of eBPF can come from the `eBPF verifier`_. In such use cases as +described, it may be used as safe instruction set. + +Just like the original BPF, eBPF runs within a controlled environment, +is deterministic and the kernel can easily prove that. The safety of the program +can be determined in two steps: first step does depth-first-search to disallow +loops and other CFG validation; second step starts from the first insn and +descends all possible paths. It simulates execution of every insn and observes +the state change of registers and stack. + +eBPF opcode encoding +==================== + +eBPF is reusing most of the opcode encoding from classic to simplify conversion +of classic BPF to eBPF. For arithmetic and jump instructions the 8-bit 'code' +field is divided into three parts:: + + +----------------+--------+--------------------+ + | 4 bits | 1 bit | 3 bits | + | operation code | source | instruction class | + +----------------+--------+--------------------+ + (MSB) (LSB) + +Three LSB bits store instruction class which is one of: + + =================== =============== + Classic BPF classes eBPF classes + =================== =============== + BPF_LD 0x00 BPF_LD 0x00 + BPF_LDX 0x01 BPF_LDX 0x01 + BPF_ST 0x02 BPF_ST 0x02 + BPF_STX 0x03 BPF_STX 0x03 + BPF_ALU 0x04 BPF_ALU 0x04 + BPF_JMP 0x05 BPF_JMP 0x05 + BPF_RET 0x06 BPF_JMP32 0x06 + BPF_MISC 0x07 BPF_ALU64 0x07 + =================== =============== + +When BPF_CLASS(code) == BPF_ALU or BPF_JMP, 4th bit encodes source operand ... + + :: + + BPF_K 0x00 + BPF_X 0x08 + + * in classic BPF, this means:: + + BPF_SRC(code) == BPF_X - use register X as source operand + BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand + + * in eBPF, this means:: + + BPF_SRC(code) == BPF_X - use 'src_reg' register as source operand + BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand + +... and four MSB bits store operation code. + +If BPF_CLASS(code) == BPF_ALU or BPF_ALU64 [ in eBPF ], BPF_OP(code) is one of:: + + BPF_ADD 0x00 + BPF_SUB 0x10 + BPF_MUL 0x20 + BPF_DIV 0x30 + BPF_OR 0x40 + BPF_AND 0x50 + BPF_LSH 0x60 + BPF_RSH 0x70 + BPF_NEG 0x80 + BPF_MOD 0x90 + BPF_XOR 0xa0 + BPF_MOV 0xb0 /* eBPF only: mov reg to reg */ + BPF_ARSH 0xc0 /* eBPF only: sign extending shift right */ + BPF_END 0xd0 /* eBPF only: endianness conversion */ + +If BPF_CLASS(code) == BPF_JMP or BPF_JMP32 [ in eBPF ], BPF_OP(code) is one of:: + + BPF_JA 0x00 /* BPF_JMP only */ + BPF_JEQ 0x10 + BPF_JGT 0x20 + BPF_JGE 0x30 + BPF_JSET 0x40 + BPF_JNE 0x50 /* eBPF only: jump != */ + BPF_JSGT 0x60 /* eBPF only: signed '>' */ + BPF_JSGE 0x70 /* eBPF only: signed '>=' */ + BPF_CALL 0x80 /* eBPF BPF_JMP only: function call */ + BPF_EXIT 0x90 /* eBPF BPF_JMP only: function return */ + BPF_JLT 0xa0 /* eBPF only: unsigned '<' */ + BPF_JLE 0xb0 /* eBPF only: unsigned '<=' */ + BPF_JSLT 0xc0 /* eBPF only: signed '<' */ + BPF_JSLE 0xd0 /* eBPF only: signed '<=' */ + +So BPF_ADD | BPF_X | BPF_ALU means 32-bit addition in both classic BPF +and eBPF. There are only two registers in classic BPF, so it means A += X. +In eBPF it means dst_reg = (u32) dst_reg + (u32) src_reg; similarly, +BPF_XOR | BPF_K | BPF_ALU means A ^= imm32 in classic BPF and analogous +src_reg = (u32) src_reg ^ (u32) imm32 in eBPF. + +Classic BPF is using BPF_MISC class to represent A = X and X = A moves. +eBPF is using BPF_MOV | BPF_X | BPF_ALU code instead. Since there are no +BPF_MISC operations in eBPF, the class 7 is used as BPF_ALU64 to mean +exactly the same operations as BPF_ALU, but with 64-bit wide operands +instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.: +dst_reg = dst_reg + src_reg + +Classic BPF wastes the whole BPF_RET class to represent a single ``ret`` +operation. Classic BPF_RET | BPF_K means copy imm32 into return register +and perform function exit. eBPF is modeled to match CPU, so BPF_JMP | BPF_EXIT +in eBPF means function exit only. The eBPF program needs to store return +value into register R0 before doing a BPF_EXIT. Class 6 in eBPF is used as +BPF_JMP32 to mean exactly the same operations as BPF_JMP, but with 32-bit wide +operands for the comparisons instead. + +For load and store instructions the 8-bit 'code' field is divided as:: + + +--------+--------+-------------------+ + | 3 bits | 2 bits | 3 bits | + | mode | size | instruction class | + +--------+--------+-------------------+ + (MSB) (LSB) + +Size modifier is one of ... + +:: + + BPF_W 0x00 /* word */ + BPF_H 0x08 /* half word */ + BPF_B 0x10 /* byte */ + BPF_DW 0x18 /* eBPF only, double word */ + +... which encodes size of load/store operation:: + + B - 1 byte + H - 2 byte + W - 4 byte + DW - 8 byte (eBPF only) + +Mode modifier is one of:: + + BPF_IMM 0x00 /* used for 32-bit mov in classic BPF and 64-bit in eBPF */ + BPF_ABS 0x20 + BPF_IND 0x40 + BPF_MEM 0x60 + BPF_LEN 0x80 /* classic BPF only, reserved in eBPF */ + BPF_MSH 0xa0 /* classic BPF only, reserved in eBPF */ + BPF_ATOMIC 0xc0 /* eBPF only, atomic operations */ + +eBPF has two non-generic instructions: (BPF_ABS | <size> | BPF_LD) and +(BPF_IND | <size> | BPF_LD) which are used to access packet data. + +They had to be carried over from classic to have strong performance of +socket filters running in eBPF interpreter. These instructions can only +be used when interpreter context is a pointer to ``struct sk_buff`` and +have seven implicit operands. Register R6 is an implicit input that must +contain pointer to sk_buff. Register R0 is an implicit output which contains +the data fetched from the packet. Registers R1-R5 are scratch registers +and must not be used to store the data across BPF_ABS | BPF_LD or +BPF_IND | BPF_LD instructions. + +These instructions have implicit program exit condition as well. When +eBPF program is trying to access the data beyond the packet boundary, +the interpreter will abort the execution of the program. JIT compilers +therefore must preserve this property. src_reg and imm32 fields are +explicit inputs to these instructions. + +For example:: + + BPF_IND | BPF_W | BPF_LD means: + + R0 = ntohl(*(u32 *) (((struct sk_buff *) R6)->data + src_reg + imm32)) + and R1 - R5 were scratched. + +Unlike classic BPF instruction set, eBPF has generic load/store operations:: + + BPF_MEM | <size> | BPF_STX: *(size *) (dst_reg + off) = src_reg + BPF_MEM | <size> | BPF_ST: *(size *) (dst_reg + off) = imm32 + BPF_MEM | <size> | BPF_LDX: dst_reg = *(size *) (src_reg + off) + +Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. + +It also includes atomic operations, which use the immediate field for extra +encoding:: + + .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_W | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg + .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg + +The basic atomic operations supported are:: + + BPF_ADD + BPF_AND + BPF_OR + BPF_XOR + +Each having equivalent semantics with the ``BPF_ADD`` example, that is: the +memory location addresed by ``dst_reg + off`` is atomically modified, with +``src_reg`` as the other operand. If the ``BPF_FETCH`` flag is set in the +immediate, then these operations also overwrite ``src_reg`` with the +value that was in memory before it was modified. + +The more special operations are:: + + BPF_XCHG + +This atomically exchanges ``src_reg`` with the value addressed by ``dst_reg + +off``. :: + + BPF_CMPXCHG + +This atomically compares the value addressed by ``dst_reg + off`` with +``R0``. If they match it is replaced with ``src_reg``. In either case, the +value that was there before is zero-extended and loaded back to ``R0``. + +Note that 1 and 2 byte atomic operations are not supported. + +Clang can generate atomic instructions by default when ``-mcpu=v3`` is +enabled. If a lower version for ``-mcpu`` is set, the only atomic instruction +Clang can generate is ``BPF_ADD`` *without* ``BPF_FETCH``. If you need to enable +the atomics features, while keeping a lower ``-mcpu`` version, you can use +``-Xclang -target-feature -Xclang +alu32``. + +You may encounter ``BPF_XADD`` - this is a legacy name for ``BPF_ATOMIC``, +referring to the exclusive-add operation encoded when the immediate field is +zero. + +eBPF has one 16-byte instruction: ``BPF_LD | BPF_DW | BPF_IMM`` which consists +of two consecutive ``struct bpf_insn`` 8-byte blocks and interpreted as single +instruction that loads 64-bit immediate value into a dst_reg. +Classic BPF has similar instruction: ``BPF_LD | BPF_W | BPF_IMM`` which loads +32-bit immediate value into a register. + +.. Links: +.. _eBPF verifier: verifiers.rst diff --git a/Documentation/bpf/libbpf/index.rst b/Documentation/bpf/libbpf/index.rst index 4f8adfc3ab83..4e8c656b539a 100644 --- a/Documentation/bpf/libbpf/index.rst +++ b/Documentation/bpf/libbpf/index.rst @@ -3,8 +3,6 @@ libbpf ====== -For API documentation see the `versioned API documentation site <https://libbpf.readthedocs.io/en/latest/api.html>`_. - .. toctree:: :maxdepth: 1 @@ -14,6 +12,8 @@ For API documentation see the `versioned API documentation site <https://libbpf. This is documentation for libbpf, a userspace library for loading and interacting with bpf programs. +For API documentation see the `versioned API documentation site <https://libbpf.readthedocs.io/en/latest/api.html>`_. + All general BPF questions, including kernel functionality, libbpf APIs and their application, should be sent to bpf@vger.kernel.org mailing list. You can `subscribe <http://vger.kernel.org/vger-lists.html#bpf>`_ to the diff --git a/Documentation/bpf/maps.rst b/Documentation/bpf/maps.rst new file mode 100644 index 000000000000..f41619e312ac --- /dev/null +++ b/Documentation/bpf/maps.rst @@ -0,0 +1,52 @@ + +========= +eBPF maps +========= + +'maps' is a generic storage of different types for sharing data between kernel +and userspace. + +The maps are accessed from user space via BPF syscall, which has commands: + +- create a map with given type and attributes + ``map_fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)`` + using attr->map_type, attr->key_size, attr->value_size, attr->max_entries + returns process-local file descriptor or negative error + +- lookup key in a given map + ``err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)`` + using attr->map_fd, attr->key, attr->value + returns zero and stores found elem into value or negative error + +- create or update key/value pair in a given map + ``err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)`` + using attr->map_fd, attr->key, attr->value + returns zero or negative error + +- find and delete element by key in a given map + ``err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)`` + using attr->map_fd, attr->key + +- to delete map: close(fd) + Exiting process will delete maps automatically + +userspace programs use this syscall to create/access maps that eBPF programs +are concurrently updating. + +maps can have different types: hash, array, bloom filter, radix-tree, etc. + +The map is defined by: + + - type + - max number of elements + - key size in bytes + - value size in bytes + +Map Types +========= + +.. toctree:: + :maxdepth: 1 + :glob: + + map_*
\ No newline at end of file diff --git a/Documentation/bpf/other.rst b/Documentation/bpf/other.rst new file mode 100644 index 000000000000..3d61963403b4 --- /dev/null +++ b/Documentation/bpf/other.rst @@ -0,0 +1,9 @@ +===== +Other +===== + +.. toctree:: + :maxdepth: 1 + + ringbuf + llvm_reloc
\ No newline at end of file diff --git a/Documentation/bpf/bpf_lsm.rst b/Documentation/bpf/prog_lsm.rst index 0dc3fb0d9544..0dc3fb0d9544 100644 --- a/Documentation/bpf/bpf_lsm.rst +++ b/Documentation/bpf/prog_lsm.rst diff --git a/Documentation/bpf/programs.rst b/Documentation/bpf/programs.rst new file mode 100644 index 000000000000..620eb667ac7a --- /dev/null +++ b/Documentation/bpf/programs.rst @@ -0,0 +1,9 @@ +============= +Program Types +============= + +.. toctree:: + :maxdepth: 1 + :glob: + + prog_* diff --git a/Documentation/bpf/syscall_api.rst b/Documentation/bpf/syscall_api.rst new file mode 100644 index 000000000000..f0a1dff087ad --- /dev/null +++ b/Documentation/bpf/syscall_api.rst @@ -0,0 +1,11 @@ +=========== +Syscall API +=========== + +The primary info for the bpf syscall is available in the `man-pages`_ +for `bpf(2)`_. For more information about the userspace API, see +Documentation/userspace-api/ebpf/index.rst. + +.. Links: +.. _man-pages: https://www.kernel.org/doc/man-pages/ +.. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html
\ No newline at end of file diff --git a/Documentation/bpf/test_debug.rst b/Documentation/bpf/test_debug.rst new file mode 100644 index 000000000000..ebf0caceb6a6 --- /dev/null +++ b/Documentation/bpf/test_debug.rst @@ -0,0 +1,9 @@ +========================= +Testing and debugging BPF +========================= + +.. toctree:: + :maxdepth: 1 + + drgn + s390 diff --git a/Documentation/bpf/verifier.rst b/Documentation/bpf/verifier.rst new file mode 100644 index 000000000000..fae5f6273bac --- /dev/null +++ b/Documentation/bpf/verifier.rst @@ -0,0 +1,529 @@ + +============= +eBPF verifier +============= + +The safety of the eBPF program is determined in two steps. + +First step does DAG check to disallow loops and other CFG validation. +In particular it will detect programs that have unreachable instructions. +(though classic BPF checker allows them) + +Second step starts from the first insn and descends all possible paths. +It simulates execution of every insn and observes the state change of +registers and stack. + +At the start of the program the register R1 contains a pointer to context +and has type PTR_TO_CTX. +If verifier sees an insn that does R2=R1, then R2 has now type +PTR_TO_CTX as well and can be used on the right hand side of expression. +If R1=PTR_TO_CTX and insn is R2=R1+R1, then R2=SCALAR_VALUE, +since addition of two valid pointers makes invalid pointer. +(In 'secure' mode verifier will reject any type of pointer arithmetic to make +sure that kernel addresses don't leak to unprivileged users) + +If register was never written to, it's not readable:: + + bpf_mov R0 = R2 + bpf_exit + +will be rejected, since R2 is unreadable at the start of the program. + +After kernel function call, R1-R5 are reset to unreadable and +R0 has a return type of the function. + +Since R6-R9 are callee saved, their state is preserved across the call. + +:: + + bpf_mov R6 = 1 + bpf_call foo + bpf_mov R0 = R6 + bpf_exit + +is a correct program. If there was R1 instead of R6, it would have +been rejected. + +load/store instructions are allowed only with registers of valid types, which +are PTR_TO_CTX, PTR_TO_MAP, PTR_TO_STACK. They are bounds and alignment checked. +For example:: + + bpf_mov R1 = 1 + bpf_mov R2 = 2 + bpf_xadd *(u32 *)(R1 + 3) += R2 + bpf_exit + +will be rejected, since R1 doesn't have a valid pointer type at the time of +execution of instruction bpf_xadd. + +At the start R1 type is PTR_TO_CTX (a pointer to generic ``struct bpf_context``) +A callback is used to customize verifier to restrict eBPF program access to only +certain fields within ctx structure with specified size and alignment. + +For example, the following insn:: + + bpf_ld R0 = *(u32 *)(R6 + 8) + +intends to load a word from address R6 + 8 and store it into R0 +If R6=PTR_TO_CTX, via is_valid_access() callback the verifier will know +that offset 8 of size 4 bytes can be accessed for reading, otherwise +the verifier will reject the program. +If R6=PTR_TO_STACK, then access should be aligned and be within +stack bounds, which are [-MAX_BPF_STACK, 0). In this example offset is 8, +so it will fail verification, since it's out of bounds. + +The verifier will allow eBPF program to read data from stack only after +it wrote into it. + +Classic BPF verifier does similar check with M[0-15] memory slots. +For example:: + + bpf_ld R0 = *(u32 *)(R10 - 4) + bpf_exit + +is invalid program. +Though R10 is correct read-only register and has type PTR_TO_STACK +and R10 - 4 is within stack bounds, there were no stores into that location. + +Pointer register spill/fill is tracked as well, since four (R6-R9) +callee saved registers may not be enough for some programs. + +Allowed function calls are customized with bpf_verifier_ops->get_func_proto() +The eBPF verifier will check that registers match argument constraints. +After the call register R0 will be set to return type of the function. + +Function calls is a main mechanism to extend functionality of eBPF programs. +Socket filters may let programs to call one set of functions, whereas tracing +filters may allow completely different set. + +If a function made accessible to eBPF program, it needs to be thought through +from safety point of view. The verifier will guarantee that the function is +called with valid arguments. + +seccomp vs socket filters have different security restrictions for classic BPF. +Seccomp solves this by two stage verifier: classic BPF verifier is followed +by seccomp verifier. In case of eBPF one configurable verifier is shared for +all use cases. + +See details of eBPF verifier in kernel/bpf/verifier.c + +Register value tracking +======================= + +In order to determine the safety of an eBPF program, the verifier must track +the range of possible values in each register and also in each stack slot. +This is done with ``struct bpf_reg_state``, defined in include/linux/ +bpf_verifier.h, which unifies tracking of scalar and pointer values. Each +register state has a type, which is either NOT_INIT (the register has not been +written to), SCALAR_VALUE (some value which is not usable as a pointer), or a +pointer type. The types of pointers describe their base, as follows: + + + PTR_TO_CTX + Pointer to bpf_context. + CONST_PTR_TO_MAP + Pointer to struct bpf_map. "Const" because arithmetic + on these pointers is forbidden. + PTR_TO_MAP_VALUE + Pointer to the value stored in a map element. + PTR_TO_MAP_VALUE_OR_NULL + Either a pointer to a map value, or NULL; map accesses + (see maps.rst) return this type, which becomes a + PTR_TO_MAP_VALUE when checked != NULL. Arithmetic on + these pointers is forbidden. + PTR_TO_STACK + Frame pointer. + PTR_TO_PACKET + skb->data. + PTR_TO_PACKET_END + skb->data + headlen; arithmetic forbidden. + PTR_TO_SOCKET + Pointer to struct bpf_sock_ops, implicitly refcounted. + PTR_TO_SOCKET_OR_NULL + Either a pointer to a socket, or NULL; socket lookup + returns this type, which becomes a PTR_TO_SOCKET when + checked != NULL. PTR_TO_SOCKET is reference-counted, + so programs must release the reference through the + socket release function before the end of the program. + Arithmetic on these pointers is forbidden. + +However, a pointer may be offset from this base (as a result of pointer +arithmetic), and this is tracked in two parts: the 'fixed offset' and 'variable +offset'. The former is used when an exactly-known value (e.g. an immediate +operand) is added to a pointer, while the latter is used for values which are +not exactly known. The variable offset is also used in SCALAR_VALUEs, to track +the range of possible values in the register. + +The verifier's knowledge about the variable offset consists of: + +* minimum and maximum values as unsigned +* minimum and maximum values as signed + +* knowledge of the values of individual bits, in the form of a 'tnum': a u64 + 'mask' and a u64 'value'. 1s in the mask represent bits whose value is unknown; + 1s in the value represent bits known to be 1. Bits known to be 0 have 0 in both + mask and value; no bit should ever be 1 in both. For example, if a byte is read + into a register from memory, the register's top 56 bits are known zero, while + the low 8 are unknown - which is represented as the tnum (0x0; 0xff). If we + then OR this with 0x40, we get (0x40; 0xbf), then if we add 1 we get (0x0; + 0x1ff), because of potential carries. + +Besides arithmetic, the register state can also be updated by conditional +branches. For instance, if a SCALAR_VALUE is compared > 8, in the 'true' branch +it will have a umin_value (unsigned minimum value) of 9, whereas in the 'false' +branch it will have a umax_value of 8. A signed compare (with BPF_JSGT or +BPF_JSGE) would instead update the signed minimum/maximum values. Information +from the signed and unsigned bounds can be combined; for instance if a value is +first tested < 8 and then tested s> 4, the verifier will conclude that the value +is also > 4 and s< 8, since the bounds prevent crossing the sign boundary. + +PTR_TO_PACKETs with a variable offset part have an 'id', which is common to all +pointers sharing that same variable offset. This is important for packet range +checks: after adding a variable to a packet pointer register A, if you then copy +it to another register B and then add a constant 4 to A, both registers will +share the same 'id' but the A will have a fixed offset of +4. Then if A is +bounds-checked and found to be less than a PTR_TO_PACKET_END, the register B is +now known to have a safe range of at least 4 bytes. See 'Direct packet access', +below, for more on PTR_TO_PACKET ranges. + +The 'id' field is also used on PTR_TO_MAP_VALUE_OR_NULL, common to all copies of +the pointer returned from a map lookup. This means that when one copy is +checked and found to be non-NULL, all copies can become PTR_TO_MAP_VALUEs. +As well as range-checking, the tracked information is also used for enforcing +alignment of pointer accesses. For instance, on most systems the packet pointer +is 2 bytes after a 4-byte alignment. If a program adds 14 bytes to that to jump +over the Ethernet header, then reads IHL and addes (IHL * 4), the resulting +pointer will have a variable offset known to be 4n+2 for some n, so adding the 2 +bytes (NET_IP_ALIGN) gives a 4-byte alignment and so word-sized accesses through +that pointer are safe. +The 'id' field is also used on PTR_TO_SOCKET and PTR_TO_SOCKET_OR_NULL, common +to all copies of the pointer returned from a socket lookup. This has similar +behaviour to the handling for PTR_TO_MAP_VALUE_OR_NULL->PTR_TO_MAP_VALUE, but +it also handles reference tracking for the pointer. PTR_TO_SOCKET implicitly +represents a reference to the corresponding ``struct sock``. To ensure that the +reference is not leaked, it is imperative to NULL-check the reference and in +the non-NULL case, and pass the valid reference to the socket release function. + +Direct packet access +==================== + +In cls_bpf and act_bpf programs the verifier allows direct access to the packet +data via skb->data and skb->data_end pointers. +Ex:: + + 1: r4 = *(u32 *)(r1 +80) /* load skb->data_end */ + 2: r3 = *(u32 *)(r1 +76) /* load skb->data */ + 3: r5 = r3 + 4: r5 += 14 + 5: if r5 > r4 goto pc+16 + R1=ctx R3=pkt(id=0,off=0,r=14) R4=pkt_end R5=pkt(id=0,off=14,r=14) R10=fp + 6: r0 = *(u16 *)(r3 +12) /* access 12 and 13 bytes of the packet */ + +this 2byte load from the packet is safe to do, since the program author +did check ``if (skb->data + 14 > skb->data_end) goto err`` at insn #5 which +means that in the fall-through case the register R3 (which points to skb->data) +has at least 14 directly accessible bytes. The verifier marks it +as R3=pkt(id=0,off=0,r=14). +id=0 means that no additional variables were added to the register. +off=0 means that no additional constants were added. +r=14 is the range of safe access which means that bytes [R3, R3 + 14) are ok. +Note that R5 is marked as R5=pkt(id=0,off=14,r=14). It also points +to the packet data, but constant 14 was added to the register, so +it now points to ``skb->data + 14`` and accessible range is [R5, R5 + 14 - 14) +which is zero bytes. + +More complex packet access may look like:: + + + R0=inv1 R1=ctx R3=pkt(id=0,off=0,r=14) R4=pkt_end R5=pkt(id=0,off=14,r=14) R10=fp + 6: r0 = *(u8 *)(r3 +7) /* load 7th byte from the packet */ + 7: r4 = *(u8 *)(r3 +12) + 8: r4 *= 14 + 9: r3 = *(u32 *)(r1 +76) /* load skb->data */ + 10: r3 += r4 + 11: r2 = r1 + 12: r2 <<= 48 + 13: r2 >>= 48 + 14: r3 += r2 + 15: r2 = r3 + 16: r2 += 8 + 17: r1 = *(u32 *)(r1 +80) /* load skb->data_end */ + 18: if r2 > r1 goto pc+2 + R0=inv(id=0,umax_value=255,var_off=(0x0; 0xff)) R1=pkt_end R2=pkt(id=2,off=8,r=8) R3=pkt(id=2,off=0,r=8) R4=inv(id=0,umax_value=3570,var_off=(0x0; 0xfffe)) R5=pkt(id=0,off=14,r=14) R10=fp + 19: r1 = *(u8 *)(r3 +4) + +The state of the register R3 is R3=pkt(id=2,off=0,r=8) +id=2 means that two ``r3 += rX`` instructions were seen, so r3 points to some +offset within a packet and since the program author did +``if (r3 + 8 > r1) goto err`` at insn #18, the safe range is [R3, R3 + 8). +The verifier only allows 'add'/'sub' operations on packet registers. Any other +operation will set the register state to 'SCALAR_VALUE' and it won't be +available for direct packet access. + +Operation ``r3 += rX`` may overflow and become less than original skb->data, +therefore the verifier has to prevent that. So when it sees ``r3 += rX`` +instruction and rX is more than 16-bit value, any subsequent bounds-check of r3 +against skb->data_end will not give us 'range' information, so attempts to read +through the pointer will give "invalid access to packet" error. + +Ex. after insn ``r4 = *(u8 *)(r3 +12)`` (insn #7 above) the state of r4 is +R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff)) which means that upper 56 bits +of the register are guaranteed to be zero, and nothing is known about the lower +8 bits. After insn ``r4 *= 14`` the state becomes +R4=inv(id=0,umax_value=3570,var_off=(0x0; 0xfffe)), since multiplying an 8-bit +value by constant 14 will keep upper 52 bits as zero, also the least significant +bit will be zero as 14 is even. Similarly ``r2 >>= 48`` will make +R2=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff)), since the shift is not sign +extending. This logic is implemented in adjust_reg_min_max_vals() function, +which calls adjust_ptr_min_max_vals() for adding pointer to scalar (or vice +versa) and adjust_scalar_min_max_vals() for operations on two scalars. + +The end result is that bpf program author can access packet directly +using normal C code as:: + + void *data = (void *)(long)skb->data; + void *data_end = (void *)(long)skb->data_end; + struct eth_hdr *eth = data; + struct iphdr *iph = data + sizeof(*eth); + struct udphdr *udp = data + sizeof(*eth) + sizeof(*iph); + + if (data + sizeof(*eth) + sizeof(*iph) + sizeof(*udp) > data_end) + return 0; + if (eth->h_proto != htons(ETH_P_IP)) + return 0; + if (iph->protocol != IPPROTO_UDP || iph->ihl != 5) + return 0; + if (udp->dest == 53 || udp->source == 9) + ...; + +which makes such programs easier to write comparing to LD_ABS insn +and significantly faster. + +Pruning +======= + +The verifier does not actually walk all possible paths through the program. For +each new branch to analyse, the verifier looks at all the states it's previously +been in when at this instruction. If any of them contain the current state as a +subset, the branch is 'pruned' - that is, the fact that the previous state was +accepted implies the current state would be as well. For instance, if in the +previous state, r1 held a packet-pointer, and in the current state, r1 holds a +packet-pointer with a range as long or longer and at least as strict an +alignment, then r1 is safe. Similarly, if r2 was NOT_INIT before then it can't +have been used by any path from that point, so any value in r2 (including +another NOT_INIT) is safe. The implementation is in the function regsafe(). +Pruning considers not only the registers but also the stack (and any spilled +registers it may hold). They must all be safe for the branch to be pruned. +This is implemented in states_equal(). + +Understanding eBPF verifier messages +==================================== + +The following are few examples of invalid eBPF programs and verifier error +messages as seen in the log: + +Program with unreachable instructions:: + + static struct bpf_insn prog[] = { + BPF_EXIT_INSN(), + BPF_EXIT_INSN(), + }; + +Error: + + unreachable insn 1 + +Program that reads uninitialized register:: + + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + +Error:: + + 0: (bf) r0 = r2 + R2 !read_ok + +Program that doesn't initialize R0 before exiting:: + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), + BPF_EXIT_INSN(), + +Error:: + + 0: (bf) r2 = r1 + 1: (95) exit + R0 !read_ok + +Program that accesses stack out of bounds:: + + BPF_ST_MEM(BPF_DW, BPF_REG_10, 8, 0), + BPF_EXIT_INSN(), + +Error:: + + 0: (7a) *(u64 *)(r10 +8) = 0 + invalid stack off=8 size=8 + +Program that doesn't initialize stack before passing its address into function:: + + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + +Error:: + + 0: (bf) r2 = r10 + 1: (07) r2 += -8 + 2: (b7) r1 = 0x0 + 3: (85) call 1 + invalid indirect read from stack off -8+0 size 8 + +Program that uses invalid map_fd=0 while calling to map_lookup_elem() function:: + + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + +Error:: + + 0: (7a) *(u64 *)(r10 -8) = 0 + 1: (bf) r2 = r10 + 2: (07) r2 += -8 + 3: (b7) r1 = 0x0 + 4: (85) call 1 + fd 0 is not pointing to valid bpf_map + +Program that doesn't check return value of map_lookup_elem() before accessing +map element:: + + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + +Error:: + + 0: (7a) *(u64 *)(r10 -8) = 0 + 1: (bf) r2 = r10 + 2: (07) r2 += -8 + 3: (b7) r1 = 0x0 + 4: (85) call 1 + 5: (7a) *(u64 *)(r0 +0) = 0 + R0 invalid mem access 'map_value_or_null' + +Program that correctly checks map_lookup_elem() returned value for NULL, but +accesses the memory with incorrect alignment:: + + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0), + BPF_EXIT_INSN(), + +Error:: + + 0: (7a) *(u64 *)(r10 -8) = 0 + 1: (bf) r2 = r10 + 2: (07) r2 += -8 + 3: (b7) r1 = 1 + 4: (85) call 1 + 5: (15) if r0 == 0x0 goto pc+1 + R0=map_ptr R10=fp + 6: (7a) *(u64 *)(r0 +4) = 0 + misaligned access off 4 size 8 + +Program that correctly checks map_lookup_elem() returned value for NULL and +accesses memory with correct alignment in one side of 'if' branch, but fails +to do so in the other side of 'if' branch:: + + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), + BPF_EXIT_INSN(), + BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + +Error:: + + 0: (7a) *(u64 *)(r10 -8) = 0 + 1: (bf) r2 = r10 + 2: (07) r2 += -8 + 3: (b7) r1 = 1 + 4: (85) call 1 + 5: (15) if r0 == 0x0 goto pc+2 + R0=map_ptr R10=fp + 6: (7a) *(u64 *)(r0 +0) = 0 + 7: (95) exit + + from 5 to 8: R0=imm0 R10=fp + 8: (7a) *(u64 *)(r0 +0) = 1 + R0 invalid mem access 'imm' + +Program that performs a socket lookup then sets the pointer to NULL without +checking it:: + + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + +Error:: + + 0: (b7) r2 = 0 + 1: (63) *(u32 *)(r10 -8) = r2 + 2: (bf) r2 = r10 + 3: (07) r2 += -8 + 4: (b7) r3 = 4 + 5: (b7) r4 = 0 + 6: (b7) r5 = 0 + 7: (85) call bpf_sk_lookup_tcp#65 + 8: (b7) r0 = 0 + 9: (95) exit + Unreleased reference id=1, alloc_insn=7 + +Program that performs a socket lookup but does not NULL-check the returned +value:: + + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_MOV64_IMM(BPF_REG_3, 4), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_IMM(BPF_REG_5, 0), + BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp), + BPF_EXIT_INSN(), + +Error:: + + 0: (b7) r2 = 0 + 1: (63) *(u32 *)(r10 -8) = r2 + 2: (bf) r2 = r10 + 3: (07) r2 += -8 + 4: (b7) r3 = 4 + 5: (b7) r4 = 0 + 6: (b7) r5 = 0 + 7: (85) call bpf_sk_lookup_tcp#65 + 8: (95) exit + Unreleased reference id=1, alloc_insn=7 diff --git a/Documentation/conf.py b/Documentation/conf.py index 17f7cee56987..76e5eb5cb62b 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -249,11 +249,16 @@ except ImportError: html_static_path = ['sphinx-static'] -html_context = { - 'css_files': [ - '_static/theme_overrides.css', - ], -} +html_css_files = [ + 'theme_overrides.css', +] + +if major <= 1 and minor < 8: + html_context = { + 'css_files': [ + '_static/theme_overrides.css', + ], + } # Add any extra paths that contain custom files (such as robots.txt or # .htaccess) here, relative to this directory. These files are copied diff --git a/Documentation/cpu-freq/core.rst b/Documentation/cpu-freq/core.rst index 33cb90bd1d8f..4ceef8e7217c 100644 --- a/Documentation/cpu-freq/core.rst +++ b/Documentation/cpu-freq/core.rst @@ -73,12 +73,12 @@ CPUFREQ_POSTCHANGE. The third argument is a struct cpufreq_freqs with the following values: -===== =========================== -cpu number of the affected CPU +====== ====================================== +policy a pointer to the struct cpufreq_policy old old frequency new new frequency flags flags of the cpufreq driver -===== =========================== +====== ====================================== 3. CPUFreq Table Generation with Operating Performance Point (OPP) ================================================================== diff --git a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml index 22fc8483256f..82b953181a52 100644 --- a/Documentation/devicetree/bindings/i2c/apple,i2c.yaml +++ b/Documentation/devicetree/bindings/i2c/apple,i2c.yaml @@ -20,9 +20,9 @@ allOf: properties: compatible: - enum: - - apple,t8103-i2c - - apple,i2c + items: + - const: apple,t8103-i2c + - const: apple,i2c reg: maxItems: 1 @@ -51,7 +51,7 @@ unevaluatedProperties: false examples: - | i2c@35010000 { - compatible = "apple,t8103-i2c"; + compatible = "apple,t8103-i2c", "apple,i2c"; reg = <0x35010000 0x4000>; interrupt-parent = <&aic>; interrupts = <0 627 4>; diff --git a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml index c65921e66dc1..81c87295912c 100644 --- a/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/samsung,exynos-adc.yaml @@ -136,7 +136,7 @@ examples: samsung,syscon-phandle = <&pmu_system_controller>; /* NTC thermistor is a hwmon device */ - ncp15wb473 { + thermistor { compatible = "murata,ncp15wb473"; pullup-uv = <1800000>; pullup-ohm = <47000>; diff --git a/Documentation/devicetree/bindings/input/gpio-keys.yaml b/Documentation/devicetree/bindings/input/gpio-keys.yaml index 060a309ff8e7..dbe7ecc19ccb 100644 --- a/Documentation/devicetree/bindings/input/gpio-keys.yaml +++ b/Documentation/devicetree/bindings/input/gpio-keys.yaml @@ -142,7 +142,7 @@ examples: down { label = "GPIO Key DOWN"; linux,code = <108>; - interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>; + interrupts = <1 IRQ_TYPE_EDGE_FALLING>; }; }; diff --git a/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml b/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml index 877183cf4278..1ef849dc74d7 100644 --- a/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml +++ b/Documentation/devicetree/bindings/media/nxp,imx7-mipi-csi2.yaml @@ -79,6 +79,8 @@ properties: properties: data-lanes: + description: + Note that 'fsl,imx7-mipi-csi2' only supports up to 2 data lines. items: minItems: 1 maxItems: 4 @@ -91,18 +93,6 @@ properties: required: - data-lanes - allOf: - - if: - properties: - compatible: - contains: - const: fsl,imx7-mipi-csi2 - then: - properties: - data-lanes: - items: - maxItems: 2 - port@1: $ref: /schemas/graph.yaml#/properties/port description: diff --git a/Documentation/devicetree/bindings/net/can/allwinner,sun4i-a10-can.yaml b/Documentation/devicetree/bindings/net/can/allwinner,sun4i-a10-can.yaml index a95960ee3feb..c93fe9d3ea82 100644 --- a/Documentation/devicetree/bindings/net/can/allwinner,sun4i-a10-can.yaml +++ b/Documentation/devicetree/bindings/net/can/allwinner,sun4i-a10-can.yaml @@ -17,6 +17,7 @@ properties: - const: allwinner,sun7i-a20-can - const: allwinner,sun4i-a10-can - const: allwinner,sun4i-a10-can + - const: allwinner,sun8i-r40-can reg: maxItems: 1 @@ -27,6 +28,19 @@ properties: clocks: maxItems: 1 + resets: + maxItems: 1 + +if: + properties: + compatible: + contains: + const: allwinner,sun8i-r40-can + +then: + required: + - resets + required: - compatible - reg @@ -47,5 +61,15 @@ examples: interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>; clocks = <&ccu CLK_APB1_CAN>; }; + - | + #define RST_BUS_CAN 68 + #define CLK_BUS_CAN 91 + can1: can@1c2bc00 { + compatible = "allwinner,sun8i-r40-can"; + reg = <0x01c2bc00 0x400>; + interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_CAN>; + resets = <&ccu RST_BUS_CAN>; + }; ... diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml index 2766fe45bb98..ee42328a109d 100644 --- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml @@ -91,6 +91,14 @@ properties: compensate for the board being designed with the lanes swapped. + enet-phy-lane-no-swap: + $ref: /schemas/types.yaml#/definitions/flag + description: + If set, indicates that PHY will disable swap of the + TX/RX lanes. This property allows the PHY to work correcly after + e.g. wrong bootstrap configuration caused by issues in PCB + layout design. + eee-broken-100tx: $ref: /schemas/types.yaml#/definitions/flag description: diff --git a/Documentation/devicetree/bindings/net/vertexcom-mse102x.yaml b/Documentation/devicetree/bindings/net/vertexcom-mse102x.yaml new file mode 100644 index 000000000000..8156a9aeb589 --- /dev/null +++ b/Documentation/devicetree/bindings/net/vertexcom-mse102x.yaml @@ -0,0 +1,71 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: "http://devicetree.org/schemas/net/vertexcom-mse102x.yaml#" +$schema: "http://devicetree.org/meta-schemas/core.yaml#" + +title: The Vertexcom MSE102x (SPI) Device Tree Bindings + +maintainers: + - Stefan Wahren <stefan.wahren@in-tech.com> + +description: + Vertexcom's MSE102x are a family of HomePlug GreenPHY chips. + They can be connected either via RGMII, RMII or SPI to a host CPU. + + In order to use a MSE102x chip as SPI device, it must be defined as + a child of an SPI master device in the device tree. + + More information can be found at + http://www.vertexcom.com/doc/MSE1022%20Product%20Brief.pdf + +allOf: + - $ref: ethernet-controller.yaml# + +properties: + compatible: + enum: + - vertexcom,mse1021 + - vertexcom,mse1022 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + spi-cpha: true + + spi-cpol: true + + spi-max-frequency: + minimum: 6000000 + maximum: 7142857 + +required: + - compatible + - reg + - interrupts + - spi-cpha + - spi-cpol + - spi-max-frequency + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + spi0 { + #address-cells = <1>; + #size-cells = <0>; + + ethernet@0 { + compatible = "vertexcom,mse1021"; + reg = <0>; + interrupt-parent = <&gpio>; + interrupts = <23 IRQ_TYPE_EDGE_RISING>; + spi-cpha; + spi-cpol; + spi-max-frequency = <7142857>; + }; + }; diff --git a/Documentation/devicetree/bindings/phy/xlnx,zynqmp-psgtr.yaml b/Documentation/devicetree/bindings/phy/xlnx,zynqmp-psgtr.yaml index 04d5654efb38..79906519c652 100644 --- a/Documentation/devicetree/bindings/phy/xlnx,zynqmp-psgtr.yaml +++ b/Documentation/devicetree/bindings/phy/xlnx,zynqmp-psgtr.yaml @@ -29,7 +29,7 @@ properties: - PHY_TYPE_PCIE - PHY_TYPE_SATA - PHY_TYPE_SGMII - - PHY_TYPE_USB + - PHY_TYPE_USB3 - description: The PHY instance minimum: 0 maximum: 1 # for DP, SATA or USB diff --git a/Documentation/devicetree/bindings/power/supply/bq25980.yaml b/Documentation/devicetree/bindings/power/supply/bq25980.yaml index 06eca6667f67..8367a1fd4057 100644 --- a/Documentation/devicetree/bindings/power/supply/bq25980.yaml +++ b/Documentation/devicetree/bindings/power/supply/bq25980.yaml @@ -105,7 +105,7 @@ examples: reg = <0x65>; interrupt-parent = <&gpio1>; interrupts = <16 IRQ_TYPE_EDGE_FALLING>; - ti,watchdog-timer = <0>; + ti,watchdog-timeout-ms = <0>; ti,sc-ocp-limit-microamp = <2000000>; ti,sc-ovp-limit-microvolt = <17800000>; monitored-battery = <&bat>; diff --git a/Documentation/devicetree/bindings/sound/wlf,wm8962.yaml b/Documentation/devicetree/bindings/sound/wlf,wm8962.yaml index 0e6249d7c133..5e172e9462b9 100644 --- a/Documentation/devicetree/bindings/sound/wlf,wm8962.yaml +++ b/Documentation/devicetree/bindings/sound/wlf,wm8962.yaml @@ -19,6 +19,9 @@ properties: clocks: maxItems: 1 + interrupts: + maxItems: 1 + "#sound-dai-cells": const: 0 diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.yaml b/Documentation/devicetree/bindings/spi/spi-rockchip.yaml index 7f987e79337c..52a78a2e362e 100644 --- a/Documentation/devicetree/bindings/spi/spi-rockchip.yaml +++ b/Documentation/devicetree/bindings/spi/spi-rockchip.yaml @@ -33,6 +33,7 @@ properties: - rockchip,rk3328-spi - rockchip,rk3368-spi - rockchip,rk3399-spi + - rockchip,rk3568-spi - rockchip,rv1126-spi - const: rockchip,rk3066-spi diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 5f4ca46bfb13..0d1679b4ff99 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -1274,6 +1274,8 @@ patternProperties: description: Variscite Ltd. "^vdl,.*": description: Van der Laan b.v. + "^vertexcom,.*": + description: Vertexcom Technologies, Inc. "^via,.*": description: VIA Technologies, Inc. "^videostrong,.*": diff --git a/Documentation/locking/locktypes.rst b/Documentation/locking/locktypes.rst index ddada4a53749..4fd7b70fcde1 100644 --- a/Documentation/locking/locktypes.rst +++ b/Documentation/locking/locktypes.rst @@ -439,11 +439,9 @@ preemption. The following substitution works on both kernels:: spin_lock(&p->lock); p->count += this_cpu_read(var2); -On a non-PREEMPT_RT kernel migrate_disable() maps to preempt_disable() -which makes the above code fully equivalent. On a PREEMPT_RT kernel migrate_disable() ensures that the task is pinned on the current CPU which in turn guarantees that the per-CPU access to var1 and var2 are staying on -the same CPU. +the same CPU while the task remains preemptible. The migrate_disable() substitution is not valid for the following scenario:: @@ -456,9 +454,8 @@ scenario:: p = this_cpu_ptr(&var1); p->val = func2(); -While correct on a non-PREEMPT_RT kernel, this breaks on PREEMPT_RT because -here migrate_disable() does not protect against reentrancy from a -preempting task. A correct substitution for this case is:: +This breaks because migrate_disable() does not protect against reentrancy from +a preempting task. A correct substitution for this case is:: func() { diff --git a/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst b/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst index f1d5233e5e51..0a233b17c664 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ixgbe.rst @@ -440,6 +440,22 @@ NOTE: For 82599-based network connections, if you are enabling jumbo frames in a virtual function (VF), jumbo frames must first be enabled in the physical function (PF). The VF MTU setting cannot be larger than the PF MTU. +NBASE-T Support +--------------- +The ixgbe driver supports NBASE-T on some devices. However, the advertisement +of NBASE-T speeds is suppressed by default, to accommodate broken network +switches which cannot cope with advertised NBASE-T speeds. Use the ethtool +command to enable advertising NBASE-T speeds on devices which support it:: + + ethtool -s eth? advertise 0x1800000001028 + +On Linux systems with INTERFACES(5), this can be specified as a pre-up command +in /etc/network/interfaces so that the interface is always brought up with +NBASE-T support, e.g.:: + + iface eth? inet dhcp + pre-up ethtool -s eth? advertise 0x1800000001028 || true + Generic Receive Offload, aka GRO -------------------------------- The driver supports the in-kernel software implementation of GRO. GRO has diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index 59c78e9717d2..8c082b139bbd 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -26,8 +26,10 @@ The ``ice`` driver reports the following versions * - ``fw.mgmt`` - running - 2.1.7 - - 3-digit version number of the management firmware that controls the - PHY, link, etc. + - 3-digit version number of the management firmware running on the + Embedded Management Processor of the device. It controls the PHY, + link, access to device resources, etc. Intel documentation refers to + this as the EMP firmware. * - ``fw.mgmt.api`` - running - 1.5.1 @@ -119,6 +121,24 @@ preserving settings, and thus ``DEVLINK_FLASH_OVERWRITE_IDENTIFIERS`` on its own will be rejected. If no overwrite mask is provided, the firmware will be instructed to preserve all settings and identifying fields when updating. +Reload +====== + +The ``ice`` driver supports activating new firmware after a flash update +using ``DEVLINK_CMD_RELOAD`` with the ``DEVLINK_RELOAD_ACTION_FW_ACTIVATE`` +action. + +.. code:: shell + + $ devlink dev reload pci/0000:01:00.0 reload action fw_activate + +The new firmware is activated by issuing a device specific Embedded +Management Processor reset which requests the device to reset and reload the +EMP firmware image. + +The driver does not currently support reloading the driver via +``DEVLINK_RELOAD_ACTION_DRIVER_REINIT``. + Regions ======= diff --git a/Documentation/networking/filter.rst b/Documentation/networking/filter.rst index ce2b8e8bb9ab..43cdc4d34745 100644 --- a/Documentation/networking/filter.rst +++ b/Documentation/networking/filter.rst @@ -6,6 +6,13 @@ Linux Socket Filtering aka Berkeley Packet Filter (BPF) ======================================================= +Notice +------ + +This file used to document the eBPF format and mechanisms even when not +related to socket filtering. The ../bpf/index.rst has more details +on eBPF. + Introduction ------------ @@ -617,15 +624,11 @@ format with similar underlying principles from BPF described in previous paragraphs is being used. However, the instruction set format is modelled closer to the underlying architecture to mimic native instruction sets, so that a better performance can be achieved (more details later). This new -ISA is called 'eBPF' or 'internal BPF' interchangeably. (Note: eBPF which +ISA is called eBPF. See the ../bpf/index.rst for details. (Note: eBPF which originates from [e]xtended BPF is not the same as BPF extensions! While eBPF is an ISA, BPF extensions date back to classic BPF's 'overloading' of BPF_LD | BPF_{B,H,W} | BPF_ABS instruction.) -It is designed to be JITed with one to one mapping, which can also open up -the possibility for GCC/LLVM compilers to generate optimized eBPF code through -an eBPF backend that performs almost as fast as natively compiled code. - The new instruction set was originally designed with the possible goal in mind to write programs in "restricted C" and compile into eBPF with a optional GCC/LLVM backend, so that it can just-in-time map to modern 64-bit CPUs with @@ -650,1032 +653,11 @@ Currently, the classic BPF format is being used for JITing on most sparc64, arm32, riscv64, riscv32 perform JIT compilation from eBPF instruction set. -Some core changes of the new internal format: - -- Number of registers increase from 2 to 10: - - The old format had two registers A and X, and a hidden frame pointer. The - new layout extends this to be 10 internal registers and a read-only frame - pointer. Since 64-bit CPUs are passing arguments to functions via registers - the number of args from eBPF program to in-kernel function is restricted - to 5 and one register is used to accept return value from an in-kernel - function. Natively, x86_64 passes first 6 arguments in registers, aarch64/ - sparcv9/mips64 have 7 - 8 registers for arguments; x86_64 has 6 callee saved - registers, and aarch64/sparcv9/mips64 have 11 or more callee saved registers. - - Therefore, eBPF calling convention is defined as: - - * R0 - return value from in-kernel function, and exit value for eBPF program - * R1 - R5 - arguments from eBPF program to in-kernel function - * R6 - R9 - callee saved registers that in-kernel function will preserve - * R10 - read-only frame pointer to access stack - - Thus, all eBPF registers map one to one to HW registers on x86_64, aarch64, - etc, and eBPF calling convention maps directly to ABIs used by the kernel on - 64-bit architectures. - - On 32-bit architectures JIT may map programs that use only 32-bit arithmetic - and may let more complex programs to be interpreted. - - R0 - R5 are scratch registers and eBPF program needs spill/fill them if - necessary across calls. Note that there is only one eBPF program (== one - eBPF main routine) and it cannot call other eBPF functions, it can only - call predefined in-kernel functions, though. - -- Register width increases from 32-bit to 64-bit: - - Still, the semantics of the original 32-bit ALU operations are preserved - via 32-bit subregisters. All eBPF registers are 64-bit with 32-bit lower - subregisters that zero-extend into 64-bit if they are being written to. - That behavior maps directly to x86_64 and arm64 subregister definition, but - makes other JITs more difficult. - - 32-bit architectures run 64-bit internal BPF programs via interpreter. - Their JITs may convert BPF programs that only use 32-bit subregisters into - native instruction set and let the rest being interpreted. - - Operation is 64-bit, because on 64-bit architectures, pointers are also - 64-bit wide, and we want to pass 64-bit values in/out of kernel functions, - so 32-bit eBPF registers would otherwise require to define register-pair - ABI, thus, there won't be able to use a direct eBPF register to HW register - mapping and JIT would need to do combine/split/move operations for every - register in and out of the function, which is complex, bug prone and slow. - Another reason is the use of atomic 64-bit counters. - -- Conditional jt/jf targets replaced with jt/fall-through: - - While the original design has constructs such as ``if (cond) jump_true; - else jump_false;``, they are being replaced into alternative constructs like - ``if (cond) jump_true; /* else fall-through */``. - -- Introduces bpf_call insn and register passing convention for zero overhead - calls from/to other kernel functions: - - Before an in-kernel function call, the internal BPF program needs to - place function arguments into R1 to R5 registers to satisfy calling - convention, then the interpreter will take them from registers and pass - to in-kernel function. If R1 - R5 registers are mapped to CPU registers - that are used for argument passing on given architecture, the JIT compiler - doesn't need to emit extra moves. Function arguments will be in the correct - registers and BPF_CALL instruction will be JITed as single 'call' HW - instruction. This calling convention was picked to cover common call - situations without performance penalty. - - After an in-kernel function call, R1 - R5 are reset to unreadable and R0 has - a return value of the function. Since R6 - R9 are callee saved, their state - is preserved across the call. - - For example, consider three C functions:: - - u64 f1() { return (*_f2)(1); } - u64 f2(u64 a) { return f3(a + 1, a); } - u64 f3(u64 a, u64 b) { return a - b; } - - GCC can compile f1, f3 into x86_64:: - - f1: - movl $1, %edi - movq _f2(%rip), %rax - jmp *%rax - f3: - movq %rdi, %rax - subq %rsi, %rax - ret - - Function f2 in eBPF may look like:: - - f2: - bpf_mov R2, R1 - bpf_add R1, 1 - bpf_call f3 - bpf_exit - - If f2 is JITed and the pointer stored to ``_f2``. The calls f1 -> f2 -> f3 and - returns will be seamless. Without JIT, __bpf_prog_run() interpreter needs to - be used to call into f2. - - For practical reasons all eBPF programs have only one argument 'ctx' which is - already placed into R1 (e.g. on __bpf_prog_run() startup) and the programs - can call kernel functions with up to 5 arguments. Calls with 6 or more arguments - are currently not supported, but these restrictions can be lifted if necessary - in the future. - - On 64-bit architectures all register map to HW registers one to one. For - example, x86_64 JIT compiler can map them as ... - - :: - - R0 - rax - R1 - rdi - R2 - rsi - R3 - rdx - R4 - rcx - R5 - r8 - R6 - rbx - R7 - r13 - R8 - r14 - R9 - r15 - R10 - rbp - - ... since x86_64 ABI mandates rdi, rsi, rdx, rcx, r8, r9 for argument passing - and rbx, r12 - r15 are callee saved. - - Then the following internal BPF pseudo-program:: - - bpf_mov R6, R1 /* save ctx */ - bpf_mov R2, 2 - bpf_mov R3, 3 - bpf_mov R4, 4 - bpf_mov R5, 5 - bpf_call foo - bpf_mov R7, R0 /* save foo() return value */ - bpf_mov R1, R6 /* restore ctx for next call */ - bpf_mov R2, 6 - bpf_mov R3, 7 - bpf_mov R4, 8 - bpf_mov R5, 9 - bpf_call bar - bpf_add R0, R7 - bpf_exit - - After JIT to x86_64 may look like:: - - push %rbp - mov %rsp,%rbp - sub $0x228,%rsp - mov %rbx,-0x228(%rbp) - mov %r13,-0x220(%rbp) - mov %rdi,%rbx - mov $0x2,%esi - mov $0x3,%edx - mov $0x4,%ecx - mov $0x5,%r8d - callq foo - mov %rax,%r13 - mov %rbx,%rdi - mov $0x6,%esi - mov $0x7,%edx - mov $0x8,%ecx - mov $0x9,%r8d - callq bar - add %r13,%rax - mov -0x228(%rbp),%rbx - mov -0x220(%rbp),%r13 - leaveq - retq - - Which is in this example equivalent in C to:: - - u64 bpf_filter(u64 ctx) - { - return foo(ctx, 2, 3, 4, 5) + bar(ctx, 6, 7, 8, 9); - } - - In-kernel functions foo() and bar() with prototype: u64 (*)(u64 arg1, u64 - arg2, u64 arg3, u64 arg4, u64 arg5); will receive arguments in proper - registers and place their return value into ``%rax`` which is R0 in eBPF. - Prologue and epilogue are emitted by JIT and are implicit in the - interpreter. R0-R5 are scratch registers, so eBPF program needs to preserve - them across the calls as defined by calling convention. - - For example the following program is invalid:: - - bpf_mov R1, 1 - bpf_call foo - bpf_mov R0, R1 - bpf_exit - - After the call the registers R1-R5 contain junk values and cannot be read. - An in-kernel eBPF verifier is used to validate internal BPF programs. - -Also in the new design, eBPF is limited to 4096 insns, which means that any -program will terminate quickly and will only call a fixed number of kernel -functions. Original BPF and the new format are two operand instructions, -which helps to do one-to-one mapping between eBPF insn and x86 insn during JIT. - -The input context pointer for invoking the interpreter function is generic, -its content is defined by a specific use case. For seccomp register R1 points -to seccomp_data, for converted BPF filters R1 points to a skb. - -A program, that is translated internally consists of the following elements:: - - op:16, jt:8, jf:8, k:32 ==> op:8, dst_reg:4, src_reg:4, off:16, imm:32 - -So far 87 internal BPF instructions were implemented. 8-bit 'op' opcode field -has room for new instructions. Some of them may use 16/24/32 byte encoding. New -instructions must be multiple of 8 bytes to preserve backward compatibility. - -Internal BPF is a general purpose RISC instruction set. Not every register and -every instruction are used during translation from original BPF to new format. -For example, socket filters are not using ``exclusive add`` instruction, but -tracing filters may do to maintain counters of events, for example. Register R9 -is not used by socket filters either, but more complex filters may be running -out of registers and would have to resort to spill/fill to stack. - -Internal BPF can be used as a generic assembler for last step performance -optimizations, socket filters and seccomp are using it as assembler. Tracing -filters may use it as assembler to generate code from kernel. In kernel usage -may not be bounded by security considerations, since generated internal BPF code -may be optimizing internal code path and not being exposed to the user space. -Safety of internal BPF can come from a verifier (TBD). In such use cases as -described, it may be used as safe instruction set. - -Just like the original BPF, the new format runs within a controlled environment, -is deterministic and the kernel can easily prove that. The safety of the program -can be determined in two steps: first step does depth-first-search to disallow -loops and other CFG validation; second step starts from the first insn and -descends all possible paths. It simulates execution of every insn and observes -the state change of registers and stack. - -eBPF opcode encoding --------------------- - -eBPF is reusing most of the opcode encoding from classic to simplify conversion -of classic BPF to eBPF. For arithmetic and jump instructions the 8-bit 'code' -field is divided into three parts:: - - +----------------+--------+--------------------+ - | 4 bits | 1 bit | 3 bits | - | operation code | source | instruction class | - +----------------+--------+--------------------+ - (MSB) (LSB) - -Three LSB bits store instruction class which is one of: - - =================== =============== - Classic BPF classes eBPF classes - =================== =============== - BPF_LD 0x00 BPF_LD 0x00 - BPF_LDX 0x01 BPF_LDX 0x01 - BPF_ST 0x02 BPF_ST 0x02 - BPF_STX 0x03 BPF_STX 0x03 - BPF_ALU 0x04 BPF_ALU 0x04 - BPF_JMP 0x05 BPF_JMP 0x05 - BPF_RET 0x06 BPF_JMP32 0x06 - BPF_MISC 0x07 BPF_ALU64 0x07 - =================== =============== - -When BPF_CLASS(code) == BPF_ALU or BPF_JMP, 4th bit encodes source operand ... - - :: - - BPF_K 0x00 - BPF_X 0x08 - - * in classic BPF, this means:: - - BPF_SRC(code) == BPF_X - use register X as source operand - BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand - - * in eBPF, this means:: - - BPF_SRC(code) == BPF_X - use 'src_reg' register as source operand - BPF_SRC(code) == BPF_K - use 32-bit immediate as source operand - -... and four MSB bits store operation code. - -If BPF_CLASS(code) == BPF_ALU or BPF_ALU64 [ in eBPF ], BPF_OP(code) is one of:: - - BPF_ADD 0x00 - BPF_SUB 0x10 - BPF_MUL 0x20 - BPF_DIV 0x30 - BPF_OR 0x40 - BPF_AND 0x50 - BPF_LSH 0x60 - BPF_RSH 0x70 - BPF_NEG 0x80 - BPF_MOD 0x90 - BPF_XOR 0xa0 - BPF_MOV 0xb0 /* eBPF only: mov reg to reg */ - BPF_ARSH 0xc0 /* eBPF only: sign extending shift right */ - BPF_END 0xd0 /* eBPF only: endianness conversion */ - -If BPF_CLASS(code) == BPF_JMP or BPF_JMP32 [ in eBPF ], BPF_OP(code) is one of:: - - BPF_JA 0x00 /* BPF_JMP only */ - BPF_JEQ 0x10 - BPF_JGT 0x20 - BPF_JGE 0x30 - BPF_JSET 0x40 - BPF_JNE 0x50 /* eBPF only: jump != */ - BPF_JSGT 0x60 /* eBPF only: signed '>' */ - BPF_JSGE 0x70 /* eBPF only: signed '>=' */ - BPF_CALL 0x80 /* eBPF BPF_JMP only: function call */ - BPF_EXIT 0x90 /* eBPF BPF_JMP only: function return */ - BPF_JLT 0xa0 /* eBPF only: unsigned '<' */ - BPF_JLE 0xb0 /* eBPF only: unsigned '<=' */ - BPF_JSLT 0xc0 /* eBPF only: signed '<' */ - BPF_JSLE 0xd0 /* eBPF only: signed '<=' */ - -So BPF_ADD | BPF_X | BPF_ALU means 32-bit addition in both classic BPF -and eBPF. There are only two registers in classic BPF, so it means A += X. -In eBPF it means dst_reg = (u32) dst_reg + (u32) src_reg; similarly, -BPF_XOR | BPF_K | BPF_ALU means A ^= imm32 in classic BPF and analogous -src_reg = (u32) src_reg ^ (u32) imm32 in eBPF. - -Classic BPF is using BPF_MISC class to represent A = X and X = A moves. -eBPF is using BPF_MOV | BPF_X | BPF_ALU code instead. Since there are no -BPF_MISC operations in eBPF, the class 7 is used as BPF_ALU64 to mean -exactly the same operations as BPF_ALU, but with 64-bit wide operands -instead. So BPF_ADD | BPF_X | BPF_ALU64 means 64-bit addition, i.e.: -dst_reg = dst_reg + src_reg - -Classic BPF wastes the whole BPF_RET class to represent a single ``ret`` -operation. Classic BPF_RET | BPF_K means copy imm32 into return register -and perform function exit. eBPF is modeled to match CPU, so BPF_JMP | BPF_EXIT -in eBPF means function exit only. The eBPF program needs to store return -value into register R0 before doing a BPF_EXIT. Class 6 in eBPF is used as -BPF_JMP32 to mean exactly the same operations as BPF_JMP, but with 32-bit wide -operands for the comparisons instead. - -For load and store instructions the 8-bit 'code' field is divided as:: - - +--------+--------+-------------------+ - | 3 bits | 2 bits | 3 bits | - | mode | size | instruction class | - +--------+--------+-------------------+ - (MSB) (LSB) - -Size modifier is one of ... - -:: - - BPF_W 0x00 /* word */ - BPF_H 0x08 /* half word */ - BPF_B 0x10 /* byte */ - BPF_DW 0x18 /* eBPF only, double word */ - -... which encodes size of load/store operation:: - - B - 1 byte - H - 2 byte - W - 4 byte - DW - 8 byte (eBPF only) - -Mode modifier is one of:: - - BPF_IMM 0x00 /* used for 32-bit mov in classic BPF and 64-bit in eBPF */ - BPF_ABS 0x20 - BPF_IND 0x40 - BPF_MEM 0x60 - BPF_LEN 0x80 /* classic BPF only, reserved in eBPF */ - BPF_MSH 0xa0 /* classic BPF only, reserved in eBPF */ - BPF_ATOMIC 0xc0 /* eBPF only, atomic operations */ - -eBPF has two non-generic instructions: (BPF_ABS | <size> | BPF_LD) and -(BPF_IND | <size> | BPF_LD) which are used to access packet data. - -They had to be carried over from classic to have strong performance of -socket filters running in eBPF interpreter. These instructions can only -be used when interpreter context is a pointer to ``struct sk_buff`` and -have seven implicit operands. Register R6 is an implicit input that must -contain pointer to sk_buff. Register R0 is an implicit output which contains -the data fetched from the packet. Registers R1-R5 are scratch registers -and must not be used to store the data across BPF_ABS | BPF_LD or -BPF_IND | BPF_LD instructions. - -These instructions have implicit program exit condition as well. When -eBPF program is trying to access the data beyond the packet boundary, -the interpreter will abort the execution of the program. JIT compilers -therefore must preserve this property. src_reg and imm32 fields are -explicit inputs to these instructions. - -For example:: - - BPF_IND | BPF_W | BPF_LD means: - - R0 = ntohl(*(u32 *) (((struct sk_buff *) R6)->data + src_reg + imm32)) - and R1 - R5 were scratched. - -Unlike classic BPF instruction set, eBPF has generic load/store operations:: - - BPF_MEM | <size> | BPF_STX: *(size *) (dst_reg + off) = src_reg - BPF_MEM | <size> | BPF_ST: *(size *) (dst_reg + off) = imm32 - BPF_MEM | <size> | BPF_LDX: dst_reg = *(size *) (src_reg + off) - -Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. - -It also includes atomic operations, which use the immediate field for extra -encoding:: - - .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_W | BPF_STX: lock xadd *(u32 *)(dst_reg + off16) += src_reg - .imm = BPF_ADD, .code = BPF_ATOMIC | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg - -The basic atomic operations supported are:: - - BPF_ADD - BPF_AND - BPF_OR - BPF_XOR - -Each having equivalent semantics with the ``BPF_ADD`` example, that is: the -memory location addresed by ``dst_reg + off`` is atomically modified, with -``src_reg`` as the other operand. If the ``BPF_FETCH`` flag is set in the -immediate, then these operations also overwrite ``src_reg`` with the -value that was in memory before it was modified. - -The more special operations are:: - - BPF_XCHG - -This atomically exchanges ``src_reg`` with the value addressed by ``dst_reg + -off``. :: - - BPF_CMPXCHG - -This atomically compares the value addressed by ``dst_reg + off`` with -``R0``. If they match it is replaced with ``src_reg``. In either case, the -value that was there before is zero-extended and loaded back to ``R0``. - -Note that 1 and 2 byte atomic operations are not supported. - -Clang can generate atomic instructions by default when ``-mcpu=v3`` is -enabled. If a lower version for ``-mcpu`` is set, the only atomic instruction -Clang can generate is ``BPF_ADD`` *without* ``BPF_FETCH``. If you need to enable -the atomics features, while keeping a lower ``-mcpu`` version, you can use -``-Xclang -target-feature -Xclang +alu32``. - -You may encounter ``BPF_XADD`` - this is a legacy name for ``BPF_ATOMIC``, -referring to the exclusive-add operation encoded when the immediate field is -zero. - -eBPF has one 16-byte instruction: ``BPF_LD | BPF_DW | BPF_IMM`` which consists -of two consecutive ``struct bpf_insn`` 8-byte blocks and interpreted as single -instruction that loads 64-bit immediate value into a dst_reg. -Classic BPF has similar instruction: ``BPF_LD | BPF_W | BPF_IMM`` which loads -32-bit immediate value into a register. - -eBPF verifier -------------- -The safety of the eBPF program is determined in two steps. - -First step does DAG check to disallow loops and other CFG validation. -In particular it will detect programs that have unreachable instructions. -(though classic BPF checker allows them) - -Second step starts from the first insn and descends all possible paths. -It simulates execution of every insn and observes the state change of -registers and stack. - -At the start of the program the register R1 contains a pointer to context -and has type PTR_TO_CTX. -If verifier sees an insn that does R2=R1, then R2 has now type -PTR_TO_CTX as well and can be used on the right hand side of expression. -If R1=PTR_TO_CTX and insn is R2=R1+R1, then R2=SCALAR_VALUE, -since addition of two valid pointers makes invalid pointer. -(In 'secure' mode verifier will reject any type of pointer arithmetic to make -sure that kernel addresses don't leak to unprivileged users) - -If register was never written to, it's not readable:: - - bpf_mov R0 = R2 - bpf_exit - -will be rejected, since R2 is unreadable at the start of the program. - -After kernel function call, R1-R5 are reset to unreadable and -R0 has a return type of the function. - -Since R6-R9 are callee saved, their state is preserved across the call. - -:: - - bpf_mov R6 = 1 - bpf_call foo - bpf_mov R0 = R6 - bpf_exit - -is a correct program. If there was R1 instead of R6, it would have -been rejected. - -load/store instructions are allowed only with registers of valid types, which -are PTR_TO_CTX, PTR_TO_MAP, PTR_TO_STACK. They are bounds and alignment checked. -For example:: - - bpf_mov R1 = 1 - bpf_mov R2 = 2 - bpf_xadd *(u32 *)(R1 + 3) += R2 - bpf_exit - -will be rejected, since R1 doesn't have a valid pointer type at the time of -execution of instruction bpf_xadd. - -At the start R1 type is PTR_TO_CTX (a pointer to generic ``struct bpf_context``) -A callback is used to customize verifier to restrict eBPF program access to only -certain fields within ctx structure with specified size and alignment. - -For example, the following insn:: - - bpf_ld R0 = *(u32 *)(R6 + 8) - -intends to load a word from address R6 + 8 and store it into R0 -If R6=PTR_TO_CTX, via is_valid_access() callback the verifier will know -that offset 8 of size 4 bytes can be accessed for reading, otherwise -the verifier will reject the program. -If R6=PTR_TO_STACK, then access should be aligned and be within -stack bounds, which are [-MAX_BPF_STACK, 0). In this example offset is 8, -so it will fail verification, since it's out of bounds. - -The verifier will allow eBPF program to read data from stack only after -it wrote into it. - -Classic BPF verifier does similar check with M[0-15] memory slots. -For example:: - - bpf_ld R0 = *(u32 *)(R10 - 4) - bpf_exit - -is invalid program. -Though R10 is correct read-only register and has type PTR_TO_STACK -and R10 - 4 is within stack bounds, there were no stores into that location. - -Pointer register spill/fill is tracked as well, since four (R6-R9) -callee saved registers may not be enough for some programs. - -Allowed function calls are customized with bpf_verifier_ops->get_func_proto() -The eBPF verifier will check that registers match argument constraints. -After the call register R0 will be set to return type of the function. - -Function calls is a main mechanism to extend functionality of eBPF programs. -Socket filters may let programs to call one set of functions, whereas tracing -filters may allow completely different set. - -If a function made accessible to eBPF program, it needs to be thought through -from safety point of view. The verifier will guarantee that the function is -called with valid arguments. - -seccomp vs socket filters have different security restrictions for classic BPF. -Seccomp solves this by two stage verifier: classic BPF verifier is followed -by seccomp verifier. In case of eBPF one configurable verifier is shared for -all use cases. - -See details of eBPF verifier in kernel/bpf/verifier.c - -Register value tracking ------------------------ -In order to determine the safety of an eBPF program, the verifier must track -the range of possible values in each register and also in each stack slot. -This is done with ``struct bpf_reg_state``, defined in include/linux/ -bpf_verifier.h, which unifies tracking of scalar and pointer values. Each -register state has a type, which is either NOT_INIT (the register has not been -written to), SCALAR_VALUE (some value which is not usable as a pointer), or a -pointer type. The types of pointers describe their base, as follows: - - - PTR_TO_CTX - Pointer to bpf_context. - CONST_PTR_TO_MAP - Pointer to struct bpf_map. "Const" because arithmetic - on these pointers is forbidden. - PTR_TO_MAP_VALUE - Pointer to the value stored in a map element. - PTR_TO_MAP_VALUE_OR_NULL - Either a pointer to a map value, or NULL; map accesses - (see section 'eBPF maps', below) return this type, - which becomes a PTR_TO_MAP_VALUE when checked != NULL. - Arithmetic on these pointers is forbidden. - PTR_TO_STACK - Frame pointer. - PTR_TO_PACKET - skb->data. - PTR_TO_PACKET_END - skb->data + headlen; arithmetic forbidden. - PTR_TO_SOCKET - Pointer to struct bpf_sock_ops, implicitly refcounted. - PTR_TO_SOCKET_OR_NULL - Either a pointer to a socket, or NULL; socket lookup - returns this type, which becomes a PTR_TO_SOCKET when - checked != NULL. PTR_TO_SOCKET is reference-counted, - so programs must release the reference through the - socket release function before the end of the program. - Arithmetic on these pointers is forbidden. - -However, a pointer may be offset from this base (as a result of pointer -arithmetic), and this is tracked in two parts: the 'fixed offset' and 'variable -offset'. The former is used when an exactly-known value (e.g. an immediate -operand) is added to a pointer, while the latter is used for values which are -not exactly known. The variable offset is also used in SCALAR_VALUEs, to track -the range of possible values in the register. - -The verifier's knowledge about the variable offset consists of: - -* minimum and maximum values as unsigned -* minimum and maximum values as signed - -* knowledge of the values of individual bits, in the form of a 'tnum': a u64 - 'mask' and a u64 'value'. 1s in the mask represent bits whose value is unknown; - 1s in the value represent bits known to be 1. Bits known to be 0 have 0 in both - mask and value; no bit should ever be 1 in both. For example, if a byte is read - into a register from memory, the register's top 56 bits are known zero, while - the low 8 are unknown - which is represented as the tnum (0x0; 0xff). If we - then OR this with 0x40, we get (0x40; 0xbf), then if we add 1 we get (0x0; - 0x1ff), because of potential carries. - -Besides arithmetic, the register state can also be updated by conditional -branches. For instance, if a SCALAR_VALUE is compared > 8, in the 'true' branch -it will have a umin_value (unsigned minimum value) of 9, whereas in the 'false' -branch it will have a umax_value of 8. A signed compare (with BPF_JSGT or -BPF_JSGE) would instead update the signed minimum/maximum values. Information -from the signed and unsigned bounds can be combined; for instance if a value is -first tested < 8 and then tested s> 4, the verifier will conclude that the value -is also > 4 and s< 8, since the bounds prevent crossing the sign boundary. - -PTR_TO_PACKETs with a variable offset part have an 'id', which is common to all -pointers sharing that same variable offset. This is important for packet range -checks: after adding a variable to a packet pointer register A, if you then copy -it to another register B and then add a constant 4 to A, both registers will -share the same 'id' but the A will have a fixed offset of +4. Then if A is -bounds-checked and found to be less than a PTR_TO_PACKET_END, the register B is -now known to have a safe range of at least 4 bytes. See 'Direct packet access', -below, for more on PTR_TO_PACKET ranges. - -The 'id' field is also used on PTR_TO_MAP_VALUE_OR_NULL, common to all copies of -the pointer returned from a map lookup. This means that when one copy is -checked and found to be non-NULL, all copies can become PTR_TO_MAP_VALUEs. -As well as range-checking, the tracked information is also used for enforcing -alignment of pointer accesses. For instance, on most systems the packet pointer -is 2 bytes after a 4-byte alignment. If a program adds 14 bytes to that to jump -over the Ethernet header, then reads IHL and addes (IHL * 4), the resulting -pointer will have a variable offset known to be 4n+2 for some n, so adding the 2 -bytes (NET_IP_ALIGN) gives a 4-byte alignment and so word-sized accesses through -that pointer are safe. -The 'id' field is also used on PTR_TO_SOCKET and PTR_TO_SOCKET_OR_NULL, common -to all copies of the pointer returned from a socket lookup. This has similar -behaviour to the handling for PTR_TO_MAP_VALUE_OR_NULL->PTR_TO_MAP_VALUE, but -it also handles reference tracking for the pointer. PTR_TO_SOCKET implicitly -represents a reference to the corresponding ``struct sock``. To ensure that the -reference is not leaked, it is imperative to NULL-check the reference and in -the non-NULL case, and pass the valid reference to the socket release function. - -Direct packet access --------------------- -In cls_bpf and act_bpf programs the verifier allows direct access to the packet -data via skb->data and skb->data_end pointers. -Ex:: - - 1: r4 = *(u32 *)(r1 +80) /* load skb->data_end */ - 2: r3 = *(u32 *)(r1 +76) /* load skb->data */ - 3: r5 = r3 - 4: r5 += 14 - 5: if r5 > r4 goto pc+16 - R1=ctx R3=pkt(id=0,off=0,r=14) R4=pkt_end R5=pkt(id=0,off=14,r=14) R10=fp - 6: r0 = *(u16 *)(r3 +12) /* access 12 and 13 bytes of the packet */ - -this 2byte load from the packet is safe to do, since the program author -did check ``if (skb->data + 14 > skb->data_end) goto err`` at insn #5 which -means that in the fall-through case the register R3 (which points to skb->data) -has at least 14 directly accessible bytes. The verifier marks it -as R3=pkt(id=0,off=0,r=14). -id=0 means that no additional variables were added to the register. -off=0 means that no additional constants were added. -r=14 is the range of safe access which means that bytes [R3, R3 + 14) are ok. -Note that R5 is marked as R5=pkt(id=0,off=14,r=14). It also points -to the packet data, but constant 14 was added to the register, so -it now points to ``skb->data + 14`` and accessible range is [R5, R5 + 14 - 14) -which is zero bytes. - -More complex packet access may look like:: - - - R0=inv1 R1=ctx R3=pkt(id=0,off=0,r=14) R4=pkt_end R5=pkt(id=0,off=14,r=14) R10=fp - 6: r0 = *(u8 *)(r3 +7) /* load 7th byte from the packet */ - 7: r4 = *(u8 *)(r3 +12) - 8: r4 *= 14 - 9: r3 = *(u32 *)(r1 +76) /* load skb->data */ - 10: r3 += r4 - 11: r2 = r1 - 12: r2 <<= 48 - 13: r2 >>= 48 - 14: r3 += r2 - 15: r2 = r3 - 16: r2 += 8 - 17: r1 = *(u32 *)(r1 +80) /* load skb->data_end */ - 18: if r2 > r1 goto pc+2 - R0=inv(id=0,umax_value=255,var_off=(0x0; 0xff)) R1=pkt_end R2=pkt(id=2,off=8,r=8) R3=pkt(id=2,off=0,r=8) R4=inv(id=0,umax_value=3570,var_off=(0x0; 0xfffe)) R5=pkt(id=0,off=14,r=14) R10=fp - 19: r1 = *(u8 *)(r3 +4) - -The state of the register R3 is R3=pkt(id=2,off=0,r=8) -id=2 means that two ``r3 += rX`` instructions were seen, so r3 points to some -offset within a packet and since the program author did -``if (r3 + 8 > r1) goto err`` at insn #18, the safe range is [R3, R3 + 8). -The verifier only allows 'add'/'sub' operations on packet registers. Any other -operation will set the register state to 'SCALAR_VALUE' and it won't be -available for direct packet access. - -Operation ``r3 += rX`` may overflow and become less than original skb->data, -therefore the verifier has to prevent that. So when it sees ``r3 += rX`` -instruction and rX is more than 16-bit value, any subsequent bounds-check of r3 -against skb->data_end will not give us 'range' information, so attempts to read -through the pointer will give "invalid access to packet" error. - -Ex. after insn ``r4 = *(u8 *)(r3 +12)`` (insn #7 above) the state of r4 is -R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff)) which means that upper 56 bits -of the register are guaranteed to be zero, and nothing is known about the lower -8 bits. After insn ``r4 *= 14`` the state becomes -R4=inv(id=0,umax_value=3570,var_off=(0x0; 0xfffe)), since multiplying an 8-bit -value by constant 14 will keep upper 52 bits as zero, also the least significant -bit will be zero as 14 is even. Similarly ``r2 >>= 48`` will make -R2=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff)), since the shift is not sign -extending. This logic is implemented in adjust_reg_min_max_vals() function, -which calls adjust_ptr_min_max_vals() for adding pointer to scalar (or vice -versa) and adjust_scalar_min_max_vals() for operations on two scalars. - -The end result is that bpf program author can access packet directly -using normal C code as:: - - void *data = (void *)(long)skb->data; - void *data_end = (void *)(long)skb->data_end; - struct eth_hdr *eth = data; - struct iphdr *iph = data + sizeof(*eth); - struct udphdr *udp = data + sizeof(*eth) + sizeof(*iph); - - if (data + sizeof(*eth) + sizeof(*iph) + sizeof(*udp) > data_end) - return 0; - if (eth->h_proto != htons(ETH_P_IP)) - return 0; - if (iph->protocol != IPPROTO_UDP || iph->ihl != 5) - return 0; - if (udp->dest == 53 || udp->source == 9) - ...; - -which makes such programs easier to write comparing to LD_ABS insn -and significantly faster. - -eBPF maps ---------- -'maps' is a generic storage of different types for sharing data between kernel -and userspace. - -The maps are accessed from user space via BPF syscall, which has commands: - -- create a map with given type and attributes - ``map_fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size)`` - using attr->map_type, attr->key_size, attr->value_size, attr->max_entries - returns process-local file descriptor or negative error - -- lookup key in a given map - ``err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size)`` - using attr->map_fd, attr->key, attr->value - returns zero and stores found elem into value or negative error - -- create or update key/value pair in a given map - ``err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)`` - using attr->map_fd, attr->key, attr->value - returns zero or negative error - -- find and delete element by key in a given map - ``err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size)`` - using attr->map_fd, attr->key - -- to delete map: close(fd) - Exiting process will delete maps automatically - -userspace programs use this syscall to create/access maps that eBPF programs -are concurrently updating. - -maps can have different types: hash, array, bloom filter, radix-tree, etc. - -The map is defined by: - - - type - - max number of elements - - key size in bytes - - value size in bytes - -Pruning -------- -The verifier does not actually walk all possible paths through the program. For -each new branch to analyse, the verifier looks at all the states it's previously -been in when at this instruction. If any of them contain the current state as a -subset, the branch is 'pruned' - that is, the fact that the previous state was -accepted implies the current state would be as well. For instance, if in the -previous state, r1 held a packet-pointer, and in the current state, r1 holds a -packet-pointer with a range as long or longer and at least as strict an -alignment, then r1 is safe. Similarly, if r2 was NOT_INIT before then it can't -have been used by any path from that point, so any value in r2 (including -another NOT_INIT) is safe. The implementation is in the function regsafe(). -Pruning considers not only the registers but also the stack (and any spilled -registers it may hold). They must all be safe for the branch to be pruned. -This is implemented in states_equal(). - -Understanding eBPF verifier messages ------------------------------------- - -The following are few examples of invalid eBPF programs and verifier error -messages as seen in the log: - -Program with unreachable instructions:: - - static struct bpf_insn prog[] = { - BPF_EXIT_INSN(), - BPF_EXIT_INSN(), - }; - -Error: - - unreachable insn 1 - -Program that reads uninitialized register:: - - BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), - BPF_EXIT_INSN(), - -Error:: - - 0: (bf) r0 = r2 - R2 !read_ok - -Program that doesn't initialize R0 before exiting:: - - BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), - BPF_EXIT_INSN(), - -Error:: - - 0: (bf) r2 = r1 - 1: (95) exit - R0 !read_ok - -Program that accesses stack out of bounds:: - - BPF_ST_MEM(BPF_DW, BPF_REG_10, 8, 0), - BPF_EXIT_INSN(), - -Error:: - - 0: (7a) *(u64 *)(r10 +8) = 0 - invalid stack off=8 size=8 - -Program that doesn't initialize stack before passing its address into function:: - - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_EXIT_INSN(), - -Error:: - - 0: (bf) r2 = r10 - 1: (07) r2 += -8 - 2: (b7) r1 = 0x0 - 3: (85) call 1 - invalid indirect read from stack off -8+0 size 8 - -Program that uses invalid map_fd=0 while calling to map_lookup_elem() function:: - - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_EXIT_INSN(), - -Error:: - - 0: (7a) *(u64 *)(r10 -8) = 0 - 1: (bf) r2 = r10 - 2: (07) r2 += -8 - 3: (b7) r1 = 0x0 - 4: (85) call 1 - fd 0 is not pointing to valid bpf_map - -Program that doesn't check return value of map_lookup_elem() before accessing -map element:: - - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), - BPF_EXIT_INSN(), - -Error:: - - 0: (7a) *(u64 *)(r10 -8) = 0 - 1: (bf) r2 = r10 - 2: (07) r2 += -8 - 3: (b7) r1 = 0x0 - 4: (85) call 1 - 5: (7a) *(u64 *)(r0 +0) = 0 - R0 invalid mem access 'map_value_or_null' - -Program that correctly checks map_lookup_elem() returned value for NULL, but -accesses the memory with incorrect alignment:: - - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), - BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0), - BPF_EXIT_INSN(), - -Error:: - - 0: (7a) *(u64 *)(r10 -8) = 0 - 1: (bf) r2 = r10 - 2: (07) r2 += -8 - 3: (b7) r1 = 1 - 4: (85) call 1 - 5: (15) if r0 == 0x0 goto pc+1 - R0=map_ptr R10=fp - 6: (7a) *(u64 *)(r0 +4) = 0 - misaligned access off 4 size 8 - -Program that correctly checks map_lookup_elem() returned value for NULL and -accesses memory with correct alignment in one side of 'if' branch, but fails -to do so in the other side of 'if' branch:: - - BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_LD_MAP_FD(BPF_REG_1, 0), - BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), - BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), - BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0), - BPF_EXIT_INSN(), - BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 1), - BPF_EXIT_INSN(), - -Error:: - - 0: (7a) *(u64 *)(r10 -8) = 0 - 1: (bf) r2 = r10 - 2: (07) r2 += -8 - 3: (b7) r1 = 1 - 4: (85) call 1 - 5: (15) if r0 == 0x0 goto pc+2 - R0=map_ptr R10=fp - 6: (7a) *(u64 *)(r0 +0) = 0 - 7: (95) exit - - from 5 to 8: R0=imm0 R10=fp - 8: (7a) *(u64 *)(r0 +0) = 1 - R0 invalid mem access 'imm' - -Program that performs a socket lookup then sets the pointer to NULL without -checking it:: - - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_MOV64_IMM(BPF_REG_3, 4), - BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_MOV64_IMM(BPF_REG_5, 0), - BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp), - BPF_MOV64_IMM(BPF_REG_0, 0), - BPF_EXIT_INSN(), - -Error:: - - 0: (b7) r2 = 0 - 1: (63) *(u32 *)(r10 -8) = r2 - 2: (bf) r2 = r10 - 3: (07) r2 += -8 - 4: (b7) r3 = 4 - 5: (b7) r4 = 0 - 6: (b7) r5 = 0 - 7: (85) call bpf_sk_lookup_tcp#65 - 8: (b7) r0 = 0 - 9: (95) exit - Unreleased reference id=1, alloc_insn=7 - -Program that performs a socket lookup but does not NULL-check the returned -value:: - - BPF_MOV64_IMM(BPF_REG_2, 0), - BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), - BPF_MOV64_IMM(BPF_REG_3, 4), - BPF_MOV64_IMM(BPF_REG_4, 0), - BPF_MOV64_IMM(BPF_REG_5, 0), - BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp), - BPF_EXIT_INSN(), - -Error:: - - 0: (b7) r2 = 0 - 1: (63) *(u32 *)(r10 -8) = r2 - 2: (bf) r2 = r10 - 3: (07) r2 += -8 - 4: (b7) r3 = 4 - 5: (b7) r4 = 0 - 6: (b7) r5 = 0 - 7: (85) call bpf_sk_lookup_tcp#65 - 8: (95) exit - Unreleased reference id=1, alloc_insn=7 - Testing ------- Next to the BPF toolchain, the kernel also ships a test module that contains -various test cases for classic and internal BPF that can be executed against +various test cases for classic and eBPF that can be executed against the BPF interpreter and JIT compiler. It can be found in lib/test_bpf.c and enabled via Kconfig:: diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index b398b8576417..cf908d79666e 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -35,6 +35,7 @@ GNU make 3.81 make --version binutils 2.23 ld -v flex 2.5.35 flex --version bison 2.0 bison --version +pahole 1.16 pahole --version util-linux 2.10o fdformat --version kmod 13 depmod -V e2fsprogs 1.41.4 e2fsck -V @@ -108,6 +109,16 @@ Bison Since Linux 4.16, the build system generates parsers during build. This requires bison 2.0 or later. +pahole: +------- + +Since Linux 5.2, if CONFIG_DEBUG_INFO_BTF is selected, the build system +generates BTF (BPF Type Format) from DWARF in vmlinux, a bit later from kernel +modules as well. This requires pahole v1.16 or later. + +It is found in the 'dwarves' or 'pahole' distro packages or from +https://fedorapeople.org/~acme/dwarves/. + Perl ---- diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst index da085d63af9b..6b3aaed66fba 100644 --- a/Documentation/process/submitting-patches.rst +++ b/Documentation/process/submitting-patches.rst @@ -14,7 +14,8 @@ works, see Documentation/process/development-process.rst. Also, read Documentation/process/submit-checklist.rst for a list of items to check before submitting code. If you are submitting a driver, also read Documentation/process/submitting-drivers.rst; for device -tree binding patches, read Documentation/process/submitting-patches.rst. +tree binding patches, read +Documentation/devicetree/bindings/submitting-patches.rst. This documentation assumes that you're using ``git`` to prepare your patches. If you're unfamiliar with ``git``, you would be well-advised to learn how to diff --git a/MAINTAINERS b/MAINTAINERS index 0dc08cda3f0f..4d479b554361 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3066,7 +3066,7 @@ F: Documentation/devicetree/bindings/phy/phy-ath79-usb.txt F: drivers/phy/qualcomm/phy-ath79-usb.c ATHEROS ATH GENERIC UTILITIES -M: Kalle Valo <kvalo@codeaurora.org> +M: Kalle Valo <kvalo@kernel.org> L: linux-wireless@vger.kernel.org S: Supported F: drivers/net/wireless/ath/* @@ -3081,7 +3081,7 @@ W: https://wireless.wiki.kernel.org/en/users/Drivers/ath5k F: drivers/net/wireless/ath/ath5k/ ATHEROS ATH6KL WIRELESS DRIVER -M: Kalle Valo <kvalo@codeaurora.org> +M: Kalle Valo <kvalo@kernel.org> L: linux-wireless@vger.kernel.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath6kl @@ -3569,7 +3569,7 @@ R: Florent Revest <revest@chromium.org> R: Brendan Jackman <jackmanb@chromium.org> L: bpf@vger.kernel.org S: Maintained -F: Documentation/bpf/bpf_lsm.rst +F: Documentation/bpf/prog_lsm.rst F: include/linux/bpf_lsm.h F: kernel/bpf/bpf_lsm.c F: security/bpf/ @@ -9329,7 +9329,6 @@ S: Maintained F: drivers/iio/pressure/dps310.c INFINIBAND SUBSYSTEM -M: Doug Ledford <dledford@redhat.com> M: Jason Gunthorpe <jgg@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported @@ -10280,9 +10279,9 @@ F: lib/Kconfig.kcsan F: scripts/Makefile.kcsan KDUMP -M: Dave Young <dyoung@redhat.com> M: Baoquan He <bhe@redhat.com> R: Vivek Goyal <vgoyal@redhat.com> +R: Dave Young <dyoung@redhat.com> L: kexec@lists.infradead.org S: Maintained W: http://lse.sourceforge.net/kdump/ @@ -12180,8 +12179,8 @@ F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* F: include/linux/mlx5/mlx5_ifc_fpga.h MELLANOX ETHERNET SWITCH DRIVERS -M: Jiri Pirko <jiri@nvidia.com> M: Ido Schimmel <idosch@nvidia.com> +M: Petr Machata <petrm@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -13256,7 +13255,7 @@ F: include/uapi/linux/if_* F: include/uapi/linux/netdevice.h NETWORKING DRIVERS (WIRELESS) -M: Kalle Valo <kvalo@codeaurora.org> +M: Kalle Valo <kvalo@kernel.org> L: linux-wireless@vger.kernel.org S: Maintained Q: http://patchwork.kernel.org/project/linux-wireless/list/ @@ -15712,7 +15711,7 @@ T: git git://linuxtv.org/anttip/media_tree.git F: drivers/media/tuners/qt1010* QUALCOMM ATHEROS ATH10K WIRELESS DRIVER -M: Kalle Valo <kvalo@codeaurora.org> +M: Kalle Valo <kvalo@kernel.org> L: ath10k@lists.infradead.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/ath10k @@ -15720,7 +15719,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git F: drivers/net/wireless/ath/ath10k/ QUALCOMM ATHEROS ATH11K WIRELESS DRIVER -M: Kalle Valo <kvalo@codeaurora.org> +M: Kalle Valo <kvalo@kernel.org> L: ath11k@lists.infradead.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git @@ -15786,6 +15785,15 @@ S: Maintained F: Documentation/devicetree/bindings/net/qcom,ethqos.txt F: drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +QUALCOMM FASTRPC DRIVER +M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> +M: Amol Maheshwari <amahesh@qti.qualcomm.com> +L: linux-arm-msm@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/misc/qcom,fastrpc.txt +F: drivers/misc/fastrpc.c +F: include/uapi/misc/fastrpc.h + QUALCOMM GENERIC INTERFACE I2C DRIVER M: Akash Asthana <akashast@codeaurora.org> M: Mukesh Savaliya <msavaliy@codeaurora.org> @@ -15892,7 +15900,7 @@ F: Documentation/devicetree/bindings/media/*venus* F: drivers/media/platform/qcom/venus/ QUALCOMM WCN36XX WIRELESS DRIVER -M: Kalle Valo <kvalo@codeaurora.org> +M: Kalle Valo <kvalo@kernel.org> L: wcn36xx@lists.infradead.org S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/wcn36xx @@ -16517,6 +16525,12 @@ T: git git://linuxtv.org/media_tree.git F: Documentation/devicetree/bindings/media/allwinner,sun8i-a83t-de2-rotate.yaml F: drivers/media/platform/sunxi/sun8i-rotate/ +RPMSG TTY DRIVER +M: Arnaud Pouliquen <arnaud.pouliquen@foss.st.com> +L: linux-remoteproc@vger.kernel.org +S: Maintained +F: drivers/tty/rpmsg_tty.c + RTL2830 MEDIA DRIVER M: Antti Palosaari <crope@iki.fi> L: linux-media@vger.kernel.org @@ -16638,7 +16652,6 @@ W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/iommu/s390-iommu.c S390 IUCV NETWORK LAYER -M: Julian Wiedmann <jwi@linux.ibm.com> M: Alexandra Winter <wintera@linux.ibm.com> M: Wenjia Zhang <wenjia@linux.ibm.com> L: linux-s390@vger.kernel.org @@ -16650,7 +16663,6 @@ F: include/net/iucv/ F: net/iucv/ S390 NETWORK DRIVERS -M: Julian Wiedmann <jwi@linux.ibm.com> M: Alexandra Winter <wintera@linux.ibm.com> M: Wenjia Zhang <wenjia@linux.ibm.com> L: linux-s390@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc5 NAME = Gobble Gobble # *DOCUMENTATION* @@ -789,7 +789,7 @@ stackp-flags-$(CONFIG_STACKPROTECTOR_STRONG) := -fstack-protector-strong KBUILD_CFLAGS += $(stackp-flags-y) KBUILD_CFLAGS-$(CONFIG_WERROR) += -Werror -KBUILD_CFLAGS += $(KBUILD_CFLAGS-y) $(CONFIG_CC_IMPLICIT_FALLTHROUGH) +KBUILD_CFLAGS += $(KBUILD_CFLAGS-y) $(CONFIG_CC_IMPLICIT_FALLTHROUGH:"%"=%) ifdef CONFIG_CC_IS_CLANG KBUILD_CPPFLAGS += -Qunused-arguments @@ -1374,17 +1374,17 @@ endif ifneq ($(dtstree),) -%.dtb: dt_binding_check include/config/kernel.release scripts_dtc - $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ $(dtstree)/$*.dt.yaml +%.dtb: include/config/kernel.release scripts_dtc + $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ -%.dtbo: dt_binding_check include/config/kernel.release scripts_dtc - $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ $(dtstree)/$*.dt.yaml +%.dtbo: include/config/kernel.release scripts_dtc + $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ PHONY += dtbs dtbs_install dtbs_check dtbs: include/config/kernel.release scripts_dtc $(Q)$(MAKE) $(build)=$(dtstree) -ifneq ($(filter dtbs_check %.dtb %.dtbo, $(MAKECMDGOALS)),) +ifneq ($(filter dtbs_check, $(MAKECMDGOALS)),) export CHECK_DTBS=y dtbs: dt_binding_check endif diff --git a/arch/arm/boot/dts/imx6qp-prtwd3.dts b/arch/arm/boot/dts/imx6qp-prtwd3.dts index 7648e8a02000..cf6571cc4682 100644 --- a/arch/arm/boot/dts/imx6qp-prtwd3.dts +++ b/arch/arm/boot/dts/imx6qp-prtwd3.dts @@ -178,6 +178,8 @@ label = "cpu"; ethernet = <&fec>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <2000>; + tx-internal-delay-ps = <2000>; fixed-link { speed = <100>; diff --git a/arch/arm/boot/dts/imx6ull-pinfunc.h b/arch/arm/boot/dts/imx6ull-pinfunc.h index eb025a9d4759..7328d4ef8559 100644 --- a/arch/arm/boot/dts/imx6ull-pinfunc.h +++ b/arch/arm/boot/dts/imx6ull-pinfunc.h @@ -82,6 +82,6 @@ #define MX6ULL_PAD_CSI_DATA04__ESAI_TX_FS 0x01F4 0x0480 0x0000 0x9 0x0 #define MX6ULL_PAD_CSI_DATA05__ESAI_TX_CLK 0x01F8 0x0484 0x0000 0x9 0x0 #define MX6ULL_PAD_CSI_DATA06__ESAI_TX5_RX0 0x01FC 0x0488 0x0000 0x9 0x0 -#define MX6ULL_PAD_CSI_DATA07__ESAI_T0 0x0200 0x048C 0x0000 0x9 0x0 +#define MX6ULL_PAD_CSI_DATA07__ESAI_TX0 0x0200 0x048C 0x0000 0x9 0x0 #endif /* __DTS_IMX6ULL_PINFUNC_H */ diff --git a/arch/arm/boot/dts/ls1021a-tsn.dts b/arch/arm/boot/dts/ls1021a-tsn.dts index ff0ffb22768b..1ea32fff4120 100644 --- a/arch/arm/boot/dts/ls1021a-tsn.dts +++ b/arch/arm/boot/dts/ls1021a-tsn.dts @@ -91,6 +91,8 @@ /* Internal port connected to eth2 */ ethernet = <&enet2>; phy-mode = "rgmii"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; reg = <4>; fixed-link { diff --git a/arch/arm/boot/dts/qcom-sdx55.dtsi b/arch/arm/boot/dts/qcom-sdx55.dtsi index 44526ad9d210..eee2f63b9bba 100644 --- a/arch/arm/boot/dts/qcom-sdx55.dtsi +++ b/arch/arm/boot/dts/qcom-sdx55.dtsi @@ -333,12 +333,10 @@ clocks = <&rpmhcc RPMH_IPA_CLK>; clock-names = "core"; - interconnects = <&system_noc MASTER_IPA &system_noc SLAVE_SNOC_MEM_NOC_GC>, - <&mem_noc MASTER_SNOC_GC_MEM_NOC &mc_virt SLAVE_EBI_CH0>, + interconnects = <&system_noc MASTER_IPA &mc_virt SLAVE_EBI_CH0>, <&system_noc MASTER_IPA &system_noc SLAVE_OCIMEM>, <&mem_noc MASTER_AMPSS_M0 &system_noc SLAVE_IPA_CFG>; - interconnect-names = "memory-a", - "memory-b", + interconnect-names = "memory", "imem", "config"; diff --git a/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts b/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts index 2b645642b935..2a745522404d 100644 --- a/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts +++ b/arch/arm/boot/dts/socfpga_arria10_socdk_qspi.dts @@ -12,7 +12,7 @@ flash0: n25q00@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00aa"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_arria5_socdk.dts b/arch/arm/boot/dts/socfpga_arria5_socdk.dts index 90e676e7019f..1b02d46496a8 100644 --- a/arch/arm/boot/dts/socfpga_arria5_socdk.dts +++ b/arch/arm/boot/dts/socfpga_arria5_socdk.dts @@ -119,7 +119,7 @@ flash: flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q256a"; + compatible = "micron,n25q256a", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts b/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts index 6f138b2b2616..51bb436784e2 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_socdk.dts @@ -124,7 +124,7 @@ flash0: n25q00@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; /* chip select */ spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts index c155ff02eb6e..cae9ddd5ed38 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts @@ -169,7 +169,7 @@ flash: flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts b/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts index 8d5d3996f6f2..ca18b959e655 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_socrates.dts @@ -80,7 +80,7 @@ flash: flash@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q256a"; + compatible = "micron,n25q256a", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; m25p,fast-read; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts b/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts index 99a71757cdf4..3f7aa7bf0863 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_sodia.dts @@ -116,7 +116,7 @@ flash0: n25q512a@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q512a"; + compatible = "micron,n25q512a", "jedec,spi-nor"; reg = <0>; spi-max-frequency = <100000000>; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts index a060718758b6..25874e1b9c82 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts @@ -224,7 +224,7 @@ n25q128@0 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q128"; + compatible = "micron,n25q128", "jedec,spi-nor"; reg = <0>; /* chip select */ spi-max-frequency = <100000000>; m25p,fast-read; @@ -241,7 +241,7 @@ n25q00@1 { #address-cells = <1>; #size-cells = <1>; - compatible = "n25q00"; + compatible = "micron,mt25qu02g", "jedec,spi-nor"; reg = <1>; /* chip select */ spi-max-frequency = <100000000>; m25p,fast-read; diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi index 1d87fc0c24ee..c99c92f008a0 100644 --- a/arch/arm/boot/dts/sun8i-r40.dtsi +++ b/arch/arm/boot/dts/sun8i-r40.dtsi @@ -511,6 +511,16 @@ #interrupt-cells = <3>; #gpio-cells = <3>; + can_ph_pins: can-ph-pins { + pins = "PH20", "PH21"; + function = "can"; + }; + + can_pa_pins: can-pa-pins { + pins = "PA16", "PA17"; + function = "can"; + }; + clk_out_a_pin: clk-out-a-pin { pins = "PI12"; function = "clk_out_a"; @@ -926,6 +936,15 @@ #size-cells = <0>; }; + can0: can@1c2bc00 { + compatible = "allwinner,sun8i-r40-can"; + reg = <0x01c2bc00 0x400>; + interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&ccu CLK_BUS_CAN>; + resets = <&ccu RST_BUS_CAN>; + status = "disabled"; + }; + i2c4: i2c@1c2c000 { compatible = "allwinner,sun6i-a31-i2c"; reg = <0x01c2c000 0x400>; diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c index d60856898d97..5ec58d004b7d 100644 --- a/arch/arm/mach-rockchip/platsmp.c +++ b/arch/arm/mach-rockchip/platsmp.c @@ -189,7 +189,7 @@ static int __init rockchip_smp_prepare_sram(struct device_node *node) rockchip_boot_fn = __pa_symbol(secondary_startup); /* copy the trampoline to sram, that runs during startup of the core */ - memcpy(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz); + memcpy_toio(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz); flush_cache_all(); outer_clean_range(0, trampoline_sz); diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index eeb6dc0ecf46..10ceebb7530b 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -163,7 +163,7 @@ static const s8 bpf2a32[][2] = { [BPF_REG_9] = {STACK_OFFSET(BPF_R9_HI), STACK_OFFSET(BPF_R9_LO)}, /* Read only Frame Pointer to access Stack */ [BPF_REG_FP] = {STACK_OFFSET(BPF_FP_HI), STACK_OFFSET(BPF_FP_LO)}, - /* Temporary Register for internal BPF JIT, can be used + /* Temporary Register for BPF JIT, can be used * for constant blindings and others. */ [TMP_REG_1] = {ARM_R7, ARM_R6}, @@ -1199,7 +1199,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) /* tmp2[0] = array, tmp2[1] = index */ - /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + /* + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; * tail_call_cnt++; */ @@ -1208,7 +1209,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) tc = arm_bpf_get_reg64(tcc, tmp, ctx); emit(ARM_CMP_I(tc[0], hi), ctx); _emit(ARM_COND_EQ, ARM_CMP_I(tc[1], lo), ctx); - _emit(ARM_COND_HI, ARM_B(jmp_offset), ctx); + _emit(ARM_COND_CS, ARM_B(jmp_offset), ctx); emit(ARM_ADDS_I(tc[1], tc[1], 1), ctx); emit(ARM_ADC_I(tc[0], tc[0], 0), ctx); arm_bpf_put_reg64(tcc, tmp, ctx); diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 1aa8b7073218..54e3910e8b9b 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -161,7 +161,6 @@ config ARCH_MEDIATEK config ARCH_MESON bool "Amlogic Platforms" - select COMMON_CLK help This enables support for the arm64 based Amlogic SoCs such as the s905, S905X/D, S912, A113X/D or S905X/D2 diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts index 52ebe371df26..561eec21b4de 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts +++ b/arch/arm64/boot/dts/amlogic/meson-axg-jethome-jethub-j100.dts @@ -134,23 +134,23 @@ type = "critical"; }; }; - }; - cpu_cooling_maps: cooling-maps { - map0 { - trip = <&cpu_passive>; - cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; - }; + cpu_cooling_maps: cooling-maps { + map0 { + trip = <&cpu_passive>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; - map1 { - trip = <&cpu_hot>; - cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, - <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + map1 { + trip = <&cpu_hot>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; }; }; }; diff --git a/arch/arm64/boot/dts/apple/t8103-j274.dts b/arch/arm64/boot/dts/apple/t8103-j274.dts index 33a80f9501dc..02c36301e985 100644 --- a/arch/arm64/boot/dts/apple/t8103-j274.dts +++ b/arch/arm64/boot/dts/apple/t8103-j274.dts @@ -60,7 +60,7 @@ &port02 { bus-range = <3 3>; - ethernet0: pci@0,0 { + ethernet0: ethernet@0,0 { reg = <0x30000 0x0 0x0 0x0 0x0>; /* To be filled by the loader */ local-mac-address = [00 10 18 00 00 00]; diff --git a/arch/arm64/boot/dts/apple/t8103.dtsi b/arch/arm64/boot/dts/apple/t8103.dtsi index fc8b2bb06ffe..8b61e7fd3e9c 100644 --- a/arch/arm64/boot/dts/apple/t8103.dtsi +++ b/arch/arm64/boot/dts/apple/t8103.dtsi @@ -7,6 +7,7 @@ * Copyright The Asahi Linux Contributors */ +#include <dt-bindings/gpio/gpio.h> #include <dt-bindings/interrupt-controller/apple-aic.h> #include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/pinctrl/apple.h> @@ -143,6 +144,7 @@ apple,npins = <212>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&aic>; interrupts = <AIC_IRQ 190 IRQ_TYPE_LEVEL_HIGH>, <AIC_IRQ 191 IRQ_TYPE_LEVEL_HIGH>, @@ -169,6 +171,7 @@ apple,npins = <42>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&aic>; interrupts = <AIC_IRQ 268 IRQ_TYPE_LEVEL_HIGH>, <AIC_IRQ 269 IRQ_TYPE_LEVEL_HIGH>, @@ -189,6 +192,7 @@ apple,npins = <23>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&aic>; interrupts = <AIC_IRQ 330 IRQ_TYPE_LEVEL_HIGH>, <AIC_IRQ 331 IRQ_TYPE_LEVEL_HIGH>, @@ -209,6 +213,7 @@ apple,npins = <16>; interrupt-controller; + #interrupt-cells = <2>; interrupt-parent = <&aic>; interrupts = <AIC_IRQ 391 IRQ_TYPE_LEVEL_HIGH>, <AIC_IRQ 392 IRQ_TYPE_LEVEL_HIGH>, @@ -281,7 +286,7 @@ port00: pci@0,0 { device_type = "pci"; reg = <0x0 0x0 0x0 0x0 0x0>; - reset-gpios = <&pinctrl_ap 152 0>; + reset-gpios = <&pinctrl_ap 152 GPIO_ACTIVE_LOW>; max-link-speed = <2>; #address-cells = <3>; @@ -301,7 +306,7 @@ port01: pci@1,0 { device_type = "pci"; reg = <0x800 0x0 0x0 0x0 0x0>; - reset-gpios = <&pinctrl_ap 153 0>; + reset-gpios = <&pinctrl_ap 153 GPIO_ACTIVE_LOW>; max-link-speed = <2>; #address-cells = <3>; @@ -321,7 +326,7 @@ port02: pci@2,0 { device_type = "pci"; reg = <0x1000 0x0 0x0 0x0 0x0>; - reset-gpios = <&pinctrl_ap 33 0>; + reset-gpios = <&pinctrl_ap 33 GPIO_ACTIVE_LOW>; max-link-speed = <1>; #address-cells = <3>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts index 3063851c2fb9..d3f03dcbb8c3 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts @@ -38,7 +38,6 @@ powerdn { label = "External Power Down"; gpios = <&gpio1 17 GPIO_ACTIVE_LOW>; - interrupts = <&gpio1 17 IRQ_TYPE_EDGE_FALLING>; linux,code = <KEY_POWER>; }; @@ -46,7 +45,6 @@ admin { label = "ADMIN button"; gpios = <&gpio3 8 GPIO_ACTIVE_HIGH>; - interrupts = <&gpio3 8 IRQ_TYPE_EDGE_RISING>; linux,code = <KEY_WPS_BUTTON>; }; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts b/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts index b21be03da0af..042c486bdda2 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-bluebox3.dts @@ -386,6 +386,8 @@ reg = <2>; ethernet = <&dpmac17>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <2000>; + tx-internal-delay-ps = <2000>; fixed-link { speed = <1000>; @@ -529,6 +531,8 @@ reg = <2>; ethernet = <&dpmac18>; phy-mode = "rgmii-id"; + rx-internal-delay-ps = <2000>; + tx-internal-delay-ps = <2000>; fixed-link { speed = <1000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 972766b67a15..71bf497f99c2 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -524,8 +524,6 @@ <&clk IMX8MQ_VIDEO_PLL1>, <&clk IMX8MQ_VIDEO_PLL1_OUT>; assigned-clock-rates = <0>, <0>, <0>, <594000000>; - interconnects = <&noc IMX8MQ_ICM_LCDIF &noc IMX8MQ_ICS_DRAM>; - interconnect-names = "dram"; status = "disabled"; port@0 { diff --git a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts index 665b2e69455d..ea6820902ede 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts @@ -97,7 +97,7 @@ regulator-max-microvolt = <3300000>; regulator-always-on; regulator-boot-on; - vim-supply = <&vcc_io>; + vin-supply = <&vcc_io>; }; vdd_core: vdd-core { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi index d5c7648c841d..f1fcc6b5b402 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-khadas-edge.dtsi @@ -705,7 +705,6 @@ &sdhci { bus-width = <8>; mmc-hs400-1_8v; - mmc-hs400-enhanced-strobe; non-removable; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts index 63c7681843da..b6ac00f64613 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-kobol-helios64.dts @@ -276,6 +276,7 @@ clock-output-names = "xin32k", "rk808-clkout2"; pinctrl-names = "default"; pinctrl-0 = <&pmic_int_l>; + rockchip,system-power-controller; vcc1-supply = <&vcc5v0_sys>; vcc2-supply = <&vcc5v0_sys>; vcc3-supply = <&vcc5v0_sys>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts b/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts index 7c93f840bc64..e890166e7fd4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-leez-p710.dts @@ -55,7 +55,7 @@ regulator-boot-on; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - vim-supply = <&vcc3v3_sys>; + vin-supply = <&vcc3v3_sys>; }; vcc3v3_sys: vcc3v3-sys { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi index 98136c88fa49..6a434be62819 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi @@ -502,7 +502,7 @@ status = "okay"; bt656-supply = <&vcc_3v0>; - audio-supply = <&vcc_3v0>; + audio-supply = <&vcc1v8_codec>; sdmmc-supply = <&vcc_sdio>; gpio1830-supply = <&vcc_3v0>; }; diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index b3e4f9a088b1..8cf970d219f5 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -77,11 +77,17 @@ .endm SYM_CODE_START(ftrace_regs_caller) +#ifdef BTI_C + BTI_C +#endif ftrace_regs_entry 1 b ftrace_common SYM_CODE_END(ftrace_regs_caller) SYM_CODE_START(ftrace_caller) +#ifdef BTI_C + BTI_C +#endif ftrace_regs_entry 0 b ftrace_common SYM_CODE_END(ftrace_caller) diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 1038494135c8..6fb31c117ebe 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -147,7 +147,7 @@ int machine_kexec_post_load(struct kimage *kimage) if (rc) return rc; kimage->arch.ttbr1 = __pa(trans_pgd); - kimage->arch.zero_page = __pa(empty_zero_page); + kimage->arch.zero_page = __pa_symbol(empty_zero_page); reloc_size = __relocate_new_kernel_end - __relocate_new_kernel_start; memcpy(reloc_code, __relocate_new_kernel_start, reloc_size); diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 63634b4d72c1..59c648d51848 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -149,6 +149,7 @@ int load_other_segments(struct kimage *image, initrd_len, cmdline, 0); if (!dtb) { pr_err("Preparing for new dtb failed\n"); + ret = -EINVAL; goto out_err; } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 86c9dc0681cc..07aad85848fa 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -44,7 +44,7 @@ static const int bpf2a64[] = { [BPF_REG_9] = A64_R(22), /* read-only frame pointer to access stack */ [BPF_REG_FP] = A64_R(25), - /* temporary registers for internal BPF JIT */ + /* temporary registers for BPF JIT */ [TMP_REG_1] = A64_R(10), [TMP_REG_2] = A64_R(11), [TMP_REG_3] = A64_R(12), @@ -287,13 +287,14 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit(A64_CMP(0, r3, tmp), ctx); emit(A64_B_(A64_COND_CS, jmp_offset), ctx); - /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + /* + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; * tail_call_cnt++; */ emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx); emit(A64_CMP(1, tcc, tmp), ctx); - emit(A64_B_(A64_COND_HI, jmp_offset), ctx); + emit(A64_B_(A64_COND_CS, jmp_offset), ctx); emit(A64_ADD_I(1, tcc, tcc, 1), ctx); /* prog = array->ptrs[index]; diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c index e5fbf8653a21..2020af88b636 100644 --- a/arch/csky/kernel/traps.c +++ b/arch/csky/kernel/traps.c @@ -209,7 +209,7 @@ asmlinkage void do_trap_illinsn(struct pt_regs *regs) asmlinkage void do_trap_fpe(struct pt_regs *regs) { -#ifdef CONFIG_CPU_HAS_FP +#ifdef CONFIG_CPU_HAS_FPU return fpu_fpe(regs); #else do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->pc, @@ -219,7 +219,7 @@ asmlinkage void do_trap_fpe(struct pt_regs *regs) asmlinkage void do_trap_priv(struct pt_regs *regs) { -#ifdef CONFIG_CPU_HAS_FP +#ifdef CONFIG_CPU_HAS_FPU if (user_mode(regs) && fpu_libc_helper(regs)) return; #endif diff --git a/arch/mips/net/bpf_jit_comp.h b/arch/mips/net/bpf_jit_comp.h index 6f3a7b07294b..a37fe20818eb 100644 --- a/arch/mips/net/bpf_jit_comp.h +++ b/arch/mips/net/bpf_jit_comp.h @@ -98,7 +98,7 @@ do { \ #define emit(...) __emit(__VA_ARGS__) /* Workaround for R10000 ll/sc errata */ -#ifdef CONFIG_WAR_R10000 +#ifdef CONFIG_WAR_R10000_LLSC #define LLSC_beqz beqzl #else #define LLSC_beqz beqz diff --git a/arch/mips/net/bpf_jit_comp32.c b/arch/mips/net/bpf_jit_comp32.c index bd996ede12f8..044b11b65bca 100644 --- a/arch/mips/net/bpf_jit_comp32.c +++ b/arch/mips/net/bpf_jit_comp32.c @@ -1381,8 +1381,7 @@ void build_prologue(struct jit_context *ctx) * 16-byte area in the parent's stack frame. On a tail call, the * calling function jumps into the prologue after these instructions. */ - emit(ctx, ori, MIPS_R_T9, MIPS_R_ZERO, - min(MAX_TAIL_CALL_CNT + 1, 0xffff)); + emit(ctx, ori, MIPS_R_T9, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT, 0xffff)); emit(ctx, sw, MIPS_R_T9, 0, MIPS_R_SP); /* diff --git a/arch/mips/net/bpf_jit_comp64.c b/arch/mips/net/bpf_jit_comp64.c index 815ade724227..6475828ffb36 100644 --- a/arch/mips/net/bpf_jit_comp64.c +++ b/arch/mips/net/bpf_jit_comp64.c @@ -552,7 +552,7 @@ void build_prologue(struct jit_context *ctx) * On a tail call, the calling function jumps into the prologue * after this instruction. */ - emit(ctx, addiu, tc, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT + 1, 0xffff)); + emit(ctx, ori, tc, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT, 0xffff)); /* === Entry-point for tail calls === */ diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 8db4af4879d0..82d77f4b0d08 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -15,7 +15,12 @@ # Mike Shaver, Helge Deller and Martin K. Petersen # +ifdef CONFIG_PARISC_SELF_EXTRACT +boot := arch/parisc/boot +KBUILD_IMAGE := $(boot)/bzImage +else KBUILD_IMAGE := vmlinuz +endif NM = sh $(srctree)/arch/parisc/nm CHECKFLAGS += -D__hppa__=1 diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index d2daeac2b217..1b8fd80cbe7f 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -1,7 +1,9 @@ CONFIG_LOCALVERSION="-64bit" # CONFIG_LOCALVERSION_AUTO is not set +CONFIG_KERNEL_LZ4=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_AUDIT=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y CONFIG_TASKSTATS=y @@ -35,6 +37,7 @@ CONFIG_MODVERSIONS=y CONFIG_BLK_DEV_INTEGRITY=y CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set +CONFIG_MEMORY_FAILURE=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -65,12 +68,15 @@ CONFIG_SCSI_ISCSI_ATTRS=y CONFIG_SCSI_SRP_ATTRS=y CONFIG_ISCSI_BOOT_SYSFS=y CONFIG_SCSI_MPT2SAS=y -CONFIG_SCSI_LASI700=m +CONFIG_SCSI_LASI700=y CONFIG_SCSI_SYM53C8XX_2=y CONFIG_SCSI_ZALON=y CONFIG_SCSI_QLA_ISCSI=m CONFIG_SCSI_DH=y CONFIG_ATA=y +CONFIG_SATA_SIL=y +CONFIG_SATA_SIS=y +CONFIG_SATA_VIA=y CONFIG_PATA_NS87415=y CONFIG_PATA_SIL680=y CONFIG_ATA_GENERIC=y @@ -79,6 +85,7 @@ CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_RAID=m CONFIG_DM_UEVENT=y +CONFIG_DM_AUDIT=y CONFIG_FUSION=y CONFIG_FUSION_SPI=y CONFIG_FUSION_SAS=y @@ -196,10 +203,15 @@ CONFIG_FB_MATROX_G=y CONFIG_FB_MATROX_I2C=y CONFIG_FB_MATROX_MAVEN=y CONFIG_FB_RADEON=y +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_CLUT224 is not set CONFIG_HIDRAW=y CONFIG_HID_PID=y CONFIG_USB_HIDDEV=y CONFIG_USB=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_UIO=y CONFIG_UIO_PDRV_GENIRQ=m CONFIG_UIO_AEC=m diff --git a/arch/parisc/install.sh b/arch/parisc/install.sh index 056d588befdd..70d3cffb0251 100644 --- a/arch/parisc/install.sh +++ b/arch/parisc/install.sh @@ -39,6 +39,7 @@ verify "$3" if [ -n "${INSTALLKERNEL}" ]; then if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi + if [ -x /usr/sbin/${INSTALLKERNEL} ]; then exec /usr/sbin/${INSTALLKERNEL} "$@"; fi fi # Default install diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 9fb1e794831b..061119a56fbe 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -249,30 +249,16 @@ void __init time_init(void) static int __init init_cr16_clocksource(void) { /* - * The cr16 interval timers are not syncronized across CPUs on - * different sockets, so mark them unstable and lower rating on - * multi-socket SMP systems. + * The cr16 interval timers are not syncronized across CPUs, even if + * they share the same socket. */ if (num_online_cpus() > 1 && !running_on_qemu) { - int cpu; - unsigned long cpu0_loc; - cpu0_loc = per_cpu(cpu_data, 0).cpu_loc; - - for_each_online_cpu(cpu) { - if (cpu == 0) - continue; - if ((cpu0_loc != 0) && - (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc)) - continue; - - /* mark sched_clock unstable */ - clear_sched_clock_stable(); - - clocksource_cr16.name = "cr16_unstable"; - clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; - clocksource_cr16.rating = 0; - break; - } + /* mark sched_clock unstable */ + clear_sched_clock_stable(); + + clocksource_cr16.name = "cr16_unstable"; + clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE; + clocksource_cr16.rating = 0; } /* register at clocksource framework */ diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 0da31d41d413..8a4faa05f9e4 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -221,13 +221,13 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o PPC_BCC(COND_GE, out); /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT(PPC_RAW_CMPLWI(_R0, MAX_TAIL_CALL_CNT)); /* tail_call_cnt++; */ EMIT(PPC_RAW_ADDIC(_R0, _R0, 1)); - PPC_BCC(COND_GT, out); + PPC_BCC(COND_GE, out); /* prog = array->ptrs[index]; */ EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29)); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 8b5157ccfeba..8571aafcc9e1 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -228,12 +228,12 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o PPC_BCC(COND_GE, out); /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; */ PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); EMIT(PPC_RAW_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT)); - PPC_BCC(COND_GT, out); + PPC_BCC(COND_GE, out); /* * tail_call_cnt++; diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index e6497424cbf6..529a83b85c1c 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -799,11 +799,10 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) emit_bcc(BPF_JGE, lo(idx_reg), RV_REG_T1, off, ctx); /* - * temp_tcc = tcc - 1; - * if (tcc < 0) + * if (--tcc < 0) * goto out; */ - emit(rv_addi(RV_REG_T1, RV_REG_TCC, -1), ctx); + emit(rv_addi(RV_REG_TCC, RV_REG_TCC, -1), ctx); off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); emit_bcc(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx); @@ -829,7 +828,6 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) if (is_12b_check(off, insn)) return -1; emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx); - emit(rv_addi(RV_REG_TCC, RV_REG_T1, 0), ctx); /* Epilogue jumps to *(t0 + 4). */ __build_epilogue(true, ctx); return 0; diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index f2a779c7e225..603630b6f3c5 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -327,12 +327,12 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); emit_branch(BPF_JGE, RV_REG_A2, RV_REG_T1, off, ctx); - /* if (TCC-- < 0) + /* if (--TCC < 0) * goto out; */ - emit_addi(RV_REG_T1, tcc, -1, ctx); + emit_addi(RV_REG_TCC, tcc, -1, ctx); off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); - emit_branch(BPF_JSLT, tcc, RV_REG_ZERO, off, ctx); + emit_branch(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx); /* prog = array->ptrs[index]; * if (!prog) @@ -352,7 +352,6 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) if (is_12b_check(off, insn)) return -1; emit_ld(RV_REG_T3, off, RV_REG_T2, ctx); - emit_mv(RV_REG_TCC, RV_REG_T1, ctx); __build_epilogue(true, ctx); return 0; } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index fd825097cf04..e45cc27716de 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -117,6 +117,7 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m +CONFIG_NET_SWITCHDEV=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -403,7 +404,6 @@ CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y @@ -476,6 +476,7 @@ CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_VXLAN=m CONFIG_BAREUDP=m +CONFIG_AMT=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -489,6 +490,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ASIX is not set # CONFIG_NET_VENDOR_ATHEROS is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_BROCADE is not set @@ -510,6 +512,7 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -571,6 +574,7 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m +# CONFIG_DRM_DEBUG_MODESET_LOCK is not set CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y @@ -775,12 +779,14 @@ CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m CONFIG_RANDOM32_SELFTEST=y +CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y CONFIG_HEADERS_INSTALL=y CONFIG_DEBUG_SECTION_MISMATCH=y @@ -807,6 +813,7 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_KFENCE=y +CONFIG_KFENCE_STATIC_KEYS=y CONFIG_DEBUG_SHIRQ=y CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y @@ -842,6 +849,7 @@ CONFIG_FTRACE_STARTUP_TEST=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m CONFIG_SAMPLE_FTRACE_DIRECT=m +CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m CONFIG_DEBUG_ENTRY=y CONFIG_CIO_INJECT=y CONFIG_KUNIT=m @@ -860,7 +868,7 @@ CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_MIN_HEAP=y -CONFIG_KPROBES_SANITY_TEST=y +CONFIG_KPROBES_SANITY_TEST=m CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index c9c3cedff2d8..1c750bfca2d8 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -109,6 +109,7 @@ CONFIG_UNIX=y CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m +CONFIG_NET_SWITCHDEV=y CONFIG_SMC=m CONFIG_SMC_DIAG=m CONFIG_INET=y @@ -394,7 +395,6 @@ CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y @@ -467,6 +467,7 @@ CONFIG_MACVLAN=m CONFIG_MACVTAP=m CONFIG_VXLAN=m CONFIG_BAREUDP=m +CONFIG_AMT=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -480,6 +481,7 @@ CONFIG_NLMON=m # CONFIG_NET_VENDOR_AMD is not set # CONFIG_NET_VENDOR_AQUANTIA is not set # CONFIG_NET_VENDOR_ARC is not set +# CONFIG_NET_VENDOR_ASIX is not set # CONFIG_NET_VENDOR_ATHEROS is not set # CONFIG_NET_VENDOR_BROADCOM is not set # CONFIG_NET_VENDOR_BROCADE is not set @@ -501,6 +503,7 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y +CONFIG_MLX5_ESWITCH=y # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -762,12 +765,14 @@ CONFIG_PRIME_NUMBERS=m CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m +CONFIG_XZ_DEC_MICROLZMA=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=0 CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_DEBUG_INFO=y CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_DEBUG_INFO_BTF=y CONFIG_GDB_SCRIPTS=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y @@ -792,9 +797,11 @@ CONFIG_HIST_TRIGGERS=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m CONFIG_SAMPLE_FTRACE_DIRECT=m +CONFIG_SAMPLE_FTRACE_DIRECT_MULTI=m CONFIG_KUNIT=m CONFIG_KUNIT_DEBUGFS=y CONFIG_LKDTM=m +CONFIG_KPROBES_SANITY_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y CONFIG_TEST_BPF=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index aceccf3b9a88..eed3b9acfa71 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -65,9 +65,11 @@ CONFIG_ZFCP=y # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" # CONFIG_ZLIB_DFLTCC is not set +CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y # CONFIG_SYMBOLIC_ERRNAME is not set CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y CONFIG_PANIC_ON_OOPS=y diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index e4dc64cc9c55..287bb88f7698 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -14,12 +14,13 @@ /* I/O Map */ #define ZPCI_IOMAP_SHIFT 48 -#define ZPCI_IOMAP_ADDR_BASE 0x8000000000000000UL +#define ZPCI_IOMAP_ADDR_SHIFT 62 +#define ZPCI_IOMAP_ADDR_BASE (1UL << ZPCI_IOMAP_ADDR_SHIFT) #define ZPCI_IOMAP_ADDR_OFF_MASK ((1UL << ZPCI_IOMAP_SHIFT) - 1) #define ZPCI_IOMAP_MAX_ENTRIES \ - ((ULONG_MAX - ZPCI_IOMAP_ADDR_BASE + 1) / (1UL << ZPCI_IOMAP_SHIFT)) + (1UL << (ZPCI_IOMAP_ADDR_SHIFT - ZPCI_IOMAP_SHIFT)) #define ZPCI_IOMAP_ADDR_IDX_MASK \ - (~ZPCI_IOMAP_ADDR_OFF_MASK - ZPCI_IOMAP_ADDR_BASE) + ((ZPCI_IOMAP_ADDR_BASE - 1) & ~ZPCI_IOMAP_ADDR_OFF_MASK) struct zpci_iomap_entry { u32 fh; diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 5510c7d10ddc..21d62d8b6b9a 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -290,7 +290,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, return; regs = ftrace_get_regs(fregs); - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) goto out; @@ -318,7 +317,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, } __this_cpu_write(current_kprobe, NULL); out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 0df83ecaa2e0..cb7099682340 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -138,7 +138,7 @@ void noinstr do_io_irq(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); int from_idle; - irq_enter(); + irq_enter_rcu(); if (user_mode(regs)) { update_timer_sys(); @@ -158,7 +158,8 @@ void noinstr do_io_irq(struct pt_regs *regs) do_irq_async(regs, IO_INTERRUPT); } while (MACHINE_IS_LPAR && irq_pending(regs)); - irq_exit(); + irq_exit_rcu(); + set_irq_regs(old_regs); irqentry_exit(regs, state); @@ -172,7 +173,7 @@ void noinstr do_ext_irq(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); int from_idle; - irq_enter(); + irq_enter_rcu(); if (user_mode(regs)) { update_timer_sys(); @@ -190,7 +191,7 @@ void noinstr do_ext_irq(struct pt_regs *regs) do_irq_async(regs, EXT_INTERRUPT); - irq_exit(); + irq_exit_rcu(); set_irq_regs(old_regs); irqentry_exit(regs, state); diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index 9975ad200d74..8f43575a4dd3 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -7,6 +7,8 @@ * Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com> */ +#define pr_fmt(fmt) "kexec: " fmt + #include <linux/elf.h> #include <linux/errno.h> #include <linux/kexec.h> @@ -290,8 +292,16 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, const Elf_Shdr *relsec, const Elf_Shdr *symtab) { + const char *strtab, *name, *shstrtab; + const Elf_Shdr *sechdrs; Elf_Rela *relas; int i, r_type; + int ret; + + /* String & section header string table */ + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; + strtab = (char *)pi->ehdr + sechdrs[symtab->sh_link].sh_offset; + shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset; relas = (void *)pi->ehdr + relsec->sh_offset; @@ -304,15 +314,27 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, sym = (void *)pi->ehdr + symtab->sh_offset; sym += ELF64_R_SYM(relas[i].r_info); - if (sym->st_shndx == SHN_UNDEF) + if (sym->st_name) + name = strtab + sym->st_name; + else + name = shstrtab + sechdrs[sym->st_shndx].sh_name; + + if (sym->st_shndx == SHN_UNDEF) { + pr_err("Undefined symbol: %s\n", name); return -ENOEXEC; + } - if (sym->st_shndx == SHN_COMMON) + if (sym->st_shndx == SHN_COMMON) { + pr_err("symbol '%s' in common section\n", name); return -ENOEXEC; + } if (sym->st_shndx >= pi->ehdr->e_shnum && - sym->st_shndx != SHN_ABS) + sym->st_shndx != SHN_ABS) { + pr_err("Invalid section %d for symbol %s\n", + sym->st_shndx, name); return -ENOEXEC; + } loc = pi->purgatory_buf; loc += section->sh_offset; @@ -326,7 +348,15 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, addr = section->sh_addr + relas[i].r_offset; r_type = ELF64_R_TYPE(relas[i].r_info); - arch_kexec_do_relocs(r_type, loc, val, addr); + + if (r_type == R_390_PLT32DBL) + r_type = R_390_PC32DBL; + + ret = arch_kexec_do_relocs(r_type, loc, val, addr); + if (ret) { + pr_err("Unknown rela relocation: %d\n", r_type); + return -ENOEXEC; + } } return 0; } diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index cfc5f5557c06..bc7973359ae2 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -173,10 +173,11 @@ static noinline int unwindme_func4(struct unwindme *u) } /* - * trigger specification exception + * Trigger operation exception; use insn notation to bypass + * llvm's integrated assembler sanity checks. */ asm volatile( - " mvcl %%r1,%%r1\n" + " .insn e,0x0000\n" /* illegal opcode */ "0: nopr %%r7\n" EX_TABLE(0b, 0b) :); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 233cc9bcd652..9ff2bd83aad7 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1369,7 +1369,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, jit->prg); /* - * if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ @@ -1381,9 +1381,9 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4_IMM(0xa7080000, REG_W0, 1); /* laal %w1,%w0,off(%r15) */ EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off); - /* clij %w1,MAX_TAIL_CALL_CNT,0x2,out */ + /* clij %w1,MAX_TAIL_CALL_CNT-1,0x2,out */ patch_2_clij = jit->prg; - EMIT6_PCREL_RIEC(0xec000000, 0x007f, REG_W1, MAX_TAIL_CALL_CNT, + EMIT6_PCREL_RIEC(0xec000000, 0x007f, REG_W1, MAX_TAIL_CALL_CNT - 1, 2, jit->prg); /* diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 9a2f20cbd48b..b1e38784eb23 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -227,7 +227,7 @@ static const int bpf2sparc[] = { [BPF_REG_AX] = G7, - /* temporary register for internal BPF JIT */ + /* temporary register for BPF JIT */ [TMP_REG_1] = G1, [TMP_REG_2] = G2, [TMP_REG_3] = G3, @@ -867,7 +867,7 @@ static void emit_tail_call(struct jit_ctx *ctx) emit(LD32 | IMMED | RS1(SP) | S13(off) | RD(tmp), ctx); emit_cmpi(tmp, MAX_TAIL_CALL_CNT, ctx); #define OFFSET2 13 - emit_branch(BGU, ctx->idx, ctx->idx + OFFSET2, ctx); + emit_branch(BGEU, ctx->idx, ctx->idx + OFFSET2, ctx); emit_nop(ctx); emit_alu_K(ADD, tmp, 1, ctx); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7399327d1eff..5c2ccb85f2ef 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1932,6 +1932,7 @@ config EFI depends on ACPI select UCS2_STRING select EFI_RUNTIME_WRAPPERS + select ARCH_USE_MEMREMAP_PROT help This enables the kernel to use EFI runtime services that are available (such as the EFI variable services). diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index e38a4cf795d9..97b1f84bb53f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -574,6 +574,10 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) ud2 1: #endif +#ifdef CONFIG_XEN_PV + ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV +#endif + POP_REGS pop_rdi=0 /* @@ -890,6 +894,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) .Lparanoid_entry_checkgs: /* EBX = 1 -> kernel GSBASE active, no restore required */ movl $1, %ebx + /* * The kernel-enforced convention is a negative GSBASE indicates * a kernel value. No SWAPGS needed on entry and exit. @@ -897,21 +902,14 @@ SYM_CODE_START_LOCAL(paranoid_entry) movl $MSR_GS_BASE, %ecx rdmsr testl %edx, %edx - jns .Lparanoid_entry_swapgs - ret + js .Lparanoid_kernel_gsbase -.Lparanoid_entry_swapgs: + /* EBX = 0 -> SWAPGS required on exit */ + xorl %ebx, %ebx swapgs +.Lparanoid_kernel_gsbase: - /* - * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an - * unconditional CR3 write, even in the PTI case. So do an lfence - * to prevent GS speculation, regardless of whether PTI is enabled. - */ FENCE_SWAPGS_KERNEL_ENTRY - - /* EBX = 0 -> SWAPGS required on exit */ - xorl %ebx, %ebx ret SYM_CODE_END(paranoid_entry) @@ -993,11 +991,6 @@ SYM_CODE_START_LOCAL(error_entry) pushq %r12 ret -.Lerror_entry_done_lfence: - FENCE_SWAPGS_KERNEL_ENTRY -.Lerror_entry_done: - ret - /* * There are two places in the kernel that can potentially fault with * usergs. Handle them here. B stepping K8s sometimes report a @@ -1020,8 +1013,14 @@ SYM_CODE_START_LOCAL(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS - FENCE_SWAPGS_USER_ENTRY - jmp .Lerror_entry_done + + /* + * Issue an LFENCE to prevent GS speculation, regardless of whether it is a + * kernel or user gsbase. + */ +.Lerror_entry_done_lfence: + FENCE_SWAPGS_KERNEL_ENTRY + ret .Lbstep_iret: /* Fix truncated RIP */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5a0bcf8b78d7..048b6d5aff50 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -108,7 +108,7 @@ #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ -#define INTEL_FAM6_RAPTOR_LAKE 0xB7 +#define INTEL_FAM6_RAPTORLAKE 0xB7 /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6ac61f85e07b..2164b9f4c7b0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -97,7 +97,7 @@ KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) #define KVM_REQ_TLB_FLUSH_GUEST \ - KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP) + KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_APF_READY KVM_ARCH_REQ(28) #define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29) #define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ @@ -1036,6 +1036,7 @@ struct kvm_x86_msr_filter { #define APICV_INHIBIT_REASON_PIT_REINJ 4 #define APICV_INHIBIT_REASON_X2APIC 5 #define APICV_INHIBIT_REASON_BLOCKIRQ 6 +#define APICV_INHIBIT_REASON_ABSENT 7 struct kvm_arch { unsigned long n_used_mmu_pages; diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 2cef6c5a52c2..6acaf5af0a3d 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -73,4 +73,15 @@ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) +/* + * Error codes related to GHCB input that can be communicated back to the guest + * by setting the lower 32-bits of the GHCB SW_EXITINFO1 field to 2. + */ +#define GHCB_ERR_NOT_REGISTERED 1 +#define GHCB_ERR_INVALID_USAGE 2 +#define GHCB_ERR_INVALID_SCRATCH_AREA 3 +#define GHCB_ERR_MISSING_INPUT 4 +#define GHCB_ERR_INVALID_INPUT 5 +#define GHCB_ERR_INVALID_EVENT 6 + #endif diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index d5958278eba6..91d4b6de58ab 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -118,7 +118,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, struct fpstate *fpstate) { struct xregs_state __user *x = buf; - struct _fpx_sw_bytes sw_bytes; + struct _fpx_sw_bytes sw_bytes = {}; u32 xfeatures; int err; diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 74f0ec955384..a9fc2ac7a8bd 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -294,11 +294,6 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, char *dst, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT | X86_PF_WRITE; - char __user *target = (char __user *)dst; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __put_user() independent of whether kernel or user @@ -320,26 +315,42 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *target = (u8 __user *)dst; + memcpy(&d1, buf, 1); if (__put_user(d1, target)) goto fault; break; - case 2: + } + case 2: { + u16 d2; + u16 __user *target = (u16 __user *)dst; + memcpy(&d2, buf, 2); if (__put_user(d2, target)) goto fault; break; - case 4: + } + case 4: { + u32 d4; + u32 __user *target = (u32 __user *)dst; + memcpy(&d4, buf, 4); if (__put_user(d4, target)) goto fault; break; - case 8: + } + case 8: { + u64 d8; + u64 __user *target = (u64 __user *)dst; + memcpy(&d8, buf, 8); if (__put_user(d8, target)) goto fault; break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; @@ -362,11 +373,6 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, char *src, char *buf, size_t size) { unsigned long error_code = X86_PF_PROT; - char __user *s = (char __user *)src; - u64 d8; - u32 d4; - u16 d2; - u8 d1; /* * This function uses __get_user() independent of whether kernel or user @@ -388,26 +394,41 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, * instructions here would cause infinite nesting. */ switch (size) { - case 1: + case 1: { + u8 d1; + u8 __user *s = (u8 __user *)src; + if (__get_user(d1, s)) goto fault; memcpy(buf, &d1, 1); break; - case 2: + } + case 2: { + u16 d2; + u16 __user *s = (u16 __user *)src; + if (__get_user(d2, s)) goto fault; memcpy(buf, &d2, 2); break; - case 4: + } + case 4: { + u32 d4; + u32 __user *s = (u32 __user *)src; + if (__get_user(d4, s)) goto fault; memcpy(buf, &d4, 4); break; - case 8: + } + case 8: { + u64 d8; + u64 __user *s = (u64 __user *)src; if (__get_user(d8, s)) goto fault; memcpy(buf, &d8, 8); break; + } default: WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size); return ES_UNSUPPORTED; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ac2909f0cab3..617012f4619f 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -579,6 +579,17 @@ static struct sched_domain_topology_level x86_numa_in_package_topology[] = { { NULL, }, }; +static struct sched_domain_topology_level x86_hybrid_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + static struct sched_domain_topology_level x86_topology[] = { #ifdef CONFIG_SCHED_SMT { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) }, @@ -1469,8 +1480,11 @@ void __init native_smp_cpus_done(unsigned int max_cpus) calculate_max_logical_packages(); + /* XXX for now assume numa-in-package and hybrid don't overlap */ if (x86_has_numa_in_package) set_sched_topology(x86_numa_in_package_topology); + if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) + set_sched_topology(x86_hybrid_topology); nmi_selftest(); impress_friends(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 2e076a459a0c..a698196377be 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1180,6 +1180,12 @@ void mark_tsc_unstable(char *reason) EXPORT_SYMBOL_GPL(mark_tsc_unstable); +static void __init tsc_disable_clocksource_watchdog(void) +{ + clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; +} + static void __init check_system_tsc_reliable(void) { #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) @@ -1196,6 +1202,23 @@ static void __init check_system_tsc_reliable(void) #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; + + /* + * Disable the clocksource watchdog when the system has: + * - TSC running at constant frequency + * - TSC which does not stop in C-States + * - the TSC_ADJUST register which allows to detect even minimal + * modifications + * - not more than two sockets. As the number of sockets cannot be + * evaluated at the early boot stage where this has to be + * invoked, check the number of online memory nodes as a + * fallback solution which is an reasonable estimate. + */ + if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && + boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && + boot_cpu_has(X86_FEATURE_TSC_ADJUST) && + nr_online_nodes <= 2) + tsc_disable_clocksource_watchdog(); } /* @@ -1387,9 +1410,6 @@ static int __init init_tsc_clocksource(void) if (tsc_unstable) goto unreg; - if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; - if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; @@ -1527,7 +1547,7 @@ void __init tsc_init(void) } if (tsc_clocksource_reliable || no_tsc_watchdog) - clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; + tsc_disable_clocksource_watchdog(); clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 50a4515fe0ad..9452dc9664b5 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -30,6 +30,7 @@ struct tsc_adjust { }; static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust); +static struct timer_list tsc_sync_check_timer; /* * TSC's on different sockets may be reset asynchronously. @@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume) } } +/* + * Normally the tsc_sync will be checked every time system enters idle + * state, but there is still caveat that a system won't enter idle, + * either because it's too busy or configured purposely to not enter + * idle. + * + * So setup a periodic timer (every 10 minutes) to make sure the check + * is always on. + */ + +#define SYNC_CHECK_INTERVAL (HZ * 600) + +static void tsc_sync_check_timer_fn(struct timer_list *unused) +{ + int next_cpu; + + tsc_verify_tsc_adjust(false); + + /* Run the check for all onlined CPUs in turn */ + next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(cpu_online_mask); + + tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL; + add_timer_on(&tsc_sync_check_timer, next_cpu); +} + +static int __init start_sync_check_timer(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable) + return 0; + + timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0); + tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL; + add_timer(&tsc_sync_check_timer); + + return 0; +} +late_initcall(start_sync_check_timer); + static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, unsigned int cpu, bool bootcpu) { diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 5e19e6e4c2ce..8d8c1cc7cb53 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1922,11 +1922,13 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; + if (all_cpus) + goto check_and_send_ipi; + if (!sparse_banks_len) goto ret_success; - if (!all_cpus && - kvm_read_guest(kvm, + if (kvm_read_guest(kvm, hc->ingpa + offsetof(struct hv_send_ipi_ex, vp_set.bank_contents), sparse_banks, @@ -1934,6 +1936,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool return HV_STATUS_INVALID_HYPERCALL_INPUT; } +check_and_send_ipi: if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return HV_STATUS_INVALID_HYPERCALL_INPUT; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6354297e92ae..e2e1d012df22 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1936,7 +1936,11 @@ static void mmu_audit_disable(void) { } static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { - return sp->role.invalid || + if (sp->role.invalid) + return true; + + /* TDP MMU pages due not use the MMU generation. */ + return !sp->tdp_mmu_page && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } @@ -3976,6 +3980,20 @@ out_retry: return true; } +/* + * Returns true if the page fault is stale and needs to be retried, i.e. if the + * root was invalidated by a memslot update or a relevant mmu_notifier fired. + */ +static bool is_page_fault_stale(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, int mmu_seq) +{ + if (is_obsolete_sp(vcpu->kvm, to_shadow_page(vcpu->arch.mmu->root_hpa))) + return true; + + return fault->slot && + mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva); +} + static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); @@ -4013,8 +4031,9 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault else write_lock(&vcpu->kvm->mmu_lock); - if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) + if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; + r = make_mmu_pages_available(vcpu); if (r) goto out_unlock; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index f87d36898c44..708a5d297fe1 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -911,7 +911,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (fault->slot && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, fault->hva)) + + if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 9d6066eb7c10..8f9af7b7dbbe 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -900,6 +900,7 @@ out: bool svm_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 871c426ec389..b4095dfeeee6 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -281,7 +281,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; - pmu->reserved_bits = 0xffffffff00200000ull; + pmu->reserved_bits = 0xfffffff000280000ull; pmu->version = 1; /* not applicable to AMD; but clean them to prevent any fall out */ pmu->counter_bitmask[KVM_PMC_FIXED] = 0; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 59727a966f90..7656a2c5662a 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2260,7 +2260,7 @@ void sev_free_vcpu(struct kvm_vcpu *vcpu) __free_page(virt_to_page(svm->sev_es.vmsa)); if (svm->sev_es.ghcb_sa_free) - kfree(svm->sev_es.ghcb_sa); + kvfree(svm->sev_es.ghcb_sa); } static void dump_ghcb(struct vcpu_svm *svm) @@ -2352,24 +2352,29 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } -static int sev_es_validate_vmgexit(struct vcpu_svm *svm) +static bool sev_es_validate_vmgexit(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu; struct ghcb *ghcb; - u64 exit_code = 0; + u64 exit_code; + u64 reason; ghcb = svm->sev_es.ghcb; - /* Only GHCB Usage code 0 is supported */ - if (ghcb->ghcb_usage) - goto vmgexit_err; - /* - * Retrieve the exit code now even though is may not be marked valid + * Retrieve the exit code now even though it may not be marked valid * as it could help with debugging. */ exit_code = ghcb_get_sw_exit_code(ghcb); + /* Only GHCB Usage code 0 is supported */ + if (ghcb->ghcb_usage) { + reason = GHCB_ERR_INVALID_USAGE; + goto vmgexit_err; + } + + reason = GHCB_ERR_MISSING_INPUT; + if (!ghcb_sw_exit_code_is_valid(ghcb) || !ghcb_sw_exit_info_1_is_valid(ghcb) || !ghcb_sw_exit_info_2_is_valid(ghcb)) @@ -2448,30 +2453,34 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; default: + reason = GHCB_ERR_INVALID_EVENT; goto vmgexit_err; } - return 0; + return true; vmgexit_err: vcpu = &svm->vcpu; - if (ghcb->ghcb_usage) { + if (reason == GHCB_ERR_INVALID_USAGE) { vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n", ghcb->ghcb_usage); + } else if (reason == GHCB_ERR_INVALID_EVENT) { + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n", + exit_code); } else { - vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n", + vcpu_unimpl(vcpu, "vmgexit: exit code %#llx input is not valid\n", exit_code); dump_ghcb(svm); } - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON; - vcpu->run->internal.ndata = 2; - vcpu->run->internal.data[0] = exit_code; - vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu; + /* Clear the valid entries fields */ + memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); + + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, reason); - return -EINVAL; + return false; } void sev_es_unmap_ghcb(struct vcpu_svm *svm) @@ -2493,7 +2502,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) svm->sev_es.ghcb_sa_sync = false; } - kfree(svm->sev_es.ghcb_sa); + kvfree(svm->sev_es.ghcb_sa); svm->sev_es.ghcb_sa = NULL; svm->sev_es.ghcb_sa_free = false; } @@ -2541,14 +2550,14 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) scratch_gpa_beg = ghcb_get_sw_scratch(ghcb); if (!scratch_gpa_beg) { pr_err("vmgexit: scratch gpa not provided\n"); - return false; + goto e_scratch; } scratch_gpa_end = scratch_gpa_beg + len; if (scratch_gpa_end < scratch_gpa_beg) { pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n", len, scratch_gpa_beg); - return false; + goto e_scratch; } if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) { @@ -2566,7 +2575,7 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) scratch_gpa_end > ghcb_scratch_end) { pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n", scratch_gpa_beg, scratch_gpa_end); - return false; + goto e_scratch; } scratch_va = (void *)svm->sev_es.ghcb; @@ -2579,18 +2588,18 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) if (len > GHCB_SCRATCH_AREA_LIMIT) { pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n", len, GHCB_SCRATCH_AREA_LIMIT); - return false; + goto e_scratch; } - scratch_va = kzalloc(len, GFP_KERNEL_ACCOUNT); + scratch_va = kvzalloc(len, GFP_KERNEL_ACCOUNT); if (!scratch_va) - return false; + goto e_scratch; if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) { /* Unable to copy scratch area from guest */ pr_err("vmgexit: kvm_read_guest for scratch area failed\n"); - kfree(scratch_va); - return false; + kvfree(scratch_va); + goto e_scratch; } /* @@ -2607,6 +2616,12 @@ static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) svm->sev_es.ghcb_sa_len = len; return true; + +e_scratch: + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA); + + return false; } static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask, @@ -2657,7 +2672,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_CPUID); if (!ret) { - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ break; } @@ -2693,10 +2708,13 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm) GHCB_MSR_TERM_REASON_POS); pr_info("SEV-ES guest requested termination: %#llx:%#llx\n", reason_set, reason_code); - fallthrough; + + ret = -EINVAL; + break; } default: - ret = -EINVAL; + /* Error, keep GHCB MSR value as-is */ + break; } trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id, @@ -2720,14 +2738,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) if (!ghcb_gpa) { vcpu_unimpl(vcpu, "vmgexit: GHCB gpa is not set\n"); - return -EINVAL; + + /* Without a GHCB, just return right back to the guest */ + return 1; } if (kvm_vcpu_map(vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->sev_es.ghcb_map)) { /* Unable to map GHCB from guest */ vcpu_unimpl(vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n", ghcb_gpa); - return -EINVAL; + + /* Without a GHCB, just return right back to the guest */ + return 1; } svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva; @@ -2737,15 +2759,14 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) exit_code = ghcb_get_sw_exit_code(ghcb); - ret = sev_es_validate_vmgexit(svm); - if (ret) - return ret; + if (!sev_es_validate_vmgexit(svm)) + return 1; sev_es_sync_from_ghcb(svm); ghcb_set_sw_exit_info_1(ghcb, 0); ghcb_set_sw_exit_info_2(ghcb, 0); - ret = -EINVAL; + ret = 1; switch (exit_code) { case SVM_VMGEXIT_MMIO_READ: if (!setup_vmgexit_scratch(svm, true, control->exit_info_2)) @@ -2786,20 +2807,17 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu) default: pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n", control->exit_info_1); - ghcb_set_sw_exit_info_1(ghcb, 1); - ghcb_set_sw_exit_info_2(ghcb, - X86_TRAP_UD | - SVM_EVTINJ_TYPE_EXEPT | - SVM_EVTINJ_VALID); + ghcb_set_sw_exit_info_1(ghcb, 2); + ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT); } - ret = 1; break; } case SVM_VMGEXIT_UNSUPPORTED_EVENT: vcpu_unimpl(vcpu, "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n", control->exit_info_1, control->exit_info_2); + ret = -EINVAL; break; default: ret = svm_invoke_exit_handler(vcpu, exit_code); @@ -2821,7 +2839,7 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in) return -EINVAL; if (!setup_vmgexit_scratch(svm, in, bytes)) - return -EINVAL; + return 1; return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->sev_es.ghcb_sa, count, in); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 64f2828035c2..9c941535f78c 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2591,8 +2591,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) && WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL, - vmcs12->guest_ia32_perf_global_ctrl))) + vmcs12->guest_ia32_perf_global_ctrl))) { + *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; + } kvm_rsp_write(vcpu, vmcs12->guest_rsp); kvm_rip_write(vcpu, vmcs12->guest_rip); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f90448809690..5aadad3e7367 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2646,15 +2646,6 @@ int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); - - if (IS_ENABLED(CONFIG_HYPERV) && - static_branch_unlikely(&enable_evmcs) && - (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { - struct hv_enlightened_vmcs *evmcs = - (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs; - - evmcs->hv_enlightenments_control.msr_bitmap = 1; - } } memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state)); @@ -6842,6 +6833,19 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) if (err < 0) goto free_pml; + /* + * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a + * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the + * feature only for vmcs01, KVM currently isn't equipped to realize any + * performance benefits from enabling it for vmcs02. + */ + if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) && + (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + evmcs->hv_enlightenments_control.msr_bitmap = 1; + } + /* The MSR bitmap starts with all ones */ bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS); bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); @@ -7525,6 +7529,7 @@ static void hardware_unsetup(void) static bool vmx_check_apicv_inhibit_reasons(ulong bit) { ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | + BIT(APICV_INHIBIT_REASON_ABSENT) | BIT(APICV_INHIBIT_REASON_HYPERV) | BIT(APICV_INHIBIT_REASON_BLOCKIRQ); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0ee1a039b490..0cf1082455df 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -890,7 +890,8 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu))) return 1; - if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + if (!(cr0 & X86_CR0_PG) && + (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))) return 1; static_call(kvm_x86_set_cr0)(vcpu, cr0); @@ -5740,6 +5741,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_SPLIT; kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; + kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); r = 0; split_irqchip_unlock: mutex_unlock(&kvm->lock); @@ -6120,6 +6122,7 @@ set_identity_unlock: /* Write kvm->irq_routing before enabling irqchip_in_kernel. */ smp_wmb(); kvm->arch.irqchip_mode = KVM_IRQCHIP_KERNEL; + kvm_request_apicv_update(kvm, true, APICV_INHIBIT_REASON_ABSENT); create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -7119,7 +7122,13 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port, void *val, unsigned int count) { if (vcpu->arch.pio.count) { - /* Complete previous iteration. */ + /* + * Complete a previous iteration that required userspace I/O. + * Note, @count isn't guaranteed to match pio.count as userspace + * can modify ECX before rerunning the vCPU. Ignore any such + * shenanigans as KVM doesn't support modifying the rep count, + * and the emulator ensures @count doesn't overflow the buffer. + */ } else { int r = __emulator_pio_in(vcpu, size, port, count); if (!r) @@ -7128,7 +7137,6 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size, /* Results already available, fall through. */ } - WARN_ON(count != vcpu->arch.pio.count); complete_emulator_pio_in(vcpu, val); return 1; } @@ -8818,10 +8826,9 @@ static void kvm_apicv_init(struct kvm *kvm) { init_rwsem(&kvm->arch.apicv_update_lock); - if (enable_apicv) - clear_bit(APICV_INHIBIT_REASON_DISABLE, - &kvm->arch.apicv_inhibit_reasons); - else + set_bit(APICV_INHIBIT_REASON_ABSENT, + &kvm->arch.apicv_inhibit_reasons); + if (!enable_apicv) set_bit(APICV_INHIBIT_REASON_DISABLE, &kvm->arch.apicv_inhibit_reasons); } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 726700fabca6..c1205414de10 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1,9 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * bpf_jit_comp.c: BPF JIT compiler + * BPF JIT compiler * * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com) - * Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/netdevice.h> #include <linux/filter.h> @@ -412,7 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... * if (index >= array->map.max_entries) * goto out; - * if (++tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; * prog = array->ptrs[index]; * if (prog == NULL) @@ -446,14 +446,14 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, EMIT2(X86_JBE, offset); /* jbe out */ /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_indirect_label - (prog + 2 - start); - EMIT2(X86_JA, offset); /* ja out */ + EMIT2(X86_JAE, offset); /* jae out */ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ @@ -504,14 +504,14 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, int offset; /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_direct_label - (prog + 2 - start); - EMIT2(X86_JA, offset); /* ja out */ + EMIT2(X86_JAE, offset); /* jae out */ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ @@ -1252,19 +1252,54 @@ st: if (is_imm8(insn->off)) case BPF_LDX | BPF_MEM | BPF_DW: case BPF_LDX | BPF_PROBE_MEM | BPF_DW: if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { - /* test src_reg, src_reg */ - maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */ - EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg)); - /* jne start_of_ldx */ - EMIT2(X86_JNE, 0); + /* Though the verifier prevents negative insn->off in BPF_PROBE_MEM + * add abs(insn->off) to the limit to make sure that negative + * offset won't be an issue. + * insn->off is s16, so it won't affect valid pointers. + */ + u64 limit = TASK_SIZE_MAX + PAGE_SIZE + abs(insn->off); + u8 *end_of_jmp1, *end_of_jmp2; + + /* Conservatively check that src_reg + insn->off is a kernel address: + * 1. src_reg + insn->off >= limit + * 2. src_reg + insn->off doesn't become small positive. + * Cannot do src_reg + insn->off >= limit in one branch, + * since it needs two spare registers, but JIT has only one. + */ + + /* movabsq r11, limit */ + EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); + EMIT((u32)limit, 4); + EMIT(limit >> 32, 4); + /* cmp src_reg, r11 */ + maybe_emit_mod(&prog, src_reg, AUX_REG, true); + EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); + /* if unsigned '<' goto end_of_jmp2 */ + EMIT2(X86_JB, 0); + end_of_jmp1 = prog; + + /* mov r11, src_reg */ + emit_mov_reg(&prog, true, AUX_REG, src_reg); + /* add r11, insn->off */ + maybe_emit_1mod(&prog, AUX_REG, true); + EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); + /* jmp if not carry to start_of_ldx + * Otherwise ERR_PTR(-EINVAL) + 128 will be the user addr + * that has to be rejected. + */ + EMIT2(0x73 /* JNC */, 0); + end_of_jmp2 = prog; + /* xor dst_reg, dst_reg */ emit_mov_imm32(&prog, false, dst_reg, 0); /* jmp byte_after_ldx */ EMIT2(0xEB, 0); - /* populate jmp_offset for JNE above */ - temp[4] = prog - temp - 5 /* sizeof(test + jne) */; + /* populate jmp_offset for JB above to jump to xor dst_reg */ + end_of_jmp1[-1] = end_of_jmp2 - end_of_jmp1; + /* populate jmp_offset for JNC above to jump to start_of_ldx */ start_of_ldx = prog; + end_of_jmp2[-1] = start_of_ldx - end_of_jmp2; } emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); if (BPF_MODE(insn->code) == BPF_PROBE_MEM) { @@ -1305,7 +1340,7 @@ st: if (is_imm8(insn->off)) * End result: x86 insn "mov rbx, qword ptr [rax+0x14]" * of 4 bytes will be ignored and rbx will be zero inited. */ - ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8); + ex->fixup = (prog - start_of_ldx) | (reg2pt_regs[dst_reg] << 8); } break; diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index da9b7cfa4632..429a89c5468b 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1323,7 +1323,7 @@ static void emit_bpf_tail_call(u8 **pprog, u8 *ip) EMIT2(IA32_JBE, jmp_label(jmp_label1, 2)); /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ lo = (u32)MAX_TAIL_CALL_CNT; @@ -1337,7 +1337,7 @@ static void emit_bpf_tail_call(u8 **pprog, u8 *ip) /* cmp ecx,lo */ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), lo); - /* ja out */ + /* jae out */ EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); /* add eax,0x1 */ diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index b15ebfe40a73..b0b848d6933a 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -277,7 +277,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) return; } - new = early_memremap(data.phys_map, data.size); + new = early_memremap_prot(data.phys_map, data.size, + pgprot_val(pgprot_encrypted(FIXMAP_PAGE_NORMAL))); if (!new) { pr_err("Failed to map new boot services memmap\n"); return; diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 4a3da7592b99..38d24d2ab38b 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -72,6 +72,7 @@ static void __init setup_real_mode(void) #ifdef CONFIG_X86_64 u64 *trampoline_pgd; u64 efer; + int i; #endif base = (unsigned char *)real_mode_header; @@ -128,8 +129,17 @@ static void __init setup_real_mode(void) trampoline_header->flags = 0; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); + + /* Map the real mode stub as virtual == physical */ trampoline_pgd[0] = trampoline_pgd_entry.pgd; - trampoline_pgd[511] = init_top_pgt[511].pgd; + + /* + * Include the entirety of the kernel mapping into the trampoline + * PGD. This way, all mappings present in the normal kernel page + * tables are usable while running on trampoline_pgd. + */ + for (i = pgd_index(__PAGE_OFFSET); i < PTRS_PER_PGD; i++) + trampoline_pgd[i] = init_top_pgt[i].pgd; #endif sme_sev_setup_real_mode(trampoline_header); diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 220dd9678494..444d824775f6 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <../entry/calling.h> .pushsection .noinstr.text, "ax" /* @@ -193,6 +194,25 @@ SYM_CODE_START(xen_iret) SYM_CODE_END(xen_iret) /* + * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is + * also the kernel stack. Reusing swapgs_restore_regs_and_return_to_usermode() + * in XEN pv would cause %rsp to move up to the top of the kernel stack and + * leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI + * interrupts. And swapgs_restore_regs_and_return_to_usermode() pushing the IRET + * frame at the same address is useless. + */ +SYM_CODE_START(xenpv_restore_regs_and_return_to_usermode) + UNWIND_HINT_REGS + POP_REGS + + /* stackleak_erase() can work safely on the kernel stack. */ + STACKLEAK_ERASE_NOCLOBBER + + addq $8, %rsp /* skip regs->orig_ax */ + jmp xen_iret +SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode) + +/* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: * - kernel gs diff --git a/block/fops.c b/block/fops.c index ad732a36f9b3..0da147edbd18 100644 --- a/block/fops.c +++ b/block/fops.c @@ -15,6 +15,7 @@ #include <linux/falloc.h> #include <linux/suspend.h> #include <linux/fs.h> +#include <linux/module.h> #include "blk.h" static inline struct inode *bdev_file_inode(struct file *file) @@ -340,8 +341,7 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, } else { ret = bio_iov_iter_get_pages(bio, iter); if (unlikely(ret)) { - bio->bi_status = BLK_STS_IOERR; - bio_endio(bio); + bio_put(bio); return ret; } } diff --git a/block/ioprio.c b/block/ioprio.c index 313c14a70bbd..6f01d35a5145 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -220,6 +220,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) pgrp = task_pgrp(current); else pgrp = find_vpid(who); + read_lock(&tasklist_lock); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { tmpio = get_task_ioprio(p); if (tmpio < 0) @@ -229,6 +230,8 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) else ret = ioprio_best(ret, tmpio); } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); + read_unlock(&tasklist_lock); + break; case IOPRIO_WHO_USER: uid = make_kuid(current_user_ns(), who); diff --git a/drivers/Makefile b/drivers/Makefile index be5d40ae1488..a110338c860c 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -41,8 +41,7 @@ obj-$(CONFIG_DMADEVICES) += dma/ # SOC specific infrastructure drivers. obj-y += soc/ -obj-$(CONFIG_VIRTIO) += virtio/ -obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio/ +obj-y += virtio/ obj-$(CONFIG_VDPA) += vdpa/ obj-$(CONFIG_XEN) += xen/ diff --git a/drivers/android/binder.c b/drivers/android/binder.c index cffbe57a8e08..c75fb600740c 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -4422,23 +4422,20 @@ static int binder_thread_release(struct binder_proc *proc, __release(&t->lock); /* - * If this thread used poll, make sure we remove the waitqueue - * from any epoll data structures holding it with POLLFREE. - * waitqueue_active() is safe to use here because we're holding - * the inner lock. + * If this thread used poll, make sure we remove the waitqueue from any + * poll data structures holding it. */ - if ((thread->looper & BINDER_LOOPER_STATE_POLL) && - waitqueue_active(&thread->wait)) { - wake_up_poll(&thread->wait, EPOLLHUP | POLLFREE); - } + if (thread->looper & BINDER_LOOPER_STATE_POLL) + wake_up_pollfree(&thread->wait); binder_inner_proc_unlock(thread->proc); /* - * This is needed to avoid races between wake_up_poll() above and - * and ep_remove_waitqueue() called for other reasons (eg the epoll file - * descriptor being closed); ep_remove_waitqueue() holds an RCU read - * lock, so we can be sure it's done after calling synchronize_rcu(). + * This is needed to avoid races between wake_up_pollfree() above and + * someone else removing the last entry from the queue for other reasons + * (e.g. ep_remove_wait_queue() being called due to an epoll file + * descriptor being closed). Such other users hold an RCU read lock, so + * we can be sure they're done after we call synchronize_rcu(). */ if (thread->looper & BINDER_LOOPER_STATE_POLL) synchronize_rcu(); diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c index 50b56cd0039d..e9c7c07fd84c 100644 --- a/drivers/ata/ahci_ceva.c +++ b/drivers/ata/ahci_ceva.c @@ -94,6 +94,7 @@ struct ceva_ahci_priv { static unsigned int ceva_ahci_read_id(struct ata_device *dev, struct ata_taskfile *tf, u16 *id) { + __le16 *__id = (__le16 *)id; u32 err_mask; err_mask = ata_do_dev_read_id(dev, tf, id); @@ -103,7 +104,7 @@ static unsigned int ceva_ahci_read_id(struct ata_device *dev, * Since CEVA controller does not support device sleep feature, we * need to clear DEVSLP (bit 8) in word78 of the IDENTIFY DEVICE data. */ - id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8)); + __id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8)); return 0; } diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 59ad8c979cb3..aba0c67d1bd6 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3920,6 +3920,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "VRFDFC22048UCHC-TE*", NULL, ATA_HORKAGE_NODMA }, /* Odd clown on sil3726/4726 PMPs */ { "Config Disk", NULL, ATA_HORKAGE_DISABLE }, + /* Similar story with ASMedia 1092 */ + { "ASMT109x- Config", NULL, ATA_HORKAGE_DISABLE }, /* Weird ATAPI devices */ { "TORiSAN DVD-ROM DRD-N216", NULL, ATA_HORKAGE_MAX_SEC_128 }, diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 5b78e86e3459..b9c77885b872 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -827,7 +827,7 @@ static ssize_t ata_scsi_lpm_show(struct device *dev, if (ap->target_lpm_policy >= ARRAY_SIZE(ata_lpm_policy_names)) return -EINVAL; - return snprintf(buf, PAGE_SIZE, "%s\n", + return sysfs_emit(buf, "%s\n", ata_lpm_policy_names[ap->target_lpm_policy]); } DEVICE_ATTR(link_power_management_policy, S_IRUGO | S_IWUSR, diff --git a/drivers/ata/pata_falcon.c b/drivers/ata/pata_falcon.c index 121635aa8c00..823c88622e34 100644 --- a/drivers/ata/pata_falcon.c +++ b/drivers/ata/pata_falcon.c @@ -55,14 +55,14 @@ static unsigned int pata_falcon_data_xfer(struct ata_queued_cmd *qc, /* Transfer multiple of 2 bytes */ if (rw == READ) { if (swap) - raw_insw_swapw((u16 *)data_addr, (u16 *)buf, words); + raw_insw_swapw(data_addr, (u16 *)buf, words); else - raw_insw((u16 *)data_addr, (u16 *)buf, words); + raw_insw(data_addr, (u16 *)buf, words); } else { if (swap) - raw_outsw_swapw((u16 *)data_addr, (u16 *)buf, words); + raw_outsw_swapw(data_addr, (u16 *)buf, words); else - raw_outsw((u16 *)data_addr, (u16 *)buf, words); + raw_outsw(data_addr, (u16 *)buf, words); } /* Transfer trailing byte, if any. */ @@ -74,16 +74,16 @@ static unsigned int pata_falcon_data_xfer(struct ata_queued_cmd *qc, if (rw == READ) { if (swap) - raw_insw_swapw((u16 *)data_addr, (u16 *)pad, 1); + raw_insw_swapw(data_addr, (u16 *)pad, 1); else - raw_insw((u16 *)data_addr, (u16 *)pad, 1); + raw_insw(data_addr, (u16 *)pad, 1); *buf = pad[0]; } else { pad[0] = *buf; if (swap) - raw_outsw_swapw((u16 *)data_addr, (u16 *)pad, 1); + raw_outsw_swapw(data_addr, (u16 *)pad, 1); else - raw_outsw((u16 *)data_addr, (u16 *)pad, 1); + raw_outsw(data_addr, (u16 *)pad, 1); } words++; } diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index e5838b23c9e0..3b31a4f596d8 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1394,6 +1394,14 @@ static int sata_fsl_init_controller(struct ata_host *host) return 0; } +static void sata_fsl_host_stop(struct ata_host *host) +{ + struct sata_fsl_host_priv *host_priv = host->private_data; + + iounmap(host_priv->hcr_base); + kfree(host_priv); +} + /* * scsi mid-layer and libata interface structures */ @@ -1426,6 +1434,8 @@ static struct ata_port_operations sata_fsl_ops = { .port_start = sata_fsl_port_start, .port_stop = sata_fsl_port_stop, + .host_stop = sata_fsl_host_stop, + .pmp_attach = sata_fsl_pmp_attach, .pmp_detach = sata_fsl_pmp_detach, }; @@ -1480,9 +1490,9 @@ static int sata_fsl_probe(struct platform_device *ofdev) host_priv->ssr_base = ssr_base; host_priv->csr_base = csr_base; - irq = irq_of_parse_and_map(ofdev->dev.of_node, 0); - if (!irq) { - dev_err(&ofdev->dev, "invalid irq from platform\n"); + irq = platform_get_irq(ofdev, 0); + if (irq < 0) { + retval = irq; goto error_exit_with_cleanup; } host_priv->irq = irq; @@ -1557,10 +1567,6 @@ static int sata_fsl_remove(struct platform_device *ofdev) ata_host_detach(host); - irq_dispose_mapping(host_priv->irq); - iounmap(host_priv->hcr_base); - kfree(host_priv); - return 0; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a154cab6cd98..c3a36cfaa855 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -2103,7 +2103,7 @@ static int loop_control_remove(int idx) int ret; if (idx < 0) { - pr_warn("deleting an unspecified loop device is not supported.\n"); + pr_warn_once("deleting an unspecified loop device is not supported.\n"); return -EINVAL; } diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c index fb99e3727155..547e6e769546 100644 --- a/drivers/bus/mhi/core/pm.c +++ b/drivers/bus/mhi/core/pm.c @@ -881,7 +881,7 @@ int mhi_pm_suspend(struct mhi_controller *mhi_cntrl) } EXPORT_SYMBOL_GPL(mhi_pm_suspend); -int mhi_pm_resume(struct mhi_controller *mhi_cntrl) +static int __mhi_pm_resume(struct mhi_controller *mhi_cntrl, bool force) { struct mhi_chan *itr, *tmp; struct device *dev = &mhi_cntrl->mhi_dev->dev; @@ -898,8 +898,12 @@ int mhi_pm_resume(struct mhi_controller *mhi_cntrl) if (MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state)) return -EIO; - if (mhi_get_mhi_state(mhi_cntrl) != MHI_STATE_M3) - return -EINVAL; + if (mhi_get_mhi_state(mhi_cntrl) != MHI_STATE_M3) { + dev_warn(dev, "Resuming from non M3 state (%s)\n", + TO_MHI_STATE_STR(mhi_get_mhi_state(mhi_cntrl))); + if (!force) + return -EINVAL; + } /* Notify clients about exiting LPM */ list_for_each_entry_safe(itr, tmp, &mhi_cntrl->lpm_chans, node) { @@ -940,8 +944,19 @@ int mhi_pm_resume(struct mhi_controller *mhi_cntrl) return 0; } + +int mhi_pm_resume(struct mhi_controller *mhi_cntrl) +{ + return __mhi_pm_resume(mhi_cntrl, false); +} EXPORT_SYMBOL_GPL(mhi_pm_resume); +int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl) +{ + return __mhi_pm_resume(mhi_cntrl, true); +} +EXPORT_SYMBOL_GPL(mhi_pm_resume_force); + int __mhi_device_get_sync(struct mhi_controller *mhi_cntrl) { int ret; diff --git a/drivers/bus/mhi/pci_generic.c b/drivers/bus/mhi/pci_generic.c index 59a4896a8030..4c577a731709 100644 --- a/drivers/bus/mhi/pci_generic.c +++ b/drivers/bus/mhi/pci_generic.c @@ -20,7 +20,7 @@ #define MHI_PCI_DEFAULT_BAR_NUM 0 -#define MHI_POST_RESET_DELAY_MS 500 +#define MHI_POST_RESET_DELAY_MS 2000 #define HEALTH_CHECK_PERIOD (HZ * 2) diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index ed3c4c42fc23..d68d05d5d383 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -281,7 +281,7 @@ agp_ioc_init(void __iomem *ioc_regs) return 0; } -static int +static int __init lba_find_capability(int cap) { struct _parisc_agp_info *info = &parisc_agp_info; @@ -366,7 +366,7 @@ fail: return error; } -static int +static int __init find_quicksilver(struct device *dev, void *data) { struct parisc_device **lba = data; @@ -378,7 +378,7 @@ find_quicksilver(struct device *dev, void *data) return 0; } -static int +static int __init parisc_agp_init(void) { extern struct sba_device *sba_list; diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index f467d63bbf1e..566ee2c78709 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -3418,6 +3418,14 @@ static int __clk_core_init(struct clk_core *core) clk_prepare_lock(); + /* + * Set hw->core after grabbing the prepare_lock to synchronize with + * callers of clk_core_fill_parent_index() where we treat hw->core + * being NULL as the clk not being registered yet. This is crucial so + * that clks aren't parented until their parent is fully registered. + */ + core->hw->core = core; + ret = clk_pm_runtime_get(core); if (ret) goto unlock; @@ -3582,8 +3590,10 @@ static int __clk_core_init(struct clk_core *core) out: clk_pm_runtime_put(core); unlock: - if (ret) + if (ret) { hlist_del_init(&core->child_node); + core->hw->core = NULL; + } clk_prepare_unlock(); @@ -3847,7 +3857,6 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) core->num_parents = init->num_parents; core->min_rate = 0; core->max_rate = ULONG_MAX; - hw->core = core; ret = clk_core_populate_parent_map(core, init); if (ret) @@ -3865,7 +3874,7 @@ __clk_register(struct device *dev, struct device_node *np, struct clk_hw *hw) goto fail_create_clk; } - clk_core_link_consumer(hw->core, hw->clk); + clk_core_link_consumer(core, hw->clk); ret = __clk_core_init(core); if (!ret) diff --git a/drivers/clk/imx/clk-imx8qxp-lpcg.c b/drivers/clk/imx/clk-imx8qxp-lpcg.c index d3e905cf867d..b23758083ce5 100644 --- a/drivers/clk/imx/clk-imx8qxp-lpcg.c +++ b/drivers/clk/imx/clk-imx8qxp-lpcg.c @@ -370,7 +370,7 @@ static struct platform_driver imx8qxp_lpcg_clk_driver = { .probe = imx8qxp_lpcg_clk_probe, }; -builtin_platform_driver(imx8qxp_lpcg_clk_driver); +module_platform_driver(imx8qxp_lpcg_clk_driver); MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>"); MODULE_DESCRIPTION("NXP i.MX8QXP LPCG clock driver"); diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c index c53a688d8ccc..40a2efb1329b 100644 --- a/drivers/clk/imx/clk-imx8qxp.c +++ b/drivers/clk/imx/clk-imx8qxp.c @@ -308,7 +308,7 @@ static struct platform_driver imx8qxp_clk_driver = { }, .probe = imx8qxp_clk_probe, }; -builtin_platform_driver(imx8qxp_clk_driver); +module_platform_driver(imx8qxp_clk_driver); MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>"); MODULE_DESCRIPTION("NXP i.MX8QXP clock driver"); diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index eaedcceb766f..8f65b9bdafce 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -1429,6 +1429,15 @@ EXPORT_SYMBOL_GPL(clk_alpha_pll_postdiv_fabia_ops); void clk_trion_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, const struct alpha_pll_config *config) { + /* + * If the bootloader left the PLL enabled it's likely that there are + * RCGs that will lock up if we disable the PLL below. + */ + if (trion_pll_is_enabled(pll, regmap)) { + pr_debug("Trion PLL is already enabled, skipping configuration\n"); + return; + } + clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l); regmap_write(regmap, PLL_CAL_L_VAL(pll), TRION_PLL_CAL_VAL); clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha); diff --git a/drivers/clk/qcom/clk-regmap-mux.c b/drivers/clk/qcom/clk-regmap-mux.c index b2d00b451963..45d9cca28064 100644 --- a/drivers/clk/qcom/clk-regmap-mux.c +++ b/drivers/clk/qcom/clk-regmap-mux.c @@ -28,7 +28,7 @@ static u8 mux_get_parent(struct clk_hw *hw) val &= mask; if (mux->parent_map) - return qcom_find_src_index(hw, mux->parent_map, val); + return qcom_find_cfg_index(hw, mux->parent_map, val); return val; } diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c index 0932e019dd12..75f09e6e057e 100644 --- a/drivers/clk/qcom/common.c +++ b/drivers/clk/qcom/common.c @@ -69,6 +69,18 @@ int qcom_find_src_index(struct clk_hw *hw, const struct parent_map *map, u8 src) } EXPORT_SYMBOL_GPL(qcom_find_src_index); +int qcom_find_cfg_index(struct clk_hw *hw, const struct parent_map *map, u8 cfg) +{ + int i, num_parents = clk_hw_get_num_parents(hw); + + for (i = 0; i < num_parents; i++) + if (cfg == map[i].cfg) + return i; + + return -ENOENT; +} +EXPORT_SYMBOL_GPL(qcom_find_cfg_index); + struct regmap * qcom_cc_map(struct platform_device *pdev, const struct qcom_cc_desc *desc) { diff --git a/drivers/clk/qcom/common.h b/drivers/clk/qcom/common.h index bb39a7e106d8..9c8f7b798d9f 100644 --- a/drivers/clk/qcom/common.h +++ b/drivers/clk/qcom/common.h @@ -49,6 +49,8 @@ extern void qcom_pll_set_fsm_mode(struct regmap *m, u32 reg, u8 bias_count, u8 lock_count); extern int qcom_find_src_index(struct clk_hw *hw, const struct parent_map *map, u8 src); +extern int qcom_find_cfg_index(struct clk_hw *hw, const struct parent_map *map, + u8 cfg); extern int qcom_cc_register_board_clk(struct device *dev, const char *path, const char *name, unsigned long rate); diff --git a/drivers/clk/qcom/gcc-sm6125.c b/drivers/clk/qcom/gcc-sm6125.c index 543cfab7561f..431b55bb0d2f 100644 --- a/drivers/clk/qcom/gcc-sm6125.c +++ b/drivers/clk/qcom/gcc-sm6125.c @@ -1121,7 +1121,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { .name = "gcc_sdcc1_apps_clk_src", .parent_data = gcc_parent_data_1, .num_parents = ARRAY_SIZE(gcc_parent_data_1), - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, }, }; @@ -1143,7 +1143,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = { .name = "gcc_sdcc1_ice_core_clk_src", .parent_data = gcc_parent_data_0, .num_parents = ARRAY_SIZE(gcc_parent_data_0), - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_ops, }, }; diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c index d52f976dc875..d5cb372f0901 100644 --- a/drivers/clk/versatile/clk-icst.c +++ b/drivers/clk/versatile/clk-icst.c @@ -543,8 +543,8 @@ static void __init of_syscon_icst_setup(struct device_node *np) regclk = icst_clk_setup(NULL, &icst_desc, name, parent_name, map, ctype); if (IS_ERR(regclk)) { - kfree(name); pr_err("error setting up syscon ICST clock %s\n", name); + kfree(name); return; } of_clk_add_provider(np, of_clk_src_simple_get, regclk); diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 9a04eacc4412..1ecd52f903b8 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -394,8 +394,13 @@ EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround); static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0); -static void erratum_set_next_event_generic(const int access, unsigned long evt, - struct clock_event_device *clk) +/* + * Force the inlining of this function so that the register accesses + * can be themselves correctly inlined. + */ +static __always_inline +void erratum_set_next_event_generic(const int access, unsigned long evt, + struct clock_event_device *clk) { unsigned long ctrl; u64 cval; diff --git a/drivers/clocksource/dw_apb_timer_of.c b/drivers/clocksource/dw_apb_timer_of.c index 3819ef5b7098..3245eb0c602d 100644 --- a/drivers/clocksource/dw_apb_timer_of.c +++ b/drivers/clocksource/dw_apb_timer_of.c @@ -47,7 +47,7 @@ static int __init timer_get_base_and_rate(struct device_node *np, pr_warn("pclk for %pOFn is present, but could not be activated\n", np); - if (!of_property_read_u32(np, "clock-freq", rate) && + if (!of_property_read_u32(np, "clock-freq", rate) || !of_property_read_u32(np, "clock-frequency", rate)) return 0; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e338d2f010fe..096c3848fa41 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1004,10 +1004,9 @@ static struct kobj_type ktype_cpufreq = { .release = cpufreq_sysfs_release, }; -static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu) +static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu, + struct device *dev) { - struct device *dev = get_cpu_device(cpu); - if (unlikely(!dev)) return; @@ -1296,8 +1295,9 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy) if (policy->max_freq_req) { /* - * CPUFREQ_CREATE_POLICY notification is sent only after - * successfully adding max_freq_req request. + * Remove max_freq_req after sending CPUFREQ_REMOVE_POLICY + * notification, since CPUFREQ_CREATE_POLICY notification was + * sent after adding max_freq_req earlier. */ blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_REMOVE_POLICY, policy); @@ -1391,7 +1391,7 @@ static int cpufreq_online(unsigned int cpu) if (new_policy) { for_each_cpu(j, policy->related_cpus) { per_cpu(cpufreq_cpu_data, j) = policy; - add_cpu_dev_symlink(policy, j); + add_cpu_dev_symlink(policy, j, get_cpu_device(j)); } policy->min_freq_req = kzalloc(2 * sizeof(*policy->min_freq_req), @@ -1565,7 +1565,7 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) /* Create sysfs link on CPU registration */ policy = per_cpu(cpufreq_cpu_data, cpu); if (policy) - add_cpu_dev_symlink(policy, cpu); + add_cpu_dev_symlink(policy, cpu, dev); return 0; } diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c index f57a39ddd063..ab7fd896d2c4 100644 --- a/drivers/dma-buf/heaps/system_heap.c +++ b/drivers/dma-buf/heaps/system_heap.c @@ -290,7 +290,7 @@ static void system_heap_dma_buf_release(struct dma_buf *dmabuf) int i; table = &buffer->sg_table; - for_each_sg(table->sgl, sg, table->nents, i) { + for_each_sgtable_sg(table, sg, i) { struct page *page = sg_page(sg); __free_pages(page, compound_order(page)); diff --git a/drivers/firmware/scpi_pm_domain.c b/drivers/firmware/scpi_pm_domain.c index 51201600d789..800673910b51 100644 --- a/drivers/firmware/scpi_pm_domain.c +++ b/drivers/firmware/scpi_pm_domain.c @@ -16,7 +16,6 @@ struct scpi_pm_domain { struct generic_pm_domain genpd; struct scpi_ops *ops; u32 domain; - char name[30]; }; /* @@ -110,8 +109,13 @@ static int scpi_pm_domain_probe(struct platform_device *pdev) scpi_pd->domain = i; scpi_pd->ops = scpi_ops; - sprintf(scpi_pd->name, "%pOFn.%d", np, i); - scpi_pd->genpd.name = scpi_pd->name; + scpi_pd->genpd.name = devm_kasprintf(dev, GFP_KERNEL, + "%pOFn.%d", np, i); + if (!scpi_pd->genpd.name) { + dev_err(dev, "Failed to allocate genpd name:%pOFn.%d\n", + np, i); + continue; + } scpi_pd->genpd.power_off = scpi_pd_power_off; scpi_pd->genpd.power_on = scpi_pd_power_on; diff --git a/drivers/firmware/tegra/bpmp-debugfs.c b/drivers/firmware/tegra/bpmp-debugfs.c index 6d66fe03fb6a..fd89899aeeed 100644 --- a/drivers/firmware/tegra/bpmp-debugfs.c +++ b/drivers/firmware/tegra/bpmp-debugfs.c @@ -77,13 +77,14 @@ static const char *get_filename(struct tegra_bpmp *bpmp, const char *root_path, *filename = NULL; char *root_path_buf; size_t root_len; + size_t root_path_buf_len = 512; - root_path_buf = kzalloc(512, GFP_KERNEL); + root_path_buf = kzalloc(root_path_buf_len, GFP_KERNEL); if (!root_path_buf) goto out; root_path = dentry_path(bpmp->debugfs_mirror, root_path_buf, - sizeof(root_path_buf)); + root_path_buf_len); if (IS_ERR(root_path)) goto out; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 71a6a9ef54ac..6348559608ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1396,7 +1396,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( struct sg_table *sg = NULL; uint64_t user_addr = 0; struct amdgpu_bo *bo; - struct drm_gem_object *gobj; + struct drm_gem_object *gobj = NULL; u32 domain, alloc_domain; u64 alloc_flags; int ret; @@ -1506,14 +1506,16 @@ allocate_init_user_pages_failed: remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info); drm_vma_node_revoke(&gobj->vma_node, drm_priv); err_node_allow: - drm_gem_object_put(gobj); /* Don't unreserve system mem limit twice */ goto err_reserve_limit; err_bo_create: unreserve_mem_limit(adev, size, alloc_domain, !!sg); err_reserve_limit: mutex_destroy(&(*mem)->lock); - kfree(*mem); + if (gobj) + drm_gem_object_put(gobj); + else + kfree(*mem); err: if (sg) { sg_free_table(sg); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d94fa748e6bb..1e651b959141 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3833,7 +3833,7 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev) /* disable all interrupts */ amdgpu_irq_disable_all(adev); if (adev->mode_info.mode_config_initialized){ - if (!amdgpu_device_has_dc_support(adev)) + if (!drm_drv_uses_atomic_modeset(adev_to_drm(adev))) drm_helper_force_disable_all(adev_to_drm(adev)); else drm_atomic_helper_shutdown(adev_to_drm(adev)); @@ -4289,6 +4289,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, { int r; + amdgpu_amdkfd_pre_reset(adev); + if (from_hypervisor) r = amdgpu_virt_request_full_gpu(adev, true); else @@ -4316,6 +4318,7 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, amdgpu_irq_gpu_reset_resume_helper(adev); r = amdgpu_ib_ring_tests(adev); + amdgpu_amdkfd_post_reset(adev); error: if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) { @@ -5030,7 +5033,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, cancel_delayed_work_sync(&tmp_adev->delayed_init_work); - amdgpu_amdkfd_pre_reset(tmp_adev); + if (!amdgpu_sriov_vf(tmp_adev)) + amdgpu_amdkfd_pre_reset(tmp_adev); /* * Mark these ASICs to be reseted as untracked first @@ -5129,7 +5133,7 @@ skip_hw_reset: drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res); } - if (!amdgpu_device_has_dc_support(tmp_adev) && !job_signaled) { + if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) { drm_helper_resume_force_mode(adev_to_drm(tmp_adev)); } @@ -5148,9 +5152,9 @@ skip_hw_reset: skip_sched_resume: list_for_each_entry(tmp_adev, device_list_handle, reset_list) { - /* unlock kfd */ - if (!need_emergency_restart) - amdgpu_amdkfd_post_reset(tmp_adev); + /* unlock kfd: SRIOV would do it separately */ + if (!need_emergency_restart && !amdgpu_sriov_vf(tmp_adev)) + amdgpu_amdkfd_post_reset(tmp_adev); /* kfd_post_reset will do nothing if kfd device is not initialized, * need to bring up kfd here if it's not be initialized before diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 503995c7ff6c..ea00090b3fb3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -157,6 +157,8 @@ static int hw_id_map[MAX_HWIP] = { [HDP_HWIP] = HDP_HWID, [SDMA0_HWIP] = SDMA0_HWID, [SDMA1_HWIP] = SDMA1_HWID, + [SDMA2_HWIP] = SDMA2_HWID, + [SDMA3_HWIP] = SDMA3_HWID, [MMHUB_HWIP] = MMHUB_HWID, [ATHUB_HWIP] = ATHUB_HWID, [NBIO_HWIP] = NBIF_HWID, @@ -918,6 +920,7 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev) case IP_VERSION(3, 0, 64): case IP_VERSION(3, 1, 1): case IP_VERSION(3, 0, 2): + case IP_VERSION(3, 0, 192): amdgpu_device_ip_block_add(adev, &vcn_v3_0_ip_block); if (!amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &jpeg_v3_0_ip_block); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 4f7c70845785..585961c2f5f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -135,6 +135,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) break; case IP_VERSION(3, 0, 0): case IP_VERSION(3, 0, 64): + case IP_VERSION(3, 0, 192): if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 3, 0)) fw_name = FIRMWARE_SIENNA_CICHLID; else diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index ce982afeff91..ac9a8cd21c4b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -504,8 +504,8 @@ static int amdgpu_vkms_sw_fini(void *handle) int i = 0; for (i = 0; i < adev->mode_info.num_crtc; i++) - if (adev->mode_info.crtcs[i]) - hrtimer_cancel(&adev->mode_info.crtcs[i]->vblank_timer); + if (adev->amdgpu_vkms_output[i].vblank_hrtimer.function) + hrtimer_cancel(&adev->amdgpu_vkms_output[i].vblank_hrtimer); kfree(adev->mode_info.bios_hardcoded_edid); kfree(adev->amdgpu_vkms_output); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 34478bcc4d09..b305fd39874f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -4060,9 +4060,10 @@ static int gfx_v9_0_hw_fini(void *handle) gfx_v9_0_cp_enable(adev, false); - /* Skip suspend with A+A reset */ - if (adev->gmc.xgmi.connected_to_cpu && amdgpu_in_reset(adev)) { - dev_dbg(adev->dev, "Device in reset. Skipping RLC halt\n"); + /* Skip stopping RLC with A+A reset or when RLC controls GFX clock */ + if ((adev->gmc.xgmi.connected_to_cpu && amdgpu_in_reset(adev)) || + (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 4, 2))) { + dev_dbg(adev->dev, "Skipping RLC halt\n"); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index a6659d9ecdd2..2ec1ffb36b1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -183,6 +183,7 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, switch (adev->ip_versions[UVD_HWIP][0]) { case IP_VERSION(3, 0, 0): case IP_VERSION(3, 0, 64): + case IP_VERSION(3, 0, 192): if (amdgpu_sriov_vf(adev)) { if (encode) *codecs = &sriov_sc_video_codecs_encode; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 58b89b53ebe6..3cb4681c5f53 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1574,7 +1574,6 @@ retry_flush_work: static void svm_range_restore_work(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); - struct amdkfd_process_info *process_info; struct svm_range_list *svms; struct svm_range *prange; struct kfd_process *p; @@ -1594,12 +1593,10 @@ static void svm_range_restore_work(struct work_struct *work) * the lifetime of this thread, kfd_process and mm will be valid. */ p = container_of(svms, struct kfd_process, svms); - process_info = p->kgd_process_info; mm = p->mm; if (!mm) return; - mutex_lock(&process_info->lock); svm_range_list_lock_and_flush_work(svms, mm); mutex_lock(&svms->lock); @@ -1652,7 +1649,6 @@ static void svm_range_restore_work(struct work_struct *work) out_reschedule: mutex_unlock(&svms->lock); mmap_write_unlock(mm); - mutex_unlock(&process_info->lock); /* If validation failed, reschedule another attempt */ if (evicted_ranges) { @@ -2614,6 +2610,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, if (atomic_read(&svms->drain_pagefaults)) { pr_debug("draining retry fault, drop fault 0x%llx\n", addr); + r = 0; goto out; } @@ -2623,6 +2620,7 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, mm = get_task_mm(p->lead_thread); if (!mm) { pr_debug("svms 0x%p failed to get mm\n", svms); + r = 0; goto out; } @@ -2660,6 +2658,7 @@ retry_write_locked: if (svm_range_skip_recover(prange)) { amdgpu_gmc_filter_faults_remove(adev, addr, pasid); + r = 0; goto out_unlock_range; } @@ -2668,6 +2667,7 @@ retry_write_locked: if (timestamp < AMDGPU_SVM_RANGE_RETRY_FAULT_PENDING) { pr_debug("svms 0x%p [0x%lx %lx] already restored\n", svms, prange->start, prange->last); + r = 0; goto out_unlock_range; } @@ -3177,7 +3177,6 @@ static int svm_range_set_attr(struct kfd_process *p, uint64_t start, uint64_t size, uint32_t nattr, struct kfd_ioctl_svm_attribute *attrs) { - struct amdkfd_process_info *process_info = p->kgd_process_info; struct mm_struct *mm = current->mm; struct list_head update_list; struct list_head insert_list; @@ -3196,8 +3195,6 @@ svm_range_set_attr(struct kfd_process *p, uint64_t start, uint64_t size, svms = &p->svms; - mutex_lock(&process_info->lock); - svm_range_list_lock_and_flush_work(svms, mm); r = svm_range_is_valid(p, start, size); @@ -3273,8 +3270,6 @@ out_unlock_range: mutex_unlock(&svms->lock); mmap_read_unlock(mm); out: - mutex_unlock(&process_info->lock); - pr_debug("pasid 0x%x svms 0x%p [0x%llx 0x%llx] done, r=%d\n", p->pasid, &p->svms, start, start + size - 1, r); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 1cd6b9f4a568..122dae1a1813 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2576,7 +2576,8 @@ static int dm_resume(void *handle) */ link_enc_cfg_init(dm->dc, dc_state); - amdgpu_dm_outbox_init(adev); + if (dc_enable_dmub_notifications(adev->dm.dc)) + amdgpu_dm_outbox_init(adev); r = dm_dmub_hw_init(adev); if (r) @@ -2625,6 +2626,10 @@ static int dm_resume(void *handle) /* TODO: Remove dc_state->dccg, use dc->dccg directly. */ dc_resource_state_construct(dm->dc, dm_state->context); + /* Re-enable outbox interrupts for DPIA. */ + if (dc_enable_dmub_notifications(adev->dm.dc)) + amdgpu_dm_outbox_init(adev); + /* Before powering on DC we need to re-initialize DMUB. */ r = dm_dmub_hw_init(adev); if (r) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c index cce062adc439..8a441a22c46e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c @@ -314,6 +314,14 @@ int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name) ret = -EINVAL; goto cleanup; } + + if ((aconn->base.connector_type != DRM_MODE_CONNECTOR_DisplayPort) && + (aconn->base.connector_type != DRM_MODE_CONNECTOR_eDP)) { + DRM_DEBUG_DRIVER("No DP connector available for CRC source\n"); + ret = -EINVAL; + goto cleanup; + } + } #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 32a5ce09a62a..cc34a35d0bcb 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -36,6 +36,8 @@ #include "dm_helpers.h" #include "dc_link_ddc.h" +#include "ddc_service_types.h" +#include "dpcd_defs.h" #include "i2caux_interface.h" #include "dmub_cmd.h" @@ -157,6 +159,16 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = { }; #if defined(CONFIG_DRM_AMD_DC_DCN) +static bool needs_dsc_aux_workaround(struct dc_link *link) +{ + if (link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 && + (link->dpcd_caps.dpcd_rev.raw == DPCD_REV_14 || link->dpcd_caps.dpcd_rev.raw == DPCD_REV_12) && + link->dpcd_caps.sink_count.bits.SINK_COUNT >= 2) + return true; + + return false; +} + static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnector) { struct dc_sink *dc_sink = aconnector->dc_sink; @@ -166,7 +178,7 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto u8 *dsc_branch_dec_caps = NULL; aconnector->dsc_aux = drm_dp_mst_dsc_aux_for_port(port); -#if defined(CONFIG_HP_HOOK_WORKAROUND) + /* * drm_dp_mst_dsc_aux_for_port() will return NULL for certain configs * because it only check the dsc/fec caps of the "port variable" and not the dock @@ -176,10 +188,10 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto * Workaround: explicitly check the use case above and use the mst dock's aux as dsc_aux * */ - - if (!aconnector->dsc_aux && !port->parent->port_parent) + if (!aconnector->dsc_aux && !port->parent->port_parent && + needs_dsc_aux_workaround(aconnector->dc_link)) aconnector->dsc_aux = &aconnector->mst_port->dm_dp_aux.aux; -#endif + if (!aconnector->dsc_aux) return false; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 60544788e911..c8457babfdea 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -758,6 +758,18 @@ static bool detect_dp(struct dc_link *link, dal_ddc_service_set_transaction_type(link->ddc, sink_caps->transaction_type); +#if defined(CONFIG_DRM_AMD_DC_DCN) + /* Apply work around for tunneled MST on certain USB4 docks. Always use DSC if dock + * reports DSC support. + */ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && + link->type == dc_connection_mst_branch && + link->dpcd_caps.branch_dev_id == DP_BRANCH_DEVICE_ID_90CC24 && + link->dpcd_caps.dsc_caps.dsc_basic_caps.fields.dsc_support.DSC_SUPPORT && + !link->dc->debug.dpia_debug.bits.disable_mst_dsc_work_around) + link->wa_flags.dpia_mst_dsc_always_on = true; +#endif + #if defined(CONFIG_DRM_AMD_DC_HDCP) /* In case of fallback to SST when topology discovery below fails * HDCP caps will be querried again later by the upper layer (caller @@ -1203,6 +1215,10 @@ static bool dc_link_detect_helper(struct dc_link *link, LINK_INFO("link=%d, mst branch is now Disconnected\n", link->link_index); + /* Disable work around which keeps DSC on for tunneled MST on certain USB4 docks. */ + if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA) + link->wa_flags.dpia_mst_dsc_always_on = false; + dm_helpers_dp_mst_stop_top_mgr(link->ctx, link); link->mst_stream_alloc_table.stream_count = 0; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index cb7bf9148904..13bc69d6b679 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -2138,7 +2138,7 @@ static enum link_training_result dp_perform_8b_10b_link_training( } for (lane = 0; lane < (uint8_t)lt_settings->link_settings.lane_count; lane++) - lt_settings->dpcd_lane_settings[lane].bits.VOLTAGE_SWING_SET = VOLTAGE_SWING_LEVEL0; + lt_settings->dpcd_lane_settings[lane].raw = 0; } if (status == LINK_TRAINING_SUCCESS) { diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index c32fdccd4d92..e2d9a46d0e1a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1664,6 +1664,10 @@ bool dc_is_stream_unchanged( if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param) return false; + // Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks + if (old_stream->audio_info.mode_count != stream->audio_info.mode_count) + return false; + return true; } @@ -2252,16 +2256,6 @@ enum dc_status dc_validate_global_state( if (!new_ctx) return DC_ERROR_UNEXPECTED; -#if defined(CONFIG_DRM_AMD_DC_DCN) - - /* - * Update link encoder to stream assignment. - * TODO: Split out reason allocation from validation. - */ - if (dc->res_pool->funcs->link_encs_assign && fast_validate == false) - dc->res_pool->funcs->link_encs_assign( - dc, new_ctx, new_ctx->streams, new_ctx->stream_count); -#endif if (dc->res_pool->funcs->validate_global) { result = dc->res_pool->funcs->validate_global(dc, new_ctx); @@ -2313,6 +2307,16 @@ enum dc_status dc_validate_global_state( if (!dc->res_pool->funcs->validate_bandwidth(dc, new_ctx, fast_validate)) result = DC_FAIL_BANDWIDTH_VALIDATE; +#if defined(CONFIG_DRM_AMD_DC_DCN) + /* + * Only update link encoder to stream assignment after bandwidth validation passed. + * TODO: Split out assignment and validation. + */ + if (result == DC_OK && dc->res_pool->funcs->link_encs_assign && fast_validate == false) + dc->res_pool->funcs->link_encs_assign( + dc, new_ctx, new_ctx->streams, new_ctx->stream_count); +#endif + return result; } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 3aac3f4a2852..618e7989176f 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -508,7 +508,8 @@ union dpia_debug_options { uint32_t disable_dpia:1; uint32_t force_non_lttpr:1; uint32_t extend_aux_rd_interval:1; - uint32_t reserved:29; + uint32_t disable_mst_dsc_work_around:1; + uint32_t reserved:28; } bits; uint32_t raw; }; diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index 180ecd860296..fad3d883ed89 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -191,6 +191,8 @@ struct dc_link { bool dp_skip_DID2; bool dp_skip_reset_segment; bool dp_mot_reset_segment; + /* Some USB4 docks do not handle turning off MST DSC once it has been enabled. */ + bool dpia_mst_dsc_always_on; } wa_flags; struct link_mst_stream_allocation_table mst_stream_alloc_table; @@ -224,6 +226,8 @@ static inline void get_edp_links(const struct dc *dc, *edp_num = 0; for (i = 0; i < dc->link_count; i++) { // report any eDP links, even unconnected DDI's + if (!dc->links[i]) + continue; if (dc->links[i]->connector_signal == SIGNAL_TYPE_EDP) { edp_links[*edp_num] = dc->links[i]; if (++(*edp_num) == MAX_NUM_EDP) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 01168b8955bf..8a3244585d80 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1468,7 +1468,7 @@ static int smu_disable_dpms(struct smu_context *smu) dev_err(adev->dev, "Failed to disable smu features.\n"); } - if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(10, 0, 0) && + if (adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 4, 2) && adev->gfx.rlc.funcs->stop) adev->gfx.rlc.funcs->stop(adev); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 7b9f69f21f1e..bca0de92802e 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -9,6 +9,7 @@ #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/module.h> #ifdef CONFIG_X86 #include <asm/set_memory.h> diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index c9a9d74f338c..c313a5b4549c 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -404,8 +404,17 @@ int drm_syncobj_find_fence(struct drm_file *file_private, if (*fence) { ret = dma_fence_chain_find_seqno(fence, point); - if (!ret) + if (!ret) { + /* If the requested seqno is already signaled + * drm_syncobj_find_fence may return a NULL + * fence. To make sure the recipient gets + * signalled, use a new fence instead. + */ + if (!*fence) + *fence = dma_fence_get_stub(); + goto out; + } dma_fence_put(*fence); } else { ret = -EINVAL; diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 39e11eaec1a3..aa7238245b0e 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1640,6 +1640,9 @@ struct intel_dp { struct intel_dp_pcon_frl frl; struct intel_psr psr; + + /* When we last wrote the OUI for eDP */ + unsigned long last_oui_write; }; enum lspcon_vendor { diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index be883469d2fc..a552f05a67e5 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -29,6 +29,7 @@ #include <linux/i2c.h> #include <linux/notifier.h> #include <linux/slab.h> +#include <linux/timekeeping.h> #include <linux/types.h> #include <asm/byteorder.h> @@ -1955,6 +1956,16 @@ intel_edp_init_source_oui(struct intel_dp *intel_dp, bool careful) if (drm_dp_dpcd_write(&intel_dp->aux, DP_SOURCE_OUI, oui, sizeof(oui)) < 0) drm_err(&i915->drm, "Failed to write source OUI\n"); + + intel_dp->last_oui_write = jiffies; +} + +void intel_dp_wait_source_oui(struct intel_dp *intel_dp) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + + drm_dbg_kms(&i915->drm, "Performing OUI wait\n"); + wait_remaining_ms_from_jiffies(intel_dp->last_oui_write, 30); } /* If the device supports it, try to set the power state appropriately */ diff --git a/drivers/gpu/drm/i915/display/intel_dp.h b/drivers/gpu/drm/i915/display/intel_dp.h index ce229026dc91..b64145a3869a 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.h +++ b/drivers/gpu/drm/i915/display/intel_dp.h @@ -119,4 +119,6 @@ void intel_dp_pcon_dsc_configure(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state); void intel_dp_phy_test(struct intel_encoder *encoder); +void intel_dp_wait_source_oui(struct intel_dp *intel_dp); + #endif /* __INTEL_DP_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 569d17b4d00f..3897468140e0 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -36,6 +36,7 @@ #include "intel_backlight.h" #include "intel_display_types.h" +#include "intel_dp.h" #include "intel_dp_aux_backlight.h" /* TODO: @@ -106,6 +107,8 @@ intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector) int ret; u8 tcon_cap[4]; + intel_dp_wait_source_oui(intel_dp); + ret = drm_dp_dpcd_read(aux, INTEL_EDP_HDR_TCON_CAP0, tcon_cap, sizeof(tcon_cap)); if (ret != sizeof(tcon_cap)) return false; @@ -204,6 +207,8 @@ intel_dp_aux_hdr_enable_backlight(const struct intel_crtc_state *crtc_state, int ret; u8 old_ctrl, ctrl; + intel_dp_wait_source_oui(intel_dp); + ret = drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &old_ctrl); if (ret != 1) { drm_err(&i915->drm, "Failed to read current backlight control mode: %d\n", ret); @@ -293,6 +298,13 @@ intel_dp_aux_vesa_enable_backlight(const struct intel_crtc_state *crtc_state, struct intel_panel *panel = &connector->panel; struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder); + if (!panel->backlight.edp.vesa.info.aux_enable) { + u32 pwm_level = intel_backlight_invert_pwm_level(connector, + panel->backlight.pwm_level_max); + + panel->backlight.pwm_funcs->enable(crtc_state, conn_state, pwm_level); + } + drm_edp_backlight_enable(&intel_dp->aux, &panel->backlight.edp.vesa.info, level); } @@ -304,6 +316,10 @@ static void intel_dp_aux_vesa_disable_backlight(const struct drm_connector_state struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder); drm_edp_backlight_disable(&intel_dp->aux, &panel->backlight.edp.vesa.info); + + if (!panel->backlight.edp.vesa.info.aux_enable) + panel->backlight.pwm_funcs->disable(old_conn_state, + intel_backlight_invert_pwm_level(connector, 0)); } static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, enum pipe pipe) @@ -321,6 +337,15 @@ static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, if (ret < 0) return ret; + if (!panel->backlight.edp.vesa.info.aux_enable) { + ret = panel->backlight.pwm_funcs->setup(connector, pipe); + if (ret < 0) { + drm_err(&i915->drm, + "Failed to setup PWM backlight controls for eDP backlight: %d\n", + ret); + return ret; + } + } panel->backlight.max = panel->backlight.edp.vesa.info.max; panel->backlight.min = 0; if (current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) { @@ -340,12 +365,7 @@ intel_dp_aux_supports_vesa_backlight(struct intel_connector *connector) struct intel_dp *intel_dp = intel_attached_dp(connector); struct drm_i915_private *i915 = dp_to_i915(intel_dp); - /* TODO: We currently only support AUX only backlight configurations, not backlights which - * require a mix of PWM and AUX controls to work. In the mean time, these machines typically - * work just fine using normal PWM controls anyway. - */ - if ((intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) && - drm_edp_backlight_supported(intel_dp->edp_dpcd)) { + if (drm_edp_backlight_supported(intel_dp->edp_dpcd)) { drm_dbg_kms(&i915->drm, "AUX Backlight Control Supported!\n"); return true; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 4d7da07442f2..9b24d9b5ade1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -3277,6 +3277,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, out_fence = eb_requests_create(&eb, in_fence, out_fence_fd); if (IS_ERR(out_fence)) { err = PTR_ERR(out_fence); + out_fence = NULL; if (eb.requests[0]) goto err_request; else diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 67d14afa6623..b67f620c3d93 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -6,6 +6,7 @@ #include <linux/slab.h> /* fault-inject.h is not standalone! */ #include <linux/fault-inject.h> +#include <linux/sched/mm.h> #include "gem/i915_gem_lmem.h" #include "i915_trace.h" diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index e1f362530889..2400d6423ba5 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -621,13 +621,6 @@ static void gen12_ctx_workarounds_init(struct intel_engine_cs *engine, FF_MODE2_GS_TIMER_MASK, FF_MODE2_GS_TIMER_224, 0, false); - - /* - * Wa_14012131227:dg1 - * Wa_1508744258:tgl,rkl,dg1,adl-s,adl-p - */ - wa_masked_en(wal, GEN7_COMMON_SLICE_CHICKEN1, - GEN9_RHWO_OPTIMIZATION_DISABLE); } static void dg1_ctx_workarounds_init(struct intel_engine_cs *engine, @@ -1134,6 +1127,15 @@ icl_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) GAMT_CHKN_BIT_REG, GAMT_CHKN_DISABLE_L3_COH_PIPE); + /* Wa_1407352427:icl,ehl */ + wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, + PSDUNIT_CLKGATE_DIS); + + /* Wa_1406680159:icl,ehl */ + wa_write_or(wal, + SUBSLICE_UNIT_LEVEL_CLKGATE, + GWUNIT_CLKGATE_DIS); + /* Wa_1607087056:icl,ehl,jsl */ if (IS_ICELAKE(i915) || IS_JSL_EHL_GT_STEP(i915, STEP_A0, STEP_B0)) @@ -1859,15 +1861,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS); - /* Wa_1407352427:icl,ehl */ - wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, - PSDUNIT_CLKGATE_DIS); - - /* Wa_1406680159:icl,ehl */ - wa_write_or(wal, - SUBSLICE_UNIT_LEVEL_CLKGATE, - GWUNIT_CLKGATE_DIS); - /* * Wa_1408767742:icl[a2..forever],ehl[all] * Wa_1605460711:icl[a0..c0] diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 820a1f38b271..89cccefeea63 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -29,6 +29,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/sched/signal.h> +#include <linux/sched/mm.h> #include "gem/i915_gem_context.h" #include "gt/intel_breadcrumbs.h" diff --git a/drivers/gpu/drm/lima/lima_device.c b/drivers/gpu/drm/lima/lima_device.c index 65fdca366e41..f74f8048af8f 100644 --- a/drivers/gpu/drm/lima/lima_device.c +++ b/drivers/gpu/drm/lima/lima_device.c @@ -4,6 +4,7 @@ #include <linux/regulator/consumer.h> #include <linux/reset.h> #include <linux/clk.h> +#include <linux/slab.h> #include <linux/dma-mapping.h> #include <linux/platform_device.h> diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index ae11061727ff..39197b4beea7 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -4,8 +4,8 @@ config DRM_MSM tristate "MSM DRM" depends on DRM depends on ARCH_QCOM || SOC_IMX5 || COMPILE_TEST + depends on COMMON_CLK depends on IOMMU_SUPPORT - depends on (OF && COMMON_CLK) || COMPILE_TEST depends on QCOM_OCMEM || QCOM_OCMEM=n depends on QCOM_LLCC || QCOM_LLCC=n depends on QCOM_COMMAND_DB || QCOM_COMMAND_DB=n diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 40577f8856d8..093454457545 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -23,8 +23,10 @@ msm-y := \ hdmi/hdmi_i2c.o \ hdmi/hdmi_phy.o \ hdmi/hdmi_phy_8960.o \ + hdmi/hdmi_phy_8996.o \ hdmi/hdmi_phy_8x60.o \ hdmi/hdmi_phy_8x74.o \ + hdmi/hdmi_pll_8960.o \ edp/edp.o \ edp/edp_aux.o \ edp/edp_bridge.o \ @@ -37,6 +39,7 @@ msm-y := \ disp/mdp4/mdp4_dtv_encoder.o \ disp/mdp4/mdp4_lcdc_encoder.o \ disp/mdp4/mdp4_lvds_connector.o \ + disp/mdp4/mdp4_lvds_pll.o \ disp/mdp4/mdp4_irq.o \ disp/mdp4/mdp4_kms.o \ disp/mdp4/mdp4_plane.o \ @@ -116,9 +119,6 @@ msm-$(CONFIG_DRM_MSM_DP)+= dp/dp_aux.o \ dp/dp_audio.o msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o -msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o -msm-$(CONFIG_COMMON_CLK) += hdmi/hdmi_pll_8960.o -msm-$(CONFIG_COMMON_CLK) += hdmi/hdmi_phy_8996.o msm-$(CONFIG_DRM_MSM_HDMI_HDCP) += hdmi/hdmi_hdcp.o diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 267a880811d6..78aad5216a61 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1424,17 +1424,24 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; struct msm_gpu *gpu = &adreno_gpu->base; - u32 gpu_scid, cntl1_regval = 0; + u32 cntl1_regval = 0; if (IS_ERR(a6xx_gpu->llc_mmio)) return; if (!llcc_slice_activate(a6xx_gpu->llc_slice)) { - gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice); + u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice); gpu_scid &= 0x1f; cntl1_regval = (gpu_scid << 0) | (gpu_scid << 5) | (gpu_scid << 10) | (gpu_scid << 15) | (gpu_scid << 20); + + /* On A660, the SCID programming for UCHE traffic is done in + * A6XX_GBIF_SCACHE_CNTL0[14:10] + */ + if (adreno_is_a660_family(adreno_gpu)) + gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) | + (1 << 8), (gpu_scid << 10) | (1 << 8)); } /* @@ -1471,13 +1478,6 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu) } gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, GENMASK(24, 0), cntl1_regval); - - /* On A660, the SCID programming for UCHE traffic is done in - * A6XX_GBIF_SCACHE_CNTL0[14:10] - */ - if (adreno_is_a660_family(adreno_gpu)) - gpu_rmw(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, (0x1f << 10) | - (1 << 8), (gpu_scid << 10) | (1 << 8)); } static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu) @@ -1640,7 +1640,7 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu) return (unsigned long)busy_time; } -void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) +static void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 7501849ed15d..6e90209cd543 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -777,12 +777,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); a6xx_state->gmu_registers = state_kcalloc(a6xx_state, - 2, sizeof(*a6xx_state->gmu_registers)); + 3, sizeof(*a6xx_state->gmu_registers)); if (!a6xx_state->gmu_registers) return; - a6xx_state->nr_gmu_registers = 2; + a6xx_state->nr_gmu_registers = 3; /* Get the CX GMU registers from AHB */ _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0], diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index eb40d8413bca..6d36f63c3338 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -33,6 +33,7 @@ struct dp_aux_private { bool read; bool no_send_addr; bool no_send_stop; + bool initted; u32 offset; u32 segment; @@ -331,6 +332,10 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, } mutex_lock(&aux->mutex); + if (!aux->initted) { + ret = -EIO; + goto exit; + } dp_aux_update_offset_and_segment(aux, msg); dp_aux_transfer_helper(aux, msg, true); @@ -380,6 +385,8 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, } aux->cmd_busy = false; + +exit: mutex_unlock(&aux->mutex); return ret; @@ -431,8 +438,13 @@ void dp_aux_init(struct drm_dp_aux *dp_aux) aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + mutex_lock(&aux->mutex); + dp_catalog_aux_enable(aux->catalog, true); aux->retry_cnt = 0; + aux->initted = true; + + mutex_unlock(&aux->mutex); } void dp_aux_deinit(struct drm_dp_aux *dp_aux) @@ -441,7 +453,12 @@ void dp_aux_deinit(struct drm_dp_aux *dp_aux) aux = container_of(dp_aux, struct dp_aux_private, dp_aux); + mutex_lock(&aux->mutex); + + aux->initted = false; dp_catalog_aux_enable(aux->catalog, false); + + mutex_unlock(&aux->mutex); } int dp_aux_register(struct drm_dp_aux *dp_aux) diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index f69a125f9559..0afc3b756f92 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1658,6 +1658,8 @@ static int dsi_host_parse_lane_data(struct msm_dsi_host *msm_host, if (!prop) { DRM_DEV_DEBUG(dev, "failed to find data lane mapping, using default\n"); + /* Set the number of date lanes to 4 by default. */ + msm_host->num_data_lanes = 4; return 0; } diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index 09d2d279c30a..dee13fedee3b 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -77,6 +77,7 @@ static int msm_gpu_open(struct inode *inode, struct file *file) goto free_priv; pm_runtime_get_sync(&gpu->pdev->dev); + msm_gpu_hw_init(gpu); show_priv->state = gpu->funcs->gpu_state_get(gpu); pm_runtime_put_sync(&gpu->pdev->dev); diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 7936e8d498dd..892c04365239 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -967,29 +967,18 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data, return ret; } -static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, - struct drm_file *file) +static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id, + ktime_t timeout) { - struct msm_drm_private *priv = dev->dev_private; - struct drm_msm_wait_fence *args = data; - ktime_t timeout = to_ktime(args->timeout); - struct msm_gpu_submitqueue *queue; - struct msm_gpu *gpu = priv->gpu; struct dma_fence *fence; int ret; - if (args->pad) { - DRM_ERROR("invalid pad: %08x\n", args->pad); + if (fence_id > queue->last_fence) { + DRM_ERROR_RATELIMITED("waiting on invalid fence: %u (of %u)\n", + fence_id, queue->last_fence); return -EINVAL; } - if (!gpu) - return 0; - - queue = msm_submitqueue_get(file->driver_priv, args->queueid); - if (!queue) - return -ENOENT; - /* * Map submitqueue scoped "seqno" (which is actually an idr key) * back to underlying dma-fence @@ -1001,7 +990,7 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, ret = mutex_lock_interruptible(&queue->lock); if (ret) return ret; - fence = idr_find(&queue->fence_idr, args->fence); + fence = idr_find(&queue->fence_idr, fence_id); if (fence) fence = dma_fence_get_rcu(fence); mutex_unlock(&queue->lock); @@ -1017,6 +1006,32 @@ static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, } dma_fence_put(fence); + + return ret; +} + +static int msm_ioctl_wait_fence(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct msm_drm_private *priv = dev->dev_private; + struct drm_msm_wait_fence *args = data; + struct msm_gpu_submitqueue *queue; + int ret; + + if (args->pad) { + DRM_ERROR("invalid pad: %08x\n", args->pad); + return -EINVAL; + } + + if (!priv->gpu) + return 0; + + queue = msm_submitqueue_get(file->driver_priv, args->queueid); + if (!queue) + return -ENOENT; + + ret = wait_fence(queue, args->fence, to_ktime(args->timeout)); + msm_submitqueue_put(queue); return ret; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 104fdfc14027..512d55eecbaf 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -1056,8 +1056,7 @@ static int msm_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct { struct msm_gem_object *msm_obj = to_msm_bo(obj); - vma->vm_flags &= ~VM_PFNMAP; - vma->vm_flags |= VM_MIXEDMAP | VM_DONTEXPAND; + vma->vm_flags |= VM_IO | VM_MIXEDMAP | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_page_prot = msm_gem_pgprot(msm_obj, vm_get_page_prot(vma->vm_flags)); return 0; @@ -1121,7 +1120,7 @@ static int msm_gem_new_impl(struct drm_device *dev, break; fallthrough; default: - DRM_DEV_ERROR(dev->dev, "invalid cache flag: %x\n", + DRM_DEV_DEBUG(dev->dev, "invalid cache flag: %x\n", (flags & MSM_BO_CACHE_MASK)); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 4a1420b05e97..086dacf2f26a 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -5,6 +5,7 @@ */ #include <linux/vmalloc.h> +#include <linux/sched/mm.h> #include "msm_drv.h" #include "msm_gem.h" diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 3cb029f10925..282628d6b72c 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -772,6 +772,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, args->nr_cmds); if (IS_ERR(submit)) { ret = PTR_ERR(submit); + submit = NULL; goto out_unlock; } @@ -904,6 +905,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, drm_sched_entity_push_job(&submit->base); args->fence = submit->fence_id; + queue->last_fence = submit->fence_id; msm_reset_syncobjs(syncobjs_to_reset, args->nr_in_syncobjs); msm_process_post_deps(post_deps, args->nr_out_syncobjs, diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 59cdd00b69d0..48ea2de911f1 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -359,6 +359,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio, * @ring_nr: the ringbuffer used by this submitqueue, which is determined * by the submitqueue's priority * @faults: the number of GPU hangs associated with this submitqueue + * @last_fence: the sequence number of the last allocated fence (for error + * checking) * @ctx: the per-drm_file context associated with the submitqueue (ie. * which set of pgtables do submits jobs associated with the * submitqueue use) @@ -374,6 +376,7 @@ struct msm_gpu_submitqueue { u32 flags; u32 ring_nr; int faults; + uint32_t last_fence; struct msm_file_private *ctx; struct list_head node; struct idr fence_idr; diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index 8b7473f69cb8..384e90c4b2a7 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -20,6 +20,10 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, struct msm_gpu *gpu = dev_to_gpu(dev); struct dev_pm_opp *opp; + /* + * Note that devfreq_recommended_opp() can modify the freq + * to something that actually is in the opp table: + */ opp = devfreq_recommended_opp(dev, freq, flags); /* @@ -28,6 +32,7 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, */ if (gpu->devfreq.idle_freq) { gpu->devfreq.idle_freq = *freq; + dev_pm_opp_put(opp); return 0; } @@ -203,9 +208,6 @@ static void msm_devfreq_idle_work(struct kthread_work *work) struct msm_gpu *gpu = container_of(df, struct msm_gpu, devfreq); unsigned long idle_freq, target_freq = 0; - if (!df->devfreq) - return; - /* * Hold devfreq lock to synchronize with get_dev_status()/ * target() callbacks @@ -227,6 +229,9 @@ void msm_devfreq_idle(struct msm_gpu *gpu) { struct msm_gpu_devfreq *df = &gpu->devfreq; + if (!df->devfreq) + return; + msm_hrtimer_queue_work(&df->idle_work, ms_to_ktime(1), - HRTIMER_MODE_ABS); + HRTIMER_MODE_REL); } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 739f11c0109c..047adc42d9a0 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -1103,7 +1103,7 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, * as an indication that we're about to swap out. */ memset(&place, 0, sizeof(place)); - place.mem_type = TTM_PL_SYSTEM; + place.mem_type = bo->resource->mem_type; if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL)) return -EBUSY; @@ -1135,6 +1135,7 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, struct ttm_place hop; memset(&hop, 0, sizeof(hop)); + place.mem_type = TTM_PL_SYSTEM; ret = ttm_resource_alloc(bo, &place, &evict_mem); if (unlikely(ret)) goto out; diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 7e83c00a3f48..79c870a3bef8 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -34,6 +34,7 @@ #include <linux/sched.h> #include <linux/shmem_fs.h> #include <linux/file.h> +#include <linux/module.h> #include <drm/drm_cache.h> #include <drm/ttm/ttm_bo_driver.h> diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index f0b3e4cf5bce..b61792d2aa65 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -337,10 +337,10 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state) struct drm_device *dev = state->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); struct vc4_hvs *hvs = vc4->hvs; - struct drm_crtc_state *old_crtc_state; struct drm_crtc_state *new_crtc_state; struct drm_crtc *crtc; struct vc4_hvs_state *old_hvs_state; + unsigned int channel; int i; for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) { @@ -353,30 +353,32 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state) vc4_hvs_mask_underrun(dev, vc4_crtc_state->assigned_channel); } - if (vc4->hvs->hvs5) - clk_set_min_rate(hvs->core_clk, 500000000); - old_hvs_state = vc4_hvs_get_old_global_state(state); - if (!old_hvs_state) + if (IS_ERR(old_hvs_state)) return; - for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) { - struct vc4_crtc_state *vc4_crtc_state = - to_vc4_crtc_state(old_crtc_state); - unsigned int channel = vc4_crtc_state->assigned_channel; + for (channel = 0; channel < HVS_NUM_CHANNELS; channel++) { + struct drm_crtc_commit *commit; int ret; - if (channel == VC4_HVS_CHANNEL_DISABLED) + if (!old_hvs_state->fifo_state[channel].in_use) continue; - if (!old_hvs_state->fifo_state[channel].in_use) + commit = old_hvs_state->fifo_state[channel].pending_commit; + if (!commit) continue; - ret = drm_crtc_commit_wait(old_hvs_state->fifo_state[channel].pending_commit); + ret = drm_crtc_commit_wait(commit); if (ret) drm_err(dev, "Timed out waiting for commit\n"); + + drm_crtc_commit_put(commit); + old_hvs_state->fifo_state[channel].pending_commit = NULL; } + if (vc4->hvs->hvs5) + clk_set_min_rate(hvs->core_clk, 500000000); + drm_atomic_helper_commit_modeset_disables(dev, state); vc4_ctm_commit(vc4, state); @@ -410,8 +412,8 @@ static int vc4_atomic_commit_setup(struct drm_atomic_state *state) unsigned int i; hvs_state = vc4_hvs_get_new_global_state(state); - if (!hvs_state) - return -EINVAL; + if (WARN_ON(IS_ERR(hvs_state))) + return PTR_ERR(hvs_state); for_each_new_crtc_in_state(state, crtc, crtc_state, i) { struct vc4_crtc_state *vc4_crtc_state = @@ -668,12 +670,6 @@ vc4_hvs_channels_duplicate_state(struct drm_private_obj *obj) for (i = 0; i < HVS_NUM_CHANNELS; i++) { state->fifo_state[i].in_use = old_state->fifo_state[i].in_use; - - if (!old_state->fifo_state[i].pending_commit) - continue; - - state->fifo_state[i].pending_commit = - drm_crtc_commit_get(old_state->fifo_state[i].pending_commit); } return &state->base; @@ -762,8 +758,8 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev, unsigned int i; hvs_new_state = vc4_hvs_get_global_state(state); - if (!hvs_new_state) - return -EINVAL; + if (IS_ERR(hvs_new_state)) + return PTR_ERR(hvs_new_state); for (i = 0; i < ARRAY_SIZE(hvs_new_state->fifo_state); i++) if (!hvs_new_state->fifo_state[i].in_use) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index d86e1ad4a972..5072dbb0669a 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -157,36 +157,6 @@ static void virtio_gpu_config_changed(struct virtio_device *vdev) schedule_work(&vgdev->config_changed_work); } -static __poll_t virtio_gpu_poll(struct file *filp, - struct poll_table_struct *wait) -{ - struct drm_file *drm_file = filp->private_data; - struct virtio_gpu_fpriv *vfpriv = drm_file->driver_priv; - struct drm_device *dev = drm_file->minor->dev; - struct virtio_gpu_device *vgdev = dev->dev_private; - struct drm_pending_event *e = NULL; - __poll_t mask = 0; - - if (!vgdev->has_virgl_3d || !vfpriv || !vfpriv->ring_idx_mask) - return drm_poll(filp, wait); - - poll_wait(filp, &drm_file->event_wait, wait); - - if (!list_empty(&drm_file->event_list)) { - spin_lock_irq(&dev->event_lock); - e = list_first_entry(&drm_file->event_list, - struct drm_pending_event, link); - drm_file->event_space += e->event->length; - list_del(&e->link); - spin_unlock_irq(&dev->event_lock); - - kfree(e); - mask |= EPOLLIN | EPOLLRDNORM; - } - - return mask; -} - static struct virtio_device_id id_table[] = { { VIRTIO_ID_GPU, VIRTIO_DEV_ANY_ID }, { 0 }, @@ -226,17 +196,7 @@ MODULE_AUTHOR("Dave Airlie <airlied@redhat.com>"); MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>"); MODULE_AUTHOR("Alon Levy"); -static const struct file_operations virtio_gpu_driver_fops = { - .owner = THIS_MODULE, - .open = drm_open, - .release = drm_release, - .unlocked_ioctl = drm_ioctl, - .compat_ioctl = drm_compat_ioctl, - .poll = virtio_gpu_poll, - .read = drm_read, - .llseek = noop_llseek, - .mmap = drm_gem_mmap -}; +DEFINE_DRM_GEM_FOPS(virtio_gpu_driver_fops); static const struct drm_driver driver = { .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_RENDER | DRIVER_ATOMIC, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index e0265fe74aa5..0a194aaad419 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -138,7 +138,6 @@ struct virtio_gpu_fence_driver { spinlock_t lock; }; -#define VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL 0x10000000 struct virtio_gpu_fence_event { struct drm_pending_event base; struct drm_event event; diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 5618a1d5879c..3607646d3229 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -54,7 +54,7 @@ static int virtio_gpu_fence_event_create(struct drm_device *dev, if (!e) return -ENOMEM; - e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED_INTERNAL; + e->event.type = VIRTGPU_EVENT_FENCE_SIGNALED; e->event.length = sizeof(e->event); ret = drm_event_reserve_init(dev, file, &e->base, &e->event); diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 9f5435b55949..a7c78ac96270 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -207,14 +207,14 @@ config HID_CHERRY config HID_CHICONY tristate "Chicony devices" - depends on HID + depends on USB_HID default !EXPERT help Support for Chicony Tactical pad and special keys on Chicony keyboards. config HID_CORSAIR tristate "Corsair devices" - depends on HID && USB && LEDS_CLASS + depends on USB_HID && LEDS_CLASS help Support for Corsair devices that are not fully compliant with the HID standard. @@ -245,7 +245,7 @@ config HID_MACALLY config HID_PRODIKEYS tristate "Prodikeys PC-MIDI Keyboard support" - depends on HID && SND + depends on USB_HID && SND select SND_RAWMIDI help Support for Prodikeys PC-MIDI Keyboard device support. @@ -560,7 +560,7 @@ config HID_LENOVO config HID_LOGITECH tristate "Logitech devices" - depends on HID + depends on USB_HID depends on LEDS_CLASS default !EXPERT help @@ -951,7 +951,7 @@ config HID_SAITEK config HID_SAMSUNG tristate "Samsung InfraRed remote control or keyboards" - depends on HID + depends on USB_HID help Support for Samsung InfraRed remote control or keyboards. diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index f3ecddc519ee..08c9a9a60ae4 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1028,8 +1028,7 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id) if (drvdata->quirks & QUIRK_IS_MULTITOUCH) drvdata->tp = &asus_i2c_tp; - if ((drvdata->quirks & QUIRK_T100_KEYBOARD) && - hid_is_using_ll_driver(hdev, &usb_hid_driver)) { + if ((drvdata->quirks & QUIRK_T100_KEYBOARD) && hid_is_usb(hdev)) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); if (intf->altsetting->desc.bInterfaceNumber == T100_TPAD_INTF) { @@ -1057,8 +1056,7 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id) drvdata->tp = &asus_t100chi_tp; } - if ((drvdata->quirks & QUIRK_MEDION_E1239T) && - hid_is_using_ll_driver(hdev, &usb_hid_driver)) { + if ((drvdata->quirks & QUIRK_MEDION_E1239T) && hid_is_usb(hdev)) { struct usb_host_interface *alt = to_usb_interface(hdev->dev.parent)->altsetting; diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index db6da21ade06..74ad8bf98bfd 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -191,7 +191,7 @@ static void bigben_worker(struct work_struct *work) struct bigben_device, worker); struct hid_field *report_field = bigben->report->field[0]; - if (bigben->removed) + if (bigben->removed || !report_field) return; if (bigben->work_led) { diff --git a/drivers/hid/hid-chicony.c b/drivers/hid/hid-chicony.c index ca556d39da2a..f04d2aa23efe 100644 --- a/drivers/hid/hid-chicony.c +++ b/drivers/hid/hid-chicony.c @@ -114,6 +114,9 @@ static int ch_probe(struct hid_device *hdev, const struct hid_device_id *id) { int ret; + if (!hid_is_usb(hdev)) + return -EINVAL; + hdev->quirks |= HID_QUIRK_INPUT_PER_APP; ret = hid_parse(hdev); if (ret) { diff --git a/drivers/hid/hid-corsair.c b/drivers/hid/hid-corsair.c index 902a60e249ed..8c895c820b67 100644 --- a/drivers/hid/hid-corsair.c +++ b/drivers/hid/hid-corsair.c @@ -553,7 +553,12 @@ static int corsair_probe(struct hid_device *dev, const struct hid_device_id *id) int ret; unsigned long quirks = id->driver_data; struct corsair_drvdata *drvdata; - struct usb_interface *usbif = to_usb_interface(dev->dev.parent); + struct usb_interface *usbif; + + if (!hid_is_usb(dev)) + return -EINVAL; + + usbif = to_usb_interface(dev->dev.parent); drvdata = devm_kzalloc(&dev->dev, sizeof(struct corsair_drvdata), GFP_KERNEL); diff --git a/drivers/hid/hid-elan.c b/drivers/hid/hid-elan.c index 021049805bb7..3091355d48df 100644 --- a/drivers/hid/hid-elan.c +++ b/drivers/hid/hid-elan.c @@ -50,7 +50,7 @@ struct elan_drvdata { static int is_not_elan_touchpad(struct hid_device *hdev) { - if (hdev->bus == BUS_USB) { + if (hid_is_usb(hdev)) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); return (intf->altsetting->desc.bInterfaceNumber != diff --git a/drivers/hid/hid-elo.c b/drivers/hid/hid-elo.c index 383dfda8c12f..8e960d7b233b 100644 --- a/drivers/hid/hid-elo.c +++ b/drivers/hid/hid-elo.c @@ -230,6 +230,9 @@ static int elo_probe(struct hid_device *hdev, const struct hid_device_id *id) int ret; struct usb_device *udev; + if (!hid_is_usb(hdev)) + return -EINVAL; + priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c index 8ee77f4afe9f..79505c64dbfe 100644 --- a/drivers/hid/hid-ft260.c +++ b/drivers/hid/hid-ft260.c @@ -915,6 +915,9 @@ static int ft260_probe(struct hid_device *hdev, const struct hid_device_id *id) struct ft260_get_chip_version_report version; int ret; + if (!hid_is_usb(hdev)) + return -EINVAL; + dev = devm_kzalloc(&hdev->dev, sizeof(*dev), GFP_KERNEL); if (!dev) return -ENOMEM; diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index 8123b871a3eb..0403beb3104b 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -586,6 +586,8 @@ static const struct hid_device_id hammer_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_DON) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_EEL) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) }, diff --git a/drivers/hid/hid-holtek-kbd.c b/drivers/hid/hid-holtek-kbd.c index 0a38e8e9bc78..403506b9697e 100644 --- a/drivers/hid/hid-holtek-kbd.c +++ b/drivers/hid/hid-holtek-kbd.c @@ -140,12 +140,17 @@ static int holtek_kbd_input_event(struct input_dev *dev, unsigned int type, static int holtek_kbd_probe(struct hid_device *hdev, const struct hid_device_id *id) { - struct usb_interface *intf = to_usb_interface(hdev->dev.parent); - int ret = hid_parse(hdev); + struct usb_interface *intf; + int ret; + + if (!hid_is_usb(hdev)) + return -EINVAL; + ret = hid_parse(hdev); if (!ret) ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); + intf = to_usb_interface(hdev->dev.parent); if (!ret && intf->cur_altsetting->desc.bInterfaceNumber == 1) { struct hid_input *hidinput; list_for_each_entry(hidinput, &hdev->inputs, list) { diff --git a/drivers/hid/hid-holtek-mouse.c b/drivers/hid/hid-holtek-mouse.c index 195b735b001d..b7172c48ef9f 100644 --- a/drivers/hid/hid-holtek-mouse.c +++ b/drivers/hid/hid-holtek-mouse.c @@ -62,6 +62,14 @@ static __u8 *holtek_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc, return rdesc; } +static int holtek_mouse_probe(struct hid_device *hdev, + const struct hid_device_id *id) +{ + if (!hid_is_usb(hdev)) + return -EINVAL; + return 0; +} + static const struct hid_device_id holtek_mouse_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067) }, @@ -83,6 +91,7 @@ static struct hid_driver holtek_mouse_driver = { .name = "holtek_mouse", .id_table = holtek_mouse_devices, .report_fixup = holtek_mouse_report_fixup, + .probe = holtek_mouse_probe, }; module_hid_driver(holtek_mouse_driver); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 96a455921c67..19da07777d62 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -399,6 +399,7 @@ #define USB_DEVICE_ID_HP_X2_10_COVER 0x0755 #define I2C_DEVICE_ID_HP_ENVY_X360_15 0x2d05 #define I2C_DEVICE_ID_HP_SPECTRE_X360_15 0x2817 +#define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN 0x2544 #define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706 #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A @@ -501,6 +502,7 @@ #define USB_DEVICE_ID_GOOGLE_MAGNEMITE 0x503d #define USB_DEVICE_ID_GOOGLE_MOONBALL 0x5044 #define USB_DEVICE_ID_GOOGLE_DON 0x5050 +#define USB_DEVICE_ID_GOOGLE_EEL 0x5057 #define USB_VENDOR_ID_GOTOP 0x08f2 #define USB_DEVICE_ID_SUPER_Q2 0x007f @@ -886,6 +888,7 @@ #define USB_DEVICE_ID_MS_TOUCH_COVER_2 0x07a7 #define USB_DEVICE_ID_MS_TYPE_COVER_2 0x07a9 #define USB_DEVICE_ID_MS_POWER_COVER 0x07da +#define USB_DEVICE_ID_MS_SURFACE3_COVER 0x07de #define USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER 0x02fd #define USB_DEVICE_ID_MS_PIXART_MOUSE 0x00cb #define USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS 0x02e0 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 217f2d1b91c5..03f994541981 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -325,6 +325,8 @@ static const struct hid_device_id hid_battery_quirks[] = { HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN), + HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15), diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c index d40af911df63..fb3f7258009c 100644 --- a/drivers/hid/hid-lg.c +++ b/drivers/hid/hid-lg.c @@ -749,12 +749,18 @@ static int lg_raw_event(struct hid_device *hdev, struct hid_report *report, static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id) { - struct usb_interface *iface = to_usb_interface(hdev->dev.parent); - __u8 iface_num = iface->cur_altsetting->desc.bInterfaceNumber; + struct usb_interface *iface; + __u8 iface_num; unsigned int connect_mask = HID_CONNECT_DEFAULT; struct lg_drv_data *drv_data; int ret; + if (!hid_is_usb(hdev)) + return -EINVAL; + + iface = to_usb_interface(hdev->dev.parent); + iface_num = iface->cur_altsetting->desc.bInterfaceNumber; + /* G29 only work with the 1st interface */ if ((hdev->product == USB_DEVICE_ID_LOGITECH_G29_WHEEL) && (iface_num != 0)) { diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index a0017b010c34..7106b921b53c 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1777,7 +1777,7 @@ static int logi_dj_probe(struct hid_device *hdev, case recvr_type_bluetooth: no_dj_interfaces = 2; break; case recvr_type_dinovo: no_dj_interfaces = 2; break; } - if (hid_is_using_ll_driver(hdev, &usb_hid_driver)) { + if (hid_is_usb(hdev)) { intf = to_usb_interface(hdev->dev.parent); if (intf && intf->altsetting->desc.bInterfaceNumber >= no_dj_interfaces) { diff --git a/drivers/hid/hid-prodikeys.c b/drivers/hid/hid-prodikeys.c index 2666af02d5c1..e4e9471d0f1e 100644 --- a/drivers/hid/hid-prodikeys.c +++ b/drivers/hid/hid-prodikeys.c @@ -798,12 +798,18 @@ static int pk_raw_event(struct hid_device *hdev, struct hid_report *report, static int pk_probe(struct hid_device *hdev, const struct hid_device_id *id) { int ret; - struct usb_interface *intf = to_usb_interface(hdev->dev.parent); - unsigned short ifnum = intf->cur_altsetting->desc.bInterfaceNumber; + struct usb_interface *intf; + unsigned short ifnum; unsigned long quirks = id->driver_data; struct pk_device *pk; struct pcmidi_snd *pm = NULL; + if (!hid_is_usb(hdev)) + return -EINVAL; + + intf = to_usb_interface(hdev->dev.parent); + ifnum = intf->cur_altsetting->desc.bInterfaceNumber; + pk = kzalloc(sizeof(*pk), GFP_KERNEL); if (pk == NULL) { hid_err(hdev, "can't alloc descriptor\n"); diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 06b7908c874c..ee7e504e7279 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -124,6 +124,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_MCS, USB_DEVICE_ID_MCS_GAMEPADBLOCK), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PIXART_MOUSE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE3_COVER), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE_PRO_2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2), HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hid/hid-roccat-arvo.c b/drivers/hid/hid-roccat-arvo.c index 4556d2a50f75..d94ee0539421 100644 --- a/drivers/hid/hid-roccat-arvo.c +++ b/drivers/hid/hid-roccat-arvo.c @@ -344,6 +344,9 @@ static int arvo_probe(struct hid_device *hdev, { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-roccat-isku.c b/drivers/hid/hid-roccat-isku.c index ce5f22519956..e95d59cd8d07 100644 --- a/drivers/hid/hid-roccat-isku.c +++ b/drivers/hid/hid-roccat-isku.c @@ -324,6 +324,9 @@ static int isku_probe(struct hid_device *hdev, { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-roccat-kone.c b/drivers/hid/hid-roccat-kone.c index ea17abc7ad52..76da04801ca9 100644 --- a/drivers/hid/hid-roccat-kone.c +++ b/drivers/hid/hid-roccat-kone.c @@ -749,6 +749,9 @@ static int kone_probe(struct hid_device *hdev, const struct hid_device_id *id) { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-roccat-koneplus.c b/drivers/hid/hid-roccat-koneplus.c index 0316edf8c5bb..1896c69ea512 100644 --- a/drivers/hid/hid-roccat-koneplus.c +++ b/drivers/hid/hid-roccat-koneplus.c @@ -431,6 +431,9 @@ static int koneplus_probe(struct hid_device *hdev, { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-roccat-konepure.c b/drivers/hid/hid-roccat-konepure.c index 5248b3c7cf78..cf8eeb33a125 100644 --- a/drivers/hid/hid-roccat-konepure.c +++ b/drivers/hid/hid-roccat-konepure.c @@ -133,6 +133,9 @@ static int konepure_probe(struct hid_device *hdev, { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-roccat-kovaplus.c b/drivers/hid/hid-roccat-kovaplus.c index 960012881570..6fb9b9563769 100644 --- a/drivers/hid/hid-roccat-kovaplus.c +++ b/drivers/hid/hid-roccat-kovaplus.c @@ -501,6 +501,9 @@ static int kovaplus_probe(struct hid_device *hdev, { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-roccat-lua.c b/drivers/hid/hid-roccat-lua.c index 4a88a76d5c62..d5ddf0d68346 100644 --- a/drivers/hid/hid-roccat-lua.c +++ b/drivers/hid/hid-roccat-lua.c @@ -160,6 +160,9 @@ static int lua_probe(struct hid_device *hdev, { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-roccat-pyra.c b/drivers/hid/hid-roccat-pyra.c index 989927defe8d..4fcc8e7d276f 100644 --- a/drivers/hid/hid-roccat-pyra.c +++ b/drivers/hid/hid-roccat-pyra.c @@ -449,6 +449,9 @@ static int pyra_probe(struct hid_device *hdev, const struct hid_device_id *id) { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-roccat-ryos.c b/drivers/hid/hid-roccat-ryos.c index 3956a6c9c521..5bf1971a2b14 100644 --- a/drivers/hid/hid-roccat-ryos.c +++ b/drivers/hid/hid-roccat-ryos.c @@ -141,6 +141,9 @@ static int ryos_probe(struct hid_device *hdev, { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-roccat-savu.c b/drivers/hid/hid-roccat-savu.c index 818701f7a028..a784bb4ee651 100644 --- a/drivers/hid/hid-roccat-savu.c +++ b/drivers/hid/hid-roccat-savu.c @@ -113,6 +113,9 @@ static int savu_probe(struct hid_device *hdev, { int retval; + if (!hid_is_usb(hdev)) + return -EINVAL; + retval = hid_parse(hdev); if (retval) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-samsung.c b/drivers/hid/hid-samsung.c index 2e1c31156eca..cf5992e97094 100644 --- a/drivers/hid/hid-samsung.c +++ b/drivers/hid/hid-samsung.c @@ -152,6 +152,9 @@ static int samsung_probe(struct hid_device *hdev, int ret; unsigned int cmask = HID_CONNECT_DEFAULT; + if (!hid_is_usb(hdev)) + return -EINVAL; + ret = hid_parse(hdev); if (ret) { hid_err(hdev, "parse failed\n"); diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c index d1b107d547f5..60ec2b29d54d 100644 --- a/drivers/hid/hid-sony.c +++ b/drivers/hid/hid-sony.c @@ -3000,7 +3000,6 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) sc->quirks = quirks; hid_set_drvdata(hdev, sc); sc->hdev = hdev; - usbdev = to_usb_device(sc->hdev->dev.parent->parent); ret = hid_parse(hdev); if (ret) { @@ -3038,14 +3037,23 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) */ if (!(hdev->claimed & HID_CLAIMED_INPUT)) { hid_err(hdev, "failed to claim input\n"); - hid_hw_stop(hdev); - return -ENODEV; + ret = -ENODEV; + goto err; } if (sc->quirks & (GHL_GUITAR_PS3WIIU | GHL_GUITAR_PS4)) { + if (!hid_is_usb(hdev)) { + ret = -EINVAL; + goto err; + } + + usbdev = to_usb_device(sc->hdev->dev.parent->parent); + sc->ghl_urb = usb_alloc_urb(0, GFP_ATOMIC); - if (!sc->ghl_urb) - return -ENOMEM; + if (!sc->ghl_urb) { + ret = -ENOMEM; + goto err; + } if (sc->quirks & GHL_GUITAR_PS3WIIU) ret = ghl_init_urb(sc, usbdev, ghl_ps3wiiu_magic_data, @@ -3055,7 +3063,7 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) ARRAY_SIZE(ghl_ps4_magic_data)); if (ret) { hid_err(hdev, "error preparing URB\n"); - return ret; + goto err; } timer_setup(&sc->ghl_poke_timer, ghl_magic_poke, 0); @@ -3064,6 +3072,10 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id) } return ret; + +err: + hid_hw_stop(hdev); + return ret; } static void sony_remove(struct hid_device *hdev) diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c index 3a5333424aa3..03b935ff02d5 100644 --- a/drivers/hid/hid-thrustmaster.c +++ b/drivers/hid/hid-thrustmaster.c @@ -274,6 +274,9 @@ static int thrustmaster_probe(struct hid_device *hdev, const struct hid_device_i int ret = 0; struct tm_wheel *tm_wheel = NULL; + if (!hid_is_usb(hdev)) + return -EINVAL; + ret = hid_parse(hdev); if (ret) { hid_err(hdev, "parse failed with error %d\n", ret); diff --git a/drivers/hid/hid-u2fzero.c b/drivers/hid/hid-u2fzero.c index 31ea7fc69916..ad489caf53ad 100644 --- a/drivers/hid/hid-u2fzero.c +++ b/drivers/hid/hid-u2fzero.c @@ -311,7 +311,7 @@ static int u2fzero_probe(struct hid_device *hdev, unsigned int minor; int ret; - if (!hid_is_using_ll_driver(hdev, &usb_hid_driver)) + if (!hid_is_usb(hdev)) return -EINVAL; dev = devm_kzalloc(&hdev->dev, sizeof(*dev), GFP_KERNEL); diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 6a9865dd703c..d8ab0139e5cd 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -164,6 +164,9 @@ static int uclogic_probe(struct hid_device *hdev, struct uclogic_drvdata *drvdata = NULL; bool params_initialized = false; + if (!hid_is_usb(hdev)) + return -EINVAL; + /* * libinput requires the pad interface to be on a different node * than the pen, so use QUIRK_MULTI_INPUT for all tablets. diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 3d67b748a3b9..adff1bd68d9f 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -843,8 +843,7 @@ int uclogic_params_init(struct uclogic_params *params, struct uclogic_params p = {0, }; /* Check arguments */ - if (params == NULL || hdev == NULL || - !hid_is_using_ll_driver(hdev, &usb_hid_driver)) { + if (params == NULL || hdev == NULL || !hid_is_usb(hdev)) { rc = -EINVAL; goto cleanup; } diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 1c5039081db2..8e9d9450cb83 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -266,7 +266,8 @@ static void __maybe_unused ish_resume_handler(struct work_struct *work) if (ish_should_leave_d0i3(pdev) && !dev->suspend_flag && IPC_IS_ISH_ILUP(fwsts)) { - disable_irq_wake(pdev->irq); + if (device_may_wakeup(&pdev->dev)) + disable_irq_wake(pdev->irq); ish_set_host_ready(dev); @@ -337,7 +338,8 @@ static int __maybe_unused ish_suspend(struct device *device) */ pci_save_state(pdev); - enable_irq_wake(pdev->irq); + if (device_may_wakeup(&pdev->dev)) + enable_irq_wake(pdev->irq); } } else { /* diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 2717d39600b4..066c567dbaa2 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -726,7 +726,7 @@ static void wacom_retrieve_hid_descriptor(struct hid_device *hdev, * Skip the query for this type and modify defaults based on * interface number. */ - if (features->type == WIRELESS) { + if (features->type == WIRELESS && intf) { if (intf->cur_altsetting->desc.bInterfaceNumber == 0) features->device_type = WACOM_DEVICETYPE_WL_MONITOR; else @@ -2214,7 +2214,7 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix) if ((features->type == HID_GENERIC) && !strcmp("Wacom HID", features->name)) { char *product_name = wacom->hdev->name; - if (hid_is_using_ll_driver(wacom->hdev, &usb_hid_driver)) { + if (hid_is_usb(wacom->hdev)) { struct usb_interface *intf = to_usb_interface(wacom->hdev->dev.parent); struct usb_device *dev = interface_to_usbdev(intf); product_name = dev->product; @@ -2451,6 +2451,9 @@ static void wacom_wireless_work(struct work_struct *work) wacom_destroy_battery(wacom); + if (!usbdev) + return; + /* Stylus interface */ hdev1 = usb_get_intfdata(usbdev->config->interface[1]); wacom1 = hid_get_drvdata(hdev1); @@ -2730,8 +2733,6 @@ static void wacom_mode_change_work(struct work_struct *work) static int wacom_probe(struct hid_device *hdev, const struct hid_device_id *id) { - struct usb_interface *intf = to_usb_interface(hdev->dev.parent); - struct usb_device *dev = interface_to_usbdev(intf); struct wacom *wacom; struct wacom_wac *wacom_wac; struct wacom_features *features; @@ -2766,8 +2767,14 @@ static int wacom_probe(struct hid_device *hdev, wacom_wac->hid_data.inputmode = -1; wacom_wac->mode_report = -1; - wacom->usbdev = dev; - wacom->intf = intf; + if (hid_is_usb(hdev)) { + struct usb_interface *intf = to_usb_interface(hdev->dev.parent); + struct usb_device *dev = interface_to_usbdev(intf); + + wacom->usbdev = dev; + wacom->intf = intf; + } + mutex_init(&wacom->lock); INIT_DELAYED_WORK(&wacom->init_work, wacom_init_work); INIT_WORK(&wacom->wireless_work, wacom_wireless_work); diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index dd12af20e467..0747a8f1fcee 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -19,6 +19,7 @@ config HYPERV_TIMER config HYPERV_UTILS tristate "Microsoft Hyper-V Utilities driver" depends on HYPERV && CONNECTOR && NLS + depends on PTP_1588_CLOCK_OPTIONAL help Select this option to enable the Hyper-V Utilities. diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c index 731d5117f9f1..14389fd7afb8 100644 --- a/drivers/hwmon/corsair-psu.c +++ b/drivers/hwmon/corsair-psu.c @@ -729,7 +729,7 @@ static int corsairpsu_probe(struct hid_device *hdev, const struct hid_device_id corsairpsu_check_cmd_support(priv); priv->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, "corsairpsu", priv, - &corsairpsu_chip_info, 0); + &corsairpsu_chip_info, NULL); if (IS_ERR(priv->hwmon_dev)) { ret = PTR_ERR(priv->hwmon_dev); diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index eaace478f508..5596c211f38d 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -627,10 +627,9 @@ static void __init i8k_init_procfs(struct device *dev) { struct dell_smm_data *data = dev_get_drvdata(dev); - /* Register the proc entry */ - proc_create_data("i8k", 0, NULL, &i8k_proc_ops, data); - - devm_add_action_or_reset(dev, i8k_exit_procfs, NULL); + /* Only register exit function if creation was successful */ + if (proc_create_data("i8k", 0, NULL, &i8k_proc_ops, data)) + devm_add_action_or_reset(dev, i8k_exit_procfs, NULL); } #else diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 93dca471972e..57ce8633a725 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -1527,7 +1527,7 @@ static u16 nct6775_wmi_read_value(struct nct6775_data *data, u16 reg) nct6775_wmi_set_bank(data, reg); - err = nct6775_asuswmi_read(data->bank, reg, &tmp); + err = nct6775_asuswmi_read(data->bank, reg & 0xff, &tmp); if (err) return 0; diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c index 17518b4cab1b..f12b9a28a232 100644 --- a/drivers/hwmon/pwm-fan.c +++ b/drivers/hwmon/pwm-fan.c @@ -336,8 +336,6 @@ static int pwm_fan_probe(struct platform_device *pdev) return ret; } - ctx->pwm_value = MAX_PWM; - pwm_init_state(ctx->pwm, &ctx->pwm_state); /* diff --git a/drivers/hwmon/sht4x.c b/drivers/hwmon/sht4x.c index 09c2a0b06444..3415d7a0e0fc 100644 --- a/drivers/hwmon/sht4x.c +++ b/drivers/hwmon/sht4x.c @@ -23,7 +23,7 @@ /* * I2C command delays (in microseconds) */ -#define SHT4X_MEAS_DELAY 1000 +#define SHT4X_MEAS_DELAY_HPM 8200 /* see t_MEAS,h in datasheet */ #define SHT4X_DELAY_EXTRA 10000 /* @@ -90,7 +90,7 @@ static int sht4x_read_values(struct sht4x_data *data) if (ret < 0) goto unlock; - usleep_range(SHT4X_MEAS_DELAY, SHT4X_MEAS_DELAY + SHT4X_DELAY_EXTRA); + usleep_range(SHT4X_MEAS_DELAY_HPM, SHT4X_MEAS_DELAY_HPM + SHT4X_DELAY_EXTRA); ret = i2c_master_recv(client, raw_data, SHT4X_RESPONSE_LENGTH); if (ret != SHT4X_RESPONSE_LENGTH) { diff --git a/drivers/i2c/busses/i2c-cbus-gpio.c b/drivers/i2c/busses/i2c-cbus-gpio.c index 72df563477b1..f8639a4457d2 100644 --- a/drivers/i2c/busses/i2c-cbus-gpio.c +++ b/drivers/i2c/busses/i2c-cbus-gpio.c @@ -195,8 +195,9 @@ static u32 cbus_i2c_func(struct i2c_adapter *adapter) } static const struct i2c_algorithm cbus_i2c_algo = { - .smbus_xfer = cbus_i2c_smbus_xfer, - .functionality = cbus_i2c_func, + .smbus_xfer = cbus_i2c_smbus_xfer, + .smbus_xfer_atomic = cbus_i2c_smbus_xfer, + .functionality = cbus_i2c_func, }; static int cbus_i2c_remove(struct platform_device *pdev) diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c index a6ea1eb1394e..53b8da6dbb23 100644 --- a/drivers/i2c/busses/i2c-mpc.c +++ b/drivers/i2c/busses/i2c-mpc.c @@ -636,7 +636,7 @@ static irqreturn_t mpc_i2c_isr(int irq, void *dev_id) status = readb(i2c->base + MPC_I2C_SR); if (status & CSR_MIF) { /* Wait up to 100us for transfer to properly complete */ - readb_poll_timeout(i2c->base + MPC_I2C_SR, status, !(status & CSR_MCF), 0, 100); + readb_poll_timeout_atomic(i2c->base + MPC_I2C_SR, status, status & CSR_MCF, 0, 100); writeb(0, i2c->base + MPC_I2C_SR); mpc_i2c_do_intr(i2c, status); return IRQ_HANDLED; diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index 819ab4ee517e..02ddb237f69a 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -423,8 +423,8 @@ static void rk3x_i2c_handle_read(struct rk3x_i2c *i2c, unsigned int ipd) if (!(ipd & REG_INT_MBRF)) return; - /* ack interrupt */ - i2c_writel(i2c, REG_INT_MBRF, REG_IPD); + /* ack interrupt (read also produces a spurious START flag, clear it too) */ + i2c_writel(i2c, REG_INT_MBRF | REG_INT_START, REG_IPD); /* Can only handle a maximum of 32 bytes at a time */ if (len > 32) diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index b9b19a2a2ffa..66145d2b9b55 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -1493,6 +1493,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) { struct stm32f7_i2c_dev *i2c_dev = data; struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg; + struct stm32_i2c_dma *dma = i2c_dev->dma; void __iomem *base = i2c_dev->base; u32 status, mask; int ret = IRQ_HANDLED; @@ -1518,6 +1519,10 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n", __func__, f7_msg->addr); writel_relaxed(STM32F7_I2C_ICR_NACKCF, base + STM32F7_I2C_ICR); + if (i2c_dev->use_dma) { + stm32f7_i2c_disable_dma_req(i2c_dev); + dmaengine_terminate_async(dma->chan_using); + } f7_msg->result = -ENXIO; } @@ -1533,7 +1538,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) /* Clear STOP flag */ writel_relaxed(STM32F7_I2C_ICR_STOPCF, base + STM32F7_I2C_ICR); - if (i2c_dev->use_dma) { + if (i2c_dev->use_dma && !f7_msg->result) { ret = IRQ_WAKE_THREAD; } else { i2c_dev->master_mode = false; @@ -1546,7 +1551,7 @@ static irqreturn_t stm32f7_i2c_isr_event(int irq, void *data) if (f7_msg->stop) { mask = STM32F7_I2C_CR2_STOP; stm32f7_i2c_set_bits(base + STM32F7_I2C_CR2, mask); - } else if (i2c_dev->use_dma) { + } else if (i2c_dev->use_dma && !f7_msg->result) { ret = IRQ_WAKE_THREAD; } else if (f7_msg->smbus) { stm32f7_i2c_smbus_rep_start(i2c_dev); @@ -1583,7 +1588,7 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) if (!ret) { dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__); stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_all(dma->chan_using); + dmaengine_terminate_async(dma->chan_using); f7_msg->result = -ETIMEDOUT; } @@ -1660,7 +1665,7 @@ static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data) /* Disable dma */ if (i2c_dev->use_dma) { stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_all(dma->chan_using); + dmaengine_terminate_async(dma->chan_using); } i2c_dev->master_mode = false; @@ -1696,12 +1701,26 @@ static int stm32f7_i2c_xfer(struct i2c_adapter *i2c_adap, time_left = wait_for_completion_timeout(&i2c_dev->complete, i2c_dev->adap.timeout); ret = f7_msg->result; + if (ret) { + if (i2c_dev->use_dma) + dmaengine_synchronize(dma->chan_using); + + /* + * It is possible that some unsent data have already been + * written into TXDR. To avoid sending old data in a + * further transfer, flush TXDR in case of any error + */ + writel_relaxed(STM32F7_I2C_ISR_TXE, + i2c_dev->base + STM32F7_I2C_ISR); + goto pm_free; + } if (!time_left) { dev_dbg(i2c_dev->dev, "Access to slave 0x%x timed out\n", i2c_dev->msg->addr); if (i2c_dev->use_dma) - dmaengine_terminate_all(dma->chan_using); + dmaengine_terminate_sync(dma->chan_using); + stm32f7_i2c_wait_free_bus(i2c_dev); ret = -ETIMEDOUT; } @@ -1744,13 +1763,25 @@ static int stm32f7_i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, timeout = wait_for_completion_timeout(&i2c_dev->complete, i2c_dev->adap.timeout); ret = f7_msg->result; - if (ret) + if (ret) { + if (i2c_dev->use_dma) + dmaengine_synchronize(dma->chan_using); + + /* + * It is possible that some unsent data have already been + * written into TXDR. To avoid sending old data in a + * further transfer, flush TXDR in case of any error + */ + writel_relaxed(STM32F7_I2C_ISR_TXE, + i2c_dev->base + STM32F7_I2C_ISR); goto pm_free; + } if (!timeout) { dev_dbg(dev, "Access to slave 0x%x timed out\n", f7_msg->addr); if (i2c_dev->use_dma) - dmaengine_terminate_all(dma->chan_using); + dmaengine_terminate_sync(dma->chan_using); + stm32f7_i2c_wait_free_bus(i2c_dev); ret = -ETIMEDOUT; goto pm_free; } diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c index 95378780da6d..41eb0dcc3204 100644 --- a/drivers/i2c/busses/i2c-virtio.c +++ b/drivers/i2c/busses/i2c-virtio.c @@ -22,24 +22,24 @@ /** * struct virtio_i2c - virtio I2C data * @vdev: virtio device for this controller - * @completion: completion of virtio I2C message * @adap: I2C adapter for this controller * @vq: the virtio virtqueue for communication */ struct virtio_i2c { struct virtio_device *vdev; - struct completion completion; struct i2c_adapter adap; struct virtqueue *vq; }; /** * struct virtio_i2c_req - the virtio I2C request structure + * @completion: completion of virtio I2C message * @out_hdr: the OUT header of the virtio I2C message * @buf: the buffer into which data is read, or from which it's written * @in_hdr: the IN header of the virtio I2C message */ struct virtio_i2c_req { + struct completion completion; struct virtio_i2c_out_hdr out_hdr ____cacheline_aligned; uint8_t *buf ____cacheline_aligned; struct virtio_i2c_in_hdr in_hdr ____cacheline_aligned; @@ -47,9 +47,11 @@ struct virtio_i2c_req { static void virtio_i2c_msg_done(struct virtqueue *vq) { - struct virtio_i2c *vi = vq->vdev->priv; + struct virtio_i2c_req *req; + unsigned int len; - complete(&vi->completion); + while ((req = virtqueue_get_buf(vq, &len))) + complete(&req->completion); } static int virtio_i2c_prepare_reqs(struct virtqueue *vq, @@ -62,6 +64,8 @@ static int virtio_i2c_prepare_reqs(struct virtqueue *vq, for (i = 0; i < num; i++) { int outcnt = 0, incnt = 0; + init_completion(&reqs[i].completion); + /* * Only 7-bit mode supported for this moment. For the address * format, Please check the Virtio I2C Specification. @@ -106,21 +110,15 @@ static int virtio_i2c_complete_reqs(struct virtqueue *vq, struct virtio_i2c_req *reqs, struct i2c_msg *msgs, int num) { - struct virtio_i2c_req *req; bool failed = false; - unsigned int len; int i, j = 0; for (i = 0; i < num; i++) { - /* Detach the ith request from the vq */ - req = virtqueue_get_buf(vq, &len); + struct virtio_i2c_req *req = &reqs[i]; - /* - * Condition req == &reqs[i] should always meet since we have - * total num requests in the vq. reqs[i] can never be NULL here. - */ - if (!failed && (WARN_ON(req != &reqs[i]) || - req->in_hdr.status != VIRTIO_I2C_MSG_OK)) + wait_for_completion(&req->completion); + + if (!failed && req->in_hdr.status != VIRTIO_I2C_MSG_OK) failed = true; i2c_put_dma_safe_msg_buf(reqs[i].buf, &msgs[i], !failed); @@ -156,12 +154,8 @@ static int virtio_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, * remote here to clear the virtqueue, so we can try another set of * messages later on. */ - - reinit_completion(&vi->completion); virtqueue_kick(vq); - wait_for_completion(&vi->completion); - count = virtio_i2c_complete_reqs(vq, reqs, msgs, count); err_free: @@ -210,8 +204,6 @@ static int virtio_i2c_probe(struct virtio_device *vdev) vdev->priv = vi; vi->vdev = vdev; - init_completion(&vi->completion); - ret = virtio_i2c_setup_vqs(vi); if (ret) return ret; diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index a51fdd3c9b5b..24c9387c2968 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -1595,8 +1595,7 @@ static int kxcjk1013_probe(struct i2c_client *client, return 0; err_buffer_cleanup: - if (data->dready_trig) - iio_triggered_buffer_cleanup(indio_dev); + iio_triggered_buffer_cleanup(indio_dev); err_trigger_unregister: if (data->dready_trig) iio_trigger_unregister(data->dready_trig); @@ -1618,8 +1617,8 @@ static int kxcjk1013_remove(struct i2c_client *client) pm_runtime_disable(&client->dev); pm_runtime_set_suspended(&client->dev); + iio_triggered_buffer_cleanup(indio_dev); if (data->dready_trig) { - iio_triggered_buffer_cleanup(indio_dev); iio_trigger_unregister(data->dready_trig); iio_trigger_unregister(data->motion_trig); } diff --git a/drivers/iio/accel/kxsd9.c b/drivers/iio/accel/kxsd9.c index 2faf85ca996e..552eba5e8b4f 100644 --- a/drivers/iio/accel/kxsd9.c +++ b/drivers/iio/accel/kxsd9.c @@ -224,14 +224,14 @@ static irqreturn_t kxsd9_trigger_handler(int irq, void *p) hw_values.chan, sizeof(hw_values.chan)); if (ret) { - dev_err(st->dev, - "error reading data\n"); - return ret; + dev_err(st->dev, "error reading data: %d\n", ret); + goto out; } iio_push_to_buffers_with_timestamp(indio_dev, &hw_values, iio_get_time_ns(indio_dev)); +out: iio_trigger_notify_done(indio_dev->trig); return IRQ_HANDLED; diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c index 715b8138fb71..09c7f10fefb6 100644 --- a/drivers/iio/accel/mma8452.c +++ b/drivers/iio/accel/mma8452.c @@ -1470,7 +1470,7 @@ static int mma8452_trigger_setup(struct iio_dev *indio_dev) if (ret) return ret; - indio_dev->trig = trig; + indio_dev->trig = iio_trigger_get(trig); return 0; } diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig index 8bf5b62a73f4..3363af15a43f 100644 --- a/drivers/iio/adc/Kconfig +++ b/drivers/iio/adc/Kconfig @@ -532,7 +532,7 @@ config IMX7D_ADC config IMX8QXP_ADC tristate "NXP IMX8QXP ADC driver" - depends on ARCH_MXC_ARM64 || COMPILE_TEST + depends on ARCH_MXC || COMPILE_TEST depends on HAS_IOMEM help Say yes here to build support for IMX8QXP ADC. diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index 2c5c8a3672b2..aa42ba759fa1 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -480,8 +480,8 @@ static irqreturn_t ad7768_trigger_handler(int irq, void *p) iio_push_to_buffers_with_timestamp(indio_dev, &st->data.scan, iio_get_time_ns(indio_dev)); - iio_trigger_notify_done(indio_dev->trig); err_unlock: + iio_trigger_notify_done(indio_dev->trig); mutex_unlock(&st->lock); return IRQ_HANDLED; diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index 4c922ef634f8..92a57cf10fba 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -1586,7 +1586,8 @@ static int at91_adc_read_info_raw(struct iio_dev *indio_dev, *val = st->conversion_value; ret = at91_adc_adjust_val_osr(st, val); if (chan->scan_type.sign == 's') - *val = sign_extend32(*val, 11); + *val = sign_extend32(*val, + chan->scan_type.realbits - 1); st->conversion_done = false; } diff --git a/drivers/iio/adc/axp20x_adc.c b/drivers/iio/adc/axp20x_adc.c index 3e0c0233b431..df99f1365c39 100644 --- a/drivers/iio/adc/axp20x_adc.c +++ b/drivers/iio/adc/axp20x_adc.c @@ -251,19 +251,8 @@ static int axp22x_adc_raw(struct iio_dev *indio_dev, struct iio_chan_spec const *chan, int *val) { struct axp20x_adc_iio *info = iio_priv(indio_dev); - int size; - /* - * N.B.: Unlike the Chinese datasheets tell, the charging current is - * stored on 12 bits, not 13 bits. Only discharging current is on 13 - * bits. - */ - if (chan->type == IIO_CURRENT && chan->channel == AXP22X_BATT_DISCHRG_I) - size = 13; - else - size = 12; - - *val = axp20x_read_variable_width(info->regmap, chan->address, size); + *val = axp20x_read_variable_width(info->regmap, chan->address, 12); if (*val < 0) return *val; @@ -386,9 +375,8 @@ static int axp22x_adc_scale(struct iio_chan_spec const *chan, int *val, return IIO_VAL_INT_PLUS_MICRO; case IIO_CURRENT: - *val = 0; - *val2 = 500000; - return IIO_VAL_INT_PLUS_MICRO; + *val = 1; + return IIO_VAL_INT; case IIO_TEMP: *val = 100; diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c index 16407664182c..97d162a3cba4 100644 --- a/drivers/iio/adc/dln2-adc.c +++ b/drivers/iio/adc/dln2-adc.c @@ -248,7 +248,6 @@ static int dln2_adc_set_chan_period(struct dln2_adc *dln2, static int dln2_adc_read(struct dln2_adc *dln2, unsigned int channel) { int ret, i; - struct iio_dev *indio_dev = platform_get_drvdata(dln2->pdev); u16 conflict; __le16 value; int olen = sizeof(value); @@ -257,13 +256,9 @@ static int dln2_adc_read(struct dln2_adc *dln2, unsigned int channel) .chan = channel, }; - ret = iio_device_claim_direct_mode(indio_dev); - if (ret < 0) - return ret; - ret = dln2_adc_set_chan_enabled(dln2, channel, true); if (ret < 0) - goto release_direct; + return ret; ret = dln2_adc_set_port_enabled(dln2, true, &conflict); if (ret < 0) { @@ -300,8 +295,6 @@ disable_port: dln2_adc_set_port_enabled(dln2, false, NULL); disable_chan: dln2_adc_set_chan_enabled(dln2, channel, false); -release_direct: - iio_device_release_direct_mode(indio_dev); return ret; } @@ -337,10 +330,16 @@ static int dln2_adc_read_raw(struct iio_dev *indio_dev, switch (mask) { case IIO_CHAN_INFO_RAW: + ret = iio_device_claim_direct_mode(indio_dev); + if (ret < 0) + return ret; + mutex_lock(&dln2->mutex); ret = dln2_adc_read(dln2, chan->channel); mutex_unlock(&dln2->mutex); + iio_device_release_direct_mode(indio_dev); + if (ret < 0) return ret; @@ -656,7 +655,11 @@ static int dln2_adc_probe(struct platform_device *pdev) return -ENOMEM; } iio_trigger_set_drvdata(dln2->trig, dln2); - devm_iio_trigger_register(dev, dln2->trig); + ret = devm_iio_trigger_register(dev, dln2->trig); + if (ret) { + dev_err(dev, "failed to register trigger: %d\n", ret); + return ret; + } iio_trigger_set_immutable(indio_dev, dln2->trig); ret = devm_iio_triggered_buffer_setup(dev, indio_dev, NULL, diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c index 6245434f8377..8cd258cb2682 100644 --- a/drivers/iio/adc/stm32-adc.c +++ b/drivers/iio/adc/stm32-adc.c @@ -1117,6 +1117,7 @@ static void stm32h7_adc_unprepare(struct iio_dev *indio_dev) { struct stm32_adc *adc = iio_priv(indio_dev); + stm32_adc_writel(adc, STM32H7_ADC_PCSEL, 0); stm32h7_adc_disable(indio_dev); stm32_adc_int_ch_disable(adc); stm32h7_adc_enter_pwr_down(adc); @@ -1986,7 +1987,7 @@ static int stm32_adc_populate_int_ch(struct iio_dev *indio_dev, const char *ch_n /* Get calibration data for vrefint channel */ ret = nvmem_cell_read_u16(&indio_dev->dev, "vrefint", &vrefint); if (ret && ret != -ENOENT) { - return dev_err_probe(&indio_dev->dev, ret, + return dev_err_probe(indio_dev->dev.parent, ret, "nvmem access error\n"); } if (ret == -ENOENT) diff --git a/drivers/iio/gyro/adxrs290.c b/drivers/iio/gyro/adxrs290.c index 3e0734ddafe3..600e9725da78 100644 --- a/drivers/iio/gyro/adxrs290.c +++ b/drivers/iio/gyro/adxrs290.c @@ -7,6 +7,7 @@ */ #include <linux/bitfield.h> +#include <linux/bitops.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/kernel.h> @@ -124,7 +125,7 @@ static int adxrs290_get_rate_data(struct iio_dev *indio_dev, const u8 cmd, int * goto err_unlock; } - *val = temp; + *val = sign_extend32(temp, 15); err_unlock: mutex_unlock(&st->lock); @@ -146,7 +147,7 @@ static int adxrs290_get_temp_data(struct iio_dev *indio_dev, int *val) } /* extract lower 12 bits temperature reading */ - *val = temp & 0x0FFF; + *val = sign_extend32(temp, 11); err_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/gyro/itg3200_buffer.c b/drivers/iio/gyro/itg3200_buffer.c index 04dd6a7969ea..4cfa0d439560 100644 --- a/drivers/iio/gyro/itg3200_buffer.c +++ b/drivers/iio/gyro/itg3200_buffer.c @@ -61,9 +61,9 @@ static irqreturn_t itg3200_trigger_handler(int irq, void *p) iio_push_to_buffers_with_timestamp(indio_dev, &scan, pf->timestamp); +error_ret: iio_trigger_notify_done(indio_dev->trig); -error_ret: return IRQ_HANDLED; } diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c index b23caa2f2aa1..93990ff1dfe3 100644 --- a/drivers/iio/industrialio-trigger.c +++ b/drivers/iio/industrialio-trigger.c @@ -556,7 +556,6 @@ struct iio_trigger *viio_trigger_alloc(struct device *parent, irq_modify_status(trig->subirq_base + i, IRQ_NOREQUEST | IRQ_NOAUTOEN, IRQ_NOPROBE); } - get_device(&trig->dev); return trig; diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c index 7e51aaac0bf8..b2983b1a9ed1 100644 --- a/drivers/iio/light/ltr501.c +++ b/drivers/iio/light/ltr501.c @@ -1275,7 +1275,7 @@ static irqreturn_t ltr501_trigger_handler(int irq, void *p) ret = regmap_bulk_read(data->regmap, LTR501_ALS_DATA1, als_buf, sizeof(als_buf)); if (ret < 0) - return ret; + goto done; if (test_bit(0, indio_dev->active_scan_mask)) scan.channels[j++] = le16_to_cpu(als_buf[1]); if (test_bit(1, indio_dev->active_scan_mask)) diff --git a/drivers/iio/light/stk3310.c b/drivers/iio/light/stk3310.c index 07e91846307c..fc63856ed54d 100644 --- a/drivers/iio/light/stk3310.c +++ b/drivers/iio/light/stk3310.c @@ -546,9 +546,8 @@ static irqreturn_t stk3310_irq_event_handler(int irq, void *private) mutex_lock(&data->lock); ret = regmap_field_read(data->reg_flag_nf, &dir); if (ret < 0) { - dev_err(&data->client->dev, "register read failed\n"); - mutex_unlock(&data->lock); - return ret; + dev_err(&data->client->dev, "register read failed: %d\n", ret); + goto out; } event = IIO_UNMOD_EVENT_CODE(IIO_PROXIMITY, 1, IIO_EV_TYPE_THRESH, @@ -560,6 +559,7 @@ static irqreturn_t stk3310_irq_event_handler(int irq, void *private) ret = regmap_field_write(data->reg_flag_psint, 0); if (ret < 0) dev_err(&data->client->dev, "failed to reset interrupts\n"); +out: mutex_unlock(&data->lock); return IRQ_HANDLED; diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c index 33083877cd19..4353b749ecef 100644 --- a/drivers/iio/trigger/stm32-timer-trigger.c +++ b/drivers/iio/trigger/stm32-timer-trigger.c @@ -912,6 +912,6 @@ static struct platform_driver stm32_timer_trigger_driver = { }; module_platform_driver(stm32_timer_trigger_driver); -MODULE_ALIAS("platform: stm32-timer-trigger"); +MODULE_ALIAS("platform:stm32-timer-trigger"); MODULE_DESCRIPTION("STMicroelectronics STM32 Timer Trigger driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index ec37f4fd8e96..f1245c94ae26 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -8415,6 +8415,8 @@ static void receive_interrupt_common(struct hfi1_ctxtdata *rcd) */ static void __hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd) { + if (!rcd->rcvhdrq) + return; clear_recv_intr(rcd); if (check_packet_present(rcd)) force_recv_intr(rcd); diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index 61f341c3005c..e2c634af40e9 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -1012,6 +1012,8 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread) struct hfi1_packet packet; int skip_pkt = 0; + if (!rcd->rcvhdrq) + return RCV_PKT_OK; /* Control context will always use the slow path interrupt handler */ needset = (rcd->ctxt == HFI1_CTRL_CTXT) ? 0 : 1; diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index dbd1c31830b9..4436ed41547c 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -113,7 +113,6 @@ static int hfi1_create_kctxt(struct hfi1_devdata *dd, rcd->fast_handler = get_dma_rtail_setting(rcd) ? handle_receive_interrupt_dma_rtail : handle_receive_interrupt_nodma_rtail; - rcd->slow_handler = handle_receive_interrupt; hfi1_set_seq_cnt(rcd, 1); @@ -334,6 +333,8 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa, rcd->numa_id = numa; rcd->rcv_array_groups = dd->rcv_entries.ngroups; rcd->rhf_rcv_function_map = normal_rhf_rcv_functions; + rcd->slow_handler = handle_receive_interrupt; + rcd->do_interrupt = rcd->slow_handler; rcd->msix_intr = CCE_NUM_MSIX_VECTORS; mutex_init(&rcd->exp_mutex); @@ -874,18 +875,6 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit) if (ret) goto done; - /* allocate dummy tail memory for all receive contexts */ - dd->rcvhdrtail_dummy_kvaddr = dma_alloc_coherent(&dd->pcidev->dev, - sizeof(u64), - &dd->rcvhdrtail_dummy_dma, - GFP_KERNEL); - - if (!dd->rcvhdrtail_dummy_kvaddr) { - dd_dev_err(dd, "cannot allocate dummy tail memory\n"); - ret = -ENOMEM; - goto done; - } - /* dd->rcd can be NULL if early initialization failed */ for (i = 0; dd->rcd && i < dd->first_dyn_alloc_ctxt; ++i) { /* @@ -898,8 +887,6 @@ int hfi1_init(struct hfi1_devdata *dd, int reinit) if (!rcd) continue; - rcd->do_interrupt = &handle_receive_interrupt; - lastfail = hfi1_create_rcvhdrq(dd, rcd); if (!lastfail) lastfail = hfi1_setup_eagerbufs(rcd); @@ -1120,7 +1107,7 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd) rcd->egrbufs.rcvtids = NULL; for (e = 0; e < rcd->egrbufs.alloced; e++) { - if (rcd->egrbufs.buffers[e].dma) + if (rcd->egrbufs.buffers[e].addr) dma_free_coherent(&dd->pcidev->dev, rcd->egrbufs.buffers[e].len, rcd->egrbufs.buffers[e].addr, @@ -1201,6 +1188,11 @@ void hfi1_free_devdata(struct hfi1_devdata *dd) dd->tx_opstats = NULL; kfree(dd->comp_vect); dd->comp_vect = NULL; + if (dd->rcvhdrtail_dummy_kvaddr) + dma_free_coherent(&dd->pcidev->dev, sizeof(u64), + (void *)dd->rcvhdrtail_dummy_kvaddr, + dd->rcvhdrtail_dummy_dma); + dd->rcvhdrtail_dummy_kvaddr = NULL; sdma_clean(dd, dd->num_sdma); rvt_dealloc_device(&dd->verbs_dev.rdi); } @@ -1298,6 +1290,15 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, goto bail; } + /* allocate dummy tail memory for all receive contexts */ + dd->rcvhdrtail_dummy_kvaddr = + dma_alloc_coherent(&dd->pcidev->dev, sizeof(u64), + &dd->rcvhdrtail_dummy_dma, GFP_KERNEL); + if (!dd->rcvhdrtail_dummy_kvaddr) { + ret = -ENOMEM; + goto bail; + } + atomic_set(&dd->ipoib_rsm_usr_num, 0); return dd; @@ -1505,13 +1506,6 @@ static void cleanup_device_data(struct hfi1_devdata *dd) free_credit_return(dd); - if (dd->rcvhdrtail_dummy_kvaddr) { - dma_free_coherent(&dd->pcidev->dev, sizeof(u64), - (void *)dd->rcvhdrtail_dummy_kvaddr, - dd->rcvhdrtail_dummy_dma); - dd->rcvhdrtail_dummy_kvaddr = NULL; - } - /* * Free any resources still in use (usually just kernel contexts) * at unload; we do for ctxtcnt, because that's what we allocate. diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 2b6c24b7b586..f07d328689d3 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -838,8 +838,8 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd, if (current->nr_cpus_allowed != 1) goto out; - cpu_id = smp_processor_id(); rcu_read_lock(); + cpu_id = smp_processor_id(); rht_node = rhashtable_lookup(dd->sdma_rht, &cpu_id, sdma_rht_params); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 9bfbaddd1763..bbfa1332dedc 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -33,6 +33,7 @@ #include <linux/acpi.h> #include <linux/etherdevice.h> #include <linux/interrupt.h> +#include <linux/iopoll.h> #include <linux/kernel.h> #include <linux/types.h> #include <net/addrconf.h> @@ -1050,9 +1051,14 @@ static u32 hns_roce_v2_cmd_hw_resetting(struct hns_roce_dev *hr_dev, unsigned long instance_stage, unsigned long reset_stage) { +#define HW_RESET_TIMEOUT_US 1000000 +#define HW_RESET_SLEEP_US 1000 + struct hns_roce_v2_priv *priv = hr_dev->priv; struct hnae3_handle *handle = priv->handle; const struct hnae3_ae_ops *ops = handle->ae_algo->ops; + unsigned long val; + int ret; /* When hardware reset is detected, we should stop sending mailbox&cmq& * doorbell to hardware. If now in .init_instance() function, we should @@ -1064,7 +1070,11 @@ static u32 hns_roce_v2_cmd_hw_resetting(struct hns_roce_dev *hr_dev, * again. */ hr_dev->dis_db = true; - if (!ops->get_hw_reset_stat(handle)) + + ret = read_poll_timeout(ops->ae_dev_reset_cnt, val, + val > hr_dev->reset_cnt, HW_RESET_SLEEP_US, + HW_RESET_TIMEOUT_US, false, handle); + if (!ret) hr_dev->is_reset = true; if (!hr_dev->is_reset || reset_stage == HNS_ROCE_STATE_RST_INIT || @@ -6387,10 +6397,8 @@ static int hns_roce_hw_v2_reset_notify_down(struct hnae3_handle *handle) if (!hr_dev) return 0; - hr_dev->is_reset = true; hr_dev->active = false; hr_dev->dis_db = true; - hr_dev->state = HNS_ROCE_DEVICE_STATE_RST_DOWN; return 0; diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 4108dcabece2..b4c657f5f2f9 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -60,6 +60,8 @@ static void irdma_iwarp_ce_handler(struct irdma_sc_cq *iwcq) { struct irdma_cq *cq = iwcq->back_cq; + if (!cq->user_mode) + cq->armed = false; if (cq->ibcq.comp_handler) cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); } @@ -146,6 +148,7 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp, qp->flush_code = FLUSH_PROT_ERR; break; case IRDMA_AE_AMP_BAD_QP: + case IRDMA_AE_WQE_UNEXPECTED_OPCODE: qp->flush_code = FLUSH_LOC_QP_OP_ERR; break; case IRDMA_AE_AMP_BAD_STAG_KEY: @@ -156,7 +159,6 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp, case IRDMA_AE_PRIV_OPERATION_DENIED: case IRDMA_AE_IB_INVALID_REQUEST: case IRDMA_AE_IB_REMOTE_ACCESS_ERROR: - case IRDMA_AE_IB_REMOTE_OP_ERROR: qp->flush_code = FLUSH_REM_ACCESS_ERR; qp->event_type = IRDMA_QP_EVENT_ACCESS_ERR; break; @@ -184,6 +186,9 @@ static void irdma_set_flush_fields(struct irdma_sc_qp *qp, case IRDMA_AE_AMP_MWBIND_INVALID_BOUNDS: qp->flush_code = FLUSH_MW_BIND_ERR; break; + case IRDMA_AE_IB_REMOTE_OP_ERROR: + qp->flush_code = FLUSH_REM_OP_ERR; + break; default: qp->flush_code = FLUSH_FATAL_ERR; break; diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h index 91a497139ba3..cb218cab79ac 100644 --- a/drivers/infiniband/hw/irdma/main.h +++ b/drivers/infiniband/hw/irdma/main.h @@ -542,6 +542,7 @@ int irdma_ah_cqp_op(struct irdma_pci_f *rf, struct irdma_sc_ah *sc_ah, u8 cmd, void (*callback_fcn)(struct irdma_cqp_request *cqp_request), void *cb_param); void irdma_gsi_ud_qp_ah_cb(struct irdma_cqp_request *cqp_request); +bool irdma_cq_empty(struct irdma_cq *iwcq); int irdma_inetaddr_event(struct notifier_block *notifier, unsigned long event, void *ptr); int irdma_inet6addr_event(struct notifier_block *notifier, unsigned long event, diff --git a/drivers/infiniband/hw/irdma/pble.c b/drivers/infiniband/hw/irdma/pble.c index aeeb1c310965..fed49da770f3 100644 --- a/drivers/infiniband/hw/irdma/pble.c +++ b/drivers/infiniband/hw/irdma/pble.c @@ -25,8 +25,7 @@ void irdma_destroy_pble_prm(struct irdma_hmc_pble_rsrc *pble_rsrc) list_del(&chunk->list); if (chunk->type == PBLE_SD_PAGED) irdma_pble_free_paged_mem(chunk); - if (chunk->bitmapbuf) - kfree(chunk->bitmapmem.va); + bitmap_free(chunk->bitmapbuf); kfree(chunk->chunkmem.va); } } @@ -283,7 +282,6 @@ add_pble_prm(struct irdma_hmc_pble_rsrc *pble_rsrc) "PBLE: next_fpm_addr = %llx chunk_size[%llu] = 0x%llx\n", pble_rsrc->next_fpm_addr, chunk->size, chunk->size); pble_rsrc->unallocated_pble -= (u32)(chunk->size >> 3); - list_add(&chunk->list, &pble_rsrc->pinfo.clist); sd_reg_val = (sd_entry_type == IRDMA_SD_TYPE_PAGED) ? sd_entry->u.pd_table.pd_page_addr.pa : sd_entry->u.bp.addr.pa; @@ -295,12 +293,12 @@ add_pble_prm(struct irdma_hmc_pble_rsrc *pble_rsrc) goto error; } + list_add(&chunk->list, &pble_rsrc->pinfo.clist); sd_entry->valid = true; return 0; error: - if (chunk->bitmapbuf) - kfree(chunk->bitmapmem.va); + bitmap_free(chunk->bitmapbuf); kfree(chunk->chunkmem.va); return ret_code; diff --git a/drivers/infiniband/hw/irdma/pble.h b/drivers/infiniband/hw/irdma/pble.h index e1b3b8118a2c..aa20827dcc9d 100644 --- a/drivers/infiniband/hw/irdma/pble.h +++ b/drivers/infiniband/hw/irdma/pble.h @@ -78,7 +78,6 @@ struct irdma_chunk { u32 pg_cnt; enum irdma_alloc_type type; struct irdma_sc_dev *dev; - struct irdma_virt_mem bitmapmem; struct irdma_virt_mem chunkmem; }; diff --git a/drivers/infiniband/hw/irdma/utils.c b/drivers/infiniband/hw/irdma/utils.c index 8b42c43fc14f..398736d8c78a 100644 --- a/drivers/infiniband/hw/irdma/utils.c +++ b/drivers/infiniband/hw/irdma/utils.c @@ -2239,15 +2239,10 @@ enum irdma_status_code irdma_prm_add_pble_mem(struct irdma_pble_prm *pprm, sizeofbitmap = (u64)pchunk->size >> pprm->pble_shift; - pchunk->bitmapmem.size = sizeofbitmap >> 3; - pchunk->bitmapmem.va = kzalloc(pchunk->bitmapmem.size, GFP_KERNEL); - - if (!pchunk->bitmapmem.va) + pchunk->bitmapbuf = bitmap_zalloc(sizeofbitmap, GFP_KERNEL); + if (!pchunk->bitmapbuf) return IRDMA_ERR_NO_MEMORY; - pchunk->bitmapbuf = pchunk->bitmapmem.va; - bitmap_zero(pchunk->bitmapbuf, sizeofbitmap); - pchunk->sizeofbitmap = sizeofbitmap; /* each pble is 8 bytes hence shift by 3 */ pprm->total_pble_alloc += pchunk->size >> 3; @@ -2491,3 +2486,18 @@ void irdma_ib_qp_event(struct irdma_qp *iwqp, enum irdma_qp_event_type event) ibevent.element.qp = &iwqp->ibqp; iwqp->ibqp.event_handler(&ibevent, iwqp->ibqp.qp_context); } + +bool irdma_cq_empty(struct irdma_cq *iwcq) +{ + struct irdma_cq_uk *ukcq; + u64 qword3; + __le64 *cqe; + u8 polarity; + + ukcq = &iwcq->sc_cq.cq_uk; + cqe = IRDMA_GET_CURRENT_CQ_ELEM(ukcq); + get_64bit_val(cqe, 24, &qword3); + polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3); + + return polarity != ukcq->polarity; +} diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 0f66e809d418..8cd5f9261692 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -3584,18 +3584,31 @@ static int irdma_req_notify_cq(struct ib_cq *ibcq, struct irdma_cq *iwcq; struct irdma_cq_uk *ukcq; unsigned long flags; - enum irdma_cmpl_notify cq_notify = IRDMA_CQ_COMPL_EVENT; + enum irdma_cmpl_notify cq_notify; + bool promo_event = false; + int ret = 0; + cq_notify = notify_flags == IB_CQ_SOLICITED ? + IRDMA_CQ_COMPL_SOLICITED : IRDMA_CQ_COMPL_EVENT; iwcq = to_iwcq(ibcq); ukcq = &iwcq->sc_cq.cq_uk; - if (notify_flags == IB_CQ_SOLICITED) - cq_notify = IRDMA_CQ_COMPL_SOLICITED; spin_lock_irqsave(&iwcq->lock, flags); - irdma_uk_cq_request_notification(ukcq, cq_notify); + /* Only promote to arm the CQ for any event if the last arm event was solicited. */ + if (iwcq->last_notify == IRDMA_CQ_COMPL_SOLICITED && notify_flags != IB_CQ_SOLICITED) + promo_event = true; + + if (!iwcq->armed || promo_event) { + iwcq->armed = true; + iwcq->last_notify = cq_notify; + irdma_uk_cq_request_notification(ukcq, cq_notify); + } + + if ((notify_flags & IB_CQ_REPORT_MISSED_EVENTS) && !irdma_cq_empty(iwcq)) + ret = 1; spin_unlock_irqrestore(&iwcq->lock, flags); - return 0; + return ret; } static int irdma_roce_port_immutable(struct ib_device *ibdev, u32 port_num, diff --git a/drivers/infiniband/hw/irdma/verbs.h b/drivers/infiniband/hw/irdma/verbs.h index 5c244cd321a3..d0fdef8d09ea 100644 --- a/drivers/infiniband/hw/irdma/verbs.h +++ b/drivers/infiniband/hw/irdma/verbs.h @@ -110,6 +110,8 @@ struct irdma_cq { u16 cq_size; u16 cq_num; bool user_mode; + bool armed; + enum irdma_cmpl_notify last_notify; u32 polled_cmpls; u32 cq_mem_size; struct irdma_dma_mem kmem; diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c index b780185d9dc6..661ed2b44508 100644 --- a/drivers/infiniband/hw/mlx5/fs.c +++ b/drivers/infiniband/hw/mlx5/fs.c @@ -1508,7 +1508,7 @@ _get_flow_table(struct mlx5_ib_dev *dev, !esw_encap) flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; break; - case MLX5_FLOW_NAMESPACE_FDB: + case MLX5_FLOW_NAMESPACE_FDB_BYPASS: max_table_size = BIT( MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, log_max_ft_size)); if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, decap) && esw_encap) @@ -1517,7 +1517,7 @@ _get_flow_table(struct mlx5_ib_dev *dev, reformat_l3_tunnel_to_l2) && esw_encap) flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; - priority = FDB_BYPASS_PATH; + priority = fs_matcher->priority; break; case MLX5_FLOW_NAMESPACE_RDMA_RX: max_table_size = BIT( @@ -1546,8 +1546,8 @@ _get_flow_table(struct mlx5_ib_dev *dev, case MLX5_FLOW_NAMESPACE_EGRESS: prio = &dev->flow_db->egress_prios[priority]; break; - case MLX5_FLOW_NAMESPACE_FDB: - prio = &dev->flow_db->fdb; + case MLX5_FLOW_NAMESPACE_FDB_BYPASS: + prio = &dev->flow_db->fdb[priority]; break; case MLX5_FLOW_NAMESPACE_RDMA_RX: prio = &dev->flow_db->rdma_rx[priority]; @@ -1937,7 +1937,7 @@ mlx5_ib_ft_type_to_namespace(enum mlx5_ib_uapi_flow_table_type table_type, *namespace = MLX5_FLOW_NAMESPACE_EGRESS; break; case MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB: - *namespace = MLX5_FLOW_NAMESPACE_FDB; + *namespace = MLX5_FLOW_NAMESPACE_FDB_BYPASS; break; case MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_RX: *namespace = MLX5_FLOW_NAMESPACE_RDMA_RX; @@ -2029,8 +2029,8 @@ static int get_dests(struct uverbs_attr_bundle *attrs, } /* Allow only DEVX object, drop as dest for FDB */ - if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB && !(dest_devx || - (*flags & MLX5_IB_ATTR_CREATE_FLOW_FLAGS_DROP))) + if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB_BYPASS && + !(dest_devx || (*flags & MLX5_IB_ATTR_CREATE_FLOW_FLAGS_DROP))) return -EINVAL; /* Allow only DEVX object or QP as dest when inserting to RDMA_RX */ @@ -2050,7 +2050,7 @@ static int get_dests(struct uverbs_attr_bundle *attrs, if (!is_flow_dest(devx_obj, dest_id, dest_type)) return -EINVAL; /* Allow only flow table as dest when inserting to FDB or RDMA_RX */ - if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB || + if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB_BYPASS || fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX) && *dest_type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) return -EINVAL; @@ -2320,7 +2320,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)( if (err) goto end; - if (obj->ns_type == MLX5_FLOW_NAMESPACE_FDB && + if (obj->ns_type == MLX5_FLOW_NAMESPACE_FDB_BYPASS && mlx5_eswitch_mode(dev->mdev) != MLX5_ESWITCH_OFFLOADS) { err = -EINVAL; goto end; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index e636e954f6bf..6038faf292d7 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -232,6 +232,7 @@ enum { #define MLX5_IB_NUM_FLOW_FT (MLX5_IB_FLOW_LEFTOVERS_PRIO + 1) #define MLX5_IB_NUM_SNIFFER_FTS 2 #define MLX5_IB_NUM_EGRESS_FTS 1 +#define MLX5_IB_NUM_FDB_FTS MLX5_BY_PASS_NUM_REGULAR_PRIOS struct mlx5_ib_flow_prio { struct mlx5_flow_table *flow_table; unsigned int refcount; @@ -276,7 +277,7 @@ struct mlx5_ib_flow_db { struct mlx5_ib_flow_prio egress_prios[MLX5_IB_NUM_FLOW_FT]; struct mlx5_ib_flow_prio sniffer[MLX5_IB_NUM_SNIFFER_FTS]; struct mlx5_ib_flow_prio egress[MLX5_IB_NUM_EGRESS_FTS]; - struct mlx5_ib_flow_prio fdb; + struct mlx5_ib_flow_prio fdb[MLX5_IB_NUM_FDB_FTS]; struct mlx5_ib_flow_prio rdma_rx[MLX5_IB_NUM_FLOW_FT]; struct mlx5_ib_flow_prio rdma_tx[MLX5_IB_NUM_FLOW_FT]; struct mlx5_ib_flow_prio opfcs[MLX5_IB_OPCOUNTER_MAX]; @@ -664,7 +665,6 @@ struct mlx5_ib_mr { /* User MR data */ struct mlx5_cache_ent *cache_ent; - struct ib_umem *umem; /* This is zero'd when the MR is allocated */ union { @@ -676,7 +676,7 @@ struct mlx5_ib_mr { struct list_head list; }; - /* Used only by kernel MRs (umem == NULL) */ + /* Used only by kernel MRs */ struct { void *descs; void *descs_alloc; @@ -697,8 +697,9 @@ struct mlx5_ib_mr { int data_length; }; - /* Used only by User MRs (umem != NULL) */ + /* Used only by User MRs */ struct { + struct ib_umem *umem; unsigned int page_shift; /* Current access_flags */ int access_flags; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 157d862fb864..63e2129f1142 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1904,19 +1904,18 @@ err: return ret; } -static void -mlx5_free_priv_descs(struct mlx5_ib_mr *mr) +static void mlx5_free_priv_descs(struct mlx5_ib_mr *mr) { - if (!mr->umem && mr->descs) { - struct ib_device *device = mr->ibmr.device; - int size = mr->max_descs * mr->desc_size; - struct mlx5_ib_dev *dev = to_mdev(device); + struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device); + int size = mr->max_descs * mr->desc_size; - dma_unmap_single(&dev->mdev->pdev->dev, mr->desc_map, size, - DMA_TO_DEVICE); - kfree(mr->descs_alloc); - mr->descs = NULL; - } + if (!mr->descs) + return; + + dma_unmap_single(&dev->mdev->pdev->dev, mr->desc_map, size, + DMA_TO_DEVICE); + kfree(mr->descs_alloc); + mr->descs = NULL; } int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) @@ -1992,7 +1991,8 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) if (mr->cache_ent) { mlx5_mr_cache_free(dev, mr); } else { - mlx5_free_priv_descs(mr); + if (!udata) + mlx5_free_priv_descs(mr); kfree(mr); } return 0; @@ -2079,7 +2079,6 @@ static struct mlx5_ib_mr *mlx5_ib_alloc_pi_mr(struct ib_pd *pd, if (err) goto err_free_in; - mr->umem = NULL; kfree(in); return mr; @@ -2206,7 +2205,6 @@ static struct ib_mr *__mlx5_ib_alloc_mr(struct ib_pd *pd, } mr->ibmr.device = pd->device; - mr->umem = NULL; switch (mr_type) { case IB_MR_TYPE_MEM_REG: diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 975321812c87..54b8711321c1 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -359,6 +359,7 @@ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, err2: rxe_queue_cleanup(qp->sq.queue); + qp->sq.queue = NULL; err1: qp->pd = NULL; qp->rcq = NULL; diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c index f7e459fe68be..76e4352fe3f6 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c @@ -19,7 +19,7 @@ void rtrs_clt_update_wc_stats(struct rtrs_clt_con *con) int cpu; cpu = raw_smp_processor_id(); - s = this_cpu_ptr(stats->pcpu_stats); + s = get_cpu_ptr(stats->pcpu_stats); if (con->cpu != cpu) { s->cpu_migr.to++; @@ -27,14 +27,16 @@ void rtrs_clt_update_wc_stats(struct rtrs_clt_con *con) s = per_cpu_ptr(stats->pcpu_stats, con->cpu); atomic_inc(&s->cpu_migr.from); } + put_cpu_ptr(stats->pcpu_stats); } void rtrs_clt_inc_failover_cnt(struct rtrs_clt_stats *stats) { struct rtrs_clt_stats_pcpu *s; - s = this_cpu_ptr(stats->pcpu_stats); + s = get_cpu_ptr(stats->pcpu_stats); s->rdma.failover_cnt++; + put_cpu_ptr(stats->pcpu_stats); } int rtrs_clt_stats_migration_from_cnt_to_str(struct rtrs_clt_stats *stats, char *buf) @@ -169,9 +171,10 @@ static inline void rtrs_clt_update_rdma_stats(struct rtrs_clt_stats *stats, { struct rtrs_clt_stats_pcpu *s; - s = this_cpu_ptr(stats->pcpu_stats); + s = get_cpu_ptr(stats->pcpu_stats); s->rdma.dir[d].cnt++; s->rdma.dir[d].size_total += size; + put_cpu_ptr(stats->pcpu_stats); } void rtrs_clt_update_all_stats(struct rtrs_clt_io_req *req, int dir) diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c index 3759dc36cc8f..2543ef65825b 100644 --- a/drivers/irqchip/irq-apple-aic.c +++ b/drivers/irqchip/irq-apple-aic.c @@ -707,7 +707,7 @@ static const struct irq_domain_ops aic_ipi_domain_ops = { .free = aic_ipi_free, }; -static int aic_init_smp(struct aic_irq_chip *irqc, struct device_node *node) +static int __init aic_init_smp(struct aic_irq_chip *irqc, struct device_node *node) { struct irq_domain *ipi_domain; int base_ipi; diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 80906bfec845..5b8d571c041d 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -232,16 +232,12 @@ static int armada_370_xp_msi_alloc(struct irq_domain *domain, unsigned int virq, int hwirq, i; mutex_lock(&msi_used_lock); + hwirq = bitmap_find_free_region(msi_used, PCI_MSI_DOORBELL_NR, + order_base_2(nr_irqs)); + mutex_unlock(&msi_used_lock); - hwirq = bitmap_find_next_zero_area(msi_used, PCI_MSI_DOORBELL_NR, - 0, nr_irqs, 0); - if (hwirq >= PCI_MSI_DOORBELL_NR) { - mutex_unlock(&msi_used_lock); + if (hwirq < 0) return -ENOSPC; - } - - bitmap_set(msi_used, hwirq, nr_irqs); - mutex_unlock(&msi_used_lock); for (i = 0; i < nr_irqs; i++) { irq_domain_set_info(domain, virq + i, hwirq + i, @@ -250,7 +246,7 @@ static int armada_370_xp_msi_alloc(struct irq_domain *domain, unsigned int virq, NULL, NULL); } - return hwirq; + return 0; } static void armada_370_xp_msi_free(struct irq_domain *domain, @@ -259,7 +255,7 @@ static void armada_370_xp_msi_free(struct irq_domain *domain, struct irq_data *d = irq_domain_get_irq_data(domain, virq); mutex_lock(&msi_used_lock); - bitmap_clear(msi_used, d->hwirq, nr_irqs); + bitmap_release_region(msi_used, d->hwirq, order_base_2(nr_irqs)); mutex_unlock(&msi_used_lock); } diff --git a/drivers/irqchip/irq-aspeed-scu-ic.c b/drivers/irqchip/irq-aspeed-scu-ic.c index f3c6855a4cef..18b77c3e6db4 100644 --- a/drivers/irqchip/irq-aspeed-scu-ic.c +++ b/drivers/irqchip/irq-aspeed-scu-ic.c @@ -76,8 +76,8 @@ static void aspeed_scu_ic_irq_handler(struct irq_desc *desc) generic_handle_domain_irq(scu_ic->irq_domain, bit - scu_ic->irq_shift); - regmap_update_bits(scu_ic->scu, scu_ic->reg, mask, - BIT(bit + ASPEED_SCU_IC_STATUS_SHIFT)); + regmap_write_bits(scu_ic->scu, scu_ic->reg, mask, + BIT(bit + ASPEED_SCU_IC_STATUS_SHIFT)); } chained_irq_exit(chip, desc); diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c index d80e67a6aad2..bb6609cebdbc 100644 --- a/drivers/irqchip/irq-bcm7120-l2.c +++ b/drivers/irqchip/irq-bcm7120-l2.c @@ -238,6 +238,7 @@ static int __init bcm7120_l2_intc_probe(struct device_node *dn, } data->num_parent_irqs = platform_irq_count(pdev); + put_device(&pdev->dev); if (data->num_parent_irqs <= 0) { pr_err("invalid number of parent interrupts\n"); ret = -ENOMEM; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index eb0882d15366..0cb584d9815b 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -742,7 +742,7 @@ static struct its_collection *its_build_invall_cmd(struct its_node *its, its_fixup_cmd(cmd); - return NULL; + return desc->its_invall_cmd.col; } static struct its_vpe *its_build_vinvall_cmd(struct its_node *its, diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index d02b05a067d9..ff89b36267dd 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "irq-mips-gic: " fmt +#include <linux/bitfield.h> #include <linux/bitmap.h> #include <linux/clocksource.h> #include <linux/cpuhotplug.h> @@ -735,8 +736,7 @@ static int __init gic_of_init(struct device_node *node, mips_gic_base = ioremap(gic_base, gic_len); gicconfig = read_gic_config(); - gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS; - gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS); + gic_shared_intrs = FIELD_GET(GIC_CONFIG_NUMINTERRUPTS, gicconfig); gic_shared_intrs = (gic_shared_intrs + 1) * 8; if (cpu_has_veic) { diff --git a/drivers/irqchip/irq-nvic.c b/drivers/irqchip/irq-nvic.c index 63bac3f78863..ba4759b3e269 100644 --- a/drivers/irqchip/irq-nvic.c +++ b/drivers/irqchip/irq-nvic.c @@ -26,7 +26,7 @@ #define NVIC_ISER 0x000 #define NVIC_ICER 0x080 -#define NVIC_IPR 0x300 +#define NVIC_IPR 0x400 #define NVIC_MAX_BANKS 16 /* diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c index 7313454e403a..e69c4bf557bf 100644 --- a/drivers/isdn/capi/kcapi.c +++ b/drivers/isdn/capi/kcapi.c @@ -32,7 +32,7 @@ #include <linux/mutex.h> #include <linux/rcupdate.h> -static int showcapimsgs = 0; +static int showcapimsgs; static struct workqueue_struct *kcapi_wq; module_param(showcapimsgs, uint, 0); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 6319deccbe09..7af242de3202 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1963,7 +1963,7 @@ static bool __journal_read_write(struct dm_integrity_io *dio, struct bio *bio, n_sectors -= bv.bv_len >> SECTOR_SHIFT; bio_advance_iter(bio, &bio->bi_iter, bv.bv_len); retry_kmap: - mem = bvec_kmap_local(&bv); + mem = kmap_local_page(bv.bv_page); if (likely(dio->op == REQ_OP_WRITE)) flush_dcache_page(bv.bv_page); diff --git a/drivers/md/md.c b/drivers/md/md.c index 5111ed966947..41d6e2383517 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2189,6 +2189,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) if (!num_sectors || num_sectors > max_sectors) num_sectors = max_sectors; + rdev->sb_start = sb_start; } sb = page_address(rdev->sb_page); sb->data_size = cpu_to_le64(num_sectors); @@ -6270,7 +6271,8 @@ static void __md_stop(struct mddev *mddev) spin_lock(&mddev->lock); mddev->pers = NULL; spin_unlock(&mddev->lock); - pers->free(mddev, mddev->private); + if (mddev->private) + pers->free(mddev, mddev->private); mddev->private = NULL; if (pers->sync_request && mddev->to_remove == NULL) mddev->to_remove = &md_redundancy_group; diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c index 70532335c7c7..cb670f16e98e 100644 --- a/drivers/md/persistent-data/dm-btree-remove.c +++ b/drivers/md/persistent-data/dm-btree-remove.c @@ -423,9 +423,9 @@ static int rebalance_children(struct shadow_spine *s, memcpy(n, dm_block_data(child), dm_bm_block_size(dm_tm_get_bm(info->tm))); - dm_tm_unlock(info->tm, child); dm_tm_dec(info->tm, dm_block_location(child)); + dm_tm_unlock(info->tm, child); return 0; } diff --git a/drivers/misc/cardreader/rtsx_pcr.c b/drivers/misc/cardreader/rtsx_pcr.c index 8c72eb590f79..6ac509c1821c 100644 --- a/drivers/misc/cardreader/rtsx_pcr.c +++ b/drivers/misc/cardreader/rtsx_pcr.c @@ -1803,8 +1803,6 @@ static int rtsx_pci_runtime_suspend(struct device *device) mutex_lock(&pcr->pcr_mutex); rtsx_pci_power_off(pcr, HOST_ENTER_S3); - free_irq(pcr->irq, (void *)pcr); - mutex_unlock(&pcr->pcr_mutex); pcr->is_runtime_suspended = true; @@ -1825,8 +1823,6 @@ static int rtsx_pci_runtime_resume(struct device *device) mutex_lock(&pcr->pcr_mutex); rtsx_pci_write_register(pcr, HOST_SLEEP_STATE, 0x03, 0x00); - rtsx_pci_acquire_irq(pcr); - synchronize_irq(pcr->irq); if (pcr->ops->fetch_vendor_settings) pcr->ops->fetch_vendor_settings(pcr); diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c index 632325474233..b38978a3b3ff 100644 --- a/drivers/misc/eeprom/at25.c +++ b/drivers/misc/eeprom/at25.c @@ -376,7 +376,6 @@ MODULE_DEVICE_TABLE(spi, at25_spi_ids); static int at25_probe(struct spi_device *spi) { struct at25_data *at25 = NULL; - struct spi_eeprom chip; int err; int sr; u8 id[FM25_ID_LEN]; @@ -389,15 +388,18 @@ static int at25_probe(struct spi_device *spi) if (match && !strcmp(match->compatible, "cypress,fm25")) is_fram = 1; + at25 = devm_kzalloc(&spi->dev, sizeof(struct at25_data), GFP_KERNEL); + if (!at25) + return -ENOMEM; + /* Chip description */ - if (!spi->dev.platform_data) { - if (!is_fram) { - err = at25_fw_to_chip(&spi->dev, &chip); - if (err) - return err; - } - } else - chip = *(struct spi_eeprom *)spi->dev.platform_data; + if (spi->dev.platform_data) { + memcpy(&at25->chip, spi->dev.platform_data, sizeof(at25->chip)); + } else if (!is_fram) { + err = at25_fw_to_chip(&spi->dev, &at25->chip); + if (err) + return err; + } /* Ping the chip ... the status register is pretty portable, * unlike probing manufacturer IDs. We do expect that system @@ -409,12 +411,7 @@ static int at25_probe(struct spi_device *spi) return -ENXIO; } - at25 = devm_kzalloc(&spi->dev, sizeof(struct at25_data), GFP_KERNEL); - if (!at25) - return -ENOMEM; - mutex_init(&at25->lock); - at25->chip = chip; at25->spi = spi; spi_set_drvdata(spi, at25); @@ -431,7 +428,7 @@ static int at25_probe(struct spi_device *spi) dev_err(&spi->dev, "Error: unsupported size (id %02x)\n", id[7]); return -ENODEV; } - chip.byte_len = int_pow(2, id[7] - 0x21 + 4) * 1024; + at25->chip.byte_len = int_pow(2, id[7] - 0x21 + 4) * 1024; if (at25->chip.byte_len > 64 * 1024) at25->chip.flags |= EE_ADDR3; @@ -464,7 +461,7 @@ static int at25_probe(struct spi_device *spi) at25->nvmem_config.type = is_fram ? NVMEM_TYPE_FRAM : NVMEM_TYPE_EEPROM; at25->nvmem_config.name = dev_name(&spi->dev); at25->nvmem_config.dev = &spi->dev; - at25->nvmem_config.read_only = chip.flags & EE_READONLY; + at25->nvmem_config.read_only = at25->chip.flags & EE_READONLY; at25->nvmem_config.root_only = true; at25->nvmem_config.owner = THIS_MODULE; at25->nvmem_config.compat = true; @@ -474,17 +471,18 @@ static int at25_probe(struct spi_device *spi) at25->nvmem_config.priv = at25; at25->nvmem_config.stride = 1; at25->nvmem_config.word_size = 1; - at25->nvmem_config.size = chip.byte_len; + at25->nvmem_config.size = at25->chip.byte_len; at25->nvmem = devm_nvmem_register(&spi->dev, &at25->nvmem_config); if (IS_ERR(at25->nvmem)) return PTR_ERR(at25->nvmem); dev_info(&spi->dev, "%d %s %s %s%s, pagesize %u\n", - (chip.byte_len < 1024) ? chip.byte_len : (chip.byte_len / 1024), - (chip.byte_len < 1024) ? "Byte" : "KByte", + (at25->chip.byte_len < 1024) ? + at25->chip.byte_len : (at25->chip.byte_len / 1024), + (at25->chip.byte_len < 1024) ? "Byte" : "KByte", at25->chip.name, is_fram ? "fram" : "eeprom", - (chip.flags & EE_READONLY) ? " (readonly)" : "", + (at25->chip.flags & EE_READONLY) ? " (readonly)" : "", at25->chip.page_size); return 0; } diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 39aca7753719..4ccbf43e6bfa 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -719,16 +719,18 @@ static int fastrpc_get_meta_size(struct fastrpc_invoke_ctx *ctx) static u64 fastrpc_get_payload_size(struct fastrpc_invoke_ctx *ctx, int metalen) { u64 size = 0; - int i; + int oix; size = ALIGN(metalen, FASTRPC_ALIGN); - for (i = 0; i < ctx->nscalars; i++) { + for (oix = 0; oix < ctx->nbufs; oix++) { + int i = ctx->olaps[oix].raix; + if (ctx->args[i].fd == 0 || ctx->args[i].fd == -1) { - if (ctx->olaps[i].offset == 0) + if (ctx->olaps[oix].offset == 0) size = ALIGN(size, FASTRPC_ALIGN); - size += (ctx->olaps[i].mend - ctx->olaps[i].mstart); + size += (ctx->olaps[oix].mend - ctx->olaps[oix].mstart); } } diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 943940b44e83..632775217d35 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -2291,8 +2291,10 @@ static int msdc_execute_hs400_tuning(struct mmc_host *mmc, struct mmc_card *card sdr_set_field(host->base + PAD_DS_TUNE, PAD_DS_TUNE_DLY1, i); ret = mmc_get_ext_csd(card, &ext_csd); - if (!ret) + if (!ret) { result_dly1 |= (1 << i); + kfree(ext_csd); + } } host->hs400_tuning = false; diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index a4407f391f66..f5b2684ad805 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -673,7 +673,7 @@ static int renesas_sdhi_execute_tuning(struct mmc_host *mmc, u32 opcode) /* Issue CMD19 twice for each tap */ for (i = 0; i < 2 * priv->tap_num; i++) { - int cmd_error; + int cmd_error = 0; /* Set sampling clock position */ sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_TAPSET, i % priv->tap_num); diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c index 9802e265fca8..2b317ed6c103 100644 --- a/drivers/mtd/devices/mtd_dataflash.c +++ b/drivers/mtd/devices/mtd_dataflash.c @@ -96,6 +96,13 @@ struct dataflash { struct mtd_info mtd; }; +static const struct spi_device_id dataflash_dev_ids[] = { + { "at45" }, + { "dataflash" }, + { }, +}; +MODULE_DEVICE_TABLE(spi, dataflash_dev_ids); + #ifdef CONFIG_OF static const struct of_device_id dataflash_dt_ids[] = { { .compatible = "atmel,at45", }, @@ -927,6 +934,7 @@ static struct spi_driver dataflash_driver = { .name = "mtd_dataflash", .of_match_table = of_match_ptr(dataflash_dt_ids), }, + .id_table = dataflash_dev_ids, .probe = dataflash_probe, .remove = dataflash_remove, diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig index 67b7cb67c030..0a45d3c6c15b 100644 --- a/drivers/mtd/nand/raw/Kconfig +++ b/drivers/mtd/nand/raw/Kconfig @@ -26,7 +26,7 @@ config MTD_NAND_DENALI_PCI config MTD_NAND_DENALI_DT tristate "Denali NAND controller as a DT device" select MTD_NAND_DENALI - depends on HAS_DMA && HAVE_CLK && OF + depends on HAS_DMA && HAVE_CLK && OF && HAS_IOMEM help Enable the driver for NAND flash on platforms using a Denali NAND controller as a DT device. diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c index 658f0cbe7ce8..6b2bda815b88 100644 --- a/drivers/mtd/nand/raw/fsmc_nand.c +++ b/drivers/mtd/nand/raw/fsmc_nand.c @@ -15,6 +15,7 @@ #include <linux/clk.h> #include <linux/completion.h> +#include <linux/delay.h> #include <linux/dmaengine.h> #include <linux/dma-direction.h> #include <linux/dma-mapping.h> @@ -93,6 +94,14 @@ #define FSMC_BUSY_WAIT_TIMEOUT (1 * HZ) +/* + * According to SPEAr300 Reference Manual (RM0082) + * TOUDEL = 7ns (Output delay from the flip-flops to the board) + * TINDEL = 5ns (Input delay from the board to the flipflop) + */ +#define TOUTDEL 7000 +#define TINDEL 5000 + struct fsmc_nand_timings { u8 tclr; u8 tar; @@ -277,7 +286,7 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host, { unsigned long hclk = clk_get_rate(host->clk); unsigned long hclkn = NSEC_PER_SEC / hclk; - u32 thiz, thold, twait, tset; + u32 thiz, thold, twait, tset, twait_min; if (sdrt->tRC_min < 30000) return -EOPNOTSUPP; @@ -309,13 +318,6 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host, else if (tims->thold > FSMC_THOLD_MASK) tims->thold = FSMC_THOLD_MASK; - twait = max(sdrt->tRP_min, sdrt->tWP_min); - tims->twait = DIV_ROUND_UP(twait / 1000, hclkn) - 1; - if (tims->twait == 0) - tims->twait = 1; - else if (tims->twait > FSMC_TWAIT_MASK) - tims->twait = FSMC_TWAIT_MASK; - tset = max(sdrt->tCS_min - sdrt->tWP_min, sdrt->tCEA_max - sdrt->tREA_max); tims->tset = DIV_ROUND_UP(tset / 1000, hclkn) - 1; @@ -324,6 +326,21 @@ static int fsmc_calc_timings(struct fsmc_nand_data *host, else if (tims->tset > FSMC_TSET_MASK) tims->tset = FSMC_TSET_MASK; + /* + * According to SPEAr300 Reference Manual (RM0082) which gives more + * information related to FSMSC timings than the SPEAr600 one (RM0305), + * twait >= tCEA - (tset * TCLK) + TOUTDEL + TINDEL + */ + twait_min = sdrt->tCEA_max - ((tims->tset + 1) * hclkn * 1000) + + TOUTDEL + TINDEL; + twait = max3(sdrt->tRP_min, sdrt->tWP_min, twait_min); + + tims->twait = DIV_ROUND_UP(twait / 1000, hclkn) - 1; + if (tims->twait == 0) + tims->twait = 1; + else if (tims->twait > FSMC_TWAIT_MASK) + tims->twait = FSMC_TWAIT_MASK; + return 0; } @@ -664,6 +681,9 @@ static int fsmc_exec_op(struct nand_chip *chip, const struct nand_operation *op, instr->ctx.waitrdy.timeout_ms); break; } + + if (instr->delay_ns) + ndelay(instr->delay_ns); } return ret; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 3d6c6e880520..a130320de412 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -926,7 +926,7 @@ int nand_choose_best_sdr_timings(struct nand_chip *chip, struct nand_sdr_timings *spec_timings) { const struct nand_controller_ops *ops = chip->controller->ops; - int best_mode = 0, mode, ret; + int best_mode = 0, mode, ret = -EOPNOTSUPP; iface->type = NAND_SDR_IFACE; @@ -977,7 +977,7 @@ int nand_choose_best_nvddr_timings(struct nand_chip *chip, struct nand_nvddr_timings *spec_timings) { const struct nand_controller_ops *ops = chip->controller->ops; - int best_mode = 0, mode, ret; + int best_mode = 0, mode, ret = -EOPNOTSUPP; iface->type = NAND_NVDDR_IFACE; @@ -1837,7 +1837,7 @@ int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock) NAND_OP_CMD(NAND_CMD_ERASE1, 0), NAND_OP_ADDR(2, addrs, 0), NAND_OP_CMD(NAND_CMD_ERASE2, - NAND_COMMON_TIMING_MS(conf, tWB_max)), + NAND_COMMON_TIMING_NS(conf, tWB_max)), NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tBERS_max), 0), }; diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index edffc3489a12..ba587e5fc24f 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -38,6 +38,13 @@ struct bareudp_net { struct list_head bareudp_list; }; +struct bareudp_conf { + __be16 ethertype; + __be16 port; + u16 sport_min; + bool multi_proto_mode; +}; + /* Pseudo network device */ struct bareudp_dev { struct net *net; /* netns for packet i/o */ @@ -602,7 +609,8 @@ static struct bareudp_dev *bareudp_find_dev(struct bareudp_net *bn, } static int bareudp_configure(struct net *net, struct net_device *dev, - struct bareudp_conf *conf) + struct bareudp_conf *conf, + struct netlink_ext_ack *extack) { struct bareudp_net *bn = net_generic(net, bareudp_net_id); struct bareudp_dev *t, *bareudp = netdev_priv(dev); @@ -611,13 +619,17 @@ static int bareudp_configure(struct net *net, struct net_device *dev, bareudp->net = net; bareudp->dev = dev; t = bareudp_find_dev(bn, conf); - if (t) + if (t) { + NL_SET_ERR_MSG(extack, "Another bareudp device using the same port already exists"); return -EBUSY; + } if (conf->multi_proto_mode && (conf->ethertype != htons(ETH_P_MPLS_UC) && - conf->ethertype != htons(ETH_P_IP))) + conf->ethertype != htons(ETH_P_IP))) { + NL_SET_ERR_MSG(extack, "Cannot set multiproto mode for this ethertype (only IPv4 and unicast MPLS are supported)"); return -EINVAL; + } bareudp->port = conf->port; bareudp->ethertype = conf->ethertype; @@ -664,7 +676,7 @@ static int bareudp_newlink(struct net *net, struct net_device *dev, if (err) return err; - err = bareudp_configure(net, dev, &conf); + err = bareudp_configure(net, dev, &conf, extack); if (err) return err; @@ -721,40 +733,6 @@ static struct rtnl_link_ops bareudp_link_ops __read_mostly = { .fill_info = bareudp_fill_info, }; -struct net_device *bareudp_dev_create(struct net *net, const char *name, - u8 name_assign_type, - struct bareudp_conf *conf) -{ - struct nlattr *tb[IFLA_MAX + 1]; - struct net_device *dev; - int err; - - memset(tb, 0, sizeof(tb)); - dev = rtnl_create_link(net, name, name_assign_type, - &bareudp_link_ops, tb, NULL); - if (IS_ERR(dev)) - return dev; - - err = bareudp_configure(net, dev, conf); - if (err) { - free_netdev(dev); - return ERR_PTR(err); - } - err = dev_set_mtu(dev, IP_MAX_MTU - BAREUDP_BASE_HLEN); - if (err) - goto err; - - err = rtnl_configure_link(dev, NULL); - if (err < 0) - goto err; - - return dev; -err: - bareudp_dellink(dev, NULL); - return ERR_PTR(err); -} -EXPORT_SYMBOL_GPL(bareudp_dev_create); - static __net_init int bareudp_init_net(struct net *net) { struct bareudp_net *bn = net_generic(net, bareudp_net_id); diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 2ec8e015c7b3..533e476988f2 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1501,14 +1501,14 @@ void bond_alb_monitor(struct work_struct *work) struct slave *slave; if (!bond_has_slaves(bond)) { - bond_info->tx_rebalance_counter = 0; + atomic_set(&bond_info->tx_rebalance_counter, 0); bond_info->lp_counter = 0; goto re_arm; } rcu_read_lock(); - bond_info->tx_rebalance_counter++; + atomic_inc(&bond_info->tx_rebalance_counter); bond_info->lp_counter++; /* send learning packets */ @@ -1530,7 +1530,7 @@ void bond_alb_monitor(struct work_struct *work) } /* rebalance tx traffic */ - if (bond_info->tx_rebalance_counter >= BOND_TLB_REBALANCE_TICKS) { + if (atomic_read(&bond_info->tx_rebalance_counter) >= BOND_TLB_REBALANCE_TICKS) { bond_for_each_slave_rcu(bond, slave, iter) { tlb_clear_slave(bond, slave, 1); if (slave == rcu_access_pointer(bond->curr_active_slave)) { @@ -1540,7 +1540,7 @@ void bond_alb_monitor(struct work_struct *work) bond_info->unbalanced_load = 0; } } - bond_info->tx_rebalance_counter = 0; + atomic_set(&bond_info->tx_rebalance_counter, 0); } if (bond_info->rlb_enabled) { @@ -1610,7 +1610,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave) tlb_init_slave(slave); /* order a rebalance ASAP */ - bond->alb_info.tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS; + atomic_set(&bond->alb_info.tx_rebalance_counter, + BOND_TLB_REBALANCE_TICKS); if (bond->alb_info.rlb_enabled) bond->alb_info.rlb_rebalance = 1; @@ -1647,7 +1648,8 @@ void bond_alb_handle_link_change(struct bonding *bond, struct slave *slave, char rlb_clear_slave(bond, slave); } else if (link == BOND_LINK_UP) { /* order a rebalance ASAP */ - bond_info->tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS; + atomic_set(&bond_info->tx_rebalance_counter, + BOND_TLB_REBALANCE_TICKS); if (bond->alb_info.rlb_enabled) { bond->alb_info.rlb_rebalance = 1; /* If the updelay module parameter is smaller than the diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0f39ad2af81c..b60e22f6394a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1097,9 +1097,6 @@ static bool bond_should_notify_peers(struct bonding *bond) slave = rcu_dereference(bond->curr_active_slave); rcu_read_unlock(); - netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n", - slave ? slave->dev->name : "NULL"); - if (!slave || !bond->send_peer_notif || bond->send_peer_notif % max(1, bond->params.peer_notif_delay) != 0 || @@ -1107,6 +1104,9 @@ static bool bond_should_notify_peers(struct bonding *bond) test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return false; + netdev_dbg(bond->dev, "bond_should_notify_peers: slave %s\n", + slave ? slave->dev->name : "NULL"); + return true; } @@ -4094,6 +4094,7 @@ static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cm struct mii_ioctl_data *mii = NULL; const struct net_device_ops *ops; struct net_device *real_dev; + struct hwtstamp_config cfg; struct ifreq ifrr; int res = 0; @@ -4124,21 +4125,29 @@ static int bond_eth_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cm break; case SIOCSHWTSTAMP: case SIOCGHWTSTAMP: - rcu_read_lock(); - real_dev = bond_option_active_slave_get_rcu(bond); - rcu_read_unlock(); - if (real_dev) { - strscpy_pad(ifrr.ifr_name, real_dev->name, IFNAMSIZ); - ifrr.ifr_ifru = ifr->ifr_ifru; + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + if (cfg.flags & HWTSTAMP_FLAG_BONDED_PHC_INDEX) { + rcu_read_lock(); + real_dev = bond_option_active_slave_get_rcu(bond); + rcu_read_unlock(); + if (real_dev) { + strscpy_pad(ifrr.ifr_name, real_dev->name, IFNAMSIZ); + ifrr.ifr_ifru = ifr->ifr_ifru; - ops = real_dev->netdev_ops; - if (netif_device_present(real_dev) && ops->ndo_eth_ioctl) - res = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd); + ops = real_dev->netdev_ops; + if (netif_device_present(real_dev) && ops->ndo_eth_ioctl) { + res = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd); - if (!res) - ifr->ifr_ifru = ifrr.ifr_ifru; + if (!res) + ifr->ifr_ifru = ifrr.ifr_ifru; + + return res; + } + } } - break; + fallthrough; default: res = -EOPNOTSUPP; } diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index 0509625c3082..d5fca3bfaf9a 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -4,6 +4,7 @@ * Copyright (C) 2008-2009 Wolfgang Grandegger <wg@grandegger.com> */ +#include <linux/units.h> #include <linux/can/dev.h> #ifdef CONFIG_CAN_CALC_BITTIMING @@ -81,9 +82,9 @@ int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, if (bt->sample_point) { sample_point_nominal = bt->sample_point; } else { - if (bt->bitrate > 800 * CAN_KBPS) + if (bt->bitrate > 800 * KILO /* BPS */) sample_point_nominal = 750; - else if (bt->bitrate > 500 * CAN_KBPS) + else if (bt->bitrate > 500 * KILO /* BPS */) sample_point_nominal = 800; else sample_point_nominal = 875; diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 74d9899fc904..eb74cdf26b88 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -248,6 +248,9 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_SPACK_EWLR BIT(23) #define KVASER_PCIEFD_SPACK_EPLR BIT(24) +/* Kvaser KCAN_EPACK second word */ +#define KVASER_PCIEFD_EPACK_DIR_TX BIT(0) + struct kvaser_pciefd; struct kvaser_pciefd_can { @@ -1285,7 +1288,10 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can, can->err_rep_cnt++; can->can.can_stats.bus_error++; - stats->rx_errors++; + if (p->header[1] & KVASER_PCIEFD_EPACK_DIR_TX) + stats->tx_errors++; + else + stats->rx_errors++; can->bec.txerr = bec.txerr; can->bec.rxerr = bec.rxerr; diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 2470c47b2e31..c2a8421e7845 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -204,16 +204,16 @@ enum m_can_reg { /* Interrupts for version 3.0.x */ #define IR_ERR_LEC_30X (IR_STE | IR_FOE | IR_ACKE | IR_BE | IR_CRCE) -#define IR_ERR_BUS_30X (IR_ERR_LEC_30X | IR_WDI | IR_ELO | IR_BEU | \ - IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \ - IR_RF1L | IR_RF0L) +#define IR_ERR_BUS_30X (IR_ERR_LEC_30X | IR_WDI | IR_BEU | IR_BEC | \ + IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | IR_RF1L | \ + IR_RF0L) #define IR_ERR_ALL_30X (IR_ERR_STATE | IR_ERR_BUS_30X) /* Interrupts for version >= 3.1.x */ #define IR_ERR_LEC_31X (IR_PED | IR_PEA) -#define IR_ERR_BUS_31X (IR_ERR_LEC_31X | IR_WDI | IR_ELO | IR_BEU | \ - IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \ - IR_RF1L | IR_RF0L) +#define IR_ERR_BUS_31X (IR_ERR_LEC_31X | IR_WDI | IR_BEU | IR_BEC | \ + IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | IR_RF1L | \ + IR_RF0L) #define IR_ERR_ALL_31X (IR_ERR_STATE | IR_ERR_BUS_31X) /* Interrupt Line Select (ILS) */ @@ -517,7 +517,7 @@ static int m_can_read_fifo(struct net_device *dev, u32 rxfs) err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DATA, cf->data, DIV_ROUND_UP(cf->len, 4)); if (err) - goto out_fail; + goto out_free_skb; } /* acknowledge rx fifo 0 */ @@ -532,6 +532,8 @@ static int m_can_read_fifo(struct net_device *dev, u32 rxfs) return 0; +out_free_skb: + kfree_skb(skb); out_fail: netdev_err(dev, "FIFO read returned %d\n", err); return err; @@ -810,8 +812,6 @@ static void m_can_handle_other_err(struct net_device *dev, u32 irqstatus) { if (irqstatus & IR_WDI) netdev_err(dev, "Message RAM Watchdog event due to missing READY\n"); - if (irqstatus & IR_ELO) - netdev_err(dev, "Error Logging Overflow\n"); if (irqstatus & IR_BEU) netdev_err(dev, "Bit Error Uncorrected\n"); if (irqstatus & IR_BEC) @@ -1494,20 +1494,32 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) case 30: /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.x */ can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); - cdev->can.bittiming_const = &m_can_bittiming_const_30X; - cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X; + cdev->can.bittiming_const = cdev->bit_timing ? + cdev->bit_timing : &m_can_bittiming_const_30X; + + cdev->can.data_bittiming_const = cdev->data_timing ? + cdev->data_timing : + &m_can_data_bittiming_const_30X; break; case 31: /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */ can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); - cdev->can.bittiming_const = &m_can_bittiming_const_31X; - cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = cdev->bit_timing ? + cdev->bit_timing : &m_can_bittiming_const_31X; + + cdev->can.data_bittiming_const = cdev->data_timing ? + cdev->data_timing : + &m_can_data_bittiming_const_31X; break; case 32: case 33: /* Support both MCAN version v3.2.x and v3.3.0 */ - cdev->can.bittiming_const = &m_can_bittiming_const_31X; - cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X; + cdev->can.bittiming_const = cdev->bit_timing ? + cdev->bit_timing : &m_can_bittiming_const_31X; + + cdev->can.data_bittiming_const = cdev->data_timing ? + cdev->data_timing : + &m_can_data_bittiming_const_31X; cdev->can.ctrlmode_supported |= (m_can_niso_supported(cdev) ? diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index d18b515e6ccc..2c5d40997168 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -85,6 +85,9 @@ struct m_can_classdev { struct sk_buff *tx_skb; struct phy *transceiver; + const struct can_bittiming_const *bit_timing; + const struct can_bittiming_const *data_timing; + struct m_can_ops *ops; int version; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index 89cc3d41e952..b56a54d6c5a9 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -18,9 +18,14 @@ #define M_CAN_PCI_MMIO_BAR 0 -#define M_CAN_CLOCK_FREQ_EHL 100000000 #define CTL_CSR_INT_CTL_OFFSET 0x508 +struct m_can_pci_config { + const struct can_bittiming_const *bit_timing; + const struct can_bittiming_const *data_timing; + unsigned int clock_freq; +}; + struct m_can_pci_priv { struct m_can_classdev cdev; @@ -42,8 +47,13 @@ static u32 iomap_read_reg(struct m_can_classdev *cdev, int reg) static int iomap_read_fifo(struct m_can_classdev *cdev, int offset, void *val, size_t val_count) { struct m_can_pci_priv *priv = cdev_to_priv(cdev); + void __iomem *src = priv->base + offset; - ioread32_rep(priv->base + offset, val, val_count); + while (val_count--) { + *(unsigned int *)val = ioread32(src); + val += 4; + src += 4; + } return 0; } @@ -61,8 +71,13 @@ static int iomap_write_fifo(struct m_can_classdev *cdev, int offset, const void *val, size_t val_count) { struct m_can_pci_priv *priv = cdev_to_priv(cdev); + void __iomem *dst = priv->base + offset; - iowrite32_rep(priv->base + offset, val, val_count); + while (val_count--) { + iowrite32(*(unsigned int *)val, dst); + val += 4; + dst += 4; + } return 0; } @@ -74,9 +89,40 @@ static struct m_can_ops m_can_pci_ops = { .read_fifo = iomap_read_fifo, }; +static const struct can_bittiming_const m_can_bittiming_const_ehl = { + .name = KBUILD_MODNAME, + .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ + .tseg1_max = 64, + .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ + .tseg2_max = 128, + .sjw_max = 128, + .brp_min = 1, + .brp_max = 512, + .brp_inc = 1, +}; + +static const struct can_bittiming_const m_can_data_bittiming_const_ehl = { + .name = KBUILD_MODNAME, + .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */ + .tseg1_max = 16, + .tseg2_min = 1, /* Time segment 2 = phase_seg2 */ + .tseg2_max = 8, + .sjw_max = 4, + .brp_min = 1, + .brp_max = 32, + .brp_inc = 1, +}; + +static const struct m_can_pci_config m_can_pci_ehl = { + .bit_timing = &m_can_bittiming_const_ehl, + .data_timing = &m_can_data_bittiming_const_ehl, + .clock_freq = 200000000, +}; + static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) { struct device *dev = &pci->dev; + const struct m_can_pci_config *cfg; struct m_can_classdev *mcan_class; struct m_can_pci_priv *priv; void __iomem *base; @@ -104,6 +150,8 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) if (!mcan_class) return -ENOMEM; + cfg = (const struct m_can_pci_config *)id->driver_data; + priv = cdev_to_priv(mcan_class); priv->base = base; @@ -115,7 +163,9 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->dev = &pci->dev; mcan_class->net->irq = pci_irq_vector(pci, 0); mcan_class->pm_clock_support = 1; - mcan_class->can.clock.freq = id->driver_data; + mcan_class->bit_timing = cfg->bit_timing; + mcan_class->data_timing = cfg->data_timing; + mcan_class->can.clock.freq = cfg->clock_freq; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class); @@ -168,8 +218,8 @@ static SIMPLE_DEV_PM_OPS(m_can_pci_pm_ops, m_can_pci_suspend, m_can_pci_resume); static const struct pci_device_id m_can_pci_id_table[] = { - { PCI_VDEVICE(INTEL, 0x4bc1), M_CAN_CLOCK_FREQ_EHL, }, - { PCI_VDEVICE(INTEL, 0x4bc2), M_CAN_CLOCK_FREQ_EHL, }, + { PCI_VDEVICE(INTEL, 0x4bc1), (kernel_ulong_t)&m_can_pci_ehl, }, + { PCI_VDEVICE(INTEL, 0x4bc2), (kernel_ulong_t)&m_can_pci_ehl, }, { } /* Terminating Entry */ }; MODULE_DEVICE_TABLE(pci, m_can_pci_id_table); diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c index 92a54a5fd4c5..964c8a09226a 100644 --- a/drivers/net/can/pch_can.c +++ b/drivers/net/can/pch_can.c @@ -692,11 +692,11 @@ static int pch_can_rx_normal(struct net_device *ndev, u32 obj_num, int quota) cf->data[i + 1] = data_reg >> 8; } - netif_receive_skb(skb); rcv_pkts++; stats->rx_packets++; quota--; stats->rx_bytes += cf->len; + netif_receive_skb(skb); pch_fifo_thresh(priv, obj_num); obj_num++; diff --git a/drivers/net/can/sja1000/ems_pcmcia.c b/drivers/net/can/sja1000/ems_pcmcia.c index e21b169c14c0..4642b6d4aaf7 100644 --- a/drivers/net/can/sja1000/ems_pcmcia.c +++ b/drivers/net/can/sja1000/ems_pcmcia.c @@ -234,7 +234,12 @@ static int ems_pcmcia_add_card(struct pcmcia_device *pdev, unsigned long base) free_sja1000dev(dev); } - err = request_irq(dev->irq, &ems_pcmcia_interrupt, IRQF_SHARED, + if (!card->channels) { + err = -ENODEV; + goto failure_cleanup; + } + + err = request_irq(pdev->irq, &ems_pcmcia_interrupt, IRQF_SHARED, DRV_NAME, card); if (!err) return 0; diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index 89d9c986a229..a17641d36468 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -25,11 +25,11 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/kernel.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/netdevice.h> -#include <linux/of.h> -#include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/property.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> #include <linux/spi/spi.h> @@ -828,19 +828,25 @@ MODULE_DEVICE_TABLE(spi, hi3110_id_table); static int hi3110_can_probe(struct spi_device *spi) { - const struct of_device_id *of_id = of_match_device(hi3110_of_match, - &spi->dev); + struct device *dev = &spi->dev; struct net_device *net; struct hi3110_priv *priv; + const void *match; struct clk *clk; - int freq, ret; + u32 freq; + int ret; + + clk = devm_clk_get_optional(&spi->dev, NULL); + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "no CAN clock source defined\n"); - clk = devm_clk_get(&spi->dev, NULL); - if (IS_ERR(clk)) { - dev_err(&spi->dev, "no CAN clock source defined\n"); - return PTR_ERR(clk); + if (clk) { + freq = clk_get_rate(clk); + } else { + ret = device_property_read_u32(dev, "clock-frequency", &freq); + if (ret) + return dev_err_probe(dev, ret, "Failed to get clock-frequency!\n"); } - freq = clk_get_rate(clk); /* Sanity check */ if (freq > 40000000) @@ -851,11 +857,9 @@ static int hi3110_can_probe(struct spi_device *spi) if (!net) return -ENOMEM; - if (!IS_ERR(clk)) { - ret = clk_prepare_enable(clk); - if (ret) - goto out_free; - } + ret = clk_prepare_enable(clk); + if (ret) + goto out_free; net->netdev_ops = &hi3110_netdev_ops; net->flags |= IFF_ECHO; @@ -870,8 +874,9 @@ static int hi3110_can_probe(struct spi_device *spi) CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING; - if (of_id) - priv->model = (enum hi3110_model)(uintptr_t)of_id->data; + match = device_get_match_data(dev); + if (match) + priv->model = (enum hi3110_model)(uintptr_t)match; else priv->model = spi_get_device_id(spi)->driver_data; priv->net = net; @@ -918,9 +923,7 @@ static int hi3110_can_probe(struct spi_device *spi) ret = hi3110_hw_probe(spi); if (ret) { - if (ret == -ENODEV) - dev_err(&spi->dev, "Cannot initialize %x. Wrong wiring?\n", - priv->model); + dev_err_probe(dev, ret, "Cannot initialize %x. Wrong wiring?\n", priv->model); goto error_probe; } hi3110_hw_sleep(spi); @@ -938,14 +941,12 @@ static int hi3110_can_probe(struct spi_device *spi) hi3110_power_enable(priv->power, 0); out_clk: - if (!IS_ERR(clk)) - clk_disable_unprepare(clk); + clk_disable_unprepare(clk); out_free: free_candev(net); - dev_err(&spi->dev, "Probe failed, err=%d\n", -ret); - return ret; + return dev_err_probe(dev, ret, "Probe failed\n"); } static int hi3110_can_remove(struct spi_device *spi) @@ -957,8 +958,7 @@ static int hi3110_can_remove(struct spi_device *spi) hi3110_power_enable(priv->power, 0); - if (!IS_ERR(priv->clk)) - clk_disable_unprepare(priv->clk); + clk_disable_unprepare(priv->clk); free_candev(net); diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 54aa7c25c4de..37862e7f6840 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -61,6 +61,7 @@ #include <linux/of.h> #include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/reset.h> #define DRV_NAME "sun4i_can" @@ -200,10 +201,20 @@ #define SUN4I_CAN_MAX_IRQ 20 #define SUN4I_MODE_MAX_RETRIES 100 +/** + * struct sun4ican_quirks - Differences between SoC variants. + * + * @has_reset: SoC needs reset deasserted. + */ +struct sun4ican_quirks { + bool has_reset; +}; + struct sun4ican_priv { struct can_priv can; void __iomem *base; struct clk *clk; + struct reset_control *reset; spinlock_t cmdreg_lock; /* lock for concurrent cmd register writes */ }; @@ -702,6 +713,13 @@ static int sun4ican_open(struct net_device *dev) goto exit_irq; } + /* software reset deassert */ + err = reset_control_deassert(priv->reset); + if (err) { + netdev_err(dev, "could not deassert CAN reset\n"); + goto exit_soft_reset; + } + /* turn on clocking for CAN peripheral block */ err = clk_prepare_enable(priv->clk); if (err) { @@ -723,6 +741,8 @@ static int sun4ican_open(struct net_device *dev) exit_can_start: clk_disable_unprepare(priv->clk); exit_clock: + reset_control_assert(priv->reset); +exit_soft_reset: free_irq(dev->irq, dev); exit_irq: close_candev(dev); @@ -736,6 +756,7 @@ static int sun4ican_close(struct net_device *dev) netif_stop_queue(dev); sun4i_can_stop(dev); clk_disable_unprepare(priv->clk); + reset_control_assert(priv->reset); free_irq(dev->irq, dev); close_candev(dev); @@ -750,9 +771,27 @@ static const struct net_device_ops sun4ican_netdev_ops = { .ndo_start_xmit = sun4ican_start_xmit, }; +static const struct sun4ican_quirks sun4ican_quirks_a10 = { + .has_reset = false, +}; + +static const struct sun4ican_quirks sun4ican_quirks_r40 = { + .has_reset = true, +}; + static const struct of_device_id sun4ican_of_match[] = { - {.compatible = "allwinner,sun4i-a10-can"}, - {}, + { + .compatible = "allwinner,sun4i-a10-can", + .data = &sun4ican_quirks_a10 + }, { + .compatible = "allwinner,sun7i-a20-can", + .data = &sun4ican_quirks_a10 + }, { + .compatible = "allwinner,sun8i-r40-can", + .data = &sun4ican_quirks_r40 + }, { + /* sentinel */ + }, }; MODULE_DEVICE_TABLE(of, sun4ican_of_match); @@ -771,10 +810,28 @@ static int sun4ican_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct clk *clk; + struct reset_control *reset = NULL; void __iomem *addr; int err, irq; struct net_device *dev; struct sun4ican_priv *priv; + const struct sun4ican_quirks *quirks; + + quirks = of_device_get_match_data(&pdev->dev); + if (!quirks) { + dev_err(&pdev->dev, "failed to determine the quirks to use\n"); + err = -ENODEV; + goto exit; + } + + if (quirks->has_reset) { + reset = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (IS_ERR(reset)) { + dev_err(&pdev->dev, "unable to request reset\n"); + err = PTR_ERR(reset); + goto exit; + } + } clk = of_clk_get(np, 0); if (IS_ERR(clk)) { @@ -818,6 +875,7 @@ static int sun4ican_probe(struct platform_device *pdev) CAN_CTRLMODE_3_SAMPLES; priv->base = addr; priv->clk = clk; + priv->reset = reset; spin_lock_init(&priv->cmdreg_lock); platform_set_drvdata(pdev, dev); diff --git a/drivers/net/can/usb/etas_es58x/es581_4.c b/drivers/net/can/usb/etas_es58x/es581_4.c index 14e360c9f2c9..1bcdcece5ec7 100644 --- a/drivers/net/can/usb/etas_es58x/es581_4.c +++ b/drivers/net/can/usb/etas_es58x/es581_4.c @@ -10,6 +10,7 @@ */ #include <linux/kernel.h> +#include <linux/units.h> #include <asm/unaligned.h> #include "es58x_core.h" @@ -469,8 +470,8 @@ const struct es58x_parameters es581_4_param = { .bittiming_const = &es581_4_bittiming_const, .data_bittiming_const = NULL, .tdc_const = NULL, - .bitrate_max = 1 * CAN_MBPS, - .clock = {.freq = 50 * CAN_MHZ}, + .bitrate_max = 1 * MEGA /* BPS */, + .clock = {.freq = 50 * MEGA /* Hz */}, .ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC, .tx_start_of_frame = 0xAFAF, .rx_start_of_frame = 0xFAFA, diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c index 4f0cae29f4d8..ec87126e1a7d 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_fd.c +++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c @@ -12,6 +12,7 @@ */ #include <linux/kernel.h> +#include <linux/units.h> #include <asm/unaligned.h> #include "es58x_core.h" @@ -522,8 +523,8 @@ const struct es58x_parameters es58x_fd_param = { * Mbps work in an optimal environment but are not recommended * for production environment. */ - .bitrate_max = 8 * CAN_MBPS, - .clock = {.freq = 80 * CAN_MHZ}, + .bitrate_max = 8 * MEGA /* BPS */, + .clock = {.freq = 80 * MEGA /* Hz */}, .ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO | CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO, diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 59ba7c7beec0..f7af1bf5ab46 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -28,10 +28,6 @@ #include "kvaser_usb.h" -/* Forward declaration */ -static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg; - -#define CAN_USB_CLOCK 8000000 #define MAX_USBCAN_NET_DEVICES 2 /* Command header size */ @@ -80,6 +76,12 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg; #define CMD_LEAF_LOG_MESSAGE 106 +/* Leaf frequency options */ +#define KVASER_USB_LEAF_SWOPTION_FREQ_MASK 0x60 +#define KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK 0 +#define KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK BIT(5) +#define KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK BIT(6) + /* error factors */ #define M16C_EF_ACKE BIT(0) #define M16C_EF_CRCE BIT(1) @@ -340,6 +342,50 @@ struct kvaser_usb_err_summary { }; }; +static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = { + .name = "kvaser_usb", + .tseg1_min = KVASER_USB_TSEG1_MIN, + .tseg1_max = KVASER_USB_TSEG1_MAX, + .tseg2_min = KVASER_USB_TSEG2_MIN, + .tseg2_max = KVASER_USB_TSEG2_MAX, + .sjw_max = KVASER_USB_SJW_MAX, + .brp_min = KVASER_USB_BRP_MIN, + .brp_max = KVASER_USB_BRP_MAX, + .brp_inc = KVASER_USB_BRP_INC, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_8mhz = { + .clock = { + .freq = 8000000, + }, + .timestamp_freq = 1, + .bittiming_const = &kvaser_usb_leaf_bittiming_const, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_16mhz = { + .clock = { + .freq = 16000000, + }, + .timestamp_freq = 1, + .bittiming_const = &kvaser_usb_leaf_bittiming_const, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_24mhz = { + .clock = { + .freq = 24000000, + }, + .timestamp_freq = 1, + .bittiming_const = &kvaser_usb_leaf_bittiming_const, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_32mhz = { + .clock = { + .freq = 32000000, + }, + .timestamp_freq = 1, + .bittiming_const = &kvaser_usb_leaf_bittiming_const, +}; + static void * kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv, const struct sk_buff *skb, int *frame_len, @@ -471,6 +517,27 @@ static int kvaser_usb_leaf_send_simple_cmd(const struct kvaser_usb *dev, return rc; } +static void kvaser_usb_leaf_get_software_info_leaf(struct kvaser_usb *dev, + const struct leaf_cmd_softinfo *softinfo) +{ + u32 sw_options = le32_to_cpu(softinfo->sw_options); + + dev->fw_version = le32_to_cpu(softinfo->fw_version); + dev->max_tx_urbs = le16_to_cpu(softinfo->max_outstanding_tx); + + switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) { + case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK: + dev->cfg = &kvaser_usb_leaf_dev_cfg_16mhz; + break; + case KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK: + dev->cfg = &kvaser_usb_leaf_dev_cfg_24mhz; + break; + case KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK: + dev->cfg = &kvaser_usb_leaf_dev_cfg_32mhz; + break; + } +} + static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev) { struct kvaser_cmd cmd; @@ -486,14 +553,13 @@ static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev) switch (dev->card_data.leaf.family) { case KVASER_LEAF: - dev->fw_version = le32_to_cpu(cmd.u.leaf.softinfo.fw_version); - dev->max_tx_urbs = - le16_to_cpu(cmd.u.leaf.softinfo.max_outstanding_tx); + kvaser_usb_leaf_get_software_info_leaf(dev, &cmd.u.leaf.softinfo); break; case KVASER_USBCAN: dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version); dev->max_tx_urbs = le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx); + dev->cfg = &kvaser_usb_leaf_dev_cfg_8mhz; break; } @@ -1225,24 +1291,11 @@ static int kvaser_usb_leaf_init_card(struct kvaser_usb *dev) { struct kvaser_usb_dev_card_data *card_data = &dev->card_data; - dev->cfg = &kvaser_usb_leaf_dev_cfg; card_data->ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES; return 0; } -static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = { - .name = "kvaser_usb", - .tseg1_min = KVASER_USB_TSEG1_MIN, - .tseg1_max = KVASER_USB_TSEG1_MAX, - .tseg2_min = KVASER_USB_TSEG2_MIN, - .tseg2_max = KVASER_USB_TSEG2_MAX, - .sjw_max = KVASER_USB_SJW_MAX, - .brp_min = KVASER_USB_BRP_MIN, - .brp_max = KVASER_USB_BRP_MAX, - .brp_inc = KVASER_USB_BRP_INC, -}; - static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev) { struct kvaser_usb_net_priv *priv = netdev_priv(netdev); @@ -1348,11 +1401,3 @@ const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = { .dev_read_bulk_callback = kvaser_usb_leaf_read_bulk_callback, .dev_frame_to_cmd = kvaser_usb_leaf_frame_to_cmd, }; - -static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg = { - .clock = { - .freq = CAN_USB_CLOCK, - }, - .timestamp_freq = 1, - .bittiming_const = &kvaser_usb_leaf_bittiming_const, -}; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index af4761968733..3867f3d4545f 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1860,7 +1860,8 @@ int b53_mdb_del(struct dsa_switch *ds, int port, } EXPORT_SYMBOL(b53_mdb_del); -int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) +int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, + bool *tx_fwd_offload) { struct b53_device *dev = ds->priv; s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index; @@ -1887,7 +1888,7 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan); b53_for_each_port(dev, i) { - if (dsa_to_port(ds, i)->bridge_dev != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Add this local port to the remote port VLAN control @@ -1911,7 +1912,7 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) } EXPORT_SYMBOL(b53_br_join); -void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) +void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { struct b53_device *dev = ds->priv; struct b53_vlan *vl = &dev->vlans[0]; @@ -1923,7 +1924,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) b53_for_each_port(dev, i) { /* Don't touch the remaining ports */ - if (dsa_to_port(ds, i)->bridge_dev != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), ®); diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 579da74ada64..b41dc8ac2ca8 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -324,8 +324,9 @@ void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset, void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data); int b53_get_sset_count(struct dsa_switch *ds, int port, int sset); void b53_get_ethtool_phy_stats(struct dsa_switch *ds, int port, uint64_t *data); -int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge); -void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge); +int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge, + bool *tx_fwd_offload); +void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state); void b53_br_fast_age(struct dsa_switch *ds, int port); int b53_br_flags_pre(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index e638e3eea911..33daaf10c488 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -167,19 +167,20 @@ static int dsa_loop_phy_write(struct dsa_switch *ds, int port, } static int dsa_loop_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge, + bool *tx_fwd_offload) { dev_dbg(ds->dev, "%s: port: %d, bridge: %s\n", - __func__, port, bridge->name); + __func__, port, bridge.dev->name); return 0; } static void dsa_loop_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { dev_dbg(ds->dev, "%s: port: %d, bridge: %s\n", - __func__, port, bridge->name); + __func__, port, bridge.dev->name); } static void dsa_loop_port_stp_state_set(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 86839b43011b..726f267cb228 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -674,7 +674,8 @@ static int hellcreek_bridge_flags(struct dsa_switch *ds, int port, } static int hellcreek_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge, + bool *tx_fwd_offload) { struct hellcreek *hellcreek = ds->priv; @@ -691,7 +692,7 @@ static int hellcreek_port_bridge_join(struct dsa_switch *ds, int port, } static void hellcreek_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct hellcreek *hellcreek = ds->priv; @@ -710,8 +711,9 @@ static int __hellcreek_fdb_add(struct hellcreek *hellcreek, u16 meta = 0; dev_dbg(hellcreek->dev, "Add static FDB entry: MAC=%pM, MASK=0x%02x, " - "OBT=%d, REPRIO_EN=%d, PRIO=%d\n", entry->mac, entry->portmask, - entry->is_obt, entry->reprio_en, entry->reprio_tc); + "OBT=%d, PASS_BLOCKED=%d, REPRIO_EN=%d, PRIO=%d\n", entry->mac, + entry->portmask, entry->is_obt, entry->pass_blocked, + entry->reprio_en, entry->reprio_tc); /* Add mac address */ hellcreek_write(hellcreek, entry->mac[1] | (entry->mac[0] << 8), HR_FDBWDH); @@ -722,6 +724,8 @@ static int __hellcreek_fdb_add(struct hellcreek *hellcreek, meta |= entry->portmask << HR_FDBWRM0_PORTMASK_SHIFT; if (entry->is_obt) meta |= HR_FDBWRM0_OBT; + if (entry->pass_blocked) + meta |= HR_FDBWRM0_PASS_BLOCKED; if (entry->reprio_en) { meta |= HR_FDBWRM0_REPRIO_EN; meta |= entry->reprio_tc << HR_FDBWRM0_REPRIO_TC_SHIFT; @@ -1049,7 +1053,7 @@ static void hellcreek_setup_tc_identity_mapping(struct hellcreek *hellcreek) static int hellcreek_setup_fdb(struct hellcreek *hellcreek) { - static struct hellcreek_fdb_entry ptp = { + static struct hellcreek_fdb_entry l2_ptp = { /* MAC: 01-1B-19-00-00-00 */ .mac = { 0x01, 0x1b, 0x19, 0x00, 0x00, 0x00 }, .portmask = 0x03, /* Management ports */ @@ -1060,24 +1064,94 @@ static int hellcreek_setup_fdb(struct hellcreek *hellcreek) .reprio_tc = 6, /* TC: 6 as per IEEE 802.1AS */ .reprio_en = 1, }; - static struct hellcreek_fdb_entry p2p = { + static struct hellcreek_fdb_entry udp4_ptp = { + /* MAC: 01-00-5E-00-01-81 */ + .mac = { 0x01, 0x00, 0x5e, 0x00, 0x01, 0x81 }, + .portmask = 0x03, /* Management ports */ + .age = 0, + .is_obt = 0, + .pass_blocked = 0, + .is_static = 1, + .reprio_tc = 6, + .reprio_en = 1, + }; + static struct hellcreek_fdb_entry udp6_ptp = { + /* MAC: 33-33-00-00-01-81 */ + .mac = { 0x33, 0x33, 0x00, 0x00, 0x01, 0x81 }, + .portmask = 0x03, /* Management ports */ + .age = 0, + .is_obt = 0, + .pass_blocked = 0, + .is_static = 1, + .reprio_tc = 6, + .reprio_en = 1, + }; + static struct hellcreek_fdb_entry l2_p2p = { /* MAC: 01-80-C2-00-00-0E */ .mac = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x0e }, .portmask = 0x03, /* Management ports */ .age = 0, .is_obt = 0, - .pass_blocked = 0, + .pass_blocked = 1, .is_static = 1, .reprio_tc = 6, /* TC: 6 as per IEEE 802.1AS */ .reprio_en = 1, }; + static struct hellcreek_fdb_entry udp4_p2p = { + /* MAC: 01-00-5E-00-00-6B */ + .mac = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x6b }, + .portmask = 0x03, /* Management ports */ + .age = 0, + .is_obt = 0, + .pass_blocked = 1, + .is_static = 1, + .reprio_tc = 6, + .reprio_en = 1, + }; + static struct hellcreek_fdb_entry udp6_p2p = { + /* MAC: 33-33-00-00-00-6B */ + .mac = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x6b }, + .portmask = 0x03, /* Management ports */ + .age = 0, + .is_obt = 0, + .pass_blocked = 1, + .is_static = 1, + .reprio_tc = 6, + .reprio_en = 1, + }; + static struct hellcreek_fdb_entry stp = { + /* MAC: 01-80-C2-00-00-00 */ + .mac = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }, + .portmask = 0x03, /* Management ports */ + .age = 0, + .is_obt = 0, + .pass_blocked = 1, + .is_static = 1, + .reprio_tc = 6, + .reprio_en = 1, + }; int ret; mutex_lock(&hellcreek->reg_lock); - ret = __hellcreek_fdb_add(hellcreek, &ptp); + ret = __hellcreek_fdb_add(hellcreek, &l2_ptp); + if (ret) + goto out; + ret = __hellcreek_fdb_add(hellcreek, &udp4_ptp); + if (ret) + goto out; + ret = __hellcreek_fdb_add(hellcreek, &udp6_ptp); + if (ret) + goto out; + ret = __hellcreek_fdb_add(hellcreek, &l2_p2p); + if (ret) + goto out; + ret = __hellcreek_fdb_add(hellcreek, &udp4_p2p); + if (ret) + goto out; + ret = __hellcreek_fdb_add(hellcreek, &udp6_p2p); if (ret) goto out; - ret = __hellcreek_fdb_add(hellcreek, &p2p); + ret = __hellcreek_fdb_add(hellcreek, &stp); out: mutex_unlock(&hellcreek->reg_lock); diff --git a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c index 40b41c794dfa..b3bc948d6145 100644 --- a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c +++ b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c @@ -52,10 +52,6 @@ static int hellcreek_set_hwtstamp_config(struct hellcreek *hellcreek, int port, */ clear_bit_unlock(HELLCREEK_HWTSTAMP_ENABLED, &ps->state); - /* Reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_ON: tx_tstamp_enable = true; diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 89f920289ae2..d55784d19fa4 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1103,12 +1103,13 @@ static void lan9303_port_disable(struct dsa_switch *ds, int port) } static int lan9303_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge, + bool *tx_fwd_offload) { struct lan9303 *chip = ds->priv; dev_dbg(chip->dev, "%s(port %d)\n", __func__, port); - if (dsa_to_port(ds, 1)->bridge_dev == dsa_to_port(ds, 2)->bridge_dev) { + if (dsa_port_bridge_same(dsa_to_port(ds, 1), dsa_to_port(ds, 2))) { lan9303_bridge_ports(chip); chip->is_bridged = true; /* unleash stp_state_set() */ } @@ -1117,7 +1118,7 @@ static int lan9303_port_bridge_join(struct dsa_switch *ds, int port, } static void lan9303_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct lan9303 *chip = ds->priv; diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 583af774e1bd..46ed953e787e 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -759,7 +759,7 @@ static int gswip_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack) { - struct net_device *bridge = dsa_to_port(ds, port)->bridge_dev; + struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); struct gswip_priv *priv = ds->priv; /* Do not allow changing the VLAN filtering options while in bridge */ @@ -1146,16 +1146,18 @@ static int gswip_vlan_remove(struct gswip_priv *priv, } static int gswip_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge, + bool *tx_fwd_offload) { + struct net_device *br = bridge.dev; struct gswip_priv *priv = ds->priv; int err; /* When the bridge uses VLAN filtering we have to configure VLAN * specific bridges. No bridge is configured here. */ - if (!br_vlan_enabled(bridge)) { - err = gswip_vlan_add_unaware(priv, bridge, port); + if (!br_vlan_enabled(br)) { + err = gswip_vlan_add_unaware(priv, br, port); if (err) return err; priv->port_vlan_filter &= ~BIT(port); @@ -1166,8 +1168,9 @@ static int gswip_port_bridge_join(struct dsa_switch *ds, int port, } static void gswip_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { + struct net_device *br = bridge.dev; struct gswip_priv *priv = ds->priv; gswip_add_single_port_br(priv, port, true); @@ -1175,16 +1178,16 @@ static void gswip_port_bridge_leave(struct dsa_switch *ds, int port, /* When the bridge uses VLAN filtering we have to configure VLAN * specific bridges. No bridge is configured here. */ - if (!br_vlan_enabled(bridge)) - gswip_vlan_remove(priv, bridge, port, 0, true, false); + if (!br_vlan_enabled(br)) + gswip_vlan_remove(priv, br, port, 0, true, false); } static int gswip_port_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) { + struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); struct gswip_priv *priv = ds->priv; - struct net_device *bridge = dsa_to_port(ds, port)->bridge_dev; unsigned int max_ports = priv->hw_info->max_ports; int pos = max_ports; int i, idx = -1; @@ -1229,8 +1232,8 @@ static int gswip_port_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) { + struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); struct gswip_priv *priv = ds->priv; - struct net_device *bridge = dsa_to_port(ds, port)->bridge_dev; bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; int err; @@ -1254,8 +1257,8 @@ static int gswip_port_vlan_add(struct dsa_switch *ds, int port, static int gswip_port_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { + struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); struct gswip_priv *priv = ds->priv; - struct net_device *bridge = dsa_to_port(ds, port)->bridge_dev; bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; /* We have to receive all packets on the CPU port and should not @@ -1340,8 +1343,8 @@ static void gswip_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) static int gswip_port_fdb(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, bool add) { + struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); struct gswip_priv *priv = ds->priv; - struct net_device *bridge = dsa_to_port(ds, port)->bridge_dev; struct gswip_pce_table_entry mac_bridge = {0,}; unsigned int cpu_port = priv->hw_info->cpu_port; int fid = -1; diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 8a04302018dc..55dbda04ea62 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -43,7 +43,7 @@ void ksz_update_port_member(struct ksz_device *dev, int port) continue; if (port == i) continue; - if (!dp->bridge_dev || dp->bridge_dev != other_dp->bridge_dev) + if (!dsa_port_bridge_same(dp, other_dp)) continue; if (other_p->stp_state == BR_STATE_FORWARDING && @@ -192,7 +192,8 @@ void ksz_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *buf) EXPORT_SYMBOL_GPL(ksz_get_ethtool_stats); int ksz_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge, + bool *tx_fwd_offload) { /* port_stp_state_set() will be called after to put the port in * appropriate state so there is no need to do anything. @@ -203,7 +204,7 @@ int ksz_port_bridge_join(struct dsa_switch *ds, int port, EXPORT_SYMBOL_GPL(ksz_port_bridge_join); void ksz_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { /* port_stp_state_set() will be called after to put the port in * forwarding state so there is no need to do anything. @@ -301,7 +302,6 @@ int ksz_port_mdb_del(struct dsa_switch *ds, int port, struct ksz_device *dev = ds->priv; struct alu_struct alu; int index; - int ret = 0; for (index = 0; index < dev->num_statics; index++) { if (!dev->dev_ops->r_sta_mac_table(dev, index, &alu)) { @@ -323,7 +323,7 @@ int ksz_port_mdb_del(struct dsa_switch *ds, int port, dev->dev_ops->w_sta_mac_table(dev, index, &alu); exit: - return ret; + return 0; } EXPORT_SYMBOL_GPL(ksz_port_mdb_del); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 54b456bc8972..df8ae59c8525 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -155,9 +155,9 @@ void ksz_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, int ksz_sset_count(struct dsa_switch *ds, int port, int sset); void ksz_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *buf); int ksz_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br); + struct dsa_bridge bridge, bool *tx_fwd_offload); void ksz_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br); + struct dsa_bridge bridge); void ksz_port_fast_age(struct dsa_switch *ds, int port); int ksz_port_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 9890672a206d..b82512e5b33b 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1186,29 +1186,33 @@ mt7530_port_bridge_flags(struct dsa_switch *ds, int port, static int mt7530_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge, bool *tx_fwd_offload) { - struct mt7530_priv *priv = ds->priv; + struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; u32 port_bitmap = BIT(MT7530_CPU_PORT); - int i; + struct mt7530_priv *priv = ds->priv; mutex_lock(&priv->reg_mutex); - for (i = 0; i < MT7530_NUM_PORTS; i++) { + dsa_switch_for_each_user_port(other_dp, ds) { + int other_port = other_dp->index; + + if (dp == other_dp) + continue; + /* Add this port to the port matrix of the other ports in the * same bridge. If the port is disabled, port matrix is kept * and not being setup until the port becomes enabled. */ - if (dsa_is_user_port(ds, i) && i != port) { - if (dsa_to_port(ds, i)->bridge_dev != bridge) - continue; - if (priv->ports[i].enable) - mt7530_set(priv, MT7530_PCR_P(i), - PCR_MATRIX(BIT(port))); - priv->ports[i].pm |= PCR_MATRIX(BIT(port)); + if (!dsa_port_offloads_bridge(other_dp, &bridge)) + continue; - port_bitmap |= BIT(i); - } + if (priv->ports[other_port].enable) + mt7530_set(priv, MT7530_PCR_P(other_port), + PCR_MATRIX(BIT(port))); + priv->ports[other_port].pm |= PCR_MATRIX(BIT(port)); + + port_bitmap |= BIT(other_port); } /* Add the all other ports to this port matrix. */ @@ -1236,7 +1240,7 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port) /* This is called after .port_bridge_leave when leaving a VLAN-aware * bridge. Don't set standalone ports to fallback mode. */ - if (dsa_to_port(ds, port)->bridge_dev) + if (dsa_port_bridge_dev_get(dsa_to_port(ds, port))) mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK, MT7530_PORT_FALLBACK_MODE); @@ -1299,26 +1303,30 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) static void mt7530_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { + struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; struct mt7530_priv *priv = ds->priv; - int i; mutex_lock(&priv->reg_mutex); - for (i = 0; i < MT7530_NUM_PORTS; i++) { + dsa_switch_for_each_user_port(other_dp, ds) { + int other_port = other_dp->index; + + if (dp == other_dp) + continue; + /* Remove this port from the port matrix of the other ports * in the same bridge. If the port is disabled, port matrix * is kept and not being setup until the port becomes enabled. */ - if (dsa_is_user_port(ds, i) && i != port) { - if (dsa_to_port(ds, i)->bridge_dev != bridge) - continue; - if (priv->ports[i].enable) - mt7530_clear(priv, MT7530_PCR_P(i), - PCR_MATRIX(BIT(port))); - priv->ports[i].pm &= ~PCR_MATRIX(BIT(port)); - } + if (!dsa_port_offloads_bridge(other_dp, &bridge)) + continue; + + if (priv->ports[other_port].enable) + mt7530_clear(priv, MT7530_PCR_P(other_port), + PCR_MATRIX(BIT(port))); + priv->ports[other_port].pm &= ~PCR_MATRIX(BIT(port)); } /* Set the cpu port to be the only one in the port matrix of diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index f00cbf5753b9..58ca684d73f7 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -471,6 +471,12 @@ static int mv88e6xxx_port_ppu_updates(struct mv88e6xxx_chip *chip, int port) u16 reg; int err; + /* The 88e6250 family does not have the PHY detect bit. Instead, + * report whether the port is internal. + */ + if (chip->info->family == MV88E6XXX_FAMILY_6250) + return port < chip->info->num_internal_phys; + err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®); if (err) { dev_err(chip->dev, @@ -692,44 +698,48 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, { struct mv88e6xxx_chip *chip = ds->priv; struct mv88e6xxx_port *p; - int err; + int err = 0; p = &chip->ports[port]; - /* FIXME: is this the correct test? If we're in fixed mode on an - * internal port, why should we process this any different from - * PHY mode? On the other hand, the port may be automedia between - * an internal PHY and the serdes... - */ - if ((mode == MLO_AN_PHY) && mv88e6xxx_phy_is_internal(ds, port)) - return; - mv88e6xxx_reg_lock(chip); - /* In inband mode, the link may come up at any time while the link - * is not forced down. Force the link down while we reconfigure the - * interface mode. - */ - if (mode == MLO_AN_INBAND && p->interface != state->interface && - chip->info->ops->port_set_link) - chip->info->ops->port_set_link(chip, port, LINK_FORCED_DOWN); - - err = mv88e6xxx_port_config_interface(chip, port, state->interface); - if (err && err != -EOPNOTSUPP) - goto err_unlock; - err = mv88e6xxx_serdes_pcs_config(chip, port, mode, state->interface, - state->advertising); - /* FIXME: we should restart negotiation if something changed - which - * is something we get if we convert to using phylinks PCS operations. - */ - if (err > 0) - err = 0; + if (mode != MLO_AN_PHY || !mv88e6xxx_phy_is_internal(ds, port)) { + /* In inband mode, the link may come up at any time while the + * link is not forced down. Force the link down while we + * reconfigure the interface mode. + */ + if (mode == MLO_AN_INBAND && + p->interface != state->interface && + chip->info->ops->port_set_link) + chip->info->ops->port_set_link(chip, port, + LINK_FORCED_DOWN); + + err = mv88e6xxx_port_config_interface(chip, port, + state->interface); + if (err && err != -EOPNOTSUPP) + goto err_unlock; + + err = mv88e6xxx_serdes_pcs_config(chip, port, mode, + state->interface, + state->advertising); + /* FIXME: we should restart negotiation if something changed - + * which is something we get if we convert to using phylinks + * PCS operations. + */ + if (err > 0) + err = 0; + } /* Undo the forced down state above after completing configuration - * irrespective of its state on entry, which allows the link to come up. + * irrespective of its state on entry, which allows the link to come + * up in the in-band case where there is no separate SERDES. Also + * ensure that the link can come up if the PPU is in use and we are + * in PHY mode (we treat the PPU as an effective in-band mechanism.) */ - if (mode == MLO_AN_INBAND && p->interface != state->interface && - chip->info->ops->port_set_link) + if (chip->info->ops->port_set_link && + ((mode == MLO_AN_INBAND && p->interface != state->interface) || + (mode == MLO_AN_PHY && mv88e6xxx_port_ppu_updates(chip, port)))) chip->info->ops->port_set_link(chip, port, LINK_UNFORCED); p->interface = state->interface; @@ -752,13 +762,16 @@ static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, ops = chip->info->ops; mv88e6xxx_reg_lock(chip); - /* Internal PHYs propagate their configuration directly to the MAC. - * External PHYs depend on whether the PPU is enabled for this port. + /* Force the link down if we know the port may not be automatically + * updated by the switch or if we are using fixed-link mode. */ - if (((!mv88e6xxx_phy_is_internal(ds, port) && - !mv88e6xxx_port_ppu_updates(chip, port)) || + if ((!mv88e6xxx_port_ppu_updates(chip, port) || mode == MLO_AN_FIXED) && ops->port_sync_link) err = ops->port_sync_link(chip, port, mode, false); + + if (!err && ops->port_set_speed_duplex) + err = ops->port_set_speed_duplex(chip, port, SPEED_UNFORCED, + DUPLEX_UNFORCED); mv88e6xxx_reg_unlock(chip); if (err) @@ -779,11 +792,11 @@ static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port, ops = chip->info->ops; mv88e6xxx_reg_lock(chip); - /* Internal PHYs propagate their configuration directly to the MAC. - * External PHYs depend on whether the PPU is enabled for this port. + /* Configure and force the link up if we know that the port may not + * automatically updated by the switch or if we are using fixed-link + * mode. */ - if ((!mv88e6xxx_phy_is_internal(ds, port) && - !mv88e6xxx_port_ppu_updates(chip, port)) || + if (!mv88e6xxx_port_ppu_updates(chip, port) || mode == MLO_AN_FIXED) { /* FIXME: for an automedia port, should we force the link * down here - what if the link comes up due to "other" media @@ -1228,8 +1241,7 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port) { struct dsa_switch *ds = chip->ds; struct dsa_switch_tree *dst = ds->dst; - struct net_device *br; - struct dsa_port *dp; + struct dsa_port *dp, *other_dp; bool found = false; u16 pvlan; @@ -1238,11 +1250,9 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port) list_for_each_entry(dp, &dst->ports, list) { if (dp->ds->index == dev && dp->index == port) { /* dp might be a DSA link or a user port, so it - * might or might not have a bridge_dev - * pointer. Use the "found" variable for both - * cases. + * might or might not have a bridge. + * Use the "found" variable for both cases. */ - br = dp->bridge_dev; found = true; break; } @@ -1250,13 +1260,14 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port) /* dev is a virtual bridge */ } else { list_for_each_entry(dp, &dst->ports, list) { - if (dp->bridge_num < 0) + unsigned int bridge_num = dsa_port_bridge_num_get(dp); + + if (!bridge_num) continue; - if (dp->bridge_num + 1 + dst->last_switch != dev) + if (bridge_num + dst->last_switch != dev) continue; - br = dp->bridge_dev; found = true; break; } @@ -1275,12 +1286,11 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port) /* Frames from user ports can egress any local DSA links and CPU ports, * as well as any local member of their bridge group. */ - list_for_each_entry(dp, &dst->ports, list) - if (dp->ds == ds && - (dp->type == DSA_PORT_TYPE_CPU || - dp->type == DSA_PORT_TYPE_DSA || - (br && dp->bridge_dev == br))) - pvlan |= BIT(dp->index); + dsa_switch_for_each_port(other_dp, ds) + if (other_dp->type == DSA_PORT_TYPE_CPU || + other_dp->type == DSA_PORT_TYPE_DSA || + dsa_port_bridge_same(dp, other_dp)) + pvlan |= BIT(other_dp->index); return pvlan; } @@ -1647,12 +1657,13 @@ static int mv88e6xxx_atu_new(struct mv88e6xxx_chip *chip, u16 *fid) static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, u16 vid) { + struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; struct mv88e6xxx_chip *chip = ds->priv; struct mv88e6xxx_vtu_entry vlan; - int i, err; + int err; /* DSA and CPU ports have to be members of multiple vlans */ - if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) return 0; err = mv88e6xxx_vtu_get(chip, vid, &vlan); @@ -1662,27 +1673,22 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, if (!vlan.valid) return 0; - for (i = 0; i < mv88e6xxx_num_ports(chip); ++i) { - if (dsa_is_dsa_port(ds, i) || dsa_is_cpu_port(ds, i)) - continue; + dsa_switch_for_each_user_port(other_dp, ds) { + struct net_device *other_br; - if (!dsa_to_port(ds, i)->slave) - continue; - - if (vlan.member[i] == + if (vlan.member[other_dp->index] == MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_NON_MEMBER) continue; - if (dsa_to_port(ds, i)->bridge_dev == - dsa_to_port(ds, port)->bridge_dev) + if (dsa_port_bridge_same(dp, other_dp)) break; /* same bridge, check next VLAN */ - if (!dsa_to_port(ds, i)->bridge_dev) + other_br = dsa_port_bridge_dev_get(other_dp); + if (!other_br) continue; dev_err(ds->dev, "p%d: hw VLAN %d already used by port %d in %s\n", - port, vlan.vid, i, - netdev_name(dsa_to_port(ds, i)->bridge_dev)); + port, vlan.vid, other_dp->index, netdev_name(other_br)); return -EOPNOTSUPP; } @@ -1692,13 +1698,14 @@ static int mv88e6xxx_port_check_hw_vlan(struct dsa_switch *ds, int port, static int mv88e6xxx_port_commit_pvid(struct mv88e6xxx_chip *chip, int port) { struct dsa_port *dp = dsa_to_port(chip->ds, port); + struct net_device *br = dsa_port_bridge_dev_get(dp); struct mv88e6xxx_port *p = &chip->ports[port]; u16 pvid = MV88E6XXX_VID_STANDALONE; bool drop_untagged = false; int err; - if (dp->bridge_dev) { - if (br_vlan_enabled(dp->bridge_dev)) { + if (br) { + if (br_vlan_enabled(br)) { pvid = p->bridge_pvid.vid; drop_untagged = !p->bridge_pvid.valid; } else { @@ -2416,7 +2423,7 @@ static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port, } static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip, - struct net_device *br) + struct dsa_bridge bridge) { struct dsa_switch *ds = chip->ds; struct dsa_switch_tree *dst = ds->dst; @@ -2424,7 +2431,7 @@ static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip, int err; list_for_each_entry(dp, &dst->ports, list) { - if (dp->bridge_dev == br) { + if (dsa_port_offloads_bridge(dp, &bridge)) { if (dp->ds == ds) { /* This is a local bridge group member, * remap its Port VLAN Map. @@ -2447,15 +2454,29 @@ static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip, return 0; } +/* Treat the software bridge as a virtual single-port switch behind the + * CPU and map in the PVT. First dst->last_switch elements are taken by + * physical switches, so start from beyond that range. + */ +static int mv88e6xxx_map_virtual_bridge_to_pvt(struct dsa_switch *ds, + unsigned int bridge_num) +{ + u8 dev = bridge_num + ds->dst->last_switch; + struct mv88e6xxx_chip *chip = ds->priv; + + return mv88e6xxx_pvt_map(chip, dev, 0); +} + static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge, + bool *tx_fwd_offload) { struct mv88e6xxx_chip *chip = ds->priv; int err; mv88e6xxx_reg_lock(chip); - err = mv88e6xxx_bridge_map(chip, br); + err = mv88e6xxx_bridge_map(chip, bridge); if (err) goto unlock; @@ -2463,6 +2484,14 @@ static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, if (err) goto unlock; + if (mv88e6xxx_has_pvt(chip)) { + err = mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge.num); + if (err) + goto unlock; + + *tx_fwd_offload = true; + } + unlock: mv88e6xxx_reg_unlock(chip); @@ -2470,14 +2499,18 @@ unlock: } static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct mv88e6xxx_chip *chip = ds->priv; int err; mv88e6xxx_reg_lock(chip); - if (mv88e6xxx_bridge_map(chip, br) || + if (bridge.tx_fwd_offload && + mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge.num)) + dev_err(ds->dev, "failed to remap cross-chip Port VLAN\n"); + + if (mv88e6xxx_bridge_map(chip, bridge) || mv88e6xxx_port_vlan_map(chip, port)) dev_err(ds->dev, "failed to remap in-chip Port VLAN\n"); @@ -2492,7 +2525,7 @@ static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, static int mv88e6xxx_crosschip_bridge_join(struct dsa_switch *ds, int tree_index, int sw_index, - int port, struct net_device *br) + int port, struct dsa_bridge bridge) { struct mv88e6xxx_chip *chip = ds->priv; int err; @@ -2502,6 +2535,7 @@ static int mv88e6xxx_crosschip_bridge_join(struct dsa_switch *ds, mv88e6xxx_reg_lock(chip); err = mv88e6xxx_pvt_map(chip, sw_index, port); + err = err ? : mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge.num); mv88e6xxx_reg_unlock(chip); return err; @@ -2509,7 +2543,7 @@ static int mv88e6xxx_crosschip_bridge_join(struct dsa_switch *ds, static void mv88e6xxx_crosschip_bridge_leave(struct dsa_switch *ds, int tree_index, int sw_index, - int port, struct net_device *br) + int port, struct dsa_bridge bridge) { struct mv88e6xxx_chip *chip = ds->priv; @@ -2517,49 +2551,12 @@ static void mv88e6xxx_crosschip_bridge_leave(struct dsa_switch *ds, return; mv88e6xxx_reg_lock(chip); - if (mv88e6xxx_pvt_map(chip, sw_index, port)) + if (mv88e6xxx_pvt_map(chip, sw_index, port) || + mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge.num)) dev_err(ds->dev, "failed to remap cross-chip Port VLAN\n"); mv88e6xxx_reg_unlock(chip); } -/* Treat the software bridge as a virtual single-port switch behind the - * CPU and map in the PVT. First dst->last_switch elements are taken by - * physical switches, so start from beyond that range. - */ -static int mv88e6xxx_map_virtual_bridge_to_pvt(struct dsa_switch *ds, - int bridge_num) -{ - u8 dev = bridge_num + ds->dst->last_switch + 1; - struct mv88e6xxx_chip *chip = ds->priv; - int err; - - mv88e6xxx_reg_lock(chip); - err = mv88e6xxx_pvt_map(chip, dev, 0); - mv88e6xxx_reg_unlock(chip); - - return err; -} - -static int mv88e6xxx_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num) -{ - return mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge_num); -} - -static void mv88e6xxx_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num) -{ - int err; - - err = mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge_num); - if (err) { - dev_err(ds->dev, "failed to remap cross-chip Port VLAN: %pe\n", - ERR_PTR(err)); - } -} - static int mv88e6xxx_software_reset(struct mv88e6xxx_chip *chip) { if (chip->info->ops->reset) @@ -3186,8 +3183,8 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) * time. */ if (mv88e6xxx_has_pvt(chip)) - ds->num_fwd_offloading_bridges = MV88E6XXX_MAX_PVT_SWITCHES - - ds->dst->last_switch - 1; + ds->max_num_bridges = MV88E6XXX_MAX_PVT_SWITCHES - + ds->dst->last_switch - 1; mv88e6xxx_reg_lock(chip); @@ -6279,8 +6276,6 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .crosschip_lag_change = mv88e6xxx_crosschip_lag_change, .crosschip_lag_join = mv88e6xxx_crosschip_lag_join, .crosschip_lag_leave = mv88e6xxx_crosschip_lag_leave, - .port_bridge_tx_fwd_offload = mv88e6xxx_bridge_tx_fwd_offload, - .port_bridge_tx_fwd_unoffload = mv88e6xxx_bridge_tx_fwd_unoffload, }; static int mv88e6xxx_register_switch(struct mv88e6xxx_chip *chip) diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c index 8f74ffc7a279..389f8a6ec0ab 100644 --- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c +++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c @@ -100,10 +100,6 @@ static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port, */ clear_bit_unlock(MV88E6XXX_HWTSTAMP_ENABLED, &ps->state); - /* reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: tstamp_enable = false; diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index d9817b20ea64..ab41619a809b 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -283,7 +283,7 @@ static int mv88e6xxx_port_set_speed_duplex(struct mv88e6xxx_chip *chip, if (err) return err; - if (speed) + if (speed != SPEED_UNFORCED) dev_dbg(chip->dev, "p%d: Speed set to %d Mbps\n", port, speed); else dev_dbg(chip->dev, "p%d: Speed unforced\n", port); @@ -516,7 +516,7 @@ int mv88e6393x_port_set_speed_duplex(struct mv88e6xxx_chip *chip, int port, if (err) return err; - if (speed) + if (speed != SPEED_UNFORCED) dev_dbg(chip->dev, "p%d: Speed set to %d Mbps\n", port, speed); else dev_dbg(chip->dev, "p%d: Speed unforced\n", port); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 55273013bfb5..2b05ead515cd 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -830,7 +830,7 @@ int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane, bool up) { u8 cmode = chip->ports[port].cmode; - int err = 0; + int err; switch (cmode) { case MV88E6XXX_PORT_STS_CMODE_SGMII: @@ -842,6 +842,9 @@ int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane, case MV88E6XXX_PORT_STS_CMODE_RXAUI: err = mv88e6390_serdes_power_10g(chip, lane, up); break; + default: + err = -EINVAL; + break; } if (!err && up) @@ -1541,6 +1544,9 @@ int mv88e6393x_serdes_power(struct mv88e6xxx_chip *chip, int port, int lane, case MV88E6393X_PORT_STS_CMODE_10GBASER: err = mv88e6390_serdes_power_10g(chip, lane, on); break; + default: + err = -EINVAL; + break; } if (err) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 57beab3d3ff3..f4fc403fbc1e 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -298,8 +298,11 @@ static int felix_setup_mmio_filtering(struct felix *felix) } } - if (cpu < 0) + if (cpu < 0) { + kfree(tagging_rule); + kfree(redirect_rule); return -EINVAL; + } tagging_rule->key_type = OCELOT_VCAP_KEY_ETYPE; *(__be16 *)tagging_rule->key.etype.etype.value = htons(ETH_P_1588); @@ -706,21 +709,21 @@ static int felix_bridge_flags(struct dsa_switch *ds, int port, } static int felix_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge, bool *tx_fwd_offload) { struct ocelot *ocelot = ds->priv; - ocelot_port_bridge_join(ocelot, port, br); + ocelot_port_bridge_join(ocelot, port, bridge.dev); return 0; } static void felix_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct ocelot *ocelot = ds->priv; - ocelot_port_bridge_leave(ocelot, port, br); + ocelot_port_bridge_leave(ocelot, port, bridge.dev); } static int felix_lag_join(struct dsa_switch *ds, int port, @@ -1152,38 +1155,22 @@ static void felix_port_deferred_xmit(struct kthread_work *work) kfree(xmit_work); } -static int felix_port_setup_tagger_data(struct dsa_switch *ds, int port) +static int felix_connect_tag_protocol(struct dsa_switch *ds, + enum dsa_tag_protocol proto) { - struct dsa_port *dp = dsa_to_port(ds, port); - struct ocelot *ocelot = ds->priv; - struct felix *felix = ocelot_to_felix(ocelot); - struct felix_port *felix_port; + struct ocelot_8021q_tagger_data *tagger_data; - if (!dsa_port_is_user(dp)) + switch (proto) { + case DSA_TAG_PROTO_OCELOT_8021Q: + tagger_data = ocelot_8021q_tagger_data(ds); + tagger_data->xmit_work_fn = felix_port_deferred_xmit; return 0; - - felix_port = kzalloc(sizeof(*felix_port), GFP_KERNEL); - if (!felix_port) - return -ENOMEM; - - felix_port->xmit_worker = felix->xmit_worker; - felix_port->xmit_work_fn = felix_port_deferred_xmit; - - dp->priv = felix_port; - - return 0; -} - -static void felix_port_teardown_tagger_data(struct dsa_switch *ds, int port) -{ - struct dsa_port *dp = dsa_to_port(ds, port); - struct felix_port *felix_port = dp->priv; - - if (!felix_port) - return; - - dp->priv = NULL; - kfree(felix_port); + case DSA_TAG_PROTO_OCELOT: + case DSA_TAG_PROTO_SEVILLE: + return 0; + default: + return -EPROTONOSUPPORT; + } } /* Hardware initialization done here so that we can allocate structures with @@ -1214,12 +1201,6 @@ static int felix_setup(struct dsa_switch *ds) } } - felix->xmit_worker = kthread_create_worker(0, "felix_xmit"); - if (IS_ERR(felix->xmit_worker)) { - err = PTR_ERR(felix->xmit_worker); - goto out_deinit_timestamp; - } - for (port = 0; port < ds->num_ports; port++) { if (dsa_is_unused_port(ds, port)) continue; @@ -1230,14 +1211,6 @@ static int felix_setup(struct dsa_switch *ds) * bits of vlan tag. */ felix_port_qos_map_init(ocelot, port); - - err = felix_port_setup_tagger_data(ds, port); - if (err) { - dev_err(ds->dev, - "port %d failed to set up tagger data: %pe\n", - port, ERR_PTR(err)); - goto out_deinit_ports; - } } err = ocelot_devlink_sb_register(ocelot); @@ -1265,13 +1238,9 @@ out_deinit_ports: if (dsa_is_unused_port(ds, port)) continue; - felix_port_teardown_tagger_data(ds, port); ocelot_deinit_port(ocelot, port); } - kthread_destroy_worker(felix->xmit_worker); - -out_deinit_timestamp: ocelot_deinit_timestamp(ocelot); ocelot_deinit(ocelot); @@ -1300,12 +1269,9 @@ static void felix_teardown(struct dsa_switch *ds) if (dsa_is_unused_port(ds, port)) continue; - felix_port_teardown_tagger_data(ds, port); ocelot_deinit_port(ocelot, port); } - kthread_destroy_worker(felix->xmit_worker); - ocelot_devlink_sb_unregister(ocelot); ocelot_deinit_timestamp(ocelot); ocelot_deinit(ocelot); @@ -1645,6 +1611,7 @@ felix_mrp_del_ring_role(struct dsa_switch *ds, int port, const struct dsa_switch_ops felix_switch_ops = { .get_tag_protocol = felix_get_tag_protocol, .change_tag_protocol = felix_change_tag_protocol, + .connect_tag_protocol = felix_connect_tag_protocol, .setup = felix_setup, .teardown = felix_teardown, .set_ageing_time = felix_set_ageing_time, diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 96a7fbf8700c..039694518788 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1810,8 +1810,9 @@ qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) QCA8K_PORT_LOOKUP_STATE_MASK, stp_state); } -static int -qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) +static int qca8k_port_bridge_join(struct dsa_switch *ds, int port, + struct dsa_bridge bridge, + bool *tx_fwd_offload) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; int port_mask, cpu_port; @@ -1823,7 +1824,7 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) for (i = 0; i < QCA8K_NUM_PORTS; i++) { if (dsa_is_cpu_port(ds, i)) continue; - if (dsa_to_port(ds, i)->bridge_dev != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Add this port to the portvlan mask of the other ports * in the bridge @@ -1844,8 +1845,8 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) return ret; } -static void -qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) +static void qca8k_port_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_bridge bridge) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; int cpu_port, i; @@ -1855,7 +1856,7 @@ qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) for (i = 0; i < QCA8K_NUM_PORTS; i++) { if (dsa_is_cpu_port(ds, i)) continue; - if (dsa_to_port(ds, i)->bridge_dev != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Remove this port to the portvlan mask of the other ports * in the bridge diff --git a/drivers/net/dsa/rtl8365mb.c b/drivers/net/dsa/rtl8365mb.c index 2ac68c867636..3b729544798b 100644 --- a/drivers/net/dsa/rtl8365mb.c +++ b/drivers/net/dsa/rtl8365mb.c @@ -900,7 +900,8 @@ static bool rtl8365mb_phy_mode_supported(struct dsa_switch *ds, int port, { if (dsa_is_user_port(ds, port) && (interface == PHY_INTERFACE_MODE_NA || - interface == PHY_INTERFACE_MODE_INTERNAL)) + interface == PHY_INTERFACE_MODE_INTERNAL || + interface == PHY_INTERFACE_MODE_GMII)) /* Internal PHY */ return true; else if (dsa_is_cpu_port(ds, port) && diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index 03deacd83e61..ecc19bd5115f 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -1186,7 +1186,8 @@ rtl8366rb_port_disable(struct dsa_switch *ds, int port) static int rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge, + bool *tx_fwd_offload) { struct realtek_smi *smi = ds->priv; unsigned int port_bitmap = 0; @@ -1198,7 +1199,7 @@ rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, if (i == port) continue; /* Not on this bridge */ - if (dsa_to_port(ds, i)->bridge_dev != bridge) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Join this port to each other port on the bridge */ ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), @@ -1218,7 +1219,7 @@ rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, static void rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { struct realtek_smi *smi = ds->priv; unsigned int port_bitmap = 0; @@ -1230,7 +1231,7 @@ rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, if (i == port) continue; /* Not on this bridge */ - if (dsa_to_port(ds, i)->bridge_dev != bridge) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Remove this port from any other port on the bridge */ ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 21dba16af097..9ba2ec2b966d 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -249,6 +249,7 @@ struct sja1105_private { bool fixed_link[SJA1105_MAX_NUM_PORTS]; unsigned long ucast_egress_floods; unsigned long bcast_egress_floods; + unsigned long hwts_tx_en; const struct sja1105_info *info; size_t max_xfer_len; struct spi_device *spidev; @@ -256,11 +257,13 @@ struct sja1105_private { u16 bridge_pvid[SJA1105_MAX_NUM_PORTS]; u16 tag_8021q_pvid[SJA1105_MAX_NUM_PORTS]; struct sja1105_flow_block flow_block; - struct sja1105_port ports[SJA1105_MAX_NUM_PORTS]; /* Serializes transmission of management frames so that * the switch doesn't confuse them with one another. */ struct mutex mgmt_lock; + /* PTP two-step TX timestamp ID, and its serialization lock */ + spinlock_t ts_id_lock; + u8 ts_id; /* Serializes access to the dynamic config interface */ struct mutex dynamic_config_lock; struct devlink_region **regions; @@ -269,7 +272,6 @@ struct sja1105_private { struct mii_bus *mdio_base_tx; struct mii_bus *mdio_pcs; struct dw_xpcs *xpcs[SJA1105_MAX_NUM_PORTS]; - struct sja1105_tagger_data tagger_data; struct sja1105_ptp_data ptp_data; struct sja1105_tas_data tas_data; }; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index c343effe2e96..b513713be610 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -118,13 +118,14 @@ static int sja1105_pvid_apply(struct sja1105_private *priv, int port, u16 pvid) static int sja1105_commit_pvid(struct dsa_switch *ds, int port) { struct dsa_port *dp = dsa_to_port(ds, port); + struct net_device *br = dsa_port_bridge_dev_get(dp); struct sja1105_private *priv = ds->priv; struct sja1105_vlan_lookup_entry *vlan; bool drop_untagged = false; int match, rc; u16 pvid; - if (dp->bridge_dev && br_vlan_enabled(dp->bridge_dev)) + if (br && br_vlan_enabled(br)) pvid = priv->bridge_pvid[port]; else pvid = priv->tag_8021q_pvid[port]; @@ -1979,7 +1980,7 @@ static int sja1105_manage_flood_domains(struct sja1105_private *priv) } static int sja1105_bridge_member(struct dsa_switch *ds, int port, - struct net_device *br, bool member) + struct dsa_bridge bridge, bool member) { struct sja1105_l2_forwarding_entry *l2_fwd; struct sja1105_private *priv = ds->priv; @@ -2004,7 +2005,7 @@ static int sja1105_bridge_member(struct dsa_switch *ds, int port, */ if (i == port) continue; - if (dsa_to_port(ds, i)->bridge_dev != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; sja1105_port_allow_traffic(l2_fwd, i, port, member); sja1105_port_allow_traffic(l2_fwd, port, i, member); @@ -2073,15 +2074,31 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port, } static int sja1105_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge, + bool *tx_fwd_offload) { - return sja1105_bridge_member(ds, port, br, true); + int rc; + + rc = sja1105_bridge_member(ds, port, bridge, true); + if (rc) + return rc; + + rc = dsa_tag_8021q_bridge_tx_fwd_offload(ds, port, bridge); + if (rc) { + sja1105_bridge_member(ds, port, bridge, false); + return rc; + } + + *tx_fwd_offload = true; + + return 0; } static void sja1105_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { - sja1105_bridge_member(ds, port, br, false); + dsa_tag_8021q_bridge_tx_fwd_unoffload(ds, port, bridge); + sja1105_bridge_member(ds, port, bridge, false); } #define BYTES_PER_KBIT (1000LL / 8) @@ -2587,8 +2604,9 @@ static int sja1105_prechangeupper(struct dsa_switch *ds, int port, if (netif_is_bridge_master(upper)) { list_for_each_entry(dp, &dst->ports, list) { - if (dp->bridge_dev && dp->bridge_dev != upper && - br_vlan_enabled(dp->bridge_dev)) { + struct net_device *br = dsa_port_bridge_dev_get(dp); + + if (br && br != upper && br_vlan_enabled(br)) { NL_SET_ERR_MSG_MOD(extack, "Only one VLAN-aware bridge is supported"); return -EBUSY; @@ -2599,18 +2617,6 @@ static int sja1105_prechangeupper(struct dsa_switch *ds, int port, return 0; } -static void sja1105_port_disable(struct dsa_switch *ds, int port) -{ - struct sja1105_private *priv = ds->priv; - struct sja1105_port *sp = &priv->ports[port]; - - if (!dsa_is_user_port(ds, port)) - return; - - kthread_cancel_work_sync(&sp->xmit_work); - skb_queue_purge(&sp->xmit_queue); -} - static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, struct sk_buff *skb, bool takets) { @@ -2669,10 +2675,8 @@ static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, return NETDEV_TX_OK; } -#define work_to_port(work) \ - container_of((work), struct sja1105_port, xmit_work) -#define tagger_to_sja1105(t) \ - container_of((t), struct sja1105_private, tagger_data) +#define work_to_xmit_work(w) \ + container_of((w), struct sja1105_deferred_xmit_work, work) /* Deferred work is unfortunately necessary because setting up the management * route cannot be done from atomit context (SPI transfer takes a sleepable @@ -2680,25 +2684,41 @@ static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, */ static void sja1105_port_deferred_xmit(struct kthread_work *work) { - struct sja1105_port *sp = work_to_port(work); - struct sja1105_tagger_data *tagger_data = sp->data; - struct sja1105_private *priv = tagger_to_sja1105(tagger_data); - int port = sp - priv->ports; - struct sk_buff *skb; + struct sja1105_deferred_xmit_work *xmit_work = work_to_xmit_work(work); + struct sk_buff *clone, *skb = xmit_work->skb; + struct dsa_switch *ds = xmit_work->dp->ds; + struct sja1105_private *priv = ds->priv; + int port = xmit_work->dp->index; - while ((skb = skb_dequeue(&sp->xmit_queue)) != NULL) { - struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; + clone = SJA1105_SKB_CB(skb)->clone; - mutex_lock(&priv->mgmt_lock); + mutex_lock(&priv->mgmt_lock); - sja1105_mgmt_xmit(priv->ds, port, 0, skb, !!clone); + sja1105_mgmt_xmit(ds, port, 0, skb, !!clone); - /* The clone, if there, was made by dsa_skb_tx_timestamp */ - if (clone) - sja1105_ptp_txtstamp_skb(priv->ds, port, clone); + /* The clone, if there, was made by dsa_skb_tx_timestamp */ + if (clone) + sja1105_ptp_txtstamp_skb(ds, port, clone); - mutex_unlock(&priv->mgmt_lock); - } + mutex_unlock(&priv->mgmt_lock); + + kfree(xmit_work); +} + +static int sja1105_connect_tag_protocol(struct dsa_switch *ds, + enum dsa_tag_protocol proto) +{ + struct sja1105_private *priv = ds->priv; + struct sja1105_tagger_data *tagger_data; + + if (proto != priv->info->tag_proto) + return -EPROTONOSUPPORT; + + tagger_data = sja1105_tagger_data(ds); + tagger_data->xmit_work_fn = sja1105_port_deferred_xmit; + tagger_data->meta_tstamp_handler = sja1110_process_meta_tstamp; + + return 0; } /* The MAXAGE setting belongs to the L2 Forwarding Parameters table, @@ -3001,58 +3021,6 @@ static int sja1105_port_bridge_flags(struct dsa_switch *ds, int port, return 0; } -static void sja1105_teardown_ports(struct sja1105_private *priv) -{ - struct dsa_switch *ds = priv->ds; - int port; - - for (port = 0; port < ds->num_ports; port++) { - struct sja1105_port *sp = &priv->ports[port]; - - if (sp->xmit_worker) - kthread_destroy_worker(sp->xmit_worker); - } -} - -static int sja1105_setup_ports(struct sja1105_private *priv) -{ - struct sja1105_tagger_data *tagger_data = &priv->tagger_data; - struct dsa_switch *ds = priv->ds; - int port, rc; - - /* Connections between dsa_port and sja1105_port */ - for (port = 0; port < ds->num_ports; port++) { - struct sja1105_port *sp = &priv->ports[port]; - struct dsa_port *dp = dsa_to_port(ds, port); - struct kthread_worker *worker; - struct net_device *slave; - - if (!dsa_port_is_user(dp)) - continue; - - dp->priv = sp; - sp->data = tagger_data; - slave = dp->slave; - kthread_init_work(&sp->xmit_work, sja1105_port_deferred_xmit); - worker = kthread_create_worker(0, "%s_xmit", slave->name); - if (IS_ERR(worker)) { - rc = PTR_ERR(worker); - dev_err(ds->dev, - "failed to create deferred xmit thread: %d\n", - rc); - goto out_destroy_workers; - } - sp->xmit_worker = worker; - skb_queue_head_init(&sp->xmit_queue); - } - - return 0; - -out_destroy_workers: - sja1105_teardown_ports(priv); - return rc; -} - /* The programming model for the SJA1105 switch is "all-at-once" via static * configuration tables. Some of these can be dynamically modified at runtime, * but not the xMII mode parameters table. @@ -3098,10 +3066,6 @@ static int sja1105_setup(struct dsa_switch *ds) } } - rc = sja1105_setup_ports(priv); - if (rc) - goto out_static_config_free; - sja1105_tas_setup(ds); sja1105_flower_setup(ds); @@ -3139,7 +3103,7 @@ static int sja1105_setup(struct dsa_switch *ds) ds->vlan_filtering_is_global = true; ds->untag_bridge_pvid = true; /* tag_8021q has 3 bits for the VBID, and the value 0 is reserved */ - ds->num_fwd_offloading_bridges = 7; + ds->max_num_bridges = 7; /* Advertise the 8 egress queues */ ds->num_tx_queues = SJA1105_NUM_TC; @@ -3158,7 +3122,6 @@ out_ptp_clock_unregister: out_flower_teardown: sja1105_flower_teardown(ds); sja1105_tas_teardown(ds); - sja1105_teardown_ports(priv); out_static_config_free: sja1105_static_config_free(&priv->static_config); @@ -3178,12 +3141,12 @@ static void sja1105_teardown(struct dsa_switch *ds) sja1105_ptp_clock_unregister(ds); sja1105_flower_teardown(ds); sja1105_tas_teardown(ds); - sja1105_teardown_ports(priv); sja1105_static_config_free(&priv->static_config); } static const struct dsa_switch_ops sja1105_switch_ops = { .get_tag_protocol = sja1105_get_tag_protocol, + .connect_tag_protocol = sja1105_connect_tag_protocol, .setup = sja1105_setup, .teardown = sja1105_teardown, .set_ageing_time = sja1105_set_ageing_time, @@ -3197,7 +3160,6 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .get_ethtool_stats = sja1105_get_ethtool_stats, .get_sset_count = sja1105_get_sset_count, .get_ts_info = sja1105_get_ts_info, - .port_disable = sja1105_port_disable, .port_fdb_dump = sja1105_fdb_dump, .port_fdb_add = sja1105_fdb_add, .port_fdb_del = sja1105_fdb_del, @@ -3228,8 +3190,6 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .tag_8021q_vlan_add = sja1105_dsa_8021q_vlan_add, .tag_8021q_vlan_del = sja1105_dsa_8021q_vlan_del, .port_prechangeupper = sja1105_prechangeupper, - .port_bridge_tx_fwd_offload = dsa_tag_8021q_bridge_tx_fwd_offload, - .port_bridge_tx_fwd_unoffload = dsa_tag_8021q_bridge_tx_fwd_unoffload, }; static const struct of_device_id sja1105_dt_ids[]; @@ -3367,6 +3327,7 @@ static int sja1105_probe(struct spi_device *spi) mutex_init(&priv->ptp_data.lock); mutex_init(&priv->dynamic_config_lock); mutex_init(&priv->mgmt_lock); + spin_lock_init(&priv->ts_id_lock); rc = sja1105_parse_dt(priv); if (rc < 0) { diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 54396992a919..be3068a935af 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -58,13 +58,12 @@ enum sja1105_ptp_clk_mode { #define ptp_data_to_sja1105(d) \ container_of((d), struct sja1105_private, ptp_data) -/* Must be called only with priv->tagger_data.state bit - * SJA1105_HWTS_RX_EN cleared +/* Must be called only while the RX timestamping state of the tagger + * is turned off */ static int sja1105_change_rxtstamping(struct sja1105_private *priv, bool on) { - struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; struct sja1105_general_params_entry *general_params; struct sja1105_table *table; @@ -74,13 +73,8 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, general_params->send_meta1 = on; general_params->send_meta0 = on; - /* Initialize the meta state machine to a known state */ - if (priv->tagger_data.stampable_skb) { - kfree_skb(priv->tagger_data.stampable_skb); - priv->tagger_data.stampable_skb = NULL; - } ptp_cancel_worker_sync(ptp_data->clock); - skb_queue_purge(&tagger_data->skb_txtstamp_queue); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); return sja1105_static_config_reload(priv, SJA1105_RX_HWTSTAMPING); @@ -88,6 +82,7 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) { + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sja1105_private *priv = ds->priv; struct hwtstamp_config config; bool rx_on; @@ -98,10 +93,10 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) switch (config.tx_type) { case HWTSTAMP_TX_OFF: - priv->ports[port].hwts_tx_en = false; + priv->hwts_tx_en &= ~BIT(port); break; case HWTSTAMP_TX_ON: - priv->ports[port].hwts_tx_en = true; + priv->hwts_tx_en |= BIT(port); break; default: return -ERANGE; @@ -116,8 +111,8 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) break; } - if (rx_on != test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) { - clear_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state); + if (rx_on != tagger_data->rxtstamp_get_state(ds)) { + tagger_data->rxtstamp_set_state(ds, false); rc = sja1105_change_rxtstamping(priv, rx_on); if (rc < 0) { @@ -126,7 +121,7 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) return rc; } if (rx_on) - set_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state); + tagger_data->rxtstamp_set_state(ds, true); } if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) @@ -136,15 +131,16 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr) { + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sja1105_private *priv = ds->priv; struct hwtstamp_config config; config.flags = 0; - if (priv->ports[port].hwts_tx_en) + if (priv->hwts_tx_en & BIT(port)) config.tx_type = HWTSTAMP_TX_ON; else config.tx_type = HWTSTAMP_TX_OFF; - if (test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) + if (tagger_data->rxtstamp_get_state(ds)) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; else config.rx_filter = HWTSTAMP_FILTER_NONE; @@ -417,10 +413,11 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp) bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sja1105_private *priv = ds->priv; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; - if (!test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) + if (!tagger_data->rxtstamp_get_state(ds)) return false; /* We need to read the full PTP clock to reconstruct the Rx @@ -453,6 +450,39 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, return priv->info->rxtstamp(ds, port, skb); } +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp) +{ + struct sja1105_private *priv = ds->priv; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct skb_shared_hwtstamps shwt = {0}; + + /* We don't care about RX timestamps on the CPU port */ + if (dir == SJA1110_META_TSTAMP_RX) + return; + + spin_lock(&ptp_data->skb_txtstamp_queue.lock); + + skb_queue_walk_safe(&ptp_data->skb_txtstamp_queue, skb, skb_tmp) { + if (SJA1105_SKB_CB(skb)->ts_id != ts_id) + continue; + + __skb_unlink(skb, &ptp_data->skb_txtstamp_queue); + skb_match = skb; + + break; + } + + spin_unlock(&ptp_data->skb_txtstamp_queue.lock); + + if (WARN_ON(!skb_match)) + return; + + shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); + skb_complete_tx_timestamp(skb_match, &shwt); +} + /* In addition to cloning the skb which is done by the common * sja1105_port_txtstamp, we need to generate a timestamp ID and save the * packet to the TX timestamping queue. @@ -461,22 +491,22 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; struct sja1105_private *priv = ds->priv; - struct sja1105_port *sp = &priv->ports[port]; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; u8 ts_id; skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - spin_lock(&sp->data->meta_lock); + spin_lock(&priv->ts_id_lock); - ts_id = sp->data->ts_id; + ts_id = priv->ts_id; /* Deal automatically with 8-bit wraparound */ - sp->data->ts_id++; + priv->ts_id++; SJA1105_SKB_CB(clone)->ts_id = ts_id; - spin_unlock(&sp->data->meta_lock); + spin_unlock(&priv->ts_id_lock); - skb_queue_tail(&sp->data->skb_txtstamp_queue, clone); + skb_queue_tail(&ptp_data->skb_txtstamp_queue, clone); } /* Called from dsa_skb_tx_timestamp. This callback is just to clone @@ -486,10 +516,9 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) void sja1105_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sja1105_private *priv = ds->priv; - struct sja1105_port *sp = &priv->ports[port]; struct sk_buff *clone; - if (!sp->hwts_tx_en) + if (!(priv->hwts_tx_en & BIT(port))) return; clone = skb_clone_sk(skb); @@ -896,7 +925,6 @@ static struct ptp_pin_desc sja1105_ptp_pin = { int sja1105_ptp_clock_register(struct dsa_switch *ds) { struct sja1105_private *priv = ds->priv; - struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; ptp_data->caps = (struct ptp_clock_info) { @@ -919,8 +947,7 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) /* Only used on SJA1105 */ skb_queue_head_init(&ptp_data->skb_rxtstamp_queue); /* Only used on SJA1110 */ - skb_queue_head_init(&tagger_data->skb_txtstamp_queue); - spin_lock_init(&tagger_data->meta_lock); + skb_queue_head_init(&ptp_data->skb_txtstamp_queue); ptp_data->clock = ptp_clock_register(&ptp_data->caps, ds->dev); if (IS_ERR_OR_NULL(ptp_data->clock)) @@ -937,7 +964,6 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) void sja1105_ptp_clock_unregister(struct dsa_switch *ds) { struct sja1105_private *priv = ds->priv; - struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; if (IS_ERR_OR_NULL(ptp_data->clock)) @@ -945,7 +971,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) del_timer_sync(&ptp_data->extts_timer); ptp_cancel_worker_sync(ptp_data->clock); - skb_queue_purge(&tagger_data->skb_txtstamp_queue); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); ptp_clock_unregister(ptp_data->clock); ptp_data->clock = NULL; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h index 3ae6b9fdd492..416461ee95d2 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.h +++ b/drivers/net/dsa/sja1105/sja1105_ptp.h @@ -8,6 +8,21 @@ #if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) +/* Timestamps are in units of 8 ns clock ticks (equivalent to + * a fixed 125 MHz clock). + */ +#define SJA1105_TICK_NS 8 + +static inline s64 ns_to_sja1105_ticks(s64 ns) +{ + return ns / SJA1105_TICK_NS; +} + +static inline s64 sja1105_ticks_to_ns(s64 ticks) +{ + return ticks * SJA1105_TICK_NS; +} + /* Calculate the first base_time in the future that satisfies this * relationship: * @@ -62,6 +77,10 @@ struct sja1105_ptp_data { struct timer_list extts_timer; /* Used only on SJA1105 to reconstruct partial timestamps */ struct sk_buff_head skb_rxtstamp_queue; + /* Used on SJA1110 where meta frames are generated only for + * 2-step TX timestamps + */ + struct sk_buff_head skb_txtstamp_queue; struct ptp_clock_info caps; struct ptp_clock *clock; struct sja1105_ptp_cmd cmd; @@ -112,6 +131,9 @@ bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); bool sja1110_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + #else struct sja1105_ptp_cmd; @@ -178,6 +200,8 @@ static inline int sja1105_ptp_commit(struct dsa_switch *ds, #define sja1110_rxtstamp NULL #define sja1110_txtstamp NULL +#define sja1110_process_meta_tstamp NULL + #endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ #endif /* _SJA1105_PTP_H */ diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index 910fcb3b252b..35fa19ddaf19 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -501,7 +501,7 @@ static void xrs700x_mac_link_up(struct dsa_switch *ds, int port, } static int xrs700x_bridge_common(struct dsa_switch *ds, int port, - struct net_device *bridge, bool join) + struct dsa_bridge bridge, bool join) { unsigned int i, cpu_mask = 0, mask = 0; struct xrs700x *priv = ds->priv; @@ -513,14 +513,14 @@ static int xrs700x_bridge_common(struct dsa_switch *ds, int port, cpu_mask |= BIT(i); - if (dsa_to_port(ds, i)->bridge_dev == bridge) + if (dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; mask |= BIT(i); } for (i = 0; i < ds->num_ports; i++) { - if (dsa_to_port(ds, i)->bridge_dev != bridge) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* 1 = Disable forwarding to the port */ @@ -540,13 +540,13 @@ static int xrs700x_bridge_common(struct dsa_switch *ds, int port, } static int xrs700x_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge, bool *tx_fwd_offload) { return xrs700x_bridge_common(ds, port, bridge, true); } static void xrs700x_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { xrs700x_bridge_common(ds, port, bridge, false); } diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 027cbacca1c9..db3ec4768159 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -183,6 +183,7 @@ source "drivers/net/ethernet/tehuti/Kconfig" source "drivers/net/ethernet/ti/Kconfig" source "drivers/net/ethernet/toshiba/Kconfig" source "drivers/net/ethernet/tundra/Kconfig" +source "drivers/net/ethernet/vertexcom/Kconfig" source "drivers/net/ethernet/via/Kconfig" source "drivers/net/ethernet/wiznet/Kconfig" source "drivers/net/ethernet/xilinx/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 33d30b619e00..8a87c1083d1d 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -93,6 +93,7 @@ obj-$(CONFIG_NET_VENDOR_TEHUTI) += tehuti/ obj-$(CONFIG_NET_VENDOR_TI) += ti/ obj-$(CONFIG_NET_VENDOR_TOSHIBA) += toshiba/ obj-$(CONFIG_NET_VENDOR_TUNDRA) += tundra/ +obj-$(CONFIG_NET_VENDOR_VERTEXCOM) += vertexcom/ obj-$(CONFIG_NET_VENDOR_VIA) += via/ obj-$(CONFIG_NET_VENDOR_WIZNET) += wiznet/ obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/ diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 800ee022388f..cccf8a3ead5e 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -76,7 +76,6 @@ struct emac_board_info { void __iomem *membase; u32 msg_enable; struct net_device *ndev; - struct sk_buff *skb_last; u16 tx_fifo_stat; int emacrx_completed_flag; @@ -499,7 +498,6 @@ static void emac_rx(struct net_device *dev) struct sk_buff *skb; u8 *rdptr; bool good_packet; - static int rxlen_last; unsigned int reg_val; u32 rxhdr, rxstatus, rxcount, rxlen; @@ -514,22 +512,6 @@ static void emac_rx(struct net_device *dev) if (netif_msg_rx_status(db)) dev_dbg(db->dev, "RXCount: %x\n", rxcount); - if ((db->skb_last != NULL) && (rxlen_last > 0)) { - dev->stats.rx_bytes += rxlen_last; - - /* Pass to upper layer */ - db->skb_last->protocol = eth_type_trans(db->skb_last, - dev); - netif_rx(db->skb_last); - dev->stats.rx_packets++; - db->skb_last = NULL; - rxlen_last = 0; - - reg_val = readl(db->membase + EMAC_RX_CTL_REG); - reg_val &= ~EMAC_RX_CTL_DMA_EN; - writel(reg_val, db->membase + EMAC_RX_CTL_REG); - } - if (!rxcount) { db->emacrx_completed_flag = 1; reg_val = readl(db->membase + EMAC_INT_CTL_REG); diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index d75d95a97dd9..993b2fb42961 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -1430,16 +1430,19 @@ static int altera_tse_probe(struct platform_device *pdev) priv->rxdescmem_busaddr = dma_res->start; } else { + ret = -ENODEV; goto err_free_netdev; } - if (!dma_set_mask(priv->device, DMA_BIT_MASK(priv->dmaops->dmamask))) + if (!dma_set_mask(priv->device, DMA_BIT_MASK(priv->dmaops->dmamask))) { dma_set_coherent_mask(priv->device, DMA_BIT_MASK(priv->dmaops->dmamask)); - else if (!dma_set_mask(priv->device, DMA_BIT_MASK(32))) + } else if (!dma_set_mask(priv->device, DMA_BIT_MASK(32))) { dma_set_coherent_mask(priv->device, DMA_BIT_MASK(32)); - else + } else { + ret = -EIO; goto err_free_netdev; + } /* MAC address space */ ret = request_and_map(pdev, "control_port", &control_port, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 30d24d19f40d..492ac383f16d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1508,9 +1508,6 @@ static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, if (copy_from_user(&config, ifreq->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) - return -EINVAL; - mac_tscr = 0; switch (config.tx_type) { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index e22935ce9573..e65ce7199dac 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -231,9 +231,6 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev) static int aq_ndev_config_hwtstamp(struct aq_nic_s *aq_nic, struct hwtstamp_config *config) { - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index ff924f06581e..270c2935591b 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1024,17 +1024,6 @@ static void ag71xx_mac_config(struct phylink_config *config, unsigned int mode, ag71xx_wr(ag, AG71XX_REG_FIFO_CFG3, ag->fifodata[2]); } -static void ag71xx_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) -{ - state->link = 0; -} - -static void ag71xx_mac_an_restart(struct phylink_config *config) -{ - /* Not Supported */ -} - static void ag71xx_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { @@ -1098,8 +1087,6 @@ static void ag71xx_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops ag71xx_phylink_mac_ops = { .validate = phylink_generic_validate, - .mac_pcs_get_state = ag71xx_mac_pcs_get_state, - .mac_an_restart = ag71xx_mac_an_restart, .mac_config = ag71xx_mac_config, .mac_link_down = ag71xx_mac_link_down, .mac_link_up = ag71xx_mac_link_up, diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c index 7cc5213c575a..b07cb9bc5f2d 100644 --- a/drivers/net/ethernet/broadcom/bcm4908_enet.c +++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c @@ -708,7 +708,9 @@ static int bcm4908_enet_probe(struct platform_device *pdev) enet->irq_tx = platform_get_irq_byname(pdev, "tx"); - dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); + err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); + if (err) + return err; err = bcm4908_enet_dma_alloc(enet); if (err) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 40933bf5a710..60dde29974bf 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1309,11 +1309,11 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb, struct bcm_sysport_priv *priv = netdev_priv(dev); struct device *kdev = &priv->pdev->dev; struct bcm_sysport_tx_ring *ring; + unsigned long flags, desc_flags; struct bcm_sysport_cb *cb; struct netdev_queue *txq; u32 len_status, addr_lo; unsigned int skb_len; - unsigned long flags; dma_addr_t mapping; u16 queue; int ret; @@ -1373,8 +1373,10 @@ static netdev_tx_t bcm_sysport_xmit(struct sk_buff *skb, ring->desc_count--; /* Ports are latched, so write upper address first */ + spin_lock_irqsave(&priv->desc_lock, desc_flags); tdma_writel(priv, len_status, TDMA_WRITE_PORT_HI(ring->index)); tdma_writel(priv, addr_lo, TDMA_WRITE_PORT_LO(ring->index)); + spin_unlock_irqrestore(&priv->desc_lock, desc_flags); /* Check ring space and update SW control flow */ if (ring->desc_count == 0) @@ -2013,6 +2015,7 @@ static int bcm_sysport_open(struct net_device *dev) } /* Initialize both hardware and software ring */ + spin_lock_init(&priv->desc_lock); for (i = 0; i < dev->num_tx_queues; i++) { ret = bcm_sysport_init_tx_ring(priv, i); if (ret) { diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 984f76e74b43..16b73bb9acc7 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -711,6 +711,7 @@ struct bcm_sysport_priv { int wol_irq; /* Transmit rings */ + spinlock_t desc_lock; struct bcm_sysport_tx_ring *tx_rings; /* Receive queue */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index aec666e97683..651bc1d7a57a 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -15356,11 +15356,6 @@ static int bnx2x_hwtstamp_ioctl(struct bnx2x *bp, struct ifreq *ifr) DP(BNX2X_MSG_PTP, "Requested tx_type: %d, requested rx_filters = %d\n", config.tx_type, config.rx_filter); - if (config.flags) { - BNX2X_ERR("config.flags is reserved for future use\n"); - return -EINVAL; - } - bp->hwtstamp_ioctl_called = true; bp->tx_type = config.tx_type; bp->rx_filter = config.rx_filter; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 8388be119f9a..48520967746f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -417,9 +417,6 @@ int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) if (copy_from_user(&stmpconf, ifr->ifr_data, sizeof(stmpconf))) return -EFAULT; - if (stmpconf.flags) - return -EINVAL; - if (stmpconf.tx_type != HWTSTAMP_TX_ON && stmpconf.tx_type != HWTSTAMP_TX_OFF) return -ERANGE; diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 5f259641437a..c888ddee1fc4 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -589,9 +589,9 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) * Internal or external PHY with MDIO access */ phydev = phy_attach(priv->dev, phy_name, pd->phy_interface); - if (!phydev) { + if (IS_ERR(phydev)) { dev_err(kdev, "failed to register PHY device\n"); - return -ENODEV; + return PTR_ERR(phydev); } } else { /* diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 283f3c1f1195..c28f8cc00d1c 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -13806,9 +13806,6 @@ static int tg3_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) if (copy_from_user(&stmpconf, ifr->ifr_data, sizeof(stmpconf))) return -EFAULT; - if (stmpconf.flags) - return -EINVAL; - if (stmpconf.tx_type != HWTSTAMP_TX_ON && stmpconf.tx_type != HWTSTAMP_TX_OFF) return -ERANGE; diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c index 4b4ad731897f..8aca768571b2 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c +++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c @@ -235,13 +235,18 @@ static int bnad_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { - u32 supported, advertising; - - supported = SUPPORTED_10000baseT_Full; - advertising = ADVERTISED_10000baseT_Full; + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + + ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseCR_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseLR_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10000baseCR_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10000baseLR_Full); cmd->base.autoneg = AUTONEG_DISABLE; - supported |= SUPPORTED_FIBRE; - advertising |= ADVERTISED_FIBRE; + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); cmd->base.port = PORT_FIBRE; cmd->base.phy_address = 0; @@ -253,11 +258,6 @@ bnad_get_link_ksettings(struct net_device *netdev, cmd->base.duplex = DUPLEX_UNKNOWN; } - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - advertising); - return 0; } diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 095c5a2144a7..fb6b27f46b15 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -464,10 +464,6 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd) sizeof(*tstamp_config))) return -EFAULT; - /* reserved for future extensions */ - if (tstamp_config->flags) - return -EINVAL; - switch (tstamp_config->tx_type) { case HWTSTAMP_TX_OFF: break; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 12eee2bc7f5c..ba28aa444e5a 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2114,9 +2114,6 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&conf, ifr->ifr_data, sizeof(conf))) return -EFAULT; - if (conf.flags) - return -EINVAL; - switch (conf.tx_type) { case HWTSTAMP_TX_ON: case HWTSTAMP_TX_OFF: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index c607756b731f..568f211d91cc 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -1254,9 +1254,6 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&conf, ifr->ifr_data, sizeof(conf))) return -EFAULT; - if (conf.flags) - return -EINVAL; - switch (conf.tx_type) { case HWTSTAMP_TX_ON: case HWTSTAMP_TX_OFF: diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 4b4ffdd1044d..103591dcea1c 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -702,9 +702,6 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev, if (copy_from_user(&config, rq->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) /* reserved for future extensions */ - return -EINVAL; - /* Check the status of hardware for tiemstamps */ if (OCTEON_IS_MODEL(OCTEON_CN6XXX)) { /* Get the current state of the PTP clock */ diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index bb45d5df2856..63191692f624 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1917,10 +1917,6 @@ static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: diff --git a/drivers/net/ethernet/engleder/tsnep_ptp.c b/drivers/net/ethernet/engleder/tsnep_ptp.c index 4bfb4d8508f5..eaad453d487e 100644 --- a/drivers/net/ethernet/engleder/tsnep_ptp.c +++ b/drivers/net/ethernet/engleder/tsnep_ptp.c @@ -31,9 +31,6 @@ int tsnep_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 2085844227fe..e54e70ebdd05 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -388,6 +388,8 @@ struct dpaa2_eth_ch_stats { __u64 bytes_per_cdan; }; +#define DPAA2_ETH_CH_STATS 7 + /* Maximum number of queues associated with a DPNI */ #define DPAA2_ETH_MAX_TCS 8 #define DPAA2_ETH_MAX_RX_QUEUES_PER_TC 16 diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index adb8ce5306ee..3fdbf87dccb1 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -278,7 +278,7 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, /* Per-channel stats */ for (k = 0; k < priv->num_channels; k++) { ch_stats = &priv->channel[k]->stats; - for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64) - 1; j++) + for (j = 0; j < DPAA2_ETH_CH_STATS; j++) *((__u64 *)data + i + j) += *((__u64 *)ch_stats + j); } i += j; diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h index 7b4961daa254..ed7301b69169 100644 --- a/drivers/net/ethernet/freescale/fec.h +++ b/drivers/net/ethernet/freescale/fec.h @@ -377,6 +377,9 @@ struct bufdesc_ex { #define FEC_ENET_WAKEUP ((uint)0x00020000) /* Wakeup request */ #define FEC_ENET_TXF (FEC_ENET_TXF_0 | FEC_ENET_TXF_1 | FEC_ENET_TXF_2) #define FEC_ENET_RXF (FEC_ENET_RXF_0 | FEC_ENET_RXF_1 | FEC_ENET_RXF_2) +#define FEC_ENET_RXF_GET(X) (((X) == 0) ? FEC_ENET_RXF_0 : \ + (((X) == 1) ? FEC_ENET_RXF_1 : \ + FEC_ENET_RXF_2)) #define FEC_ENET_TS_AVAIL ((uint)0x00010000) #define FEC_ENET_TS_TIMER ((uint)0x00008000) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index f38e70692514..796133de527e 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1185,6 +1185,21 @@ static void fec_enet_stop_mode(struct fec_enet_private *fep, bool enabled) } } +static void fec_irqs_disable(struct net_device *ndev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + + writel(0, fep->hwp + FEC_IMASK); +} + +static void fec_irqs_disable_except_wakeup(struct net_device *ndev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + + writel(0, fep->hwp + FEC_IMASK); + writel(FEC_ENET_WAKEUP, fep->hwp + FEC_IMASK); +} + static void fec_stop(struct net_device *ndev) { @@ -1211,15 +1226,13 @@ fec_stop(struct net_device *ndev) writel(1, fep->hwp + FEC_ECNTRL); udelay(10); } - writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); } else { - writel(FEC_DEFAULT_IMASK | FEC_ENET_WAKEUP, fep->hwp + FEC_IMASK); val = readl(fep->hwp + FEC_ECNTRL); val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP); writel(val, fep->hwp + FEC_ECNTRL); - fec_enet_stop_mode(fep, true); } writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED); + writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK); /* We have to keep ENET enabled to have MII interrupt stay working */ if (fep->quirks & FEC_QUIRK_ENET_MAC && @@ -1480,7 +1493,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) break; pkt_received++; - writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT); + writel(FEC_ENET_RXF_GET(queue_id), fep->hwp + FEC_IEVENT); /* Check for errors. */ status ^= BD_ENET_RX_LAST; @@ -2877,15 +2890,10 @@ fec_enet_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) return -EINVAL; device_set_wakeup_enable(&ndev->dev, wol->wolopts & WAKE_MAGIC); - if (device_may_wakeup(&ndev->dev)) { + if (device_may_wakeup(&ndev->dev)) fep->wol_flag |= FEC_WOL_FLAG_ENABLE; - if (fep->wake_irq > 0) - enable_irq_wake(fep->wake_irq); - } else { + else fep->wol_flag &= (~FEC_WOL_FLAG_ENABLE); - if (fep->wake_irq > 0) - disable_irq_wake(fep->wake_irq); - } return 0; } @@ -4057,9 +4065,19 @@ static int __maybe_unused fec_suspend(struct device *dev) netif_device_detach(ndev); netif_tx_unlock_bh(ndev); fec_stop(ndev); - fec_enet_clk_enable(ndev, false); - if (!(fep->wol_flag & FEC_WOL_FLAG_ENABLE)) + if (!(fep->wol_flag & FEC_WOL_FLAG_ENABLE)) { + fec_irqs_disable(ndev); pinctrl_pm_select_sleep_state(&fep->pdev->dev); + } else { + fec_irqs_disable_except_wakeup(ndev); + if (fep->wake_irq > 0) { + disable_irq(fep->wake_irq); + enable_irq_wake(fep->wake_irq); + } + fec_enet_stop_mode(fep, true); + } + /* It's safe to disable clocks since interrupts are masked */ + fec_enet_clk_enable(ndev, false); } rtnl_unlock(); @@ -4097,6 +4115,10 @@ static int __maybe_unused fec_resume(struct device *dev) } if (fep->wol_flag & FEC_WOL_FLAG_ENABLE) { fec_enet_stop_mode(fep, false); + if (fep->wake_irq) { + disable_irq_wake(fep->wake_irq); + enable_irq(fep->wake_irq); + } val = readl(fep->hwp + FEC_ECNTRL); val &= ~(FEC_ECR_MAGICEN | FEC_ECR_SLEEP); diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index d71eac7e1924..af99017a5453 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -473,10 +473,6 @@ int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: fep->hwts_tx_en = 0; diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index acab58fd3db3..206b7a35eaf5 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -2076,10 +2076,6 @@ static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: priv->hwts_tx_en = 0; diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index b719f72281c4..5f5d4f7aa813 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -229,6 +229,7 @@ struct gve_rx_ring { /* A TX desc ring entry */ union gve_tx_desc { struct gve_tx_pkt_desc pkt; /* first desc for a packet */ + struct gve_tx_mtd_desc mtd; /* optional metadata descriptor */ struct gve_tx_seg_desc seg; /* subsequent descs for a packet */ }; @@ -441,13 +442,13 @@ struct gve_tx_ring { * associated with that irq. */ struct gve_notify_block { - __be32 irq_db_index; /* idx into Bar2 - set by device, must be 1st */ + __be32 *irq_db_index; /* pointer to idx into Bar2 */ char name[IFNAMSIZ + 16]; /* name registered with the kernel */ struct napi_struct napi; /* kernel napi struct for this block */ struct gve_priv *priv; struct gve_tx_ring *tx; /* tx rings on this block */ struct gve_rx_ring *rx; /* rx rings on this block */ -} ____cacheline_aligned; +}; /* Tracks allowed and current queue settings */ struct gve_queue_config { @@ -466,6 +467,10 @@ struct gve_options_dqo_rda { u16 rx_buff_ring_entries; /* number of rx_buff descriptors */ }; +struct gve_irq_db { + __be32 index; +} ____cacheline_aligned; + struct gve_ptype { u8 l3_type; /* `gve_l3_type` in gve_adminq.h */ u8 l4_type; /* `gve_l4_type` in gve_adminq.h */ @@ -492,7 +497,8 @@ struct gve_priv { struct gve_rx_ring *rx; /* array of rx_cfg.num_queues */ struct gve_queue_page_list *qpls; /* array of num qpls */ struct gve_notify_block *ntfy_blocks; /* array of num_ntfy_blks */ - dma_addr_t ntfy_block_bus; + struct gve_irq_db *irq_db_indices; /* array of num_ntfy_blks */ + dma_addr_t irq_db_indices_bus; struct msix_entry *msix_vectors; /* array of num_ntfy_blks + 1 */ char mgmt_msix_name[IFNAMSIZ + 16]; u32 mgmt_msix_idx; @@ -551,6 +557,8 @@ struct gve_priv { u32 page_alloc_fail; /* count of page alloc fails */ u32 dma_mapping_error; /* count of dma mapping errors */ u32 stats_report_trigger_cnt; /* count of device-requested stats-reports since last reset */ + u32 suspend_cnt; /* count of times suspended */ + u32 resume_cnt; /* count of times resumed */ struct workqueue_struct *gve_wq; struct work_struct service_task; struct work_struct stats_report_task; @@ -567,6 +575,7 @@ struct gve_priv { /* Gvnic device link speed from hypervisor. */ u64 link_speed; + bool up_before_suspend; /* True if dev was up before suspend */ struct gve_options_dqo_rda options_dqo_rda; struct gve_ptype_lut *ptype_lut_dqo; @@ -575,6 +584,10 @@ struct gve_priv { int data_buffer_size_dqo; enum gve_queue_format queue_format; + + /* Interrupt coalescing settings */ + u32 tx_coalesce_usecs; + u32 rx_coalesce_usecs; }; enum gve_service_task_flags_bit { @@ -733,7 +746,7 @@ static inline void gve_clear_report_stats(struct gve_priv *priv) static inline __be32 __iomem *gve_irq_doorbell(struct gve_priv *priv, struct gve_notify_block *block) { - return &priv->db_bar2[be32_to_cpu(block->irq_db_index)]; + return &priv->db_bar2[be32_to_cpu(*block->irq_db_index)]; } /* Returns the index into ntfy_blocks of the given tx ring's block diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 83ae56c310d3..2ad7f57f7e5b 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -462,7 +462,7 @@ int gve_adminq_configure_device_resources(struct gve_priv *priv, .num_counters = cpu_to_be32(num_counters), .irq_db_addr = cpu_to_be64(db_array_bus_addr), .num_irq_dbs = cpu_to_be32(num_ntfy_blks), - .irq_db_stride = cpu_to_be32(sizeof(priv->ntfy_blocks[0])), + .irq_db_stride = cpu_to_be32(sizeof(*priv->irq_db_indices)), .ntfy_blk_msix_base_idx = cpu_to_be32(GVE_NTFY_BLK_BASE_MSIX_IDX), .queue_format = priv->queue_format, @@ -738,10 +738,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) * is not set to GqiRda, choose the queue format in a priority order: * DqoRda, GqiRda, GqiQpl. Use GqiQpl as default. */ - if (priv->queue_format == GVE_GQI_RDA_FORMAT) { - dev_info(&priv->pdev->dev, - "Driver is running with GQI RDA queue format.\n"); - } else if (dev_op_dqo_rda) { + if (dev_op_dqo_rda) { priv->queue_format = GVE_DQO_RDA_FORMAT; dev_info(&priv->pdev->dev, "Driver is running with DQO RDA queue format.\n"); @@ -753,6 +750,9 @@ int gve_adminq_describe_device(struct gve_priv *priv) "Driver is running with GQI RDA queue format.\n"); supported_features_mask = be32_to_cpu(dev_op_gqi_rda->supported_features_mask); + } else if (priv->queue_format == GVE_GQI_RDA_FORMAT) { + dev_info(&priv->pdev->dev, + "Driver is running with GQI RDA queue format.\n"); } else { priv->queue_format = GVE_GQI_QPL_FORMAT; if (dev_op_gqi_qpl) diff --git a/drivers/net/ethernet/google/gve/gve_desc.h b/drivers/net/ethernet/google/gve/gve_desc.h index 4d225a18d8ce..f4ae9e19b844 100644 --- a/drivers/net/ethernet/google/gve/gve_desc.h +++ b/drivers/net/ethernet/google/gve/gve_desc.h @@ -33,6 +33,14 @@ struct gve_tx_pkt_desc { __be64 seg_addr; /* Base address (see note) of this segment */ } __packed; +struct gve_tx_mtd_desc { + u8 type_flags; /* type is lower 4 bits, subtype upper */ + u8 path_state; /* state is lower 4 bits, hash type upper */ + __be16 reserved0; + __be32 path_hash; + __be64 reserved1; +} __packed; + struct gve_tx_seg_desc { u8 type_flags; /* type is lower 4 bits, flags upper */ u8 l3_offset; /* TSO: 2 byte units to start of IPH */ @@ -46,6 +54,7 @@ struct gve_tx_seg_desc { #define GVE_TXD_STD (0x0 << 4) /* Std with Host Address */ #define GVE_TXD_TSO (0x1 << 4) /* TSO with Host Address */ #define GVE_TXD_SEG (0x2 << 4) /* Seg with Host Address */ +#define GVE_TXD_MTD (0x3 << 4) /* Metadata */ /* GVE Transmit Descriptor Flags for Std Pkts */ #define GVE_TXF_L4CSUM BIT(0) /* Need csum offload */ @@ -54,6 +63,17 @@ struct gve_tx_seg_desc { /* GVE Transmit Descriptor Flags for TSO Segs */ #define GVE_TXSF_IPV6 BIT(1) /* IPv6 TSO */ +/* GVE Transmit Descriptor Options for MTD Segs */ +#define GVE_MTD_SUBTYPE_PATH 0 + +#define GVE_MTD_PATH_STATE_DEFAULT 0 +#define GVE_MTD_PATH_STATE_TIMEOUT 1 +#define GVE_MTD_PATH_STATE_CONGESTION 2 +#define GVE_MTD_PATH_STATE_RETRANSMIT 3 + +#define GVE_MTD_PATH_HASH_NONE (0x0 << 4) +#define GVE_MTD_PATH_HASH_L4 (0x1 << 4) + /* GVE Receive Packet Descriptor */ /* The start of an ethernet packet comes 2 bytes into the rx buffer. * gVNIC adds this padding so that both the DMA and the L3/4 protocol header diff --git a/drivers/net/ethernet/google/gve/gve_dqo.h b/drivers/net/ethernet/google/gve/gve_dqo.h index 836042364124..1eb4d5fd8561 100644 --- a/drivers/net/ethernet/google/gve/gve_dqo.h +++ b/drivers/net/ethernet/google/gve/gve_dqo.h @@ -18,6 +18,7 @@ #define GVE_TX_IRQ_RATELIMIT_US_DQO 50 #define GVE_RX_IRQ_RATELIMIT_US_DQO 20 +#define GVE_MAX_ITR_INTERVAL_DQO (GVE_ITR_INTERVAL_DQO_MASK * 2) /* Timeout in seconds to wait for a reinjection completion after receiving * its corresponding miss completion. @@ -54,17 +55,17 @@ gve_tx_put_doorbell_dqo(const struct gve_priv *priv, } /* Builds register value to write to DQO IRQ doorbell to enable with specified - * ratelimit. + * ITR interval. */ -static inline u32 gve_set_itr_ratelimit_dqo(u32 ratelimit_us) +static inline u32 gve_setup_itr_interval_dqo(u32 interval_us) { u32 result = GVE_ITR_ENABLE_BIT_DQO; /* Interval has 2us granularity. */ - ratelimit_us >>= 1; + interval_us >>= 1; - ratelimit_us &= GVE_ITR_INTERVAL_DQO_MASK; - result |= (ratelimit_us << GVE_ITR_INTERVAL_DQO_SHIFT); + interval_us &= GVE_ITR_INTERVAL_DQO_MASK; + result |= (interval_us << GVE_ITR_INTERVAL_DQO_SHIFT); return result; } @@ -73,9 +74,20 @@ static inline void gve_write_irq_doorbell_dqo(const struct gve_priv *priv, const struct gve_notify_block *block, u32 val) { - u32 index = be32_to_cpu(block->irq_db_index); + u32 index = be32_to_cpu(*block->irq_db_index); iowrite32(val, &priv->db_bar2[index]); } +/* Sets interrupt throttling interval and enables interrupt + * by writing to IRQ doorbell. + */ +static inline void +gve_set_itr_coalesce_usecs_dqo(struct gve_priv *priv, + struct gve_notify_block *block, + u32 usecs) +{ + gve_write_irq_doorbell_dqo(priv, block, + gve_setup_itr_interval_dqo(usecs)); +} #endif /* _GVE_DQO_H_ */ diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index fd2d2c705391..50b384910c83 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -8,6 +8,7 @@ #include <linux/rtnetlink.h> #include "gve.h" #include "gve_adminq.h" +#include "gve_dqo.h" static void gve_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info) @@ -42,7 +43,7 @@ static const char gve_gstrings_main_stats[][ETH_GSTRING_LEN] = { }; static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = { - "rx_posted_desc[%u]", "rx_completed_desc[%u]", "rx_bytes[%u]", + "rx_posted_desc[%u]", "rx_completed_desc[%u]", "rx_consumed_desc[%u]", "rx_bytes[%u]", "rx_cont_packet_cnt[%u]", "rx_frag_flip_cnt[%u]", "rx_frag_copy_cnt[%u]", "rx_dropped_pkt[%u]", "rx_copybreak_pkt[%u]", "rx_copied_pkt[%u]", "rx_queue_drop_cnt[%u]", "rx_no_buffers_posted[%u]", @@ -50,7 +51,7 @@ static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = { }; static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = { - "tx_posted_desc[%u]", "tx_completed_desc[%u]", "tx_bytes[%u]", + "tx_posted_desc[%u]", "tx_completed_desc[%u]", "tx_consumed_desc[%u]", "tx_bytes[%u]", "tx_wake[%u]", "tx_stop[%u]", "tx_event_counter[%u]", "tx_dma_mapping_error[%u]", }; @@ -139,10 +140,11 @@ static void gve_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { - u64 tmp_rx_pkts, tmp_rx_bytes, tmp_rx_skb_alloc_fail, tmp_rx_buf_alloc_fail, - tmp_rx_desc_err_dropped_pkt, tmp_tx_pkts, tmp_tx_bytes; + u64 tmp_rx_pkts, tmp_rx_bytes, tmp_rx_skb_alloc_fail, + tmp_rx_buf_alloc_fail, tmp_rx_desc_err_dropped_pkt, + tmp_tx_pkts, tmp_tx_bytes; u64 rx_buf_alloc_fail, rx_desc_err_dropped_pkt, rx_pkts, - rx_skb_alloc_fail, rx_bytes, tx_pkts, tx_bytes; + rx_skb_alloc_fail, rx_bytes, tx_pkts, tx_bytes, tx_dropped; int stats_idx, base_stats_idx, max_stats_idx; struct stats *report_stats; int *rx_qid_to_stats_idx; @@ -191,7 +193,7 @@ gve_get_ethtool_stats(struct net_device *netdev, rx_desc_err_dropped_pkt += tmp_rx_desc_err_dropped_pkt; } } - for (tx_pkts = 0, tx_bytes = 0, ring = 0; + for (tx_pkts = 0, tx_bytes = 0, tx_dropped = 0, ring = 0; ring < priv->tx_cfg.num_queues; ring++) { if (priv->tx) { do { @@ -203,6 +205,7 @@ gve_get_ethtool_stats(struct net_device *netdev, start)); tx_pkts += tmp_tx_pkts; tx_bytes += tmp_tx_bytes; + tx_dropped += priv->tx[ring].dropped_pkt; } } @@ -214,9 +217,7 @@ gve_get_ethtool_stats(struct net_device *netdev, /* total rx dropped packets */ data[i++] = rx_skb_alloc_fail + rx_buf_alloc_fail + rx_desc_err_dropped_pkt; - /* Skip tx_dropped */ - i++; - + data[i++] = tx_dropped; data[i++] = priv->tx_timeo_cnt; data[i++] = rx_skb_alloc_fail; data[i++] = rx_buf_alloc_fail; @@ -255,6 +256,7 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = rx->fill_cnt; data[i++] = rx->cnt; + data[i++] = rx->fill_cnt - rx->cnt; do { start = u64_stats_fetch_begin(&priv->rx[ring].statss); @@ -318,12 +320,14 @@ gve_get_ethtool_stats(struct net_device *netdev, if (gve_is_gqi(priv)) { data[i++] = tx->req; data[i++] = tx->done; + data[i++] = tx->req - tx->done; } else { /* DQO doesn't currently support * posted/completed descriptor counts; */ data[i++] = 0; data[i++] = 0; + data[i++] = tx->dqo_tx.tail - tx->dqo_tx.head; } do { start = @@ -537,7 +541,65 @@ static int gve_get_link_ksettings(struct net_device *netdev, return err; } +static int gve_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_ec, + struct netlink_ext_ack *extack) +{ + struct gve_priv *priv = netdev_priv(netdev); + + if (gve_is_gqi(priv)) + return -EOPNOTSUPP; + ec->tx_coalesce_usecs = priv->tx_coalesce_usecs; + ec->rx_coalesce_usecs = priv->rx_coalesce_usecs; + + return 0; +} + +static int gve_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_ec, + struct netlink_ext_ack *extack) +{ + struct gve_priv *priv = netdev_priv(netdev); + u32 tx_usecs_orig = priv->tx_coalesce_usecs; + u32 rx_usecs_orig = priv->rx_coalesce_usecs; + int idx; + + if (gve_is_gqi(priv)) + return -EOPNOTSUPP; + + if (ec->tx_coalesce_usecs > GVE_MAX_ITR_INTERVAL_DQO || + ec->rx_coalesce_usecs > GVE_MAX_ITR_INTERVAL_DQO) + return -EINVAL; + priv->tx_coalesce_usecs = ec->tx_coalesce_usecs; + priv->rx_coalesce_usecs = ec->rx_coalesce_usecs; + + if (tx_usecs_orig != priv->tx_coalesce_usecs) { + for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) { + int ntfy_idx = gve_tx_idx_to_ntfy(priv, idx); + struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; + + gve_set_itr_coalesce_usecs_dqo(priv, block, + priv->tx_coalesce_usecs); + } + } + + if (rx_usecs_orig != priv->rx_coalesce_usecs) { + for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) { + int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx); + struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx]; + + gve_set_itr_coalesce_usecs_dqo(priv, block, + priv->rx_coalesce_usecs); + } + } + + return 0; +} + const struct ethtool_ops gve_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_USECS, .get_drvinfo = gve_get_drvinfo, .get_strings = gve_get_strings, .get_sset_count = gve_get_sset_count, @@ -547,6 +609,8 @@ const struct ethtool_ops gve_ethtool_ops = { .set_channels = gve_set_channels, .get_channels = gve_get_channels, .get_link = ethtool_op_get_link, + .get_coalesce = gve_get_coalesce, + .set_coalesce = gve_set_coalesce, .get_ringparam = gve_get_ringparam, .reset = gve_user_reset, .get_tunable = gve_get_tunable, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 59b66f679e46..f7f65c4bf993 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -334,15 +334,23 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) dev_err(&priv->pdev->dev, "Did not receive management vector.\n"); goto abort_with_msix_enabled; } - priv->ntfy_blocks = + priv->irq_db_indices = dma_alloc_coherent(&priv->pdev->dev, priv->num_ntfy_blks * - sizeof(*priv->ntfy_blocks), - &priv->ntfy_block_bus, GFP_KERNEL); - if (!priv->ntfy_blocks) { + sizeof(*priv->irq_db_indices), + &priv->irq_db_indices_bus, GFP_KERNEL); + if (!priv->irq_db_indices) { err = -ENOMEM; goto abort_with_mgmt_vector; } + + priv->ntfy_blocks = kvzalloc(priv->num_ntfy_blks * + sizeof(*priv->ntfy_blocks), GFP_KERNEL); + if (!priv->ntfy_blocks) { + err = -ENOMEM; + goto abort_with_irq_db_indices; + } + /* Setup the other blocks - the first n-1 vectors */ for (i = 0; i < priv->num_ntfy_blks; i++) { struct gve_notify_block *block = &priv->ntfy_blocks[i]; @@ -361,6 +369,7 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) } irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector, get_cpu_mask(i % active_cpus)); + block->irq_db_index = &priv->irq_db_indices[i].index; } return 0; abort_with_some_ntfy_blocks: @@ -372,10 +381,13 @@ abort_with_some_ntfy_blocks: NULL); free_irq(priv->msix_vectors[msix_idx].vector, block); } - dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks * - sizeof(*priv->ntfy_blocks), - priv->ntfy_blocks, priv->ntfy_block_bus); + kvfree(priv->ntfy_blocks); priv->ntfy_blocks = NULL; +abort_with_irq_db_indices: + dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks * + sizeof(*priv->irq_db_indices), + priv->irq_db_indices, priv->irq_db_indices_bus); + priv->irq_db_indices = NULL; abort_with_mgmt_vector: free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); abort_with_msix_enabled: @@ -403,10 +415,12 @@ static void gve_free_notify_blocks(struct gve_priv *priv) free_irq(priv->msix_vectors[msix_idx].vector, block); } free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv); - dma_free_coherent(&priv->pdev->dev, - priv->num_ntfy_blks * sizeof(*priv->ntfy_blocks), - priv->ntfy_blocks, priv->ntfy_block_bus); + kvfree(priv->ntfy_blocks); priv->ntfy_blocks = NULL; + dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks * + sizeof(*priv->irq_db_indices), + priv->irq_db_indices, priv->irq_db_indices_bus); + priv->irq_db_indices = NULL; pci_disable_msix(priv->pdev); kvfree(priv->msix_vectors); priv->msix_vectors = NULL; @@ -428,7 +442,7 @@ static int gve_setup_device_resources(struct gve_priv *priv) err = gve_adminq_configure_device_resources(priv, priv->counter_array_bus, priv->num_event_counters, - priv->ntfy_block_bus, + priv->irq_db_indices_bus, priv->num_ntfy_blks); if (unlikely(err)) { dev_err(&priv->pdev->dev, @@ -817,8 +831,7 @@ void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma, put_page(page); } -static void gve_free_queue_page_list(struct gve_priv *priv, - int id) +static void gve_free_queue_page_list(struct gve_priv *priv, u32 id) { struct gve_queue_page_list *qpl = &priv->qpls[id]; int i; @@ -1100,9 +1113,8 @@ static void gve_turnup(struct gve_priv *priv) if (gve_is_gqi(priv)) { iowrite32be(0, gve_irq_doorbell(priv, block)); } else { - u32 val = gve_set_itr_ratelimit_dqo(GVE_TX_IRQ_RATELIMIT_US_DQO); - - gve_write_irq_doorbell_dqo(priv, block, val); + gve_set_itr_coalesce_usecs_dqo(priv, block, + priv->tx_coalesce_usecs); } } for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) { @@ -1113,9 +1125,8 @@ static void gve_turnup(struct gve_priv *priv) if (gve_is_gqi(priv)) { iowrite32be(0, gve_irq_doorbell(priv, block)); } else { - u32 val = gve_set_itr_ratelimit_dqo(GVE_RX_IRQ_RATELIMIT_US_DQO); - - gve_write_irq_doorbell_dqo(priv, block, val); + gve_set_itr_coalesce_usecs_dqo(priv, block, + priv->rx_coalesce_usecs); } } @@ -1412,6 +1423,11 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) dev_info(&priv->pdev->dev, "Max TX queues %d, Max RX queues %d\n", priv->tx_cfg.max_queues, priv->rx_cfg.max_queues); + if (!gve_is_gqi(priv)) { + priv->tx_coalesce_usecs = GVE_TX_IRQ_RATELIMIT_US_DQO; + priv->rx_coalesce_usecs = GVE_RX_IRQ_RATELIMIT_US_DQO; + } + setup_device: err = gve_setup_device_resources(priv); if (!err) @@ -1663,6 +1679,58 @@ static void gve_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static void gve_shutdown(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct gve_priv *priv = netdev_priv(netdev); + bool was_up = netif_carrier_ok(priv->dev); + + rtnl_lock(); + if (was_up && gve_close(priv->dev)) { + /* If the dev was up, attempt to close, if close fails, reset */ + gve_reset_and_teardown(priv, was_up); + } else { + /* If the dev wasn't up or close worked, finish tearing down */ + gve_teardown_priv_resources(priv); + } + rtnl_unlock(); +} + +#ifdef CONFIG_PM +static int gve_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct gve_priv *priv = netdev_priv(netdev); + bool was_up = netif_carrier_ok(priv->dev); + + priv->suspend_cnt++; + rtnl_lock(); + if (was_up && gve_close(priv->dev)) { + /* If the dev was up, attempt to close, if close fails, reset */ + gve_reset_and_teardown(priv, was_up); + } else { + /* If the dev wasn't up or close worked, finish tearing down */ + gve_teardown_priv_resources(priv); + } + priv->up_before_suspend = was_up; + rtnl_unlock(); + return 0; +} + +static int gve_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct gve_priv *priv = netdev_priv(netdev); + int err; + + priv->resume_cnt++; + rtnl_lock(); + err = gve_reset_recovery(priv, priv->up_before_suspend); + rtnl_unlock(); + return err; +} +#endif /* CONFIG_PM */ + static const struct pci_device_id gve_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_GOOGLE, PCI_DEV_ID_GVNIC) }, { } @@ -1673,6 +1741,11 @@ static struct pci_driver gvnic_driver = { .id_table = gve_id_table, .probe = gve_probe, .remove = gve_remove, + .shutdown = gve_shutdown, +#ifdef CONFIG_PM + .suspend = gve_suspend, + .resume = gve_resume, +#endif }; module_pci_driver(gvnic_driver); diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 3d04b5aff331..9ddcc497f48e 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -639,8 +639,6 @@ bool gve_rx_work_pending(struct gve_rx_ring *rx) desc = rx->desc.desc_ring + next_idx; flags_seq = desc->flags_seq; - /* Make sure we have synchronized the seq no with the device */ - smp_rmb(); return (GVE_SEQNO(flags_seq) == rx->desc.seqno); } diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index a9cb241fedf4..4888bf05fbed 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -296,11 +296,14 @@ static inline int gve_skb_fifo_bytes_required(struct gve_tx_ring *tx, return bytes; } -/* The most descriptors we could need is MAX_SKB_FRAGS + 3 : 1 for each skb frag, - * +1 for the skb linear portion, +1 for when tcp hdr needs to be in separate descriptor, - * and +1 if the payload wraps to the beginning of the FIFO. +/* The most descriptors we could need is MAX_SKB_FRAGS + 4 : + * 1 for each skb frag + * 1 for the skb linear portion + * 1 for when tcp hdr needs to be in separate descriptor + * 1 if the payload wraps to the beginning of the FIFO + * 1 for metadata descriptor */ -#define MAX_TX_DESC_NEEDED (MAX_SKB_FRAGS + 3) +#define MAX_TX_DESC_NEEDED (MAX_SKB_FRAGS + 4) static void gve_tx_unmap_buf(struct device *dev, struct gve_tx_buffer_state *info) { if (info->skb) { @@ -395,6 +398,19 @@ static void gve_tx_fill_pkt_desc(union gve_tx_desc *pkt_desc, pkt_desc->pkt.seg_addr = cpu_to_be64(addr); } +static void gve_tx_fill_mtd_desc(union gve_tx_desc *mtd_desc, + struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(mtd_desc->mtd) != sizeof(mtd_desc->pkt)); + + mtd_desc->mtd.type_flags = GVE_TXD_MTD | GVE_MTD_SUBTYPE_PATH; + mtd_desc->mtd.path_state = GVE_MTD_PATH_STATE_DEFAULT | + GVE_MTD_PATH_HASH_L4; + mtd_desc->mtd.path_hash = cpu_to_be32(skb->hash); + mtd_desc->mtd.reserved0 = 0; + mtd_desc->mtd.reserved1 = 0; +} + static void gve_tx_fill_seg_desc(union gve_tx_desc *seg_desc, struct sk_buff *skb, bool is_gso, u16 len, u64 addr) @@ -426,6 +442,7 @@ static int gve_tx_add_skb_copy(struct gve_priv *priv, struct gve_tx_ring *tx, st int pad_bytes, hlen, hdr_nfrags, payload_nfrags, l4_hdr_offset; union gve_tx_desc *pkt_desc, *seg_desc; struct gve_tx_buffer_state *info; + int mtd_desc_nr = !!skb->l4_hash; bool is_gso = skb_is_gso(skb); u32 idx = tx->req & tx->mask; int payload_iov = 2; @@ -457,7 +474,7 @@ static int gve_tx_add_skb_copy(struct gve_priv *priv, struct gve_tx_ring *tx, st &info->iov[payload_iov]); gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset, - 1 + payload_nfrags, hlen, + 1 + mtd_desc_nr + payload_nfrags, hlen, info->iov[hdr_nfrags - 1].iov_offset); skb_copy_bits(skb, 0, @@ -468,8 +485,13 @@ static int gve_tx_add_skb_copy(struct gve_priv *priv, struct gve_tx_ring *tx, st info->iov[hdr_nfrags - 1].iov_len); copy_offset = hlen; + if (mtd_desc_nr) { + next_idx = (tx->req + 1) & tx->mask; + gve_tx_fill_mtd_desc(&tx->desc[next_idx], skb); + } + for (i = payload_iov; i < payload_nfrags + payload_iov; i++) { - next_idx = (tx->req + 1 + i - payload_iov) & tx->mask; + next_idx = (tx->req + 1 + mtd_desc_nr + i - payload_iov) & tx->mask; seg_desc = &tx->desc[next_idx]; gve_tx_fill_seg_desc(seg_desc, skb, is_gso, @@ -485,16 +507,17 @@ static int gve_tx_add_skb_copy(struct gve_priv *priv, struct gve_tx_ring *tx, st copy_offset += info->iov[i].iov_len; } - return 1 + payload_nfrags; + return 1 + mtd_desc_nr + payload_nfrags; } static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); - int hlen, payload_nfrags, l4_hdr_offset; - union gve_tx_desc *pkt_desc, *seg_desc; + int hlen, num_descriptors, l4_hdr_offset; + union gve_tx_desc *pkt_desc, *mtd_desc, *seg_desc; struct gve_tx_buffer_state *info; + int mtd_desc_nr = !!skb->l4_hash; bool is_gso = skb_is_gso(skb); u32 idx = tx->req & tx->mask; u64 addr; @@ -523,23 +546,30 @@ static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, dma_unmap_len_set(info, len, len); dma_unmap_addr_set(info, dma, addr); - payload_nfrags = shinfo->nr_frags; + num_descriptors = 1 + shinfo->nr_frags; + if (hlen < len) + num_descriptors++; + if (mtd_desc_nr) + num_descriptors++; + + gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset, + num_descriptors, hlen, addr); + + if (mtd_desc_nr) { + idx = (idx + 1) & tx->mask; + mtd_desc = &tx->desc[idx]; + gve_tx_fill_mtd_desc(mtd_desc, skb); + } + if (hlen < len) { /* For gso the rest of the linear portion of the skb needs to * be in its own descriptor. */ - payload_nfrags++; - gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset, - 1 + payload_nfrags, hlen, addr); - len -= hlen; addr += hlen; - idx = (tx->req + 1) & tx->mask; + idx = (idx + 1) & tx->mask; seg_desc = &tx->desc[idx]; gve_tx_fill_seg_desc(seg_desc, skb, is_gso, len, addr); - } else { - gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset, - 1 + payload_nfrags, hlen, addr); } for (i = 0; i < shinfo->nr_frags; i++) { @@ -560,11 +590,14 @@ static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, gve_tx_fill_seg_desc(seg_desc, skb, is_gso, len, addr); } - return 1 + payload_nfrags; + return num_descriptors; unmap_drop: - i += (payload_nfrags == shinfo->nr_frags ? 1 : 2); + i += num_descriptors - shinfo->nr_frags; while (i--) { + /* Skip metadata descriptor, if set */ + if (i == 1 && mtd_desc_nr == 1) + continue; idx--; gve_tx_unmap_buf(tx->dev, &tx->info[idx & tx->mask]); } diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c index 88ca49cbc1e2..d57508bc4307 100644 --- a/drivers/net/ethernet/google/gve/gve_utils.c +++ b/drivers/net/ethernet/google/gve/gve_utils.c @@ -68,6 +68,9 @@ struct sk_buff *gve_rx_copy(struct net_device *dev, struct napi_struct *napi, set_protocol = ctx->curr_frag_cnt == ctx->expected_frag_cnt - 1; } else { skb = napi_alloc_skb(napi, len); + + if (unlikely(!skb)) + return NULL; set_protocol = true; } __skb_put(skb, len); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 54caf0dd1204..9298fbecb31a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -839,6 +839,8 @@ struct hnae3_handle { u8 netdev_flags; struct dentry *hnae3_dbgfs; + /* protects concurrent contention between debugfs commands */ + struct mutex dbgfs_lock; /* Network interface message level enabled bits */ u32 msg_enable; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 817e2e8a7287..f726a5b70f9e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1226,6 +1226,7 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, if (ret) return ret; + mutex_lock(&handle->dbgfs_lock); save_buf = &hns3_dbg_cmd[index].buf; if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) || @@ -1238,15 +1239,15 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, read_buf = *save_buf; } else { read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL); - if (!read_buf) - return -ENOMEM; + if (!read_buf) { + ret = -ENOMEM; + goto out; + } /* save the buffer addr until the last read operation */ *save_buf = read_buf; - } - /* get data ready for the first time to read */ - if (!*ppos) { + /* get data ready for the first time to read */ ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd, read_buf, hns3_dbg_cmd[index].buf_len); if (ret) @@ -1255,8 +1256,10 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, size = simple_read_from_buffer(buffer, count, ppos, read_buf, strlen(read_buf)); - if (size > 0) + if (size > 0) { + mutex_unlock(&handle->dbgfs_lock); return size; + } out: /* free the buffer for the last read operation */ @@ -1265,6 +1268,7 @@ out: *save_buf = NULL; } + mutex_unlock(&handle->dbgfs_lock); return ret; } @@ -1337,6 +1341,8 @@ int hns3_dbg_init(struct hnae3_handle *handle) debugfs_create_dir(hns3_dbg_dentry[i].name, handle->hnae3_dbgfs); + mutex_init(&handle->dbgfs_lock); + for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) { if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES && ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) || @@ -1363,6 +1369,7 @@ int hns3_dbg_init(struct hnae3_handle *handle) return 0; out: + mutex_destroy(&handle->dbgfs_lock); debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; return ret; @@ -1378,6 +1385,7 @@ void hns3_dbg_uninit(struct hnae3_handle *handle) hns3_dbg_cmd[i].buf = NULL; } + mutex_destroy(&handle->dbgfs_lock); debugfs_remove_recursive(handle->hnae3_dbgfs); handle->hnae3_dbgfs = NULL; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index fdc66fae0960..c5ac6ecf36e1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -114,7 +114,8 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, memcpy(&req->msg, send_msg, sizeof(struct hclge_vf_to_pf_msg)); - trace_hclge_vf_mbx_send(hdev, req); + if (test_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state)) + trace_hclge_vf_mbx_send(hdev, req); /* synchronous send */ if (need_resp) { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c index 06586173add7..998717f02136 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c @@ -814,7 +814,6 @@ static int api_chain_init(struct hinic_api_cmd_chain *chain, { struct hinic_hwif *hwif = attr->hwif; struct pci_dev *pdev = hwif->pdev; - size_t cell_ctxt_size; chain->hwif = hwif; chain->chain_type = attr->chain_type; @@ -826,8 +825,8 @@ static int api_chain_init(struct hinic_api_cmd_chain *chain, sema_init(&chain->sem, 1); - cell_ctxt_size = chain->num_cells * sizeof(*chain->cell_ctxt); - chain->cell_ctxt = devm_kzalloc(&pdev->dev, cell_ctxt_size, GFP_KERNEL); + chain->cell_ctxt = devm_kcalloc(&pdev->dev, chain->num_cells, + sizeof(*chain->cell_ctxt), GFP_KERNEL); if (!chain->cell_ctxt) return -ENOMEM; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c index 307a6d4af993..a627237f694b 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c @@ -796,11 +796,10 @@ static int init_cmdqs_ctxt(struct hinic_hwdev *hwdev, struct hinic_cmdq_ctxt *cmdq_ctxts; struct pci_dev *pdev = hwif->pdev; struct hinic_pfhwdev *pfhwdev; - size_t cmdq_ctxts_size; int err; - cmdq_ctxts_size = HINIC_MAX_CMDQ_TYPES * sizeof(*cmdq_ctxts); - cmdq_ctxts = devm_kzalloc(&pdev->dev, cmdq_ctxts_size, GFP_KERNEL); + cmdq_ctxts = devm_kcalloc(&pdev->dev, HINIC_MAX_CMDQ_TYPES, + sizeof(*cmdq_ctxts), GFP_KERNEL); if (!cmdq_ctxts) return -ENOMEM; @@ -884,7 +883,6 @@ int hinic_init_cmdqs(struct hinic_cmdqs *cmdqs, struct hinic_hwif *hwif, struct hinic_func_to_io *func_to_io = cmdqs_to_func_to_io(cmdqs); struct pci_dev *pdev = hwif->pdev; struct hinic_hwdev *hwdev; - size_t saved_wqs_size; u16 max_wqe_size; int err; @@ -895,8 +893,8 @@ int hinic_init_cmdqs(struct hinic_cmdqs *cmdqs, struct hinic_hwif *hwif, if (!cmdqs->cmdq_buf_pool) return -ENOMEM; - saved_wqs_size = HINIC_MAX_CMDQ_TYPES * sizeof(struct hinic_wq); - cmdqs->saved_wqs = devm_kzalloc(&pdev->dev, saved_wqs_size, GFP_KERNEL); + cmdqs->saved_wqs = devm_kcalloc(&pdev->dev, HINIC_MAX_CMDQ_TYPES, + sizeof(*cmdqs->saved_wqs), GFP_KERNEL); if (!cmdqs->saved_wqs) { err = -ENOMEM; goto err_saved_wqs; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 657a15447bd0..2127a48749a8 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -162,7 +162,6 @@ static int init_msix(struct hinic_hwdev *hwdev) struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; int nr_irqs, num_aeqs, num_ceqs; - size_t msix_entries_size; int i, err; num_aeqs = HINIC_HWIF_NUM_AEQS(hwif); @@ -171,8 +170,8 @@ static int init_msix(struct hinic_hwdev *hwdev) if (nr_irqs > HINIC_HWIF_NUM_IRQS(hwif)) nr_irqs = HINIC_HWIF_NUM_IRQS(hwif); - msix_entries_size = nr_irqs * sizeof(*hwdev->msix_entries); - hwdev->msix_entries = devm_kzalloc(&pdev->dev, msix_entries_size, + hwdev->msix_entries = devm_kcalloc(&pdev->dev, nr_irqs, + sizeof(*hwdev->msix_entries), GFP_KERNEL); if (!hwdev->msix_entries) return -ENOMEM; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c index d3fc05a07fdb..045c47786a04 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c @@ -631,16 +631,15 @@ static int alloc_eq_pages(struct hinic_eq *eq) struct hinic_hwif *hwif = eq->hwif; struct pci_dev *pdev = hwif->pdev; u32 init_val, addr, val; - size_t addr_size; int err, pg; - addr_size = eq->num_pages * sizeof(*eq->dma_addr); - eq->dma_addr = devm_kzalloc(&pdev->dev, addr_size, GFP_KERNEL); + eq->dma_addr = devm_kcalloc(&pdev->dev, eq->num_pages, + sizeof(*eq->dma_addr), GFP_KERNEL); if (!eq->dma_addr) return -ENOMEM; - addr_size = eq->num_pages * sizeof(*eq->virt_addr); - eq->virt_addr = devm_kzalloc(&pdev->dev, addr_size, GFP_KERNEL); + eq->virt_addr = devm_kcalloc(&pdev->dev, eq->num_pages, + sizeof(*eq->virt_addr), GFP_KERNEL); if (!eq->virt_addr) { err = -ENOMEM; goto err_virt_addr_alloc; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c index a6e43d686293..c4a0ba6e183a 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c @@ -375,31 +375,30 @@ int hinic_io_create_qps(struct hinic_func_to_io *func_to_io, { struct hinic_hwif *hwif = func_to_io->hwif; struct pci_dev *pdev = hwif->pdev; - size_t qps_size, wq_size, db_size; void *ci_addr_base; int i, j, err; - qps_size = num_qps * sizeof(*func_to_io->qps); - func_to_io->qps = devm_kzalloc(&pdev->dev, qps_size, GFP_KERNEL); + func_to_io->qps = devm_kcalloc(&pdev->dev, num_qps, + sizeof(*func_to_io->qps), GFP_KERNEL); if (!func_to_io->qps) return -ENOMEM; - wq_size = num_qps * sizeof(*func_to_io->sq_wq); - func_to_io->sq_wq = devm_kzalloc(&pdev->dev, wq_size, GFP_KERNEL); + func_to_io->sq_wq = devm_kcalloc(&pdev->dev, num_qps, + sizeof(*func_to_io->sq_wq), GFP_KERNEL); if (!func_to_io->sq_wq) { err = -ENOMEM; goto err_sq_wq; } - wq_size = num_qps * sizeof(*func_to_io->rq_wq); - func_to_io->rq_wq = devm_kzalloc(&pdev->dev, wq_size, GFP_KERNEL); + func_to_io->rq_wq = devm_kcalloc(&pdev->dev, num_qps, + sizeof(*func_to_io->rq_wq), GFP_KERNEL); if (!func_to_io->rq_wq) { err = -ENOMEM; goto err_rq_wq; } - db_size = num_qps * sizeof(*func_to_io->sq_db); - func_to_io->sq_db = devm_kzalloc(&pdev->dev, db_size, GFP_KERNEL); + func_to_io->sq_db = devm_kcalloc(&pdev->dev, num_qps, + sizeof(*func_to_io->sq_db), GFP_KERNEL); if (!func_to_io->sq_db) { err = -ENOMEM; goto err_sq_db; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c index 7f0f1aa3cedd..2d9b06d7caad 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c @@ -193,20 +193,20 @@ static int alloc_page_arrays(struct hinic_wqs *wqs) { struct hinic_hwif *hwif = wqs->hwif; struct pci_dev *pdev = hwif->pdev; - size_t size; - size = wqs->num_pages * sizeof(*wqs->page_paddr); - wqs->page_paddr = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + wqs->page_paddr = devm_kcalloc(&pdev->dev, wqs->num_pages, + sizeof(*wqs->page_paddr), GFP_KERNEL); if (!wqs->page_paddr) return -ENOMEM; - size = wqs->num_pages * sizeof(*wqs->page_vaddr); - wqs->page_vaddr = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + wqs->page_vaddr = devm_kcalloc(&pdev->dev, wqs->num_pages, + sizeof(*wqs->page_vaddr), GFP_KERNEL); if (!wqs->page_vaddr) goto err_page_vaddr; - size = wqs->num_pages * sizeof(*wqs->shadow_page_vaddr); - wqs->shadow_page_vaddr = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + wqs->shadow_page_vaddr = devm_kcalloc(&pdev->dev, wqs->num_pages, + sizeof(*wqs->shadow_page_vaddr), + GFP_KERNEL); if (!wqs->shadow_page_vaddr) goto err_page_shadow_vaddr; @@ -379,15 +379,14 @@ static int alloc_wqes_shadow(struct hinic_wq *wq) { struct hinic_hwif *hwif = wq->hwif; struct pci_dev *pdev = hwif->pdev; - size_t size; - size = wq->num_q_pages * wq->max_wqe_size; - wq->shadow_wqe = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + wq->shadow_wqe = devm_kcalloc(&pdev->dev, wq->num_q_pages, + wq->max_wqe_size, GFP_KERNEL); if (!wq->shadow_wqe) return -ENOMEM; - size = wq->num_q_pages * sizeof(wq->prod_idx); - wq->shadow_idx = devm_kzalloc(&pdev->dev, size, GFP_KERNEL); + wq->shadow_idx = devm_kcalloc(&pdev->dev, wq->num_q_pages, + sizeof(wq->prod_idx), GFP_KERNEL); if (!wq->shadow_idx) goto err_shadow_idx; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index f9a766b8ac43..1e1b1be86174 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -144,13 +144,12 @@ static int create_txqs(struct hinic_dev *nic_dev) { int err, i, j, num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev); struct net_device *netdev = nic_dev->netdev; - size_t txq_size; if (nic_dev->txqs) return -EINVAL; - txq_size = num_txqs * sizeof(*nic_dev->txqs); - nic_dev->txqs = devm_kzalloc(&netdev->dev, txq_size, GFP_KERNEL); + nic_dev->txqs = devm_kcalloc(&netdev->dev, num_txqs, + sizeof(*nic_dev->txqs), GFP_KERNEL); if (!nic_dev->txqs) return -ENOMEM; @@ -241,13 +240,12 @@ static int create_rxqs(struct hinic_dev *nic_dev) { int err, i, j, num_rxqs = hinic_hwdev_num_qps(nic_dev->hwdev); struct net_device *netdev = nic_dev->netdev; - size_t rxq_size; if (nic_dev->rxqs) return -EINVAL; - rxq_size = num_rxqs * sizeof(*nic_dev->rxqs); - nic_dev->rxqs = devm_kzalloc(&netdev->dev, rxq_size, GFP_KERNEL); + nic_dev->rxqs = devm_kcalloc(&netdev->dev, num_rxqs, + sizeof(*nic_dev->rxqs), GFP_KERNEL); if (!nic_dev->rxqs) return -ENOMEM; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index a78c398bf5b2..01e7d3c0b68e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -8,6 +8,7 @@ #include <linux/interrupt.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> +#include <linux/module.h> #include "hinic_hw_dev.h" #include "hinic_dev.h" diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index c5bdb0d374ef..a984a7a6dd2e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -862,7 +862,6 @@ int hinic_init_txq(struct hinic_txq *txq, struct hinic_sq *sq, struct hinic_dev *nic_dev = netdev_priv(netdev); struct hinic_hwdev *hwdev = nic_dev->hwdev; int err, irqname_len; - size_t sges_size; txq->netdev = netdev; txq->sq = sq; @@ -871,13 +870,13 @@ int hinic_init_txq(struct hinic_txq *txq, struct hinic_sq *sq, txq->max_sges = HINIC_MAX_SQ_BUFDESCS; - sges_size = txq->max_sges * sizeof(*txq->sges); - txq->sges = devm_kzalloc(&netdev->dev, sges_size, GFP_KERNEL); + txq->sges = devm_kcalloc(&netdev->dev, txq->max_sges, + sizeof(*txq->sges), GFP_KERNEL); if (!txq->sges) return -ENOMEM; - sges_size = txq->max_sges * sizeof(*txq->free_sges); - txq->free_sges = devm_kzalloc(&netdev->dev, sges_size, GFP_KERNEL); + txq->free_sges = devm_kcalloc(&netdev->dev, txq->max_sges, + sizeof(*txq->free_sges), GFP_KERNEL); if (!txq->free_sges) { err = -ENOMEM; goto err_alloc_free_sges; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4ba4c4f3be4f..59536bd5cab1 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -308,7 +308,7 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter, if (adapter->fw_done_rc) { dev_err(dev, "Couldn't map LTB, rc = %d\n", adapter->fw_done_rc); - rc = -1; + rc = -EIO; goto out; } rc = 0; @@ -540,13 +540,15 @@ static int init_stats_token(struct ibmvnic_adapter *adapter) { struct device *dev = &adapter->vdev->dev; dma_addr_t stok; + int rc; stok = dma_map_single(dev, &adapter->stats, sizeof(struct ibmvnic_statistics), DMA_FROM_DEVICE); - if (dma_mapping_error(dev, stok)) { - dev_err(dev, "Couldn't map stats buffer\n"); - return -1; + rc = dma_mapping_error(dev, stok); + if (rc) { + dev_err(dev, "Couldn't map stats buffer, rc = %d\n", rc); + return rc; } adapter->stats_token = stok; @@ -655,7 +657,7 @@ static int init_rx_pools(struct net_device *netdev) u64 num_pools; u64 pool_size; /* # of buffers in one pool */ u64 buff_size; - int i, j; + int i, j, rc; pool_size = adapter->req_rx_add_entries_per_subcrq; num_pools = adapter->req_rx_queues; @@ -674,7 +676,7 @@ static int init_rx_pools(struct net_device *netdev) GFP_KERNEL); if (!adapter->rx_pool) { dev_err(dev, "Failed to allocate rx pools\n"); - return -1; + return -ENOMEM; } /* Set num_active_rx_pools early. If we fail below after partial @@ -697,6 +699,7 @@ static int init_rx_pools(struct net_device *netdev) GFP_KERNEL); if (!rx_pool->free_map) { dev_err(dev, "Couldn't alloc free_map %d\n", i); + rc = -ENOMEM; goto out_release; } @@ -705,6 +708,7 @@ static int init_rx_pools(struct net_device *netdev) GFP_KERNEL); if (!rx_pool->rx_buff) { dev_err(dev, "Couldn't alloc rx buffers\n"); + rc = -ENOMEM; goto out_release; } } @@ -718,8 +722,9 @@ update_ltb: dev_dbg(dev, "Updating LTB for rx pool %d [%d, %d]\n", i, rx_pool->size, rx_pool->buff_size); - if (alloc_long_term_buff(adapter, &rx_pool->long_term_buff, - rx_pool->size * rx_pool->buff_size)) + rc = alloc_long_term_buff(adapter, &rx_pool->long_term_buff, + rx_pool->size * rx_pool->buff_size); + if (rc) goto out; for (j = 0; j < rx_pool->size; ++j) { @@ -756,7 +761,7 @@ out: /* We failed to allocate one or more LTBs or map them on the VIOS. * Hold onto the pools and any LTBs that we did allocate/map. */ - return -1; + return rc; } static void release_vpd_data(struct ibmvnic_adapter *adapter) @@ -817,13 +822,13 @@ static int init_one_tx_pool(struct net_device *netdev, sizeof(struct ibmvnic_tx_buff), GFP_KERNEL); if (!tx_pool->tx_buff) - return -1; + return -ENOMEM; tx_pool->free_map = kcalloc(pool_size, sizeof(int), GFP_KERNEL); if (!tx_pool->free_map) { kfree(tx_pool->tx_buff); tx_pool->tx_buff = NULL; - return -1; + return -ENOMEM; } for (i = 0; i < pool_size; i++) @@ -914,7 +919,7 @@ static int init_tx_pools(struct net_device *netdev) adapter->tx_pool = kcalloc(num_pools, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL); if (!adapter->tx_pool) - return -1; + return -ENOMEM; adapter->tso_pool = kcalloc(num_pools, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL); @@ -924,7 +929,7 @@ static int init_tx_pools(struct net_device *netdev) if (!adapter->tso_pool) { kfree(adapter->tx_pool); adapter->tx_pool = NULL; - return -1; + return -ENOMEM; } /* Set num_active_tx_pools early. If we fail below after partial @@ -1113,7 +1118,7 @@ static int ibmvnic_login(struct net_device *netdev) retry = false; if (retry_count > retries) { netdev_warn(netdev, "Login attempts exceeded\n"); - return -1; + return -EACCES; } adapter->init_done_rc = 0; @@ -1154,25 +1159,26 @@ static int ibmvnic_login(struct net_device *netdev) timeout)) { netdev_warn(netdev, "Capabilities query timed out\n"); - return -1; + return -ETIMEDOUT; } rc = init_sub_crqs(adapter); if (rc) { netdev_warn(netdev, "SCRQ initialization failed\n"); - return -1; + return rc; } rc = init_sub_crq_irqs(adapter); if (rc) { netdev_warn(netdev, "SCRQ irq initialization failed\n"); - return -1; + return rc; } } else if (adapter->init_done_rc) { - netdev_warn(netdev, "Adapter login failed\n"); - return -1; + netdev_warn(netdev, "Adapter login failed, init_done_rc = %d\n", + adapter->init_done_rc); + return -EIO; } } while (retry); @@ -1231,7 +1237,7 @@ static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { netdev_err(netdev, "timeout setting link state\n"); - return -1; + return -ETIMEDOUT; } if (adapter->init_done_rc == PARTIALSUCCESS) { @@ -2288,7 +2294,7 @@ static int do_reset(struct ibmvnic_adapter *adapter, /* If someone else changed the adapter state * when we dropped the rtnl, fail the reset */ - rc = -1; + rc = -EAGAIN; goto out; } adapter->state = VNIC_CLOSED; @@ -2330,10 +2336,8 @@ static int do_reset(struct ibmvnic_adapter *adapter, } rc = ibmvnic_reset_init(adapter, true); - if (rc) { - rc = IBMVNIC_INIT_FAILED; + if (rc) goto out; - } /* If the adapter was in PROBE or DOWN state prior to the reset, * exit here. @@ -3763,7 +3767,7 @@ static int init_sub_crqs(struct ibmvnic_adapter *adapter) allqueues = kcalloc(total_queues, sizeof(*allqueues), GFP_KERNEL); if (!allqueues) - return -1; + return -ENOMEM; for (i = 0; i < total_queues; i++) { allqueues[i] = init_sub_crq_queue(adapter); @@ -3832,7 +3836,7 @@ tx_failed: for (i = 0; i < registered_queues; i++) release_sub_crq_queue(adapter, allqueues[i], 1); kfree(allqueues); - return -1; + return -ENOMEM; } static void send_request_cap(struct ibmvnic_adapter *adapter, int retry) @@ -4191,7 +4195,7 @@ static int send_login(struct ibmvnic_adapter *adapter) if (!adapter->tx_scrq || !adapter->rx_scrq) { netdev_err(adapter->netdev, "RX or TX queues are not allocated, device login failed\n"); - return -1; + return -ENOMEM; } release_login_buffer(adapter); @@ -4311,7 +4315,7 @@ buf_map_failed: kfree(login_buffer); adapter->login_buf = NULL; buf_alloc_failed: - return -1; + return -ENOMEM; } static int send_request_map(struct ibmvnic_adapter *adapter, dma_addr_t addr, @@ -5632,7 +5636,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { dev_err(dev, "Initialization sequence timed out\n"); - return -1; + return -ETIMEDOUT; } if (adapter->init_done_rc) { @@ -5643,7 +5647,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset) if (adapter->from_passive_init) { adapter->state = VNIC_OPEN; adapter->from_passive_init = false; - return -1; + return -EINVAL; } if (reset && diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index b8e42f67d897..4a8f36e0ab07 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -18,8 +18,6 @@ #define IBMVNIC_NAME "ibmvnic" #define IBMVNIC_DRIVER_VERSION "1.0.1" #define IBMVNIC_INVALID_MAP -1 -#define IBMVNIC_STATS_TIMEOUT 1 -#define IBMVNIC_INIT_FAILED 2 #define IBMVNIC_OPEN_FAILED 3 /* basic structures plus 100 2k buffers */ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 44e2dc8328a2..635a95927e93 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3614,10 +3614,6 @@ static int e1000e_config_hwtstamp(struct e1000_adapter *adapter, if (!(adapter->flags & FLAG_HAS_HW_TIMESTAMP)) return -EINVAL; - /* flags reserved for future extensions - must be zero */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: tsync_tx_ctl = 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 291e61ac3e44..2c1b1da1220e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -553,6 +553,14 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n, dev_info(&pf->pdev->dev, "vsi %d not found\n", vsi_seid); return; } + if (vsi->type != I40E_VSI_MAIN && + vsi->type != I40E_VSI_FDIR && + vsi->type != I40E_VSI_VMDQ2) { + dev_info(&pf->pdev->dev, + "vsi %d type %d descriptor rings not available\n", + vsi_seid, vsi->type); + return; + } if (type == RING_TYPE_XDP && !i40e_enabled_xdp_vsi(vsi)) { dev_info(&pf->pdev->dev, "XDP not enabled on VSI %d\n", vsi_seid); return; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 09b1d5aed1c9..61e5789d78db 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -1205,10 +1205,6 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, INIT_WORK(&pf->ptp_extts0_work, i40e_ptp_extts0_work); - /* Reserved for future extensions. */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: pf->ptp_tx = false; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 80ae264c99ba..2ea4deb8fc44 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1949,6 +1949,32 @@ static int i40e_vc_send_resp_to_vf(struct i40e_vf *vf, } /** + * i40e_sync_vf_state + * @vf: pointer to the VF info + * @state: VF state + * + * Called from a VF message to synchronize the service with a potential + * VF reset state + **/ +static bool i40e_sync_vf_state(struct i40e_vf *vf, enum i40e_vf_states state) +{ + int i; + + /* When handling some messages, it needs VF state to be set. + * It is possible that this flag is cleared during VF reset, + * so there is a need to wait until the end of the reset to + * handle the request message correctly. + */ + for (i = 0; i < I40E_VF_STATE_WAIT_COUNT; i++) { + if (test_bit(state, &vf->vf_states)) + return true; + usleep_range(10000, 20000); + } + + return test_bit(state, &vf->vf_states); +} + +/** * i40e_vc_get_version_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2008,7 +2034,7 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) size_t len = 0; int ret; - if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_INIT)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -2131,7 +2157,7 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg) bool allmulti = false; bool alluni = false; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err_out; } @@ -2219,7 +2245,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) struct i40e_vsi *vsi; u16 num_qps_all = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2368,7 +2394,7 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2540,7 +2566,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2590,7 +2616,7 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg) u8 cur_pairs = vf->num_queue_pairs; struct i40e_pf *pf = vf->pf; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) return -EINVAL; if (req_pairs > I40E_MAX_VF_QUEUES) { @@ -2635,7 +2661,7 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg) memset(&stats, 0, sizeof(struct i40e_eth_stats)); - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto error_param; } @@ -2752,7 +2778,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) i40e_status ret = 0; int i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) { ret = I40E_ERR_PARAM; goto error_param; @@ -2824,7 +2850,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) i40e_status ret = 0; int i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) { ret = I40E_ERR_PARAM; goto error_param; @@ -2968,7 +2994,7 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) { aq_ret = I40E_ERR_PARAM; goto error_param; @@ -3088,9 +3114,9 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg) struct i40e_vsi *vsi = NULL; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vrk->vsi_id) || - (vrk->key_len != I40E_HKEY_ARRAY_SIZE)) { + vrk->key_len != I40E_HKEY_ARRAY_SIZE) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3119,9 +3145,9 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; u16 i; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vrl->vsi_id) || - (vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)) { + vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3154,7 +3180,7 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int len = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3190,7 +3216,7 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg) struct i40e_hw *hw = &pf->hw; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3215,7 +3241,7 @@ static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; struct i40e_vsi *vsi; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3241,7 +3267,7 @@ static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; struct i40e_vsi *vsi; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3468,7 +3494,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int i, ret; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3599,7 +3625,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; int i, ret; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err_out; } @@ -3708,7 +3734,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) i40e_status aq_ret = 0; u64 speed = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } @@ -3797,11 +3823,6 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) /* set this flag only after making sure all inputs are sane */ vf->adq_enabled = true; - /* num_req_queues is set when user changes number of queues via ethtool - * and this causes issue for default VSI(which depends on this variable) - * when ADq is enabled, hence reset it. - */ - vf->num_req_queues = 0; /* reset the VF in order to allocate resources */ i40e_vc_reset_vf(vf, true); @@ -3824,7 +3845,7 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; - if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { + if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; goto err; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 091e32c1bb46..49575a640a84 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -18,6 +18,8 @@ #define I40E_MAX_VF_PROMISC_FLAGS 3 +#define I40E_VF_STATE_WAIT_COUNT 20 + /* Various queue ctrls */ enum i40e_queue_ctrl { I40E_QUEUE_CTRL_UNKNOWN = 0, diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 1d01d6be8a86..3bb56714beb0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -631,23 +631,44 @@ static int iavf_set_ringparam(struct net_device *netdev, if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; - new_tx_count = clamp_t(u32, ring->tx_pending, - IAVF_MIN_TXD, - IAVF_MAX_TXD); - new_tx_count = ALIGN(new_tx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + if (ring->tx_pending > IAVF_MAX_TXD || + ring->tx_pending < IAVF_MIN_TXD || + ring->rx_pending > IAVF_MAX_RXD || + ring->rx_pending < IAVF_MIN_RXD) { + netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d] (increment %d)\n", + ring->tx_pending, ring->rx_pending, IAVF_MIN_TXD, + IAVF_MAX_RXD, IAVF_REQ_DESCRIPTOR_MULTIPLE); + return -EINVAL; + } - new_rx_count = clamp_t(u32, ring->rx_pending, - IAVF_MIN_RXD, - IAVF_MAX_RXD); - new_rx_count = ALIGN(new_rx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + new_tx_count = ALIGN(ring->tx_pending, IAVF_REQ_DESCRIPTOR_MULTIPLE); + if (new_tx_count != ring->tx_pending) + netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n", + new_tx_count); + + new_rx_count = ALIGN(ring->rx_pending, IAVF_REQ_DESCRIPTOR_MULTIPLE); + if (new_rx_count != ring->rx_pending) + netdev_info(netdev, "Requested Rx descriptor count rounded up to %d\n", + new_rx_count); /* if nothing to do return success */ if ((new_tx_count == adapter->tx_desc_count) && - (new_rx_count == adapter->rx_desc_count)) + (new_rx_count == adapter->rx_desc_count)) { + netdev_dbg(netdev, "Nothing to change, descriptor count is same as requested\n"); return 0; + } - adapter->tx_desc_count = new_tx_count; - adapter->rx_desc_count = new_rx_count; + if (new_tx_count != adapter->tx_desc_count) { + netdev_dbg(netdev, "Changing Tx descriptor count from %d to %d\n", + adapter->tx_desc_count, new_tx_count); + adapter->tx_desc_count = new_tx_count; + } + + if (new_rx_count != adapter->rx_desc_count) { + netdev_dbg(netdev, "Changing Rx descriptor count from %d to %d\n", + adapter->rx_desc_count, new_rx_count); + adapter->rx_desc_count = new_rx_count; + } if (netif_running(netdev)) { adapter->flags |= IAVF_FLAG_RESET_NEEDED; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 285c0e28ec98..aa5b8042b13d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2046,6 +2046,7 @@ static void iavf_watchdog_task(struct work_struct *work) } adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; + mutex_unlock(&adapter->crit_lock); queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(10)); @@ -2076,16 +2077,14 @@ static void iavf_watchdog_task(struct work_struct *work) iavf_detect_recover_hung(&adapter->vsi); break; case __IAVF_REMOVE: - mutex_unlock(&adapter->crit_lock); - return; default: + mutex_unlock(&adapter->crit_lock); return; } /* check for hw reset */ reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) { - iavf_change_state(adapter, __IAVF_RESETTING); adapter->flags |= IAVF_FLAG_RESET_PENDING; adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; @@ -2248,6 +2247,7 @@ static void iavf_reset_task(struct work_struct *work) } pci_set_master(adapter->pdev); + pci_restore_msi_state(adapter->pdev); if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index b67ad51cbcc9..5505bd658a9b 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -503,6 +503,7 @@ struct ice_pf { struct pci_dev *pdev; struct devlink_region *nvm_region; + struct devlink_region *sram_region; struct devlink_region *devcaps_region; /* devlink port data */ @@ -552,6 +553,7 @@ struct ice_pf { spinlock_t aq_wait_lock; struct hlist_head aq_wait_list; wait_queue_head_t aq_wait_queue; + bool fw_emp_reset_disabled; wait_queue_head_t reset_wait_queue; @@ -848,7 +850,6 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup); int ice_plug_aux_dev(struct ice_pf *pf); void ice_unplug_aux_dev(struct ice_pf *pf); int ice_init_rdma(struct ice_pf *pf); -const char *ice_stat_str(enum ice_status stat_err); const char *ice_aq_str(enum ice_aq_err aq_err); bool ice_is_wol_supported(struct ice_hw *hw); int diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 4eef3488d86f..ad1dcfa5ff65 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -117,6 +117,8 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_NET_VER 0x004C #define ICE_AQC_CAPS_PENDING_NET_VER 0x004D #define ICE_AQC_CAPS_RDMA 0x0051 +#define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE 0x0076 +#define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT 0x0077 #define ICE_AQC_CAPS_NVM_MGMT 0x0080 u8 major_ver; @@ -1408,6 +1410,11 @@ struct ice_aqc_nvm { #define ICE_AQC_NVM_REVERT_LAST_ACTIV BIT(6) /* Write Activate only */ #define ICE_AQC_NVM_ACTIV_SEL_MASK ICE_M(0x7, 3) #define ICE_AQC_NVM_FLASH_ONLY BIT(7) +#define ICE_AQC_NVM_RESET_LVL_M ICE_M(0x3, 0) /* Write reply only */ +#define ICE_AQC_NVM_POR_FLAG 0 +#define ICE_AQC_NVM_PERST_FLAG 1 +#define ICE_AQC_NVM_EMPR_FLAG 2 +#define ICE_AQC_NVM_EMPR_ENA BIT(0) /* Write Activate reply only */ __le16 module_typeid; __le16 length; #define ICE_AQC_NVM_ERASE_LEN 0xFFFF diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 1efc635cc0f5..44bdd0ed1629 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -759,7 +759,7 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, struct ice_channel *ch = ring->ch; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - enum ice_status status; + int status; u16 pf_q; u8 tc; @@ -804,9 +804,9 @@ ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_tx_ring *ring, ring->q_handle, 1, qg_buf, buf_len, NULL); if (status) { - dev_err(ice_pf_to_dev(pf), "Failed to set LAN Tx queue context, error: %s\n", - ice_stat_str(status)); - return -ENODEV; + dev_err(ice_pf_to_dev(pf), "Failed to set LAN Tx queue context, error: %d\n", + status); + return status; } /* Add Tx Queue TEID into the VSI Tx ring from the @@ -929,7 +929,7 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, struct ice_pf *pf = vsi->back; struct ice_q_vector *q_vector; struct ice_hw *hw = &pf->hw; - enum ice_status status; + int status; u32 val; /* clear cause_ena bit for disabled queues */ @@ -953,18 +953,18 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, rel_vmvf_num, NULL); /* if the disable queue command was exercised during an - * active reset flow, ICE_ERR_RESET_ONGOING is returned. + * active reset flow, -EBUSY is returned. * This is not an error as the reset operation disables * queues at the hardware level anyway. */ - if (status == ICE_ERR_RESET_ONGOING) { + if (status == -EBUSY) { dev_dbg(ice_pf_to_dev(vsi->back), "Reset in progress. LAN Tx queues already disabled\n"); - } else if (status == ICE_ERR_DOES_NOT_EXIST) { + } else if (status == -ENOENT) { dev_dbg(ice_pf_to_dev(vsi->back), "LAN Tx queues do not exist, nothing to disable\n"); } else if (status) { - dev_dbg(ice_pf_to_dev(vsi->back), "Failed to disable LAN Tx queues, error: %s\n", - ice_stat_str(status)); - return -ENODEV; + dev_dbg(ice_pf_to_dev(vsi->back), "Failed to disable LAN Tx queues, error: %d\n", + status); + return status; } return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index b3066d0fea8b..157add1268d9 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2,7 +2,6 @@ /* Copyright (c) 2018, Intel Corporation. */ #include "ice_common.h" -#include "ice_lib.h" #include "ice_sched.h" #include "ice_adminq_cmd.h" #include "ice_flow.h" @@ -16,10 +15,10 @@ * This function sets the MAC type of the adapter based on the * vendor ID and device ID stored in the HW structure. */ -static enum ice_status ice_set_mac_type(struct ice_hw *hw) +static int ice_set_mac_type(struct ice_hw *hw) { if (hw->vendor_id != PCI_VENDOR_ID_INTEL) - return ICE_ERR_DEVICE_NOT_SUPPORTED; + return -ENODEV; switch (hw->device_id) { case ICE_DEV_ID_E810C_BACKPLANE: @@ -99,7 +98,7 @@ bool ice_is_e810t(struct ice_hw *hw) * Clears any existing PF configuration (VSIs, VSI lists, switch rules, port * configuration, flow director filters, etc.). */ -enum ice_status ice_clear_pf_cfg(struct ice_hw *hw) +int ice_clear_pf_cfg(struct ice_hw *hw) { struct ice_aq_desc desc; @@ -123,21 +122,21 @@ enum ice_status ice_clear_pf_cfg(struct ice_hw *hw) * ice_discover_dev_caps is expected to be called before this function is * called. */ -static enum ice_status +static int ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size, struct ice_sq_cd *cd) { struct ice_aqc_manage_mac_read_resp *resp; struct ice_aqc_manage_mac_read *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; u16 flags; u8 i; cmd = &desc.params.mac_read; if (buf_size < sizeof(*resp)) - return ICE_ERR_BUF_TOO_SHORT; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_manage_mac_read); @@ -150,7 +149,7 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size, if (!(flags & ICE_AQC_MAN_MAC_LAN_ADDR_VALID)) { ice_debug(hw, ICE_DBG_LAN, "got invalid MAC address\n"); - return ICE_ERR_CFG; + return -EIO; } /* A single port can report up to two (LAN and WoL) addresses */ @@ -176,7 +175,7 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size, * * Returns the various PHY capabilities supported on the Port (0x0600) */ -enum ice_status +int ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *pcaps, struct ice_sq_cd *cd) @@ -184,18 +183,18 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps *cmd; u16 pcaps_size = sizeof(*pcaps); struct ice_aq_desc desc; - enum ice_status status; struct ice_hw *hw; + int status; cmd = &desc.params.get_phy; if (!pcaps || (report_mode & ~ICE_AQC_REPORT_MODE_M) || !pi) - return ICE_ERR_PARAM; + return -EINVAL; hw = pi->hw; if (report_mode == ICE_AQC_REPORT_DFLT_CFG && !ice_fw_supports_report_dflt_cfg(hw)) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_phy_caps); @@ -252,7 +251,7 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, * returns error (ENOENT), then no cage present. If no cage present, then * connection type is backplane or BASE-T. */ -static enum ice_status +static int ice_aq_get_link_topo_handle(struct ice_port_info *pi, u8 node_type, struct ice_sq_cd *cd) { @@ -418,7 +417,7 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi) * * Get Link Status (0x607). Returns the link status of the adapter. */ -enum ice_status +int ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, struct ice_link_status *link, struct ice_sq_cd *cd) { @@ -429,12 +428,12 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, struct ice_fc_info *hw_fc_info; bool tx_pause, rx_pause; struct ice_aq_desc desc; - enum ice_status status; struct ice_hw *hw; u16 cmd_flags; + int status; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; hw = pi->hw; li_old = &pi->phy.link_info_old; hw_media_type = &pi->phy.media_type; @@ -556,7 +555,7 @@ ice_fill_tx_timer_and_fc_thresh(struct ice_hw *hw, * * Set MAC configuration (0x0603) */ -enum ice_status +int ice_aq_set_mac_cfg(struct ice_hw *hw, u16 max_frame_size, struct ice_sq_cd *cd) { struct ice_aqc_set_mac_cfg *cmd; @@ -565,7 +564,7 @@ ice_aq_set_mac_cfg(struct ice_hw *hw, u16 max_frame_size, struct ice_sq_cd *cd) cmd = &desc.params.set_mac_cfg; if (max_frame_size == 0) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_mac_cfg); @@ -580,17 +579,17 @@ ice_aq_set_mac_cfg(struct ice_hw *hw, u16 max_frame_size, struct ice_sq_cd *cd) * ice_init_fltr_mgmt_struct - initializes filter management list and locks * @hw: pointer to the HW struct */ -static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw) +static int ice_init_fltr_mgmt_struct(struct ice_hw *hw) { struct ice_switch_info *sw; - enum ice_status status; + int status; hw->switch_info = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*hw->switch_info), GFP_KERNEL); sw = hw->switch_info; if (!sw) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; INIT_LIST_HEAD(&sw->vsi_list_map_head); sw->prof_res_bm_init = 0; @@ -666,17 +665,17 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) * ice_get_fw_log_cfg - get FW logging configuration * @hw: pointer to the HW struct */ -static enum ice_status ice_get_fw_log_cfg(struct ice_hw *hw) +static int ice_get_fw_log_cfg(struct ice_hw *hw) { struct ice_aq_desc desc; - enum ice_status status; __le16 *config; + int status; u16 size; size = sizeof(*config) * ICE_AQC_FW_LOG_ID_MAX; config = devm_kzalloc(ice_hw_to_dev(hw), size, GFP_KERNEL); if (!config) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging_info); @@ -738,15 +737,15 @@ static enum ice_status ice_get_fw_log_cfg(struct ice_hw *hw) * messages from FW to SW. Interrupts are typically disabled during the device's * initialization phase. */ -static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable) +static int ice_cfg_fw_log(struct ice_hw *hw, bool enable) { struct ice_aqc_fw_logging *cmd; - enum ice_status status = 0; u16 i, chgs = 0, len = 0; struct ice_aq_desc desc; __le16 *data = NULL; u8 actv_evnts = 0; void *buf = NULL; + int status = 0; if (!hw->fw_log.cq_en && !hw->fw_log.uart_en) return 0; @@ -790,7 +789,7 @@ static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable) sizeof(*data), GFP_KERNEL); if (!data) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } val = i << ICE_AQC_FW_LOG_ID_S; @@ -904,12 +903,12 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw) * ice_init_hw - main hardware initialization routine * @hw: pointer to the hardware structure */ -enum ice_status ice_init_hw(struct ice_hw *hw) +int ice_init_hw(struct ice_hw *hw) { struct ice_aqc_get_phy_caps_data *pcaps; - enum ice_status status; u16 mac_buf_len; void *mac_buf; + int status; /* Set MAC type based on DeviceID */ status = ice_set_mac_type(hw); @@ -956,7 +955,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw) hw->port_info = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*hw->port_info), GFP_KERNEL); if (!hw->port_info) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_unroll_cqinit; } @@ -985,7 +984,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw) pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL); if (!pcaps) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_unroll_sched; } @@ -1006,7 +1005,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw) /* need a valid SW entry point to build a Tx tree */ if (!hw->sw_entry_point_layer) { ice_debug(hw, ICE_DBG_SCHED, "invalid sw entry point\n"); - status = ICE_ERR_CFG; + status = -EIO; goto err_unroll_sched; } INIT_LIST_HEAD(&hw->agg_list); @@ -1026,7 +1025,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw) mac_buf_len = 2 * sizeof(struct ice_aqc_manage_mac_read_resp); if (!mac_buf) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_unroll_fltr_mgmt_struct; } @@ -1096,7 +1095,7 @@ void ice_deinit_hw(struct ice_hw *hw) * ice_check_reset - Check to see if a global reset is complete * @hw: pointer to the hardware structure */ -enum ice_status ice_check_reset(struct ice_hw *hw) +int ice_check_reset(struct ice_hw *hw) { u32 cnt, reg = 0, grst_timeout, uld_mask; @@ -1116,7 +1115,7 @@ enum ice_status ice_check_reset(struct ice_hw *hw) if (cnt == grst_timeout) { ice_debug(hw, ICE_DBG_INIT, "Global reset polling failed to complete.\n"); - return ICE_ERR_RESET_FAILED; + return -EIO; } #define ICE_RESET_DONE_MASK (GLNVM_ULD_PCIER_DONE_M |\ @@ -1143,7 +1142,7 @@ enum ice_status ice_check_reset(struct ice_hw *hw) if (cnt == ICE_PF_RESET_WAIT_COUNT) { ice_debug(hw, ICE_DBG_INIT, "Wait for Reset Done timed out. GLNVM_ULD = 0x%x\n", reg); - return ICE_ERR_RESET_FAILED; + return -EIO; } return 0; @@ -1156,7 +1155,7 @@ enum ice_status ice_check_reset(struct ice_hw *hw) * If a global reset has been triggered, this function checks * for its completion and then issues the PF reset */ -static enum ice_status ice_pf_reset(struct ice_hw *hw) +static int ice_pf_reset(struct ice_hw *hw) { u32 cnt, reg; @@ -1169,7 +1168,7 @@ static enum ice_status ice_pf_reset(struct ice_hw *hw) (rd32(hw, GLNVM_ULD) & ICE_RESET_DONE_MASK) ^ ICE_RESET_DONE_MASK) { /* poll on global reset currently in progress until done */ if (ice_check_reset(hw)) - return ICE_ERR_RESET_FAILED; + return -EIO; return 0; } @@ -1194,7 +1193,7 @@ static enum ice_status ice_pf_reset(struct ice_hw *hw) if (cnt == ICE_PF_RESET_WAIT_COUNT) { ice_debug(hw, ICE_DBG_INIT, "PF reset polling failed to complete.\n"); - return ICE_ERR_RESET_FAILED; + return -EIO; } return 0; @@ -1212,7 +1211,7 @@ static enum ice_status ice_pf_reset(struct ice_hw *hw) * This has to be cleared using ice_clear_pxe_mode again, once the AQ * interface has been restored in the rebuild flow. */ -enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req) +int ice_reset(struct ice_hw *hw, enum ice_reset_req req) { u32 val = 0; @@ -1228,7 +1227,7 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req) val = GLGEN_RTRIG_GLOBR_M; break; default: - return ICE_ERR_PARAM; + return -EINVAL; } val |= rd32(hw, GLGEN_RTRIG); @@ -1247,16 +1246,16 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req) * * Copies rxq context from dense structure to HW register space */ -static enum ice_status +static int ice_copy_rxq_ctx_to_hw(struct ice_hw *hw, u8 *ice_rxq_ctx, u32 rxq_index) { u8 i; if (!ice_rxq_ctx) - return ICE_ERR_BAD_PTR; + return -EINVAL; if (rxq_index > QRX_CTRL_MAX_INDEX) - return ICE_ERR_PARAM; + return -EINVAL; /* Copy each dword separately to HW */ for (i = 0; i < ICE_RXQ_CTX_SIZE_DWORDS; i++) { @@ -1306,14 +1305,14 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { * it to HW register space and enables the hardware to prefetch descriptors * instead of only fetching them on demand */ -enum ice_status +int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index) { u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 }; if (!rlan_ctx) - return ICE_ERR_BAD_PTR; + return -EINVAL; rlan_ctx->prefena = 1; @@ -1369,9 +1368,8 @@ static int ice_sbq_send_cmd(struct ice_hw *hw, struct ice_sbq_cmd_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd) { - return ice_status_to_errno(ice_sq_send_cmd(hw, ice_get_sbq(hw), - (struct ice_aq_desc *)desc, - buf, buf_size, cd)); + return ice_sq_send_cmd(hw, ice_get_sbq(hw), + (struct ice_aq_desc *)desc, buf, buf_size, cd); } /** @@ -1453,17 +1451,17 @@ static bool ice_should_retry_sq_send_cmd(u16 opcode) * Retry sending the FW Admin Queue command, multiple times, to the FW Admin * Queue if the EBUSY AQ error is returned. */ -static enum ice_status +static int ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd) { struct ice_aq_desc desc_cpy; - enum ice_status status; bool is_cmd_for_retry; u8 *buf_cpy = NULL; u8 idx = 0; u16 opcode; + int status; opcode = le16_to_cpu(desc->opcode); is_cmd_for_retry = ice_should_retry_sq_send_cmd(opcode); @@ -1473,7 +1471,7 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, if (buf) { buf_cpy = kzalloc(buf_size, GFP_KERNEL); if (!buf_cpy) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } memcpy(&desc_cpy, desc, sizeof(desc_cpy)); @@ -1510,13 +1508,13 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, * * Helper function to send FW Admin Queue commands to the FW Admin Queue. */ -enum ice_status +int ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd) { struct ice_aqc_req_res *cmd = &desc->params.res_owner; bool lock_acquired = false; - enum ice_status status; + int status; /* When a package download is in process (i.e. when the firmware's * Global Configuration Lock resource is held), only the Download @@ -1555,11 +1553,11 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, * * Get the firmware version (0x0001) from the admin queue commands */ -enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd) +int ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd) { struct ice_aqc_get_ver *resp; struct ice_aq_desc desc; - enum ice_status status; + int status; resp = &desc.params.get_ver; @@ -1590,7 +1588,7 @@ enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd) * * Send the driver version (0x0002) to the firmware */ -enum ice_status +int ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv, struct ice_sq_cd *cd) { @@ -1601,7 +1599,7 @@ ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv, cmd = &desc.params.driver_ver; if (!dv) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_ver); @@ -1627,7 +1625,7 @@ ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv, * Tell the Firmware that we're shutting down the AdminQ and whether * or not the driver is unloading as well (0x0003). */ -enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading) +int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading) { struct ice_aqc_q_shutdown *cmd; struct ice_aq_desc desc; @@ -1654,12 +1652,12 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading) * Requests common resource using the admin queue commands (0x0008). * When attempting to acquire the Global Config Lock, the driver can * learn of three states: - * 1) ICE_SUCCESS - acquired lock, and can perform download package - * 2) ICE_ERR_AQ_ERROR - did not get lock, driver should fail to load - * 3) ICE_ERR_AQ_NO_WORK - did not get lock, but another driver has - * successfully downloaded the package; the driver does - * not have to download the package and can continue - * loading + * 1) 0 - acquired lock, and can perform download package + * 2) -EIO - did not get lock, driver should fail to load + * 3) -EALREADY - did not get lock, but another driver has + * successfully downloaded the package; the driver does + * not have to download the package and can continue + * loading * * Note that if the caller is in an acquire lock, perform action, release lock * phase of operation, it is possible that the FW may detect a timeout and issue @@ -1668,14 +1666,14 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading) * will likely get an error propagated back to it indicating the Download * Package, Update Package or the Release Resource AQ commands timed out. */ -static enum ice_status +static int ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res, enum ice_aq_res_access_type access, u8 sdp_number, u32 *timeout, struct ice_sq_cd *cd) { struct ice_aqc_req_res *cmd_resp; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd_resp = &desc.params.res_owner; @@ -1707,15 +1705,15 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res, } else if (le16_to_cpu(cmd_resp->status) == ICE_AQ_RES_GLBL_IN_PROG) { *timeout = le32_to_cpu(cmd_resp->timeout); - return ICE_ERR_AQ_ERROR; + return -EIO; } else if (le16_to_cpu(cmd_resp->status) == ICE_AQ_RES_GLBL_DONE) { - return ICE_ERR_AQ_NO_WORK; + return -EALREADY; } /* invalid FW response, force a timeout immediately */ *timeout = 0; - return ICE_ERR_AQ_ERROR; + return -EIO; } /* If the resource is held by some other driver, the command completes @@ -1737,7 +1735,7 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res, * * release common resource using the admin queue commands (0x0009) */ -static enum ice_status +static int ice_aq_release_res(struct ice_hw *hw, enum ice_aq_res_ids res, u8 sdp_number, struct ice_sq_cd *cd) { @@ -1763,23 +1761,23 @@ ice_aq_release_res(struct ice_hw *hw, enum ice_aq_res_ids res, u8 sdp_number, * * This function will attempt to acquire the ownership of a resource. */ -enum ice_status +int ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, enum ice_aq_res_access_type access, u32 timeout) { #define ICE_RES_POLLING_DELAY_MS 10 u32 delay = ICE_RES_POLLING_DELAY_MS; u32 time_left = timeout; - enum ice_status status; + int status; status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL); - /* A return code of ICE_ERR_AQ_NO_WORK means that another driver has + /* A return code of -EALREADY means that another driver has * previously acquired the resource and performed any necessary updates; * in this case the caller does not obtain the resource and has no * further work to do. */ - if (status == ICE_ERR_AQ_NO_WORK) + if (status == -EALREADY) goto ice_acquire_res_exit; if (status) @@ -1792,7 +1790,7 @@ ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, timeout = (timeout > delay) ? timeout - delay : 0; status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL); - if (status == ICE_ERR_AQ_NO_WORK) + if (status == -EALREADY) /* lock free, but no work to do */ break; @@ -1800,15 +1798,15 @@ ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, /* lock acquired */ break; } - if (status && status != ICE_ERR_AQ_NO_WORK) + if (status && status != -EALREADY) ice_debug(hw, ICE_DBG_RES, "resource acquire timed out.\n"); ice_acquire_res_exit: - if (status == ICE_ERR_AQ_NO_WORK) { + if (status == -EALREADY) { if (access == ICE_RES_WRITE) ice_debug(hw, ICE_DBG_RES, "resource indicates no work to do.\n"); else - ice_debug(hw, ICE_DBG_RES, "Warning: ICE_ERR_AQ_NO_WORK not expected\n"); + ice_debug(hw, ICE_DBG_RES, "Warning: -EALREADY not expected\n"); } return status; } @@ -1822,16 +1820,15 @@ ice_acquire_res_exit: */ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) { - enum ice_status status; u32 total_delay = 0; + int status; status = ice_aq_release_res(hw, res, 0, NULL); /* there are some rare cases when trying to release the resource * results in an admin queue timeout, so handle them correctly */ - while ((status == ICE_ERR_AQ_TIMEOUT) && - (total_delay < hw->adminq.sq_cmd_timeout)) { + while ((status == -EIO) && (total_delay < hw->adminq.sq_cmd_timeout)) { mdelay(1); status = ice_aq_release_res(hw, res, 0, NULL); total_delay++; @@ -1849,7 +1846,7 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) * * Helper function to allocate/free resources using the admin queue commands */ -enum ice_status +int ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, enum ice_adminq_opc opc, struct ice_sq_cd *cd) @@ -1860,10 +1857,10 @@ ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, cmd = &desc.params.sw_res_ctrl; if (!buf) - return ICE_ERR_PARAM; + return -EINVAL; if (buf_size < flex_array_size(buf, elem, num_entries)) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, opc); @@ -1882,17 +1879,17 @@ ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, * @btm: allocate from bottom * @res: pointer to array that will receive the resources */ -enum ice_status +int ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res) { struct ice_aqc_alloc_free_res_elem *buf; - enum ice_status status; u16 buf_len; + int status; buf_len = struct_size(buf, elem, num); buf = kzalloc(buf_len, GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Prepare buffer to allocate resource. */ buf->num_elems = cpu_to_le16(num); @@ -1920,16 +1917,16 @@ ice_alloc_res_exit: * @num: number of resources * @res: pointer to array that contains the resources to free */ -enum ice_status ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res) +int ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res) { struct ice_aqc_alloc_free_res_elem *buf; - enum ice_status status; u16 buf_len; + int status; buf_len = struct_size(buf, elem, num); buf = kzalloc(buf_len, GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Prepare buffer to free resource. */ buf->num_elems = cpu_to_le16(num); @@ -2071,6 +2068,18 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n", prefix, caps->max_mtu); break; + case ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE: + caps->pcie_reset_avoidance = (number > 0); + ice_debug(hw, ICE_DBG_INIT, + "%s: pcie_reset_avoidance = %d\n", prefix, + caps->pcie_reset_avoidance); + break; + case ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT: + caps->reset_restrict_support = (number == 1); + ice_debug(hw, ICE_DBG_INIT, + "%s: reset_restrict_support = %d\n", prefix, + caps->reset_restrict_support); + break; default: /* Not one of the recognized common capabilities */ found = false; @@ -2486,19 +2495,19 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, * buffer size be set to ICE_AQ_MAX_BUF_LEN (the largest possible buffer that * firmware could return) to avoid this. */ -enum ice_status +int ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, enum ice_adminq_opc opc, struct ice_sq_cd *cd) { struct ice_aqc_list_caps *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd = &desc.params.get_cap; if (opc != ice_aqc_opc_list_func_caps && opc != ice_aqc_opc_list_dev_caps) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, opc); status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); @@ -2517,16 +2526,16 @@ ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, * Read the device capabilities and extract them into the dev_caps structure * for later use. */ -enum ice_status +int ice_discover_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_caps) { - enum ice_status status; u32 cap_count = 0; void *cbuf; + int status; cbuf = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); if (!cbuf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Although the driver doesn't know the number of capabilities the * device will return, we can simply send a 4KB buffer, the maximum @@ -2551,16 +2560,16 @@ ice_discover_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_caps) * Read the function capabilities and extract them into the func_caps structure * for later use. */ -static enum ice_status +static int ice_discover_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_caps) { - enum ice_status status; u32 cap_count = 0; void *cbuf; + int status; cbuf = kzalloc(ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); if (!cbuf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Although the driver doesn't know the number of capabilities the * device will return, we can simply send a 4KB buffer, the maximum @@ -2650,9 +2659,9 @@ void ice_set_safe_mode_caps(struct ice_hw *hw) * ice_get_caps - get info about the HW * @hw: pointer to the hardware structure */ -enum ice_status ice_get_caps(struct ice_hw *hw) +int ice_get_caps(struct ice_hw *hw) { - enum ice_status status; + int status; status = ice_discover_dev_caps(hw, &hw->dev_caps); if (status) @@ -2670,7 +2679,7 @@ enum ice_status ice_get_caps(struct ice_hw *hw) * * This function is used to write MAC address to the NVM (0x0108). */ -enum ice_status +int ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags, struct ice_sq_cd *cd) { @@ -2692,7 +2701,7 @@ ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags, * * Tell the firmware that the driver is taking over from PXE (0x0110). */ -static enum ice_status ice_aq_clear_pxe_mode(struct ice_hw *hw) +static int ice_aq_clear_pxe_mode(struct ice_hw *hw) { struct ice_aq_desc desc; @@ -2903,15 +2912,15 @@ ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high, * mode as the PF may not have the privilege to set some of the PHY Config * parameters. This status will be indicated by the command response (0x0601). */ -enum ice_status +int ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd) { struct ice_aq_desc desc; - enum ice_status status; + int status; if (!cfg) - return ICE_ERR_PARAM; + return -EINVAL; /* Ensure that only valid bits of cfg->caps can be turned on. */ if (cfg->caps & ~ICE_AQ_PHY_ENA_VALID_MASK) { @@ -2952,13 +2961,13 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi, * ice_update_link_info - update status of the HW network link * @pi: port info structure of the interested logical port */ -enum ice_status ice_update_link_info(struct ice_port_info *pi) +int ice_update_link_info(struct ice_port_info *pi) { struct ice_link_status *li; - enum ice_status status; + int status; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; li = &pi->phy.link_info; @@ -2974,7 +2983,7 @@ enum ice_status ice_update_link_info(struct ice_port_info *pi) pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL); if (!pcaps) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, pcaps, NULL); @@ -3070,7 +3079,7 @@ enum ice_fec_mode ice_caps_to_fec_mode(u8 caps, u8 fec_options) * @cfg: PHY configuration data to set FC mode * @req_mode: FC mode to configure */ -enum ice_status +int ice_cfg_phy_fc(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fc_mode req_mode) { @@ -3078,7 +3087,7 @@ ice_cfg_phy_fc(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, u8 pause_mask = 0x0; if (!pi || !cfg) - return ICE_ERR_BAD_PTR; + return -EINVAL; switch (req_mode) { case ICE_FC_FULL: @@ -3117,23 +3126,23 @@ ice_cfg_phy_fc(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, * * Set the requested flow control mode. */ -enum ice_status +int ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) { struct ice_aqc_set_phy_cfg_data cfg = { 0 }; struct ice_aqc_get_phy_caps_data *pcaps; - enum ice_status status; struct ice_hw *hw; + int status; if (!pi || !aq_failures) - return ICE_ERR_BAD_PTR; + return -EINVAL; *aq_failures = 0; hw = pi->hw; pcaps = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*pcaps), GFP_KERNEL); if (!pcaps) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Get the current PHY config */ status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, @@ -3258,22 +3267,22 @@ ice_copy_phy_caps_to_cfg(struct ice_port_info *pi, * @cfg: PHY configuration data to set FEC mode * @fec: FEC mode to configure */ -enum ice_status +int ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec) { struct ice_aqc_get_phy_caps_data *pcaps; - enum ice_status status; struct ice_hw *hw; + int status; if (!pi || !cfg) - return ICE_ERR_BAD_PTR; + return -EINVAL; hw = pi->hw; pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; status = ice_aq_get_phy_caps(pi, false, (ice_fw_supports_report_dflt_cfg(hw) ? @@ -3313,7 +3322,7 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, cfg->link_fec_opt |= pcaps->link_fec_options; break; default: - status = ICE_ERR_PARAM; + status = -EINVAL; break; } @@ -3344,13 +3353,13 @@ out: * The variable link_up is invalid if status is non zero. As a * result of this call, link status reporting becomes enabled */ -enum ice_status ice_get_link_status(struct ice_port_info *pi, bool *link_up) +int ice_get_link_status(struct ice_port_info *pi, bool *link_up) { struct ice_phy_info *phy_info; - enum ice_status status = 0; + int status = 0; if (!pi || !link_up) - return ICE_ERR_PARAM; + return -EINVAL; phy_info = &pi->phy; @@ -3375,7 +3384,7 @@ enum ice_status ice_get_link_status(struct ice_port_info *pi, bool *link_up) * * Sets up the link and restarts the Auto-Negotiation over the link. */ -enum ice_status +int ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link, struct ice_sq_cd *cd) { @@ -3405,7 +3414,7 @@ ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link, * * Set event mask (0x0613) */ -enum ice_status +int ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask, struct ice_sq_cd *cd) { @@ -3430,7 +3439,7 @@ ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask, * * Enable/disable loopback on a given port */ -enum ice_status +int ice_aq_set_mac_loopback(struct ice_hw *hw, bool ena_lpbk, struct ice_sq_cd *cd) { struct ice_aqc_set_mac_lb *cmd; @@ -3453,7 +3462,7 @@ ice_aq_set_mac_loopback(struct ice_hw *hw, bool ena_lpbk, struct ice_sq_cd *cd) * * Set LED value for the given port (0x06e9) */ -enum ice_status +int ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode, struct ice_sq_cd *cd) { @@ -3488,17 +3497,17 @@ ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode, * * Read/Write SFF EEPROM (0x06EE) */ -enum ice_status +int ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length, bool write, struct ice_sq_cd *cd) { struct ice_aqc_sff_eeprom *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; if (!data || (mem_addr & 0xff00)) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_sff_eeprom); cmd = &desc.params.read_write_sff_param; @@ -3527,23 +3536,23 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, * * Internal function to get (0x0B05) or set (0x0B03) RSS look up table */ -static enum ice_status +static int __ice_aq_get_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *params, bool set) { u16 flags = 0, vsi_id, lut_type, lut_size, glob_lut_idx, vsi_handle; struct ice_aqc_get_set_rss_lut *cmd_resp; struct ice_aq_desc desc; - enum ice_status status; + int status; u8 *lut; if (!params) - return ICE_ERR_PARAM; + return -EINVAL; vsi_handle = params->vsi_handle; lut = params->lut; if (!ice_is_vsi_valid(hw, vsi_handle) || !lut) - return ICE_ERR_PARAM; + return -EINVAL; lut_size = params->lut_size; lut_type = params->lut_type; @@ -3572,7 +3581,7 @@ __ice_aq_get_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_M); break; default: - status = ICE_ERR_PARAM; + status = -EINVAL; goto ice_aq_get_set_rss_lut_exit; } @@ -3607,7 +3616,7 @@ __ice_aq_get_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params } fallthrough; default: - status = ICE_ERR_PARAM; + status = -EINVAL; goto ice_aq_get_set_rss_lut_exit; } @@ -3626,7 +3635,7 @@ ice_aq_get_set_rss_lut_exit: * * get the RSS lookup table, PF or VSI type */ -enum ice_status +int ice_aq_get_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *get_params) { return __ice_aq_get_set_rss_lut(hw, get_params, false); @@ -3639,7 +3648,7 @@ ice_aq_get_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *get_ * * set the RSS lookup table, PF or VSI type */ -enum ice_status +int ice_aq_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *set_params) { return __ice_aq_get_set_rss_lut(hw, set_params, true); @@ -3654,10 +3663,9 @@ ice_aq_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *set_ * * get (0x0B04) or set (0x0B02) the RSS key per VSI */ -static enum -ice_status __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, - struct ice_aqc_get_set_rss_keys *key, - bool set) +static int +__ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, + struct ice_aqc_get_set_rss_keys *key, bool set) { struct ice_aqc_get_set_rss_key *cmd_resp; u16 key_size = sizeof(*key); @@ -3688,12 +3696,12 @@ ice_status __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id, * * get the RSS key per VSI */ -enum ice_status +int ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *key) { if (!ice_is_vsi_valid(hw, vsi_handle) || !key) - return ICE_ERR_PARAM; + return -EINVAL; return __ice_aq_get_set_rss_key(hw, ice_get_hw_vsi_num(hw, vsi_handle), key, false); @@ -3707,12 +3715,12 @@ ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle, * * set the RSS key per VSI */ -enum ice_status +int ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys) { if (!ice_is_vsi_valid(hw, vsi_handle) || !keys) - return ICE_ERR_PARAM; + return -EINVAL; return __ice_aq_get_set_rss_key(hw, ice_get_hw_vsi_num(hw, vsi_handle), keys, true); @@ -3739,7 +3747,7 @@ ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, * Association of Tx queue to Doorbell queue is not part of Add LAN Tx queue * flow. */ -static enum ice_status +static int ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *qg_list, u16 buf_size, struct ice_sq_cd *cd) @@ -3754,10 +3762,10 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_txqs); if (!qg_list) - return ICE_ERR_PARAM; + return -EINVAL; if (num_qgrps > ICE_LAN_TXQ_MAX_QGRPS) - return ICE_ERR_PARAM; + return -EINVAL; for (i = 0, list = qg_list; i < num_qgrps; i++) { sum_size += struct_size(list, txqs, list->num_txqs); @@ -3766,7 +3774,7 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, } if (buf_size != sum_size) - return ICE_ERR_PARAM; + return -EINVAL; desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); @@ -3787,7 +3795,7 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps, * * Disable LAN Tx queue (0x0C31) */ -static enum ice_status +static int ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, struct ice_aqc_dis_txq_item *qg_list, u16 buf_size, enum ice_disq_rst_src rst_src, u16 vmvf_num, @@ -3796,18 +3804,18 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, struct ice_aqc_dis_txq_item *item; struct ice_aqc_dis_txqs *cmd; struct ice_aq_desc desc; - enum ice_status status; u16 i, sz = 0; + int status; cmd = &desc.params.dis_txqs; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dis_txqs); /* qg_list can be NULL only in VM/VF reset flow */ if (!qg_list && !rst_src) - return ICE_ERR_PARAM; + return -EINVAL; if (num_qgrps > ICE_LAN_TXQ_MAX_QGRPS) - return ICE_ERR_PARAM; + return -EINVAL; cmd->num_entries = num_qgrps; @@ -3856,7 +3864,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps, } if (buf_size != sz) - return ICE_ERR_PARAM; + return -EINVAL; do_aq: status = ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd); @@ -3914,8 +3922,7 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps, cmd->num_qset_grps = num_qset_grps; - return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, qset_list, - buf_size, cd)); + return ice_aq_send_cmd(hw, &desc, qset_list, buf_size, cd); } /* End of FW Admin Queue command wrappers */ @@ -4111,7 +4118,7 @@ ice_write_qword(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) * @dest_ctx: pointer to memory for the packed structure * @ce_info: a description of the structure to be transformed */ -enum ice_status +int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info) { @@ -4141,7 +4148,7 @@ ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, ice_write_qword(src_ctx, dest_ctx, &ce_info[f]); break; default: - return ICE_ERR_INVAL_SIZE; + return -EINVAL; } } @@ -4185,7 +4192,7 @@ ice_get_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 q_handle) * * This function adds one LAN queue */ -enum ice_status +int ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd) @@ -4193,19 +4200,19 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, struct ice_aqc_txsched_elem_data node = { 0 }; struct ice_sched_node *parent; struct ice_q_ctx *q_ctx; - enum ice_status status; struct ice_hw *hw; + int status; if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) - return ICE_ERR_CFG; + return -EIO; if (num_qgrps > 1 || buf->num_txqs > 1) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; hw = pi->hw; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; mutex_lock(&pi->sched_lock); @@ -4213,7 +4220,7 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, if (!q_ctx) { ice_debug(hw, ICE_DBG_SCHED, "Enaq: invalid queue handle %d\n", q_handle); - status = ICE_ERR_PARAM; + status = -EINVAL; goto ena_txq_exit; } @@ -4221,7 +4228,7 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, parent = ice_sched_get_free_qparent(pi, vsi_handle, tc, ICE_SCHED_NODE_OWNER_LAN); if (!parent) { - status = ICE_ERR_PARAM; + status = -EINVAL; goto ena_txq_exit; } @@ -4290,20 +4297,20 @@ ena_txq_exit: * * This function removes queues and their corresponding nodes in SW DB */ -enum ice_status +int ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, u16 *q_handles, u16 *q_ids, u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cd) { - enum ice_status status = ICE_ERR_DOES_NOT_EXIST; struct ice_aqc_dis_txq_item *qg_list; struct ice_q_ctx *q_ctx; + int status = -ENOENT; struct ice_hw *hw; u16 i, buf_size; if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) - return ICE_ERR_CFG; + return -EIO; hw = pi->hw; @@ -4315,13 +4322,13 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, if (rst_src) return ice_aq_dis_lan_txq(hw, 0, NULL, 0, rst_src, vmvf_num, NULL); - return ICE_ERR_CFG; + return -EIO; } buf_size = struct_size(qg_list, q_id, 1); qg_list = kzalloc(buf_size, GFP_KERNEL); if (!qg_list) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; mutex_lock(&pi->sched_lock); @@ -4368,18 +4375,18 @@ ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, * * This function adds/updates the VSI queues per TC. */ -static enum ice_status +static int ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *maxqs, u8 owner) { - enum ice_status status = 0; + int status = 0; u8 i; if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) - return ICE_ERR_CFG; + return -EIO; if (!ice_is_vsi_valid(pi->hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; mutex_lock(&pi->sched_lock); @@ -4407,7 +4414,7 @@ ice_cfg_vsi_qs(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, * * This function adds/updates the VSI LAN queues per TC. */ -enum ice_status +int ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *max_lanqs) { @@ -4428,9 +4435,8 @@ int ice_cfg_vsi_rdma(struct ice_port_info *pi, u16 vsi_handle, u16 tc_bitmap, u16 *max_rdmaqs) { - return ice_status_to_errno(ice_cfg_vsi_qs(pi, vsi_handle, tc_bitmap, - max_rdmaqs, - ICE_SCHED_NODE_OWNER_RDMA)); + return ice_cfg_vsi_qs(pi, vsi_handle, tc_bitmap, max_rdmaqs, + ICE_SCHED_NODE_OWNER_RDMA); } /** @@ -4451,7 +4457,6 @@ ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc, struct ice_aqc_txsched_elem_data node = { 0 }; struct ice_aqc_add_rdma_qset_data *buf; struct ice_sched_node *parent; - enum ice_status status; struct ice_hw *hw; u16 i, buf_size; int ret; @@ -4502,12 +4507,10 @@ ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc, node.data.elem_type = ICE_AQC_ELEM_TYPE_LEAF; for (i = 0; i < num_qsets; i++) { node.node_teid = buf->rdma_qsets[i].qset_teid; - status = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, - &node); - if (status) { - ret = ice_status_to_errno(status); + ret = ice_sched_add_node(pi, hw->num_tx_sched_layers - 1, + &node); + if (ret) break; - } qset_teid[i] = le32_to_cpu(node.node_teid); } rdma_error_exit: @@ -4528,8 +4531,8 @@ ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, u16 *q_id) { struct ice_aqc_dis_txq_item *qg_list; - enum ice_status status = 0; struct ice_hw *hw; + int status = 0; u16 qg_size; int i; @@ -4568,7 +4571,7 @@ ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, mutex_unlock(&pi->sched_lock); kfree(qg_list); - return ice_status_to_errno(status); + return status; } /** @@ -4577,7 +4580,7 @@ ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, * * Initializes required config data for VSI, FD, ACL, and RSS before replay. */ -static enum ice_status ice_replay_pre_init(struct ice_hw *hw) +static int ice_replay_pre_init(struct ice_hw *hw) { struct ice_switch_info *sw = hw->switch_info; u8 i; @@ -4604,12 +4607,12 @@ static enum ice_status ice_replay_pre_init(struct ice_hw *hw) * Restore all VSI configuration after reset. It is required to call this * function with main VSI first. */ -enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle) +int ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle) { - enum ice_status status; + int status; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; /* Replay pre-initialization if there is any */ if (vsi_handle == ICE_MAIN_VSI_HANDLE) { @@ -4725,12 +4728,12 @@ ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, * * This function queries HW element information */ -enum ice_status +int ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf) { u16 buf_size, num_elem_ret = 0; - enum ice_status status; + int status; buf_size = sizeof(*buf); memset(buf, 0, buf_size); @@ -4775,7 +4778,7 @@ ice_aq_set_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, cmd->param_indx = idx; cmd->param_val = cpu_to_le32(value); - return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, NULL, 0, cd)); + return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); } /** @@ -4796,7 +4799,7 @@ ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, { struct ice_aqc_driver_shared_params *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; if (idx >= ICE_AQC_DRIVER_PARAM_MAX) return -EIO; @@ -4810,7 +4813,7 @@ ice_aq_get_driver_param(struct ice_hw *hw, enum ice_aqc_driver_params idx, status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); if (status) - return ice_status_to_errno(status); + return status; *value = le32_to_cpu(cmd->param_val); @@ -4840,7 +4843,7 @@ ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value, cmd->gpio_num = pin_idx; cmd->gpio_val = value ? 1 : 0; - return ice_status_to_errno(ice_aq_send_cmd(hw, &desc, NULL, 0, cd)); + return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); } /** @@ -4860,7 +4863,7 @@ ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, { struct ice_aqc_gpio *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_gpio); cmd = &desc.params.read_write_gpio; @@ -4869,7 +4872,7 @@ ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); if (status) - return ice_status_to_errno(status); + return status; *value = !!cmd->gpio_val; return 0; @@ -4903,13 +4906,13 @@ bool ice_fw_supports_link_override(struct ice_hw *hw) * * Gets the link default override for a port */ -enum ice_status +int ice_get_link_default_override(struct ice_link_default_override_tlv *ldo, struct ice_port_info *pi) { u16 i, tlv, tlv_len, tlv_start, buf, offset; struct ice_hw *hw = pi->hw; - enum ice_status status; + int status; status = ice_get_pfa_module_tlv(hw, &tlv, &tlv_len, ICE_SR_LINK_DEFAULT_OVERRIDE_PTR); @@ -4994,7 +4997,7 @@ bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps) * * Set the LLDP MIB. (0x0A08) */ -enum ice_status +int ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, struct ice_sq_cd *cd) { @@ -5004,7 +5007,7 @@ ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, cmd = &desc.params.lldp_set_mib; if (buf_size == 0 || !buf) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_local_mib); @@ -5044,7 +5047,7 @@ bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw) * @vsi_num: absolute HW index for VSI * @add: boolean for if adding or removing a filter */ -enum ice_status +int ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add) { struct ice_aqc_lldp_filter_ctrl *cmd; diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 65c1b3244264..1c57097ddf0b 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -14,108 +14,108 @@ #define ICE_SQ_SEND_DELAY_TIME_MS 10 #define ICE_SQ_SEND_MAX_EXECUTE 3 -enum ice_status ice_init_hw(struct ice_hw *hw); +int ice_init_hw(struct ice_hw *hw); void ice_deinit_hw(struct ice_hw *hw); -enum ice_status ice_check_reset(struct ice_hw *hw); -enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req); -enum ice_status ice_create_all_ctrlq(struct ice_hw *hw); -enum ice_status ice_init_all_ctrlq(struct ice_hw *hw); +int ice_check_reset(struct ice_hw *hw); +int ice_reset(struct ice_hw *hw, enum ice_reset_req req); +int ice_create_all_ctrlq(struct ice_hw *hw); +int ice_init_all_ctrlq(struct ice_hw *hw); void ice_shutdown_all_ctrlq(struct ice_hw *hw); void ice_destroy_all_ctrlq(struct ice_hw *hw); -enum ice_status +int ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_rq_event_info *e, u16 *pending); -enum ice_status +int ice_get_link_status(struct ice_port_info *pi, bool *link_up); -enum ice_status ice_update_link_info(struct ice_port_info *pi); -enum ice_status +int ice_update_link_info(struct ice_port_info *pi); +int ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, enum ice_aq_res_access_type access, u32 timeout); void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res); -enum ice_status +int ice_alloc_hw_res(struct ice_hw *hw, u16 type, u16 num, bool btm, u16 *res); -enum ice_status +int ice_free_hw_res(struct ice_hw *hw, u16 type, u16 num, u16 *res); -enum ice_status +int ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, struct ice_aqc_alloc_free_res_elem *buf, u16 buf_size, enum ice_adminq_opc opc, struct ice_sq_cd *cd); bool ice_is_sbq_supported(struct ice_hw *hw); struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw); -enum ice_status +int ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd); void ice_clear_pxe_mode(struct ice_hw *hw); -enum ice_status ice_get_caps(struct ice_hw *hw); +int ice_get_caps(struct ice_hw *hw); void ice_set_safe_mode_caps(struct ice_hw *hw); -enum ice_status +int ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index); -enum ice_status +int ice_aq_get_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *get_params); -enum ice_status +int ice_aq_set_rss_lut(struct ice_hw *hw, struct ice_aq_get_set_rss_lut_params *set_params); -enum ice_status +int ice_aq_get_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys); -enum ice_status +int ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle, struct ice_aqc_get_set_rss_keys *keys); bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq); -enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading); +int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading); void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode); extern const struct ice_ctx_ele ice_tlan_ctx_info[]; -enum ice_status +int ice_set_ctx(struct ice_hw *hw, u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info); extern struct mutex ice_global_cfg_lock_sw; -enum ice_status +int ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd); -enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd); +int ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *caps, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, enum ice_adminq_opc opc, struct ice_sq_cd *cd); -enum ice_status +int ice_discover_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_caps); void ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high, u16 link_speeds_bitmap); -enum ice_status +int ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags, struct ice_sq_cd *cd); bool ice_is_e810(struct ice_hw *hw); -enum ice_status ice_clear_pf_cfg(struct ice_hw *hw); -enum ice_status +int ice_clear_pf_cfg(struct ice_hw *hw); +int ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd); bool ice_fw_supports_link_override(struct ice_hw *hw); -enum ice_status +int ice_get_link_default_override(struct ice_link_default_override_tlv *ldo, struct ice_port_info *pi); bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps); enum ice_fc_mode ice_caps_to_fc_mode(u8 caps); enum ice_fec_mode ice_caps_to_fec_mode(u8 caps, u8 fec_options); -enum ice_status +int ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update); -enum ice_status +int ice_cfg_phy_fc(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fc_mode fc); bool @@ -125,27 +125,27 @@ void ice_copy_phy_caps_to_cfg(struct ice_port_info *pi, struct ice_aqc_get_phy_caps_data *caps, struct ice_aqc_set_phy_cfg_data *cfg); -enum ice_status +int ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec); -enum ice_status +int ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_set_mac_cfg(struct ice_hw *hw, u16 max_frame_size, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, struct ice_link_status *link, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_set_mac_loopback(struct ice_hw *hw, bool ena_lpbk, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length, bool write, struct ice_sq_cd *cd); @@ -159,19 +159,19 @@ ice_ena_vsi_rdma_qset(struct ice_port_info *pi, u16 vsi_handle, u8 tc, int ice_dis_vsi_rdma_qset(struct ice_port_info *pi, u16 count, u32 *qset_teid, u16 *q_id); -enum ice_status +int ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, u16 *q_handle, u16 *q_ids, u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cd); -enum ice_status +int ice_cfg_vsi_lan(struct ice_port_info *pi, u16 vsi_handle, u8 tc_bitmap, u16 *max_lanqs); -enum ice_status +int ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd); -enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); +int ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); void ice_replay_post(struct ice_hw *hw); void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); struct ice_q_ctx * @@ -184,7 +184,7 @@ void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); bool ice_is_e810t(struct ice_hw *hw); -enum ice_status +int ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); int @@ -199,11 +199,11 @@ ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value, int ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool *value, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size, struct ice_sq_cd *cd); bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw); -enum ice_status +int ice_lldp_fltr_add_remove(struct ice_hw *hw, u16 vsi_num, bool add); bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 03bdb125be36..6bcfee295991 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -87,7 +87,7 @@ bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq) * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue */ -static enum ice_status +static int ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) { size_t size = cq->num_sq_entries * sizeof(struct ice_aq_desc); @@ -96,7 +96,7 @@ ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) &cq->sq.desc_buf.pa, GFP_KERNEL | __GFP_ZERO); if (!cq->sq.desc_buf.va) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; cq->sq.desc_buf.size = size; cq->sq.cmd_buf = devm_kcalloc(ice_hw_to_dev(hw), cq->num_sq_entries, @@ -107,7 +107,7 @@ ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) cq->sq.desc_buf.va = NULL; cq->sq.desc_buf.pa = 0; cq->sq.desc_buf.size = 0; - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } return 0; @@ -118,7 +118,7 @@ ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue */ -static enum ice_status +static int ice_alloc_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) { size_t size = cq->num_rq_entries * sizeof(struct ice_aq_desc); @@ -127,7 +127,7 @@ ice_alloc_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) &cq->rq.desc_buf.pa, GFP_KERNEL | __GFP_ZERO); if (!cq->rq.desc_buf.va) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; cq->rq.desc_buf.size = size; return 0; } @@ -154,7 +154,7 @@ static void ice_free_cq_ring(struct ice_hw *hw, struct ice_ctl_q_ring *ring) * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue */ -static enum ice_status +static int ice_alloc_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq) { int i; @@ -165,7 +165,7 @@ ice_alloc_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq) cq->rq.dma_head = devm_kcalloc(ice_hw_to_dev(hw), cq->num_rq_entries, sizeof(cq->rq.desc_buf), GFP_KERNEL); if (!cq->rq.dma_head) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; cq->rq.r.rq_bi = (struct ice_dma_mem *)cq->rq.dma_head; /* allocate the mapped buffers */ @@ -218,7 +218,7 @@ unwind_alloc_rq_bufs: devm_kfree(ice_hw_to_dev(hw), cq->rq.dma_head); cq->rq.dma_head = NULL; - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } /** @@ -226,7 +226,7 @@ unwind_alloc_rq_bufs: * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue */ -static enum ice_status +static int ice_alloc_sq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq) { int i; @@ -235,7 +235,7 @@ ice_alloc_sq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq) cq->sq.dma_head = devm_kcalloc(ice_hw_to_dev(hw), cq->num_sq_entries, sizeof(cq->sq.desc_buf), GFP_KERNEL); if (!cq->sq.dma_head) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; cq->sq.r.sq_bi = (struct ice_dma_mem *)cq->sq.dma_head; /* allocate the mapped buffers */ @@ -266,10 +266,10 @@ unwind_alloc_sq_bufs: devm_kfree(ice_hw_to_dev(hw), cq->sq.dma_head); cq->sq.dma_head = NULL; - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } -static enum ice_status +static int ice_cfg_cq_regs(struct ice_hw *hw, struct ice_ctl_q_ring *ring, u16 num_entries) { /* Clear Head and Tail */ @@ -283,7 +283,7 @@ ice_cfg_cq_regs(struct ice_hw *hw, struct ice_ctl_q_ring *ring, u16 num_entries) /* Check one register to verify that config was applied */ if (rd32(hw, ring->bal) != lower_32_bits(ring->desc_buf.pa)) - return ICE_ERR_AQ_ERROR; + return -EIO; return 0; } @@ -295,8 +295,7 @@ ice_cfg_cq_regs(struct ice_hw *hw, struct ice_ctl_q_ring *ring, u16 num_entries) * * Configure base address and length registers for the transmit queue */ -static enum ice_status -ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) +static int ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) { return ice_cfg_cq_regs(hw, &cq->sq, cq->num_sq_entries); } @@ -308,10 +307,9 @@ ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) * * Configure base address and length registers for the receive (event queue) */ -static enum ice_status -ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) +static int ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) { - enum ice_status status; + int status; status = ice_cfg_cq_regs(hw, &cq->rq, cq->num_rq_entries); if (status) @@ -361,19 +359,19 @@ do { \ * Do *NOT* hold the lock when calling this as the memory allocation routines * called are not going to be atomic context safe */ -static enum ice_status ice_init_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) +static int ice_init_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) { - enum ice_status ret_code; + int ret_code; if (cq->sq.count > 0) { /* queue already initialized */ - ret_code = ICE_ERR_NOT_READY; + ret_code = -EBUSY; goto init_ctrlq_exit; } /* verify input for valid configuration */ if (!cq->num_sq_entries || !cq->sq_buf_size) { - ret_code = ICE_ERR_CFG; + ret_code = -EIO; goto init_ctrlq_exit; } @@ -421,19 +419,19 @@ init_ctrlq_exit: * Do *NOT* hold the lock when calling this as the memory allocation routines * called are not going to be atomic context safe */ -static enum ice_status ice_init_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq) +static int ice_init_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq) { - enum ice_status ret_code; + int ret_code; if (cq->rq.count > 0) { /* queue already initialized */ - ret_code = ICE_ERR_NOT_READY; + ret_code = -EBUSY; goto init_ctrlq_exit; } /* verify input for valid configuration */ if (!cq->num_rq_entries || !cq->rq_buf_size) { - ret_code = ICE_ERR_CFG; + ret_code = -EIO; goto init_ctrlq_exit; } @@ -474,15 +472,14 @@ init_ctrlq_exit: * * The main shutdown routine for the Control Transmit Queue */ -static enum ice_status -ice_shutdown_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) +static int ice_shutdown_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) { - enum ice_status ret_code = 0; + int ret_code = 0; mutex_lock(&cq->sq_lock); if (!cq->sq.count) { - ret_code = ICE_ERR_NOT_READY; + ret_code = -EBUSY; goto shutdown_sq_out; } @@ -541,15 +538,14 @@ static bool ice_aq_ver_check(struct ice_hw *hw) * * The main shutdown routine for the Control Receive Queue */ -static enum ice_status -ice_shutdown_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq) +static int ice_shutdown_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq) { - enum ice_status ret_code = 0; + int ret_code = 0; mutex_lock(&cq->rq_lock); if (!cq->rq.count) { - ret_code = ICE_ERR_NOT_READY; + ret_code = -EBUSY; goto shutdown_rq_out; } @@ -576,17 +572,17 @@ shutdown_rq_out: * ice_init_check_adminq - Check version for Admin Queue to know if its alive * @hw: pointer to the hardware structure */ -static enum ice_status ice_init_check_adminq(struct ice_hw *hw) +static int ice_init_check_adminq(struct ice_hw *hw) { struct ice_ctl_q_info *cq = &hw->adminq; - enum ice_status status; + int status; status = ice_aq_get_fw_ver(hw, NULL); if (status) goto init_ctrlq_free_rq; if (!ice_aq_ver_check(hw)) { - status = ICE_ERR_FW_API_VER; + status = -EIO; goto init_ctrlq_free_rq; } @@ -612,10 +608,10 @@ init_ctrlq_free_rq: * * NOTE: this function does not initialize the controlq locks */ -static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) +static int ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) { struct ice_ctl_q_info *cq; - enum ice_status ret_code; + int ret_code; switch (q_type) { case ICE_CTL_Q_ADMIN: @@ -631,14 +627,14 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) cq = &hw->mailboxq; break; default: - return ICE_ERR_PARAM; + return -EINVAL; } cq->qtype = q_type; /* verify input for valid configuration */ if (!cq->num_rq_entries || !cq->num_sq_entries || !cq->rq_buf_size || !cq->sq_buf_size) { - return ICE_ERR_CFG; + return -EIO; } /* setup SQ command write back timeout */ @@ -751,10 +747,10 @@ void ice_shutdown_all_ctrlq(struct ice_hw *hw) * * NOTE: this function does not initialize the controlq locks. */ -enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) +int ice_init_all_ctrlq(struct ice_hw *hw) { - enum ice_status status; u32 retry = 0; + int status; /* Init FW admin queue */ do { @@ -763,7 +759,7 @@ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) return status; status = ice_init_check_adminq(hw); - if (status != ICE_ERR_AQ_FW_CRITICAL) + if (status != -EIO) break; ice_debug(hw, ICE_DBG_AQ_MSG, "Retry Admin Queue init due to FW critical error\n"); @@ -814,7 +810,7 @@ static void ice_init_ctrlq_locks(struct ice_ctl_q_info *cq) * driver needs to re-initialize control queues at run time it should call * ice_init_all_ctrlq instead. */ -enum ice_status ice_create_all_ctrlq(struct ice_hw *hw) +int ice_create_all_ctrlq(struct ice_hw *hw) { ice_init_ctrlq_locks(&hw->adminq); if (ice_is_sbq_supported(hw)) @@ -962,7 +958,7 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq) * This is the main send command routine for the ATQ. It runs the queue, * cleans the queue, etc. */ -enum ice_status +int ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd) @@ -970,27 +966,27 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_dma_mem *dma_buf = NULL; struct ice_aq_desc *desc_on_ring; bool cmd_completed = false; - enum ice_status status = 0; struct ice_sq_cd *details; u32 total_delay = 0; + int status = 0; u16 retval = 0; u32 val = 0; /* if reset is in progress return a soft error */ if (hw->reset_ongoing) - return ICE_ERR_RESET_ONGOING; + return -EBUSY; mutex_lock(&cq->sq_lock); cq->sq_last_status = ICE_AQ_RC_OK; if (!cq->sq.count) { ice_debug(hw, ICE_DBG_AQ_MSG, "Control Send queue not initialized.\n"); - status = ICE_ERR_AQ_EMPTY; + status = -EIO; goto sq_send_command_error; } if ((buf && !buf_size) || (!buf && buf_size)) { - status = ICE_ERR_PARAM; + status = -EINVAL; goto sq_send_command_error; } @@ -998,7 +994,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, if (buf_size > cq->sq_buf_size) { ice_debug(hw, ICE_DBG_AQ_MSG, "Invalid buffer size for Control Send queue: %d.\n", buf_size); - status = ICE_ERR_INVAL_SIZE; + status = -EINVAL; goto sq_send_command_error; } @@ -1011,7 +1007,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, if (val >= cq->num_sq_entries) { ice_debug(hw, ICE_DBG_AQ_MSG, "head overrun at %d in the Control Send Queue ring\n", val); - status = ICE_ERR_AQ_EMPTY; + status = -EIO; goto sq_send_command_error; } @@ -1028,7 +1024,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, */ if (ice_clean_sq(hw, cq) == 0) { ice_debug(hw, ICE_DBG_AQ_MSG, "Error: Control Send Queue is full.\n"); - status = ICE_ERR_AQ_FULL; + status = -ENOSPC; goto sq_send_command_error; } @@ -1082,7 +1078,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, if (copy_size > buf_size) { ice_debug(hw, ICE_DBG_AQ_MSG, "Return len %d > than buf len %d\n", copy_size, buf_size); - status = ICE_ERR_AQ_ERROR; + status = -EIO; } else { memcpy(buf, dma_buf->va, copy_size); } @@ -1098,7 +1094,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, } cmd_completed = true; if (!status && retval != ICE_AQ_RC_OK) - status = ICE_ERR_AQ_ERROR; + status = -EIO; cq->sq_last_status = (enum ice_aq_err)retval; } @@ -1116,10 +1112,10 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, if (rd32(hw, cq->rq.len) & cq->rq.len_crit_mask || rd32(hw, cq->sq.len) & cq->sq.len_crit_mask) { ice_debug(hw, ICE_DBG_AQ_MSG, "Critical FW error.\n"); - status = ICE_ERR_AQ_FW_CRITICAL; + status = -EIO; } else { ice_debug(hw, ICE_DBG_AQ_MSG, "Control Send Queue Writeback timeout.\n"); - status = ICE_ERR_AQ_TIMEOUT; + status = -EIO; } } @@ -1154,15 +1150,15 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode) * the contents through e. It can also return how many events are * left to process through 'pending'. */ -enum ice_status +int ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_rq_event_info *e, u16 *pending) { u16 ntc = cq->rq.next_to_clean; enum ice_aq_err rq_last_status; - enum ice_status ret_code = 0; struct ice_aq_desc *desc; struct ice_dma_mem *bi; + int ret_code = 0; u16 desc_idx; u16 datalen; u16 flags; @@ -1176,7 +1172,7 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, if (!cq->rq.count) { ice_debug(hw, ICE_DBG_AQ_MSG, "Control Receive queue not initialized.\n"); - ret_code = ICE_ERR_AQ_EMPTY; + ret_code = -EIO; goto clean_rq_elem_err; } @@ -1185,7 +1181,7 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, if (ntu == ntc) { /* nothing to do - shouldn't need to update ring's values */ - ret_code = ICE_ERR_AQ_NO_WORK; + ret_code = -EALREADY; goto clean_rq_elem_out; } @@ -1196,7 +1192,7 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval); flags = le16_to_cpu(desc->flags); if (flags & ICE_AQ_FLAG_ERR) { - ret_code = ICE_ERR_AQ_ERROR; + ret_code = -EIO; ice_debug(hw, ICE_DBG_AQ_MSG, "Control Receive Queue Event 0x%04X received with error 0x%X\n", le16_to_cpu(desc->opcode), rq_last_status); } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 241427cd9bc0..0b146a0d4205 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -2,7 +2,6 @@ /* Copyright (c) 2019, Intel Corporation. */ #include "ice_common.h" -#include "ice_lib.h" #include "ice_sched.h" #include "ice_dcb.h" @@ -19,19 +18,19 @@ * * Requests the complete LLDP MIB (entire packet). (0x0A00) */ -static enum ice_status +static int ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf, u16 buf_size, u16 *local_len, u16 *remote_len, struct ice_sq_cd *cd) { struct ice_aqc_lldp_get_mib *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd = &desc.params.lldp_get_mib; if (buf_size == 0 || !buf) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_get_mib); @@ -61,7 +60,7 @@ ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf, * Enable or Disable posting of an event on ARQ when LLDP MIB * associated with the interface changes (0x0A01) */ -static enum ice_status +static int ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update, struct ice_sq_cd *cd) { @@ -89,7 +88,7 @@ ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update, * * Stop or Shutdown the embedded LLDP Agent (0x0A05) */ -enum ice_status +int ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist, struct ice_sq_cd *cd) { @@ -117,8 +116,7 @@ ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist, * * Start the embedded LLDP Agent on all ports. (0x0A06) */ -enum ice_status -ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd) +int ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd) { struct ice_aqc_lldp_start *cmd; struct ice_aq_desc desc; @@ -598,18 +596,17 @@ ice_parse_org_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) * * Parse DCB configuration from the LLDPDU */ -static enum ice_status -ice_lldp_to_dcb_cfg(u8 *lldpmib, struct ice_dcbx_cfg *dcbcfg) +static int ice_lldp_to_dcb_cfg(u8 *lldpmib, struct ice_dcbx_cfg *dcbcfg) { struct ice_lldp_org_tlv *tlv; - enum ice_status ret = 0; u16 offset = 0; + int ret = 0; u16 typelen; u16 type; u16 len; if (!lldpmib || !dcbcfg) - return ICE_ERR_PARAM; + return -EINVAL; /* set to the start of LLDPDU */ lldpmib += ETH_HLEN; @@ -649,17 +646,17 @@ ice_lldp_to_dcb_cfg(u8 *lldpmib, struct ice_dcbx_cfg *dcbcfg) * * Query DCB configuration from the firmware */ -enum ice_status +int ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype, struct ice_dcbx_cfg *dcbcfg) { - enum ice_status ret; u8 *lldpmib; + int ret; /* Allocate the LLDPDU */ lldpmib = devm_kzalloc(ice_hw_to_dev(hw), ICE_LLDPDU_SIZE, GFP_KERNEL); if (!lldpmib) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; ret = ice_aq_get_lldp_mib(hw, bridgetype, mib_type, (void *)lldpmib, ICE_LLDPDU_SIZE, NULL, NULL, NULL); @@ -684,17 +681,17 @@ ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype, * @cd: pointer to command details structure or NULL * * Start/Stop the embedded dcbx Agent. In case that this wrapper function - * returns ICE_SUCCESS, caller will need to check if FW returns back the same + * returns 0, caller will need to check if FW returns back the same * value as stated in dcbx_agent_status, and react accordingly. (0x0A09) */ -enum ice_status +int ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent, bool *dcbx_agent_status, struct ice_sq_cd *cd) { struct ice_aqc_lldp_stop_start_specific_agent *cmd; - enum ice_status status; struct ice_aq_desc desc; u16 opcode; + int status; cmd = &desc.params.lldp_agent_ctrl; @@ -724,7 +721,7 @@ ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent, * * Get CEE DCBX mode operational configuration from firmware (0x0A07) */ -static enum ice_status +static int ice_aq_get_cee_dcb_cfg(struct ice_hw *hw, struct ice_aqc_get_cee_dcb_cfg_resp *buff, struct ice_sq_cd *cd) @@ -749,7 +746,7 @@ int ice_aq_set_pfc_mode(struct ice_hw *hw, u8 pfc_mode, struct ice_sq_cd *cd) { struct ice_aqc_set_query_pfc_mode *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; if (pfc_mode > ICE_AQC_PFC_DSCP_BASED_PFC) return -EINVAL; @@ -762,7 +759,7 @@ int ice_aq_set_pfc_mode(struct ice_hw *hw, u8 pfc_mode, struct ice_sq_cd *cd) status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); if (status) - return ice_status_to_errno(status); + return status; /* FW will write the PFC mode set back into cmd->pfc_mode, but if DCB is * disabled, FW will write back 0 to cmd->pfc_mode. After the AQ has @@ -903,14 +900,13 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, * * Get IEEE or CEE mode DCB configuration from the Firmware */ -static enum ice_status -ice_get_ieee_or_cee_dcb_cfg(struct ice_port_info *pi, u8 dcbx_mode) +static int ice_get_ieee_or_cee_dcb_cfg(struct ice_port_info *pi, u8 dcbx_mode) { struct ice_dcbx_cfg *dcbx_cfg = NULL; - enum ice_status ret; + int ret; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; if (dcbx_mode == ICE_DCBX_MODE_IEEE) dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg; @@ -943,14 +939,14 @@ out: * * Get DCB configuration from the Firmware */ -enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi) +int ice_get_dcb_cfg(struct ice_port_info *pi) { struct ice_aqc_get_cee_dcb_cfg_resp cee_cfg; struct ice_dcbx_cfg *dcbx_cfg; - enum ice_status ret; + int ret; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; ret = ice_aq_get_cee_dcb_cfg(pi->hw, &cee_cfg, NULL); if (!ret) { @@ -974,13 +970,13 @@ enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi) * * Update DCB configuration from the Firmware */ -enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change) +int ice_init_dcb(struct ice_hw *hw, bool enable_mib_change) { struct ice_qos_cfg *qos_cfg = &hw->port_info->qos_cfg; - enum ice_status ret = 0; + int ret = 0; if (!hw->func_caps.common_cap.dcb) - return ICE_ERR_NOT_SUPPORTED; + return -EOPNOTSUPP; qos_cfg->is_sw_lldp = true; @@ -996,7 +992,7 @@ enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change) return ret; qos_cfg->is_sw_lldp = false; } else if (qos_cfg->dcbx_status == ICE_DCBX_STATUS_DIS) { - return ICE_ERR_NOT_READY; + return -EBUSY; } /* Configure the LLDP MIB change event */ @@ -1016,19 +1012,19 @@ enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change) * * Configure (disable/enable) MIB */ -enum ice_status ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib) +int ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib) { struct ice_qos_cfg *qos_cfg = &hw->port_info->qos_cfg; - enum ice_status ret; + int ret; if (!hw->func_caps.common_cap.dcb) - return ICE_ERR_NOT_SUPPORTED; + return -EOPNOTSUPP; /* Get DCBX status */ qos_cfg->dcbx_status = ice_get_dcbx_status(hw); if (qos_cfg->dcbx_status == ICE_DCBX_STATUS_DIS) - return ICE_ERR_NOT_READY; + return -EBUSY; ret = ice_aq_cfg_lldp_mib_change(hw, ena_mib, NULL); if (!ret) @@ -1469,16 +1465,16 @@ ice_dcb_cfg_to_lldp(u8 *lldpmib, u16 *miblen, struct ice_dcbx_cfg *dcbcfg) * * Set DCB configuration to the Firmware */ -enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi) +int ice_set_dcb_cfg(struct ice_port_info *pi) { u8 mib_type, *lldpmib = NULL; struct ice_dcbx_cfg *dcbcfg; - enum ice_status ret; struct ice_hw *hw; u16 miblen; + int ret; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; hw = pi->hw; @@ -1487,7 +1483,7 @@ enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi) /* Allocate the LLDPDU */ lldpmib = devm_kzalloc(ice_hw_to_dev(hw), ICE_LLDPDU_SIZE, GFP_KERNEL); if (!lldpmib) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; mib_type = SET_LOCAL_MIB_TYPE_LOCAL_MIB; if (dcbcfg->app_mode == ICE_DCBX_APPS_NON_WILLING) @@ -1511,17 +1507,17 @@ enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi) * * query current port ETS configuration */ -static enum ice_status +static int ice_aq_query_port_ets(struct ice_port_info *pi, struct ice_aqc_port_ets_elem *buf, u16 buf_size, struct ice_sq_cd *cd) { struct ice_aqc_query_port_ets *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; cmd = &desc.params.port_ets; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_query_port_ets); cmd->port_teid = pi->root->info.node_teid; @@ -1537,18 +1533,18 @@ ice_aq_query_port_ets(struct ice_port_info *pi, * * update the SW DB with the new TC changes */ -static enum ice_status +static int ice_update_port_tc_tree_cfg(struct ice_port_info *pi, struct ice_aqc_port_ets_elem *buf) { struct ice_sched_node *node, *tc_node; struct ice_aqc_txsched_elem_data elem; - enum ice_status status = 0; u32 teid1, teid2; + int status = 0; u8 i, j; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; /* suspend the missing TC nodes */ for (i = 0; i < pi->root->num_children; i++) { teid1 = le32_to_cpu(pi->root->children[i]->info.node_teid); @@ -1605,12 +1601,12 @@ ice_update_port_tc_tree_cfg(struct ice_port_info *pi, * query current port ETS configuration and update the * SW DB with the TC changes */ -enum ice_status +int ice_query_port_ets(struct ice_port_info *pi, struct ice_aqc_port_ets_elem *buf, u16 buf_size, struct ice_sq_cd *cd) { - enum ice_status status; + int status; mutex_lock(&pi->sched_lock); status = ice_aq_query_port_ets(pi, buf, buf_size, cd); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.h b/drivers/net/ethernet/intel/ice/ice_dcb.h index 9b6f87a889a6..d73348f279f7 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb.h @@ -138,28 +138,27 @@ struct ice_cee_app_prio { } __packed; int ice_aq_set_pfc_mode(struct ice_hw *hw, u8 pfc_mode, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype, struct ice_dcbx_cfg *dcbcfg); -enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi); -enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi); -enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change); -enum ice_status +int ice_get_dcb_cfg(struct ice_port_info *pi); +int ice_set_dcb_cfg(struct ice_port_info *pi); +int ice_init_dcb(struct ice_hw *hw, bool enable_mib_change); +int ice_query_port_ets(struct ice_port_info *pi, struct ice_aqc_port_ets_elem *buf, u16 buf_size, struct ice_sq_cd *cmd_details); #ifdef CONFIG_DCB -enum ice_status +int ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist, struct ice_sq_cd *cd); -enum ice_status -ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd); +int ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent, bool *dcbx_agent_status, struct ice_sq_cd *cd); -enum ice_status ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib); +int ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib); #else /* CONFIG_DCB */ -static inline enum ice_status +static inline int ice_aq_stop_lldp(struct ice_hw __always_unused *hw, bool __always_unused shutdown_lldp_agent, bool __always_unused persist, @@ -168,7 +167,7 @@ ice_aq_stop_lldp(struct ice_hw __always_unused *hw, return 0; } -static inline enum ice_status +static inline int ice_aq_start_lldp(struct ice_hw __always_unused *hw, bool __always_unused persist, struct ice_sq_cd __always_unused *cd) @@ -176,7 +175,7 @@ ice_aq_start_lldp(struct ice_hw __always_unused *hw, return 0; } -static inline enum ice_status +static inline int ice_aq_start_stop_dcbx(struct ice_hw __always_unused *hw, bool __always_unused start_dcbx_agent, bool *dcbx_agent_status, @@ -187,7 +186,7 @@ ice_aq_start_stop_dcbx(struct ice_hw __always_unused *hw, return 0; } -static inline enum ice_status +static inline int ice_cfg_lldp_mib_change(struct ice_hw __always_unused *hw, bool __always_unused ena_mib) { diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index a72e18320a22..b94d8daeaa58 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -528,7 +528,7 @@ void ice_dcb_rebuild(struct ice_pf *pf) struct ice_aqc_port_ets_elem buf = { 0 }; struct device *dev = ice_pf_to_dev(pf); struct ice_dcbx_cfg *err_cfg; - enum ice_status ret; + int ret; ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); if (ret) { diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 7fdeb411b6df..3eb01731e496 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -97,6 +97,9 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) new_cfg->etscfg.maxtcs = pf->hw.func_caps.common_cap.maxtc; + if (!bwcfg) + new_cfg->etscfg.tcbwtable[0] = 100; + if (!bwrec) new_cfg->etsrec.tcbwtable[0] = 100; @@ -167,15 +170,18 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode) if (mode == pf->dcbx_cap) return ICE_DCB_NO_HW_CHG; - pf->dcbx_cap = mode; qos_cfg = &pf->hw.port_info->qos_cfg; - if (mode & DCB_CAP_DCBX_VER_CEE) { - if (qos_cfg->local_dcbx_cfg.pfc_mode == ICE_QOS_MODE_DSCP) - return ICE_DCB_NO_HW_CHG; + + /* DSCP configuration is not DCBx negotiated */ + if (qos_cfg->local_dcbx_cfg.pfc_mode == ICE_QOS_MODE_DSCP) + return ICE_DCB_NO_HW_CHG; + + pf->dcbx_cap = mode; + + if (mode & DCB_CAP_DCBX_VER_CEE) qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_CEE; - } else { + else qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_IEEE; - } dev_info(ice_pf_to_dev(pf), "DCBx mode = 0x%x\n", mode); return ICE_DCB_HW_CHG_RST; diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 1cfe918db8b9..5aa18219920b 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -39,13 +39,13 @@ static void ice_info_get_dsn(struct ice_pf *pf, struct ice_info_ctx *ctx) static void ice_info_pba(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_hw *hw = &pf->hw; - enum ice_status status; + int status; status = ice_read_pba_string(hw, (u8 *)ctx->buf, sizeof(ctx->buf)); if (status) /* We failed to locate the PBA, so just skip this entry */ - dev_dbg(ice_pf_to_dev(pf), "Failed to read Product Board Assembly string, status %s\n", - ice_stat_str(status)); + dev_dbg(ice_pf_to_dev(pf), "Failed to read Product Board Assembly string, status %d\n", + status); } static void ice_info_fw_mgmt(struct ice_pf *pf, struct ice_info_ctx *ctx) @@ -251,7 +251,6 @@ static int ice_devlink_info_get(struct devlink *devlink, struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; struct ice_info_ctx *ctx; - enum ice_status status; size_t i; int err; @@ -266,20 +265,19 @@ static int ice_devlink_info_get(struct devlink *devlink, return -ENOMEM; /* discover capabilities first */ - status = ice_discover_dev_caps(hw, &ctx->dev_caps); - if (status) { - dev_dbg(dev, "Failed to discover device capabilities, status %s aq_err %s\n", - ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status)); + err = ice_discover_dev_caps(hw, &ctx->dev_caps); + if (err) { + dev_dbg(dev, "Failed to discover device capabilities, status %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); NL_SET_ERR_MSG_MOD(extack, "Unable to discover device capabilities"); - err = -EIO; goto out_free_ctx; } if (ctx->dev_caps.common_cap.nvm_update_pending_orom) { - status = ice_get_inactive_orom_ver(hw, &ctx->pending_orom); - if (status) { - dev_dbg(dev, "Unable to read inactive Option ROM version data, status %s aq_err %s\n", - ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status)); + err = ice_get_inactive_orom_ver(hw, &ctx->pending_orom); + if (err) { + dev_dbg(dev, "Unable to read inactive Option ROM version data, status %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); /* disable display of pending Option ROM */ ctx->dev_caps.common_cap.nvm_update_pending_orom = false; @@ -287,10 +285,10 @@ static int ice_devlink_info_get(struct devlink *devlink, } if (ctx->dev_caps.common_cap.nvm_update_pending_nvm) { - status = ice_get_inactive_nvm_ver(hw, &ctx->pending_nvm); - if (status) { - dev_dbg(dev, "Unable to read inactive NVM version data, status %s aq_err %s\n", - ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status)); + err = ice_get_inactive_nvm_ver(hw, &ctx->pending_nvm); + if (err) { + dev_dbg(dev, "Unable to read inactive NVM version data, status %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); /* disable display of pending Option ROM */ ctx->dev_caps.common_cap.nvm_update_pending_nvm = false; @@ -298,10 +296,10 @@ static int ice_devlink_info_get(struct devlink *devlink, } if (ctx->dev_caps.common_cap.nvm_update_pending_netlist) { - status = ice_get_inactive_netlist_ver(hw, &ctx->pending_netlist); - if (status) { - dev_dbg(dev, "Unable to read inactive Netlist version data, status %s aq_err %s\n", - ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status)); + err = ice_get_inactive_netlist_ver(hw, &ctx->pending_netlist); + if (err) { + dev_dbg(dev, "Unable to read inactive Netlist version data, status %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); /* disable display of pending Option ROM */ ctx->dev_caps.common_cap.nvm_update_pending_netlist = false; @@ -373,57 +371,105 @@ out_free_ctx: } /** - * ice_devlink_flash_update - Update firmware stored in flash on the device - * @devlink: pointer to devlink associated with device to update - * @params: flash update parameters + * ice_devlink_reload_empr_start - Start EMP reset to activate new firmware + * @devlink: pointer to the devlink instance to reload + * @netns_change: if true, the network namespace is changing + * @action: the action to perform. Must be DEVLINK_RELOAD_ACTION_FW_ACTIVATE + * @limit: limits on what reload should do, such as not resetting * @extack: netlink extended ACK structure * - * Perform a device flash update. The bulk of the update logic is contained - * within the ice_flash_pldm_image function. + * Allow user to activate new Embedded Management Processor firmware by + * issuing device specific EMP reset. Called in response to + * a DEVLINK_CMD_RELOAD with the DEVLINK_RELOAD_ACTION_FW_ACTIVATE. * - * Returns: zero on success, or an error code on failure. + * Note that teardown and rebuild of the driver state happens automatically as + * part of an interrupt and watchdog task. This is because all physical + * functions on the device must be able to reset when an EMP reset occurs from + * any source. */ static int -ice_devlink_flash_update(struct devlink *devlink, - struct devlink_flash_update_params *params, - struct netlink_ext_ack *extack) +ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + struct netlink_ext_ack *extack) { struct ice_pf *pf = devlink_priv(devlink); + struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - u8 preservation; + u8 pending; int err; - if (!params->overwrite_mask) { - /* preserve all settings and identifiers */ - preservation = ICE_AQC_NVM_PRESERVE_ALL; - } else if (params->overwrite_mask == DEVLINK_FLASH_OVERWRITE_SETTINGS) { - /* overwrite settings, but preserve the vital device identifiers */ - preservation = ICE_AQC_NVM_PRESERVE_SELECTED; - } else if (params->overwrite_mask == (DEVLINK_FLASH_OVERWRITE_SETTINGS | - DEVLINK_FLASH_OVERWRITE_IDENTIFIERS)) { - /* overwrite both settings and identifiers, preserve nothing */ - preservation = ICE_AQC_NVM_NO_PRESERVATION; - } else { - NL_SET_ERR_MSG_MOD(extack, "Requested overwrite mask is not supported"); - return -EOPNOTSUPP; + err = ice_get_pending_updates(pf, &pending, extack); + if (err) + return err; + + /* pending is a bitmask of which flash banks have a pending update, + * including the main NVM bank, the Option ROM bank, and the netlist + * bank. If any of these bits are set, then there is a pending update + * waiting to be activated. + */ + if (!pending) { + NL_SET_ERR_MSG_MOD(extack, "No pending firmware update"); + return -ECANCELED; } - if (!hw->dev_caps.common_cap.nvm_unified_update) { - NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update"); - return -EOPNOTSUPP; + if (pf->fw_emp_reset_disabled) { + NL_SET_ERR_MSG_MOD(extack, "EMP reset is not available. To activate firmware, a reboot or power cycle is needed"); + return -ECANCELED; } - err = ice_check_for_pending_update(pf, NULL, extack); - if (err) + dev_dbg(dev, "Issuing device EMP reset to activate firmware\n"); + + err = ice_aq_nvm_update_empr(hw); + if (err) { + dev_err(dev, "Failed to trigger EMP device reset to reload firmware, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to trigger EMP device reset to reload firmware"); return err; + } - devlink_flash_update_status_notify(devlink, "Preparing to flash", NULL, 0, 0); + return 0; +} - return ice_flash_pldm_image(pf, params->fw, preservation, extack); +/** + * ice_devlink_reload_empr_finish - Wait for EMP reset to finish + * @devlink: pointer to the devlink instance reloading + * @action: the action requested + * @limit: limits imposed by userspace, such as not resetting + * @actions_performed: on return, indicate what actions actually performed + * @extack: netlink extended ACK structure + * + * Wait for driver to finish rebuilding after EMP reset is completed. This + * includes time to wait for both the actual device reset as well as the time + * for the driver's rebuild to complete. + */ +static int +ice_devlink_reload_empr_finish(struct devlink *devlink, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + int err; + + *actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE); + + err = ice_wait_for_reset(pf, 60 * HZ); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Device still resetting after 1 minute"); + return err; + } + + return 0; } static const struct devlink_ops ice_devlink_ops = { .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, + .reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), + /* The ice driver currently does not support driver reinit */ + .reload_down = ice_devlink_reload_empr_start, + .reload_up = ice_devlink_reload_empr_finish, .eswitch_mode_get = ice_eswitch_mode_get, .eswitch_mode_set = ice_eswitch_mode_set, .info_get = ice_devlink_info_get, @@ -584,6 +630,7 @@ void ice_devlink_register(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); + devlink_set_features(devlink, DEVLINK_F_RELOAD); devlink_register(devlink); } @@ -741,16 +788,20 @@ void ice_devlink_destroy_vf_port(struct ice_vf *vf) } /** - * ice_devlink_nvm_snapshot - Capture a snapshot of the Shadow RAM contents + * ice_devlink_nvm_snapshot - Capture a snapshot of the NVM flash contents * @devlink: the devlink instance * @ops: the devlink region being snapshotted * @extack: extended ACK response structure * @data: on exit points to snapshot data buffer * * This function is called in response to the DEVLINK_CMD_REGION_TRIGGER for - * the shadow-ram devlink region. It captures a snapshot of the shadow ram - * contents. This snapshot can later be viewed via the devlink-region - * interface. + * the nvm-flash devlink region. It captures a snapshot of the full NVM flash + * contents, including both banks of flash. This snapshot can later be viewed + * via the devlink-region interface. + * + * It captures the flash using the FLASH_ONLY bit set when reading via + * firmware, so it does not read the current Shadow RAM contents. For that, + * use the shadow-ram region. * * @returns zero on success, and updates the data pointer. Returns a non-zero * error code on failure. @@ -762,9 +813,9 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - enum ice_status status; void *nvm_data; u32 nvm_size; + int status; nvm_size = hw->flash.flash_size; nvm_data = vzalloc(nvm_size); @@ -777,7 +828,7 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, status, hw->adminq.sq_last_status); NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); vfree(nvm_data); - return -EIO; + return status; } status = ice_read_flat_nvm(hw, 0, &nvm_size, nvm_data, false); @@ -787,7 +838,7 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents"); ice_release_nvm(hw); vfree(nvm_data); - return -EIO; + return status; } ice_release_nvm(hw); @@ -798,6 +849,66 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink, } /** + * ice_devlink_sram_snapshot - Capture a snapshot of the Shadow RAM contents + * @devlink: the devlink instance + * @ops: the devlink region being snapshotted + * @extack: extended ACK response structure + * @data: on exit points to snapshot data buffer + * + * This function is called in response to the DEVLINK_CMD_REGION_TRIGGER for + * the shadow-ram devlink region. It captures a snapshot of the shadow ram + * contents. This snapshot can later be viewed via the devlink-region + * interface. + * + * @returns zero on success, and updates the data pointer. Returns a non-zero + * error code on failure. + */ +static int +ice_devlink_sram_snapshot(struct devlink *devlink, + const struct devlink_region_ops __always_unused *ops, + struct netlink_ext_ack *extack, u8 **data) +{ + struct ice_pf *pf = devlink_priv(devlink); + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + u8 *sram_data; + u32 sram_size; + int err; + + sram_size = hw->flash.sr_words * 2u; + sram_data = vzalloc(sram_size); + if (!sram_data) + return -ENOMEM; + + err = ice_acquire_nvm(hw, ICE_RES_READ); + if (err) { + dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n", + err, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore"); + vfree(sram_data); + return err; + } + + /* Read from the Shadow RAM, rather than directly from NVM */ + err = ice_read_flat_nvm(hw, 0, &sram_size, sram_data, true); + if (err) { + dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n", + sram_size, err, hw->adminq.sq_last_status); + NL_SET_ERR_MSG_MOD(extack, + "Failed to read Shadow RAM contents"); + ice_release_nvm(hw); + vfree(sram_data); + return err; + } + + ice_release_nvm(hw); + + *data = sram_data; + + return 0; +} + +/** * ice_devlink_devcaps_snapshot - Capture snapshot of device capabilities * @devlink: the devlink instance * @ops: the devlink region being snapshotted @@ -819,8 +930,8 @@ ice_devlink_devcaps_snapshot(struct devlink *devlink, struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - enum ice_status status; void *devcaps; + int status; devcaps = vzalloc(ICE_AQ_MAX_BUF_LEN); if (!devcaps) @@ -833,7 +944,7 @@ ice_devlink_devcaps_snapshot(struct devlink *devlink, status, hw->adminq.sq_last_status); NL_SET_ERR_MSG_MOD(extack, "Failed to read device capabilities"); vfree(devcaps); - return -EIO; + return status; } *data = (u8 *)devcaps; @@ -847,6 +958,12 @@ static const struct devlink_region_ops ice_nvm_region_ops = { .snapshot = ice_devlink_nvm_snapshot, }; +static const struct devlink_region_ops ice_sram_region_ops = { + .name = "shadow-ram", + .destructor = vfree, + .snapshot = ice_devlink_sram_snapshot, +}; + static const struct devlink_region_ops ice_devcaps_region_ops = { .name = "device-caps", .destructor = vfree, @@ -864,7 +981,7 @@ void ice_devlink_init_regions(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); struct device *dev = ice_pf_to_dev(pf); - u64 nvm_size; + u64 nvm_size, sram_size; nvm_size = pf->hw.flash.flash_size; pf->nvm_region = devlink_region_create(devlink, &ice_nvm_region_ops, 1, @@ -875,6 +992,15 @@ void ice_devlink_init_regions(struct ice_pf *pf) pf->nvm_region = NULL; } + sram_size = pf->hw.flash.sr_words * 2u; + pf->sram_region = devlink_region_create(devlink, &ice_sram_region_ops, + 1, sram_size); + if (IS_ERR(pf->sram_region)) { + dev_err(dev, "failed to create shadow-ram devlink region, err %ld\n", + PTR_ERR(pf->sram_region)); + pf->sram_region = NULL; + } + pf->devcaps_region = devlink_region_create(devlink, &ice_devcaps_region_ops, 10, ICE_AQ_MAX_BUF_LEN); @@ -895,6 +1021,10 @@ void ice_devlink_destroy_regions(struct ice_pf *pf) { if (pf->nvm_region) devlink_region_destroy(pf->nvm_region); + + if (pf->sram_region) + devlink_region_destroy(pf->sram_region); + if (pf->devcaps_region) devlink_region_destroy(pf->devcaps_region); } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 5af2faaa21e1..e2e3ef7fba7f 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -270,9 +270,8 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom, struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - enum ice_status status; struct device *dev; - int ret = 0; + int ret; u8 *buf; dev = ice_pf_to_dev(pf); @@ -285,22 +284,18 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom, if (!buf) return -ENOMEM; - status = ice_acquire_nvm(hw, ICE_RES_READ); - if (status) { - dev_err(dev, "ice_acquire_nvm failed, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - ret = -EIO; + ret = ice_acquire_nvm(hw, ICE_RES_READ); + if (ret) { + dev_err(dev, "ice_acquire_nvm failed, err %d aq_err %s\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); goto out; } - status = ice_read_flat_nvm(hw, eeprom->offset, &eeprom->len, buf, - false); - if (status) { - dev_err(dev, "ice_read_flat_nvm failed, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - ret = -EIO; + ret = ice_read_flat_nvm(hw, eeprom->offset, &eeprom->len, buf, + false); + if (ret) { + dev_err(dev, "ice_read_flat_nvm failed, err %d aq_err %s\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); goto release; } @@ -342,14 +337,14 @@ static bool ice_active_vfs(struct ice_pf *pf) static u64 ice_link_test(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); - enum ice_status status; bool link_up = false; + int status; netdev_info(netdev, "link test\n"); status = ice_get_link_status(np->vsi->port_info, &link_up); if (status) { - netdev_err(netdev, "link query error, status = %s\n", - ice_stat_str(status)); + netdev_err(netdev, "link query error, status = %d\n", + status); return 1; } @@ -1052,8 +1047,7 @@ ice_get_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam) struct ice_link_status *link_info; struct ice_vsi *vsi = np->vsi; struct ice_port_info *pi; - enum ice_status status; - int err = 0; + int err; pi = vsi->port_info; @@ -1079,12 +1073,10 @@ ice_get_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam) if (!caps) return -ENOMEM; - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, - caps, NULL); - if (status) { - err = -EAGAIN; + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, + caps, NULL); + if (err) goto done; - } /* Set supported/configured FEC modes based on PHY capability */ if (caps->caps & ICE_AQC_PHY_EN_AUTO_FEC) @@ -1203,7 +1195,7 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) if (test_bit(ICE_FLAG_FW_LLDP_AGENT, change_flags)) { if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) { - enum ice_status status; + int status; /* Disable FW LLDP engine */ status = ice_cfg_lldp_mib_change(&pf->hw, false); @@ -1232,8 +1224,8 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) pf->dcbx_cap &= ~DCB_CAP_DCBX_LLD_MANAGED; pf->dcbx_cap |= DCB_CAP_DCBX_HOST; } else { - enum ice_status status; bool dcbx_agent_status; + int status; if (ice_get_pfc_mode(pf) == ICE_QOS_MODE_DSCP) { clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags); @@ -1288,8 +1280,10 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) } if (test_bit(ICE_FLAG_LEGACY_RX, change_flags)) { /* down and up VSI so that changes of Rx cfg are reflected. */ - ice_down(vsi); - ice_up(vsi); + if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state)) { + ice_down(vsi); + ice_up(vsi); + } } /* don't allow modification of this flag when a single VF is in * promiscuous mode because it's not supported @@ -1938,8 +1932,7 @@ ice_get_link_ksettings(struct net_device *netdev, struct ice_aqc_get_phy_caps_data *caps; struct ice_link_status *hw_link_info; struct ice_vsi *vsi = np->vsi; - enum ice_status status; - int err = 0; + int err; ethtool_link_ksettings_zero_link_mode(ks, supported); ethtool_link_ksettings_zero_link_mode(ks, advertising); @@ -1990,12 +1983,10 @@ ice_get_link_ksettings(struct net_device *netdev, if (!caps) return -ENOMEM; - status = ice_aq_get_phy_caps(vsi->port_info, false, - ICE_AQC_REPORT_ACTIVE_CFG, caps, NULL); - if (status) { - err = -EIO; + err = ice_aq_get_phy_caps(vsi->port_info, false, + ICE_AQC_REPORT_ACTIVE_CFG, caps, NULL); + if (err) goto done; - } /* Set the advertised flow control based on the PHY capability */ if ((caps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE) && @@ -2027,12 +2018,10 @@ ice_get_link_ksettings(struct net_device *netdev, caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ) ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - status = ice_aq_get_phy_caps(vsi->port_info, false, - ICE_AQC_REPORT_TOPO_CAP_MEDIA, caps, NULL); - if (status) { - err = -EIO; + err = ice_aq_get_phy_caps(vsi->port_info, false, + ICE_AQC_REPORT_TOPO_CAP_MEDIA, caps, NULL); + if (err) goto done; - } /* Set supported FEC modes based on PHY capability */ ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); @@ -2210,11 +2199,10 @@ ice_set_link_ksettings(struct net_device *netdev, struct ice_pf *pf = np->vsi->back; struct ice_port_info *pi; u8 autoneg_changed = 0; - enum ice_status status; u64 phy_type_high = 0; u64 phy_type_low = 0; - int err = 0; bool linkup; + int err; pi = np->vsi->port_info; @@ -2234,15 +2222,13 @@ ice_set_link_ksettings(struct net_device *netdev, /* Get the PHY capabilities based on media */ if (ice_fw_supports_report_dflt_cfg(pi->hw)) - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_DFLT_CFG, - phy_caps, NULL); + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_DFLT_CFG, + phy_caps, NULL); else - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, - phy_caps, NULL); - if (status) { - err = -EIO; + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, + phy_caps, NULL); + if (err) goto done; - } /* save autoneg out of ksettings */ autoneg = copy_ks.base.autoneg; @@ -2308,11 +2294,9 @@ ice_set_link_ksettings(struct net_device *netdev, /* Call to get the current link speed */ pi->phy.get_link_info = true; - status = ice_get_link_status(pi, &linkup); - if (status) { - err = -EIO; + err = ice_get_link_status(pi, &linkup); + if (err) goto done; - } curr_link_speed = pi->phy.link_info.link_speed; adv_link_speed = ice_ksettings_find_adv_link_speed(ks); @@ -2381,10 +2365,9 @@ ice_set_link_ksettings(struct net_device *netdev, } /* make the aq call */ - status = ice_aq_set_phy_cfg(&pf->hw, pi, &config, NULL); - if (status) { + err = ice_aq_set_phy_cfg(&pf->hw, pi, &config, NULL); + if (err) { netdev_info(netdev, "Set phy config failed,\n"); - err = -EIO; goto done; } @@ -2522,9 +2505,9 @@ static int ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) { struct ice_pf *pf = vsi->back; - enum ice_status status; struct device *dev; u64 hashed_flds; + int status; u32 hdrs; dev = ice_pf_to_dev(pf); @@ -2550,9 +2533,9 @@ ice_set_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc) status = ice_add_rss_cfg(&pf->hw, vsi->idx, hashed_flds, hdrs); if (status) { - dev_dbg(dev, "ice_add_rss_cfg failed, vsi num = %d, error = %s\n", - vsi->vsi_num, ice_stat_str(status)); - return -EINVAL; + dev_dbg(dev, "ice_add_rss_cfg failed, vsi num = %d, error = %d\n", + vsi->vsi_num, status); + return status; } return 0; @@ -2953,7 +2936,7 @@ ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) struct ice_port_info *pi = np->vsi->port_info; struct ice_aqc_get_phy_caps_data *pcaps; struct ice_dcbx_cfg *dcbx_cfg; - enum ice_status status; + int status; /* Initialize pause params */ pause->rx_pause = 0; @@ -3003,11 +2986,10 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) struct ice_vsi *vsi = np->vsi; struct ice_hw *hw = &pf->hw; struct ice_port_info *pi; - enum ice_status status; u8 aq_failures; bool link_up; - int err = 0; u32 is_an; + int err; pi = vsi->port_info; hw_link_info = &pi->phy.link_info; @@ -3033,11 +3015,11 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) return -ENOMEM; /* Get current PHY config */ - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, pcaps, - NULL); - if (status) { + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, pcaps, + NULL); + if (err) { kfree(pcaps); - return -EIO; + return err; } is_an = ice_is_phy_caps_an_enabled(pcaps) ? AUTONEG_ENABLE : @@ -3073,22 +3055,19 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) return -EINVAL; /* Set the FC mode and only restart AN if link is up */ - status = ice_set_fc(pi, &aq_failures, link_up); + err = ice_set_fc(pi, &aq_failures, link_up); if (aq_failures & ICE_SET_FC_AQ_FAIL_GET) { - netdev_info(netdev, "Set fc failed on the get_phy_capabilities call with err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + netdev_info(netdev, "Set fc failed on the get_phy_capabilities call with err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); err = -EAGAIN; } else if (aq_failures & ICE_SET_FC_AQ_FAIL_SET) { - netdev_info(netdev, "Set fc failed on the set_phy_config call with err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + netdev_info(netdev, "Set fc failed on the set_phy_config call with err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); err = -EAGAIN; } else if (aq_failures & ICE_SET_FC_AQ_FAIL_UPDATE) { - netdev_info(netdev, "Set fc failed on the get_link_info call with err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + netdev_info(netdev, "Set fc failed on the get_link_info call with err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); err = -EAGAIN; } @@ -3928,16 +3907,16 @@ ice_get_module_info(struct net_device *netdev, struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - enum ice_status status; u8 sff8472_comp = 0; u8 sff8472_swap = 0; u8 sff8636_rev = 0; u8 value = 0; + int status; status = ice_aq_sff_eeprom(hw, 0, ICE_I2C_EEPROM_DEV_ADDR, 0x00, 0x00, 0, &value, 1, 0, NULL); if (status) - return -EIO; + return status; switch (value) { case ICE_MODULE_TYPE_SFP: @@ -3945,12 +3924,12 @@ ice_get_module_info(struct net_device *netdev, ICE_MODULE_SFF_8472_COMP, 0x00, 0, &sff8472_comp, 1, 0, NULL); if (status) - return -EIO; + return status; status = ice_aq_sff_eeprom(hw, 0, ICE_I2C_EEPROM_DEV_ADDR, ICE_MODULE_SFF_8472_SWAP, 0x00, 0, &sff8472_swap, 1, 0, NULL); if (status) - return -EIO; + return status; if (sff8472_swap & ICE_MODULE_SFF_ADDR_MODE) { modinfo->type = ETH_MODULE_SFF_8079; @@ -3970,7 +3949,7 @@ ice_get_module_info(struct net_device *netdev, ICE_MODULE_REVISION_ADDR, 0x00, 0, &sff8636_rev, 1, 0, NULL); if (status) - return -EIO; + return status; /* Check revision compliance */ if (sff8636_rev > 0x02) { /* Module is SFF-8636 compliant */ @@ -4005,11 +3984,11 @@ ice_get_module_eeprom(struct net_device *netdev, struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - enum ice_status status; bool is_sfp = false; unsigned int i, j; u16 offset = 0; u8 page = 0; + int status; if (!ee || !ee->len || !data) return -EINVAL; @@ -4017,7 +3996,7 @@ ice_get_module_eeprom(struct net_device *netdev, status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, 0, value, 1, 0, NULL); if (status) - return -EIO; + return status; if (value[0] == ICE_MODULE_TYPE_SFP) is_sfp = true; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 38960bcc384c..bbc64d6ce4cd 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -530,7 +530,6 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg, struct ice_flow_prof *prof = NULL; struct ice_fd_hw_prof *hw_prof; struct ice_hw *hw = &pf->hw; - enum ice_status status; u64 entry1_h = 0; u64 entry2_h = 0; u64 prof_id; @@ -581,24 +580,20 @@ ice_fdir_set_hw_fltr_rule(struct ice_pf *pf, struct ice_flow_seg_info *seg, * actions (NULL) and zero actions 0. */ prof_id = flow + tun * ICE_FLTR_PTYPE_MAX; - status = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg, - TNL_SEG_CNT(tun), &prof); - if (status) - return ice_status_to_errno(status); - status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx, - main_vsi->idx, ICE_FLOW_PRIO_NORMAL, - seg, &entry1_h); - if (status) { - err = ice_status_to_errno(status); + err = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg, + TNL_SEG_CNT(tun), &prof); + if (err) + return err; + err = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx, + main_vsi->idx, ICE_FLOW_PRIO_NORMAL, + seg, &entry1_h); + if (err) goto err_prof; - } - status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx, - ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL, - seg, &entry2_h); - if (status) { - err = ice_status_to_errno(status); + err = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, main_vsi->idx, + ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL, + seg, &entry2_h); + if (err) goto err_entry; - } hw_prof->fdir_seg[tun] = seg; hw_prof->entry_h[0][tun] = entry1_h; @@ -1190,7 +1185,6 @@ ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add, struct ice_hw *hw = &pf->hw; struct ice_fltr_desc desc; struct ice_vsi *ctrl_vsi; - enum ice_status status; u8 *pkt, *frag_pkt; bool has_frag; int err; @@ -1209,11 +1203,9 @@ ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add, } ice_fdir_get_prgm_desc(hw, input, &desc, add); - status = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); - if (status) { - err = ice_status_to_errno(status); + err = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); + if (err) goto err_free_all; - } err = ice_prgm_fdir_fltr(ctrl_vsi, &desc, pkt); if (err) goto err_free_all; @@ -1223,12 +1215,10 @@ ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add, if (has_frag) { /* does not return error */ ice_fdir_get_prgm_desc(hw, input, &desc, add); - status = ice_fdir_get_gen_prgm_pkt(hw, input, frag_pkt, true, - is_tun); - if (status) { - err = ice_status_to_errno(status); + err = ice_fdir_get_gen_prgm_pkt(hw, input, frag_pkt, true, + is_tun); + if (err) goto err_frag; - } err = ice_prgm_fdir_fltr(ctrl_vsi, &desc, frag_pkt); if (err) goto err_frag; @@ -1268,7 +1258,7 @@ ice_fdir_write_all_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool is_tun = tun == ICE_FD_HW_SEG_TUN; int err; - if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num)) + if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num, TNL_ALL)) continue; err = ice_fdir_write_fltr(pf, input, add, is_tun); if (err) @@ -1652,7 +1642,7 @@ int ice_add_fdir_ethtool(struct ice_vsi *vsi, struct ethtool_rxnfc *cmd) } /* return error if not an update and no available filters */ - fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port) ? 2 : 1; + fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port, TNL_ALL) ? 2 : 1; if (!ice_fdir_find_fltr_by_idx(hw, fsp->location) && ice_fdir_num_avail_fltr(hw, pf->vsi[vsi->idx]) < fltrs_needed) { dev_err(dev, "Failed to add filter. The maximum number of flow director filters has been reached.\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c index cbd8424631e3..ae089d32ee9d 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_fdir.c @@ -712,7 +712,7 @@ ice_fdir_get_prgm_desc(struct ice_hw *hw, struct ice_fdir_fltr *input, * @hw: pointer to the hardware structure * @cntr_id: returns counter index */ -enum ice_status ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id) +int ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id) { return ice_alloc_res_cntr(hw, ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK, ICE_AQC_RES_TYPE_FLAG_DEDICATED, 1, cntr_id); @@ -723,7 +723,7 @@ enum ice_status ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id) * @hw: pointer to the hardware structure * @cntr_id: counter index to be freed */ -enum ice_status ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id) +int ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id) { return ice_free_res_cntr(hw, ICE_AQC_RES_TYPE_FDIR_COUNTER_BLOCK, ICE_AQC_RES_TYPE_FLAG_DEDICATED, 1, cntr_id); @@ -735,8 +735,7 @@ enum ice_status ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id) * @cntr_id: returns counter index * @num_fltr: number of filter entries to be allocated */ -enum ice_status -ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr) +int ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr) { return ice_alloc_res_cntr(hw, ICE_AQC_RES_TYPE_FDIR_GUARANTEED_ENTRIES, ICE_AQC_RES_TYPE_FLAG_DEDICATED, num_fltr, @@ -749,8 +748,7 @@ ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr) * @cntr_id: returns counter index * @num_fltr: number of filter entries to be allocated */ -enum ice_status -ice_alloc_fd_shrd_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr) +int ice_alloc_fd_shrd_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr) { return ice_alloc_res_cntr(hw, ICE_AQC_RES_TYPE_FDIR_SHARED_ENTRIES, ICE_AQC_RES_TYPE_FLAG_DEDICATED, num_fltr, @@ -872,7 +870,7 @@ static void ice_pkt_insert_mac_addr(u8 *pkt, u8 *addr) * @frag: generate a fragment packet * @tun: true implies generate a tunnel packet */ -enum ice_status +int ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, u8 *pkt, bool frag, bool tun) { @@ -919,15 +917,15 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, if (ice_fdir_pkt[idx].flow == flow) break; if (idx == ICE_FDIR_NUM_PKT) - return ICE_ERR_PARAM; + return -EINVAL; if (!tun) { memcpy(pkt, ice_fdir_pkt[idx].pkt, ice_fdir_pkt[idx].pkt_len); loc = pkt; } else { - if (!ice_get_open_tunnel_port(hw, &tnl_port)) - return ICE_ERR_DOES_NOT_EXIST; + if (!ice_get_open_tunnel_port(hw, &tnl_port, TNL_ALL)) + return -ENOENT; if (!ice_fdir_pkt[idx].tun_pkt) - return ICE_ERR_PARAM; + return -EINVAL; memcpy(pkt, ice_fdir_pkt[idx].tun_pkt, ice_fdir_pkt[idx].tun_pkt_len); ice_pkt_insert_u16(pkt, ICE_IPV4_UDP_DST_PORT_OFFSET, @@ -1111,7 +1109,7 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); break; default: - return ICE_ERR_PARAM; + return -EINVAL; } if (input->flex_fltr) diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h index da4163856f4c..b6c7c6903f35 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.h +++ b/drivers/net/ethernet/intel/ice/ice_fdir.h @@ -201,16 +201,14 @@ struct ice_fdir_base_pkt { const u8 *tun_pkt; }; -enum ice_status ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id); -enum ice_status ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id); -enum ice_status -ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr); -enum ice_status -ice_alloc_fd_shrd_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr); +int ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id); +int ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id); +int ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr); +int ice_alloc_fd_shrd_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr); void ice_fdir_get_prgm_desc(struct ice_hw *hw, struct ice_fdir_fltr *input, struct ice_fltr_desc *fdesc, bool add); -enum ice_status +int ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, u8 *pkt, bool frag, bool tun); int ice_get_fdir_cnt_all(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 23cfcceb1536..d29197ab3d02 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -314,6 +314,78 @@ ice_pkg_enum_entry(struct ice_seg *ice_seg, struct ice_pkg_enum *state, } /** + * ice_hw_ptype_ena - check if the PTYPE is enabled or not + * @hw: pointer to the HW structure + * @ptype: the hardware PTYPE + */ +bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype) +{ + return ptype < ICE_FLOW_PTYPE_MAX && + test_bit(ptype, hw->hw_ptype); +} + +/** + * ice_marker_ptype_tcam_handler + * @sect_type: section type + * @section: pointer to section + * @index: index of the Marker PType TCAM entry to be returned + * @offset: pointer to receive absolute offset, always 0 for ptype TCAM sections + * + * This is a callback function that can be passed to ice_pkg_enum_entry. + * Handles enumeration of individual Marker PType TCAM entries. + */ +static void * +ice_marker_ptype_tcam_handler(u32 sect_type, void *section, u32 index, + u32 *offset) +{ + struct ice_marker_ptype_tcam_section *marker_ptype; + + if (sect_type != ICE_SID_RXPARSER_MARKER_PTYPE) + return NULL; + + if (index > ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF) + return NULL; + + if (offset) + *offset = 0; + + marker_ptype = section; + if (index >= le16_to_cpu(marker_ptype->count)) + return NULL; + + return marker_ptype->tcam + index; +} + +/** + * ice_fill_hw_ptype - fill the enabled PTYPE bit information + * @hw: pointer to the HW structure + */ +static void ice_fill_hw_ptype(struct ice_hw *hw) +{ + struct ice_marker_ptype_tcam_entry *tcam; + struct ice_seg *seg = hw->seg; + struct ice_pkg_enum state; + + bitmap_zero(hw->hw_ptype, ICE_FLOW_PTYPE_MAX); + if (!seg) + return; + + memset(&state, 0, sizeof(state)); + + do { + tcam = ice_pkg_enum_entry(seg, &state, + ICE_SID_RXPARSER_MARKER_PTYPE, NULL, + ice_marker_ptype_tcam_handler); + if (tcam && + le16_to_cpu(tcam->addr) < ICE_MARKER_PTYPE_TCAM_ADDR_MAX && + le16_to_cpu(tcam->ptype) < ICE_FLOW_PTYPE_MAX) + set_bit(le16_to_cpu(tcam->ptype), hw->hw_ptype); + + seg = NULL; + } while (tcam); +} + +/** * ice_boost_tcam_handler * @sect_type: section type * @section: pointer to section @@ -358,7 +430,7 @@ ice_boost_tcam_handler(u32 sect_type, void *section, u32 index, u32 *offset) * if it is found. The ice_seg parameter must not be NULL since the first call * to ice_pkg_enum_entry requires a pointer to an actual ice_segment structure. */ -static enum ice_status +static int ice_find_boost_entry(struct ice_seg *ice_seg, u16 addr, struct ice_boost_tcam_entry **entry) { @@ -368,7 +440,7 @@ ice_find_boost_entry(struct ice_seg *ice_seg, u16 addr, memset(&state, 0, sizeof(state)); if (!ice_seg) - return ICE_ERR_PARAM; + return -EINVAL; do { tcam = ice_pkg_enum_entry(ice_seg, &state, @@ -383,7 +455,7 @@ ice_find_boost_entry(struct ice_seg *ice_seg, u16 addr, } while (tcam); *entry = NULL; - return ICE_ERR_CFG; + return -EIO; } /** @@ -549,7 +621,7 @@ static void ice_init_pkg_hints(struct ice_hw *hw, struct ice_seg *ice_seg) * ------------------------------ * Result: key: b01 10 11 11 00 00 */ -static enum ice_status +static int ice_gen_key_word(u8 val, u8 valid, u8 dont_care, u8 nvr_mtch, u8 *key, u8 *key_inv) { @@ -558,7 +630,7 @@ ice_gen_key_word(u8 val, u8 valid, u8 dont_care, u8 nvr_mtch, u8 *key, /* 'dont_care' and 'nvr_mtch' masks cannot overlap */ if ((dont_care ^ nvr_mtch) != (dont_care | nvr_mtch)) - return ICE_ERR_CFG; + return -EIO; *key = 0; *key_inv = 0; @@ -651,7 +723,7 @@ static bool ice_bits_max_set(const u8 *mask, u16 size, u16 max) * dc == NULL --> dc mask is all 0's (no don't care bits) * nm == NULL --> nm mask is all 0's (no never match bits) */ -static enum ice_status +static int ice_set_key(u8 *key, u16 size, u8 *val, u8 *upd, u8 *dc, u8 *nm, u16 off, u16 len) { @@ -660,11 +732,11 @@ ice_set_key(u8 *key, u16 size, u8 *val, u8 *upd, u8 *dc, u8 *nm, u16 off, /* size must be a multiple of 2 bytes. */ if (size % 2) - return ICE_ERR_CFG; + return -EIO; half_size = size / 2; if (off + len > half_size) - return ICE_ERR_CFG; + return -EIO; /* Make sure at most one bit is set in the never match mask. Having more * than one never match mask bit set will cause HW to consume excessive @@ -672,13 +744,13 @@ ice_set_key(u8 *key, u16 size, u8 *val, u8 *upd, u8 *dc, u8 *nm, u16 off, */ #define ICE_NVR_MTCH_BITS_MAX 1 if (nm && !ice_bits_max_set(nm, len, ICE_NVR_MTCH_BITS_MAX)) - return ICE_ERR_CFG; + return -EIO; for (i = 0; i < len; i++) if (ice_gen_key_word(val[i], upd ? upd[i] : 0xff, dc ? dc[i] : 0, nm ? nm[i] : 0, key + off + i, key + half_size + off + i)) - return ICE_ERR_CFG; + return -EIO; return 0; } @@ -692,25 +764,25 @@ ice_set_key(u8 *key, u16 size, u8 *val, u8 *upd, u8 *dc, u8 *nm, u16 off, * or writing of the package. When attempting to obtain write access, the * caller must check for the following two return values: * - * ICE_SUCCESS - Means the caller has acquired the global config lock - * and can perform writing of the package. - * ICE_ERR_AQ_NO_WORK - Indicates another driver has already written the - * package or has found that no update was necessary; in - * this case, the caller can just skip performing any - * update of the package. - */ -static enum ice_status + * 0 - Means the caller has acquired the global config lock + * and can perform writing of the package. + * -EALREADY - Indicates another driver has already written the + * package or has found that no update was necessary; in + * this case, the caller can just skip performing any + * update of the package. + */ +static int ice_acquire_global_cfg_lock(struct ice_hw *hw, enum ice_aq_res_access_type access) { - enum ice_status status; + int status; status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, access, ICE_GLOBAL_CFG_LOCK_TIMEOUT); if (!status) mutex_lock(&ice_global_cfg_lock_sw); - else if (status == ICE_ERR_AQ_NO_WORK) + else if (status == -EALREADY) ice_debug(hw, ICE_DBG_PKG, "Global config lock: No work to do\n"); return status; @@ -735,7 +807,7 @@ static void ice_release_global_cfg_lock(struct ice_hw *hw) * * This function will request ownership of the change lock. */ -enum ice_status +int ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access) { return ice_acquire_res(hw, ICE_CHANGE_LOCK_RES_ID, access, @@ -765,14 +837,14 @@ void ice_release_change_lock(struct ice_hw *hw) * * Download Package (0x0C40) */ -static enum ice_status +static int ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size, bool last_buf, u32 *error_offset, u32 *error_info, struct ice_sq_cd *cd) { struct ice_aqc_download_pkg *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; if (error_offset) *error_offset = 0; @@ -787,7 +859,7 @@ ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); - if (status == ICE_ERR_AQ_ERROR) { + if (status == -EIO) { /* Read error from buffer only when the FW returned an error */ struct ice_aqc_download_pkg_resp *resp; @@ -813,14 +885,14 @@ ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, * * Update Package (0x0C42) */ -static enum ice_status +static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size, bool last_buf, u32 *error_offset, u32 *error_info, struct ice_sq_cd *cd) { struct ice_aqc_download_pkg *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; if (error_offset) *error_offset = 0; @@ -835,7 +907,7 @@ ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, u16 buf_size, cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); - if (status == ICE_ERR_AQ_ERROR) { + if (status == -EIO) { /* Read error from buffer only when the FW returned an error */ struct ice_aqc_download_pkg_resp *resp; @@ -892,11 +964,10 @@ ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, * * Obtains change lock and updates package. */ -static enum ice_status -ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +static int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) { - enum ice_status status; u32 offset, info, i; + int status; status = ice_acquire_change_lock(hw, ICE_RES_WRITE); if (status) @@ -921,6 +992,22 @@ ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) return status; } +static enum ice_ddp_state ice_map_aq_err_to_ddp_state(enum ice_aq_err aq_err) +{ + switch (aq_err) { + case ICE_AQ_RC_ENOSEC: + case ICE_AQ_RC_EBADSIG: + return ICE_DDP_PKG_FILE_SIGNATURE_INVALID; + case ICE_AQ_RC_ESVN: + return ICE_DDP_PKG_FILE_REVISION_TOO_LOW; + case ICE_AQ_RC_EBADMAN: + case ICE_AQ_RC_EBADBUF: + return ICE_DDP_PKG_LOAD_ERROR; + default: + return ICE_DDP_PKG_ERR; + } +} + /** * ice_dwnld_cfg_bufs * @hw: pointer to the hardware structure @@ -931,15 +1018,17 @@ ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count) * to the firmware. Metadata buffers are skipped, and the first metadata buffer * found indicates that the rest of the buffers are all metadata buffers. */ -static enum ice_status +static enum ice_ddp_state ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) { - enum ice_status status; + enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; struct ice_buf_hdr *bh; + enum ice_aq_err err; u32 offset, info, i; + int status; if (!bufs || !count) - return ICE_ERR_PARAM; + return ICE_DDP_PKG_ERR; /* If the first buffer's first section has its metadata bit set * then there are no buffers to be downloaded, and the operation is @@ -947,20 +1036,13 @@ ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) */ bh = (struct ice_buf_hdr *)bufs; if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) - return 0; - - /* reset pkg_dwnld_status in case this function is called in the - * reset/rebuild flow - */ - hw->pkg_dwnld_status = ICE_AQ_RC_OK; + return ICE_DDP_PKG_SUCCESS; status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); if (status) { - if (status == ICE_ERR_AQ_NO_WORK) - hw->pkg_dwnld_status = ICE_AQ_RC_EEXIST; - else - hw->pkg_dwnld_status = hw->adminq.sq_last_status; - return status; + if (status == -EALREADY) + return ICE_DDP_PKG_ALREADY_LOADED; + return ice_map_aq_err_to_ddp_state(hw->adminq.sq_last_status); } for (i = 0; i < count; i++) { @@ -986,11 +1068,11 @@ ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) &offset, &info, NULL); /* Save AQ status from download package */ - hw->pkg_dwnld_status = hw->adminq.sq_last_status; if (status) { ice_debug(hw, ICE_DBG_PKG, "Pkg download failed: err %d off %d inf %d\n", status, offset, info); - + err = hw->adminq.sq_last_status; + state = ice_map_aq_err_to_ddp_state(err); break; } @@ -1000,7 +1082,7 @@ ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) ice_release_global_cfg_lock(hw); - return status; + return state; } /** @@ -1012,7 +1094,7 @@ ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) * * Get Package Info List (0x0C43) */ -static enum ice_status +static int ice_aq_get_pkg_info_list(struct ice_hw *hw, struct ice_aqc_get_pkg_info_resp *pkg_info, u16 buf_size, struct ice_sq_cd *cd) @@ -1031,7 +1113,7 @@ ice_aq_get_pkg_info_list(struct ice_hw *hw, * * Handles the download of a complete package. */ -static enum ice_status +static enum ice_ddp_state ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg) { struct ice_buf_table *ice_buf_tbl; @@ -1062,13 +1144,13 @@ ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg) * * Saves off the package details into the HW structure. */ -static enum ice_status +static enum ice_ddp_state ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) { struct ice_generic_seg_hdr *seg_hdr; if (!pkg_hdr) - return ICE_ERR_PARAM; + return ICE_DDP_PKG_ERR; seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr); if (seg_hdr) { @@ -1082,7 +1164,7 @@ ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) ICE_SID_METADATA); if (!meta) { ice_debug(hw, ICE_DBG_INIT, "Did not find ice metadata section in package\n"); - return ICE_ERR_CFG; + return ICE_DDP_PKG_INVALID_FILE; } hw->pkg_ver = meta->ver; @@ -1104,10 +1186,10 @@ ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) seg_hdr->seg_id); } else { ice_debug(hw, ICE_DBG_INIT, "Did not find ice segment in driver package\n"); - return ICE_ERR_CFG; + return ICE_DDP_PKG_INVALID_FILE; } - return 0; + return ICE_DDP_PKG_SUCCESS; } /** @@ -1116,21 +1198,22 @@ ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) * * Store details of the package currently loaded in HW into the HW structure. */ -static enum ice_status ice_get_pkg_info(struct ice_hw *hw) +static enum ice_ddp_state ice_get_pkg_info(struct ice_hw *hw) { + enum ice_ddp_state state = ICE_DDP_PKG_SUCCESS; struct ice_aqc_get_pkg_info_resp *pkg_info; - enum ice_status status; u16 size; u32 i; size = struct_size(pkg_info, pkg_info, ICE_PKG_CNT); pkg_info = kzalloc(size, GFP_KERNEL); if (!pkg_info) - return ICE_ERR_NO_MEMORY; + return ICE_DDP_PKG_ERR; - status = ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL); - if (status) + if (ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL)) { + state = ICE_DDP_PKG_ERR; goto init_pkg_free_alloc; + } for (i = 0; i < le32_to_cpu(pkg_info->count); i++) { #define ICE_PKG_FLAG_COUNT 4 @@ -1165,7 +1248,7 @@ static enum ice_status ice_get_pkg_info(struct ice_hw *hw) init_pkg_free_alloc: kfree(pkg_info); - return status; + return state; } /** @@ -1176,28 +1259,28 @@ init_pkg_free_alloc: * Verifies various attributes of the package file, including length, format * version, and the requirement of at least one segment. */ -static enum ice_status ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) +static enum ice_ddp_state ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) { u32 seg_count; u32 i; if (len < struct_size(pkg, seg_offset, 1)) - return ICE_ERR_BUF_TOO_SHORT; + return ICE_DDP_PKG_INVALID_FILE; if (pkg->pkg_format_ver.major != ICE_PKG_FMT_VER_MAJ || pkg->pkg_format_ver.minor != ICE_PKG_FMT_VER_MNR || pkg->pkg_format_ver.update != ICE_PKG_FMT_VER_UPD || pkg->pkg_format_ver.draft != ICE_PKG_FMT_VER_DFT) - return ICE_ERR_CFG; + return ICE_DDP_PKG_INVALID_FILE; /* pkg must have at least one segment */ seg_count = le32_to_cpu(pkg->seg_count); if (seg_count < 1) - return ICE_ERR_CFG; + return ICE_DDP_PKG_INVALID_FILE; /* make sure segment array fits in package length */ if (len < struct_size(pkg, seg_offset, seg_count)) - return ICE_ERR_BUF_TOO_SHORT; + return ICE_DDP_PKG_INVALID_FILE; /* all segments must fit within length */ for (i = 0; i < seg_count; i++) { @@ -1206,16 +1289,16 @@ static enum ice_status ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) /* segment header must fit */ if (len < off + sizeof(*seg)) - return ICE_ERR_BUF_TOO_SHORT; + return ICE_DDP_PKG_INVALID_FILE; seg = (struct ice_generic_seg_hdr *)((u8 *)pkg + off); /* segment body must fit */ if (len < off + le32_to_cpu(seg->seg_size)) - return ICE_ERR_BUF_TOO_SHORT; + return ICE_DDP_PKG_INVALID_FILE; } - return 0; + return ICE_DDP_PKG_SUCCESS; } /** @@ -1259,13 +1342,18 @@ static void ice_init_pkg_regs(struct ice_hw *hw) * version must match our ICE_PKG_SUPP_VER_MAJ and ICE_PKG_SUPP_VER_MNR * definitions. */ -static enum ice_status ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) +static enum ice_ddp_state ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) { - if (pkg_ver->major != ICE_PKG_SUPP_VER_MAJ || - pkg_ver->minor != ICE_PKG_SUPP_VER_MNR) - return ICE_ERR_NOT_SUPPORTED; + if (pkg_ver->major > ICE_PKG_SUPP_VER_MAJ || + (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ && + pkg_ver->minor > ICE_PKG_SUPP_VER_MNR)) + return ICE_DDP_PKG_FILE_VERSION_TOO_HIGH; + else if (pkg_ver->major < ICE_PKG_SUPP_VER_MAJ || + (pkg_ver->major == ICE_PKG_SUPP_VER_MAJ && + pkg_ver->minor < ICE_PKG_SUPP_VER_MNR)) + return ICE_DDP_PKG_FILE_VERSION_TOO_LOW; - return 0; + return ICE_DDP_PKG_SUCCESS; } /** @@ -1276,20 +1364,20 @@ static enum ice_status ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) * * This function checks the package version compatibility with driver and NVM */ -static enum ice_status +static enum ice_ddp_state ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg, struct ice_seg **seg) { struct ice_aqc_get_pkg_info_resp *pkg; - enum ice_status status; + enum ice_ddp_state state; u16 size; u32 i; /* Check package version compatibility */ - status = ice_chk_pkg_version(&hw->pkg_ver); - if (status) { + state = ice_chk_pkg_version(&hw->pkg_ver); + if (state) { ice_debug(hw, ICE_DBG_INIT, "Package version check failed.\n"); - return status; + return state; } /* find ICE segment in given package */ @@ -1297,18 +1385,19 @@ ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg, ospkg); if (!*seg) { ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n"); - return ICE_ERR_CFG; + return ICE_DDP_PKG_INVALID_FILE; } /* Check if FW is compatible with the OS package */ size = struct_size(pkg, pkg_info, ICE_PKG_CNT); pkg = kzalloc(size, GFP_KERNEL); if (!pkg) - return ICE_ERR_NO_MEMORY; + return ICE_DDP_PKG_ERR; - status = ice_aq_get_pkg_info_list(hw, pkg, size, NULL); - if (status) + if (ice_aq_get_pkg_info_list(hw, pkg, size, NULL)) { + state = ICE_DDP_PKG_LOAD_ERROR; goto fw_ddp_compat_free_alloc; + } for (i = 0; i < le32_to_cpu(pkg->count); i++) { /* loop till we find the NVM package */ @@ -1318,7 +1407,7 @@ ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg, pkg->pkg_info[i].ver.major || (*seg)->hdr.seg_format_ver.minor > pkg->pkg_info[i].ver.minor) { - status = ICE_ERR_FW_DDP_MISMATCH; + state = ICE_DDP_PKG_FW_MISMATCH; ice_debug(hw, ICE_DBG_INIT, "OS package is not compatible with NVM.\n"); } /* done processing NVM package so break */ @@ -1326,7 +1415,7 @@ ice_chk_pkg_compat(struct ice_hw *hw, struct ice_pkg_hdr *ospkg, } fw_ddp_compat_free_alloc: kfree(pkg); - return status; + return state; } /** @@ -1367,7 +1456,7 @@ ice_sw_fv_handler(u32 sect_type, void *section, u32 index, u32 *offset) * and store the index number in struct ice_switch_info *switch_info * in HW for following use. */ -static enum ice_status ice_get_prof_index_max(struct ice_hw *hw) +static int ice_get_prof_index_max(struct ice_hw *hw) { u16 prof_index = 0, j, max_prof_index = 0; struct ice_pkg_enum state; @@ -1379,7 +1468,7 @@ static enum ice_status ice_get_prof_index_max(struct ice_hw *hw) memset(&state, 0, sizeof(state)); if (!hw->seg) - return ICE_ERR_PARAM; + return -EINVAL; ice_seg = hw->seg; @@ -1410,6 +1499,34 @@ static enum ice_status ice_get_prof_index_max(struct ice_hw *hw) } /** + * ice_get_ddp_pkg_state - get DDP pkg state after download + * @hw: pointer to the HW struct + * @already_loaded: indicates if pkg was already loaded onto the device + */ +static enum ice_ddp_state +ice_get_ddp_pkg_state(struct ice_hw *hw, bool already_loaded) +{ + if (hw->pkg_ver.major == hw->active_pkg_ver.major && + hw->pkg_ver.minor == hw->active_pkg_ver.minor && + hw->pkg_ver.update == hw->active_pkg_ver.update && + hw->pkg_ver.draft == hw->active_pkg_ver.draft && + !memcmp(hw->pkg_name, hw->active_pkg_name, sizeof(hw->pkg_name))) { + if (already_loaded) + return ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED; + else + return ICE_DDP_PKG_SUCCESS; + } else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ || + hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) { + return ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED; + } else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && + hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) { + return ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED; + } else { + return ICE_DDP_PKG_ERR; + } +} + +/** * ice_init_pkg - initialize/download package * @hw: pointer to the hardware structure * @buf: pointer to the package buffer @@ -1434,53 +1551,54 @@ static enum ice_status ice_get_prof_index_max(struct ice_hw *hw) * ice_copy_and_init_pkg() instead of directly calling ice_init_pkg() in this * case. */ -enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) +enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) { + bool already_loaded = false; + enum ice_ddp_state state; struct ice_pkg_hdr *pkg; - enum ice_status status; struct ice_seg *seg; if (!buf || !len) - return ICE_ERR_PARAM; + return ICE_DDP_PKG_ERR; pkg = (struct ice_pkg_hdr *)buf; - status = ice_verify_pkg(pkg, len); - if (status) { + state = ice_verify_pkg(pkg, len); + if (state) { ice_debug(hw, ICE_DBG_INIT, "failed to verify pkg (err: %d)\n", - status); - return status; + state); + return state; } /* initialize package info */ - status = ice_init_pkg_info(hw, pkg); - if (status) - return status; + state = ice_init_pkg_info(hw, pkg); + if (state) + return state; /* before downloading the package, check package version for * compatibility with driver */ - status = ice_chk_pkg_compat(hw, pkg, &seg); - if (status) - return status; + state = ice_chk_pkg_compat(hw, pkg, &seg); + if (state) + return state; /* initialize package hints and then download package */ ice_init_pkg_hints(hw, seg); - status = ice_download_pkg(hw, seg); - if (status == ICE_ERR_AQ_NO_WORK) { + state = ice_download_pkg(hw, seg); + if (state == ICE_DDP_PKG_ALREADY_LOADED) { ice_debug(hw, ICE_DBG_INIT, "package previously loaded - no work.\n"); - status = 0; + already_loaded = true; } /* Get information on the package currently loaded in HW, then make sure * the driver is compatible with this version. */ - if (!status) { - status = ice_get_pkg_info(hw); - if (!status) - status = ice_chk_pkg_version(&hw->active_pkg_ver); + if (!state || state == ICE_DDP_PKG_ALREADY_LOADED) { + state = ice_get_pkg_info(hw); + if (!state) + state = ice_get_ddp_pkg_state(hw, already_loaded); } - if (!status) { + if (ice_is_init_pkg_successful(state)) { hw->seg = seg; /* on successful package download update other required * registers to support the package and fill HW tables @@ -1488,13 +1606,14 @@ enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) */ ice_init_pkg_regs(hw); ice_fill_blk_tbls(hw); + ice_fill_hw_ptype(hw); ice_get_prof_index_max(hw); } else { ice_debug(hw, ICE_DBG_INIT, "package load failed, %d\n", - status); + state); } - return status; + return state; } /** @@ -1520,18 +1639,19 @@ enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) * package buffer, as the new copy will be managed by this function and * related routines. */ -enum ice_status ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len) +enum ice_ddp_state +ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len) { - enum ice_status status; + enum ice_ddp_state state; u8 *buf_copy; if (!buf || !len) - return ICE_ERR_PARAM; + return ICE_DDP_PKG_ERR; buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL); - status = ice_init_pkg(hw, buf_copy, len); - if (status) { + state = ice_init_pkg(hw, buf_copy, len); + if (!ice_is_init_pkg_successful(state)) { /* Free the copy, since we failed to initialize the package */ devm_kfree(ice_hw_to_dev(hw), buf_copy); } else { @@ -1540,7 +1660,23 @@ enum ice_status ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len) hw->pkg_size = len; } - return status; + return state; +} + +/** + * ice_is_init_pkg_successful - check if DDP init was successful + * @state: state of the DDP pkg after download + */ +bool ice_is_init_pkg_successful(enum ice_ddp_state state) +{ + switch (state) { + case ICE_DDP_PKG_SUCCESS: + case ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED: + case ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED: + return true; + default: + return false; + } } /** @@ -1644,7 +1780,7 @@ ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type req_profs, * NOTE: The caller of the function is responsible for freeing the memory * allocated for every list entry. */ -enum ice_status +int ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, unsigned long *bm, struct list_head *fv_list) { @@ -1658,7 +1794,7 @@ ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, memset(&state, 0, sizeof(state)); if (!ids_cnt || !hw->seg) - return ICE_ERR_PARAM; + return -EINVAL; ice_seg = hw->seg; do { @@ -1702,7 +1838,7 @@ ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, } } while (fv); if (list_empty(fv_list)) - return ICE_ERR_CFG; + return -EIO; return 0; err: @@ -1711,7 +1847,7 @@ err: devm_kfree(ice_hw_to_dev(hw), fvl); } - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } /** @@ -1779,7 +1915,7 @@ static void ice_pkg_buf_free(struct ice_hw *hw, struct ice_buf_build *bld) * result in some wasted space in the buffer. * Note: all package contents must be in Little Endian form. */ -static enum ice_status +static int ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count) { struct ice_buf_hdr *buf; @@ -1787,17 +1923,17 @@ ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count) u16 data_end; if (!bld) - return ICE_ERR_PARAM; + return -EINVAL; buf = (struct ice_buf_hdr *)&bld->buf; /* already an active section, can't increase table size */ section_count = le16_to_cpu(buf->section_count); if (section_count > 0) - return ICE_ERR_CFG; + return -EIO; if (bld->reserved_section_table_entries + count > ICE_MAX_S_COUNT) - return ICE_ERR_CFG; + return -EIO; bld->reserved_section_table_entries += count; data_end = le16_to_cpu(buf->data_end) + @@ -1899,9 +2035,11 @@ static struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld) * ice_get_open_tunnel_port - retrieve an open tunnel port * @hw: pointer to the HW structure * @port: returns open port + * @type: type of tunnel, can be TNL_LAST if it doesn't matter */ bool -ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port) +ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port, + enum ice_tunnel_type type) { bool res = false; u16 i; @@ -1909,7 +2047,8 @@ ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port) mutex_lock(&hw->tnl_lock); for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++) - if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port) { + if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port && + (type == TNL_LAST || type == hw->tnl.tbl[i].type)) { *port = hw->tnl.tbl[i].port; res = true; break; @@ -1956,19 +2095,19 @@ static u16 ice_tunnel_idx_to_entry(struct ice_hw *hw, enum ice_tunnel_type type, * creating a package buffer with the tunnel info and issuing an update package * command. */ -static enum ice_status +static int ice_create_tunnel(struct ice_hw *hw, u16 index, enum ice_tunnel_type type, u16 port) { struct ice_boost_tcam_section *sect_rx, *sect_tx; - enum ice_status status = ICE_ERR_MAX_LIMIT; struct ice_buf_build *bld; + int status = -ENOSPC; mutex_lock(&hw->tnl_lock); bld = ice_pkg_buf_alloc(hw); if (!bld) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto ice_create_tunnel_end; } @@ -2027,26 +2166,26 @@ ice_create_tunnel_end: * targeting the specific updates requested and then performing an update * package. */ -static enum ice_status +static int ice_destroy_tunnel(struct ice_hw *hw, u16 index, enum ice_tunnel_type type, u16 port) { struct ice_boost_tcam_section *sect_rx, *sect_tx; - enum ice_status status = ICE_ERR_MAX_LIMIT; struct ice_buf_build *bld; + int status = -ENOSPC; mutex_lock(&hw->tnl_lock); if (WARN_ON(!hw->tnl.tbl[index].valid || hw->tnl.tbl[index].type != type || hw->tnl.tbl[index].port != port)) { - status = ICE_ERR_OUT_OF_RANGE; + status = -EIO; goto ice_destroy_tunnel_end; } bld = ice_pkg_buf_alloc(hw); if (!bld) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto ice_destroy_tunnel_end; } @@ -2094,7 +2233,7 @@ int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; enum ice_tunnel_type tnl_type; - enum ice_status status; + int status; u16 index; tnl_type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? TNL_VXLAN : TNL_GENEVE; @@ -2102,8 +2241,8 @@ int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, status = ice_create_tunnel(&pf->hw, index, tnl_type, ntohs(ti->port)); if (status) { - netdev_err(netdev, "Error adding UDP tunnel - %s\n", - ice_stat_str(status)); + netdev_err(netdev, "Error adding UDP tunnel - %d\n", + status); return -EIO; } @@ -2118,15 +2257,15 @@ int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; enum ice_tunnel_type tnl_type; - enum ice_status status; + int status; tnl_type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? TNL_VXLAN : TNL_GENEVE; status = ice_destroy_tunnel(&pf->hw, ti->hw_priv, tnl_type, ntohs(ti->port)); if (status) { - netdev_err(netdev, "Error removing UDP tunnel - %s\n", - ice_stat_str(status)); + netdev_err(netdev, "Error removing UDP tunnel - %d\n", + status); return -EIO; } @@ -2142,17 +2281,17 @@ int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, * @prot: variable to receive the protocol ID * @off: variable to receive the protocol offset */ -enum ice_status +int ice_find_prot_off(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 fv_idx, u8 *prot, u16 *off) { struct ice_fv_word *fv_ext; if (prof >= hw->blk[blk].es.count) - return ICE_ERR_PARAM; + return -EINVAL; if (fv_idx >= hw->blk[blk].es.fvw) - return ICE_ERR_PARAM; + return -EINVAL; fv_ext = hw->blk[blk].es.t + (prof * hw->blk[blk].es.fvw); @@ -2175,11 +2314,11 @@ ice_find_prot_off(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 fv_idx, * PTG ID that contains it through the PTG parameter, with the value of * ICE_DEFAULT_PTG (0) meaning it is part the default PTG. */ -static enum ice_status +static int ice_ptg_find_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 *ptg) { if (ptype >= ICE_XLT1_CNT || !ptg) - return ICE_ERR_PARAM; + return -EINVAL; *ptg = hw->blk[blk].xlt1.ptypes[ptype].ptg; return 0; @@ -2209,21 +2348,21 @@ static void ice_ptg_alloc_val(struct ice_hw *hw, enum ice_block blk, u8 ptg) * This function will remove the ptype from the specific PTG, and move it to * the default PTG (ICE_DEFAULT_PTG). */ -static enum ice_status +static int ice_ptg_remove_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 ptg) { struct ice_ptg_ptype **ch; struct ice_ptg_ptype *p; if (ptype > ICE_XLT1_CNT - 1) - return ICE_ERR_PARAM; + return -EINVAL; if (!hw->blk[blk].xlt1.ptg_tbl[ptg].in_use) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; /* Should not happen if .in_use is set, bad config */ if (!hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype) - return ICE_ERR_CFG; + return -EIO; /* find the ptype within this PTG, and bypass the link over it */ p = hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype; @@ -2256,17 +2395,17 @@ ice_ptg_remove_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 ptg) * a destination PTG ID of ICE_DEFAULT_PTG (0) will move the ptype to the * default PTG. */ -static enum ice_status +static int ice_ptg_add_mv_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 ptg) { - enum ice_status status; u8 original_ptg; + int status; if (ptype > ICE_XLT1_CNT - 1) - return ICE_ERR_PARAM; + return -EINVAL; if (!hw->blk[blk].xlt1.ptg_tbl[ptg].in_use && ptg != ICE_DEFAULT_PTG) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; status = ice_ptg_find_ptype(hw, blk, ptype, &original_ptg); if (status) @@ -2401,11 +2540,11 @@ ice_match_prop_lst(struct list_head *list1, struct list_head *list2) * This function will lookup the VSI entry in the XLT2 list and return * the VSI group its associated with. */ -static enum ice_status +static int ice_vsig_find_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 *vsig) { if (!vsig || vsi >= ICE_MAX_VSI) - return ICE_ERR_PARAM; + return -EINVAL; /* As long as there's a default or valid VSIG associated with the input * VSI, the functions returns a success. Any handling of VSIG will be @@ -2470,7 +2609,7 @@ static u16 ice_vsig_alloc(struct ice_hw *hw, enum ice_block blk) * for, the list must match exactly, including the order in which the * characteristics are listed. */ -static enum ice_status +static int ice_find_dup_props_vsig(struct ice_hw *hw, enum ice_block blk, struct list_head *chs, u16 *vsig) { @@ -2484,7 +2623,7 @@ ice_find_dup_props_vsig(struct ice_hw *hw, enum ice_block blk, return 0; } - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; } /** @@ -2496,8 +2635,7 @@ ice_find_dup_props_vsig(struct ice_hw *hw, enum ice_block blk, * The function will remove all VSIs associated with the input VSIG and move * them to the DEFAULT_VSIG and mark the VSIG available. */ -static enum ice_status -ice_vsig_free(struct ice_hw *hw, enum ice_block blk, u16 vsig) +static int ice_vsig_free(struct ice_hw *hw, enum ice_block blk, u16 vsig) { struct ice_vsig_prof *dtmp, *del; struct ice_vsig_vsi *vsi_cur; @@ -2505,10 +2643,10 @@ ice_vsig_free(struct ice_hw *hw, enum ice_block blk, u16 vsig) idx = vsig & ICE_VSIG_IDX_M; if (idx >= ICE_MAX_VSIGS) - return ICE_ERR_PARAM; + return -EINVAL; if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; hw->blk[blk].xlt2.vsig_tbl[idx].in_use = false; @@ -2557,7 +2695,7 @@ ice_vsig_free(struct ice_hw *hw, enum ice_block blk, u16 vsig) * The function will remove the input VSI from its VSI group and move it * to the DEFAULT_VSIG. */ -static enum ice_status +static int ice_vsig_remove_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig) { struct ice_vsig_vsi **vsi_head, *vsi_cur, *vsi_tgt; @@ -2566,10 +2704,10 @@ ice_vsig_remove_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig) idx = vsig & ICE_VSIG_IDX_M; if (vsi >= ICE_MAX_VSI || idx >= ICE_MAX_VSIGS) - return ICE_ERR_PARAM; + return -EINVAL; if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; /* entry already in default VSIG, don't have to remove */ if (idx == ICE_DEFAULT_VSIG) @@ -2577,7 +2715,7 @@ ice_vsig_remove_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig) vsi_head = &hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi; if (!(*vsi_head)) - return ICE_ERR_CFG; + return -EIO; vsi_tgt = &hw->blk[blk].xlt2.vsis[vsi]; vsi_cur = (*vsi_head); @@ -2594,7 +2732,7 @@ ice_vsig_remove_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig) /* verify if VSI was removed from group list */ if (!vsi_cur) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; vsi_cur->vsig = ICE_DEFAULT_VSIG; vsi_cur->changed = 1; @@ -2615,24 +2753,24 @@ ice_vsig_remove_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig) * move the entry to the DEFAULT_VSIG, update the original VSIG and * then move entry to the new VSIG. */ -static enum ice_status +static int ice_vsig_add_mv_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig) { struct ice_vsig_vsi *tmp; - enum ice_status status; u16 orig_vsig, idx; + int status; idx = vsig & ICE_VSIG_IDX_M; if (vsi >= ICE_MAX_VSI || idx >= ICE_MAX_VSIGS) - return ICE_ERR_PARAM; + return -EINVAL; /* if VSIG not in use and VSIG is not default type this VSIG * doesn't exist. */ if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use && vsig != ICE_DEFAULT_VSIG) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; status = ice_vsig_find_vsi(hw, blk, vsi, &orig_vsig); if (status) @@ -2738,7 +2876,7 @@ ice_prof_has_mask(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 *masks) * @masks: masks for FV * @prof_id: receives the profile ID */ -static enum ice_status +static int ice_find_prof_id_with_mask(struct ice_hw *hw, enum ice_block blk, struct ice_fv_word *fv, u16 *masks, u8 *prof_id) { @@ -2749,7 +2887,7 @@ ice_find_prof_id_with_mask(struct ice_hw *hw, enum ice_block blk, * field vector and mask. This will cause rule interference. */ if (blk == ICE_BLK_FD) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; for (i = 0; i < (u8)es->count; i++) { u16 off = i * es->fvw; @@ -2765,7 +2903,7 @@ ice_find_prof_id_with_mask(struct ice_hw *hw, enum ice_block blk, return 0; } - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; } /** @@ -2818,14 +2956,14 @@ static bool ice_tcam_ent_rsrc_type(enum ice_block blk, u16 *rsrc_type) * This function allocates a new entry in a Profile ID TCAM for a specific * block. */ -static enum ice_status +static int ice_alloc_tcam_ent(struct ice_hw *hw, enum ice_block blk, bool btm, u16 *tcam_idx) { u16 res_type; if (!ice_tcam_ent_rsrc_type(blk, &res_type)) - return ICE_ERR_PARAM; + return -EINVAL; return ice_alloc_hw_res(hw, res_type, 1, btm, tcam_idx); } @@ -2838,13 +2976,13 @@ ice_alloc_tcam_ent(struct ice_hw *hw, enum ice_block blk, bool btm, * * This function frees an entry in a Profile ID TCAM for a specific block. */ -static enum ice_status +static int ice_free_tcam_ent(struct ice_hw *hw, enum ice_block blk, u16 tcam_idx) { u16 res_type; if (!ice_tcam_ent_rsrc_type(blk, &res_type)) - return ICE_ERR_PARAM; + return -EINVAL; return ice_free_hw_res(hw, res_type, 1, &tcam_idx); } @@ -2858,15 +2996,14 @@ ice_free_tcam_ent(struct ice_hw *hw, enum ice_block blk, u16 tcam_idx) * This function allocates a new profile ID, which also corresponds to a Field * Vector (Extraction Sequence) entry. */ -static enum ice_status -ice_alloc_prof_id(struct ice_hw *hw, enum ice_block blk, u8 *prof_id) +static int ice_alloc_prof_id(struct ice_hw *hw, enum ice_block blk, u8 *prof_id) { - enum ice_status status; u16 res_type; u16 get_prof; + int status; if (!ice_prof_id_rsrc_type(blk, &res_type)) - return ICE_ERR_PARAM; + return -EINVAL; status = ice_alloc_hw_res(hw, res_type, 1, false, &get_prof); if (!status) @@ -2883,14 +3020,13 @@ ice_alloc_prof_id(struct ice_hw *hw, enum ice_block blk, u8 *prof_id) * * This function frees a profile ID, which also corresponds to a Field Vector. */ -static enum ice_status -ice_free_prof_id(struct ice_hw *hw, enum ice_block blk, u8 prof_id) +static int ice_free_prof_id(struct ice_hw *hw, enum ice_block blk, u8 prof_id) { u16 tmp_prof_id = (u16)prof_id; u16 res_type; if (!ice_prof_id_rsrc_type(blk, &res_type)) - return ICE_ERR_PARAM; + return -EINVAL; return ice_free_hw_res(hw, res_type, 1, &tmp_prof_id); } @@ -2901,11 +3037,10 @@ ice_free_prof_id(struct ice_hw *hw, enum ice_block blk, u8 prof_id) * @blk: the block from which to free the profile ID * @prof_id: the profile ID for which to increment the reference count */ -static enum ice_status -ice_prof_inc_ref(struct ice_hw *hw, enum ice_block blk, u8 prof_id) +static int ice_prof_inc_ref(struct ice_hw *hw, enum ice_block blk, u8 prof_id) { if (prof_id > hw->blk[blk].es.count) - return ICE_ERR_PARAM; + return -EINVAL; hw->blk[blk].es.ref_count[prof_id]++; @@ -3022,17 +3157,17 @@ static void ice_init_all_prof_masks(struct ice_hw *hw) * @mask: the 16-bit mask * @mask_idx: variable to receive the mask index */ -static enum ice_status +static int ice_alloc_prof_mask(struct ice_hw *hw, enum ice_block blk, u16 idx, u16 mask, u16 *mask_idx) { bool found_unused = false, found_copy = false; - enum ice_status status = ICE_ERR_MAX_LIMIT; u16 unused_idx = 0, copy_idx = 0; + int status = -ENOSPC; u16 i; if (blk != ICE_BLK_RSS && blk != ICE_BLK_FD) - return ICE_ERR_PARAM; + return -EINVAL; mutex_lock(&hw->blk[blk].masks.lock); @@ -3090,15 +3225,15 @@ err_ice_alloc_prof_mask: * @blk: hardware block * @mask_idx: index of mask */ -static enum ice_status +static int ice_free_prof_mask(struct ice_hw *hw, enum ice_block blk, u16 mask_idx) { if (blk != ICE_BLK_RSS && blk != ICE_BLK_FD) - return ICE_ERR_PARAM; + return -EINVAL; if (!(mask_idx >= hw->blk[blk].masks.first && mask_idx < hw->blk[blk].masks.first + hw->blk[blk].masks.count)) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; mutex_lock(&hw->blk[blk].masks.lock); @@ -3132,14 +3267,14 @@ exit_ice_free_prof_mask: * @blk: hardware block * @prof_id: profile ID */ -static enum ice_status +static int ice_free_prof_masks(struct ice_hw *hw, enum ice_block blk, u16 prof_id) { u32 mask_bm; u16 i; if (blk != ICE_BLK_RSS && blk != ICE_BLK_FD) - return ICE_ERR_PARAM; + return -EINVAL; mask_bm = hw->blk[blk].es.mask_ena[prof_id]; for (i = 0; i < BITS_PER_BYTE * sizeof(mask_bm); i++) @@ -3194,7 +3329,7 @@ static void ice_shutdown_all_prof_masks(struct ice_hw *hw) * @prof_id: profile ID * @masks: masks */ -static enum ice_status +static int ice_update_prof_masking(struct ice_hw *hw, enum ice_block blk, u16 prof_id, u16 *masks) { @@ -3224,7 +3359,7 @@ ice_update_prof_masking(struct ice_hw *hw, enum ice_block blk, u16 prof_id, if (ena_mask & BIT(i)) ice_free_prof_mask(hw, blk, i); - return ICE_ERR_OUT_OF_RANGE; + return -EIO; } /* enable the masks for this profile */ @@ -3266,11 +3401,11 @@ ice_write_es(struct ice_hw *hw, enum ice_block blk, u8 prof_id, * @blk: the block from which to free the profile ID * @prof_id: the profile ID for which to decrement the reference count */ -static enum ice_status +static int ice_prof_dec_ref(struct ice_hw *hw, enum ice_block blk, u8 prof_id) { if (prof_id > hw->blk[blk].es.count) - return ICE_ERR_PARAM; + return -EINVAL; if (hw->blk[blk].es.ref_count[prof_id] > 0) { if (!--hw->blk[blk].es.ref_count[prof_id]) { @@ -3708,7 +3843,7 @@ void ice_clear_hw_tbls(struct ice_hw *hw) * ice_init_hw_tbls - init hardware table memory * @hw: pointer to the hardware structure */ -enum ice_status ice_init_hw_tbls(struct ice_hw *hw) +int ice_init_hw_tbls(struct ice_hw *hw) { u8 i; @@ -3827,7 +3962,7 @@ enum ice_status ice_init_hw_tbls(struct ice_hw *hw) err: ice_free_hw_tbls(hw); - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } /** @@ -3843,7 +3978,7 @@ err: * @nm_msk: never match mask * @key: output of profile ID key */ -static enum ice_status +static int ice_prof_gen_key(struct ice_hw *hw, enum ice_block blk, u8 ptg, u16 vsig, u8 cdid, u16 flags, u8 vl_msk[ICE_TCAM_KEY_VAL_SZ], u8 dc_msk[ICE_TCAM_KEY_VAL_SZ], u8 nm_msk[ICE_TCAM_KEY_VAL_SZ], @@ -3899,7 +4034,7 @@ ice_prof_gen_key(struct ice_hw *hw, enum ice_block blk, u8 ptg, u16 vsig, * @dc_msk: don't care mask * @nm_msk: never match mask */ -static enum ice_status +static int ice_tcam_write_entry(struct ice_hw *hw, enum ice_block blk, u16 idx, u8 prof_id, u8 ptg, u16 vsig, u8 cdid, u16 flags, u8 vl_msk[ICE_TCAM_KEY_VAL_SZ], @@ -3907,7 +4042,7 @@ ice_tcam_write_entry(struct ice_hw *hw, enum ice_block blk, u16 idx, u8 nm_msk[ICE_TCAM_KEY_VAL_SZ]) { struct ice_prof_tcam_entry; - enum ice_status status; + int status; status = ice_prof_gen_key(hw, blk, ptg, vsig, cdid, flags, vl_msk, dc_msk, nm_msk, hw->blk[blk].prof.t[idx].key); @@ -3926,7 +4061,7 @@ ice_tcam_write_entry(struct ice_hw *hw, enum ice_block blk, u16 idx, * @vsig: VSIG to query * @refs: pointer to variable to receive the reference count */ -static enum ice_status +static int ice_vsig_get_ref(struct ice_hw *hw, enum ice_block blk, u16 vsig, u16 *refs) { u16 idx = vsig & ICE_VSIG_IDX_M; @@ -3935,7 +4070,7 @@ ice_vsig_get_ref(struct ice_hw *hw, enum ice_block blk, u16 vsig, u16 *refs) *refs = 0; if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; ptr = hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi; while (ptr) { @@ -3976,7 +4111,7 @@ ice_has_prof_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl) * @bld: the update package buffer build to add to * @chgs: the list of changes to make in hardware */ -static enum ice_status +static int ice_prof_bld_es(struct ice_hw *hw, enum ice_block blk, struct ice_buf_build *bld, struct list_head *chgs) { @@ -3996,7 +4131,7 @@ ice_prof_bld_es(struct ice_hw *hw, enum ice_block blk, sizeof(p->es[0])); if (!p) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; p->count = cpu_to_le16(1); p->offset = cpu_to_le16(tmp->prof_id); @@ -4014,7 +4149,7 @@ ice_prof_bld_es(struct ice_hw *hw, enum ice_block blk, * @bld: the update package buffer build to add to * @chgs: the list of changes to make in hardware */ -static enum ice_status +static int ice_prof_bld_tcam(struct ice_hw *hw, enum ice_block blk, struct ice_buf_build *bld, struct list_head *chgs) { @@ -4030,7 +4165,7 @@ ice_prof_bld_tcam(struct ice_hw *hw, enum ice_block blk, struct_size(p, entry, 1)); if (!p) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; p->count = cpu_to_le16(1); p->entry[0].addr = cpu_to_le16(tmp->tcam_idx); @@ -4050,7 +4185,7 @@ ice_prof_bld_tcam(struct ice_hw *hw, enum ice_block blk, * @bld: the update package buffer build to add to * @chgs: the list of changes to make in hardware */ -static enum ice_status +static int ice_prof_bld_xlt1(enum ice_block blk, struct ice_buf_build *bld, struct list_head *chgs) { @@ -4066,7 +4201,7 @@ ice_prof_bld_xlt1(enum ice_block blk, struct ice_buf_build *bld, struct_size(p, value, 1)); if (!p) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; p->count = cpu_to_le16(1); p->offset = cpu_to_le16(tmp->ptype); @@ -4082,7 +4217,7 @@ ice_prof_bld_xlt1(enum ice_block blk, struct ice_buf_build *bld, * @bld: the update package buffer build to add to * @chgs: the list of changes to make in hardware */ -static enum ice_status +static int ice_prof_bld_xlt2(enum ice_block blk, struct ice_buf_build *bld, struct list_head *chgs) { @@ -4101,7 +4236,7 @@ ice_prof_bld_xlt2(enum ice_block blk, struct ice_buf_build *bld, struct_size(p, value, 1)); if (!p) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; p->count = cpu_to_le16(1); p->offset = cpu_to_le16(tmp->vsi); @@ -4121,18 +4256,18 @@ ice_prof_bld_xlt2(enum ice_block blk, struct ice_buf_build *bld, * @blk: hardware block * @chgs: the list of changes to make in hardware */ -static enum ice_status +static int ice_upd_prof_hw(struct ice_hw *hw, enum ice_block blk, struct list_head *chgs) { struct ice_buf_build *b; struct ice_chs_chg *tmp; - enum ice_status status; u16 pkg_sects; u16 xlt1 = 0; u16 xlt2 = 0; u16 tcam = 0; u16 es = 0; + int status; u16 sects; /* count number of sections we need */ @@ -4164,7 +4299,7 @@ ice_upd_prof_hw(struct ice_hw *hw, enum ice_block blk, /* Build update package buffer */ b = ice_pkg_buf_alloc(hw); if (!b) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; status = ice_pkg_buf_reserve_section(b, sects); if (status) @@ -4201,13 +4336,13 @@ ice_upd_prof_hw(struct ice_hw *hw, enum ice_block blk, */ pkg_sects = ice_pkg_buf_get_active_sections(b); if (!pkg_sects || pkg_sects != sects) { - status = ICE_ERR_INVAL_SIZE; + status = -EINVAL; goto error_tmp; } /* update package */ status = ice_update_pkg(hw, ice_pkg_buf(b), 1); - if (status == ICE_ERR_AQ_ERROR) + if (status == -EIO) ice_debug(hw, ICE_DBG_INIT, "Unable to update HW profile\n"); error_tmp: @@ -4273,7 +4408,7 @@ static const struct ice_fd_src_dst_pair ice_fd_pairs[] = { * @prof_id: profile ID * @es: extraction sequence (length of array is determined by the block) */ -static enum ice_status +static int ice_update_fd_swap(struct ice_hw *hw, u16 prof_id, struct ice_fv_word *es) { DECLARE_BITMAP(pair_list, ICE_FD_SRC_DST_PAIR_COUNT); @@ -4328,7 +4463,7 @@ ice_update_fd_swap(struct ice_hw *hw, u16 prof_id, struct ice_fv_word *es) /* check for room */ if (first_free + 1 < (s8)ice_fd_pairs[index].count) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; /* place in extraction sequence */ for (k = 0; k < ice_fd_pairs[index].count; k++) { @@ -4338,7 +4473,7 @@ ice_update_fd_swap(struct ice_hw *hw, u16 prof_id, struct ice_fv_word *es) ice_fd_pairs[index].off + (k * 2); if (k > first_free) - return ICE_ERR_OUT_OF_RANGE; + return -EIO; /* keep track of non-relevant fields */ mask_sel |= BIT(first_free - k); @@ -4449,7 +4584,7 @@ ice_get_ptype_attrib_info(enum ice_ptype_attrib_type type, * @attr: array of attributes that will be considered * @attr_cnt: number of elements in the attribute array */ -static enum ice_status +static int ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, const struct ice_ptype_attributes *attr, u16 attr_cnt) { @@ -4465,11 +4600,11 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, &prof->attr[prof->ptg_cnt]); if (++prof->ptg_cnt >= ICE_MAX_PTG_PER_PROFILE) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; } if (!found) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; return 0; } @@ -4490,7 +4625,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, * it will not be written until the first call to ice_add_flow that specifies * the ID value used here. */ -enum ice_status +int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, struct ice_fv_word *es, u16 *masks) @@ -4498,9 +4633,9 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE); DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT); struct ice_prof_map *prof; - enum ice_status status; u8 byte = 0; u8 prof_id; + int status; bitmap_zero(ptgs_used, ICE_XLT1_CNT); @@ -4538,7 +4673,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], /* add profile info */ prof = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*prof), GFP_KERNEL); if (!prof) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_ice_add_prof; } @@ -4581,7 +4716,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], */ status = ice_add_prof_attrib(prof, ptg, ptype, attr, attr_cnt); - if (status == ICE_ERR_MAX_LIMIT) + if (status == -ENOSPC) break; if (status) { /* This is simple a PTYPE/PTG with no @@ -4658,14 +4793,13 @@ ice_vsig_prof_id_count(struct ice_hw *hw, enum ice_block blk, u16 vsig) * @blk: hardware block * @idx: the index to release */ -static enum ice_status -ice_rel_tcam_idx(struct ice_hw *hw, enum ice_block blk, u16 idx) +static int ice_rel_tcam_idx(struct ice_hw *hw, enum ice_block blk, u16 idx) { /* Masks to invoke a never match entry */ u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; u8 dc_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFE, 0xFF, 0xFF, 0xFF, 0xFF }; u8 nm_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x01, 0x00, 0x00, 0x00, 0x00 }; - enum ice_status status; + int status; /* write the TCAM entry */ status = ice_tcam_write_entry(hw, blk, idx, 0, 0, 0, 0, 0, vl_msk, @@ -4685,11 +4819,11 @@ ice_rel_tcam_idx(struct ice_hw *hw, enum ice_block blk, u16 idx) * @blk: hardware block * @prof: pointer to profile structure to remove */ -static enum ice_status +static int ice_rem_prof_id(struct ice_hw *hw, enum ice_block blk, struct ice_vsig_prof *prof) { - enum ice_status status; + int status; u16 i; for (i = 0; i < prof->tcam_count; i++) @@ -4698,7 +4832,7 @@ ice_rem_prof_id(struct ice_hw *hw, enum ice_block blk, status = ice_rel_tcam_idx(hw, blk, prof->tcam[i].tcam_idx); if (status) - return ICE_ERR_HW_TABLE; + return -EIO; } return 0; @@ -4711,14 +4845,14 @@ ice_rem_prof_id(struct ice_hw *hw, enum ice_block blk, * @vsig: the VSIG to remove * @chg: the change list */ -static enum ice_status +static int ice_rem_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, struct list_head *chg) { u16 idx = vsig & ICE_VSIG_IDX_M; struct ice_vsig_vsi *vsi_cur; struct ice_vsig_prof *d, *t; - enum ice_status status; + int status; /* remove TCAM entries */ list_for_each_entry_safe(d, t, @@ -4745,7 +4879,7 @@ ice_rem_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); if (!p) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; p->type = ICE_VSIG_REM; p->orig_vsig = vsig; @@ -4768,13 +4902,13 @@ ice_rem_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, * @hdl: profile handle indicating which profile to remove * @chg: list to receive a record of changes */ -static enum ice_status +static int ice_rem_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, struct list_head *chg) { u16 idx = vsig & ICE_VSIG_IDX_M; struct ice_vsig_prof *p, *t; - enum ice_status status; + int status; list_for_each_entry_safe(p, t, &hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst, @@ -4792,7 +4926,7 @@ ice_rem_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, return status; } - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; } /** @@ -4801,12 +4935,11 @@ ice_rem_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, * @blk: hardware block * @id: profile tracking ID */ -static enum ice_status -ice_rem_flow_all(struct ice_hw *hw, enum ice_block blk, u64 id) +static int ice_rem_flow_all(struct ice_hw *hw, enum ice_block blk, u64 id) { struct ice_chs_chg *del, *tmp; - enum ice_status status; struct list_head chg; + int status; u16 i; INIT_LIST_HEAD(&chg); @@ -4842,16 +4975,16 @@ err_ice_rem_flow_all: * previously created through ice_add_prof. If any existing entries * are associated with this profile, they will be removed as well. */ -enum ice_status ice_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 id) +int ice_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 id) { struct ice_prof_map *pmap; - enum ice_status status; + int status; mutex_lock(&hw->blk[blk].es.prof_map_lock); pmap = ice_search_prof_id(hw, blk, id); if (!pmap) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; goto err_ice_rem_prof; } @@ -4878,20 +5011,20 @@ err_ice_rem_prof: * @hdl: profile handle * @chg: change list */ -static enum ice_status +static int ice_get_prof(struct ice_hw *hw, enum ice_block blk, u64 hdl, struct list_head *chg) { - enum ice_status status = 0; struct ice_prof_map *map; struct ice_chs_chg *p; + int status = 0; u16 i; mutex_lock(&hw->blk[blk].es.prof_map_lock); /* Get the details on the profile specified by the handle ID */ map = ice_search_prof_id(hw, blk, hdl); if (!map) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; goto err_ice_get_prof; } @@ -4901,7 +5034,7 @@ ice_get_prof(struct ice_hw *hw, enum ice_block blk, u64 hdl, p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); if (!p) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_ice_get_prof; } @@ -4933,7 +5066,7 @@ err_ice_get_prof: * * This routine makes a copy of the list of profiles in the specified VSIG. */ -static enum ice_status +static int ice_get_profs_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, struct list_head *lst) { @@ -4961,7 +5094,7 @@ err_ice_get_profs_vsig: devm_kfree(ice_hw_to_dev(hw), ent1); } - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } /** @@ -4971,25 +5104,25 @@ err_ice_get_profs_vsig: * @lst: the list to be added to * @hdl: profile handle of entry to add */ -static enum ice_status +static int ice_add_prof_to_lst(struct ice_hw *hw, enum ice_block blk, struct list_head *lst, u64 hdl) { - enum ice_status status = 0; struct ice_prof_map *map; struct ice_vsig_prof *p; + int status = 0; u16 i; mutex_lock(&hw->blk[blk].es.prof_map_lock); map = ice_search_prof_id(hw, blk, hdl); if (!map) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; goto err_ice_add_prof_to_lst; } p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); if (!p) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_ice_add_prof_to_lst; } @@ -5018,17 +5151,17 @@ err_ice_add_prof_to_lst: * @vsig: the VSIG to move the VSI to * @chg: the change list */ -static enum ice_status +static int ice_move_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig, struct list_head *chg) { - enum ice_status status; struct ice_chs_chg *p; u16 orig_vsig; + int status; p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); if (!p) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; status = ice_vsig_find_vsi(hw, blk, vsi, &orig_vsig); if (!status) @@ -5078,13 +5211,13 @@ ice_rem_chg_tcam_ent(struct ice_hw *hw, u16 idx, struct list_head *chg) * * This function appends an enable or disable TCAM entry in the change log */ -static enum ice_status +static int ice_prof_tcam_ena_dis(struct ice_hw *hw, enum ice_block blk, bool enable, u16 vsig, struct ice_tcam_inf *tcam, struct list_head *chg) { - enum ice_status status; struct ice_chs_chg *p; + int status; u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; u8 dc_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0x00, 0x00, 0x00 }; @@ -5117,7 +5250,7 @@ ice_prof_tcam_ena_dis(struct ice_hw *hw, enum ice_block blk, bool enable, /* add TCAM to change list */ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); if (!p) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; status = ice_tcam_write_entry(hw, blk, tcam->tcam_idx, tcam->prof_id, tcam->ptg, vsig, 0, tcam->attr.flags, @@ -5151,13 +5284,13 @@ err_ice_prof_tcam_ena_dis: * @vsig: the VSIG for which to adjust profile priorities * @chg: the change list */ -static enum ice_status +static int ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig, struct list_head *chg) { DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT); struct ice_vsig_prof *t; - enum ice_status status; + int status; u16 idx; bitmap_zero(ptgs_used, ICE_XLT1_CNT); @@ -5222,7 +5355,7 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig, * @rev: true to add entries to the end of the list * @chg: the change list */ -static enum ice_status +static int ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, bool rev, struct list_head *chg) { @@ -5230,26 +5363,26 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, u8 vl_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; u8 dc_msk[ICE_TCAM_KEY_VAL_SZ] = { 0xFF, 0xFF, 0x00, 0x00, 0x00 }; u8 nm_msk[ICE_TCAM_KEY_VAL_SZ] = { 0x00, 0x00, 0x00, 0x00, 0x00 }; - enum ice_status status = 0; struct ice_prof_map *map; struct ice_vsig_prof *t; struct ice_chs_chg *p; u16 vsig_idx, i; + int status = 0; /* Error, if this VSIG already has this profile */ if (ice_has_prof_vsig(hw, blk, vsig, hdl)) - return ICE_ERR_ALREADY_EXISTS; + return -EEXIST; /* new VSIG profile structure */ t = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*t), GFP_KERNEL); if (!t) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; mutex_lock(&hw->blk[blk].es.prof_map_lock); /* Get the details on the profile specified by the handle ID */ map = ice_search_prof_id(hw, blk, hdl); if (!map) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; goto err_ice_add_prof_id_vsig; } @@ -5264,7 +5397,7 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, /* add TCAM to change list */ p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); if (!p) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_ice_add_prof_id_vsig; } @@ -5334,21 +5467,21 @@ err_ice_add_prof_id_vsig: * @hdl: the profile handle of the profile that will be added to the VSIG * @chg: the change list */ -static enum ice_status +static int ice_create_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl, struct list_head *chg) { - enum ice_status status; struct ice_chs_chg *p; u16 new_vsig; + int status; p = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*p), GFP_KERNEL); if (!p) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; new_vsig = ice_vsig_alloc(hw, blk); if (!new_vsig) { - status = ICE_ERR_HW_TABLE; + status = -EIO; goto err_ice_create_prof_id_vsig; } @@ -5384,18 +5517,18 @@ err_ice_create_prof_id_vsig: * @new_vsig: return of new VSIG * @chg: the change list */ -static enum ice_status +static int ice_create_vsig_from_lst(struct ice_hw *hw, enum ice_block blk, u16 vsi, struct list_head *lst, u16 *new_vsig, struct list_head *chg) { struct ice_vsig_prof *t; - enum ice_status status; + int status; u16 vsig; vsig = ice_vsig_alloc(hw, blk); if (!vsig) - return ICE_ERR_HW_TABLE; + return -EIO; status = ice_move_vsi(hw, blk, vsi, vsig, chg); if (status) @@ -5425,8 +5558,8 @@ static bool ice_find_prof_vsig(struct ice_hw *hw, enum ice_block blk, u64 hdl, u16 *vsig) { struct ice_vsig_prof *t; - enum ice_status status; struct list_head lst; + int status; INIT_LIST_HEAD(&lst); @@ -5456,14 +5589,14 @@ ice_find_prof_vsig(struct ice_hw *hw, enum ice_block blk, u64 hdl, u16 *vsig) * profile indicated by the ID parameter for the VSIs specified in the VSI * array. Once successfully called, the flow will be enabled. */ -enum ice_status +int ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl) { struct ice_vsig_prof *tmp1, *del1; struct ice_chs_chg *tmp, *del; struct list_head union_lst; - enum ice_status status; struct list_head chg; + int status; u16 vsig; INIT_LIST_HEAD(&union_lst); @@ -5489,7 +5622,7 @@ ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl) * scenario */ if (ice_has_prof_vsig(hw, blk, vsig, hdl)) { - status = ICE_ERR_ALREADY_EXISTS; + status = -EEXIST; goto err_ice_add_prof_id_flow; } @@ -5597,7 +5730,7 @@ err_ice_add_prof_id_flow: * @lst: list to remove the profile from * @hdl: the profile handle indicating the profile to remove */ -static enum ice_status +static int ice_rem_prof_from_list(struct ice_hw *hw, struct list_head *lst, u64 hdl) { struct ice_vsig_prof *ent, *tmp; @@ -5609,7 +5742,7 @@ ice_rem_prof_from_list(struct ice_hw *hw, struct list_head *lst, u64 hdl) return 0; } - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; } /** @@ -5623,13 +5756,13 @@ ice_rem_prof_from_list(struct ice_hw *hw, struct list_head *lst, u64 hdl) * profile indicated by the ID parameter for the VSIs specified in the VSI * array. Once successfully called, the flow will be disabled. */ -enum ice_status +int ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl) { struct ice_vsig_prof *tmp1, *del1; struct ice_chs_chg *tmp, *del; struct list_head chg, copy; - enum ice_status status; + int status; u16 vsig; INIT_LIST_HEAD(©); @@ -5724,7 +5857,7 @@ ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl) } } } else { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; } /* update hardware tables */ diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 344c2637facd..6cbc29bcb02f 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -18,10 +18,67 @@ #define ICE_PKG_CNT 4 -enum ice_status +enum ice_ddp_state { + /* Indicates that this call to ice_init_pkg + * successfully loaded the requested DDP package + */ + ICE_DDP_PKG_SUCCESS = 0, + + /* Generic error for already loaded errors, it is mapped later to + * the more specific one (one of the next 3) + */ + ICE_DDP_PKG_ALREADY_LOADED = -1, + + /* Indicates that a DDP package of the same version has already been + * loaded onto the device by a previous call or by another PF + */ + ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED = -2, + + /* The device has a DDP package that is not supported by the driver */ + ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED = -3, + + /* The device has a compatible package + * (but different from the request) already loaded + */ + ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED = -4, + + /* The firmware loaded on the device is not compatible with + * the DDP package loaded + */ + ICE_DDP_PKG_FW_MISMATCH = -5, + + /* The DDP package file is invalid */ + ICE_DDP_PKG_INVALID_FILE = -6, + + /* The version of the DDP package provided is higher than + * the driver supports + */ + ICE_DDP_PKG_FILE_VERSION_TOO_HIGH = -7, + + /* The version of the DDP package provided is lower than the + * driver supports + */ + ICE_DDP_PKG_FILE_VERSION_TOO_LOW = -8, + + /* The signature of the DDP package file provided is invalid */ + ICE_DDP_PKG_FILE_SIGNATURE_INVALID = -9, + + /* The DDP package file security revision is too low and not + * supported by firmware + */ + ICE_DDP_PKG_FILE_REVISION_TOO_LOW = -10, + + /* An error occurred in firmware while loading the DDP package */ + ICE_DDP_PKG_LOAD_ERROR = -11, + + /* Other errors */ + ICE_DDP_PKG_ERR = -12 +}; + +int ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access); void ice_release_change_lock(struct ice_hw *hw); -enum ice_status +int ice_find_prot_off(struct ice_hw *hw, enum ice_block blk, u8 prof, u16 fv_idx, u8 *prot, u16 *off); void @@ -29,32 +86,37 @@ ice_get_sw_fv_bitmap(struct ice_hw *hw, enum ice_prof_type type, unsigned long *bm); void ice_init_prof_result_bm(struct ice_hw *hw); -enum ice_status +int ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt, unsigned long *bm, struct list_head *fv_list); bool -ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port); +ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port, + enum ice_tunnel_type type); int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti); -enum ice_status +/* Rx parser PTYPE functions */ +bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype); + +/* XLT2/VSI group functions */ +int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, struct ice_fv_word *es, u16 *masks); -enum ice_status +int ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); -enum ice_status +int ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); -enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buff, u32 len); -enum ice_status +enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buff, u32 len); +enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len); -enum ice_status ice_init_hw_tbls(struct ice_hw *hw); +bool ice_is_init_pkg_successful(enum ice_ddp_state state); +int ice_init_hw_tbls(struct ice_hw *hw); void ice_free_seg(struct ice_hw *hw); void ice_fill_blk_tbls(struct ice_hw *hw); void ice_clear_hw_tbls(struct ice_hw *hw); void ice_free_hw_tbls(struct ice_hw *hw); -enum ice_status -ice_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 id); +int ice_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 id); #endif /* _ICE_FLEX_PIPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index 0f572a36d021..fc087e0b5292 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -160,6 +160,7 @@ struct ice_meta_sect { #define ICE_SID_CDID_KEY_BUILDER_RSS 47 #define ICE_SID_CDID_REDIR_RSS 48 +#define ICE_SID_RXPARSER_MARKER_PTYPE 55 #define ICE_SID_RXPARSER_BOOST_TCAM 56 #define ICE_SID_TXPARSER_BOOST_TCAM 66 @@ -201,6 +202,24 @@ enum ice_sect { ICE_SECT_COUNT }; +/* Packet Type (PTYPE) values */ +#define ICE_PTYPE_MAC_PAY 1 +#define ICE_PTYPE_IPV4_PAY 23 +#define ICE_PTYPE_IPV4_UDP_PAY 24 +#define ICE_PTYPE_IPV4_TCP_PAY 26 +#define ICE_PTYPE_IPV4_SCTP_PAY 27 +#define ICE_PTYPE_IPV6_PAY 89 +#define ICE_PTYPE_IPV6_UDP_PAY 90 +#define ICE_PTYPE_IPV6_TCP_PAY 92 +#define ICE_PTYPE_IPV6_SCTP_PAY 93 +#define ICE_MAC_IPV4_ESP 160 +#define ICE_MAC_IPV6_ESP 161 +#define ICE_MAC_IPV4_AH 162 +#define ICE_MAC_IPV6_AH 163 +#define ICE_MAC_IPV4_NAT_T_ESP 164 +#define ICE_MAC_IPV6_NAT_T_ESP 165 +#define ICE_MAC_IPV4_GTPU 329 +#define ICE_MAC_IPV6_GTPU 330 #define ICE_MAC_IPV4_GTPU_IPV4_FRAG 331 #define ICE_MAC_IPV4_GTPU_IPV4_PAY 332 #define ICE_MAC_IPV4_GTPU_IPV4_UDP_PAY 333 @@ -221,6 +240,10 @@ enum ice_sect { #define ICE_MAC_IPV6_GTPU_IPV6_UDP_PAY 348 #define ICE_MAC_IPV6_GTPU_IPV6_TCP 349 #define ICE_MAC_IPV6_GTPU_IPV6_ICMPV6 350 +#define ICE_MAC_IPV4_PFCP_SESSION 352 +#define ICE_MAC_IPV6_PFCP_SESSION 354 +#define ICE_MAC_IPV4_L2TPV3 360 +#define ICE_MAC_IPV6_L2TPV3 361 /* Attributes that can modify PTYPE definitions. * @@ -329,6 +352,25 @@ struct ice_boost_tcam_section { sizeof(struct ice_boost_tcam_entry), \ sizeof(struct ice_boost_tcam_entry)) +/* package Marker Ptype TCAM entry */ +struct ice_marker_ptype_tcam_entry { +#define ICE_MARKER_PTYPE_TCAM_ADDR_MAX 1024 + __le16 addr; + __le16 ptype; + u8 keys[20]; +}; + +struct ice_marker_ptype_tcam_section { + __le16 count; + __le16 reserved; + struct ice_marker_ptype_tcam_entry tcam[]; +}; + +#define ICE_MAX_MARKER_PTYPE_TCAMS_IN_BUF \ + ICE_MAX_ENTRIES_IN_BUF(struct_size((struct ice_marker_ptype_tcam_section *)0, tcam, 1) - \ + sizeof(struct ice_marker_ptype_tcam_entry), \ + sizeof(struct ice_marker_ptype_tcam_entry)) + struct ice_xlt1_section { __le16 count; __le16 offset; diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index f160672448a0..2c5332953679 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -609,8 +609,6 @@ struct ice_flow_prof_params { ICE_FLOW_SEG_HDR_ESP | ICE_FLOW_SEG_HDR_AH | \ ICE_FLOW_SEG_HDR_NAT_T_ESP) -#define ICE_FLOW_SEG_HDRS_L2_MASK \ - (ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN) #define ICE_FLOW_SEG_HDRS_L3_MASK \ (ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_ARP) #define ICE_FLOW_SEG_HDRS_L4_MASK \ @@ -625,8 +623,7 @@ struct ice_flow_prof_params { * @segs: array of one or more packet segments that describe the flow * @segs_cnt: number of packet segments provided */ -static enum ice_status -ice_flow_val_hdrs(struct ice_flow_seg_info *segs, u8 segs_cnt) +static int ice_flow_val_hdrs(struct ice_flow_seg_info *segs, u8 segs_cnt) { u8 i; @@ -634,12 +631,12 @@ ice_flow_val_hdrs(struct ice_flow_seg_info *segs, u8 segs_cnt) /* Multiple L3 headers */ if (segs[i].hdrs & ICE_FLOW_SEG_HDRS_L3_MASK && !is_power_of_2(segs[i].hdrs & ICE_FLOW_SEG_HDRS_L3_MASK)) - return ICE_ERR_PARAM; + return -EINVAL; /* Multiple L4 headers */ if (segs[i].hdrs & ICE_FLOW_SEG_HDRS_L4_MASK && !is_power_of_2(segs[i].hdrs & ICE_FLOW_SEG_HDRS_L4_MASK)) - return ICE_ERR_PARAM; + return -EINVAL; } return 0; @@ -700,8 +697,7 @@ static u16 ice_flow_calc_seg_sz(struct ice_flow_prof_params *params, u8 seg) * This function identifies the packet types associated with the protocol * headers being present in packet segments of the specified flow profile. */ -static enum ice_status -ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params) +static int ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params) { struct ice_flow_prof *prof; u8 i; @@ -898,7 +894,7 @@ ice_flow_proc_seg_hdrs(struct ice_flow_prof_params *params) * field. It then allocates one or more extraction sequence entries for the * given field, and fill the entries with protocol ID and offset information. */ -static enum ice_status +static int ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params, u8 seg, enum ice_flow_field fld, u64 match) { @@ -1035,7 +1031,7 @@ ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params, prot_id = ICE_PROT_GRE_OF; break; default: - return ICE_ERR_NOT_IMPL; + return -EOPNOTSUPP; } /* Each extraction sequence entry is a word in size, and extracts a @@ -1073,7 +1069,7 @@ ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params, * does not exceed the block's capability */ if (params->es_cnt >= fv_words) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; /* some blocks require a reversed field vector layout */ if (hw->blk[params->blk].es.reverse) @@ -1099,7 +1095,7 @@ ice_flow_xtract_fld(struct ice_hw *hw, struct ice_flow_prof_params *params, * @params: information about the flow to be processed * @seg: index of packet segment whose raw fields are to be extracted */ -static enum ice_status +static int ice_flow_xtract_raws(struct ice_hw *hw, struct ice_flow_prof_params *params, u8 seg) { @@ -1112,12 +1108,12 @@ ice_flow_xtract_raws(struct ice_hw *hw, struct ice_flow_prof_params *params, if (params->prof->segs[seg].raws_cnt > ARRAY_SIZE(params->prof->segs[seg].raws)) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; /* Offsets within the segment headers are not supported */ hdrs_sz = ice_flow_calc_seg_sz(params, seg); if (!hdrs_sz) - return ICE_ERR_PARAM; + return -EINVAL; fv_words = hw->blk[params->blk].es.fvw; @@ -1150,7 +1146,7 @@ ice_flow_xtract_raws(struct ice_hw *hw, struct ice_flow_prof_params *params, */ if (params->es_cnt >= hw->blk[params->blk].es.count || params->es_cnt >= ICE_MAX_FV_WORDS) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; /* some blocks require a reversed field vector layout */ if (hw->blk[params->blk].es.reverse) @@ -1176,12 +1172,12 @@ ice_flow_xtract_raws(struct ice_hw *hw, struct ice_flow_prof_params *params, * This function iterates through all matched fields in the given segments, and * creates an extraction sequence for the fields. */ -static enum ice_status +static int ice_flow_create_xtrct_seq(struct ice_hw *hw, struct ice_flow_prof_params *params) { struct ice_flow_prof *prof = params->prof; - enum ice_status status = 0; + int status = 0; u8 i; for (i = 0; i < prof->segs_cnt; i++) { @@ -1210,10 +1206,10 @@ ice_flow_create_xtrct_seq(struct ice_hw *hw, * @hw: pointer to the HW struct * @params: information about the flow to be processed */ -static enum ice_status +static int ice_flow_proc_segs(struct ice_hw *hw, struct ice_flow_prof_params *params) { - enum ice_status status; + int status; status = ice_flow_proc_seg_hdrs(params); if (status) @@ -1229,7 +1225,7 @@ ice_flow_proc_segs(struct ice_hw *hw, struct ice_flow_prof_params *params) status = 0; break; default: - return ICE_ERR_NOT_IMPL; + return -EOPNOTSUPP; } return status; @@ -1329,12 +1325,12 @@ ice_dealloc_flow_entry(struct ice_hw *hw, struct ice_flow_entry *entry) * @blk: classification stage * @entry: flow entry to be removed */ -static enum ice_status +static int ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk, struct ice_flow_entry *entry) { if (!entry) - return ICE_ERR_BAD_PTR; + return -EINVAL; list_del(&entry->l_entry); @@ -1355,27 +1351,27 @@ ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk, * * Assumption: the caller has acquired the lock to the profile list */ -static enum ice_status +static int ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt, struct ice_flow_prof **prof) { struct ice_flow_prof_params *params; - enum ice_status status; + int status; u8 i; if (!prof) - return ICE_ERR_BAD_PTR; + return -EINVAL; params = kzalloc(sizeof(*params), GFP_KERNEL); if (!params) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; params->prof = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*params->prof), GFP_KERNEL); if (!params->prof) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto free_params; } @@ -1432,11 +1428,11 @@ free_params: * * Assumption: the caller has acquired the lock to the profile list */ -static enum ice_status +static int ice_flow_rem_prof_sync(struct ice_hw *hw, enum ice_block blk, struct ice_flow_prof *prof) { - enum ice_status status; + int status; /* Remove all remaining flow entries before removing the flow profile */ if (!list_empty(&prof->entries)) { @@ -1474,11 +1470,11 @@ ice_flow_rem_prof_sync(struct ice_hw *hw, enum ice_block blk, * Assumption: the caller has acquired the lock to the profile list * and the software VSI handle has been validated */ -static enum ice_status +static int ice_flow_assoc_prof(struct ice_hw *hw, enum ice_block blk, struct ice_flow_prof *prof, u16 vsi_handle) { - enum ice_status status = 0; + int status = 0; if (!test_bit(vsi_handle, prof->vsis)) { status = ice_add_prof_id_flow(hw, blk, @@ -1505,11 +1501,11 @@ ice_flow_assoc_prof(struct ice_hw *hw, enum ice_block blk, * Assumption: the caller has acquired the lock to the profile list * and the software VSI handle has been validated */ -static enum ice_status +static int ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk, struct ice_flow_prof *prof, u16 vsi_handle) { - enum ice_status status = 0; + int status = 0; if (test_bit(vsi_handle, prof->vsis)) { status = ice_rem_prof_id_flow(hw, blk, @@ -1536,21 +1532,21 @@ ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk, * @segs_cnt: number of packet segments provided * @prof: stores the returned flow profile added */ -enum ice_status +int ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt, struct ice_flow_prof **prof) { - enum ice_status status; + int status; if (segs_cnt > ICE_FLOW_SEG_MAX) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; if (!segs_cnt) - return ICE_ERR_PARAM; + return -EINVAL; if (!segs) - return ICE_ERR_BAD_PTR; + return -EINVAL; status = ice_flow_val_hdrs(segs, segs_cnt); if (status) @@ -1574,17 +1570,16 @@ ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, * @blk: the block for which the flow profile is to be removed * @prof_id: unique ID of the flow profile to be removed */ -enum ice_status -ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id) +int ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id) { struct ice_flow_prof *prof; - enum ice_status status; + int status; mutex_lock(&hw->fl_profs_locks[blk]); prof = ice_flow_find_prof_id(hw, blk, prof_id); if (!prof) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; goto out; } @@ -1608,34 +1603,34 @@ out: * @data: pointer to a data buffer containing flow entry's match values/masks * @entry_h: pointer to buffer that receives the new flow entry's handle */ -enum ice_status +int ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, u64 entry_id, u16 vsi_handle, enum ice_flow_priority prio, void *data, u64 *entry_h) { struct ice_flow_entry *e = NULL; struct ice_flow_prof *prof; - enum ice_status status; + int status; /* No flow entry data is expected for RSS */ if (!entry_h || (!data && blk != ICE_BLK_RSS)) - return ICE_ERR_BAD_PTR; + return -EINVAL; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; mutex_lock(&hw->fl_profs_locks[blk]); prof = ice_flow_find_prof_id(hw, blk, prof_id); if (!prof) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; } else { /* Allocate memory for the entry being added and associate * the VSI to the found flow profile */ e = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*e), GFP_KERNEL); if (!e) - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; else status = ice_flow_assoc_prof(hw, blk, prof, vsi_handle); } @@ -1654,7 +1649,7 @@ ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, case ICE_BLK_RSS: break; default: - status = ICE_ERR_NOT_IMPL; + status = -EOPNOTSUPP; goto out; } @@ -1680,15 +1675,14 @@ out: * @blk: classification stage * @entry_h: handle to the flow entry to be removed */ -enum ice_status ice_flow_rem_entry(struct ice_hw *hw, enum ice_block blk, - u64 entry_h) +int ice_flow_rem_entry(struct ice_hw *hw, enum ice_block blk, u64 entry_h) { struct ice_flow_entry *entry; struct ice_flow_prof *prof; - enum ice_status status = 0; + int status = 0; if (entry_h == ICE_FLOW_ENTRY_HANDLE_INVAL) - return ICE_ERR_PARAM; + return -EINVAL; entry = ICE_FLOW_ENTRY_PTR(entry_h); @@ -1836,7 +1830,7 @@ ice_flow_add_fld_raw(struct ice_flow_seg_info *seg, u16 off, u8 len, * header value to set flow field segment for further use in flow * profile entry or removal. */ -static enum ice_status +static int ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u64 hash_fields, u32 flow_hdr) { @@ -1853,15 +1847,15 @@ ice_flow_set_rss_seg_info(struct ice_flow_seg_info *segs, u64 hash_fields, if (segs->hdrs & ~ICE_FLOW_RSS_SEG_HDR_VAL_MASKS & ~ICE_FLOW_RSS_HDRS_INNER_MASK & ~ICE_FLOW_SEG_HDR_IPV_OTHER) - return ICE_ERR_PARAM; + return -EINVAL; val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L3_MASKS); if (val && !is_power_of_2(val)) - return ICE_ERR_CFG; + return -EIO; val = (u64)(segs->hdrs & ICE_FLOW_RSS_SEG_HDR_L4_MASKS); if (val && !is_power_of_2(val)) - return ICE_ERR_CFG; + return -EIO; return 0; } @@ -1899,14 +1893,14 @@ void ice_rem_vsi_rss_list(struct ice_hw *hw, u16 vsi_handle) * the VSI from that profile. If the flow profile has no VSIs it will * be removed. */ -enum ice_status ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle) +int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle) { const enum ice_block blk = ICE_BLK_RSS; struct ice_flow_prof *p, *t; - enum ice_status status = 0; + int status = 0; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; if (list_empty(&hw->fl_profs[blk])) return 0; @@ -1966,7 +1960,7 @@ ice_rem_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) * * Assumption: lock has already been acquired for RSS list */ -static enum ice_status +static int ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) { struct ice_rss_cfg *r, *rss_cfg; @@ -1981,7 +1975,7 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) rss_cfg = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*rss_cfg), GFP_KERNEL); if (!rss_cfg) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; rss_cfg->hashed_flds = prof->segs[prof->segs_cnt - 1].match; rss_cfg->packet_hdr = prof->segs[prof->segs_cnt - 1].hdrs; @@ -2022,21 +2016,21 @@ ice_add_rss_list(struct ice_hw *hw, u16 vsi_handle, struct ice_flow_prof *prof) * * Assumption: lock has already been acquired for RSS list */ -static enum ice_status +static int ice_add_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, u32 addl_hdrs, u8 segs_cnt) { const enum ice_block blk = ICE_BLK_RSS; struct ice_flow_prof *prof = NULL; struct ice_flow_seg_info *segs; - enum ice_status status; + int status; if (!segs_cnt || segs_cnt > ICE_FLOW_SEG_MAX) - return ICE_ERR_PARAM; + return -EINVAL; segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL); if (!segs) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Construct the packet segment info from the hashed fields */ status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds, @@ -2128,15 +2122,15 @@ exit: * the input fields to hash on, the flow type and use the VSI number to add * a flow entry to the profile. */ -enum ice_status +int ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, u32 addl_hdrs) { - enum ice_status status; + int status; if (hashed_flds == ICE_HASH_INVALID || !ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; mutex_lock(&hw->rss_locks); status = ice_add_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs, @@ -2159,18 +2153,18 @@ ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, * * Assumption: lock has already been acquired for RSS list */ -static enum ice_status +static int ice_rem_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, u32 addl_hdrs, u8 segs_cnt) { const enum ice_block blk = ICE_BLK_RSS; struct ice_flow_seg_info *segs; struct ice_flow_prof *prof; - enum ice_status status; + int status; segs = kcalloc(segs_cnt, sizeof(*segs), GFP_KERNEL); if (!segs) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Construct the packet segment info from the hashed fields */ status = ice_flow_set_rss_seg_info(&segs[segs_cnt - 1], hashed_flds, @@ -2182,7 +2176,7 @@ ice_rem_rss_cfg_sync(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, vsi_handle, ICE_FLOW_FIND_PROF_CHK_FLDS); if (!prof) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; goto out; } @@ -2216,15 +2210,15 @@ out: * removed. Calls are made to underlying flow s which will APIs * turn build or update buffers for RSS XLT1 section. */ -enum ice_status __maybe_unused +int __maybe_unused ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, u32 addl_hdrs) { - enum ice_status status; + int status; if (hashed_flds == ICE_HASH_INVALID || !ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; mutex_lock(&hw->rss_locks); status = ice_rem_rss_cfg_sync(hw, vsi_handle, hashed_flds, addl_hdrs, @@ -2279,20 +2273,19 @@ ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, * message, convert it to ICE-compatible values, and configure RSS flow * profiles. */ -enum ice_status -ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash) +int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash) { - enum ice_status status = 0; + int status = 0; u64 hash_flds; if (avf_hash == ICE_AVF_FLOW_FIELD_INVALID || !ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; /* Make sure no unsupported bits are specified */ if (avf_hash & ~(ICE_FLOW_AVF_RSS_ALL_IPV4_MASKS | ICE_FLOW_AVF_RSS_ALL_IPV6_MASKS)) - return ICE_ERR_CFG; + return -EIO; hash_flds = avf_hash; @@ -2352,7 +2345,7 @@ ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash) } if (rss_hash == ICE_HASH_INVALID) - return ICE_ERR_OUT_OF_RANGE; + return -EIO; status = ice_add_rss_cfg(hw, vsi_handle, rss_hash, ICE_FLOW_SEG_HDR_NONE); @@ -2368,13 +2361,13 @@ ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 avf_hash) * @hw: pointer to the hardware structure * @vsi_handle: software VSI handle */ -enum ice_status ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle) +int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle) { - enum ice_status status = 0; struct ice_rss_cfg *r; + int status = 0; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; mutex_lock(&hw->rss_locks); list_for_each_entry(r, &hw->rss_list_head, l_entry) { diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index 2a2d8c1536cb..d8782b28323e 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -383,18 +383,16 @@ struct ice_rss_cfg { u32 packet_hdr; }; -enum ice_status +int ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, u64 prof_id, struct ice_flow_seg_info *segs, u8 segs_cnt, struct ice_flow_prof **prof); -enum ice_status -ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id); -enum ice_status +int ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id); +int ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, u64 entry_id, u16 vsi, enum ice_flow_priority prio, void *data, u64 *entry_h); -enum ice_status -ice_flow_rem_entry(struct ice_hw *hw, enum ice_block blk, u64 entry_h); +int ice_flow_rem_entry(struct ice_hw *hw, enum ice_block blk, u64 entry_h); void ice_flow_set_fld(struct ice_flow_seg_info *seg, enum ice_flow_field fld, u16 val_loc, u16 mask_loc, u16 last_loc, bool range); @@ -402,14 +400,13 @@ void ice_flow_add_fld_raw(struct ice_flow_seg_info *seg, u16 off, u8 len, u16 val_loc, u16 mask_loc); void ice_rem_vsi_rss_list(struct ice_hw *hw, u16 vsi_handle); -enum ice_status ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle); -enum ice_status -ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds); -enum ice_status ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle); -enum ice_status +int ice_replay_rss_cfg(struct ice_hw *hw, u16 vsi_handle); +int ice_add_avf_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds); +int ice_rem_vsi_rss_cfg(struct ice_hw *hw, u16 vsi_handle); +int ice_add_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, u32 addl_hdrs); -enum ice_status +int ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u64 hashed_flds, u32 addl_hdrs); u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs); diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index c2e78eaf4ccb..94903b450345 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -47,12 +47,69 @@ ice_fltr_add_entry_to_list(struct device *dev, struct ice_fltr_info *info, } /** + * ice_fltr_set_vlan_vsi_promisc + * @hw: pointer to the hardware structure + * @vsi: the VSI being configured + * @promisc_mask: mask of promiscuous config bits + * + * Set VSI with all associated VLANs to given promiscuous mode(s) + */ +int +ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, + u8 promisc_mask) +{ + return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); +} + +/** + * ice_fltr_clear_vlan_vsi_promisc + * @hw: pointer to the hardware structure + * @vsi: the VSI being configured + * @promisc_mask: mask of promiscuous config bits + * + * Clear VSI with all associated VLANs to given promiscuous mode(s) + */ +int +ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, + u8 promisc_mask) +{ + return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); +} + +/** + * ice_fltr_clear_vsi_promisc - clear specified promiscuous mode(s) + * @hw: pointer to the hardware structure + * @vsi_handle: VSI handle to clear mode + * @promisc_mask: mask of promiscuous config bits to clear + * @vid: VLAN ID to clear VLAN promiscuous + */ +int +ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, + u16 vid) +{ + return ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); +} + +/** + * ice_fltr_set_vsi_promisc - set given VSI to given promiscuous mode(s) + * @hw: pointer to the hardware structure + * @vsi_handle: VSI handle to configure + * @promisc_mask: mask of promiscuous config bits + * @vid: VLAN ID to set VLAN promiscuous + */ +int +ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, + u16 vid) +{ + return ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); +} + +/** * ice_fltr_add_mac_list - add list of MAC filters * @vsi: pointer to VSI struct * @list: list of filters */ -enum ice_status -ice_fltr_add_mac_list(struct ice_vsi *vsi, struct list_head *list) +int ice_fltr_add_mac_list(struct ice_vsi *vsi, struct list_head *list) { return ice_add_mac(&vsi->back->hw, list); } @@ -62,8 +119,7 @@ ice_fltr_add_mac_list(struct ice_vsi *vsi, struct list_head *list) * @vsi: pointer to VSI struct * @list: list of filters */ -enum ice_status -ice_fltr_remove_mac_list(struct ice_vsi *vsi, struct list_head *list) +int ice_fltr_remove_mac_list(struct ice_vsi *vsi, struct list_head *list) { return ice_remove_mac(&vsi->back->hw, list); } @@ -73,8 +129,7 @@ ice_fltr_remove_mac_list(struct ice_vsi *vsi, struct list_head *list) * @vsi: pointer to VSI struct * @list: list of filters */ -static enum ice_status -ice_fltr_add_vlan_list(struct ice_vsi *vsi, struct list_head *list) +static int ice_fltr_add_vlan_list(struct ice_vsi *vsi, struct list_head *list) { return ice_add_vlan(&vsi->back->hw, list); } @@ -84,7 +139,7 @@ ice_fltr_add_vlan_list(struct ice_vsi *vsi, struct list_head *list) * @vsi: pointer to VSI struct * @list: list of filters */ -static enum ice_status +static int ice_fltr_remove_vlan_list(struct ice_vsi *vsi, struct list_head *list) { return ice_remove_vlan(&vsi->back->hw, list); @@ -95,8 +150,7 @@ ice_fltr_remove_vlan_list(struct ice_vsi *vsi, struct list_head *list) * @vsi: pointer to VSI struct * @list: list of filters */ -static enum ice_status -ice_fltr_add_eth_list(struct ice_vsi *vsi, struct list_head *list) +static int ice_fltr_add_eth_list(struct ice_vsi *vsi, struct list_head *list) { return ice_add_eth_mac(&vsi->back->hw, list); } @@ -106,8 +160,7 @@ ice_fltr_add_eth_list(struct ice_vsi *vsi, struct list_head *list) * @vsi: pointer to VSI struct * @list: list of filters */ -static enum ice_status -ice_fltr_remove_eth_list(struct ice_vsi *vsi, struct list_head *list) +static int ice_fltr_remove_eth_list(struct ice_vsi *vsi, struct list_head *list) { return ice_remove_eth_mac(&vsi->back->hw, list); } @@ -207,18 +260,17 @@ ice_fltr_add_eth_to_list(struct ice_vsi *vsi, struct list_head *list, * @action: action to be performed on filter match * @mac_action: pointer to add or remove MAC function */ -static enum ice_status +static int ice_fltr_prepare_mac(struct ice_vsi *vsi, const u8 *mac, enum ice_sw_fwd_act_type action, - enum ice_status (*mac_action)(struct ice_vsi *, - struct list_head *)) + int (*mac_action)(struct ice_vsi *, struct list_head *)) { - enum ice_status result; LIST_HEAD(tmp_list); + int result; if (ice_fltr_add_mac_to_list(vsi, &tmp_list, mac, action)) { ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list); - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } result = mac_action(vsi, &tmp_list); @@ -233,21 +285,21 @@ ice_fltr_prepare_mac(struct ice_vsi *vsi, const u8 *mac, * @action: action to be performed on filter match * @mac_action: pointer to add or remove MAC function */ -static enum ice_status +static int ice_fltr_prepare_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac, enum ice_sw_fwd_act_type action, - enum ice_status(*mac_action) + int(*mac_action) (struct ice_vsi *, struct list_head *)) { u8 broadcast[ETH_ALEN]; - enum ice_status result; LIST_HEAD(tmp_list); + int result; eth_broadcast_addr(broadcast); if (ice_fltr_add_mac_to_list(vsi, &tmp_list, mac, action) || ice_fltr_add_mac_to_list(vsi, &tmp_list, broadcast, action)) { ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list); - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } result = mac_action(vsi, &tmp_list); @@ -262,17 +314,16 @@ ice_fltr_prepare_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac, * @action: action to be performed on filter match * @vlan_action: pointer to add or remove VLAN function */ -static enum ice_status +static int ice_fltr_prepare_vlan(struct ice_vsi *vsi, u16 vlan_id, enum ice_sw_fwd_act_type action, - enum ice_status (*vlan_action)(struct ice_vsi *, - struct list_head *)) + int (*vlan_action)(struct ice_vsi *, struct list_head *)) { - enum ice_status result; LIST_HEAD(tmp_list); + int result; if (ice_fltr_add_vlan_to_list(vsi, &tmp_list, vlan_id, action)) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; result = vlan_action(vsi, &tmp_list); ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list); @@ -287,17 +338,16 @@ ice_fltr_prepare_vlan(struct ice_vsi *vsi, u16 vlan_id, * @action: action to be performed on filter match * @eth_action: pointer to add or remove ethertype function */ -static enum ice_status +static int ice_fltr_prepare_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, enum ice_sw_fwd_act_type action, - enum ice_status (*eth_action)(struct ice_vsi *, - struct list_head *)) + int (*eth_action)(struct ice_vsi *, struct list_head *)) { - enum ice_status result; LIST_HEAD(tmp_list); + int result; if (ice_fltr_add_eth_to_list(vsi, &tmp_list, ethertype, flag, action)) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; result = eth_action(vsi, &tmp_list); ice_fltr_free_list(ice_pf_to_dev(vsi->back), &tmp_list); @@ -310,8 +360,8 @@ ice_fltr_prepare_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, * @mac: MAC to add * @action: action to be performed on filter match */ -enum ice_status ice_fltr_add_mac(struct ice_vsi *vsi, const u8 *mac, - enum ice_sw_fwd_act_type action) +int ice_fltr_add_mac(struct ice_vsi *vsi, const u8 *mac, + enum ice_sw_fwd_act_type action) { return ice_fltr_prepare_mac(vsi, mac, action, ice_fltr_add_mac_list); } @@ -322,7 +372,7 @@ enum ice_status ice_fltr_add_mac(struct ice_vsi *vsi, const u8 *mac, * @mac: MAC to add * @action: action to be performed on filter match */ -enum ice_status +int ice_fltr_add_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac, enum ice_sw_fwd_act_type action) { @@ -336,8 +386,8 @@ ice_fltr_add_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac, * @mac: filter MAC to remove * @action: action to remove */ -enum ice_status ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac, - enum ice_sw_fwd_act_type action) +int ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac, + enum ice_sw_fwd_act_type action) { return ice_fltr_prepare_mac(vsi, mac, action, ice_fltr_remove_mac_list); } @@ -348,8 +398,8 @@ enum ice_status ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac, * @vlan_id: VLAN ID to add * @action: action to be performed on filter match */ -enum ice_status ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vlan_id, - enum ice_sw_fwd_act_type action) +int ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vlan_id, + enum ice_sw_fwd_act_type action) { return ice_fltr_prepare_vlan(vsi, vlan_id, action, ice_fltr_add_vlan_list); @@ -361,8 +411,8 @@ enum ice_status ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vlan_id, * @vlan_id: filter VLAN to remove * @action: action to remove */ -enum ice_status ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vlan_id, - enum ice_sw_fwd_act_type action) +int ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vlan_id, + enum ice_sw_fwd_act_type action) { return ice_fltr_prepare_vlan(vsi, vlan_id, action, ice_fltr_remove_vlan_list); @@ -375,8 +425,8 @@ enum ice_status ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vlan_id, * @flag: direction of packet to be filtered, Tx or Rx * @action: action to be performed on filter match */ -enum ice_status ice_fltr_add_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, - enum ice_sw_fwd_act_type action) +int ice_fltr_add_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, + enum ice_sw_fwd_act_type action) { return ice_fltr_prepare_eth(vsi, ethertype, flag, action, ice_fltr_add_eth_list); @@ -389,8 +439,8 @@ enum ice_status ice_fltr_add_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, * @flag: direction of filter * @action: action to remove */ -enum ice_status ice_fltr_remove_eth(struct ice_vsi *vsi, u16 ethertype, - u16 flag, enum ice_sw_fwd_act_type action) +int ice_fltr_remove_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, + enum ice_sw_fwd_act_type action) { return ice_fltr_prepare_eth(vsi, ethertype, flag, action, ice_fltr_remove_eth_list); @@ -406,17 +456,17 @@ enum ice_status ice_fltr_remove_eth(struct ice_vsi *vsi, u16 ethertype, * @src: source VSI * @new_flags: combinations of lb_en and lan_en */ -static enum ice_status +static int ice_fltr_update_rule_flags(struct ice_hw *hw, u16 rule_id, u16 recipe_id, u32 act, u16 type, u16 src, u32 new_flags) { struct ice_aqc_sw_rules_elem *s_rule; - enum ice_status err; u32 flags_mask; + int err; s_rule = kzalloc(ICE_SW_RULE_RX_TX_NO_HDR_SIZE, GFP_KERNEL); if (!s_rule) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; flags_mask = ICE_SINGLE_ACT_LB_ENABLE | ICE_SINGLE_ACT_LAN_ENABLE; act &= ~flags_mask; @@ -465,7 +515,7 @@ static u32 ice_fltr_build_action(u16 vsi_id) * Flags should be a combination of ICE_SINGLE_ACT_LB_ENABLE and * ICE_SINGLE_ACT_LAN_ENABLE. */ -enum ice_status +int ice_fltr_update_flags_dflt_rule(struct ice_vsi *vsi, u16 rule_id, u8 direction, u32 new_flags) { diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.h b/drivers/net/ethernet/intel/ice/ice_fltr.h index 8eec4febead1..0e65fd021ad2 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.h +++ b/drivers/net/ethernet/intel/ice/ice_fltr.h @@ -5,38 +5,52 @@ #define _ICE_FLTR_H_ void ice_fltr_free_list(struct device *dev, struct list_head *h); -enum ice_status +int +ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, + u8 promisc_mask); +int +ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, + u8 promisc_mask); +int +ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, + u16 vid); +int +ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, + u16 vid); +int ice_fltr_add_mac_to_list(struct ice_vsi *vsi, struct list_head *list, const u8 *mac, enum ice_sw_fwd_act_type action); -enum ice_status +int ice_fltr_add_mac(struct ice_vsi *vsi, const u8 *mac, enum ice_sw_fwd_act_type action); -enum ice_status +int ice_fltr_add_mac_and_broadcast(struct ice_vsi *vsi, const u8 *mac, enum ice_sw_fwd_act_type action); -enum ice_status -ice_fltr_add_mac_list(struct ice_vsi *vsi, struct list_head *list); -enum ice_status +int ice_fltr_add_mac_list(struct ice_vsi *vsi, struct list_head *list); +int ice_fltr_remove_mac(struct ice_vsi *vsi, const u8 *mac, enum ice_sw_fwd_act_type action); -enum ice_status -ice_fltr_remove_mac_list(struct ice_vsi *vsi, struct list_head *list); +int ice_fltr_remove_mac_list(struct ice_vsi *vsi, struct list_head *list); -enum ice_status +int ice_fltr_add_vlan(struct ice_vsi *vsi, u16 vid, enum ice_sw_fwd_act_type action); -enum ice_status +int ice_fltr_remove_vlan(struct ice_vsi *vsi, u16 vid, enum ice_sw_fwd_act_type action); -enum ice_status +int ice_fltr_add_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, enum ice_sw_fwd_act_type action); -enum ice_status +int ice_fltr_remove_eth(struct ice_vsi *vsi, u16 ethertype, u16 flag, enum ice_sw_fwd_act_type action); void ice_fltr_remove_all(struct ice_vsi *vsi); -enum ice_status + +int +ice_fltr_update_flags(struct ice_vsi *vsi, u16 rule_id, u16 recipe_id, + u32 new_flags); +int ice_fltr_update_flags_dflt_rule(struct ice_vsi *vsi, u16 rule_id, u8 direction, u32 new_flags); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index f8601d5b0b19..665a344fb9c0 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -16,6 +16,18 @@ struct ice_fwu_priv { /* Track which NVM banks to activate at the end of the update */ u8 activate_flags; + + /* Track the firmware response of the required reset to complete the + * flash update. + * + * 0 - ICE_AQC_NVM_POR_FLAG - A full power on is required + * 1 - ICE_AQC_NVM_PERST_FLAG - A cold PCIe reset is required + * 2 - ICE_AQC_NVM_EMPR_FLAG - An EMP reset is required + */ + u8 reset_level; + + /* Track if EMP reset is available */ + u8 emp_reset_available; }; /** @@ -40,8 +52,8 @@ ice_send_package_data(struct pldmfw *context, const u8 *data, u16 length) struct device *dev = context->dev; struct ice_pf *pf = priv->pf; struct ice_hw *hw = &pf->hw; - enum ice_status status; u8 *package_data; + int status; dev_dbg(dev, "Sending PLDM record package data to firmware\n"); @@ -54,9 +66,8 @@ ice_send_package_data(struct pldmfw *context, const u8 *data, u16 length) kfree(package_data); if (status) { - dev_err(dev, "Failed to send record package data to firmware, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + dev_err(dev, "Failed to send record package data to firmware, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); NL_SET_ERR_MSG_MOD(extack, "Failed to record package data to firmware"); return -EIO; } @@ -203,8 +214,8 @@ ice_send_component_table(struct pldmfw *context, struct pldmfw_component *compon struct device *dev = context->dev; struct ice_pf *pf = priv->pf; struct ice_hw *hw = &pf->hw; - enum ice_status status; size_t length; + int status; switch (component->identifier) { case NVM_COMP_ID_OROM: @@ -240,9 +251,8 @@ ice_send_component_table(struct pldmfw *context, struct pldmfw_component *compon kfree(comp_tbl); if (status) { - dev_err(dev, "Failed to transfer component table to firmware, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + dev_err(dev, "Failed to transfer component table to firmware, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); NL_SET_ERR_MSG_MOD(extack, "Failed to transfer component table to firmware"); return -EIO; } @@ -259,6 +269,7 @@ ice_send_component_table(struct pldmfw *context, struct pldmfw_component *compon * @block_size: size of the block to write, up to 4k * @block: pointer to block of data to write * @last_cmd: whether this is the last command + * @reset_level: storage for reset level required * @extack: netlink extended ACK structure * * Write a block of data to a flash module, and await for the completion @@ -266,18 +277,24 @@ ice_send_component_table(struct pldmfw *context, struct pldmfw_component *compon * * Note this function assumes the caller has acquired the NVM resource. * + * On successful return, reset level indicates the device reset required to + * complete the update. + * + * 0 - ICE_AQC_NVM_POR_FLAG - A full power on is required + * 1 - ICE_AQC_NVM_PERST_FLAG - A cold PCIe reset is required + * 2 - ICE_AQC_NVM_EMPR_FLAG - An EMP reset is required + * * Returns: zero on success, or a negative error code on failure. */ static int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, u16 block_size, u8 *block, bool last_cmd, - struct netlink_ext_ack *extack) + u8 *reset_level, struct netlink_ext_ack *extack) { u16 completion_module, completion_retval; struct device *dev = ice_pf_to_dev(pf); struct ice_rq_event_info event; struct ice_hw *hw = &pf->hw; - enum ice_status status; u32 completion_offset; int err; @@ -286,11 +303,11 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, dev_dbg(dev, "Writing block of %u bytes for module 0x%02x at offset %u\n", block_size, module, offset); - status = ice_aq_update_nvm(hw, module, offset, block_size, block, - last_cmd, 0, NULL); - if (status) { - dev_err(dev, "Failed to flash module 0x%02x with block of size %u at offset %u, err %s aq_err %s\n", - module, block_size, offset, ice_stat_str(status), + err = ice_aq_update_nvm(hw, module, offset, block_size, block, + last_cmd, 0, NULL); + if (err) { + dev_err(dev, "Failed to flash module 0x%02x with block of size %u at offset %u, err %d aq_err %s\n", + module, block_size, offset, err, ice_aq_str(hw->adminq.sq_last_status)); NL_SET_ERR_MSG_MOD(extack, "Failed to program flash module"); return -EIO; @@ -338,6 +355,24 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, return -EIO; } + /* For the last command to write the NVM bank, newer versions of + * firmware indicate the required level of reset to complete + * activation of firmware. If the firmware supports this, cache the + * response for indicating to the user later. Otherwise, assume that + * a full power cycle is required. + */ + if (reset_level && last_cmd && module == ICE_SR_1ST_NVM_BANK_PTR) { + if (hw->dev_caps.common_cap.pcie_reset_avoidance) { + *reset_level = (event.desc.params.nvm.cmd_flags & + ICE_AQC_NVM_RESET_LVL_M); + dev_dbg(dev, "Firmware reported required reset level as %u\n", + *reset_level); + } else { + *reset_level = ICE_AQC_NVM_POR_FLAG; + dev_dbg(dev, "Firmware doesn't support indicating required reset level. Assuming a power cycle is required\n"); + } + } + return 0; } @@ -348,6 +383,7 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, * @component: the name of the component being updated * @image: buffer of image data to write to the NVM * @length: length of the buffer + * @reset_level: storage for reset level required * @extack: netlink extended ACK structure * * Loop over the data for a given NVM module and program it in 4 Kb @@ -360,7 +396,7 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, */ static int ice_write_nvm_module(struct ice_pf *pf, u16 module, const char *component, - const u8 *image, u32 length, + const u8 *image, u32 length, u8 *reset_level, struct netlink_ext_ack *extack) { struct device *dev = ice_pf_to_dev(pf); @@ -394,7 +430,8 @@ ice_write_nvm_module(struct ice_pf *pf, u16 module, const char *component, memcpy(block, image + offset, block_size); err = ice_write_one_nvm_block(pf, module, offset, block_size, - block, last_cmd, extack); + block, last_cmd, reset_level, + extack); if (err) break; @@ -445,7 +482,6 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, struct ice_rq_event_info event; struct ice_hw *hw = &pf->hw; struct devlink *devlink; - enum ice_status status; int err; dev_dbg(dev, "Beginning erase of flash component '%s', module 0x%02x\n", component, module); @@ -456,10 +492,10 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component, devlink_flash_update_timeout_notify(devlink, "Erasing", component, ICE_FW_ERASE_TIMEOUT); - status = ice_aq_erase_nvm(hw, module, NULL); - if (status) { - dev_err(dev, "Failed to erase %s (module 0x%02x), err %s aq_err %s\n", - component, module, ice_stat_str(status), + err = ice_aq_erase_nvm(hw, module, NULL); + if (err) { + dev_err(dev, "Failed to erase %s (module 0x%02x), err %d aq_err %s\n", + component, module, err, ice_aq_str(hw->adminq.sq_last_status)); NL_SET_ERR_MSG_MOD(extack, "Failed to erase flash module"); err = -EIO; @@ -511,6 +547,7 @@ out_notify_devlink: * ice_switch_flash_banks - Tell firmware to switch NVM banks * @pf: Pointer to the PF data structure * @activate_flags: flags used for the activation command + * @emp_reset_available: on return, indicates if EMP reset is available * @extack: netlink extended ACK structure * * Notify firmware to activate the newly written flash banks, and wait for the @@ -518,27 +555,43 @@ out_notify_devlink: * * Returns: zero on success or an error code on failure. */ -static int ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, - struct netlink_ext_ack *extack) +static int +ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, + u8 *emp_reset_available, struct netlink_ext_ack *extack) { struct device *dev = ice_pf_to_dev(pf); struct ice_rq_event_info event; struct ice_hw *hw = &pf->hw; - enum ice_status status; u16 completion_retval; + u8 response_flags; int err; memset(&event, 0, sizeof(event)); - status = ice_nvm_write_activate(hw, activate_flags); - if (status) { - dev_err(dev, "Failed to switch active flash banks, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + err = ice_nvm_write_activate(hw, activate_flags, &response_flags); + if (err) { + dev_err(dev, "Failed to switch active flash banks, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); NL_SET_ERR_MSG_MOD(extack, "Failed to switch active flash banks"); return -EIO; } + /* Newer versions of firmware have support to indicate whether an EMP + * reset to reload firmware is available. For older firmware, EMP + * reset is always available. + */ + if (emp_reset_available) { + if (hw->dev_caps.common_cap.reset_restrict_support) { + *emp_reset_available = response_flags & ICE_AQC_NVM_EMPR_ENA; + dev_dbg(dev, "Firmware indicated that EMP reset is %s\n", + *emp_reset_available ? + "available" : "not available"); + } else { + *emp_reset_available = ICE_AQC_NVM_EMPR_ENA; + dev_dbg(dev, "Firmware does not support restricting EMP reset availability\n"); + } + } + err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, 30 * HZ, &event); if (err) { @@ -579,6 +632,7 @@ ice_flash_component(struct pldmfw *context, struct pldmfw_component *component) struct netlink_ext_ack *extack = priv->extack; struct ice_pf *pf = priv->pf; const char *name; + u8 *reset_level; u16 module; u8 flag; int err; @@ -587,16 +641,19 @@ ice_flash_component(struct pldmfw *context, struct pldmfw_component *component) case NVM_COMP_ID_OROM: module = ICE_SR_1ST_OROM_BANK_PTR; flag = ICE_AQC_NVM_ACTIV_SEL_OROM; + reset_level = NULL; name = "fw.undi"; break; case NVM_COMP_ID_NVM: module = ICE_SR_1ST_NVM_BANK_PTR; flag = ICE_AQC_NVM_ACTIV_SEL_NVM; + reset_level = &priv->reset_level; name = "fw.mgmt"; break; case NVM_COMP_ID_NETLIST: module = ICE_SR_NETLIST_BANK_PTR; flag = ICE_AQC_NVM_ACTIV_SEL_NETLIST; + reset_level = NULL; name = "fw.netlist"; break; default: @@ -616,7 +673,8 @@ ice_flash_component(struct pldmfw *context, struct pldmfw_component *component) return err; return ice_write_nvm_module(pf, module, name, component->component_data, - component->component_size, extack); + component->component_size, reset_level, + extack); } /** @@ -634,110 +692,75 @@ static int ice_finalize_update(struct pldmfw *context) struct ice_fwu_priv *priv = container_of(context, struct ice_fwu_priv, context); struct netlink_ext_ack *extack = priv->extack; struct ice_pf *pf = priv->pf; + struct devlink *devlink; + int err; /* Finally, notify firmware to activate the written NVM banks */ - return ice_switch_flash_banks(pf, priv->activate_flags, extack); -} + err = ice_switch_flash_banks(pf, priv->activate_flags, + &priv->emp_reset_available, extack); + if (err) + return err; -static const struct pldmfw_ops ice_fwu_ops = { - .match_record = &pldmfw_op_pci_match_record, - .send_package_data = &ice_send_package_data, - .send_component_table = &ice_send_component_table, - .flash_component = &ice_flash_component, - .finalize_update = &ice_finalize_update, -}; + devlink = priv_to_devlink(pf); -/** - * ice_flash_pldm_image - Write a PLDM-formatted firmware image to the device - * @pf: private device driver structure - * @fw: firmware object pointing to the relevant firmware file - * @preservation: preservation level to request from firmware - * @extack: netlink extended ACK structure - * - * Parse the data for a given firmware file, verifying that it is a valid PLDM - * formatted image that matches this device. - * - * Extract the device record Package Data and Component Tables and send them - * to the firmware. Extract and write the flash data for each of the three - * main flash components, "fw.mgmt", "fw.undi", and "fw.netlist". Notify - * firmware once the data is written to the inactive banks. - * - * Returns: zero on success or a negative error code on failure. - */ -int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw, - u8 preservation, struct netlink_ext_ack *extack) -{ - struct device *dev = ice_pf_to_dev(pf); - struct ice_hw *hw = &pf->hw; - struct ice_fwu_priv priv; - enum ice_status status; - int err; + /* If the required reset is EMPR, but EMPR is disabled, report that + * a reboot is required instead. + */ + if (priv->reset_level == ICE_AQC_NVM_EMPR_FLAG && + !priv->emp_reset_available) { + dev_dbg(ice_pf_to_dev(pf), "Firmware indicated EMP reset as sufficient, but EMP reset is disabled\n"); + priv->reset_level = ICE_AQC_NVM_PERST_FLAG; + } - switch (preservation) { - case ICE_AQC_NVM_PRESERVE_ALL: - case ICE_AQC_NVM_PRESERVE_SELECTED: - case ICE_AQC_NVM_NO_PRESERVATION: - case ICE_AQC_NVM_FACTORY_DEFAULT: + switch (priv->reset_level) { + case ICE_AQC_NVM_EMPR_FLAG: + devlink_flash_update_status_notify(devlink, + "Activate new firmware by devlink reload", + NULL, 0, 0); break; + case ICE_AQC_NVM_PERST_FLAG: + devlink_flash_update_status_notify(devlink, + "Activate new firmware by rebooting the system", + NULL, 0, 0); + break; + case ICE_AQC_NVM_POR_FLAG: default: - WARN(1, "Unexpected preservation level request %u", preservation); - return -EINVAL; - } - - memset(&priv, 0, sizeof(priv)); - - priv.context.ops = &ice_fwu_ops; - priv.context.dev = dev; - priv.extack = extack; - priv.pf = pf; - priv.activate_flags = preservation; - - status = ice_acquire_nvm(hw, ICE_RES_WRITE); - if (status) { - dev_err(dev, "Failed to acquire device flash lock, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - NL_SET_ERR_MSG_MOD(extack, "Failed to acquire device flash lock"); - return -EIO; - } - - err = pldmfw_flash_image(&priv.context, fw); - if (err == -ENOENT) { - dev_err(dev, "Firmware image has no record matching this device\n"); - NL_SET_ERR_MSG_MOD(extack, "Firmware image has no record matching this device"); - } else if (err) { - /* Do not set a generic extended ACK message here. A more - * specific message may already have been set by one of our - * ops. - */ - dev_err(dev, "Failed to flash PLDM image, err %d", err); + devlink_flash_update_status_notify(devlink, + "Activate new firmware by power cycling the system", + NULL, 0, 0); + break; } - ice_release_nvm(hw); + pf->fw_emp_reset_disabled = !priv->emp_reset_available; - return err; + return 0; } +static const struct pldmfw_ops ice_fwu_ops = { + .match_record = &pldmfw_op_pci_match_record, + .send_package_data = &ice_send_package_data, + .send_component_table = &ice_send_component_table, + .flash_component = &ice_flash_component, + .finalize_update = &ice_finalize_update, +}; + /** - * ice_check_for_pending_update - Check for a pending flash update + * ice_get_pending_updates - Check if the component has a pending update * @pf: the PF driver structure - * @component: if not NULL, the name of the component being updated - * @extack: Netlink extended ACK structure + * @pending: on return, bitmap of updates pending + * @extack: Netlink extended ACK * - * Check whether the device already has a pending flash update. If such an - * update is found, cancel it so that the requested update may proceed. + * Check if the device has any pending updates on any flash components. * - * Returns: zero on success, or a negative error code on failure. + * Returns: zero on success, or a negative error code on failure. Updates + * pending with the bitmap of pending updates. */ -int ice_check_for_pending_update(struct ice_pf *pf, const char *component, - struct netlink_ext_ack *extack) +int ice_get_pending_updates(struct ice_pf *pf, u8 *pending, + struct netlink_ext_ack *extack) { - struct devlink *devlink = priv_to_devlink(pf); struct device *dev = ice_pf_to_dev(pf); struct ice_hw_dev_caps *dev_caps; struct ice_hw *hw = &pf->hw; - enum ice_status status; - u8 pending = 0; int err; dev_caps = kzalloc(sizeof(*dev_caps), GFP_KERNEL); @@ -749,30 +772,60 @@ int ice_check_for_pending_update(struct ice_pf *pf, const char *component, * may have changed, e.g. if an update was previously completed and * the system has not yet rebooted. */ - status = ice_discover_dev_caps(hw, dev_caps); - if (status) { + err = ice_discover_dev_caps(hw, dev_caps); + if (err) { NL_SET_ERR_MSG_MOD(extack, "Unable to read device capabilities"); kfree(dev_caps); - return -EIO; + return err; } + *pending = 0; + if (dev_caps->common_cap.nvm_update_pending_nvm) { dev_info(dev, "The fw.mgmt flash component has a pending update\n"); - pending |= ICE_AQC_NVM_ACTIV_SEL_NVM; + *pending |= ICE_AQC_NVM_ACTIV_SEL_NVM; } if (dev_caps->common_cap.nvm_update_pending_orom) { dev_info(dev, "The fw.undi flash component has a pending update\n"); - pending |= ICE_AQC_NVM_ACTIV_SEL_OROM; + *pending |= ICE_AQC_NVM_ACTIV_SEL_OROM; } if (dev_caps->common_cap.nvm_update_pending_netlist) { dev_info(dev, "The fw.netlist flash component has a pending update\n"); - pending |= ICE_AQC_NVM_ACTIV_SEL_NETLIST; + *pending |= ICE_AQC_NVM_ACTIV_SEL_NETLIST; } kfree(dev_caps); + return 0; +} + +/** + * ice_cancel_pending_update - Cancel any pending update for a component + * @pf: the PF driver structure + * @component: if not NULL, the name of the component being updated + * @extack: Netlink extended ACK structure + * + * Cancel any pending update for the specified component. If component is + * NULL, all device updates will be canceled. + * + * Returns: zero on success, or a negative error code on failure. + */ +static int +ice_cancel_pending_update(struct ice_pf *pf, const char *component, + struct netlink_ext_ack *extack) +{ + struct devlink *devlink = priv_to_devlink(pf); + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + u8 pending; + int err; + + err = ice_get_pending_updates(pf, &pending, extack); + if (err) + return err; + /* If the flash_update request is for a specific component, ignore all * of the other components. */ @@ -798,17 +851,107 @@ int ice_check_for_pending_update(struct ice_pf *pf, const char *component, "Canceling previous pending update", component, 0, 0); - status = ice_acquire_nvm(hw, ICE_RES_WRITE); - if (status) { - dev_err(dev, "Failed to acquire device flash lock, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + err = ice_acquire_nvm(hw, ICE_RES_WRITE); + if (err) { + dev_err(dev, "Failed to acquire device flash lock, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); NL_SET_ERR_MSG_MOD(extack, "Failed to acquire device flash lock"); - return -EIO; + return err; } pending |= ICE_AQC_NVM_REVERT_LAST_ACTIV; - err = ice_switch_flash_banks(pf, pending, extack); + err = ice_switch_flash_banks(pf, pending, NULL, extack); + + ice_release_nvm(hw); + + /* Since we've canceled the pending update, we no longer know if EMP + * reset is restricted. + */ + pf->fw_emp_reset_disabled = false; + + return err; +} + +/** + * ice_devlink_flash_update - Write a firmware image to the device + * @devlink: pointer to devlink associated with the device to update + * @params: devlink flash update parameters + * @extack: netlink extended ACK structure + * + * Parse the data for a given firmware file, verifying that it is a valid PLDM + * formatted image that matches this device. + * + * Extract the device record Package Data and Component Tables and send them + * to the firmware. Extract and write the flash data for each of the three + * main flash components, "fw.mgmt", "fw.undi", and "fw.netlist". Notify + * firmware once the data is written to the inactive banks. + * + * Returns: zero on success or a negative error code on failure. + */ +int ice_devlink_flash_update(struct devlink *devlink, + struct devlink_flash_update_params *params, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + struct ice_fwu_priv priv; + u8 preservation; + int err; + + if (!params->overwrite_mask) { + /* preserve all settings and identifiers */ + preservation = ICE_AQC_NVM_PRESERVE_ALL; + } else if (params->overwrite_mask == DEVLINK_FLASH_OVERWRITE_SETTINGS) { + /* overwrite settings, but preserve the vital device identifiers */ + preservation = ICE_AQC_NVM_PRESERVE_SELECTED; + } else if (params->overwrite_mask == (DEVLINK_FLASH_OVERWRITE_SETTINGS | + DEVLINK_FLASH_OVERWRITE_IDENTIFIERS)) { + /* overwrite both settings and identifiers, preserve nothing */ + preservation = ICE_AQC_NVM_NO_PRESERVATION; + } else { + NL_SET_ERR_MSG_MOD(extack, "Requested overwrite mask is not supported"); + return -EOPNOTSUPP; + } + + if (!hw->dev_caps.common_cap.nvm_unified_update) { + NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update"); + return -EOPNOTSUPP; + } + + memset(&priv, 0, sizeof(priv)); + + priv.context.ops = &ice_fwu_ops; + priv.context.dev = dev; + priv.extack = extack; + priv.pf = pf; + priv.activate_flags = preservation; + + devlink_flash_update_status_notify(devlink, "Preparing to flash", NULL, 0, 0); + + err = ice_cancel_pending_update(pf, NULL, extack); + if (err) + return err; + + err = ice_acquire_nvm(hw, ICE_RES_WRITE); + if (err) { + dev_err(dev, "Failed to acquire device flash lock, err %d aq_err %s\n", + err, ice_aq_str(hw->adminq.sq_last_status)); + NL_SET_ERR_MSG_MOD(extack, "Failed to acquire device flash lock"); + return err; + } + + err = pldmfw_flash_image(&priv.context, params->fw); + if (err == -ENOENT) { + dev_err(dev, "Firmware image has no record matching this device\n"); + NL_SET_ERR_MSG_MOD(extack, "Firmware image has no record matching this device"); + } else if (err) { + /* Do not set a generic extended ACK message here. A more + * specific message may already have been set by one of our + * ops. + */ + dev_err(dev, "Failed to flash PLDM image, err %d", err); + } ice_release_nvm(hw); diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.h b/drivers/net/ethernet/intel/ice/ice_fw_update.h index c6390f6851ff..750574885716 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.h +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.h @@ -4,9 +4,10 @@ #ifndef _ICE_FW_UPDATE_H_ #define _ICE_FW_UPDATE_H_ -int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw, - u8 preservation, struct netlink_ext_ack *extack); -int ice_check_for_pending_update(struct ice_pf *pf, const char *component, - struct netlink_ext_ack *extack); +int ice_devlink_flash_update(struct devlink *devlink, + struct devlink_flash_update_params *params, + struct netlink_ext_ack *extack); +int ice_get_pending_updates(struct ice_pf *pf, u8 *pending, + struct netlink_ext_ack *extack); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 09a3297cd63c..1999b12708de 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -291,7 +291,7 @@ void ice_vsi_delete(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_vsi_ctx *ctxt; - enum ice_status status; + int status; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); if (!ctxt) @@ -305,8 +305,8 @@ void ice_vsi_delete(struct ice_vsi *vsi) status = ice_free_vsi(&pf->hw, vsi->idx, ctxt, false, NULL); if (status) - dev_err(ice_pf_to_dev(pf), "Failed to delete VSI %i in FW - error: %s\n", - vsi->vsi_num, ice_stat_str(status)); + dev_err(ice_pf_to_dev(pf), "Failed to delete VSI %i in FW - error: %d\n", + vsi->vsi_num, status); kfree(ctxt); } @@ -709,15 +709,15 @@ bool ice_is_aux_ena(struct ice_pf *pf) static void ice_vsi_clean_rss_flow_fld(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; - enum ice_status status; + int status; if (ice_is_safe_mode(pf)) return; status = ice_rem_vsi_rss_cfg(&pf->hw, vsi->idx); if (status) - dev_dbg(ice_pf_to_dev(pf), "ice_rem_vsi_rss_cfg failed for vsi = %d, error = %s\n", - vsi->vsi_num, ice_stat_str(status)); + dev_dbg(ice_pf_to_dev(pf), "ice_rem_vsi_rss_cfg failed for vsi = %d, error = %d\n", + vsi->vsi_num, status); } /** @@ -1545,8 +1545,8 @@ ice_vsi_cfg_rss_exit: static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; - enum ice_status status; struct device *dev; + int status; dev = ice_pf_to_dev(pf); if (ice_is_safe_mode(pf)) { @@ -1557,8 +1557,8 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi) status = ice_add_avf_rss_cfg(&pf->hw, vsi->idx, ICE_DEFAULT_RSS_HENA); if (status) - dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %s\n", - vsi->vsi_num, ice_stat_str(status)); + dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %d\n", + vsi->vsi_num, status); } /** @@ -1577,8 +1577,8 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) u16 vsi_handle = vsi->idx, vsi_num = vsi->vsi_num; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - enum ice_status status; struct device *dev; + int status; dev = ice_pf_to_dev(pf); if (ice_is_safe_mode(pf)) { @@ -1590,57 +1590,57 @@ static void ice_vsi_set_rss_flow_fld(struct ice_vsi *vsi) status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4, ICE_FLOW_SEG_HDR_IPV4); if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for ipv4 flow, vsi = %d, error = %s\n", - vsi_num, ice_stat_str(status)); + dev_dbg(dev, "ice_add_rss_cfg failed for ipv4 flow, vsi = %d, error = %d\n", + vsi_num, status); /* configure RSS for IPv6 with input set IPv6 src/dst */ status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6, ICE_FLOW_SEG_HDR_IPV6); if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for ipv6 flow, vsi = %d, error = %s\n", - vsi_num, ice_stat_str(status)); + dev_dbg(dev, "ice_add_rss_cfg failed for ipv6 flow, vsi = %d, error = %d\n", + vsi_num, status); /* configure RSS for tcp4 with input set IP src/dst, TCP src/dst */ status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV4, ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV4); if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for tcp4 flow, vsi = %d, error = %s\n", - vsi_num, ice_stat_str(status)); + dev_dbg(dev, "ice_add_rss_cfg failed for tcp4 flow, vsi = %d, error = %d\n", + vsi_num, status); /* configure RSS for udp4 with input set IP src/dst, UDP src/dst */ status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV4, ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV4); if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for udp4 flow, vsi = %d, error = %s\n", - vsi_num, ice_stat_str(status)); + dev_dbg(dev, "ice_add_rss_cfg failed for udp4 flow, vsi = %d, error = %d\n", + vsi_num, status); /* configure RSS for sctp4 with input set IP src/dst */ status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV4, ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4); if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for sctp4 flow, vsi = %d, error = %s\n", - vsi_num, ice_stat_str(status)); + dev_dbg(dev, "ice_add_rss_cfg failed for sctp4 flow, vsi = %d, error = %d\n", + vsi_num, status); /* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */ status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_TCP_IPV6, ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6); if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for tcp6 flow, vsi = %d, error = %s\n", - vsi_num, ice_stat_str(status)); + dev_dbg(dev, "ice_add_rss_cfg failed for tcp6 flow, vsi = %d, error = %d\n", + vsi_num, status); /* configure RSS for udp6 with input set IPv6 src/dst, UDP src/dst */ status = ice_add_rss_cfg(hw, vsi_handle, ICE_HASH_UDP_IPV6, ICE_FLOW_SEG_HDR_UDP | ICE_FLOW_SEG_HDR_IPV6); if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for udp6 flow, vsi = %d, error = %s\n", - vsi_num, ice_stat_str(status)); + dev_dbg(dev, "ice_add_rss_cfg failed for udp6 flow, vsi = %d, error = %d\n", + vsi_num, status); /* configure RSS for sctp6 with input set IPv6 src/dst */ status = ice_add_rss_cfg(hw, vsi_handle, ICE_FLOW_HASH_IPV6, ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6); if (status) - dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %s\n", - vsi_num, ice_stat_str(status)); + dev_dbg(dev, "ice_add_rss_cfg failed for sctp6 flow, vsi = %d, error = %d\n", + vsi_num, status); } /** @@ -1749,22 +1749,21 @@ ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid, enum ice_sw_fwd_act_type action) int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) { struct ice_pf *pf = vsi->back; - enum ice_status status; struct device *dev; - int err = 0; + int err; dev = ice_pf_to_dev(pf); - status = ice_fltr_remove_vlan(vsi, vid, ICE_FWD_TO_VSI); - if (!status) { + err = ice_fltr_remove_vlan(vsi, vid, ICE_FWD_TO_VSI); + if (!err) { vsi->num_vlan--; - } else if (status == ICE_ERR_DOES_NOT_EXIST) { - dev_dbg(dev, "Failed to remove VLAN %d on VSI %i, it does not exist, status: %s\n", - vid, vsi->vsi_num, ice_stat_str(status)); + } else if (err == -ENOENT) { + dev_dbg(dev, "Failed to remove VLAN %d on VSI %i, it does not exist, error: %d\n", + vid, vsi->vsi_num, err); + err = 0; } else { - dev_err(dev, "Error removing VLAN %d on vsi %i error: %s\n", - vid, vsi->vsi_num, ice_stat_str(status)); - err = -EIO; + dev_err(dev, "Error removing VLAN %d on vsi %i error: %d\n", + vid, vsi->vsi_num, err); } return err; @@ -2105,8 +2104,7 @@ int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) { struct ice_hw *hw = &vsi->back->hw; struct ice_vsi_ctx *ctxt; - enum ice_status status; - int ret = 0; + int ret; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); if (!ctxt) @@ -2124,12 +2122,10 @@ int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); - if (status) { - dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - ret = -EIO; + ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (ret) { + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN insert failed, err %d aq_err %s\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); goto out; } @@ -2148,8 +2144,7 @@ int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) { struct ice_hw *hw = &vsi->back->hw; struct ice_vsi_ctx *ctxt; - enum ice_status status; - int ret = 0; + int ret; /* do not allow modifying VLAN stripping when a port VLAN is configured * on this VSI @@ -2177,12 +2172,10 @@ int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); - status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); - if (status) { - dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %s aq_err %s\n", - ena, ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - ret = -EIO; + ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (ret) { + dev_err(ice_pf_to_dev(vsi->back), "update VSI for VLAN strip failed, ena = %d err %d aq_err %s\n", + ena, ret, ice_aq_str(hw->adminq.sq_last_status)); goto out; } @@ -2324,10 +2317,9 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) status = ice_update_vsi(&pf->hw, vsi->idx, ctxt, NULL); if (status) { - netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %s, aq_err = %s\n", + netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %s\n", ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, - ice_stat_str(status), - ice_aq_str(pf->hw.adminq.sq_last_status)); + status, ice_aq_str(pf->hw.adminq.sq_last_status)); goto err_out; } @@ -2405,11 +2397,11 @@ clear_reg_idx: */ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) { - enum ice_status (*eth_fltr)(struct ice_vsi *v, u16 type, u16 flag, - enum ice_sw_fwd_act_type act); + int (*eth_fltr)(struct ice_vsi *v, u16 type, u16 flag, + enum ice_sw_fwd_act_type act); struct ice_pf *pf = vsi->back; - enum ice_status status; struct device *dev; + int status; dev = ice_pf_to_dev(pf); eth_fltr = create ? ice_fltr_add_eth : ice_fltr_remove_eth; @@ -2428,9 +2420,9 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create) } if (status) - dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n", + dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %d\n", create ? "adding" : "removing", tx ? "TX" : "RX", - vsi->vsi_num, ice_stat_str(status)); + vsi->vsi_num, status); } /** @@ -2450,7 +2442,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) struct ice_port_info *port_info; struct ice_pf *pf = vsi->back; u32 agg_node_id_start = 0; - enum ice_status status; + int status; /* create (as needed) scheduler aggregator node and move VSI into * corresponding aggregator node @@ -2576,7 +2568,6 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct device *dev = ice_pf_to_dev(pf); - enum ice_status status; struct ice_vsi *vsi; int ret, i; @@ -2725,11 +2716,11 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, } dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); - status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, - max_txqs); - if (status) { - dev_err(dev, "VSI %d failed lan queue config, error %s\n", - vsi->vsi_num, ice_stat_str(status)); + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_txqs); + if (ret) { + dev_err(dev, "VSI %d failed lan queue config, error %d\n", + vsi->vsi_num, ret); goto unroll_clear_rings; } @@ -3036,8 +3027,8 @@ void ice_napi_del(struct ice_vsi *vsi) */ int ice_vsi_release(struct ice_vsi *vsi) { - enum ice_status err; struct ice_pf *pf; + int err; if (!vsi->back) return -ENODEV; @@ -3273,7 +3264,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) int prev_num_q_vectors = 0; struct ice_vf *vf = NULL; enum ice_vsi_type vtype; - enum ice_status status; struct ice_pf *pf; int ret, i; @@ -3421,14 +3411,14 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) /* If MQPRIO is set, means channel code path, hence for main * VSI's, use TC as 1 */ - status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, max_txqs); + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, max_txqs); else - status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, - vsi->tc_cfg.ena_tc, max_txqs); + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, + vsi->tc_cfg.ena_tc, max_txqs); - if (status) { - dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %s\n", - vsi->vsi_num, ice_stat_str(status)); + if (ret) { + dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %d\n", + vsi->vsi_num, ret); if (init_vsi) { ret = -EIO; goto err_vectors; @@ -3663,7 +3653,6 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct ice_pf *pf = vsi->back; struct ice_vsi_ctx *ctx; - enum ice_status status; struct device *dev; int i, ret = 0; u8 num_tc = 0; @@ -3705,25 +3694,22 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) /* must to indicate which section of VSI context are being modified */ ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_RXQ_MAP_VALID); - status = ice_update_vsi(&pf->hw, vsi->idx, ctx, NULL); - if (status) { + ret = ice_update_vsi(&pf->hw, vsi->idx, ctx, NULL); + if (ret) { dev_info(dev, "Failed VSI Update\n"); - ret = -EIO; goto out; } if (vsi->type == ICE_VSI_PF && test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) - status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, - max_txqs); + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, max_txqs); else - status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, - vsi->tc_cfg.ena_tc, max_txqs); + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, + vsi->tc_cfg.ena_tc, max_txqs); - if (status) { - dev_err(dev, "VSI %d failed TC config, error %s\n", - vsi->vsi_num, ice_stat_str(status)); - ret = -EIO; + if (ret) { + dev_err(dev, "VSI %d failed TC config, error %d\n", + vsi->vsi_num, ret); goto out; } ice_vsi_update_q_map(vsi, ctx); @@ -3776,39 +3762,6 @@ void ice_update_rx_ring_stats(struct ice_rx_ring *rx_ring, u64 pkts, u64 bytes) } /** - * ice_status_to_errno - convert from enum ice_status to Linux errno - * @err: ice_status value to convert - */ -int ice_status_to_errno(enum ice_status err) -{ - switch (err) { - case ICE_SUCCESS: - return 0; - case ICE_ERR_DOES_NOT_EXIST: - return -ENOENT; - case ICE_ERR_OUT_OF_RANGE: - case ICE_ERR_AQ_ERROR: - case ICE_ERR_AQ_TIMEOUT: - case ICE_ERR_AQ_EMPTY: - case ICE_ERR_AQ_FW_CRITICAL: - return -EIO; - case ICE_ERR_PARAM: - case ICE_ERR_INVAL_SIZE: - return -EINVAL; - case ICE_ERR_NO_MEMORY: - return -ENOMEM; - case ICE_ERR_MAX_LIMIT: - return -EAGAIN; - case ICE_ERR_RESET_ONGOING: - return -EBUSY; - case ICE_ERR_AQ_FULL: - return -ENOSPC; - default: - return -EINVAL; - } -} - -/** * ice_is_dflt_vsi_in_use - check if the default forwarding VSI is being used * @sw: switch to check if its default forwarding VSI is free * @@ -3849,8 +3802,8 @@ bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi) */ int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi) { - enum ice_status status; struct device *dev; + int status; if (!sw || !vsi) return -EINVAL; @@ -3873,9 +3826,9 @@ int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi) status = ice_cfg_dflt_vsi(&vsi->back->hw, vsi->idx, true, ICE_FLTR_RX); if (status) { - dev_err(dev, "Failed to set VSI %d as the default forwarding VSI, error %s\n", - vsi->vsi_num, ice_stat_str(status)); - return -EIO; + dev_err(dev, "Failed to set VSI %d as the default forwarding VSI, error %d\n", + vsi->vsi_num, status); + return status; } sw->dflt_vsi = vsi; @@ -3895,8 +3848,8 @@ int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi) int ice_clear_dflt_vsi(struct ice_sw *sw) { struct ice_vsi *dflt_vsi; - enum ice_status status; struct device *dev; + int status; if (!sw) return -EINVAL; @@ -3912,8 +3865,8 @@ int ice_clear_dflt_vsi(struct ice_sw *sw) status = ice_cfg_dflt_vsi(&dflt_vsi->back->hw, dflt_vsi->idx, false, ICE_FLTR_RX); if (status) { - dev_err(dev, "Failed to clear the default forwarding VSI %d, error %s\n", - dflt_vsi->vsi_num, ice_stat_str(status)); + dev_err(dev, "Failed to clear the default forwarding VSI %d, error %d\n", + dflt_vsi->vsi_num, status); return -EIO; } @@ -3987,8 +3940,8 @@ int ice_get_link_speed_kbps(struct ice_vsi *vsi) int ice_set_min_bw_limit(struct ice_vsi *vsi, u64 min_tx_rate) { struct ice_pf *pf = vsi->back; - enum ice_status status; struct device *dev; + int status; int speed; dev = ice_pf_to_dev(pf); @@ -4014,7 +3967,7 @@ int ice_set_min_bw_limit(struct ice_vsi *vsi, u64 min_tx_rate) dev_err(dev, "failed to set min Tx rate(%llu Kbps) for %s %d\n", min_tx_rate, ice_vsi_type_str(vsi->type), vsi->idx); - return -EIO; + return status; } dev_dbg(dev, "set min Tx rate(%llu Kbps) for %s\n", @@ -4026,7 +3979,7 @@ int ice_set_min_bw_limit(struct ice_vsi *vsi, u64 min_tx_rate) if (status) { dev_err(dev, "failed to clear min Tx rate configuration for %s %d\n", ice_vsi_type_str(vsi->type), vsi->idx); - return -EIO; + return status; } dev_dbg(dev, "cleared min Tx rate configuration for %s %d\n", @@ -4048,8 +4001,8 @@ int ice_set_min_bw_limit(struct ice_vsi *vsi, u64 min_tx_rate) int ice_set_max_bw_limit(struct ice_vsi *vsi, u64 max_tx_rate) { struct ice_pf *pf = vsi->back; - enum ice_status status; struct device *dev; + int status; int speed; dev = ice_pf_to_dev(pf); @@ -4075,7 +4028,7 @@ int ice_set_max_bw_limit(struct ice_vsi *vsi, u64 max_tx_rate) dev_err(dev, "failed setting max Tx rate(%llu Kbps) for %s %d\n", max_tx_rate, ice_vsi_type_str(vsi->type), vsi->idx); - return -EIO; + return status; } dev_dbg(dev, "set max Tx rate(%llu Kbps) for %s %d\n", @@ -4087,7 +4040,7 @@ int ice_set_max_bw_limit(struct ice_vsi *vsi, u64 max_tx_rate) if (status) { dev_err(dev, "failed clearing max Tx rate configuration for %s %d\n", ice_vsi_type_str(vsi->type), vsi->idx); - return -EIO; + return status; } dev_dbg(dev, "cleared max Tx rate configuration for %s %d\n", @@ -4107,7 +4060,7 @@ int ice_set_link(struct ice_vsi *vsi, bool ena) struct device *dev = ice_pf_to_dev(vsi->back); struct ice_port_info *pi = vsi->port_info; struct ice_hw *hw = pi->hw; - enum ice_status status; + int status; if (vsi->type != ICE_VSI_PF) return -EINVAL; @@ -4119,16 +4072,16 @@ int ice_set_link(struct ice_vsi *vsi, bool ena) * a success code. Return an error if FW returns an error code other * than ICE_AQ_RC_EMODE */ - if (status == ICE_ERR_AQ_ERROR) { + if (status == -EIO) { if (hw->adminq.sq_last_status == ICE_AQ_RC_EMODE) - dev_warn(dev, "can't set link to %s, err %s aq_err %s. not fatal, continuing\n", - (ena ? "ON" : "OFF"), ice_stat_str(status), + dev_warn(dev, "can't set link to %s, err %d aq_err %s. not fatal, continuing\n", + (ena ? "ON" : "OFF"), status, ice_aq_str(hw->adminq.sq_last_status)); } else if (status) { - dev_err(dev, "can't set link to %s, err %s aq_err %s\n", - (ena ? "ON" : "OFF"), ice_stat_str(status), + dev_err(dev, "can't set link to %s, err %d aq_err %s\n", + (ena ? "ON" : "OFF"), status, ice_aq_str(hw->adminq.sq_last_status)); - return -EIO; + return status; } return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 6c803407b67d..b2ed189527d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -103,15 +103,11 @@ void ice_update_tx_ring_stats(struct ice_tx_ring *ring, u64 pkts, u64 bytes); void ice_update_rx_ring_stats(struct ice_rx_ring *ring, u64 pkts, u64 bytes); void ice_vsi_cfg_frame_size(struct ice_vsi *vsi); - -int ice_status_to_errno(enum ice_status err); - void ice_write_intrl(struct ice_q_vector *q_vector, u8 intrl); void ice_write_itr(struct ice_ring_container *rc, u16 itr); void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); -enum ice_status -ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); +int ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); bool ice_is_safe_mode(struct ice_pf *pf); bool ice_is_aux_ena(struct ice_pf *pf); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 515ac8c4e891..865f2231bb24 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -155,7 +155,6 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) */ static int ice_init_mac_fltr(struct ice_pf *pf) { - enum ice_status status; struct ice_vsi *vsi; u8 *perm_addr; @@ -164,11 +163,7 @@ static int ice_init_mac_fltr(struct ice_pf *pf) return -EINVAL; perm_addr = vsi->port_info->mac.perm_addr; - status = ice_fltr_add_mac_and_broadcast(vsi, perm_addr, ICE_FWD_TO_VSI); - if (status) - return -EIO; - - return 0; + return ice_fltr_add_mac_and_broadcast(vsi, perm_addr, ICE_FWD_TO_VSI); } /** @@ -237,36 +232,43 @@ static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) } /** - * ice_cfg_promisc - Enable or disable promiscuous mode for a given PF + * ice_set_promisc - Enable promiscuous mode for a given PF * @vsi: the VSI being configured * @promisc_m: mask of promiscuous config bits - * @set_promisc: enable or disable promisc flag request * */ -static int ice_cfg_promisc(struct ice_vsi *vsi, u8 promisc_m, bool set_promisc) +static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) { - struct ice_hw *hw = &vsi->back->hw; - enum ice_status status = 0; + int status; if (vsi->type != ICE_VSI_PF) return 0; - if (vsi->num_vlan > 1) { - status = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_m, - set_promisc); - } else { - if (set_promisc) - status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m, - 0); - else - status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m, - 0); - } + if (vsi->num_vlan > 1) + status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); + else + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + return status; +} - if (status) - return -EIO; +/** + * ice_clear_promisc - Disable promiscuous mode for a given PF + * @vsi: the VSI being configured + * @promisc_m: mask of promiscuous config bits + * + */ +static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) +{ + int status; - return 0; + if (vsi->type != ICE_VSI_PF) + return 0; + + if (vsi->num_vlan > 1) + status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); + else + status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + return status; } /** @@ -282,10 +284,9 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) bool promisc_forced_on = false; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - enum ice_status status = 0; u32 changed_flags = 0; u8 promisc_m; - int err = 0; + int err; if (!vsi->netdev) return -EINVAL; @@ -315,25 +316,23 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) } /* Remove MAC addresses in the unsync list */ - status = ice_fltr_remove_mac_list(vsi, &vsi->tmp_unsync_list); + err = ice_fltr_remove_mac_list(vsi, &vsi->tmp_unsync_list); ice_fltr_free_list(dev, &vsi->tmp_unsync_list); - if (status) { + if (err) { netdev_err(netdev, "Failed to delete MAC filters\n"); /* if we failed because of alloc failures, just bail */ - if (status == ICE_ERR_NO_MEMORY) { - err = -ENOMEM; + if (err == -ENOMEM) goto out; - } } /* Add MAC addresses in the sync list */ - status = ice_fltr_add_mac_list(vsi, &vsi->tmp_sync_list); + err = ice_fltr_add_mac_list(vsi, &vsi->tmp_sync_list); ice_fltr_free_list(dev, &vsi->tmp_sync_list); /* If filter is added successfully or already exists, do not go into * 'if' condition and report it as error. Instead continue processing * rest of the function. */ - if (status && status != ICE_ERR_ALREADY_EXISTS) { + if (err && err != -EEXIST) { netdev_err(netdev, "Failed to add MAC filters\n"); /* If there is no more space for new umac filters, VSI * should go into promiscuous mode. There should be some @@ -346,10 +345,10 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) netdev_warn(netdev, "Reached MAC filter limit, forcing promisc mode on VSI %d\n", vsi->vsi_num); } else { - err = -EIO; goto out; } } + err = 0; /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { if (vsi->current_netdev_flags & IFF_ALLMULTI) { @@ -358,7 +357,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) else promisc_m = ICE_MCAST_PROMISC_BITS; - err = ice_cfg_promisc(vsi, promisc_m, true); + err = ice_set_promisc(vsi, promisc_m); if (err) { netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n", vsi->vsi_num); @@ -372,7 +371,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) else promisc_m = ICE_MCAST_PROMISC_BITS; - err = ice_cfg_promisc(vsi, promisc_m, false); + err = ice_clear_promisc(vsi, promisc_m); if (err) { netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n", vsi->vsi_num); @@ -396,6 +395,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) ~IFF_PROMISC; goto out_promisc; } + err = 0; ice_cfg_vlan_pruning(vsi, false); } } else { @@ -695,12 +695,12 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) { struct ice_aqc_get_phy_caps_data *caps; const char *an_advertised; - enum ice_status status; const char *fec_req; const char *speed; const char *fec; const char *fc; const char *an; + int status; if (!vsi) return; @@ -1020,10 +1020,10 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, { struct device *dev = ice_pf_to_dev(pf); struct ice_phy_info *phy_info; - enum ice_status status; struct ice_vsi *vsi; u16 old_link_speed; bool old_link; + int status; phy_info = &pi->phy; phy_info->link_info_old = phy_info->link_info; @@ -1036,8 +1036,8 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, */ status = ice_update_link_info(pi); if (status) - dev_dbg(dev, "Failed to update link status on port %d, err %s aq_err %s\n", - pi->lport, ice_stat_str(status), + dev_dbg(dev, "Failed to update link status on port %d, err %d aq_err %s\n", + pi->lport, status, ice_aq_str(pi->hw->adminq.sq_last_status)); ice_check_link_cfg_err(pf, pi->phy.link_info.link_cfg_err); @@ -1407,15 +1407,15 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) return 0; do { - enum ice_status ret; u16 opcode; + int ret; ret = ice_clean_rq_elem(hw, cq, &event, &pending); - if (ret == ICE_ERR_AQ_NO_WORK) + if (ret == -EALREADY) break; if (ret) { - dev_err(dev, "%s Receive Queue event error %s\n", qtype, - ice_stat_str(ret)); + dev_err(dev, "%s Receive Queue event error %d\n", qtype, + ret); break; } @@ -1866,19 +1866,17 @@ static int ice_init_nvm_phy_type(struct ice_port_info *pi) { struct ice_aqc_get_phy_caps_data *pcaps; struct ice_pf *pf = pi->hw->back; - enum ice_status status; - int err = 0; + int err; pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); if (!pcaps) return -ENOMEM; - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_NO_MEDIA, pcaps, - NULL); + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_NO_MEDIA, + pcaps, NULL); - if (status) { + if (err) { dev_err(ice_pf_to_dev(pf), "Get PHY capability failed.\n"); - err = -EIO; goto out; } @@ -1977,8 +1975,7 @@ static int ice_init_phy_user_cfg(struct ice_port_info *pi) struct ice_aqc_get_phy_caps_data *pcaps; struct ice_phy_info *phy = &pi->phy; struct ice_pf *pf = pi->hw->back; - enum ice_status status; - int err = 0; + int err; if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) return -EIO; @@ -1988,14 +1985,13 @@ static int ice_init_phy_user_cfg(struct ice_port_info *pi) return -ENOMEM; if (ice_fw_supports_report_dflt_cfg(pi->hw)) - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_DFLT_CFG, - pcaps, NULL); + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_DFLT_CFG, + pcaps, NULL); else - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, - pcaps, NULL); - if (status) { + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, + pcaps, NULL); + if (err) { dev_err(ice_pf_to_dev(pf), "Get PHY capability failed.\n"); - err = -EIO; goto err_out; } @@ -2049,8 +2045,7 @@ static int ice_configure_phy(struct ice_vsi *vsi) struct ice_aqc_set_phy_cfg_data *cfg; struct ice_phy_info *phy = &pi->phy; struct ice_pf *pf = vsi->back; - enum ice_status status; - int err = 0; + int err; /* Ensure we have media as we cannot configure a medialess port */ if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) @@ -2070,12 +2065,11 @@ static int ice_configure_phy(struct ice_vsi *vsi) return -ENOMEM; /* Get current PHY config */ - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, pcaps, - NULL); - if (status) { - dev_err(dev, "Failed to get PHY configuration, VSI %d error %s\n", - vsi->vsi_num, ice_stat_str(status)); - err = -EIO; + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_ACTIVE_CFG, pcaps, + NULL); + if (err) { + dev_err(dev, "Failed to get PHY configuration, VSI %d error %d\n", + vsi->vsi_num, err); goto done; } @@ -2089,15 +2083,14 @@ static int ice_configure_phy(struct ice_vsi *vsi) /* Use PHY topology as baseline for configuration */ memset(pcaps, 0, sizeof(*pcaps)); if (ice_fw_supports_report_dflt_cfg(pi->hw)) - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_DFLT_CFG, - pcaps, NULL); + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_DFLT_CFG, + pcaps, NULL); else - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, - pcaps, NULL); - if (status) { - dev_err(dev, "Failed to get PHY caps, VSI %d error %s\n", - vsi->vsi_num, ice_stat_str(status)); - err = -EIO; + err = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP_MEDIA, + pcaps, NULL); + if (err) { + dev_err(dev, "Failed to get PHY caps, VSI %d error %d\n", + vsi->vsi_num, err); goto done; } @@ -2150,12 +2143,10 @@ static int ice_configure_phy(struct ice_vsi *vsi) /* Enable link and link update */ cfg->caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT | ICE_AQ_PHY_ENA_LINK; - status = ice_aq_set_phy_cfg(&pf->hw, pi, cfg, NULL); - if (status) { - dev_err(dev, "Failed to set phy config, VSI %d error %s\n", - vsi->vsi_num, ice_stat_str(status)); - err = -EIO; - } + err = ice_aq_set_phy_cfg(&pf->hw, pi, cfg, NULL); + if (err) + dev_err(dev, "Failed to set phy config, VSI %d error %d\n", + vsi->vsi_num, err); kfree(cfg); done: @@ -2549,9 +2540,9 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) .vsi_map_offset = vsi->alloc_txq, .mapping_mode = ICE_VSI_MAP_CONTIG }; - enum ice_status status; struct device *dev; int i, v_idx; + int status; dev = ice_pf_to_dev(pf); vsi->xdp_rings = devm_kcalloc(dev, vsi->num_xdp_txq, @@ -2605,8 +2596,8 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, max_txqs); if (status) { - dev_err(dev, "Failed VSI LAN queue config for XDP, error: %s\n", - ice_stat_str(status)); + dev_err(dev, "Failed VSI LAN queue config for XDP, error: %d\n", + status); goto clear_xdp_rings; } @@ -3520,7 +3511,7 @@ static int ice_setup_pf_sw(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_vsi *vsi; - int status = 0; + int status; if (ice_is_reset_in_progress(pf->state)) return -EBUSY; @@ -3533,10 +3524,8 @@ static int ice_setup_pf_sw(struct ice_pf *pf) INIT_LIST_HEAD(&vsi->ch_list); status = ice_cfg_netdev(vsi); - if (status) { - status = -ENODEV; + if (status) goto unroll_vsi_setup; - } /* netdev has to be configured before setting frame size */ ice_vsi_cfg_frame_size(vsi); @@ -3560,14 +3549,13 @@ static int ice_setup_pf_sw(struct ice_pf *pf) if (status) { dev_err(dev, "Failed to set CPU Rx map VSI %d error %d\n", vsi->vsi_num, status); - status = -EINVAL; goto unroll_napi_add; } status = ice_init_mac_fltr(pf); if (status) goto free_cpu_rx_map; - return status; + return 0; free_cpu_rx_map: ice_free_cpu_rx_rmap(vsi); @@ -4023,8 +4011,8 @@ static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf) { struct ice_vsi *vsi = ice_get_main_vsi(pf); struct ice_vsi_ctx *ctxt; - enum ice_status status; struct ice_hw *hw; + int status; if (!vsi) return; @@ -4054,9 +4042,8 @@ static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf) status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); if (status) { - dev_err(ice_pf_to_dev(vsi->back), "Failed to update VSI for safe mode VLANs, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + dev_err(ice_pf_to_dev(vsi->back), "Failed to update VSI for safe mode VLANs, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); } else { vsi->info.sec_flags = ctxt->info.sec_flags; vsi->info.sw_flags2 = ctxt->info.sw_flags2; @@ -4069,109 +4056,80 @@ static void ice_set_safe_mode_vlan_cfg(struct ice_pf *pf) /** * ice_log_pkg_init - log result of DDP package load * @hw: pointer to hardware info - * @status: status of package load + * @state: state of package load */ -static void -ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status) +static void ice_log_pkg_init(struct ice_hw *hw, enum ice_ddp_state state) { - struct ice_pf *pf = (struct ice_pf *)hw->back; - struct device *dev = ice_pf_to_dev(pf); + struct ice_pf *pf = hw->back; + struct device *dev; - switch (*status) { - case ICE_SUCCESS: - /* The package download AdminQ command returned success because - * this download succeeded or ICE_ERR_AQ_NO_WORK since there is - * already a package loaded on the device. - */ - if (hw->pkg_ver.major == hw->active_pkg_ver.major && - hw->pkg_ver.minor == hw->active_pkg_ver.minor && - hw->pkg_ver.update == hw->active_pkg_ver.update && - hw->pkg_ver.draft == hw->active_pkg_ver.draft && - !memcmp(hw->pkg_name, hw->active_pkg_name, - sizeof(hw->pkg_name))) { - if (hw->pkg_dwnld_status == ICE_AQ_RC_EEXIST) - dev_info(dev, "DDP package already present on device: %s version %d.%d.%d.%d\n", - hw->active_pkg_name, - hw->active_pkg_ver.major, - hw->active_pkg_ver.minor, - hw->active_pkg_ver.update, - hw->active_pkg_ver.draft); - else - dev_info(dev, "The DDP package was successfully loaded: %s version %d.%d.%d.%d\n", - hw->active_pkg_name, - hw->active_pkg_ver.major, - hw->active_pkg_ver.minor, - hw->active_pkg_ver.update, - hw->active_pkg_ver.draft); - } else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ || - hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) { - dev_err(dev, "The device has a DDP package that is not supported by the driver. The device has package '%s' version %d.%d.x.x. The driver requires version %d.%d.x.x. Entering Safe Mode.\n", - hw->active_pkg_name, - hw->active_pkg_ver.major, - hw->active_pkg_ver.minor, - ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR); - *status = ICE_ERR_NOT_SUPPORTED; - } else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && - hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) { - dev_info(dev, "The driver could not load the DDP package file because a compatible DDP package is already present on the device. The device has package '%s' version %d.%d.%d.%d. The package file found by the driver: '%s' version %d.%d.%d.%d.\n", - hw->active_pkg_name, - hw->active_pkg_ver.major, - hw->active_pkg_ver.minor, - hw->active_pkg_ver.update, - hw->active_pkg_ver.draft, - hw->pkg_name, - hw->pkg_ver.major, - hw->pkg_ver.minor, - hw->pkg_ver.update, - hw->pkg_ver.draft); - } else { - dev_err(dev, "An unknown error occurred when loading the DDP package, please reboot the system. If the problem persists, update the NVM. Entering Safe Mode.\n"); - *status = ICE_ERR_NOT_SUPPORTED; - } + dev = ice_pf_to_dev(pf); + + switch (state) { + case ICE_DDP_PKG_SUCCESS: + dev_info(dev, "The DDP package was successfully loaded: %s version %d.%d.%d.%d\n", + hw->active_pkg_name, + hw->active_pkg_ver.major, + hw->active_pkg_ver.minor, + hw->active_pkg_ver.update, + hw->active_pkg_ver.draft); + break; + case ICE_DDP_PKG_SAME_VERSION_ALREADY_LOADED: + dev_info(dev, "DDP package already present on device: %s version %d.%d.%d.%d\n", + hw->active_pkg_name, + hw->active_pkg_ver.major, + hw->active_pkg_ver.minor, + hw->active_pkg_ver.update, + hw->active_pkg_ver.draft); + break; + case ICE_DDP_PKG_ALREADY_LOADED_NOT_SUPPORTED: + dev_err(dev, "The device has a DDP package that is not supported by the driver. The device has package '%s' version %d.%d.x.x. The driver requires version %d.%d.x.x. Entering Safe Mode.\n", + hw->active_pkg_name, + hw->active_pkg_ver.major, + hw->active_pkg_ver.minor, + ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR); + break; + case ICE_DDP_PKG_COMPATIBLE_ALREADY_LOADED: + dev_info(dev, "The driver could not load the DDP package file because a compatible DDP package is already present on the device. The device has package '%s' version %d.%d.%d.%d. The package file found by the driver: '%s' version %d.%d.%d.%d.\n", + hw->active_pkg_name, + hw->active_pkg_ver.major, + hw->active_pkg_ver.minor, + hw->active_pkg_ver.update, + hw->active_pkg_ver.draft, + hw->pkg_name, + hw->pkg_ver.major, + hw->pkg_ver.minor, + hw->pkg_ver.update, + hw->pkg_ver.draft); break; - case ICE_ERR_FW_DDP_MISMATCH: + case ICE_DDP_PKG_FW_MISMATCH: dev_err(dev, "The firmware loaded on the device is not compatible with the DDP package. Please update the device's NVM. Entering safe mode.\n"); break; - case ICE_ERR_BUF_TOO_SHORT: - case ICE_ERR_CFG: + case ICE_DDP_PKG_INVALID_FILE: dev_err(dev, "The DDP package file is invalid. Entering Safe Mode.\n"); break; - case ICE_ERR_NOT_SUPPORTED: - /* Package File version not supported */ - if (hw->pkg_ver.major > ICE_PKG_SUPP_VER_MAJ || - (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && - hw->pkg_ver.minor > ICE_PKG_SUPP_VER_MNR)) - dev_err(dev, "The DDP package file version is higher than the driver supports. Please use an updated driver. Entering Safe Mode.\n"); - else if (hw->pkg_ver.major < ICE_PKG_SUPP_VER_MAJ || - (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && - hw->pkg_ver.minor < ICE_PKG_SUPP_VER_MNR)) - dev_err(dev, "The DDP package file version is lower than the driver supports. The driver requires version %d.%d.x.x. Please use an updated DDP Package file. Entering Safe Mode.\n", - ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR); + case ICE_DDP_PKG_FILE_VERSION_TOO_HIGH: + dev_err(dev, "The DDP package file version is higher than the driver supports. Please use an updated driver. Entering Safe Mode.\n"); break; - case ICE_ERR_AQ_ERROR: - switch (hw->pkg_dwnld_status) { - case ICE_AQ_RC_ENOSEC: - case ICE_AQ_RC_EBADSIG: - dev_err(dev, "The DDP package could not be loaded because its signature is not valid. Please use a valid DDP Package. Entering Safe Mode.\n"); - return; - case ICE_AQ_RC_ESVN: - dev_err(dev, "The DDP Package could not be loaded because its security revision is too low. Please use an updated DDP Package. Entering Safe Mode.\n"); - return; - case ICE_AQ_RC_EBADMAN: - case ICE_AQ_RC_EBADBUF: - dev_err(dev, "An error occurred on the device while loading the DDP package. The device will be reset.\n"); + case ICE_DDP_PKG_FILE_VERSION_TOO_LOW: + dev_err(dev, "The DDP package file version is lower than the driver supports. The driver requires version %d.%d.x.x. Please use an updated DDP Package file. Entering Safe Mode.\n", + ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR); + break; + case ICE_DDP_PKG_FILE_SIGNATURE_INVALID: + dev_err(dev, "The DDP package could not be loaded because its signature is not valid. Please use a valid DDP Package. Entering Safe Mode.\n"); + break; + case ICE_DDP_PKG_FILE_REVISION_TOO_LOW: + dev_err(dev, "The DDP Package could not be loaded because its security revision is too low. Please use an updated DDP Package. Entering Safe Mode.\n"); + break; + case ICE_DDP_PKG_LOAD_ERROR: + dev_err(dev, "An error occurred on the device while loading the DDP package. The device will be reset.\n"); /* poll for reset to complete */ if (ice_check_reset(hw)) dev_err(dev, "Error resetting device. Please reload the driver\n"); - return; - default: - break; - } - fallthrough; - default: - dev_err(dev, "An unknown error (%d) occurred when loading the DDP package. Entering Safe Mode.\n", - *status); break; + case ICE_DDP_PKG_ERR: + default: + dev_err(dev, "An unknown error occurred when loading the DDP package. Entering Safe Mode.\n"); } } @@ -4186,24 +4144,24 @@ ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status) static void ice_load_pkg(const struct firmware *firmware, struct ice_pf *pf) { - enum ice_status status = ICE_ERR_PARAM; + enum ice_ddp_state state = ICE_DDP_PKG_ERR; struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; /* Load DDP Package */ if (firmware && !hw->pkg_copy) { - status = ice_copy_and_init_pkg(hw, firmware->data, - firmware->size); - ice_log_pkg_init(hw, &status); + state = ice_copy_and_init_pkg(hw, firmware->data, + firmware->size); + ice_log_pkg_init(hw, state); } else if (!firmware && hw->pkg_copy) { /* Reload package during rebuild after CORER/GLOBR reset */ - status = ice_init_pkg(hw, hw->pkg_copy, hw->pkg_size); - ice_log_pkg_init(hw, &status); + state = ice_init_pkg(hw, hw->pkg_copy, hw->pkg_size); + ice_log_pkg_init(hw, state); } else { dev_err(dev, "The DDP package file failed to load. Entering Safe Mode.\n"); } - if (status) { + if (!ice_is_init_pkg_successful(state)) { /* Safe Mode */ clear_bit(ICE_FLAG_ADV_FEATURES, pf->flags); return; @@ -4234,9 +4192,9 @@ static void ice_verify_cacheline_size(struct ice_pf *pf) * ice_send_version - update firmware with driver version * @pf: PF struct * - * Returns ICE_SUCCESS on success, else error code + * Returns 0 on success, else error code */ -static enum ice_status ice_send_version(struct ice_pf *pf) +static int ice_send_version(struct ice_pf *pf) { struct ice_driver_ver dv; @@ -4526,7 +4484,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) * true */ if (ice_is_safe_mode(pf)) { - dev_err(dev, "Package download failed. Advanced features disabled - Device now in Safe Mode\n"); /* we already got function/device capabilities but these don't * reflect what the driver needs to do in safe mode. Instead of * adding conditional logic everywhere to ignore these @@ -4809,9 +4766,9 @@ static void ice_setup_mc_magic_wake(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - enum ice_status status; u8 mac_addr[ETH_ALEN]; struct ice_vsi *vsi; + int status; u8 flags; if (!pf->wol_ena) @@ -4833,9 +4790,8 @@ static void ice_setup_mc_magic_wake(struct ice_pf *pf) status = ice_aq_manage_mac_write(hw, mac_addr, flags, NULL); if (status) - dev_err(dev, "Failed to enable Multicast Magic Packet wake, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + dev_err(dev, "Failed to enable Multicast Magic Packet wake, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); } /** @@ -5374,11 +5330,10 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; struct sockaddr *addr = pi; - enum ice_status status; u8 old_mac[ETH_ALEN]; u8 flags = 0; - int err = 0; u8 *mac; + int err; mac = (u8 *)addr->sa_data; @@ -5410,22 +5365,22 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) netif_addr_unlock_bh(netdev); /* Clean up old MAC filter. Not an error if old filter doesn't exist */ - status = ice_fltr_remove_mac(vsi, old_mac, ICE_FWD_TO_VSI); - if (status && status != ICE_ERR_DOES_NOT_EXIST) { + err = ice_fltr_remove_mac(vsi, old_mac, ICE_FWD_TO_VSI); + if (err && err != -ENOENT) { err = -EADDRNOTAVAIL; goto err_update_filters; } /* Add filter for new MAC. If filter exists, return success */ - status = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); - if (status == ICE_ERR_ALREADY_EXISTS) + err = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); + if (err == -EEXIST) /* Although this MAC filter is already present in hardware it's * possible in some cases (e.g. bonding) that dev_addr was * modified outside of the driver and needs to be restored back * to this value. */ netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); - else if (status) + else if (err) /* error if the new filter addition failed */ err = -EADDRNOTAVAIL; @@ -5444,10 +5399,10 @@ err_update_filters: /* write new MAC address to the firmware */ flags = ICE_AQC_MAN_MAC_UPDATE_LAA_WOL; - status = ice_aq_manage_mac_write(hw, mac, flags, NULL); - if (status) { - netdev_err(netdev, "can't set MAC %pM. write to firmware failed error %s\n", - mac, ice_stat_str(status)); + err = ice_aq_manage_mac_write(hw, mac, flags, NULL); + if (err) { + netdev_err(netdev, "can't set MAC %pM. write to firmware failed error %d\n", + mac, err); } return 0; } @@ -5489,8 +5444,8 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - enum ice_status status; u16 q_handle; + int status; u8 tc; /* Validate maxrate requested is within permitted range */ @@ -5510,13 +5465,11 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate) else status = ice_cfg_q_bw_lmt(vsi->port_info, vsi->idx, tc, q_handle, ICE_MAX_BW, maxrate * 1000); - if (status) { - netdev_err(netdev, "Unable to set Tx max rate, error %s\n", - ice_stat_str(status)); - return -EIO; - } + if (status) + netdev_err(netdev, "Unable to set Tx max rate, error %d\n", + status); - return 0; + return status; } /** @@ -5888,6 +5841,9 @@ static int ice_up_complete(struct ice_vsi *vsi) netif_carrier_on(vsi->netdev); } + /* clear this now, and the first stats read will be used as baseline */ + vsi->stat_offsets_loaded = false; + ice_service_task_schedule(pf); return 0; @@ -5934,14 +5890,15 @@ ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, struct ice_q_stats st /** * ice_update_vsi_tx_ring_stats - Update VSI Tx ring stats counters * @vsi: the VSI to be updated + * @vsi_stats: the stats struct to be updated * @rings: rings to work on * @count: number of rings */ static void -ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_tx_ring **rings, - u16 count) +ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, + struct rtnl_link_stats64 *vsi_stats, + struct ice_tx_ring **rings, u16 count) { - struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats; u16 i; for (i = 0; i < count; i++) { @@ -5965,15 +5922,13 @@ ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_tx_ring **rings, */ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) { - struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats; + struct rtnl_link_stats64 *vsi_stats; u64 pkts, bytes; int i; - /* reset netdev stats */ - vsi_stats->tx_packets = 0; - vsi_stats->tx_bytes = 0; - vsi_stats->rx_packets = 0; - vsi_stats->rx_bytes = 0; + vsi_stats = kzalloc(sizeof(*vsi_stats), GFP_ATOMIC); + if (!vsi_stats) + return; /* reset non-netdev (extended) stats */ vsi->tx_restart = 0; @@ -5985,7 +5940,8 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) rcu_read_lock(); /* update Tx rings counters */ - ice_update_vsi_tx_ring_stats(vsi, vsi->tx_rings, vsi->num_txq); + ice_update_vsi_tx_ring_stats(vsi, vsi_stats, vsi->tx_rings, + vsi->num_txq); /* update Rx rings counters */ ice_for_each_rxq(vsi, i) { @@ -6000,10 +5956,17 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) /* update XDP Tx rings counters */ if (ice_is_xdp_ena_vsi(vsi)) - ice_update_vsi_tx_ring_stats(vsi, vsi->xdp_rings, + ice_update_vsi_tx_ring_stats(vsi, vsi_stats, vsi->xdp_rings, vsi->num_xdp_txq); rcu_read_unlock(); + + vsi->net_stats.tx_packets = vsi_stats->tx_packets; + vsi->net_stats.tx_bytes = vsi_stats->tx_bytes; + vsi->net_stats.rx_packets = vsi_stats->rx_packets; + vsi->net_stats.rx_bytes = vsi_stats->rx_bytes; + + kfree(vsi_stats); } /** @@ -6266,14 +6229,15 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) /** * ice_down - Shutdown the connection * @vsi: The VSI being stopped + * + * Caller of this function is expected to set the vsi->state ICE_DOWN bit */ int ice_down(struct ice_vsi *vsi) { int i, tx_err, rx_err, link_err = 0; - /* Caller of this function is expected to set the - * vsi->state ICE_DOWN bit - */ + WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state)); + if (vsi->netdev && vsi->type == ICE_VSI_PF) { netif_carrier_off(vsi->netdev); netif_tx_disable(vsi->netdev); @@ -6540,7 +6504,6 @@ static void ice_vsi_release_all(struct ice_pf *pf) static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type) { struct device *dev = ice_pf_to_dev(pf); - enum ice_status status; int i, err; ice_for_each_vsi(pf, i) { @@ -6558,12 +6521,11 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type) } /* replay filters for the VSI */ - status = ice_replay_vsi(&pf->hw, vsi->idx); - if (status) { - dev_err(dev, "replay VSI failed, status %s, VSI index %d, type %s\n", - ice_stat_str(status), vsi->idx, - ice_vsi_type_str(type)); - return -EIO; + err = ice_replay_vsi(&pf->hw, vsi->idx); + if (err) { + dev_err(dev, "replay VSI failed, error %d, VSI index %d, type %s\n", + err, vsi->idx, ice_vsi_type_str(type)); + return err; } /* Re-map HW VSI number, using VSI handle that has been @@ -6626,7 +6588,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; - enum ice_status ret; int err; if (test_bit(ICE_DOWN, pf->state)) @@ -6634,10 +6595,17 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); - ret = ice_init_all_ctrlq(hw); - if (ret) { - dev_err(dev, "control queues init failed %s\n", - ice_stat_str(ret)); + if (reset_type == ICE_RESET_EMPR) { + /* If an EMP reset has occurred, any previously pending flash + * update will have completed. We no longer know whether or + * not the NVM update EMP reset is restricted. + */ + pf->fw_emp_reset_disabled = false; + } + + err = ice_init_all_ctrlq(hw); + if (err) { + dev_err(dev, "control queues init failed %d\n", err); goto err_init_ctrlq; } @@ -6651,10 +6619,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_load_pkg(NULL, pf); } - ret = ice_clear_pf_cfg(hw); - if (ret) { - dev_err(dev, "clear PF configuration failed %s\n", - ice_stat_str(ret)); + err = ice_clear_pf_cfg(hw); + if (err) { + dev_err(dev, "clear PF configuration failed %d\n", err); goto err_init_ctrlq; } @@ -6666,21 +6633,21 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_clear_pxe_mode(hw); - ret = ice_init_nvm(hw); - if (ret) { - dev_err(dev, "ice_init_nvm failed %s\n", ice_stat_str(ret)); + err = ice_init_nvm(hw); + if (err) { + dev_err(dev, "ice_init_nvm failed %d\n", err); goto err_init_ctrlq; } - ret = ice_get_caps(hw); - if (ret) { - dev_err(dev, "ice_get_caps failed %s\n", ice_stat_str(ret)); + err = ice_get_caps(hw); + if (err) { + dev_err(dev, "ice_get_caps failed %d\n", err); goto err_init_ctrlq; } - ret = ice_aq_set_mac_cfg(hw, ICE_AQ_SET_MAC_FRAME_SIZE_MAX, NULL); - if (ret) { - dev_err(dev, "set_mac_cfg failed %s\n", ice_stat_str(ret)); + err = ice_aq_set_mac_cfg(hw, ICE_AQ_SET_MAC_FRAME_SIZE_MAX, NULL); + if (err) { + dev_err(dev, "set_mac_cfg failed %d\n", err); goto err_init_ctrlq; } @@ -6763,10 +6730,10 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_update_pf_netdev_link(pf); /* tell the firmware we are up */ - ret = ice_send_version(pf); - if (ret) { - dev_err(dev, "Rebuild failed due to error sending driver version: %s\n", - ice_stat_str(ret)); + err = ice_send_version(pf); + if (err) { + dev_err(dev, "Rebuild failed due to error sending driver version: %d\n", + err); goto err_vsi_rebuild; } @@ -6947,78 +6914,6 @@ const char *ice_aq_str(enum ice_aq_err aq_err) } /** - * ice_stat_str - convert status err code to a string - * @stat_err: the status error code to convert - */ -const char *ice_stat_str(enum ice_status stat_err) -{ - switch (stat_err) { - case ICE_SUCCESS: - return "OK"; - case ICE_ERR_PARAM: - return "ICE_ERR_PARAM"; - case ICE_ERR_NOT_IMPL: - return "ICE_ERR_NOT_IMPL"; - case ICE_ERR_NOT_READY: - return "ICE_ERR_NOT_READY"; - case ICE_ERR_NOT_SUPPORTED: - return "ICE_ERR_NOT_SUPPORTED"; - case ICE_ERR_BAD_PTR: - return "ICE_ERR_BAD_PTR"; - case ICE_ERR_INVAL_SIZE: - return "ICE_ERR_INVAL_SIZE"; - case ICE_ERR_DEVICE_NOT_SUPPORTED: - return "ICE_ERR_DEVICE_NOT_SUPPORTED"; - case ICE_ERR_RESET_FAILED: - return "ICE_ERR_RESET_FAILED"; - case ICE_ERR_FW_API_VER: - return "ICE_ERR_FW_API_VER"; - case ICE_ERR_NO_MEMORY: - return "ICE_ERR_NO_MEMORY"; - case ICE_ERR_CFG: - return "ICE_ERR_CFG"; - case ICE_ERR_OUT_OF_RANGE: - return "ICE_ERR_OUT_OF_RANGE"; - case ICE_ERR_ALREADY_EXISTS: - return "ICE_ERR_ALREADY_EXISTS"; - case ICE_ERR_NVM: - return "ICE_ERR_NVM"; - case ICE_ERR_NVM_CHECKSUM: - return "ICE_ERR_NVM_CHECKSUM"; - case ICE_ERR_BUF_TOO_SHORT: - return "ICE_ERR_BUF_TOO_SHORT"; - case ICE_ERR_NVM_BLANK_MODE: - return "ICE_ERR_NVM_BLANK_MODE"; - case ICE_ERR_IN_USE: - return "ICE_ERR_IN_USE"; - case ICE_ERR_MAX_LIMIT: - return "ICE_ERR_MAX_LIMIT"; - case ICE_ERR_RESET_ONGOING: - return "ICE_ERR_RESET_ONGOING"; - case ICE_ERR_HW_TABLE: - return "ICE_ERR_HW_TABLE"; - case ICE_ERR_DOES_NOT_EXIST: - return "ICE_ERR_DOES_NOT_EXIST"; - case ICE_ERR_FW_DDP_MISMATCH: - return "ICE_ERR_FW_DDP_MISMATCH"; - case ICE_ERR_AQ_ERROR: - return "ICE_ERR_AQ_ERROR"; - case ICE_ERR_AQ_TIMEOUT: - return "ICE_ERR_AQ_TIMEOUT"; - case ICE_ERR_AQ_FULL: - return "ICE_ERR_AQ_FULL"; - case ICE_ERR_AQ_NO_WORK: - return "ICE_ERR_AQ_NO_WORK"; - case ICE_ERR_AQ_EMPTY: - return "ICE_ERR_AQ_EMPTY"; - case ICE_ERR_AQ_FW_CRITICAL: - return "ICE_ERR_AQ_FW_CRITICAL"; - } - - return "ICE_ERR_UNKNOWN"; -} - -/** * ice_set_rss_lut - Set RSS LUT * @vsi: Pointer to VSI structure * @lut: Lookup table @@ -7030,7 +6925,7 @@ int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) { struct ice_aq_get_set_rss_lut_params params = {}; struct ice_hw *hw = &vsi->back->hw; - enum ice_status status; + int status; if (!lut) return -EINVAL; @@ -7041,14 +6936,11 @@ int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) params.lut = lut; status = ice_aq_set_rss_lut(hw, ¶ms); - if (status) { - dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS lut, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - return -EIO; - } + if (status) + dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS lut, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); - return 0; + return status; } /** @@ -7061,20 +6953,17 @@ int ice_set_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) int ice_set_rss_key(struct ice_vsi *vsi, u8 *seed) { struct ice_hw *hw = &vsi->back->hw; - enum ice_status status; + int status; if (!seed) return -EINVAL; status = ice_aq_set_rss_key(hw, vsi->idx, (struct ice_aqc_get_set_rss_keys *)seed); - if (status) { - dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS key, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - return -EIO; - } + if (status) + dev_err(ice_pf_to_dev(vsi->back), "Cannot set RSS key, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); - return 0; + return status; } /** @@ -7089,7 +6978,7 @@ int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) { struct ice_aq_get_set_rss_lut_params params = {}; struct ice_hw *hw = &vsi->back->hw; - enum ice_status status; + int status; if (!lut) return -EINVAL; @@ -7100,14 +6989,11 @@ int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) params.lut = lut; status = ice_aq_get_rss_lut(hw, ¶ms); - if (status) { - dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS lut, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - return -EIO; - } + if (status) + dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS lut, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); - return 0; + return status; } /** @@ -7120,20 +7006,17 @@ int ice_get_rss_lut(struct ice_vsi *vsi, u8 *lut, u16 lut_size) int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed) { struct ice_hw *hw = &vsi->back->hw; - enum ice_status status; + int status; if (!seed) return -EINVAL; status = ice_aq_get_rss_key(hw, vsi->idx, (struct ice_aqc_get_set_rss_keys *)seed); - if (status) { - dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS key, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - return -EIO; - } + if (status) + dev_err(ice_pf_to_dev(vsi->back), "Cannot get RSS key, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); - return 0; + return status; } /** @@ -7174,8 +7057,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) struct ice_aqc_vsi_props *vsi_props; struct ice_hw *hw = &vsi->back->hw; struct ice_vsi_ctx *ctxt; - enum ice_status status; - int ret = 0; + int ret; vsi_props = &vsi->info; @@ -7193,12 +7075,10 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) ctxt->info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB; ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); - status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); - if (status) { - dev_err(ice_pf_to_dev(vsi->back), "update VSI for bridge mode failed, bmode = %d err %s aq_err %s\n", - bmode, ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - ret = -EIO; + ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (ret) { + dev_err(ice_pf_to_dev(vsi->back), "update VSI for bridge mode failed, bmode = %d err %d aq_err %s\n", + bmode, ret, ice_aq_str(hw->adminq.sq_last_status)); goto out; } /* Update sw flags for book keeping */ @@ -7230,7 +7110,6 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, struct ice_pf *pf = np->vsi->back; struct nlattr *attr, *br_spec; struct ice_hw *hw = &pf->hw; - enum ice_status status; struct ice_sw *pf_sw; int rem, v, err = 0; @@ -7264,14 +7143,14 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, /* Update the unicast switch filter rules for the corresponding * switch of the netdev */ - status = ice_update_sw_rule_bridge_mode(hw); - if (status) { - netdev_err(dev, "switch rule update failed, mode = %d err %s aq_err %s\n", - mode, ice_stat_str(status), + err = ice_update_sw_rule_bridge_mode(hw); + if (err) { + netdev_err(dev, "switch rule update failed, mode = %d err %d aq_err %s\n", + mode, err, ice_aq_str(hw->adminq.sq_last_status)); /* revert hw->evb_veb */ hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB); - return -EIO; + return err; } pf_sw->bridge_mode = mode; @@ -8446,7 +8325,6 @@ int ice_open_internal(struct net_device *netdev) struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_port_info *pi; - enum ice_status status; int err; if (test_bit(ICE_NEEDS_RESTART, pf->state)) { @@ -8457,11 +8335,10 @@ int ice_open_internal(struct net_device *netdev) netif_carrier_off(netdev); pi = vsi->port_info; - status = ice_update_link_info(pi); - if (status) { - netdev_err(netdev, "Failed to get link info, error %s\n", - ice_stat_str(status)); - return -EIO; + err = ice_update_link_info(pi); + if (err) { + netdev_err(netdev, "Failed to get link info, error %d\n", err); + return err; } ice_check_link_cfg_err(pf, pi->phy.link_info.link_cfg_err); diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index fee37a5844cf..cd739a2c64e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -16,7 +16,7 @@ * * Read the NVM using the admin queue commands (0x0701) */ -static enum ice_status +static int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length, void *data, bool last_command, bool read_shadow_ram, struct ice_sq_cd *cd) @@ -27,7 +27,7 @@ ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length, cmd = &desc.params.nvm; if (offset > ICE_AQC_NVM_MAX_OFFSET) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_read); @@ -60,21 +60,21 @@ ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length, * Returns a status code on failure. Note that the data pointer may be * partially updated if some reads succeed before a failure. */ -enum ice_status +int ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data, bool read_shadow_ram) { - enum ice_status status; u32 inlen = *length; u32 bytes_read = 0; bool last_cmd; + int status; *length = 0; /* Verify the length of the read if this is for the Shadow RAM */ if (read_shadow_ram && ((offset + inlen) > (hw->flash.sr_words * 2u))) { ice_debug(hw, ICE_DBG_NVM, "NVM error: requested offset is beyond Shadow RAM limit\n"); - return ICE_ERR_PARAM; + return -EINVAL; } do { @@ -119,7 +119,7 @@ ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data, * * Update the NVM using the admin queue commands (0x0703) */ -enum ice_status +int ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length, void *data, bool last_command, u8 command_flags, struct ice_sq_cd *cd) @@ -131,7 +131,7 @@ ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, /* In offset the highest byte must be zeroed. */ if (offset & 0xFF000000) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_write); @@ -158,8 +158,7 @@ ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, * * Erase the NVM sector using the admin queue commands (0x0702) */ -enum ice_status -ice_aq_erase_nvm(struct ice_hw *hw, u16 module_typeid, struct ice_sq_cd *cd) +int ice_aq_erase_nvm(struct ice_hw *hw, u16 module_typeid, struct ice_sq_cd *cd) { struct ice_aq_desc desc; struct ice_aqc_nvm *cmd; @@ -184,12 +183,11 @@ ice_aq_erase_nvm(struct ice_hw *hw, u16 module_typeid, struct ice_sq_cd *cd) * * Reads one 16 bit word from the Shadow RAM using ice_read_flat_nvm. */ -static enum ice_status -ice_read_sr_word_aq(struct ice_hw *hw, u16 offset, u16 *data) +static int ice_read_sr_word_aq(struct ice_hw *hw, u16 offset, u16 *data) { u32 bytes = sizeof(u16); - enum ice_status status; __le16 data_local; + int status; /* Note that ice_read_flat_nvm takes into account the 4Kb AdminQ and * Shadow RAM sector restrictions necessary when reading from the NVM. @@ -210,8 +208,7 @@ ice_read_sr_word_aq(struct ice_hw *hw, u16 offset, u16 *data) * * This function will request NVM ownership. */ -enum ice_status -ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access) +int ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access) { if (hw->flash.blank_nvm_mode) return 0; @@ -318,18 +315,18 @@ static u32 ice_get_flash_bank_offset(struct ice_hw *hw, enum ice_bank_select ban * hw->flash.banks data being setup by ice_determine_active_flash_banks() * during initialization. */ -static enum ice_status +static int ice_read_flash_module(struct ice_hw *hw, enum ice_bank_select bank, u16 module, u32 offset, u8 *data, u32 length) { - enum ice_status status; + int status; u32 start; start = ice_get_flash_bank_offset(hw, bank, module); if (!start) { ice_debug(hw, ICE_DBG_NVM, "Unable to calculate flash bank offset for module 0x%04x\n", module); - return ICE_ERR_PARAM; + return -EINVAL; } status = ice_acquire_nvm(hw, ICE_RES_READ); @@ -353,11 +350,11 @@ ice_read_flash_module(struct ice_hw *hw, enum ice_bank_select bank, u16 module, * Read the specified word from the active NVM module. This includes the CSS * header at the start of the NVM module. */ -static enum ice_status +static int ice_read_nvm_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u16 *data) { - enum ice_status status; __le16 data_local; + int status; status = ice_read_flash_module(hw, bank, ICE_SR_1ST_NVM_BANK_PTR, offset * sizeof(u16), (__force u8 *)&data_local, sizeof(u16)); @@ -377,7 +374,7 @@ ice_read_nvm_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u1 * Read the specified word from the copy of the Shadow RAM found in the * specified NVM module. */ -static enum ice_status +static int ice_read_nvm_sr_copy(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u16 *data) { return ice_read_nvm_module(hw, bank, ICE_NVM_SR_COPY_WORD_OFFSET + offset, data); @@ -392,11 +389,11 @@ ice_read_nvm_sr_copy(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u * * Read a word from the specified netlist bank. */ -static enum ice_status +static int ice_read_netlist_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u16 *data) { - enum ice_status status; __le16 data_local; + int status; status = ice_read_flash_module(hw, bank, ICE_SR_NETLIST_BANK_PTR, offset * sizeof(u16), (__force u8 *)&data_local, sizeof(u16)); @@ -414,9 +411,9 @@ ice_read_netlist_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset * * Reads one 16 bit word from the Shadow RAM using the ice_read_sr_word_aq. */ -enum ice_status ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data) +int ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data) { - enum ice_status status; + int status; status = ice_acquire_nvm(hw, ICE_RES_READ); if (!status) { @@ -438,13 +435,13 @@ enum ice_status ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data) * Area (PFA) and returns the TLV pointer and length. The caller can * use these to read the variable length TLV value. */ -enum ice_status +int ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, u16 module_type) { - enum ice_status status; u16 pfa_len, pfa_ptr; u16 next_tlv; + int status; status = ice_read_sr_word(hw, ICE_SR_PFA_PTR, &pfa_ptr); if (status) { @@ -482,7 +479,7 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, *module_tlv_len = tlv_len; return 0; } - return ICE_ERR_INVAL_SIZE; + return -EINVAL; } /* Check next TLV, i.e. current TLV pointer + length + 2 words * (for current TLV's type and length) @@ -490,7 +487,7 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, next_tlv = next_tlv + tlv_len + 2; } /* Module does not exist */ - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; } /** @@ -501,12 +498,11 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, * * Reads the part number string from the NVM. */ -enum ice_status -ice_read_pba_string(struct ice_hw *hw, u8 *pba_num, u32 pba_num_size) +int ice_read_pba_string(struct ice_hw *hw, u8 *pba_num, u32 pba_num_size) { u16 pba_tlv, pba_tlv_len; - enum ice_status status; u16 pba_word, pba_size; + int status; u16 i; status = ice_get_pfa_module_tlv(hw, &pba_tlv, &pba_tlv_len, @@ -525,7 +521,7 @@ ice_read_pba_string(struct ice_hw *hw, u8 *pba_num, u32 pba_num_size) if (pba_tlv_len < pba_size) { ice_debug(hw, ICE_DBG_INIT, "Invalid PBA Block TLV size.\n"); - return ICE_ERR_INVAL_SIZE; + return -EINVAL; } /* Subtract one to get PBA word count (PBA Size word is included in @@ -534,7 +530,7 @@ ice_read_pba_string(struct ice_hw *hw, u8 *pba_num, u32 pba_num_size) pba_size--; if (pba_num_size < (((u32)pba_size * 2) + 1)) { ice_debug(hw, ICE_DBG_INIT, "Buffer too small for PBA data.\n"); - return ICE_ERR_PARAM; + return -EINVAL; } for (i = 0; i < pba_size; i++) { @@ -561,11 +557,11 @@ ice_read_pba_string(struct ice_hw *hw, u8 *pba_num, u32 pba_num_size) * Read the NVM EETRACK ID and map version of the main NVM image bank, filling * in the NVM info structure. */ -static enum ice_status +static int ice_get_nvm_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_nvm_info *nvm) { u16 eetrack_lo, eetrack_hi, ver; - enum ice_status status; + int status; status = ice_read_nvm_sr_copy(hw, bank, ICE_SR_NVM_DEV_STARTER_VER, &ver); if (status) { @@ -601,7 +597,7 @@ ice_get_nvm_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_nv * inactive NVM bank. Used to access version data for a pending update that * has not yet been activated. */ -enum ice_status ice_get_inactive_nvm_ver(struct ice_hw *hw, struct ice_nvm_info *nvm) +int ice_get_inactive_nvm_ver(struct ice_hw *hw, struct ice_nvm_info *nvm) { return ice_get_nvm_ver_info(hw, ICE_INACTIVE_FLASH_BANK, nvm); } @@ -615,49 +611,73 @@ enum ice_status ice_get_inactive_nvm_ver(struct ice_hw *hw, struct ice_nvm_info * Searches through the Option ROM flash contents to locate the CIVD data for * the image. */ -static enum ice_status +static int ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank, struct ice_orom_civd_info *civd) { - struct ice_orom_civd_info tmp; - enum ice_status status; + u8 *orom_data; + int status; u32 offset; /* The CIVD section is located in the Option ROM aligned to 512 bytes. * The first 4 bytes must contain the ASCII characters "$CIV". * A simple modulo 256 sum of all of the bytes of the structure must * equal 0. + * + * The exact location is unknown and varies between images but is + * usually somewhere in the middle of the bank. We need to scan the + * Option ROM bank to locate it. + * + * It's significantly faster to read the entire Option ROM up front + * using the maximum page size, than to read each possible location + * with a separate firmware command. */ + orom_data = vzalloc(hw->flash.banks.orom_size); + if (!orom_data) + return -ENOMEM; + + status = ice_read_flash_module(hw, bank, ICE_SR_1ST_OROM_BANK_PTR, 0, + orom_data, hw->flash.banks.orom_size); + if (status) { + ice_debug(hw, ICE_DBG_NVM, "Unable to read Option ROM data\n"); + return status; + } + + /* Scan the memory buffer to locate the CIVD data section */ for (offset = 0; (offset + 512) <= hw->flash.banks.orom_size; offset += 512) { + struct ice_orom_civd_info *tmp; u8 sum = 0, i; - status = ice_read_flash_module(hw, bank, ICE_SR_1ST_OROM_BANK_PTR, - offset, (u8 *)&tmp, sizeof(tmp)); - if (status) { - ice_debug(hw, ICE_DBG_NVM, "Unable to read Option ROM CIVD data\n"); - return status; - } + tmp = (struct ice_orom_civd_info *)&orom_data[offset]; /* Skip forward until we find a matching signature */ - if (memcmp("$CIV", tmp.signature, sizeof(tmp.signature)) != 0) + if (memcmp("$CIV", tmp->signature, sizeof(tmp->signature)) != 0) continue; + ice_debug(hw, ICE_DBG_NVM, "Found CIVD section at offset %u\n", + offset); + /* Verify that the simple checksum is zero */ - for (i = 0; i < sizeof(tmp); i++) + for (i = 0; i < sizeof(*tmp); i++) /* cppcheck-suppress objectIndex */ - sum += ((u8 *)&tmp)[i]; + sum += ((u8 *)tmp)[i]; if (sum) { ice_debug(hw, ICE_DBG_NVM, "Found CIVD data with invalid checksum of %u\n", sum); - return ICE_ERR_NVM; + goto err_invalid_checksum; } - *civd = tmp; + *civd = *tmp; + vfree(orom_data); return 0; } - return ICE_ERR_NVM; + ice_debug(hw, ICE_DBG_NVM, "Unable to locate CIVD data within the Option ROM\n"); + +err_invalid_checksum: + vfree(orom_data); + return -EIO; } /** @@ -669,12 +689,12 @@ ice_get_orom_civd_data(struct ice_hw *hw, enum ice_bank_select bank, * Read Option ROM version and security revision from the Option ROM flash * section. */ -static enum ice_status +static int ice_get_orom_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_orom_info *orom) { struct ice_orom_civd_info civd; - enum ice_status status; u32 combo_ver; + int status; status = ice_get_orom_civd_data(hw, bank, &civd); if (status) { @@ -700,7 +720,7 @@ ice_get_orom_ver_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_o * section of flash. Used to access version data for a pending update that has * not yet been activated. */ -enum ice_status ice_get_inactive_orom_ver(struct ice_hw *hw, struct ice_orom_info *orom) +int ice_get_inactive_orom_ver(struct ice_hw *hw, struct ice_orom_info *orom) { return ice_get_orom_ver_info(hw, ICE_INACTIVE_FLASH_BANK, orom); } @@ -715,13 +735,13 @@ enum ice_status ice_get_inactive_orom_ver(struct ice_hw *hw, struct ice_orom_inf * Topology section to find the Netlist ID block and extract the relevant * information into the netlist version structure. */ -static enum ice_status +static int ice_get_netlist_info(struct ice_hw *hw, enum ice_bank_select bank, struct ice_netlist_info *netlist) { u16 module_id, length, node_count, i; - enum ice_status status; u16 *id_blk; + int status; status = ice_read_netlist_module(hw, bank, ICE_NETLIST_TYPE_OFFSET, &module_id); if (status) @@ -730,7 +750,7 @@ ice_get_netlist_info(struct ice_hw *hw, enum ice_bank_select bank, if (module_id != ICE_NETLIST_LINK_TOPO_MOD_ID) { ice_debug(hw, ICE_DBG_NVM, "Expected netlist module_id ID of 0x%04x, but got 0x%04x\n", ICE_NETLIST_LINK_TOPO_MOD_ID, module_id); - return ICE_ERR_NVM; + return -EIO; } status = ice_read_netlist_module(hw, bank, ICE_LINK_TOPO_MODULE_LEN, &length); @@ -741,7 +761,7 @@ ice_get_netlist_info(struct ice_hw *hw, enum ice_bank_select bank, if (length < ICE_NETLIST_ID_BLK_SIZE) { ice_debug(hw, ICE_DBG_NVM, "Netlist Link Topology module too small. Expected at least %u words, but got %u words.\n", ICE_NETLIST_ID_BLK_SIZE, length); - return ICE_ERR_NVM; + return -EIO; } status = ice_read_netlist_module(hw, bank, ICE_LINK_TOPO_NODE_COUNT, &node_count); @@ -751,7 +771,7 @@ ice_get_netlist_info(struct ice_hw *hw, enum ice_bank_select bank, id_blk = kcalloc(ICE_NETLIST_ID_BLK_SIZE, sizeof(*id_blk), GFP_KERNEL); if (!id_blk) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Read out the entire Netlist ID Block at once. */ status = ice_read_flash_module(hw, bank, ICE_SR_NETLIST_BANK_PTR, @@ -791,7 +811,7 @@ exit_error: * extract version data of a pending flash update in order to display the * version data. */ -enum ice_status ice_get_inactive_netlist_ver(struct ice_hw *hw, struct ice_netlist_info *netlist) +int ice_get_inactive_netlist_ver(struct ice_hw *hw, struct ice_netlist_info *netlist) { return ice_get_netlist_info(hw, ICE_INACTIVE_FLASH_BANK, netlist); } @@ -804,10 +824,10 @@ enum ice_status ice_get_inactive_netlist_ver(struct ice_hw *hw, struct ice_netli * the actual size is smaller. Use bisection to determine the accessible size * of flash memory. */ -static enum ice_status ice_discover_flash_size(struct ice_hw *hw) +static int ice_discover_flash_size(struct ice_hw *hw) { u32 min_size = 0, max_size = ICE_AQC_NVM_MAX_OFFSET + 1; - enum ice_status status; + int status; status = ice_acquire_nvm(hw, ICE_RES_READ); if (status) @@ -819,7 +839,7 @@ static enum ice_status ice_discover_flash_size(struct ice_hw *hw) u8 data; status = ice_read_flat_nvm(hw, offset, &len, &data, false); - if (status == ICE_ERR_AQ_ERROR && + if (status == -EIO && hw->adminq.sq_last_status == ICE_AQ_RC_EINVAL) { ice_debug(hw, ICE_DBG_NVM, "%s: New upper bound of %u bytes\n", __func__, offset); @@ -859,10 +879,9 @@ err_read_flat_nvm: * sector size by using the highest bit. The reported pointer value will be in * bytes, intended for flat NVM reads. */ -static enum ice_status -ice_read_sr_pointer(struct ice_hw *hw, u16 offset, u32 *pointer) +static int ice_read_sr_pointer(struct ice_hw *hw, u16 offset, u32 *pointer) { - enum ice_status status; + int status; u16 value; status = ice_read_sr_word(hw, offset, &value); @@ -891,10 +910,9 @@ ice_read_sr_pointer(struct ice_hw *hw, u16 offset, u32 *pointer) * Each area size word is specified in 4KB sector units. This function reports * the size in bytes, intended for flat NVM reads. */ -static enum ice_status -ice_read_sr_area_size(struct ice_hw *hw, u16 offset, u32 *size) +static int ice_read_sr_area_size(struct ice_hw *hw, u16 offset, u32 *size) { - enum ice_status status; + int status; u16 value; status = ice_read_sr_word(hw, offset, &value); @@ -917,12 +935,11 @@ ice_read_sr_area_size(struct ice_hw *hw, u16 offset, u32 *size) * structure for later use in order to calculate the correct offset to read * from the active module. */ -static enum ice_status -ice_determine_active_flash_banks(struct ice_hw *hw) +static int ice_determine_active_flash_banks(struct ice_hw *hw) { struct ice_bank_info *banks = &hw->flash.banks; - enum ice_status status; u16 ctrl_word; + int status; status = ice_read_sr_word(hw, ICE_SR_NVM_CTRL_WORD, &ctrl_word); if (status) { @@ -933,7 +950,7 @@ ice_determine_active_flash_banks(struct ice_hw *hw) /* Check that the control word indicates validity */ if ((ctrl_word & ICE_SR_CTRL_WORD_1_M) >> ICE_SR_CTRL_WORD_1_S != ICE_SR_CTRL_WORD_VALID) { ice_debug(hw, ICE_DBG_NVM, "Shadow RAM control word is invalid\n"); - return ICE_ERR_CFG; + return -EIO; } if (!(ctrl_word & ICE_SR_CTRL_WORD_NVM_BANK)) @@ -997,12 +1014,12 @@ ice_determine_active_flash_banks(struct ice_hw *hw) * This function reads and populates NVM settings such as Shadow RAM size, * max_timeout, and blank_nvm_mode */ -enum ice_status ice_init_nvm(struct ice_hw *hw) +int ice_init_nvm(struct ice_hw *hw) { struct ice_flash_info *flash = &hw->flash; - enum ice_status status; u32 fla, gens_stat; u8 sr_size; + int status; /* The SR size is stored regardless of the NVM programming mode * as the blank mode may be used in the factory line. @@ -1021,7 +1038,7 @@ enum ice_status ice_init_nvm(struct ice_hw *hw) /* Blank programming mode */ flash->blank_nvm_mode = true; ice_debug(hw, ICE_DBG_NVM, "NVM init error: unsupported blank mode.\n"); - return ICE_ERR_NVM_BLANK_MODE; + return -EIO; } status = ice_discover_flash_size(hw); @@ -1060,11 +1077,11 @@ enum ice_status ice_init_nvm(struct ice_hw *hw) * * Verify NVM PFA checksum validity (0x0706) */ -enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw) +int ice_nvm_validate_checksum(struct ice_hw *hw) { struct ice_aqc_nvm_checksum *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; status = ice_acquire_nvm(hw, ICE_RES_READ); if (status) @@ -1080,7 +1097,7 @@ enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw) if (!status) if (le16_to_cpu(cmd->checksum) != ICE_AQC_NVM_CHECKSUM_CORRECT) - status = ICE_ERR_NVM_CHECKSUM; + status = -EIO; return status; } @@ -1088,22 +1105,35 @@ enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw) /** * ice_nvm_write_activate * @hw: pointer to the HW struct - * @cmd_flags: NVM activate admin command bits (banks to be validated) + * @cmd_flags: flags for write activate command + * @response_flags: response indicators from firmware * * Update the control word with the required banks' validity bits * and dumps the Shadow RAM to flash (0x0707) + * + * cmd_flags controls which banks to activate, and the preservation level to + * use when activating the NVM bank. + * + * On successful return of the firmware command, the response_flags variable + * is updated with the flags reported by firmware indicating certain status, + * such as whether EMP reset is enabled. */ -enum ice_status ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags) +int ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags, u8 *response_flags) { struct ice_aqc_nvm *cmd; struct ice_aq_desc desc; + int err; cmd = &desc.params.nvm; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_write_activate); cmd->cmd_flags = cmd_flags; - return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + err = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (!err && response_flags) + *response_flags = cmd->cmd_flags; + + return err; } /** @@ -1113,7 +1143,7 @@ enum ice_status ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags) * Update empr (0x0709). This command allows SW to * request an EMPR to activate new FW. */ -enum ice_status ice_aq_nvm_update_empr(struct ice_hw *hw) +int ice_aq_nvm_update_empr(struct ice_hw *hw) { struct ice_aq_desc desc; @@ -1136,7 +1166,7 @@ enum ice_status ice_aq_nvm_update_empr(struct ice_hw *hw) * as part of the NVM update as the first cmd in the flow. */ -enum ice_status +int ice_nvm_set_pkg_data(struct ice_hw *hw, bool del_pkg_data_flag, u8 *data, u16 length, struct ice_sq_cd *cd) { @@ -1144,7 +1174,7 @@ ice_nvm_set_pkg_data(struct ice_hw *hw, bool del_pkg_data_flag, u8 *data, struct ice_aq_desc desc; if (length != 0 && !data) - return ICE_ERR_PARAM; + return -EINVAL; cmd = &desc.params.pkg_data; @@ -1173,17 +1203,17 @@ ice_nvm_set_pkg_data(struct ice_hw *hw, bool del_pkg_data_flag, u8 *data, * the TransferFlag is set to End or StartAndEnd. */ -enum ice_status +int ice_nvm_pass_component_tbl(struct ice_hw *hw, u8 *data, u16 length, u8 transfer_flag, u8 *comp_response, u8 *comp_response_code, struct ice_sq_cd *cd) { struct ice_aqc_nvm_pass_comp_tbl *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; if (!data || !comp_response || !comp_response_code) - return ICE_ERR_PARAM; + return -EINVAL; cmd = &desc.params.pass_comp_tbl; diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.h b/drivers/net/ethernet/intel/ice/ice_nvm.h index c6f05f43d593..856d1ad4398b 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.h +++ b/drivers/net/ethernet/intel/ice/ice_nvm.h @@ -12,38 +12,34 @@ struct ice_orom_civd_info { __le16 combo_name[32]; /* Unicode string representing the Combo Image version */ } __packed; -enum ice_status -ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access); +int ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access); void ice_release_nvm(struct ice_hw *hw); -enum ice_status +int ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data, bool read_shadow_ram); -enum ice_status +int ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len, u16 module_type); -enum ice_status -ice_get_inactive_orom_ver(struct ice_hw *hw, struct ice_orom_info *orom); -enum ice_status -ice_get_inactive_nvm_ver(struct ice_hw *hw, struct ice_nvm_info *nvm); -enum ice_status +int ice_get_inactive_orom_ver(struct ice_hw *hw, struct ice_orom_info *orom); +int ice_get_inactive_nvm_ver(struct ice_hw *hw, struct ice_nvm_info *nvm); +int ice_get_inactive_netlist_ver(struct ice_hw *hw, struct ice_netlist_info *netlist); -enum ice_status -ice_read_pba_string(struct ice_hw *hw, u8 *pba_num, u32 pba_num_size); -enum ice_status ice_init_nvm(struct ice_hw *hw); -enum ice_status ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data); -enum ice_status +int ice_read_pba_string(struct ice_hw *hw, u8 *pba_num, u32 pba_num_size); +int ice_init_nvm(struct ice_hw *hw); +int ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data); +int ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset, u16 length, void *data, bool last_command, u8 command_flags, struct ice_sq_cd *cd); -enum ice_status +int ice_aq_erase_nvm(struct ice_hw *hw, u16 module_typeid, struct ice_sq_cd *cd); -enum ice_status ice_nvm_validate_checksum(struct ice_hw *hw); -enum ice_status ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags); -enum ice_status ice_aq_nvm_update_empr(struct ice_hw *hw); -enum ice_status +int ice_nvm_validate_checksum(struct ice_hw *hw); +int ice_nvm_write_activate(struct ice_hw *hw, u8 cmd_flags, u8 *response_flags); +int ice_aq_nvm_update_empr(struct ice_hw *hw); +int ice_nvm_set_pkg_data(struct ice_hw *hw, bool del_pkg_data_flag, u8 *data, u16 length, struct ice_sq_cd *cd); -enum ice_status +int ice_nvm_pass_component_tbl(struct ice_hw *hw, u8 *data, u16 length, u8 transfer_flag, u8 *comp_response, u8 *comp_response_code, struct ice_sq_cd *cd); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index bf7247c6f58e..0014a1002ed3 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -705,7 +705,7 @@ static int ice_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) scaled_ppm = -scaled_ppm; } - while ((u64)scaled_ppm > div_u64(U64_MAX, incval)) { + while ((u64)scaled_ppm > div64_u64(U64_MAX, incval)) { /* handle overflow by scaling down the scaled_ppm and * the divisor, losing some precision */ @@ -1205,10 +1205,6 @@ int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr) static int ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) { - /* Reserved for future extensions. */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: ice_set_tx_tstamp(pf, false); @@ -1540,19 +1536,16 @@ static void ice_ptp_tx_tstamp_work(struct kthread_work *work) if (err) continue; - /* Check if the timestamp is valid */ - if (!(raw_tstamp & ICE_PTP_TS_VALID)) + /* Check if the timestamp is invalid or stale */ + if (!(raw_tstamp & ICE_PTP_TS_VALID) || + raw_tstamp == tx->tstamps[idx].cached_tstamp) continue; - /* clear the timestamp register, so that it won't show valid - * again when re-used. - */ - ice_clear_phy_tstamp(hw, tx->quad, phy_idx); - /* The timestamp is valid, so we'll go ahead and clear this * index and then send the timestamp up to the stack. */ spin_lock(&tx->lock); + tx->tstamps[idx].cached_tstamp = raw_tstamp; clear_bit(idx, tx->in_use); skb = tx->tstamps[idx].skb; tx->tstamps[idx].skb = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index f71ad317d6c8..53c15fc9d996 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -55,15 +55,21 @@ struct ice_perout_channel { * struct ice_tx_tstamp - Tracking for a single Tx timestamp * @skb: pointer to the SKB for this timestamp request * @start: jiffies when the timestamp was first requested + * @cached_tstamp: last read timestamp * * This structure tracks a single timestamp request. The SKB pointer is * provided when initiating a request. The start time is used to ensure that * we discard old requests that were not fulfilled within a 2 second time * window. + * Timestamp values in the PHY are read only and do not get cleared except at + * hardware reset or when a new timestamp value is captured. The cached_tstamp + * field is used to detect the case where a new timestamp has not yet been + * captured, ensuring that we avoid sending stale timestamp data to the stack. */ struct ice_tx_tstamp { struct sk_buff *skb; unsigned long start; + u64 cached_tstamp; }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index ce3c7bded4cb..7947223536e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -11,7 +11,7 @@ * This function inserts the root node of the scheduling tree topology * to the SW DB. */ -static enum ice_status +static int ice_sched_add_root_node(struct ice_port_info *pi, struct ice_aqc_txsched_elem_data *info) { @@ -19,20 +19,20 @@ ice_sched_add_root_node(struct ice_port_info *pi, struct ice_hw *hw; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; hw = pi->hw; root = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*root), GFP_KERNEL); if (!root) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* coverity[suspicious_sizeof] */ root->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[0], sizeof(*root), GFP_KERNEL); if (!root->children) { devm_kfree(ice_hw_to_dev(hw), root); - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } memcpy(&root->info, info, sizeof(*info)); @@ -96,14 +96,14 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid) * * This function sends a scheduling elements cmd (cmd_opc) */ -static enum ice_status +static int ice_aqc_send_sched_elem_cmd(struct ice_hw *hw, enum ice_adminq_opc cmd_opc, u16 elems_req, void *buf, u16 buf_size, u16 *elems_resp, struct ice_sq_cd *cd) { struct ice_aqc_sched_elem_cmd *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd = &desc.params.sched_elem_cmd; ice_fill_dflt_direct_cmd_desc(&desc, cmd_opc); @@ -127,7 +127,7 @@ ice_aqc_send_sched_elem_cmd(struct ice_hw *hw, enum ice_adminq_opc cmd_opc, * * Query scheduling elements (0x0404) */ -enum ice_status +int ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req, struct ice_aqc_txsched_elem_data *buf, u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd) @@ -145,18 +145,18 @@ ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req, * * This function inserts a scheduler node to the SW DB. */ -enum ice_status +int ice_sched_add_node(struct ice_port_info *pi, u8 layer, struct ice_aqc_txsched_elem_data *info) { struct ice_aqc_txsched_elem_data elem; struct ice_sched_node *parent; struct ice_sched_node *node; - enum ice_status status; struct ice_hw *hw; + int status; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; hw = pi->hw; @@ -166,7 +166,7 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, if (!parent) { ice_debug(hw, ICE_DBG_SCHED, "Parent Node not found for parent_teid=0x%x\n", le32_to_cpu(info->parent_teid)); - return ICE_ERR_PARAM; + return -EINVAL; } /* query the current node information from FW before adding it @@ -178,7 +178,7 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, node = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*node), GFP_KERNEL); if (!node) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; if (hw->max_children[layer]) { /* coverity[suspicious_sizeof] */ node->children = devm_kcalloc(ice_hw_to_dev(hw), @@ -186,7 +186,7 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, sizeof(*node), GFP_KERNEL); if (!node->children) { devm_kfree(ice_hw_to_dev(hw), node); - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } } @@ -209,7 +209,7 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, * * Delete scheduling elements (0x040F) */ -static enum ice_status +static int ice_aq_delete_sched_elems(struct ice_hw *hw, u16 grps_req, struct ice_aqc_delete_elem *buf, u16 buf_size, u16 *grps_del, struct ice_sq_cd *cd) @@ -228,19 +228,19 @@ ice_aq_delete_sched_elems(struct ice_hw *hw, u16 grps_req, * * This function remove nodes from HW */ -static enum ice_status +static int ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, u16 num_nodes, u32 *node_teids) { struct ice_aqc_delete_elem *buf; u16 i, num_groups_removed = 0; - enum ice_status status; u16 buf_size; + int status; buf_size = struct_size(buf, teid, num_nodes); buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; buf->hdr.parent_teid = parent->info.node_teid; buf->hdr.num_elems = cpu_to_le16(num_nodes); @@ -369,14 +369,14 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) * * Get default scheduler topology (0x400) */ -static enum ice_status +static int ice_aq_get_dflt_topo(struct ice_hw *hw, u8 lport, struct ice_aqc_get_topo_elem *buf, u16 buf_size, u8 *num_branches, struct ice_sq_cd *cd) { struct ice_aqc_get_topo *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd = &desc.params.get_topo; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_dflt_topo); @@ -399,7 +399,7 @@ ice_aq_get_dflt_topo(struct ice_hw *hw, u8 lport, * * Add scheduling elements (0x0401) */ -static enum ice_status +static int ice_aq_add_sched_elems(struct ice_hw *hw, u16 grps_req, struct ice_aqc_add_elem *buf, u16 buf_size, u16 *grps_added, struct ice_sq_cd *cd) @@ -420,7 +420,7 @@ ice_aq_add_sched_elems(struct ice_hw *hw, u16 grps_req, * * Configure scheduling elements (0x0403) */ -static enum ice_status +static int ice_aq_cfg_sched_elems(struct ice_hw *hw, u16 elems_req, struct ice_aqc_txsched_elem_data *buf, u16 buf_size, u16 *elems_cfgd, struct ice_sq_cd *cd) @@ -441,7 +441,7 @@ ice_aq_cfg_sched_elems(struct ice_hw *hw, u16 elems_req, * * Move scheduling elements (0x0408) */ -static enum ice_status +static int ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req, struct ice_aqc_move_elem *buf, u16 buf_size, u16 *grps_movd, struct ice_sq_cd *cd) @@ -462,7 +462,7 @@ ice_aq_move_sched_elems(struct ice_hw *hw, u16 grps_req, * * Suspend scheduling elements (0x0409) */ -static enum ice_status +static int ice_aq_suspend_sched_elems(struct ice_hw *hw, u16 elems_req, __le32 *buf, u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd) { @@ -482,7 +482,7 @@ ice_aq_suspend_sched_elems(struct ice_hw *hw, u16 elems_req, __le32 *buf, * * resume scheduling elements (0x040A) */ -static enum ice_status +static int ice_aq_resume_sched_elems(struct ice_hw *hw, u16 elems_req, __le32 *buf, u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd) { @@ -500,7 +500,7 @@ ice_aq_resume_sched_elems(struct ice_hw *hw, u16 elems_req, __le32 *buf, * * Query scheduler resource allocation (0x0412) */ -static enum ice_status +static int ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size, struct ice_aqc_query_txsched_res_resp *buf, struct ice_sq_cd *cd) @@ -520,18 +520,18 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size, * * This function suspends or resumes HW nodes */ -static enum ice_status +static int ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, bool suspend) { u16 i, buf_size, num_elem_ret = 0; - enum ice_status status; __le32 *buf; + int status; buf_size = sizeof(*buf) * num_nodes; buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; for (i = 0; i < num_nodes; i++) buf[i] = cpu_to_le32(node_teids[i]); @@ -558,7 +558,7 @@ ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids, * @tc: TC number * @new_numqs: number of queues */ -static enum ice_status +static int ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) { struct ice_vsi_ctx *vsi_ctx; @@ -566,7 +566,7 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); if (!vsi_ctx) - return ICE_ERR_PARAM; + return -EINVAL; /* allocate LAN queue contexts */ if (!vsi_ctx->lan_q_ctx[tc]) { vsi_ctx->lan_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw), @@ -574,7 +574,7 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) sizeof(*q_ctx), GFP_KERNEL); if (!vsi_ctx->lan_q_ctx[tc]) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; vsi_ctx->num_lan_q_entries[tc] = new_numqs; return 0; } @@ -585,7 +585,7 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs, sizeof(*q_ctx), GFP_KERNEL); if (!q_ctx) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; memcpy(q_ctx, vsi_ctx->lan_q_ctx[tc], prev_num * sizeof(*q_ctx)); devm_kfree(ice_hw_to_dev(hw), vsi_ctx->lan_q_ctx[tc]); @@ -602,7 +602,7 @@ ice_alloc_lan_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) * @tc: TC number * @new_numqs: number of queues */ -static enum ice_status +static int ice_alloc_rdma_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) { struct ice_vsi_ctx *vsi_ctx; @@ -610,7 +610,7 @@ ice_alloc_rdma_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); if (!vsi_ctx) - return ICE_ERR_PARAM; + return -EINVAL; /* allocate RDMA queue contexts */ if (!vsi_ctx->rdma_q_ctx[tc]) { vsi_ctx->rdma_q_ctx[tc] = devm_kcalloc(ice_hw_to_dev(hw), @@ -618,7 +618,7 @@ ice_alloc_rdma_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) sizeof(*q_ctx), GFP_KERNEL); if (!vsi_ctx->rdma_q_ctx[tc]) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; vsi_ctx->num_rdma_q_entries[tc] = new_numqs; return 0; } @@ -629,7 +629,7 @@ ice_alloc_rdma_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) q_ctx = devm_kcalloc(ice_hw_to_dev(hw), new_numqs, sizeof(*q_ctx), GFP_KERNEL); if (!q_ctx) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; memcpy(q_ctx, vsi_ctx->rdma_q_ctx[tc], prev_num * sizeof(*q_ctx)); devm_kfree(ice_hw_to_dev(hw), vsi_ctx->rdma_q_ctx[tc]); @@ -651,14 +651,14 @@ ice_alloc_rdma_q_ctx(struct ice_hw *hw, u16 vsi_handle, u8 tc, u16 new_numqs) * * RL profile function to add, query, or remove profile(s) */ -static enum ice_status +static int ice_aq_rl_profile(struct ice_hw *hw, enum ice_adminq_opc opcode, u16 num_profiles, struct ice_aqc_rl_profile_elem *buf, u16 buf_size, u16 *num_processed, struct ice_sq_cd *cd) { struct ice_aqc_rl_profile *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd = &desc.params.rl_profile; @@ -682,7 +682,7 @@ ice_aq_rl_profile(struct ice_hw *hw, enum ice_adminq_opc opcode, * * Add RL profile (0x0410) */ -static enum ice_status +static int ice_aq_add_rl_profile(struct ice_hw *hw, u16 num_profiles, struct ice_aqc_rl_profile_elem *buf, u16 buf_size, u16 *num_profiles_added, struct ice_sq_cd *cd) @@ -702,7 +702,7 @@ ice_aq_add_rl_profile(struct ice_hw *hw, u16 num_profiles, * * Remove RL profile (0x0415) */ -static enum ice_status +static int ice_aq_remove_rl_profile(struct ice_hw *hw, u16 num_profiles, struct ice_aqc_rl_profile_elem *buf, u16 buf_size, u16 *num_profiles_removed, struct ice_sq_cd *cd) @@ -721,24 +721,24 @@ ice_aq_remove_rl_profile(struct ice_hw *hw, u16 num_profiles, * its associated parameters from HW DB,and locally. The caller needs to * hold scheduler lock. */ -static enum ice_status +static int ice_sched_del_rl_profile(struct ice_hw *hw, struct ice_aqc_rl_profile_info *rl_info) { struct ice_aqc_rl_profile_elem *buf; u16 num_profiles_removed; - enum ice_status status; u16 num_profiles = 1; + int status; if (rl_info->prof_id_ref != 0) - return ICE_ERR_IN_USE; + return -EBUSY; /* Safe to remove profile ID */ buf = &rl_info->profile; status = ice_aq_remove_rl_profile(hw, num_profiles, buf, sizeof(*buf), &num_profiles_removed, NULL); if (status || num_profiles_removed != num_profiles) - return ICE_ERR_CFG; + return -EIO; /* Delete stale entry now */ list_del(&rl_info->list_entry); @@ -763,7 +763,7 @@ static void ice_sched_clear_rl_prof(struct ice_port_info *pi) list_for_each_entry_safe(rl_prof_elem, rl_prof_tmp, &pi->rl_prof_list[ln], list_entry) { struct ice_hw *hw = pi->hw; - enum ice_status status; + int status; rl_prof_elem->prof_id_ref = 0; status = ice_sched_del_rl_profile(hw, rl_prof_elem); @@ -875,7 +875,7 @@ void ice_sched_cleanup_all(struct ice_hw *hw) * * This function add nodes to HW as well as to SW DB for a given layer */ -static enum ice_status +static int ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, struct ice_sched_node *parent, u8 layer, u16 num_nodes, u16 *num_nodes_added, u32 *first_node_teid) @@ -883,15 +883,15 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, struct ice_sched_node *prev, *new_node; struct ice_aqc_add_elem *buf; u16 i, num_groups_added = 0; - enum ice_status status = 0; struct ice_hw *hw = pi->hw; size_t buf_size; + int status = 0; u32 teid; buf_size = struct_size(buf, generic, num_nodes); buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; buf->hdr.parent_teid = parent->info.node_teid; buf->hdr.num_elems = cpu_to_le16(num_nodes); @@ -918,7 +918,7 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, ice_debug(hw, ICE_DBG_SCHED, "add node failed FW Error %d\n", hw->adminq.sq_last_status); devm_kfree(ice_hw_to_dev(hw), buf); - return ICE_ERR_CFG; + return -EIO; } *num_nodes_added = num_nodes; @@ -974,7 +974,7 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, * * Add nodes into specific HW layer. */ -static enum ice_status +static int ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, struct ice_sched_node *tc_node, struct ice_sched_node *parent, u8 layer, @@ -989,7 +989,7 @@ ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, return 0; if (!parent || layer < pi->hw->sw_entry_point_layer) - return ICE_ERR_PARAM; + return -EINVAL; /* max children per node per layer */ max_child_nodes = pi->hw->max_children[parent->tx_sched_layer]; @@ -998,8 +998,8 @@ ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, if ((parent->num_children + num_nodes) > max_child_nodes) { /* Fail if the parent is a TC node */ if (parent == tc_node) - return ICE_ERR_CFG; - return ICE_ERR_MAX_LIMIT; + return -EIO; + return -ENOSPC; } return ice_sched_add_elems(pi, tc_node, parent, layer, num_nodes, @@ -1018,7 +1018,7 @@ ice_sched_add_nodes_to_hw_layer(struct ice_port_info *pi, * * This function add nodes to a given layer. */ -static enum ice_status +static int ice_sched_add_nodes_to_layer(struct ice_port_info *pi, struct ice_sched_node *tc_node, struct ice_sched_node *parent, u8 layer, @@ -1027,7 +1027,7 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi, { u32 *first_teid_ptr = first_node_teid; u16 new_num_nodes = num_nodes; - enum ice_status status = 0; + int status = 0; *num_nodes_added = 0; while (*num_nodes_added < num_nodes) { @@ -1045,14 +1045,14 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi, if (*num_nodes_added > num_nodes) { ice_debug(pi->hw, ICE_DBG_SCHED, "added extra nodes %d %d\n", num_nodes, *num_nodes_added); - status = ICE_ERR_CFG; + status = -EIO; break; } /* break if all the nodes are added successfully */ if (!status && (*num_nodes_added == num_nodes)) break; /* break if the error is not max limit */ - if (status && status != ICE_ERR_MAX_LIMIT) + if (status && status != -ENOSPC) break; /* Exceeded the max children */ max_child_nodes = pi->hw->max_children[parent->tx_sched_layer]; @@ -1152,7 +1152,7 @@ static void ice_rm_dflt_leaf_node(struct ice_port_info *pi) } if (node && node->info.data.elem_type == ICE_AQC_ELEM_TYPE_LEAF) { u32 teid = le32_to_cpu(node->info.node_teid); - enum ice_status status; + int status; /* remove the default leaf node */ status = ice_sched_remove_elems(pi->hw, node->parent, 1, &teid); @@ -1198,23 +1198,23 @@ static void ice_sched_rm_dflt_nodes(struct ice_port_info *pi) * resources, default topology created by firmware and storing the information * in SW DB. */ -enum ice_status ice_sched_init_port(struct ice_port_info *pi) +int ice_sched_init_port(struct ice_port_info *pi) { struct ice_aqc_get_topo_elem *buf; - enum ice_status status; struct ice_hw *hw; u8 num_branches; u16 num_elems; + int status; u8 i, j; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; hw = pi->hw; /* Query the Default Topology from FW */ buf = devm_kzalloc(ice_hw_to_dev(hw), ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Query default scheduling tree topology */ status = ice_aq_get_dflt_topo(hw, pi->lport, buf, ICE_AQ_MAX_BUF_LEN, @@ -1226,7 +1226,7 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi) if (num_branches < 1 || num_branches > ICE_TXSCHED_MAX_BRANCHES) { ice_debug(hw, ICE_DBG_SCHED, "num_branches unexpected %d\n", num_branches); - status = ICE_ERR_PARAM; + status = -EINVAL; goto err_init_port; } @@ -1237,7 +1237,7 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi) if (num_elems < 1 || num_elems > ICE_AQC_TOPO_MAX_LEVEL_NUM) { ice_debug(hw, ICE_DBG_SCHED, "num_elems unexpected %d\n", num_elems); - status = ICE_ERR_PARAM; + status = -EINVAL; goto err_init_port; } @@ -1300,11 +1300,11 @@ err_init_port: * * query FW for allocated scheduler resources and store in HW struct */ -enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) +int ice_sched_query_res_alloc(struct ice_hw *hw) { struct ice_aqc_query_txsched_res_resp *buf; - enum ice_status status = 0; __le16 max_sibl; + int status = 0; u16 i; if (hw->layer_info) @@ -1312,7 +1312,7 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) buf = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*buf), GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; status = ice_aq_query_sched_res(hw, sizeof(*buf), buf, NULL); if (status) @@ -1341,7 +1341,7 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) sizeof(*hw->layer_info)), GFP_KERNEL); if (!hw->layer_info) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto sched_query_out; } @@ -1614,31 +1614,31 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes) * This function adds the VSI child nodes to tree. It gets called for * LAN and RDMA separately. */ -static enum ice_status +static int ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, struct ice_sched_node *tc_node, u16 *num_nodes, u8 owner) { struct ice_sched_node *parent, *node; struct ice_hw *hw = pi->hw; - enum ice_status status; u32 first_node_teid; u16 num_added = 0; u8 i, qgl, vsil; + int status; qgl = ice_sched_get_qgrp_layer(hw); vsil = ice_sched_get_vsi_layer(hw); parent = ice_sched_get_vsi_node(pi, tc_node, vsi_handle); for (i = vsil + 1; i <= qgl; i++) { if (!parent) - return ICE_ERR_CFG; + return -EIO; status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, i, num_nodes[i], &first_node_teid, &num_added); if (status || num_nodes[i] != num_added) - return ICE_ERR_CFG; + return -EIO; /* The newly added node can be a new parent for the next * layer nodes @@ -1717,18 +1717,18 @@ ice_sched_calc_vsi_support_nodes(struct ice_port_info *pi, * This function adds the VSI supported nodes into Tx tree including the * VSI, its parent and intermediate nodes in below layers */ -static enum ice_status +static int ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle, struct ice_sched_node *tc_node, u16 *num_nodes) { struct ice_sched_node *parent = tc_node; - enum ice_status status; u32 first_node_teid; u16 num_added = 0; u8 i, vsil; + int status; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; vsil = ice_sched_get_vsi_layer(pi->hw); for (i = pi->hw->sw_entry_point_layer; i <= vsil; i++) { @@ -1737,7 +1737,7 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle, &first_node_teid, &num_added); if (status || num_nodes[i] != num_added) - return ICE_ERR_CFG; + return -EIO; /* The newly added node can be a new parent for the next * layer nodes @@ -1749,7 +1749,7 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle, parent = parent->children[0]; if (!parent) - return ICE_ERR_CFG; + return -EIO; if (i == vsil) parent->vsi_handle = vsi_handle; @@ -1766,7 +1766,7 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_handle, * * This function adds a new VSI into scheduler tree */ -static enum ice_status +static int ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc) { u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; @@ -1774,7 +1774,7 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc) tc_node = ice_sched_get_tc_node(pi, tc); if (!tc_node) - return ICE_ERR_PARAM; + return -EINVAL; /* calculate number of supported nodes needed for this VSI */ ice_sched_calc_vsi_support_nodes(pi, tc_node, num_nodes); @@ -1794,7 +1794,7 @@ ice_sched_add_vsi_to_topo(struct ice_port_info *pi, u16 vsi_handle, u8 tc) * * This function updates the VSI child nodes based on the number of queues */ -static enum ice_status +static int ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 new_numqs, u8 owner) { @@ -1802,21 +1802,21 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, struct ice_sched_node *vsi_node; struct ice_sched_node *tc_node; struct ice_vsi_ctx *vsi_ctx; - enum ice_status status = 0; struct ice_hw *hw = pi->hw; u16 prev_numqs; + int status = 0; tc_node = ice_sched_get_tc_node(pi, tc); if (!tc_node) - return ICE_ERR_CFG; + return -EIO; vsi_node = ice_sched_get_vsi_node(pi, tc_node, vsi_handle); if (!vsi_node) - return ICE_ERR_CFG; + return -EIO; vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); if (!vsi_ctx) - return ICE_ERR_PARAM; + return -EINVAL; if (owner == ICE_SCHED_NODE_OWNER_LAN) prev_numqs = vsi_ctx->sched.max_lanq[tc]; @@ -1869,22 +1869,22 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, * enabled and VSI is in suspended state then resume the VSI back. If TC is * disabled then suspend the VSI if it is not already. */ -enum ice_status +int ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, u8 owner, bool enable) { struct ice_sched_node *vsi_node, *tc_node; struct ice_vsi_ctx *vsi_ctx; - enum ice_status status = 0; struct ice_hw *hw = pi->hw; + int status = 0; ice_debug(pi->hw, ICE_DBG_SCHED, "add/config VSI %d\n", vsi_handle); tc_node = ice_sched_get_tc_node(pi, tc); if (!tc_node) - return ICE_ERR_PARAM; + return -EINVAL; vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); if (!vsi_ctx) - return ICE_ERR_PARAM; + return -EINVAL; vsi_node = ice_sched_get_vsi_node(pi, tc_node, vsi_handle); /* suspend the VSI if TC is not enabled */ @@ -1908,7 +1908,7 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, vsi_node = ice_sched_get_vsi_node(pi, tc_node, vsi_handle); if (!vsi_node) - return ICE_ERR_CFG; + return -EIO; vsi_ctx->sched.vsi_node[tc] = vsi_node; vsi_node->in_use = true; @@ -1993,11 +1993,11 @@ static bool ice_sched_is_leaf_node_present(struct ice_sched_node *node) * This function removes the VSI and its LAN or RDMA children nodes from the * scheduler tree. */ -static enum ice_status +static int ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner) { - enum ice_status status = ICE_ERR_PARAM; struct ice_vsi_ctx *vsi_ctx; + int status = -EINVAL; u8 i; ice_debug(pi->hw, ICE_DBG_SCHED, "removing VSI %d\n", vsi_handle); @@ -2022,7 +2022,7 @@ ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner) if (ice_sched_is_leaf_node_present(vsi_node)) { ice_debug(pi->hw, ICE_DBG_SCHED, "VSI has leaf nodes in TC %d\n", i); - status = ICE_ERR_IN_USE; + status = -EBUSY; goto exit_sched_rm_vsi_cfg; } while (j < vsi_node->num_children) { @@ -2065,7 +2065,7 @@ exit_sched_rm_vsi_cfg: * This function clears the VSI and its LAN children nodes from scheduler tree * for all TCs. */ -enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle) +int ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle) { return ice_sched_rm_vsi_cfg(pi, vsi_handle, ICE_SCHED_NODE_OWNER_LAN); } @@ -2078,7 +2078,7 @@ enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle) * This function clears the VSI and its RDMA children nodes from scheduler tree * for all TCs. */ -enum ice_status ice_rm_vsi_rdma_cfg(struct ice_port_info *pi, u16 vsi_handle) +int ice_rm_vsi_rdma_cfg(struct ice_port_info *pi, u16 vsi_handle) { return ice_sched_rm_vsi_cfg(pi, vsi_handle, ICE_SCHED_NODE_OWNER_RDMA); } @@ -2188,36 +2188,36 @@ ice_sched_update_parent(struct ice_sched_node *new_parent, * * This function move the child nodes to a given parent. */ -static enum ice_status +static int ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, u16 num_items, u32 *list) { struct ice_aqc_move_elem *buf; struct ice_sched_node *node; - enum ice_status status = 0; u16 i, grps_movd = 0; struct ice_hw *hw; + int status = 0; u16 buf_len; hw = pi->hw; if (!parent || !num_items) - return ICE_ERR_PARAM; + return -EINVAL; /* Does parent have enough space */ if (parent->num_children + num_items > hw->max_children[parent->tx_sched_layer]) - return ICE_ERR_AQ_FULL; + return -ENOSPC; buf_len = struct_size(buf, teid, 1); buf = kzalloc(buf_len, GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; for (i = 0; i < num_items; i++) { node = ice_sched_find_node_by_teid(pi->root, list[i]); if (!node) { - status = ICE_ERR_PARAM; + status = -EINVAL; goto move_err_exit; } @@ -2228,7 +2228,7 @@ ice_sched_move_nodes(struct ice_port_info *pi, struct ice_sched_node *parent, status = ice_aq_move_sched_elems(hw, 1, buf, buf_len, &grps_movd, NULL); if (status && grps_movd != 1) { - status = ICE_ERR_CFG; + status = -EIO; goto move_err_exit; } @@ -2251,28 +2251,28 @@ move_err_exit: * This function moves a VSI to an aggregator node or its subtree. * Intermediate nodes may be created if required. */ -static enum ice_status +static int ice_sched_move_vsi_to_agg(struct ice_port_info *pi, u16 vsi_handle, u32 agg_id, u8 tc) { struct ice_sched_node *vsi_node, *agg_node, *tc_node, *parent; u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; u32 first_node_teid, vsi_teid; - enum ice_status status; u16 num_nodes_added; u8 aggl, vsil, i; + int status; tc_node = ice_sched_get_tc_node(pi, tc); if (!tc_node) - return ICE_ERR_CFG; + return -EIO; agg_node = ice_sched_get_agg_node(pi, tc_node, agg_id); if (!agg_node) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; vsi_node = ice_sched_get_vsi_node(pi, tc_node, vsi_handle); if (!vsi_node) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; /* Is this VSI already part of given aggregator? */ if (ice_sched_find_node_in_subtree(pi->hw, agg_node, vsi_node)) @@ -2302,7 +2302,7 @@ ice_sched_move_vsi_to_agg(struct ice_port_info *pi, u16 vsi_handle, u32 agg_id, &first_node_teid, &num_nodes_added); if (status || num_nodes[i] != num_nodes_added) - return ICE_ERR_CFG; + return -EIO; /* The newly added node can be a new parent for the next * layer nodes @@ -2314,7 +2314,7 @@ ice_sched_move_vsi_to_agg(struct ice_port_info *pi, u16 vsi_handle, u32 agg_id, parent = parent->children[0]; if (!parent) - return ICE_ERR_CFG; + return -EIO; } move_nodes: @@ -2333,14 +2333,14 @@ move_nodes: * aggregator VSI info based on passed in boolean parameter rm_vsi_info. The * caller holds the scheduler lock. */ -static enum ice_status +static int ice_move_all_vsi_to_dflt_agg(struct ice_port_info *pi, struct ice_sched_agg_info *agg_info, u8 tc, bool rm_vsi_info) { struct ice_sched_agg_vsi_info *agg_vsi_info; struct ice_sched_agg_vsi_info *tmp; - enum ice_status status = 0; + int status = 0; list_for_each_entry_safe(agg_vsi_info, tmp, &agg_info->agg_vsi_list, list_entry) { @@ -2397,7 +2397,7 @@ ice_sched_is_agg_inuse(struct ice_port_info *pi, struct ice_sched_node *node) * This function removes the aggregator node and intermediate nodes if any * from the given TC */ -static enum ice_status +static int ice_sched_rm_agg_cfg(struct ice_port_info *pi, u32 agg_id, u8 tc) { struct ice_sched_node *tc_node, *agg_node; @@ -2405,15 +2405,15 @@ ice_sched_rm_agg_cfg(struct ice_port_info *pi, u32 agg_id, u8 tc) tc_node = ice_sched_get_tc_node(pi, tc); if (!tc_node) - return ICE_ERR_CFG; + return -EIO; agg_node = ice_sched_get_agg_node(pi, tc_node, agg_id); if (!agg_node) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; /* Can't remove the aggregator node if it has children */ if (ice_sched_is_agg_inuse(pi, agg_node)) - return ICE_ERR_IN_USE; + return -EBUSY; /* need to remove the whole subtree if aggregator node is the * only child. @@ -2422,7 +2422,7 @@ ice_sched_rm_agg_cfg(struct ice_port_info *pi, u32 agg_id, u8 tc) struct ice_sched_node *parent = agg_node->parent; if (!parent) - return ICE_ERR_CFG; + return -EIO; if (parent->num_children > 1) break; @@ -2445,11 +2445,11 @@ ice_sched_rm_agg_cfg(struct ice_port_info *pi, u32 agg_id, u8 tc) * the aggregator configuration completely for requested TC. The caller needs * to hold the scheduler lock. */ -static enum ice_status +static int ice_rm_agg_cfg_tc(struct ice_port_info *pi, struct ice_sched_agg_info *agg_info, u8 tc, bool rm_vsi_info) { - enum ice_status status = 0; + int status = 0; /* If nothing to remove - return success */ if (!ice_is_tc_ena(agg_info->tc_bitmap[0], tc)) @@ -2478,7 +2478,7 @@ exit_rm_agg_cfg_tc: * Save aggregator TC bitmap. This function needs to be called with scheduler * lock held. */ -static enum ice_status +static int ice_save_agg_tc_bitmap(struct ice_port_info *pi, u32 agg_id, unsigned long *tc_bitmap) { @@ -2486,7 +2486,7 @@ ice_save_agg_tc_bitmap(struct ice_port_info *pi, u32 agg_id, agg_info = ice_get_agg_info(pi->hw, agg_id); if (!agg_info) - return ICE_ERR_PARAM; + return -EINVAL; bitmap_copy(agg_info->replay_tc_bitmap, tc_bitmap, ICE_MAX_TRAFFIC_CLASS); return 0; @@ -2501,20 +2501,20 @@ ice_save_agg_tc_bitmap(struct ice_port_info *pi, u32 agg_id, * This function creates an aggregator node and intermediate nodes if required * for the given TC */ -static enum ice_status +static int ice_sched_add_agg_cfg(struct ice_port_info *pi, u32 agg_id, u8 tc) { struct ice_sched_node *parent, *agg_node, *tc_node; u16 num_nodes[ICE_AQC_TOPO_MAX_LEVEL_NUM] = { 0 }; - enum ice_status status = 0; struct ice_hw *hw = pi->hw; u32 first_node_teid; u16 num_nodes_added; + int status = 0; u8 i, aggl; tc_node = ice_sched_get_tc_node(pi, tc); if (!tc_node) - return ICE_ERR_CFG; + return -EIO; agg_node = ice_sched_get_agg_node(pi, tc_node, agg_id); /* Does Agg node already exist ? */ @@ -2549,14 +2549,14 @@ ice_sched_add_agg_cfg(struct ice_port_info *pi, u32 agg_id, u8 tc) parent = tc_node; for (i = hw->sw_entry_point_layer; i <= aggl; i++) { if (!parent) - return ICE_ERR_CFG; + return -EIO; status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, i, num_nodes[i], &first_node_teid, &num_nodes_added); if (status || num_nodes[i] != num_nodes_added) - return ICE_ERR_CFG; + return -EIO; /* The newly added node can be a new parent for the next * layer nodes @@ -2591,13 +2591,13 @@ ice_sched_add_agg_cfg(struct ice_port_info *pi, u32 agg_id, u8 tc) * resources and remove aggregator ID. * This function needs to be called with scheduler lock held. */ -static enum ice_status +static int ice_sched_cfg_agg(struct ice_port_info *pi, u32 agg_id, enum ice_agg_type agg_type, unsigned long *tc_bitmap) { struct ice_sched_agg_info *agg_info; - enum ice_status status = 0; struct ice_hw *hw = pi->hw; + int status = 0; u8 tc; agg_info = ice_get_agg_info(hw, agg_id); @@ -2606,7 +2606,7 @@ ice_sched_cfg_agg(struct ice_port_info *pi, u32 agg_id, agg_info = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*agg_info), GFP_KERNEL); if (!agg_info) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; agg_info->agg_id = agg_id; agg_info->agg_type = agg_type; @@ -2653,19 +2653,17 @@ ice_sched_cfg_agg(struct ice_port_info *pi, u32 agg_id, * * This function configures aggregator node(s). */ -enum ice_status +int ice_cfg_agg(struct ice_port_info *pi, u32 agg_id, enum ice_agg_type agg_type, u8 tc_bitmap) { unsigned long bitmap = tc_bitmap; - enum ice_status status; + int status; mutex_lock(&pi->sched_lock); - status = ice_sched_cfg_agg(pi, agg_id, agg_type, - (unsigned long *)&bitmap); + status = ice_sched_cfg_agg(pi, agg_id, agg_type, &bitmap); if (!status) - status = ice_save_agg_tc_bitmap(pi, agg_id, - (unsigned long *)&bitmap); + status = ice_save_agg_tc_bitmap(pi, agg_id, &bitmap); mutex_unlock(&pi->sched_lock); return status; } @@ -2724,7 +2722,7 @@ ice_get_vsi_agg_info(struct ice_hw *hw, u16 vsi_handle) * Save VSI to aggregator TC bitmap. This function needs to call with scheduler * lock held. */ -static enum ice_status +static int ice_save_agg_vsi_tc_bitmap(struct ice_port_info *pi, u32 agg_id, u16 vsi_handle, unsigned long *tc_bitmap) { @@ -2733,11 +2731,11 @@ ice_save_agg_vsi_tc_bitmap(struct ice_port_info *pi, u32 agg_id, u16 vsi_handle, agg_info = ice_get_agg_info(pi->hw, agg_id); if (!agg_info) - return ICE_ERR_PARAM; + return -EINVAL; /* check if entry already exist */ agg_vsi_info = ice_get_agg_vsi_info(agg_info, vsi_handle); if (!agg_vsi_info) - return ICE_ERR_PARAM; + return -EINVAL; bitmap_copy(agg_vsi_info->replay_tc_bitmap, tc_bitmap, ICE_MAX_TRAFFIC_CLASS); return 0; @@ -2754,21 +2752,21 @@ ice_save_agg_vsi_tc_bitmap(struct ice_port_info *pi, u32 agg_id, u16 vsi_handle, * already associated to the aggregator node then no operation is performed on * the tree. This function needs to be called with scheduler lock held. */ -static enum ice_status +static int ice_sched_assoc_vsi_to_agg(struct ice_port_info *pi, u32 agg_id, u16 vsi_handle, unsigned long *tc_bitmap) { struct ice_sched_agg_vsi_info *agg_vsi_info, *old_agg_vsi_info = NULL; struct ice_sched_agg_info *agg_info, *old_agg_info; - enum ice_status status = 0; struct ice_hw *hw = pi->hw; + int status = 0; u8 tc; if (!ice_is_vsi_valid(pi->hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; agg_info = ice_get_agg_info(hw, agg_id); if (!agg_info) - return ICE_ERR_PARAM; + return -EINVAL; /* If the VSI is already part of another aggregator then update * its VSI info list */ @@ -2790,7 +2788,7 @@ ice_sched_assoc_vsi_to_agg(struct ice_port_info *pi, u32 agg_id, agg_vsi_info = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*agg_vsi_info), GFP_KERNEL); if (!agg_vsi_info) - return ICE_ERR_PARAM; + return -EINVAL; /* add VSI ID into the aggregator list */ agg_vsi_info->vsi_handle = vsi_handle; @@ -2851,14 +2849,14 @@ static void ice_sched_rm_unused_rl_prof(struct ice_port_info *pi) * returns success or error on config sched element failure. The caller * needs to hold scheduler lock. */ -static enum ice_status +static int ice_sched_update_elem(struct ice_hw *hw, struct ice_sched_node *node, struct ice_aqc_txsched_elem_data *info) { struct ice_aqc_txsched_elem_data buf; - enum ice_status status; u16 elem_cfgd = 0; u16 num_elems = 1; + int status; buf = *info; /* Parent TEID is reserved field in this aq call */ @@ -2874,7 +2872,7 @@ ice_sched_update_elem(struct ice_hw *hw, struct ice_sched_node *node, &elem_cfgd, NULL); if (status || elem_cfgd != num_elems) { ice_debug(hw, ICE_DBG_SCHED, "Config sched elem error\n"); - return ICE_ERR_CFG; + return -EIO; } /* Config success case */ @@ -2893,7 +2891,7 @@ ice_sched_update_elem(struct ice_hw *hw, struct ice_sched_node *node, * * This function configures node element's BW allocation. */ -static enum ice_status +static int ice_sched_cfg_node_bw_alloc(struct ice_hw *hw, struct ice_sched_node *node, enum ice_rl_type rl_type, u16 bw_alloc) { @@ -2909,7 +2907,7 @@ ice_sched_cfg_node_bw_alloc(struct ice_hw *hw, struct ice_sched_node *node, data->valid_sections |= ICE_AQC_ELEM_VALID_EIR; data->eir_bw.bw_alloc = cpu_to_le16(bw_alloc); } else { - return ICE_ERR_PARAM; + return -EINVAL; } /* Configure element */ @@ -2925,12 +2923,12 @@ ice_sched_cfg_node_bw_alloc(struct ice_hw *hw, struct ice_sched_node *node, * * Move or associate VSI to a new or default aggregator node. */ -enum ice_status +int ice_move_vsi_to_agg(struct ice_port_info *pi, u32 agg_id, u16 vsi_handle, u8 tc_bitmap) { unsigned long bitmap = tc_bitmap; - enum ice_status status; + int status; mutex_lock(&pi->sched_lock); status = ice_sched_assoc_vsi_to_agg(pi, agg_id, vsi_handle, @@ -3098,12 +3096,12 @@ static u16 ice_sched_calc_wakeup(struct ice_hw *hw, s32 bw) * * This function converts the BW to profile structure format. */ -static enum ice_status +static int ice_sched_bw_to_rl_profile(struct ice_hw *hw, u32 bw, struct ice_aqc_rl_profile_elem *profile) { - enum ice_status status = ICE_ERR_PARAM; s64 bytes_per_sec, ts_rate, mv_tmp; + int status = -EINVAL; bool found = false; s32 encode = 0; s64 mv = 0; @@ -3150,7 +3148,7 @@ ice_sched_bw_to_rl_profile(struct ice_hw *hw, u32 bw, profile->rl_encode = cpu_to_le16(encode); status = 0; } else { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; } return status; @@ -3176,9 +3174,9 @@ ice_sched_add_rl_profile(struct ice_port_info *pi, struct ice_aqc_rl_profile_info *rl_prof_elem; u16 profiles_added = 0, num_profiles = 1; struct ice_aqc_rl_profile_elem *buf; - enum ice_status status; struct ice_hw *hw; u8 profile_type; + int status; if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM) return NULL; @@ -3249,7 +3247,7 @@ exit_add_rl_prof: * * This function configures node element's BW limit. */ -static enum ice_status +static int ice_sched_cfg_node_bw_lmt(struct ice_hw *hw, struct ice_sched_node *node, enum ice_rl_type rl_type, u16 rl_prof_id) { @@ -3268,7 +3266,7 @@ ice_sched_cfg_node_bw_lmt(struct ice_hw *hw, struct ice_sched_node *node, * hence only one of them may be set for any given element */ if (data->valid_sections & ICE_AQC_ELEM_VALID_SHARED) - return ICE_ERR_CFG; + return -EIO; data->valid_sections |= ICE_AQC_ELEM_VALID_EIR; data->eir_bw.bw_profile_idx = cpu_to_le16(rl_prof_id); break; @@ -3291,7 +3289,7 @@ ice_sched_cfg_node_bw_lmt(struct ice_hw *hw, struct ice_sched_node *node, if ((data->valid_sections & ICE_AQC_ELEM_VALID_EIR) && (le16_to_cpu(data->eir_bw.bw_profile_idx) != ICE_SCHED_DFLT_RL_PROF_ID)) - return ICE_ERR_CFG; + return -EIO; /* EIR BW is set to default, disable it */ data->valid_sections &= ~ICE_AQC_ELEM_VALID_EIR; /* Okay to enable shared BW now */ @@ -3300,7 +3298,7 @@ ice_sched_cfg_node_bw_lmt(struct ice_hw *hw, struct ice_sched_node *node, break; default: /* Unknown rate limit type */ - return ICE_ERR_PARAM; + return -EINVAL; } /* Configure element */ @@ -3420,15 +3418,15 @@ ice_sched_get_srl_node(struct ice_sched_node *node, u8 srl_layer) * 'profile_type' and profile ID as 'profile_id'. The caller needs to hold * scheduler lock. */ -static enum ice_status +static int ice_sched_rm_rl_profile(struct ice_port_info *pi, u8 layer_num, u8 profile_type, u16 profile_id) { struct ice_aqc_rl_profile_info *rl_prof_elem; - enum ice_status status = 0; + int status = 0; if (layer_num >= ICE_AQC_TOPO_MAX_LEVEL_NUM) - return ICE_ERR_PARAM; + return -EINVAL; /* Check the existing list for RL profile */ list_for_each_entry(rl_prof_elem, &pi->rl_prof_list[layer_num], list_entry) @@ -3441,11 +3439,11 @@ ice_sched_rm_rl_profile(struct ice_port_info *pi, u8 layer_num, u8 profile_type, /* Remove old profile ID from database */ status = ice_sched_del_rl_profile(pi->hw, rl_prof_elem); - if (status && status != ICE_ERR_IN_USE) + if (status && status != -EBUSY) ice_debug(pi->hw, ICE_DBG_SCHED, "Remove rl profile failed\n"); break; } - if (status == ICE_ERR_IN_USE) + if (status == -EBUSY) status = 0; return status; } @@ -3461,16 +3459,16 @@ ice_sched_rm_rl_profile(struct ice_port_info *pi, u8 layer_num, u8 profile_type, * type CIR, EIR, or SRL to default. This function needs to be called * with the scheduler lock held. */ -static enum ice_status +static int ice_sched_set_node_bw_dflt(struct ice_port_info *pi, struct ice_sched_node *node, enum ice_rl_type rl_type, u8 layer_num) { - enum ice_status status; struct ice_hw *hw; u8 profile_type; u16 rl_prof_id; u16 old_id; + int status; hw = pi->hw; switch (rl_type) { @@ -3488,7 +3486,7 @@ ice_sched_set_node_bw_dflt(struct ice_port_info *pi, rl_prof_id = ICE_SCHED_NO_SHARED_RL_PROF_ID; break; default: - return ICE_ERR_PARAM; + return -EINVAL; } /* Save existing RL prof ID for later clean up */ old_id = ice_sched_get_node_rl_prof_id(node, rl_type); @@ -3518,7 +3516,7 @@ ice_sched_set_node_bw_dflt(struct ice_port_info *pi, * them may be set for any given element. This function needs to be called * with the scheduler lock held. */ -static enum ice_status +static int ice_sched_set_eir_srl_excl(struct ice_port_info *pi, struct ice_sched_node *node, u8 layer_num, enum ice_rl_type rl_type, u32 bw) @@ -3562,14 +3560,14 @@ ice_sched_set_eir_srl_excl(struct ice_port_info *pi, * node's RL profile ID of type CIR, EIR, or SRL, and removes old profile * ID from local database. The caller needs to hold scheduler lock. */ -static enum ice_status +static int ice_sched_set_node_bw(struct ice_port_info *pi, struct ice_sched_node *node, enum ice_rl_type rl_type, u32 bw, u8 layer_num) { struct ice_aqc_rl_profile_info *rl_prof_info; - enum ice_status status = ICE_ERR_PARAM; struct ice_hw *hw = pi->hw; u16 old_id, rl_prof_id; + int status = -EINVAL; rl_prof_info = ice_sched_add_rl_profile(pi, rl_type, bw, layer_num); if (!rl_prof_info) @@ -3608,31 +3606,31 @@ ice_sched_set_node_bw(struct ice_port_info *pi, struct ice_sched_node *node, * It updates node's BW limit parameters like BW RL profile ID of type CIR, * EIR, or SRL. The caller needs to hold scheduler lock. */ -static enum ice_status +static int ice_sched_set_node_bw_lmt(struct ice_port_info *pi, struct ice_sched_node *node, enum ice_rl_type rl_type, u32 bw) { struct ice_sched_node *cfg_node = node; - enum ice_status status; + int status; struct ice_hw *hw; u8 layer_num; if (!pi) - return ICE_ERR_PARAM; + return -EINVAL; hw = pi->hw; /* Remove unused RL profile IDs from HW and SW DB */ ice_sched_rm_unused_rl_prof(pi); layer_num = ice_sched_get_rl_prof_layer(pi, rl_type, node->tx_sched_layer); if (layer_num >= hw->num_tx_sched_layers) - return ICE_ERR_PARAM; + return -EINVAL; if (rl_type == ICE_SHARED_BW) { /* SRL node may be different */ cfg_node = ice_sched_get_srl_node(node, layer_num); if (!cfg_node) - return ICE_ERR_CFG; + return -EIO; } /* EIR BW and Shared BW profiles are mutually exclusive and * hence only one of them may be set for any given element @@ -3657,7 +3655,7 @@ ice_sched_set_node_bw_lmt(struct ice_port_info *pi, struct ice_sched_node *node, * type CIR, EIR, or SRL to default. This function needs to be called * with the scheduler lock held. */ -static enum ice_status +static int ice_sched_set_node_bw_dflt_lmt(struct ice_port_info *pi, struct ice_sched_node *node, enum ice_rl_type rl_type) @@ -3675,7 +3673,7 @@ ice_sched_set_node_bw_dflt_lmt(struct ice_port_info *pi, * behalf of the requested node (first argument). This function needs to be * called with scheduler lock held. */ -static enum ice_status +static int ice_sched_validate_srl_node(struct ice_sched_node *node, u8 sel_layer) { /* SRL profiles are not available on all layers. Check if the @@ -3690,7 +3688,7 @@ ice_sched_validate_srl_node(struct ice_sched_node *node, u8 sel_layer) (node->parent && node->parent->num_children == 1))) return 0; - return ICE_ERR_CFG; + return -EIO; } /** @@ -3701,7 +3699,7 @@ ice_sched_validate_srl_node(struct ice_sched_node *node, u8 sel_layer) * * Save BW information of queue type node for post replay use. */ -static enum ice_status +static int ice_sched_save_q_bw(struct ice_q_ctx *q_ctx, enum ice_rl_type rl_type, u32 bw) { switch (rl_type) { @@ -3715,7 +3713,7 @@ ice_sched_save_q_bw(struct ice_q_ctx *q_ctx, enum ice_rl_type rl_type, u32 bw) ice_set_clear_shared_bw(&q_ctx->bw_t_info, bw); break; default: - return ICE_ERR_PARAM; + return -EINVAL; } return 0; } @@ -3731,16 +3729,16 @@ ice_sched_save_q_bw(struct ice_q_ctx *q_ctx, enum ice_rl_type rl_type, u32 bw) * * This function sets BW limit of queue scheduling node. */ -static enum ice_status +static int ice_sched_set_q_bw_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, enum ice_rl_type rl_type, u32 bw) { - enum ice_status status = ICE_ERR_PARAM; struct ice_sched_node *node; struct ice_q_ctx *q_ctx; + int status = -EINVAL; if (!ice_is_vsi_valid(pi->hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; mutex_lock(&pi->sched_lock); q_ctx = ice_get_lan_q_ctx(pi->hw, vsi_handle, tc, q_handle); if (!q_ctx) @@ -3762,7 +3760,7 @@ ice_sched_set_q_bw_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, sel_layer = ice_sched_get_rl_prof_layer(pi, rl_type, node->tx_sched_layer); if (sel_layer >= pi->hw->num_tx_sched_layers) { - status = ICE_ERR_PARAM; + status = -EINVAL; goto exit_q_bw_lmt; } status = ice_sched_validate_srl_node(node, sel_layer); @@ -3794,7 +3792,7 @@ exit_q_bw_lmt: * * This function configures BW limit of queue scheduling node. */ -enum ice_status +int ice_cfg_q_bw_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, enum ice_rl_type rl_type, u32 bw) { @@ -3812,7 +3810,7 @@ ice_cfg_q_bw_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, * * This function configures BW default limit of queue scheduling node. */ -enum ice_status +int ice_cfg_q_bw_dflt_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, enum ice_rl_type rl_type) { @@ -3880,13 +3878,13 @@ ice_sched_get_node_by_id_type(struct ice_port_info *pi, u32 id, * This function sets BW limit of VSI or Aggregator scheduling node * based on TC information from passed in argument BW. */ -static enum ice_status +int ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, enum ice_agg_type agg_type, u8 tc, enum ice_rl_type rl_type, u32 bw) { - enum ice_status status = ICE_ERR_PARAM; struct ice_sched_node *node; + int status = -EINVAL; if (!pi) return status; @@ -3921,7 +3919,7 @@ exit_set_node_bw_lmt_per_tc: * This function configures BW limit of VSI scheduling node based on TC * information. */ -enum ice_status +int ice_cfg_vsi_bw_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, enum ice_rl_type rl_type, u32 bw) { @@ -3948,7 +3946,7 @@ ice_cfg_vsi_bw_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, * This function configures default BW limit of VSI scheduling node based on TC * information. */ -enum ice_status +int ice_cfg_vsi_bw_dflt_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, enum ice_rl_type rl_type) { @@ -3976,13 +3974,13 @@ ice_cfg_vsi_bw_dflt_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, * burst size value is used for future rate limit calls. It doesn't change the * existing or previously created RL profiles. */ -enum ice_status ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes) +int ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes) { u16 burst_size_to_prog; if (bytes < ICE_MIN_BURST_SIZE_ALLOWED || bytes > ICE_MAX_BURST_SIZE_ALLOWED) - return ICE_ERR_PARAM; + return -EINVAL; if (ice_round_to_num(bytes, 64) <= ICE_MAX_BURST_SIZE_64_BYTE_GRANULARITY) { /* 64 byte granularity case */ @@ -4017,13 +4015,13 @@ enum ice_status ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes) * This function configures node element's priority value. It * needs to be called with scheduler lock held. */ -static enum ice_status +static int ice_sched_replay_node_prio(struct ice_hw *hw, struct ice_sched_node *node, u8 priority) { struct ice_aqc_txsched_elem_data buf; struct ice_aqc_txsched_elem *data; - enum ice_status status; + int status; buf = node->info; data = &buf.data; @@ -4044,12 +4042,12 @@ ice_sched_replay_node_prio(struct ice_hw *hw, struct ice_sched_node *node, * This function restores node's BW from bw_t_info. The caller needs * to hold the scheduler lock. */ -static enum ice_status +static int ice_sched_replay_node_bw(struct ice_hw *hw, struct ice_sched_node *node, struct ice_bw_type_info *bw_t_info) { struct ice_port_info *pi = hw->port_info; - enum ice_status status = ICE_ERR_PARAM; + int status = -EINVAL; u16 bw_alloc; if (!node) @@ -4137,7 +4135,7 @@ void ice_sched_replay_agg(struct ice_hw *hw) if (!bitmap_equal(agg_info->tc_bitmap, agg_info->replay_tc_bitmap, ICE_MAX_TRAFFIC_CLASS)) { DECLARE_BITMAP(replay_bitmap, ICE_MAX_TRAFFIC_CLASS); - enum ice_status status; + int status; bitmap_zero(replay_bitmap, ICE_MAX_TRAFFIC_CLASS); ice_sched_get_ena_tc_bitmap(pi, @@ -4191,18 +4189,17 @@ void ice_sched_replay_agg_vsi_preinit(struct ice_hw *hw) * their node bandwidth information. This function needs to be called with * scheduler lock held. */ -static enum ice_status -ice_sched_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle) +static int ice_sched_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle) { DECLARE_BITMAP(replay_bitmap, ICE_MAX_TRAFFIC_CLASS); struct ice_sched_agg_vsi_info *agg_vsi_info; struct ice_port_info *pi = hw->port_info; struct ice_sched_agg_info *agg_info; - enum ice_status status; + int status; bitmap_zero(replay_bitmap, ICE_MAX_TRAFFIC_CLASS); if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; agg_info = ice_get_vsi_agg_info(hw, vsi_handle); if (!agg_info) return 0; /* Not present in list - default Agg case */ @@ -4233,10 +4230,10 @@ ice_sched_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle) * This function replays association of VSI to aggregator type nodes, and * node bandwidth information. */ -enum ice_status ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle) +int ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle) { struct ice_port_info *pi = hw->port_info; - enum ice_status status; + int status; mutex_lock(&pi->sched_lock); status = ice_sched_replay_vsi_agg(hw, vsi_handle); @@ -4252,14 +4249,13 @@ enum ice_status ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle) * This function replays queue type node bandwidth. This function needs to be * called with scheduler lock held. */ -enum ice_status -ice_sched_replay_q_bw(struct ice_port_info *pi, struct ice_q_ctx *q_ctx) +int ice_sched_replay_q_bw(struct ice_port_info *pi, struct ice_q_ctx *q_ctx) { struct ice_sched_node *q_node; /* Following also checks the presence of node in tree */ q_node = ice_sched_find_node_by_teid(pi->root, q_ctx->q_teid); if (!q_node) - return ICE_ERR_PARAM; + return -EINVAL; return ice_sched_replay_node_bw(pi->hw, q_node, &q_ctx->bw_t_info); } diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 6bddcbecaf5e..4f91577fed56 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -65,12 +65,12 @@ struct ice_sched_agg_info { }; /* FW AQ command calls */ -enum ice_status +int ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req, struct ice_aqc_txsched_elem_data *buf, u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd); -enum ice_status ice_sched_init_port(struct ice_port_info *pi); -enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw); +int ice_sched_init_port(struct ice_port_info *pi); +int ice_sched_query_res_alloc(struct ice_hw *hw); void ice_sched_get_psm_clk_freq(struct ice_hw *hw); void ice_sched_clear_port(struct ice_port_info *pi); @@ -79,7 +79,7 @@ void ice_sched_clear_agg(struct ice_hw *hw); struct ice_sched_node * ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid); -enum ice_status +int ice_sched_add_node(struct ice_port_info *pi, u8 layer, struct ice_aqc_txsched_elem_data *info); void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node); @@ -87,35 +87,38 @@ struct ice_sched_node *ice_sched_get_tc_node(struct ice_port_info *pi, u8 tc); struct ice_sched_node * ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 owner); -enum ice_status +int ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, u8 owner, bool enable); -enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle); -enum ice_status ice_rm_vsi_rdma_cfg(struct ice_port_info *pi, u16 vsi_handle); +int ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle); +int ice_rm_vsi_rdma_cfg(struct ice_port_info *pi, u16 vsi_handle); /* Tx scheduler rate limiter functions */ -enum ice_status +int ice_cfg_agg(struct ice_port_info *pi, u32 agg_id, enum ice_agg_type agg_type, u8 tc_bitmap); -enum ice_status +int ice_move_vsi_to_agg(struct ice_port_info *pi, u32 agg_id, u16 vsi_handle, u8 tc_bitmap); -enum ice_status +int ice_cfg_q_bw_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, enum ice_rl_type rl_type, u32 bw); -enum ice_status +int ice_cfg_q_bw_dflt_lmt(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 q_handle, enum ice_rl_type rl_type); -enum ice_status +int ice_cfg_vsi_bw_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, enum ice_rl_type rl_type, u32 bw); -enum ice_status +int ice_cfg_vsi_bw_dflt_lmt_per_tc(struct ice_port_info *pi, u16 vsi_handle, u8 tc, enum ice_rl_type rl_type); -enum ice_status ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes); +int +ice_sched_set_node_bw_lmt_per_tc(struct ice_port_info *pi, u32 id, + enum ice_agg_type agg_type, u8 tc, + enum ice_rl_type rl_type, u32 bw); +int ice_cfg_rl_burst_size(struct ice_hw *hw, u32 bytes); void ice_sched_replay_agg_vsi_preinit(struct ice_hw *hw); void ice_sched_replay_agg(struct ice_hw *hw); -enum ice_status ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle); -enum ice_status -ice_sched_replay_q_bw(struct ice_port_info *pi, struct ice_q_ctx *q_ctx); +int ice_replay_vsi_agg(struct ice_hw *hw, u16 vsi_handle); +int ice_sched_replay_q_bw(struct ice_port_info *pi, struct ice_q_ctx *q_ctx); #endif /* _ICE_SCHED_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index aa11d07793d4..52c6bac41bf7 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -18,7 +18,7 @@ * queue and asynchronously sending message via * ice_sq_send_cmd() function */ -enum ice_status +int ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, struct ice_sq_cd *cd) { @@ -228,7 +228,7 @@ ice_mbx_traverse(struct ice_hw *hw, * sent per VF and marks the VF as malicious if it exceeds * the permissible number of messages to send. */ -static enum ice_status +static int ice_mbx_detect_malvf(struct ice_hw *hw, u16 vf_id, enum ice_mbx_snapshot_state *new_state, bool *is_malvf) @@ -236,7 +236,7 @@ ice_mbx_detect_malvf(struct ice_hw *hw, u16 vf_id, struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; if (vf_id >= snap->mbx_vf.vfcntr_len) - return ICE_ERR_OUT_OF_RANGE; + return -EIO; /* increment the message count in the VF array */ snap->mbx_vf.vf_cntr[vf_id]++; @@ -297,7 +297,7 @@ static void ice_mbx_reset_snapshot(struct ice_mbx_snapshot *snap) * Detect: If pending message count exceeds watermark traverse * the static snapshot and look for a malicious VF. */ -enum ice_status +int ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data, u16 vf_id, bool *is_malvf) @@ -306,10 +306,10 @@ ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_snap_buffer_data *snap_buf; struct ice_ctl_q_info *cq = &hw->mailboxq; enum ice_mbx_snapshot_state new_state; - enum ice_status status = 0; + int status = 0; if (!is_malvf || !mbx_data) - return ICE_ERR_BAD_PTR; + return -EINVAL; /* When entering the mailbox state machine assume that the VF * is not malicious until detected. @@ -320,7 +320,7 @@ ice_mbx_vf_state_handler(struct ice_hw *hw, * interrupt is not less than the defined AVF message threshold. */ if (mbx_data->max_num_msgs_mbx <= ICE_ASYNC_VF_MSG_THRESHOLD) - return ICE_ERR_INVAL_SIZE; + return -EINVAL; /* The watermark value should not be lesser than the threshold limit * set for the number of asynchronous messages a VF can send to mailbox @@ -329,7 +329,7 @@ ice_mbx_vf_state_handler(struct ice_hw *hw, */ if (mbx_data->async_watermark_val < ICE_ASYNC_VF_MSG_THRESHOLD || mbx_data->async_watermark_val > mbx_data->max_num_msgs_mbx) - return ICE_ERR_PARAM; + return -EINVAL; new_state = ICE_MAL_VF_DETECT_STATE_INVALID; snap_buf = &snap->mbx_buf; @@ -383,7 +383,7 @@ ice_mbx_vf_state_handler(struct ice_hw *hw, default: new_state = ICE_MAL_VF_DETECT_STATE_INVALID; - status = ICE_ERR_CFG; + status = -EIO; } snap_buf->state = new_state; @@ -405,20 +405,20 @@ ice_mbx_vf_state_handler(struct ice_hw *hw, * the input vf_id against the bitmap to verify if the VF has been * detected in any previous mailbox iterations. */ -enum ice_status +int ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, u16 bitmap_len, u16 vf_id, bool *report_malvf) { if (!all_malvfs || !report_malvf) - return ICE_ERR_PARAM; + return -EINVAL; *report_malvf = false; if (bitmap_len < hw->mbx_snapshot.mbx_vf.vfcntr_len) - return ICE_ERR_INVAL_SIZE; + return -EINVAL; if (vf_id >= bitmap_len) - return ICE_ERR_OUT_OF_RANGE; + return -EIO; /* If the vf_id is found in the bitmap set bit and boolean to true */ if (!test_and_set_bit(vf_id, all_malvfs)) @@ -441,19 +441,19 @@ ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, * that the new VF loaded is not considered malicious before going * through the overflow detection algorithm. */ -enum ice_status +int ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, u16 bitmap_len, u16 vf_id) { if (!snap || !all_malvfs) - return ICE_ERR_PARAM; + return -EINVAL; if (bitmap_len < snap->mbx_vf.vfcntr_len) - return ICE_ERR_INVAL_SIZE; + return -EINVAL; /* Ensure VF ID value is not larger than bitmap or VF counter length */ if (vf_id >= bitmap_len || vf_id >= snap->mbx_vf.vfcntr_len) - return ICE_ERR_OUT_OF_RANGE; + return -EIO; /* Clear VF ID bit in the bitmap tracking malicious VFs attached to PF */ clear_bit(vf_id, all_malvfs); @@ -482,7 +482,7 @@ ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, * called to ensure that the vf_count can be compared against the number * of VFs supported as defined in the functional capabilities of the device. */ -enum ice_status ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count) +int ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count) { struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; @@ -491,13 +491,13 @@ enum ice_status ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count) * the functional capabilities of the PF. */ if (!vf_count || vf_count > hw->func_caps.num_allocd_vfs) - return ICE_ERR_INVAL_SIZE; + return -EINVAL; snap->mbx_vf.vf_cntr = devm_kcalloc(ice_hw_to_dev(hw), vf_count, sizeof(*snap->mbx_vf.vf_cntr), GFP_KERNEL); if (!snap->mbx_vf.vf_cntr) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Setting the VF counter length to the number of allocated * VFs for given PF's functional capabilities. diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h index 161dc55d9e9c..68686a3fd7e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.h +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -14,24 +14,24 @@ #define ICE_ASYNC_VF_MSG_THRESHOLD 63 #ifdef CONFIG_PCI_IOV -enum ice_status +int ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, struct ice_sq_cd *cd); u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed); -enum ice_status +int ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data, u16 vf_id, bool *is_mal_vf); -enum ice_status +int ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, u16 bitmap_len, u16 vf_id); -enum ice_status ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count); +int ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count); void ice_mbx_deinit_snapshot(struct ice_hw *hw); -enum ice_status +int ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, u16 bitmap_len, u16 vf_id, bool *report_malvf); #else /* CONFIG_PCI_IOV */ -static inline enum ice_status +static inline int ice_aq_send_msg_to_vf(struct ice_hw __always_unused *hw, u16 __always_unused vfid, u32 __always_unused v_opcode, u32 __always_unused v_retval, u8 __always_unused *msg, diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h deleted file mode 100644 index dbf66057371d..000000000000 --- a/drivers/net/ethernet/intel/ice/ice_status.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2018, Intel Corporation. */ - -#ifndef _ICE_STATUS_H_ -#define _ICE_STATUS_H_ - -/* Error Codes */ -enum ice_status { - ICE_SUCCESS = 0, - - /* Generic codes : Range -1..-49 */ - ICE_ERR_PARAM = -1, - ICE_ERR_NOT_IMPL = -2, - ICE_ERR_NOT_READY = -3, - ICE_ERR_NOT_SUPPORTED = -4, - ICE_ERR_BAD_PTR = -5, - ICE_ERR_INVAL_SIZE = -6, - ICE_ERR_DEVICE_NOT_SUPPORTED = -8, - ICE_ERR_RESET_FAILED = -9, - ICE_ERR_FW_API_VER = -10, - ICE_ERR_NO_MEMORY = -11, - ICE_ERR_CFG = -12, - ICE_ERR_OUT_OF_RANGE = -13, - ICE_ERR_ALREADY_EXISTS = -14, - ICE_ERR_DOES_NOT_EXIST = -15, - ICE_ERR_IN_USE = -16, - ICE_ERR_MAX_LIMIT = -17, - ICE_ERR_RESET_ONGOING = -18, - ICE_ERR_HW_TABLE = -19, - ICE_ERR_FW_DDP_MISMATCH = -20, - - ICE_ERR_NVM = -50, - ICE_ERR_NVM_CHECKSUM = -51, - ICE_ERR_BUF_TOO_SHORT = -52, - ICE_ERR_NVM_BLANK_MODE = -53, - ICE_ERR_AQ_ERROR = -100, - ICE_ERR_AQ_TIMEOUT = -101, - ICE_ERR_AQ_FULL = -102, - ICE_ERR_AQ_NO_WORK = -103, - ICE_ERR_AQ_EMPTY = -104, - ICE_ERR_AQ_FW_CRITICAL = -105, -}; - -#endif /* _ICE_STATUS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 793f4a9fc2cd..e477c2b1d5bb 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -528,7 +528,7 @@ static DECLARE_BITMAP(profile_to_recipe[ICE_MAX_NUM_PROFILES], * Allocate memory for the entire recipe table and initialize the structures/ * entries corresponding to basic recipes. */ -enum ice_status ice_init_def_sw_recp(struct ice_hw *hw) +int ice_init_def_sw_recp(struct ice_hw *hw) { struct ice_sw_recipe *recps; u8 i; @@ -536,7 +536,7 @@ enum ice_status ice_init_def_sw_recp(struct ice_hw *hw) recps = devm_kcalloc(ice_hw_to_dev(hw), ICE_MAX_NUM_RECIPES, sizeof(*recps), GFP_KERNEL); if (!recps) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; for (i = 0; i < ICE_MAX_NUM_RECIPES; i++) { recps[i].root_rid = i; @@ -576,14 +576,14 @@ enum ice_status ice_init_def_sw_recp(struct ice_hw *hw) * in response buffer. The caller of this function to use *num_elems while * parsing the response buffer. */ -static enum ice_status +static int ice_aq_get_sw_cfg(struct ice_hw *hw, struct ice_aqc_get_sw_cfg_resp_elem *buf, u16 buf_size, u16 *req_desc, u16 *num_elems, struct ice_sq_cd *cd) { struct ice_aqc_get_sw_cfg *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sw_cfg); cmd = &desc.params.get_sw_conf; @@ -606,14 +606,14 @@ ice_aq_get_sw_cfg(struct ice_hw *hw, struct ice_aqc_get_sw_cfg_resp_elem *buf, * * Add a VSI context to the hardware (0x0210) */ -static enum ice_status +static int ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd) { struct ice_aqc_add_update_free_vsi_resp *res; struct ice_aqc_add_get_update_free_vsi *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd = &desc.params.vsi_cmd; res = &desc.params.add_update_free_vsi_res; @@ -650,14 +650,14 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, * * Free VSI context info from hardware (0x0213) */ -static enum ice_status +static int ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, bool keep_vsi_alloc, struct ice_sq_cd *cd) { struct ice_aqc_add_update_free_vsi_resp *resp; struct ice_aqc_add_get_update_free_vsi *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd = &desc.params.vsi_cmd; resp = &desc.params.add_update_free_vsi_res; @@ -685,14 +685,14 @@ ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, * * Update VSI context in the hardware (0x0211) */ -static enum ice_status +static int ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd) { struct ice_aqc_add_update_free_vsi_resp *resp; struct ice_aqc_add_get_update_free_vsi *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd = &desc.params.vsi_cmd; resp = &desc.params.add_update_free_vsi_res; @@ -832,15 +832,15 @@ void ice_clear_all_vsi_ctx(struct ice_hw *hw) * If this function gets called after reset for existing VSIs then update * with the new HW VSI number in the corresponding VSI handle list entry. */ -enum ice_status +int ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd) { struct ice_vsi_ctx *tmp_vsi_ctx; - enum ice_status status; + int status; if (vsi_handle >= ICE_MAX_VSI) - return ICE_ERR_PARAM; + return -EINVAL; status = ice_aq_add_vsi(hw, vsi_ctx, cd); if (status) return status; @@ -851,7 +851,7 @@ ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, sizeof(*tmp_vsi_ctx), GFP_KERNEL); if (!tmp_vsi_ctx) { ice_aq_free_vsi(hw, vsi_ctx, false, cd); - return ICE_ERR_NO_MEMORY; + return -ENOMEM; } *tmp_vsi_ctx = *vsi_ctx; ice_save_vsi_ctx(hw, vsi_handle, tmp_vsi_ctx); @@ -873,14 +873,14 @@ ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, * * Free VSI context info from hardware as well as from VSI handle list */ -enum ice_status +int ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, bool keep_vsi_alloc, struct ice_sq_cd *cd) { - enum ice_status status; + int status; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; vsi_ctx->vsi_num = ice_get_hw_vsi_num(hw, vsi_handle); status = ice_aq_free_vsi(hw, vsi_ctx, keep_vsi_alloc, cd); if (!status) @@ -897,12 +897,12 @@ ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, * * Update VSI context in the hardware */ -enum ice_status +int ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd) { if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; vsi_ctx->vsi_num = ice_get_hw_vsi_num(hw, vsi_handle); return ice_aq_update_vsi(hw, vsi_ctx, cd); } @@ -927,7 +927,7 @@ ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable) else ctx->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; - return ice_status_to_errno(ice_update_vsi(hw, vsi_handle, ctx, NULL)); + return ice_update_vsi(hw, vsi_handle, ctx, NULL); } /** @@ -939,20 +939,20 @@ ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable) * * allocates or free a VSI list resource */ -static enum ice_status +static int ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, enum ice_sw_lkup_type lkup_type, enum ice_adminq_opc opc) { struct ice_aqc_alloc_free_res_elem *sw_buf; struct ice_aqc_res_elem *vsi_ele; - enum ice_status status; u16 buf_len; + int status; buf_len = struct_size(sw_buf, elem, 1); sw_buf = devm_kzalloc(ice_hw_to_dev(hw), buf_len, GFP_KERNEL); if (!sw_buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; sw_buf->num_elems = cpu_to_le16(1); if (lkup_type == ICE_SW_LKUP_MAC || @@ -966,7 +966,7 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_PRUNE); } else { - status = ICE_ERR_PARAM; + status = -EINVAL; goto ice_aq_alloc_free_vsi_list_exit; } @@ -998,17 +998,17 @@ ice_aq_alloc_free_vsi_list_exit: * * Add(0x02a0)/Update(0x02a1)/Remove(0x02a2) switch rules commands to firmware */ -enum ice_status +int ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, u8 num_rules, enum ice_adminq_opc opc, struct ice_sq_cd *cd) { struct ice_aq_desc desc; - enum ice_status status; + int status; if (opc != ice_aqc_opc_add_sw_rules && opc != ice_aqc_opc_update_sw_rules && opc != ice_aqc_opc_remove_sw_rules) - return ICE_ERR_PARAM; + return -EINVAL; ice_fill_dflt_direct_cmd_desc(&desc, opc); @@ -1018,7 +1018,7 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, status = ice_aq_send_cmd(hw, &desc, rule_list, rule_list_sz, cd); if (opc != ice_aqc_opc_add_sw_rules && hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; return status; } @@ -1032,7 +1032,7 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, * * Add(0x0290) */ -static enum ice_status +static int ice_aq_add_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 num_recipes, struct ice_sq_cd *cd) @@ -1069,18 +1069,18 @@ ice_aq_add_recipe(struct ice_hw *hw, * The caller must supply enough space in s_recipe_list to hold all possible * recipes and *num_recipes must equal ICE_MAX_NUM_RECIPES. */ -static enum ice_status +static int ice_aq_get_recipe(struct ice_hw *hw, struct ice_aqc_recipe_data_elem *s_recipe_list, u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd) { struct ice_aqc_add_get_recipe *cmd; struct ice_aq_desc desc; - enum ice_status status; u16 buf_size; + int status; if (*num_recipes != ICE_MAX_NUM_RECIPES) - return ICE_ERR_PARAM; + return -EINVAL; cmd = &desc.params.add_get_recipe; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe); @@ -1104,7 +1104,7 @@ ice_aq_get_recipe(struct ice_hw *hw, * @cd: pointer to command details structure or NULL * Recipe to profile association (0x0291) */ -static enum ice_status +static int ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { @@ -1130,13 +1130,13 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @cd: pointer to command details structure or NULL * Associate profile ID with given recipe (0x0293) */ -static enum ice_status +static int ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, struct ice_sq_cd *cd) { struct ice_aqc_recipe_to_profile *cmd; struct ice_aq_desc desc; - enum ice_status status; + int status; cmd = &desc.params.recipe_to_profile; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe_to_profile); @@ -1154,16 +1154,16 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u8 *r_bitmap, * @hw: pointer to the hardware structure * @rid: recipe ID returned as response to AQ call */ -static enum ice_status ice_alloc_recipe(struct ice_hw *hw, u16 *rid) +static int ice_alloc_recipe(struct ice_hw *hw, u16 *rid) { struct ice_aqc_alloc_free_res_elem *sw_buf; - enum ice_status status; u16 buf_len; + int status; buf_len = struct_size(sw_buf, elem, 1); sw_buf = kzalloc(buf_len, GFP_KERNEL); if (!sw_buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; sw_buf->num_elems = cpu_to_le16(1); sw_buf->res_type = cpu_to_le16((ICE_AQC_RES_TYPE_RECIPE << @@ -1230,7 +1230,7 @@ ice_collect_result_idx(struct ice_aqc_recipe_data_elem *buf, * bookkeeping so that we have a current list of all the recipes that are * programmed in the firmware. */ -static enum ice_status +static int ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, bool *refresh_required) { @@ -1238,16 +1238,16 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, struct ice_aqc_recipe_data_elem *tmp; u16 num_recps = ICE_MAX_NUM_RECIPES; struct ice_prot_lkup_ext *lkup_exts; - enum ice_status status; u8 fv_word_idx = 0; u16 sub_recps; + int status; bitmap_zero(result_bm, ICE_MAX_FV_WORDS); /* we need a buffer big enough to accommodate all the recipes */ tmp = kcalloc(ICE_MAX_NUM_RECIPES, sizeof(*tmp), GFP_KERNEL); if (!tmp) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; tmp[0].recipe_indx = rid; status = ice_aq_get_recipe(hw, tmp, &num_recps, rid, NULL); @@ -1284,7 +1284,7 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, rg_entry = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*rg_entry), GFP_KERNEL); if (!rg_entry) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_unroll; } @@ -1364,7 +1364,7 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid, recps[rid].n_grp_count * sizeof(*recps[rid].root_buf), GFP_KERNEL); if (!recps[rid].root_buf) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_unroll; } @@ -1407,19 +1407,19 @@ ice_init_port_info(struct ice_port_info *pi, u16 vsi_port_num, u8 type, /* ice_get_initial_sw_cfg - Get initial port and default VSI data * @hw: pointer to the hardware structure */ -enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw) +int ice_get_initial_sw_cfg(struct ice_hw *hw) { struct ice_aqc_get_sw_cfg_resp_elem *rbuf; - enum ice_status status; u16 req_desc = 0; u16 num_elems; + int status; u16 i; rbuf = devm_kzalloc(ice_hw_to_dev(hw), ICE_SW_CFG_MAX_BUF_LEN, GFP_KERNEL); if (!rbuf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Multiple calls to ice_aq_get_sw_cfg may be required * to get all the switch configuration information. The need @@ -1670,7 +1670,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, * Create a large action to hold software marker and update the switch rule * entry pointed by m_ent with newly created large action */ -static enum ice_status +static int ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, u16 sw_marker, u16 l_id) { @@ -1681,14 +1681,14 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, * 3. GENERIC VALUE action to hold the software marker ID */ const u16 num_lg_acts = 3; - enum ice_status status; u16 lg_act_size; u16 rules_size; + int status; u32 act; u16 id; if (m_ent->fltr_info.lkup_type != ICE_SW_LKUP_MAC) - return ICE_ERR_PARAM; + return -EINVAL; /* Create two back-to-back switch rules and submit them to the HW using * one memory buffer: @@ -1699,7 +1699,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, rules_size = lg_act_size + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE; lg_act = devm_kzalloc(ice_hw_to_dev(hw), rules_size, GFP_KERNEL); if (!lg_act) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; rx_tx = (struct ice_aqc_sw_rules_elem *)((u8 *)lg_act + lg_act_size); @@ -1808,19 +1808,19 @@ ice_create_vsi_list_map(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, * Call AQ command to add a new switch rule or update existing switch rule * using the given VSI list ID */ -static enum ice_status +static int ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, u16 vsi_list_id, bool remove, enum ice_adminq_opc opc, enum ice_sw_lkup_type lkup_type) { struct ice_aqc_sw_rules_elem *s_rule; - enum ice_status status; u16 s_rule_size; u16 rule_type; + int status; int i; if (!num_vsi) - return ICE_ERR_PARAM; + return -EINVAL; if (lkup_type == ICE_SW_LKUP_MAC || lkup_type == ICE_SW_LKUP_MAC_VLAN || @@ -1834,15 +1834,15 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, rule_type = remove ? ICE_AQC_SW_RULES_T_PRUNE_LIST_CLEAR : ICE_AQC_SW_RULES_T_PRUNE_LIST_SET; else - return ICE_ERR_PARAM; + return -EINVAL; s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(num_vsi); s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); if (!s_rule) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; for (i = 0; i < num_vsi; i++) { if (!ice_is_vsi_valid(hw, vsi_handle_arr[i])) { - status = ICE_ERR_PARAM; + status = -EINVAL; goto exit; } /* AQ call requires hw_vsi_id(s) */ @@ -1869,11 +1869,11 @@ exit: * @vsi_list_id: stores the ID of the VSI list to be created * @lkup_type: switch rule filter's lookup type */ -static enum ice_status +static int ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, u16 *vsi_list_id, enum ice_sw_lkup_type lkup_type) { - enum ice_status status; + int status; status = ice_aq_alloc_free_vsi_list(hw, vsi_list_id, lkup_type, ice_aqc_opc_alloc_res); @@ -1895,7 +1895,7 @@ ice_create_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, * to the corresponding filter management list to track this switch rule * and VSI mapping */ -static enum ice_status +static int ice_create_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { @@ -1903,16 +1903,16 @@ ice_create_pkt_fwd_rule(struct ice_hw *hw, struct ice_aqc_sw_rules_elem *s_rule; enum ice_sw_lkup_type l_type; struct ice_sw_recipe *recp; - enum ice_status status; + int status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, GFP_KERNEL); if (!s_rule) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; fm_entry = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*fm_entry), GFP_KERNEL); if (!fm_entry) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto ice_create_pkt_fwd_rule_exit; } @@ -1959,16 +1959,16 @@ ice_create_pkt_fwd_rule_exit: * Call AQ command to update a previously created switch rule with a * VSI list ID */ -static enum ice_status +static int ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info) { struct ice_aqc_sw_rules_elem *s_rule; - enum ice_status status; + int status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, GFP_KERNEL); if (!s_rule) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; ice_fill_sw_rule(hw, f_info, s_rule, ice_aqc_opc_update_sw_rules); @@ -1988,13 +1988,13 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info) * * Updates unicast switch filter rules based on VEB/VEPA mode */ -enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw) +int ice_update_sw_rule_bridge_mode(struct ice_hw *hw) { struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_mgmt_list_entry *fm_entry; - enum ice_status status = 0; struct list_head *rule_head; struct mutex *rule_lock; /* Lock to protect filter rule list */ + int status = 0; rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; @@ -2044,24 +2044,24 @@ enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw) * Add the new VSI to the previously created VSI list set * using the update switch rule command */ -static enum ice_status +static int ice_add_update_vsi_list(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_entry, struct ice_fltr_info *cur_fltr, struct ice_fltr_info *new_fltr) { - enum ice_status status = 0; u16 vsi_list_id = 0; + int status = 0; if ((cur_fltr->fltr_act == ICE_FWD_TO_Q || cur_fltr->fltr_act == ICE_FWD_TO_QGRP)) - return ICE_ERR_NOT_IMPL; + return -EOPNOTSUPP; if ((new_fltr->fltr_act == ICE_FWD_TO_Q || new_fltr->fltr_act == ICE_FWD_TO_QGRP) && (cur_fltr->fltr_act == ICE_FWD_TO_VSI || cur_fltr->fltr_act == ICE_FWD_TO_VSI_LIST)) - return ICE_ERR_NOT_IMPL; + return -EOPNOTSUPP; if (m_entry->vsi_count < 2 && !m_entry->vsi_list_info) { /* Only one entry existed in the mapping and it was not already @@ -2073,7 +2073,7 @@ ice_add_update_vsi_list(struct ice_hw *hw, /* A rule already exists with the new VSI being added */ if (cur_fltr->fwd_id.hw_vsi_id == new_fltr->fwd_id.hw_vsi_id) - return ICE_ERR_ALREADY_EXISTS; + return -EEXIST; vsi_handle_arr[0] = cur_fltr->vsi_handle; vsi_handle_arr[1] = new_fltr->vsi_handle; @@ -2101,7 +2101,7 @@ ice_add_update_vsi_list(struct ice_hw *hw, vsi_list_id); if (!m_entry->vsi_list_info) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* If this entry was large action then the large action needs * to be updated to point to FWD to VSI list @@ -2116,7 +2116,7 @@ ice_add_update_vsi_list(struct ice_hw *hw, enum ice_adminq_opc opcode; if (!m_entry->vsi_list_info) - return ICE_ERR_CFG; + return -EIO; /* A rule already exists with the new VSI being added */ if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) @@ -2209,7 +2209,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle, * * Adds or updates the rule lists for a given recipe */ -static enum ice_status +static int ice_add_rule_internal(struct ice_hw *hw, u8 recp_id, struct ice_fltr_list_entry *f_entry) { @@ -2217,10 +2217,10 @@ ice_add_rule_internal(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *new_fltr, *cur_fltr; struct ice_fltr_mgmt_list_entry *m_entry; struct mutex *rule_lock; /* Lock to protect filter rule list */ - enum ice_status status = 0; + int status = 0; if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; f_entry->fltr_info.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle); @@ -2255,18 +2255,18 @@ ice_add_rule_internal(struct ice_hw *hw, u8 recp_id, * The VSI list should be emptied before this function is called to remove the * VSI list. */ -static enum ice_status +static int ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, enum ice_sw_lkup_type lkup_type) { struct ice_aqc_sw_rules_elem *s_rule; - enum ice_status status; u16 s_rule_size; + int status; s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0); s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); if (!s_rule) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR); s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id); @@ -2288,21 +2288,21 @@ ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, * @fm_list: filter management entry for which the VSI list management needs to * be done */ -static enum ice_status +static int ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, struct ice_fltr_mgmt_list_entry *fm_list) { enum ice_sw_lkup_type lkup_type; - enum ice_status status = 0; u16 vsi_list_id; + int status = 0; if (fm_list->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST || fm_list->vsi_count == 0) - return ICE_ERR_PARAM; + return -EINVAL; /* A rule with the VSI being removed does not exist */ if (!test_bit(vsi_handle, fm_list->vsi_list_info->vsi_map)) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; lkup_type = fm_list->fltr_info.lkup_type; vsi_list_id = fm_list->fltr_info.fwd_id.vsi_list_id; @@ -2324,7 +2324,7 @@ ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, rem_vsi_handle = find_first_bit(vsi_list_info->vsi_map, ICE_MAX_VSI); if (!ice_is_vsi_valid(hw, rem_vsi_handle)) - return ICE_ERR_OUT_OF_RANGE; + return -EIO; /* Make sure VSI list is empty before removing it below */ status = ice_update_vsi_list_rule(hw, &rem_vsi_handle, 1, @@ -2375,19 +2375,19 @@ ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, * @recp_id: recipe ID for which the rule needs to removed * @f_entry: rule entry containing filter information */ -static enum ice_status +static int ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, struct ice_fltr_list_entry *f_entry) { struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_mgmt_list_entry *list_elem; struct mutex *rule_lock; /* Lock to protect filter rule list */ - enum ice_status status = 0; bool remove_rule = false; u16 vsi_handle; + int status = 0; if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; f_entry->fltr_info.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle); @@ -2395,14 +2395,14 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, mutex_lock(rule_lock); list_elem = ice_find_rule_entry(hw, recp_id, &f_entry->fltr_info); if (!list_elem) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; goto exit; } if (list_elem->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST) { remove_rule = true; } else if (!list_elem->vsi_list_info) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; goto exit; } else if (list_elem->vsi_list_info->ref_cnt > 1) { /* a ref_cnt > 1 indicates that the vsi_list is being @@ -2435,7 +2435,7 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, ICE_SW_RULE_RX_TX_NO_HDR_SIZE, GFP_KERNEL); if (!s_rule) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto exit; } @@ -2590,7 +2590,7 @@ bool ice_vlan_fltr_exist(struct ice_hw *hw, u16 vlan_id, u16 vsi_handle) * check for duplicates in this case, removing duplicates from a given * list should be taken care of in the caller of this function. */ -enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_list) +int ice_add_mac(struct ice_hw *hw, struct list_head *m_list) { struct ice_aqc_sw_rules_elem *s_rule, *r_iter; struct ice_fltr_list_entry *m_list_itr; @@ -2598,12 +2598,12 @@ enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_list) u16 total_elem_left, s_rule_size; struct ice_switch_info *sw; struct mutex *rule_lock; /* Lock to protect filter rule list */ - enum ice_status status = 0; u16 num_unicast = 0; + int status = 0; u8 elem_sent; if (!m_list || !hw) - return ICE_ERR_PARAM; + return -EINVAL; s_rule = NULL; sw = hw->switch_info; @@ -2616,23 +2616,23 @@ enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_list) m_list_itr->fltr_info.flag = ICE_FLTR_TX; vsi_handle = m_list_itr->fltr_info.vsi_handle; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); m_list_itr->fltr_info.fwd_id.hw_vsi_id = hw_vsi_id; /* update the src in case it is VSI num */ if (m_list_itr->fltr_info.src_id != ICE_SRC_ID_VSI) - return ICE_ERR_PARAM; + return -EINVAL; m_list_itr->fltr_info.src = hw_vsi_id; if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC || is_zero_ether_addr(add)) - return ICE_ERR_PARAM; + return -EINVAL; if (is_unicast_ether_addr(add) && !hw->ucast_shared) { /* Don't overwrite the unicast address */ mutex_lock(rule_lock); if (ice_find_rule_entry(hw, ICE_SW_LKUP_MAC, &m_list_itr->fltr_info)) { mutex_unlock(rule_lock); - return ICE_ERR_ALREADY_EXISTS; + return -EEXIST; } mutex_unlock(rule_lock); num_unicast++; @@ -2660,7 +2660,7 @@ enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_list) s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size, GFP_KERNEL); if (!s_rule) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto ice_add_mac_exit; } @@ -2710,7 +2710,7 @@ enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_list) fm_entry = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*fm_entry), GFP_KERNEL); if (!fm_entry) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto ice_add_mac_exit; } fm_entry->fltr_info = *f_info; @@ -2737,7 +2737,7 @@ ice_add_mac_exit: * @hw: pointer to the hardware structure * @f_entry: filter entry containing one VLAN information */ -static enum ice_status +static int ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { struct ice_switch_info *sw = hw->switch_info; @@ -2746,10 +2746,10 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) enum ice_sw_lkup_type lkup_type; u16 vsi_list_id = 0, vsi_handle; struct mutex *rule_lock; /* Lock to protect filter rule list */ - enum ice_status status = 0; + int status = 0; if (!ice_is_vsi_valid(hw, f_entry->fltr_info.vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; f_entry->fltr_info.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, f_entry->fltr_info.vsi_handle); @@ -2757,10 +2757,10 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) /* VLAN ID should only be 12 bits */ if (new_fltr->l_data.vlan.vlan_id > ICE_MAX_VLAN_ID) - return ICE_ERR_PARAM; + return -EINVAL; if (new_fltr->src_id != ICE_SRC_ID_VSI) - return ICE_ERR_PARAM; + return -EINVAL; new_fltr->src = new_fltr->fwd_id.hw_vsi_id; lkup_type = new_fltr->lkup_type; @@ -2799,7 +2799,7 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, new_fltr); if (!v_list_itr) { - status = ICE_ERR_DOES_NOT_EXIST; + status = -ENOENT; goto exit; } /* reuse VSI list for new rule and increment ref_cnt */ @@ -2835,7 +2835,7 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) if (v_list_itr->vsi_count > 1 && v_list_itr->vsi_list_info->ref_cnt > 1) { ice_debug(hw, ICE_DBG_SW, "Invalid configuration: Optimization to reuse VSI list with more than one VSI is not being done yet\n"); - status = ICE_ERR_CFG; + status = -EIO; goto exit; } @@ -2845,7 +2845,7 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) /* A rule already exists with the new VSI being added */ if (cur_handle == vsi_handle) { - status = ICE_ERR_ALREADY_EXISTS; + status = -EEXIST; goto exit; } @@ -2890,16 +2890,16 @@ exit: * @hw: pointer to the hardware structure * @v_list: list of VLAN entries and forwarding information */ -enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *v_list) +int ice_add_vlan(struct ice_hw *hw, struct list_head *v_list) { struct ice_fltr_list_entry *v_list_itr; if (!v_list || !hw) - return ICE_ERR_PARAM; + return -EINVAL; list_for_each_entry(v_list_itr, v_list, list_entry) { if (v_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_VLAN) - return ICE_ERR_PARAM; + return -EINVAL; v_list_itr->fltr_info.flag = ICE_FLTR_TX; v_list_itr->status = ice_add_vlan_internal(hw, v_list_itr); if (v_list_itr->status) @@ -2917,13 +2917,12 @@ enum ice_status ice_add_vlan(struct ice_hw *hw, struct list_head *v_list) * the filter list with the necessary fields (including flags to * indicate Tx or Rx rules). */ -enum ice_status -ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list) +int ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list) { struct ice_fltr_list_entry *em_list_itr; if (!em_list || !hw) - return ICE_ERR_PARAM; + return -EINVAL; list_for_each_entry(em_list_itr, em_list, list_entry) { enum ice_sw_lkup_type l_type = @@ -2931,7 +2930,7 @@ ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list) if (l_type != ICE_SW_LKUP_ETHERTYPE_MAC && l_type != ICE_SW_LKUP_ETHERTYPE) - return ICE_ERR_PARAM; + return -EINVAL; em_list_itr->status = ice_add_rule_internal(hw, l_type, em_list_itr); @@ -2946,13 +2945,12 @@ ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list) * @hw: pointer to the hardware structure * @em_list: list of ethertype or ethertype MAC entries */ -enum ice_status -ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list) +int ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list) { struct ice_fltr_list_entry *em_list_itr, *tmp; if (!em_list || !hw) - return ICE_ERR_PARAM; + return -EINVAL; list_for_each_entry_safe(em_list_itr, tmp, em_list, list_entry) { enum ice_sw_lkup_type l_type = @@ -2960,7 +2958,7 @@ ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list) if (l_type != ICE_SW_LKUP_ETHERTYPE_MAC && l_type != ICE_SW_LKUP_ETHERTYPE) - return ICE_ERR_PARAM; + return -EINVAL; em_list_itr->status = ice_remove_rule_internal(hw, l_type, em_list_itr); @@ -3020,18 +3018,17 @@ ice_rem_adv_rule_info(struct ice_hw *hw, struct list_head *rule_head) * add filter rule to set/unset given VSI as default VSI for the switch * (represented by swid) */ -enum ice_status -ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction) +int ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction) { struct ice_aqc_sw_rules_elem *s_rule; struct ice_fltr_info f_info; enum ice_adminq_opc opcode; - enum ice_status status; u16 s_rule_size; u16 hw_vsi_id; + int status; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); s_rule_size = set ? ICE_SW_RULE_RX_TX_ETH_HDR_SIZE : @@ -3039,7 +3036,7 @@ ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction) s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); if (!s_rule) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; memset(&f_info, 0, sizeof(f_info)); @@ -3137,18 +3134,18 @@ ice_find_ucast_rule_entry(struct ice_hw *hw, u8 recp_id, * This function removes either a MAC filter rule or a specific VSI from a * VSI list for a multicast MAC address. * - * Returns ICE_ERR_DOES_NOT_EXIST if a given entry was not added by - * ice_add_mac. Caller should be aware that this call will only work if all - * the entries passed into m_list were added previously. It will not attempt to - * do a partial remove of entries that were found. + * Returns -ENOENT if a given entry was not added by ice_add_mac. Caller should + * be aware that this call will only work if all the entries passed into m_list + * were added previously. It will not attempt to do a partial remove of entries + * that were found. */ -enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) +int ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) { struct ice_fltr_list_entry *list_itr, *tmp; struct mutex *rule_lock; /* Lock to protect filter rule list */ if (!m_list) - return ICE_ERR_PARAM; + return -EINVAL; rule_lock = &hw->switch_info->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; list_for_each_entry_safe(list_itr, tmp, m_list, list_entry) { @@ -3157,11 +3154,11 @@ enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) u16 vsi_handle; if (l_type != ICE_SW_LKUP_MAC) - return ICE_ERR_PARAM; + return -EINVAL; vsi_handle = list_itr->fltr_info.vsi_handle; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; list_itr->fltr_info.fwd_id.hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); @@ -3174,7 +3171,7 @@ enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) if (!ice_find_ucast_rule_entry(hw, ICE_SW_LKUP_MAC, &list_itr->fltr_info)) { mutex_unlock(rule_lock); - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; } mutex_unlock(rule_lock); } @@ -3192,19 +3189,18 @@ enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) * @hw: pointer to the hardware structure * @v_list: list of VLAN entries and forwarding information */ -enum ice_status -ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) +int ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) { struct ice_fltr_list_entry *v_list_itr, *tmp; if (!v_list || !hw) - return ICE_ERR_PARAM; + return -EINVAL; list_for_each_entry_safe(v_list_itr, tmp, v_list, list_entry) { enum ice_sw_lkup_type l_type = v_list_itr->fltr_info.lkup_type; if (l_type != ICE_SW_LKUP_VLAN) - return ICE_ERR_PARAM; + return -EINVAL; v_list_itr->status = ice_remove_rule_internal(hw, ICE_SW_LKUP_VLAN, v_list_itr); @@ -3242,7 +3238,7 @@ ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_handle) * fltr_info.fwd_id fields. These are set such that later logic can * extract which VSI to remove the fltr from, and pass on that information. */ -static enum ice_status +static int ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, struct list_head *vsi_list_head, struct ice_fltr_info *fi) @@ -3254,7 +3250,7 @@ ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, */ tmp = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*tmp), GFP_KERNEL); if (!tmp) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; tmp->fltr_info = *fi; @@ -3285,17 +3281,17 @@ ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, * Note that this means all entries in vsi_list_head must be explicitly * deallocated by the caller when done with list. */ -static enum ice_status +static int ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, struct list_head *lkup_list_head, struct list_head *vsi_list_head) { struct ice_fltr_mgmt_list_entry *fm_entry; - enum ice_status status = 0; + int status = 0; /* check to make sure VSI ID is valid and within boundary */ if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; list_for_each_entry(fm_entry, lkup_list_head, list_entry) { if (!ice_vsi_uses_fltr(fm_entry, vsi_handle)) @@ -3349,9 +3345,8 @@ static u8 ice_determine_promisc_mask(struct ice_fltr_info *fi) * @recp_id: recipe ID for which the rule needs to removed * @v_list: list of promisc entries */ -static enum ice_status -ice_remove_promisc(struct ice_hw *hw, u8 recp_id, - struct list_head *v_list) +static int +ice_remove_promisc(struct ice_hw *hw, u8 recp_id, struct list_head *v_list) { struct ice_fltr_list_entry *v_list_itr, *tmp; @@ -3371,7 +3366,7 @@ ice_remove_promisc(struct ice_hw *hw, u8 recp_id, * @promisc_mask: mask of promiscuous config bits to clear * @vid: VLAN ID to clear VLAN promiscuous */ -enum ice_status +int ice_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { @@ -3381,11 +3376,11 @@ ice_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, struct ice_fltr_mgmt_list_entry *itr; struct list_head *rule_head; struct mutex *rule_lock; /* Lock to protect filter rule list */ - enum ice_status status = 0; + int status = 0; u8 recipe_id; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; if (promisc_mask & (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX)) recipe_id = ICE_SW_LKUP_PROMISC_VLAN; @@ -3444,20 +3439,20 @@ free_fltr_list: * @promisc_mask: mask of promiscuous config bits * @vid: VLAN ID to set VLAN promiscuous */ -enum ice_status +int ice_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { enum { UCAST_FLTR = 1, MCAST_FLTR, BCAST_FLTR }; struct ice_fltr_list_entry f_list_entry; struct ice_fltr_info new_fltr; - enum ice_status status = 0; bool is_tx_fltr; + int status = 0; u16 hw_vsi_id; int pkt_type; u8 recipe_id; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; hw_vsi_id = ice_get_hw_vsi_num(hw, vsi_handle); memset(&new_fltr, 0, sizeof(new_fltr)); @@ -3558,7 +3553,7 @@ set_promisc_exit: * * Configure VSI with all associated VLANs to given promiscuous mode(s) */ -enum ice_status +int ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, bool rm_vlan_promisc) { @@ -3567,8 +3562,8 @@ ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, struct list_head vsi_list_head; struct list_head *vlan_head; struct mutex *vlan_lock; /* Lock to protect filter rule list */ - enum ice_status status; u16 vlan_id; + int status; INIT_LIST_HEAD(&vsi_list_head); vlan_lock = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rule_lock; @@ -3616,7 +3611,7 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle, struct list_head *rule_head; struct ice_fltr_list_entry *tmp; struct mutex *rule_lock; /* Lock to protect filter rule list */ - enum ice_status status; + int status; INIT_LIST_HEAD(&remove_list_head); rule_lock = &sw->recp_list[lkup].filt_rule_lock; @@ -3681,19 +3676,19 @@ void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle) * @num_items: number of entries requested for FD resource type * @counter_id: counter index returned by AQ call */ -enum ice_status +int ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 *counter_id) { struct ice_aqc_alloc_free_res_elem *buf; - enum ice_status status; u16 buf_len; + int status; /* Allocate resource */ buf_len = struct_size(buf, elem, 1); buf = kzalloc(buf_len, GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; buf->num_elems = cpu_to_le16(num_items); buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & @@ -3719,19 +3714,19 @@ exit: * @num_items: number of entries to be freed for FD resource type * @counter_id: counter ID resource which needs to be freed */ -enum ice_status +int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id) { struct ice_aqc_alloc_free_res_elem *buf; - enum ice_status status; u16 buf_len; + int status; /* Free resource */ buf_len = struct_size(buf, elem, 1); buf = kzalloc(buf_len, GFP_KERNEL); if (!buf) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; buf->num_elems = cpu_to_le16(num_items); buf->res_type = cpu_to_le16(((type << ICE_AQC_RES_TYPE_S) & @@ -3796,10 +3791,13 @@ static struct ice_protocol_entry ice_prot_id_tbl[ICE_PROTOCOL_LAST] = { * ice_find_recp - find a recipe * @hw: pointer to the hardware structure * @lkup_exts: extension sequence to match + * @tun_type: type of recipe tunnel * * Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found. */ -static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts) +static u16 +ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, + enum ice_sw_tunnel_type tun_type) { bool refresh_required = true; struct ice_sw_recipe *recp; @@ -3860,8 +3858,9 @@ static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts) } /* If for "i"th recipe the found was never set to false * then it means we found our match + * Also tun type of recipe needs to be checked */ - if (found) + if (found && recp[i].tun_type == tun_type) return i; /* Return the recipe ID */ } } @@ -3937,7 +3936,7 @@ ice_fill_valid_words(struct ice_adv_lkup_elem *rule, * and start grouping them in 4-word groups. Each group makes up one * recipe. */ -static enum ice_status +static int ice_create_first_fit_recp_def(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, struct list_head *rg_list, @@ -3961,7 +3960,7 @@ ice_create_first_fit_recp_def(struct ice_hw *hw, sizeof(*entry), GFP_KERNEL); if (!entry) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; list_add(&entry->l_entry, rg_list); grp = &entry->r_group; (*recp_cnt)++; @@ -3987,7 +3986,7 @@ ice_create_first_fit_recp_def(struct ice_hw *hw, * Helper function to fill in the field vector indices for protocol-offset * pairs. These indexes are then ultimately programmed into a recipe. */ -static enum ice_status +static int ice_fill_fv_word_index(struct ice_hw *hw, struct list_head *fv_list, struct list_head *rg_list) { @@ -4029,7 +4028,7 @@ ice_fill_fv_word_index(struct ice_hw *hw, struct list_head *fv_list, * invalid pair */ if (!found) - return ICE_ERR_PARAM; + return -EINVAL; } } @@ -4111,7 +4110,7 @@ ice_find_free_recp_res_idx(struct ice_hw *hw, const unsigned long *profiles, * @rm: recipe management list entry * @profiles: bitmap of profiles that will be associated. */ -static enum ice_status +static int ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, unsigned long *profiles) { @@ -4119,11 +4118,11 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, struct ice_aqc_recipe_data_elem *tmp; struct ice_aqc_recipe_data_elem *buf; struct ice_recp_grp_entry *entry; - enum ice_status status; u16 free_res_idx; u16 recipe_count; u8 chain_idx; u8 recps = 0; + int status; /* When more than one recipe are required, another recipe is needed to * chain them together. Matching a tunnel metadata ID takes up one of @@ -4139,22 +4138,22 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, if (rm->n_grp_count > 1) { if (rm->n_grp_count > free_res_idx) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; rm->n_grp_count++; } if (rm->n_grp_count > ICE_MAX_CHAIN_RECIPE) - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; tmp = kcalloc(ICE_MAX_NUM_RECIPES, sizeof(*tmp), GFP_KERNEL); if (!tmp) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; buf = devm_kcalloc(ice_hw_to_dev(hw), rm->n_grp_count, sizeof(*buf), GFP_KERNEL); if (!buf) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_mem; } @@ -4214,7 +4213,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, */ if (chain_idx >= ICE_MAX_FV_WORDS) { ice_debug(hw, ICE_DBG_SW, "No chain index available\n"); - status = ICE_ERR_MAX_LIMIT; + status = -ENOSPC; goto err_unroll; } @@ -4245,7 +4244,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, memcpy(buf[0].recipe_bitmap, rm->r_bitmap, sizeof(buf[0].recipe_bitmap)); } else { - status = ICE_ERR_BAD_PTR; + status = -EINVAL; goto err_unroll; } /* Applicable only for ROOT_RECIPE, set the fwd_priority for @@ -4281,7 +4280,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, sizeof(*last_chain_entry), GFP_KERNEL); if (!last_chain_entry) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_unroll; } last_chain_entry->rid = rid; @@ -4316,7 +4315,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, memcpy(buf[recps].recipe_bitmap, rm->r_bitmap, sizeof(buf[recps].recipe_bitmap)); } else { - status = ICE_ERR_BAD_PTR; + status = -EINVAL; goto err_unroll; } buf[recps].content.act_ctrl_fwd_priority = rm->priority; @@ -4350,7 +4349,7 @@ ice_add_sw_recipe(struct ice_hw *hw, struct ice_sw_recipe *rm, } if (!idx_found) { - status = ICE_ERR_OUT_OF_RANGE; + status = -EIO; goto err_unroll; } @@ -4403,12 +4402,12 @@ err_mem: * @rm: recipe management list entry * @lkup_exts: lookup elements */ -static enum ice_status +static int ice_create_recipe_group(struct ice_hw *hw, struct ice_sw_recipe *rm, struct ice_prot_lkup_ext *lkup_exts) { - enum ice_status status; u8 recp_count = 0; + int status; rm->n_grp_count = 0; @@ -4438,21 +4437,21 @@ ice_create_recipe_group(struct ice_hw *hw, struct ice_sw_recipe *rm, * @bm: bitmap of field vectors to consider * @fv_list: pointer to a list that holds the returned field vectors */ -static enum ice_status +static int ice_get_fv(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, unsigned long *bm, struct list_head *fv_list) { - enum ice_status status; u8 *prot_ids; + int status; u16 i; prot_ids = kcalloc(lkups_cnt, sizeof(*prot_ids), GFP_KERNEL); if (!prot_ids) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; for (i = 0; i < lkups_cnt; i++) if (!ice_prot_type_to_id(lkups[i].type, &prot_ids[i])) { - status = ICE_ERR_CFG; + status = -EIO; goto free_mem; } @@ -4489,7 +4488,7 @@ static bool ice_tun_type_match_word(enum ice_sw_tunnel_type tun_type, u16 *mask) * @rinfo: other information regarding the rule e.g. priority and action info * @lkup_exts: lookup word structure */ -static enum ice_status +static int ice_add_special_words(struct ice_adv_rule_info *rinfo, struct ice_prot_lkup_ext *lkup_exts) { @@ -4506,7 +4505,7 @@ ice_add_special_words(struct ice_adv_rule_info *rinfo, lkup_exts->fv_words[word].off = ICE_TUN_FLAG_MDID_OFF; lkup_exts->field_mask[word] = mask; } else { - return ICE_ERR_MAX_LIMIT; + return -ENOSPC; } } @@ -4557,7 +4556,7 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, * @rinfo: other information regarding the rule e.g. priority and action info * @rid: return the recipe ID of the recipe created */ -static enum ice_status +static int ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, struct ice_adv_rule_info *rinfo, u16 *rid) { @@ -4568,16 +4567,16 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, struct ice_sw_fv_list_entry *fvit; struct ice_recp_grp_entry *r_tmp; struct ice_sw_fv_list_entry *tmp; - enum ice_status status = 0; struct ice_sw_recipe *rm; + int status = 0; u8 i; if (!lkups_cnt) - return ICE_ERR_PARAM; + return -EINVAL; lkup_exts = kzalloc(sizeof(*lkup_exts), GFP_KERNEL); if (!lkup_exts) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; /* Determine the number of words to be matched and if it exceeds a * recipe's restrictions @@ -4586,20 +4585,20 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 count; if (lkups[i].type >= ICE_PROTOCOL_LAST) { - status = ICE_ERR_CFG; + status = -EIO; goto err_free_lkup_exts; } count = ice_fill_valid_words(&lkups[i], lkup_exts); if (!count) { - status = ICE_ERR_CFG; + status = -EIO; goto err_free_lkup_exts; } } rm = kzalloc(sizeof(*rm), GFP_KERNEL); if (!rm) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_free_lkup_exts; } @@ -4651,11 +4650,12 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } /* Look for a recipe which matches our requested fv / mask list */ - *rid = ice_find_recp(hw, lkup_exts); + *rid = ice_find_recp(hw, lkup_exts, rinfo->tun_type); if (*rid < ICE_MAX_NUM_RECIPES) /* Success if found a recipe that match the existing criteria */ goto err_unroll; + rm->tun_type = rinfo->tun_type; /* Recipe we need does not exist, add a recipe */ status = ice_add_sw_recipe(hw, rm, profiles); if (status) @@ -4844,7 +4844,7 @@ ice_find_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, * @pkt_len: packet length of dummy packet * @offsets: offset info for the dummy packet */ -static enum ice_status +static int ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, struct ice_aqc_sw_rules_elem *s_rule, const u8 *dummy_pkt, u16 pkt_len, @@ -4878,7 +4878,7 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, } /* this should never happen in a correct calling sequence */ if (!found) - return ICE_ERR_PARAM; + return -EINVAL; switch (lkups[i].type) { case ICE_MAC_OFOS: @@ -4915,12 +4915,12 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, len = sizeof(struct ice_udp_tnl_hdr); break; default: - return ICE_ERR_PARAM; + return -EINVAL; } /* the length should be a word multiple */ if (len % ICE_BYTES_PER_WORD) - return ICE_ERR_CFG; + return -EIO; /* We have the offset to the header start, the length, the * caller's header values and mask. Use this information to @@ -4950,7 +4950,7 @@ ice_fill_adv_dummy_packet(struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, * @pkt: dummy packet to fill in * @offsets: offset info for the dummy packet */ -static enum ice_status +static int ice_fill_adv_packet_tun(struct ice_hw *hw, enum ice_sw_tunnel_type tun_type, u8 *pkt, const struct ice_dummy_pkt_offsets *offsets) { @@ -4958,11 +4958,13 @@ ice_fill_adv_packet_tun(struct ice_hw *hw, enum ice_sw_tunnel_type tun_type, switch (tun_type) { case ICE_SW_TUN_VXLAN: + if (!ice_get_open_tunnel_port(hw, &open_port, TNL_VXLAN)) + return -EIO; + break; case ICE_SW_TUN_GENEVE: - if (!ice_get_open_tunnel_port(hw, &open_port)) - return ICE_ERR_CFG; + if (!ice_get_open_tunnel_port(hw, &open_port, TNL_GENEVE)) + return -EIO; break; - default: /* Nothing needs to be done for this tunnel type */ return 0; @@ -4982,7 +4984,7 @@ ice_fill_adv_packet_tun(struct ice_hw *hw, enum ice_sw_tunnel_type tun_type, } } - return ICE_ERR_CFG; + return -EIO; } /** @@ -5047,25 +5049,25 @@ ice_find_adv_rule_entry(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, * Add the new VSI to the previously created VSI list set * using the update switch rule command */ -static enum ice_status +static int ice_adv_add_update_vsi_list(struct ice_hw *hw, struct ice_adv_fltr_mgmt_list_entry *m_entry, struct ice_adv_rule_info *cur_fltr, struct ice_adv_rule_info *new_fltr) { - enum ice_status status; u16 vsi_list_id = 0; + int status; if (cur_fltr->sw_act.fltr_act == ICE_FWD_TO_Q || cur_fltr->sw_act.fltr_act == ICE_FWD_TO_QGRP || cur_fltr->sw_act.fltr_act == ICE_DROP_PACKET) - return ICE_ERR_NOT_IMPL; + return -EOPNOTSUPP; if ((new_fltr->sw_act.fltr_act == ICE_FWD_TO_Q || new_fltr->sw_act.fltr_act == ICE_FWD_TO_QGRP) && (cur_fltr->sw_act.fltr_act == ICE_FWD_TO_VSI || cur_fltr->sw_act.fltr_act == ICE_FWD_TO_VSI_LIST)) - return ICE_ERR_NOT_IMPL; + return -EOPNOTSUPP; if (m_entry->vsi_count < 2 && !m_entry->vsi_list_info) { /* Only one entry existed in the mapping and it was not already @@ -5078,7 +5080,7 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw, /* A rule already exists with the new VSI being added */ if (cur_fltr->sw_act.fwd_id.hw_vsi_id == new_fltr->sw_act.fwd_id.hw_vsi_id) - return ICE_ERR_ALREADY_EXISTS; + return -EEXIST; vsi_handle_arr[0] = cur_fltr->sw_act.vsi_handle; vsi_handle_arr[1] = new_fltr->sw_act.vsi_handle; @@ -5111,7 +5113,7 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw, u16 vsi_handle = new_fltr->sw_act.vsi_handle; if (!m_entry->vsi_list_info) - return ICE_ERR_CFG; + return -EIO; /* A rule already exists with the new VSI being added */ if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) @@ -5153,7 +5155,7 @@ ice_adv_add_update_vsi_list(struct ice_hw *hw, * rinfo describes other information related to this rule such as forwarding * IDs, priority of this rule, etc. */ -enum ice_status +int ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, struct ice_adv_rule_info *rinfo, struct ice_rule_query_data *added_entry) @@ -5164,10 +5166,10 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, struct ice_aqc_sw_rules_elem *s_rule = NULL; struct list_head *rule_head; struct ice_switch_info *sw; - enum ice_status status; const u8 *pkt = NULL; u16 word_cnt; u32 act = 0; + int status; u8 q_rgn; /* Initialize profile to result index bitmap */ @@ -5177,7 +5179,7 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } if (!lkups_cnt) - return ICE_ERR_PARAM; + return -EINVAL; /* get # of words we need to match */ word_cnt = 0; @@ -5191,13 +5193,13 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, } if (!word_cnt || word_cnt > ICE_MAX_CHAIN_WORDS) - return ICE_ERR_PARAM; + return -EINVAL; /* make sure that we can locate a dummy packet */ ice_find_dummy_packet(lkups, lkups_cnt, rinfo->tun_type, &pkt, &pkt_len, &pkt_offsets); if (!pkt) { - status = ICE_ERR_PARAM; + status = -EINVAL; goto err_ice_add_adv_rule; } @@ -5205,11 +5207,11 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, rinfo->sw_act.fltr_act == ICE_FWD_TO_Q || rinfo->sw_act.fltr_act == ICE_FWD_TO_QGRP || rinfo->sw_act.fltr_act == ICE_DROP_PACKET)) - return ICE_ERR_CFG; + return -EIO; vsi_handle = rinfo->sw_act.vsi_handle; if (!ice_is_vsi_valid(hw, vsi_handle)) - return ICE_ERR_PARAM; + return -EINVAL; if (rinfo->sw_act.fltr_act == ICE_FWD_TO_VSI) rinfo->sw_act.fwd_id.hw_vsi_id = @@ -5243,7 +5245,7 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, rule_buf_sz = ICE_SW_RULE_RX_TX_NO_HDR_SIZE + pkt_len; s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); if (!s_rule) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; if (!rinfo->flags_info.act_valid) { act |= ICE_SINGLE_ACT_LAN_ENABLE; act |= ICE_SINGLE_ACT_LB_ENABLE; @@ -5277,7 +5279,7 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, ICE_SINGLE_ACT_VALID_BIT; break; default: - status = ICE_ERR_CFG; + status = -EIO; goto err_ice_add_adv_rule; } @@ -5322,14 +5324,14 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, sizeof(struct ice_adv_fltr_mgmt_list_entry), GFP_KERNEL); if (!adv_fltr) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_ice_add_adv_rule; } adv_fltr->lkups = devm_kmemdup(ice_hw_to_dev(hw), lkups, lkups_cnt * sizeof(*lkups), GFP_KERNEL); if (!adv_fltr->lkups) { - status = ICE_ERR_NO_MEMORY; + status = -ENOMEM; goto err_ice_add_adv_rule; } @@ -5372,12 +5374,12 @@ err_ice_add_adv_rule: * Replays the filter of recipe recp_id for a VSI represented via vsi_handle. * It is required to pass valid VSI handle. */ -static enum ice_status +static int ice_replay_vsi_fltr(struct ice_hw *hw, u16 vsi_handle, u8 recp_id, struct list_head *list_head) { struct ice_fltr_mgmt_list_entry *itr; - enum ice_status status = 0; + int status = 0; u16 hw_vsi_id; if (list_empty(list_head)) @@ -5426,22 +5428,22 @@ end: * @fm_list: filter management entry for which the VSI list management needs to * be done */ -static enum ice_status +static int ice_adv_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, struct ice_adv_fltr_mgmt_list_entry *fm_list) { struct ice_vsi_list_map_info *vsi_list_info; enum ice_sw_lkup_type lkup_type; - enum ice_status status; u16 vsi_list_id; + int status; if (fm_list->rule_info.sw_act.fltr_act != ICE_FWD_TO_VSI_LIST || fm_list->vsi_count == 0) - return ICE_ERR_PARAM; + return -EINVAL; /* A rule with the VSI being removed does not exist */ if (!test_bit(vsi_handle, fm_list->vsi_list_info->vsi_map)) - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; lkup_type = ICE_SW_LKUP_LAST; vsi_list_id = fm_list->rule_info.sw_act.fwd_id.vsi_list_id; @@ -5461,7 +5463,7 @@ ice_adv_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, rem_vsi_handle = find_first_bit(vsi_list_info->vsi_map, ICE_MAX_VSI); if (!ice_is_vsi_valid(hw, rem_vsi_handle)) - return ICE_ERR_OUT_OF_RANGE; + return -EIO; /* Make sure VSI list is empty before removing it below */ status = ice_update_vsi_list_rule(hw, &rem_vsi_handle, 1, @@ -5525,27 +5527,27 @@ ice_adv_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_handle, * header. rinfo describes other information related to this rule such as * forwarding IDs, priority of this rule, etc. */ -static enum ice_status +static int ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, struct ice_adv_rule_info *rinfo) { struct ice_adv_fltr_mgmt_list_entry *list_elem; struct ice_prot_lkup_ext lkup_exts; - enum ice_status status = 0; bool remove_rule = false; struct mutex *rule_lock; /* Lock to protect filter rule list */ u16 i, rid, vsi_handle; + int status = 0; memset(&lkup_exts, 0, sizeof(lkup_exts)); for (i = 0; i < lkups_cnt; i++) { u16 count; if (lkups[i].type >= ICE_PROTOCOL_LAST) - return ICE_ERR_CFG; + return -EIO; count = ice_fill_valid_words(&lkups[i], &lkup_exts); if (!count) - return ICE_ERR_CFG; + return -EIO; } /* Create any special protocol/offset pairs, such as looking at tunnel @@ -5555,10 +5557,10 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (status) return status; - rid = ice_find_recp(hw, &lkup_exts); + rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type); /* If did not find a recipe that match the existing criteria */ if (rid == ICE_MAX_NUM_RECIPES) - return ICE_ERR_PARAM; + return -EINVAL; rule_lock = &hw->switch_info->recp_list[rid].filt_rule_lock; list_elem = ice_find_adv_rule_entry(hw, lkups, lkups_cnt, rid, rinfo); @@ -5590,7 +5592,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, rule_buf_sz = ICE_SW_RULE_RX_TX_NO_HDR_SIZE; s_rule = kzalloc(rule_buf_sz, GFP_KERNEL); if (!s_rule) - return ICE_ERR_NO_MEMORY; + return -ENOMEM; s_rule->pdata.lkup_tx_rx.act = 0; s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(list_elem->rule_info.fltr_rule_id); @@ -5598,7 +5600,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, status = ice_aq_sw_rules(hw, (struct ice_aqc_sw_rules *)s_rule, rule_buf_sz, 1, ice_aqc_opc_remove_sw_rules, NULL); - if (!status || status == ICE_ERR_DOES_NOT_EXIST) { + if (!status || status == -ENOENT) { struct ice_switch_info *sw = hw->switch_info; mutex_lock(rule_lock); @@ -5623,7 +5625,7 @@ ice_rem_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, * the remove_entry parameter. This function will remove rule for a given * vsi_handle with a given rule_id which is passed as parameter in remove_entry */ -enum ice_status +int ice_rem_adv_rule_by_id(struct ice_hw *hw, struct ice_rule_query_data *remove_entry) { @@ -5634,7 +5636,7 @@ ice_rem_adv_rule_by_id(struct ice_hw *hw, sw = hw->switch_info; if (!sw->recp_list[remove_entry->rid].recp_created) - return ICE_ERR_PARAM; + return -EINVAL; list_head = &sw->recp_list[remove_entry->rid].filt_rules; list_for_each_entry(list_itr, list_head, list_entry) { if (list_itr->rule_info.fltr_rule_id == @@ -5646,7 +5648,7 @@ ice_rem_adv_rule_by_id(struct ice_hw *hw, } } /* either list is empty or unable to find rule */ - return ICE_ERR_DOES_NOT_EXIST; + return -ENOENT; } /** @@ -5656,10 +5658,10 @@ ice_rem_adv_rule_by_id(struct ice_hw *hw, * * Replays filters for requested VSI via vsi_handle. */ -enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle) +int ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle) { struct ice_switch_info *sw = hw->switch_info; - enum ice_status status = 0; + int status = 0; u8 i; for (i = 0; i < ICE_SW_LKUP_LAST; i++) { diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index d8a38906f16f..d8334beaaa8a 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -256,7 +256,7 @@ struct ice_vsi_list_map_info { struct ice_fltr_list_entry { struct list_head list_entry; - enum ice_status status; + int status; struct ice_fltr_info fltr_info; }; @@ -302,75 +302,69 @@ enum ice_promisc_flags { }; /* VSI related commands */ -enum ice_status +int ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd); -enum ice_status +int ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, bool keep_vsi_alloc, struct ice_sq_cd *cd); -enum ice_status +int ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd); bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle); struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle); void ice_clear_all_vsi_ctx(struct ice_hw *hw); /* Switch config */ -enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw); +int ice_get_initial_sw_cfg(struct ice_hw *hw); -enum ice_status +int ice_alloc_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 *counter_id); -enum ice_status +int ice_free_res_cntr(struct ice_hw *hw, u8 type, u8 alloc_shared, u16 num_items, u16 counter_id); /* Switch/bridge related commands */ -enum ice_status +int ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, u16 lkups_cnt, struct ice_adv_rule_info *rinfo, struct ice_rule_query_data *added_entry); -enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw); -enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); -enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); -enum ice_status -ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list); -enum ice_status -ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list); -int -ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable); +int ice_update_sw_rule_bridge_mode(struct ice_hw *hw); +int ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); +int ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); +int ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); +int ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); bool ice_mac_fltr_exist(struct ice_hw *hw, u8 *mac, u16 vsi_handle); bool ice_vlan_fltr_exist(struct ice_hw *hw, u16 vlan_id, u16 vsi_handle); +int ice_add_eth_mac(struct ice_hw *hw, struct list_head *em_list); +int ice_remove_eth_mac(struct ice_hw *hw, struct list_head *em_list); +int ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable); void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle); -enum ice_status -ice_add_vlan(struct ice_hw *hw, struct list_head *m_list); -enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); /* Promisc/defport setup for VSIs */ -enum ice_status -ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction); -enum ice_status +int ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_handle, bool set, u8 direction); +int ice_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid); -enum ice_status +int ice_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid); -enum ice_status +int ice_set_vlan_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, bool rm_vlan_promisc); -enum ice_status -ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle); -enum ice_status +int ice_rem_adv_rule_for_vsi(struct ice_hw *hw, u16 vsi_handle); +int ice_rem_adv_rule_by_id(struct ice_hw *hw, struct ice_rule_query_data *remove_entry); -enum ice_status ice_init_def_sw_recp(struct ice_hw *hw); +int ice_init_def_sw_recp(struct ice_hw *hw); u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle); -enum ice_status ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); +int ice_replay_vsi_all_fltr(struct ice_hw *hw, u16 vsi_handle); void ice_rm_all_sw_replay_rule_info(struct ice_hw *hw); -enum ice_status +int ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz, u8 num_rules, enum ice_adminq_opc opc, struct ice_sq_cd *cd); #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index e5d23feb6701..e8aab664270a 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -74,21 +74,13 @@ static enum ice_protocol_type ice_proto_type_from_ipv6(bool inner) return inner ? ICE_IPV6_IL : ICE_IPV6_OFOS; } -static enum ice_protocol_type -ice_proto_type_from_l4_port(bool inner, u16 ip_proto) +static enum ice_protocol_type ice_proto_type_from_l4_port(u16 ip_proto) { - if (inner) { - switch (ip_proto) { - case IPPROTO_UDP: - return ICE_UDP_ILOS; - } - } else { - switch (ip_proto) { - case IPPROTO_TCP: - return ICE_TCP_IL; - case IPPROTO_UDP: - return ICE_UDP_OF; - } + switch (ip_proto) { + case IPPROTO_TCP: + return ICE_TCP_IL; + case IPPROTO_UDP: + return ICE_UDP_ILOS; } return 0; @@ -191,8 +183,9 @@ ice_tc_fill_tunnel_outer(u32 flags, struct ice_tc_flower_fltr *fltr, i++; } - if (flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) { - list[i].type = ice_proto_type_from_l4_port(false, hdr->l3_key.ip_proto); + if ((flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) && + hdr->l3_key.ip_proto == IPPROTO_UDP) { + list[i].type = ICE_UDP_OF; list[i].h_u.l4_hdr.dst_port = hdr->l4_key.dst_port; list[i].m_u.l4_hdr.dst_port = hdr->l4_mask.dst_port; i++; @@ -317,7 +310,7 @@ ice_tc_fill_rules(struct ice_hw *hw, u32 flags, ICE_TC_FLWR_FIELD_SRC_L4_PORT)) { struct ice_tc_l4_hdr *l4_key, *l4_mask; - list[i].type = ice_proto_type_from_l4_port(inner, headers->l3_key.ip_proto); + list[i].type = ice_proto_type_from_l4_port(headers->l3_key.ip_proto); l4_key = &headers->l4_key; l4_mask = &headers->l4_mask; @@ -405,9 +398,8 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) struct ice_hw *hw = &vsi->back->hw; struct ice_adv_lkup_elem *list; u32 flags = fltr->flags; - enum ice_status status; int lkups_cnt; - int ret = 0; + int ret; int i; if (!flags || (flags & ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT)) { @@ -456,14 +448,13 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) /* specify the cookie as filter_rule_id */ rule_info.fltr_rule_id = fltr->cookie; - status = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); - if (status == ICE_ERR_ALREADY_EXISTS) { + ret = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, &rule_added); + if (ret == -EEXIST) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because it already exist"); ret = -EINVAL; goto exit; - } else if (status) { + } else if (ret) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter due to error"); - ret = -EIO; goto exit; } @@ -802,7 +793,8 @@ ice_parse_tunnel_attr(struct net_device *dev, struct flow_rule *rule, headers->l3_mask.ttl = match.mask->ttl; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) && + fltr->tunnel_type != TNL_VXLAN && fltr->tunnel_type != TNL_GENEVE) { struct flow_match_ports match; flow_rule_match_enc_ports(rule, &match); @@ -1168,7 +1160,7 @@ static int ice_del_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) rule_rem.vsi_handle = fltr->dest_id; err = ice_rem_adv_rule_by_id(&pf->hw, &rule_rem); if (err) { - if (err == ICE_ERR_DOES_NOT_EXIST) { + if (err == -ENOENT) { NL_SET_ERR_MSG_MOD(fltr->extack, "Filter does not exist"); return -ENOENT; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index bc3ba19dc88f..3987a0dd0e11 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -3,8 +3,9 @@ /* The driver transmit and receive code */ -#include <linux/prefetch.h> #include <linux/mm.h> +#include <linux/netdevice.h> +#include <linux/prefetch.h> #include <linux/bpf_trace.h> #include <net/dsfield.h> #include <net/xdp.h> @@ -219,6 +220,10 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget) struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; + /* get the bql data ready */ + if (!ice_ring_is_xdp(tx_ring)) + netdev_txq_bql_complete_prefetchw(txring_txq(tx_ring)); + tx_buf = &tx_ring->tx_buf[i]; tx_desc = ICE_TX_DESC(tx_ring, i); i -= tx_ring->count; @@ -232,6 +237,9 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget) if (!eop_desc) break; + /* follow the guidelines of other drivers */ + prefetchw(&tx_buf->skb->users); + smp_rmb(); /* prevent any other reads prior to eop_desc */ ice_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); @@ -304,8 +312,10 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget) ice_update_tx_ring_stats(tx_ring, total_pkts, total_bytes); - netdev_tx_completed_queue(txring_txq(tx_ring), total_pkts, - total_bytes); + if (ice_ring_is_xdp(tx_ring)) + return !!budget; + + netdev_tx_completed_queue(txring_txq(tx_ring), total_pkts, total_bytes); #define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2)) if (unlikely(total_pkts && netif_carrier_ok(tx_ring->netdev) && @@ -314,11 +324,9 @@ static bool ice_clean_tx_irq(struct ice_tx_ring *tx_ring, int napi_budget) * sees the new next_to_clean. */ smp_mb(); - if (__netif_subqueue_stopped(tx_ring->netdev, - tx_ring->q_index) && + if (netif_tx_queue_stopped(txring_txq(tx_ring)) && !test_bit(ICE_VSI_DOWN, vsi->state)) { - netif_wake_subqueue(tx_ring->netdev, - tx_ring->q_index); + netif_tx_wake_queue(txring_txq(tx_ring)); ++tx_ring->tx_stats.restart_q; } } @@ -1517,7 +1525,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget) */ static int __ice_maybe_stop_tx(struct ice_tx_ring *tx_ring, unsigned int size) { - netif_stop_subqueue(tx_ring->netdev, tx_ring->q_index); + netif_tx_stop_queue(txring_txq(tx_ring)); /* Memory barrier before checking head and tail */ smp_mb(); @@ -1525,8 +1533,8 @@ static int __ice_maybe_stop_tx(struct ice_tx_ring *tx_ring, unsigned int size) if (likely(ICE_DESC_UNUSED(tx_ring) < size)) return -EBUSY; - /* A reprieve! - use start_subqueue because it doesn't call schedule */ - netif_start_subqueue(tx_ring->netdev, tx_ring->q_index); + /* A reprieve! - use start_queue because it doesn't call schedule */ + netif_tx_start_queue(txring_txq(tx_ring)); ++tx_ring->tx_stats.restart_q; return 0; } @@ -1568,6 +1576,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, struct sk_buff *skb; skb_frag_t *frag; dma_addr_t dma; + bool kick; td_tag = off->td_l2tag1; td_cmd = off->td_cmd; @@ -1649,9 +1658,6 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, tx_buf = &tx_ring->tx_buf[i]; } - /* record bytecount for BQL */ - netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount); - /* record SW timestamp if HW timestamp is not available */ skb_tx_timestamp(first->skb); @@ -1680,7 +1686,10 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, ice_maybe_stop_tx(tx_ring, DESC_NEEDED); /* notify HW of packet */ - if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) + kick = __netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount, + netdev_xmit_more()); + if (kick) + /* notify HW of packet */ writel(i, tx_ring->tail); return; @@ -2265,6 +2274,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) return NETDEV_TX_BUSY; } + /* prefetch for bql data which is infrequently used */ + netdev_txq_bql_enqueue_prefetchw(txring_txq(tx_ring)); + offload.tx_ring = tx_ring; /* record the location of the first descriptor for this packet */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 9e0c2923c62e..58b1907e3ff1 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -7,7 +7,6 @@ #define ICE_BYTES_PER_WORD 2 #define ICE_BYTES_PER_DWORD 4 -#include "ice_status.h" #include "ice_hw_autogen.h" #include "ice_osdep.h" #include "ice_controlq.h" @@ -279,6 +278,10 @@ struct ice_hw_common_caps { #define ICE_NVM_PENDING_NETLIST BIT(2) bool nvm_unified_update; #define ICE_NVM_MGMT_UNIFIED_UPD_SUPPORT BIT(3) + /* PCIe reset avoidance */ + bool pcie_reset_avoidance; + /* Post update reset restriction */ + bool reset_restrict_support; }; /* IEEE 1588 TIME_SYNC specific info */ @@ -873,8 +876,6 @@ struct ice_hw { u8 active_pkg_name[ICE_PKG_NAME_SIZE]; u8 active_pkg_in_nvm; - enum ice_aq_err pkg_dwnld_status; - /* Driver's package ver - (from the Ice Metadata section) */ struct ice_pkg_ver pkg_ver; u8 pkg_name[ICE_PKG_NAME_SIZE]; @@ -919,6 +920,7 @@ struct ice_hw { struct mutex rss_locks; /* protect RSS configuration */ struct list_head rss_list_head; struct ice_mbx_snapshot mbx_snapshot; + DECLARE_BITMAP(hw_ptype, ICE_FLOW_PTYPE_MAX); u16 io_expander_handle; }; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index eee180d8c024..d64df81d4893 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -47,197 +47,6 @@ struct virtchnl_fdir_fltr_conf { u32 flow_id; }; -static enum virtchnl_proto_hdr_type vc_pattern_ether[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_tcp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_TCP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_udp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_UDP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_sctp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_SCTP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv6[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV6, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv6_tcp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV6, - VIRTCHNL_PROTO_HDR_TCP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv6_udp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV6, - VIRTCHNL_PROTO_HDR_UDP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv6_sctp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV6, - VIRTCHNL_PROTO_HDR_SCTP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_gtpu[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_UDP, - VIRTCHNL_PROTO_HDR_GTPU_IP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_gtpu_eh[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_UDP, - VIRTCHNL_PROTO_HDR_GTPU_IP, - VIRTCHNL_PROTO_HDR_GTPU_EH, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_l2tpv3[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_L2TPV3, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv6_l2tpv3[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV6, - VIRTCHNL_PROTO_HDR_L2TPV3, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_esp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_ESP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv6_esp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV6, - VIRTCHNL_PROTO_HDR_ESP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_ah[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_AH, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv6_ah[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV6, - VIRTCHNL_PROTO_HDR_AH, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_nat_t_esp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_UDP, - VIRTCHNL_PROTO_HDR_ESP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv6_nat_t_esp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV6, - VIRTCHNL_PROTO_HDR_UDP, - VIRTCHNL_PROTO_HDR_ESP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv4_pfcp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV4, - VIRTCHNL_PROTO_HDR_UDP, - VIRTCHNL_PROTO_HDR_PFCP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -static enum virtchnl_proto_hdr_type vc_pattern_ipv6_pfcp[] = { - VIRTCHNL_PROTO_HDR_ETH, - VIRTCHNL_PROTO_HDR_IPV6, - VIRTCHNL_PROTO_HDR_UDP, - VIRTCHNL_PROTO_HDR_PFCP, - VIRTCHNL_PROTO_HDR_NONE, -}; - -struct virtchnl_fdir_pattern_match_item { - enum virtchnl_proto_hdr_type *list; - u64 input_set; - u64 *meta; -}; - -static const struct virtchnl_fdir_pattern_match_item vc_fdir_pattern_os[] = { - {vc_pattern_ipv4, 0, NULL}, - {vc_pattern_ipv4_tcp, 0, NULL}, - {vc_pattern_ipv4_udp, 0, NULL}, - {vc_pattern_ipv4_sctp, 0, NULL}, - {vc_pattern_ipv6, 0, NULL}, - {vc_pattern_ipv6_tcp, 0, NULL}, - {vc_pattern_ipv6_udp, 0, NULL}, - {vc_pattern_ipv6_sctp, 0, NULL}, -}; - -static const struct virtchnl_fdir_pattern_match_item vc_fdir_pattern_comms[] = { - {vc_pattern_ipv4, 0, NULL}, - {vc_pattern_ipv4_tcp, 0, NULL}, - {vc_pattern_ipv4_udp, 0, NULL}, - {vc_pattern_ipv4_sctp, 0, NULL}, - {vc_pattern_ipv6, 0, NULL}, - {vc_pattern_ipv6_tcp, 0, NULL}, - {vc_pattern_ipv6_udp, 0, NULL}, - {vc_pattern_ipv6_sctp, 0, NULL}, - {vc_pattern_ether, 0, NULL}, - {vc_pattern_ipv4_gtpu, 0, NULL}, - {vc_pattern_ipv4_gtpu_eh, 0, NULL}, - {vc_pattern_ipv4_l2tpv3, 0, NULL}, - {vc_pattern_ipv6_l2tpv3, 0, NULL}, - {vc_pattern_ipv4_esp, 0, NULL}, - {vc_pattern_ipv6_esp, 0, NULL}, - {vc_pattern_ipv4_ah, 0, NULL}, - {vc_pattern_ipv6_ah, 0, NULL}, - {vc_pattern_ipv4_nat_t_esp, 0, NULL}, - {vc_pattern_ipv6_nat_t_esp, 0, NULL}, - {vc_pattern_ipv4_pfcp, 0, NULL}, - {vc_pattern_ipv6_pfcp, 0, NULL}, -}; - struct virtchnl_fdir_inset_map { enum virtchnl_proto_hdr_field field; enum ice_flow_field fld; @@ -751,7 +560,6 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, struct ice_flow_seg_info *old_seg; struct ice_flow_prof *prof = NULL; struct ice_fd_hw_prof *vf_prof; - enum ice_status status; struct device *dev; struct ice_pf *pf; struct ice_hw *hw; @@ -794,29 +602,26 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, prof_id = ICE_FLOW_PROF_FD(vf_vsi->vsi_num, flow, tun ? ICE_FLTR_PTYPE_MAX : 0); - status = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg, - tun + 1, &prof); - ret = ice_status_to_errno(status); + ret = ice_flow_add_prof(hw, ICE_BLK_FD, ICE_FLOW_RX, prof_id, seg, + tun + 1, &prof); if (ret) { dev_dbg(dev, "Could not add VSI flow 0x%x for VF %d\n", flow, vf->vf_id); goto err_exit; } - status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx, - vf_vsi->idx, ICE_FLOW_PRIO_NORMAL, - seg, &entry1_h); - ret = ice_status_to_errno(status); + ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx, + vf_vsi->idx, ICE_FLOW_PRIO_NORMAL, + seg, &entry1_h); if (ret) { dev_dbg(dev, "Could not add flow 0x%x VSI entry for VF %d\n", flow, vf->vf_id); goto err_prof; } - status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx, - ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL, - seg, &entry2_h); - ret = ice_status_to_errno(status); + ret = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id, vf_vsi->idx, + ctrl_vsi->idx, ICE_FLOW_PRIO_NORMAL, + seg, &entry2_h); if (ret) { dev_dbg(dev, "Could not add flow 0x%x Ctrl VSI entry for VF %d\n", @@ -911,83 +716,6 @@ err_exit: } /** - * ice_vc_fdir_match_pattern - * @fltr: virtual channel add cmd buffer - * @type: virtual channel protocol filter header type - * - * Matching the header type by comparing fltr and type's value. - * - * Return: true on success, and false on error. - */ -static bool -ice_vc_fdir_match_pattern(struct virtchnl_fdir_add *fltr, - enum virtchnl_proto_hdr_type *type) -{ - struct virtchnl_proto_hdrs *proto = &fltr->rule_cfg.proto_hdrs; - int i = 0; - - while ((i < proto->count) && - (*type == proto->proto_hdr[i].type) && - (*type != VIRTCHNL_PROTO_HDR_NONE)) { - type++; - i++; - } - - return ((i == proto->count) && (*type == VIRTCHNL_PROTO_HDR_NONE)); -} - -/** - * ice_vc_fdir_get_pattern - get while list pattern - * @vf: pointer to the VF info - * @len: filter list length - * - * Return: pointer to allowed filter list - */ -static const struct virtchnl_fdir_pattern_match_item * -ice_vc_fdir_get_pattern(struct ice_vf *vf, int *len) -{ - const struct virtchnl_fdir_pattern_match_item *item; - struct ice_pf *pf = vf->pf; - struct ice_hw *hw; - - hw = &pf->hw; - if (!strncmp(hw->active_pkg_name, "ICE COMMS Package", - sizeof(hw->active_pkg_name))) { - item = vc_fdir_pattern_comms; - *len = ARRAY_SIZE(vc_fdir_pattern_comms); - } else { - item = vc_fdir_pattern_os; - *len = ARRAY_SIZE(vc_fdir_pattern_os); - } - - return item; -} - -/** - * ice_vc_fdir_search_pattern - * @vf: pointer to the VF info - * @fltr: virtual channel add cmd buffer - * - * Search for matched pattern from supported pattern list - * - * Return: 0 on success, and other on error. - */ -static int -ice_vc_fdir_search_pattern(struct ice_vf *vf, struct virtchnl_fdir_add *fltr) -{ - const struct virtchnl_fdir_pattern_match_item *pattern; - int len, i; - - pattern = ice_vc_fdir_get_pattern(vf, &len); - - for (i = 0; i < len; i++) - if (ice_vc_fdir_match_pattern(fltr, pattern[i].list)) - return 0; - - return -EINVAL; -} - -/** * ice_vc_fdir_parse_pattern * @vf: pointer to the VF info * @fltr: virtual channel add cmd buffer @@ -1299,11 +1027,11 @@ static int ice_vc_validate_fdir_fltr(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, struct virtchnl_fdir_fltr_conf *conf) { + struct virtchnl_proto_hdrs *proto = &fltr->rule_cfg.proto_hdrs; int ret; - ret = ice_vc_fdir_search_pattern(vf, fltr); - if (ret) - return ret; + if (!ice_vc_validate_pattern(vf, proto)) + return -EINVAL; ret = ice_vc_fdir_parse_pattern(vf, fltr, conf); if (ret) @@ -1467,7 +1195,6 @@ static int ice_vc_fdir_write_fltr(struct ice_vf *vf, struct ice_fdir_fltr *input = &conf->input; struct ice_vsi *vsi, *ctrl_vsi; struct ice_fltr_desc desc; - enum ice_status status; struct device *dev; struct ice_pf *pf; struct ice_hw *hw; @@ -1497,8 +1224,7 @@ static int ice_vc_fdir_write_fltr(struct ice_vf *vf, return -ENOMEM; ice_fdir_get_prgm_desc(hw, input, &desc, add); - status = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); - ret = ice_status_to_errno(status); + ret = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); if (ret) { dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n", vf->vf_id, input->flow_type); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 217ff5e9a6f1..61b2db3342ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -9,6 +9,7 @@ #include "ice_flow.h" #include "ice_eswitch.h" #include "ice_virtchnl_allowlist.h" +#include "ice_flex_pipe.h" #define FIELD_SELECTOR(proto_hdr_field) \ BIT((proto_hdr_field) & PROTO_HDR_FIELD_MASK) @@ -18,18 +19,7 @@ struct ice_vc_hdr_match_type { u32 ice_hdr; /* ice headers (ICE_FLOW_SEG_HDR_XXX) */ }; -static const struct ice_vc_hdr_match_type ice_vc_hdr_list_os[] = { - {VIRTCHNL_PROTO_HDR_NONE, ICE_FLOW_SEG_HDR_NONE}, - {VIRTCHNL_PROTO_HDR_IPV4, ICE_FLOW_SEG_HDR_IPV4 | - ICE_FLOW_SEG_HDR_IPV_OTHER}, - {VIRTCHNL_PROTO_HDR_IPV6, ICE_FLOW_SEG_HDR_IPV6 | - ICE_FLOW_SEG_HDR_IPV_OTHER}, - {VIRTCHNL_PROTO_HDR_TCP, ICE_FLOW_SEG_HDR_TCP}, - {VIRTCHNL_PROTO_HDR_UDP, ICE_FLOW_SEG_HDR_UDP}, - {VIRTCHNL_PROTO_HDR_SCTP, ICE_FLOW_SEG_HDR_SCTP}, -}; - -static const struct ice_vc_hdr_match_type ice_vc_hdr_list_comms[] = { +static const struct ice_vc_hdr_match_type ice_vc_hdr_list[] = { {VIRTCHNL_PROTO_HDR_NONE, ICE_FLOW_SEG_HDR_NONE}, {VIRTCHNL_PROTO_HDR_ETH, ICE_FLOW_SEG_HDR_ETH}, {VIRTCHNL_PROTO_HDR_S_VLAN, ICE_FLOW_SEG_HDR_VLAN}, @@ -67,83 +57,7 @@ struct ice_vc_hash_field_match_type { }; static const struct -ice_vc_hash_field_match_type ice_vc_hash_field_list_os[] = { - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), - ICE_FLOW_HASH_IPV4}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), - ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), - ICE_FLOW_HASH_IPV6}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) | - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA) | - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), - ICE_FLOW_HASH_IPV6 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), - BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, - {VIRTCHNL_PROTO_HDR_TCP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)}, - {VIRTCHNL_PROTO_HDR_TCP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)}, - {VIRTCHNL_PROTO_HDR_TCP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), - ICE_FLOW_HASH_TCP_PORT}, - {VIRTCHNL_PROTO_HDR_UDP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)}, - {VIRTCHNL_PROTO_HDR_UDP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT)}, - {VIRTCHNL_PROTO_HDR_UDP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), - ICE_FLOW_HASH_UDP_PORT}, - {VIRTCHNL_PROTO_HDR_SCTP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)}, - {VIRTCHNL_PROTO_HDR_SCTP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), - BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)}, - {VIRTCHNL_PROTO_HDR_SCTP, - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) | - FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), - ICE_FLOW_HASH_SCTP_PORT}, -}; - -static const struct -ice_vc_hash_field_match_type ice_vc_hash_field_list_comms[] = { +ice_vc_hash_field_match_type ice_vc_hash_field_list[] = { {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_SRC), BIT_ULL(ICE_FLOW_FIELD_IDX_ETH_SA)}, {VIRTCHNL_PROTO_HDR_ETH, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_ETH_DST), @@ -289,37 +203,6 @@ static int ice_check_vf_init(struct ice_pf *pf, struct ice_vf *vf) } /** - * ice_err_to_virt_err - translate errors for VF return code - * @ice_err: error return code - */ -static enum virtchnl_status_code ice_err_to_virt_err(enum ice_status ice_err) -{ - switch (ice_err) { - case ICE_SUCCESS: - return VIRTCHNL_STATUS_SUCCESS; - case ICE_ERR_BAD_PTR: - case ICE_ERR_INVAL_SIZE: - case ICE_ERR_DEVICE_NOT_SUPPORTED: - case ICE_ERR_PARAM: - case ICE_ERR_CFG: - return VIRTCHNL_STATUS_ERR_PARAM; - case ICE_ERR_NO_MEMORY: - return VIRTCHNL_STATUS_ERR_NO_MEMORY; - case ICE_ERR_NOT_READY: - case ICE_ERR_RESET_FAILED: - case ICE_ERR_FW_API_VER: - case ICE_ERR_AQ_ERROR: - case ICE_ERR_AQ_TIMEOUT: - case ICE_ERR_AQ_FULL: - case ICE_ERR_AQ_NO_WORK: - case ICE_ERR_AQ_EMPTY: - return VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; - default: - return VIRTCHNL_STATUS_ERR_NOT_SUPPORTED; - } -} - -/** * ice_vc_vf_broadcast - Broadcast a message to all VFs on PF * @pf: pointer to the PF structure * @v_opcode: operation code @@ -770,8 +653,7 @@ static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 pvid_info, bool enable) struct ice_hw *hw = &vsi->back->hw; struct ice_aqc_vsi_props *info; struct ice_vsi_ctx *ctxt; - enum ice_status status; - int ret = 0; + int ret; ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); if (!ctxt) @@ -794,12 +676,10 @@ static int ice_vsi_manage_pvid(struct ice_vsi *vsi, u16 pvid_info, bool enable) info->valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID | ICE_AQ_VSI_PROP_SW_VALID); - status = ice_update_vsi(hw, vsi->idx, ctxt, NULL); - if (status) { - dev_info(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); - ret = -EIO; + ret = ice_update_vsi(hw, vsi->idx, ctxt, NULL); + if (ret) { + dev_info(ice_hw_to_dev(hw), "update VSI for port VLAN failed, err %d aq_err %s\n", + ret, ice_aq_str(hw->adminq.sq_last_status)); goto out; } @@ -968,8 +848,8 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) { struct device *dev = ice_pf_to_dev(vf->pf); struct ice_vsi *vsi = ice_get_vf_vsi(vf); - enum ice_status status; u8 broadcast[ETH_ALEN]; + int status; if (ice_is_eswitch_mode_switchdev(vf->pf)) return 0; @@ -977,9 +857,9 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) eth_broadcast_addr(broadcast); status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); if (status) { - dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %s\n", - vf->vf_id, ice_stat_str(status)); - return ice_status_to_errno(status); + dev_err(dev, "failed to add broadcast MAC filter for VF %u, error %d\n", + vf->vf_id, status); + return status; } vf->num_mac++; @@ -988,10 +868,10 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) status = ice_fltr_add_mac(vsi, vf->hw_lan_addr.addr, ICE_FWD_TO_VSI); if (status) { - dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %s\n", + dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n", &vf->hw_lan_addr.addr[0], vf->vf_id, - ice_stat_str(status)); - return ice_status_to_errno(status); + status); + return status; } vf->num_mac++; @@ -1341,45 +1221,50 @@ static void ice_clear_vf_reset_trigger(struct ice_vf *vf) ice_flush(hw); } -/** - * ice_vf_set_vsi_promisc - set given VF VSI to given promiscuous mode(s) - * @vf: pointer to the VF info - * @vsi: the VSI being configured - * @promisc_m: mask of promiscuous config bits - * @rm_promisc: promisc flag request from the VF to remove or add filter - * - * This function configures VF VSI promiscuous mode, based on the VF requests, - * for Unicast, Multicast and VLAN - */ -static enum ice_status -ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m, - bool rm_promisc) +static int +ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) { - struct ice_pf *pf = vf->pf; - enum ice_status status = 0; - struct ice_hw *hw; + struct ice_hw *hw = &vsi->back->hw; + int status; - hw = &pf->hw; - if (vsi->num_vlan) { - status = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_m, - rm_promisc); - } else if (vf->port_vlan_info) { - if (rm_promisc) - status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m, - vf->port_vlan_info); - else - status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m, - vf->port_vlan_info); - } else { - if (rm_promisc) - status = ice_clear_vsi_promisc(hw, vsi->idx, promisc_m, - 0); - else - status = ice_set_vsi_promisc(hw, vsi->idx, promisc_m, - 0); + if (vf->port_vlan_info) + status = ice_fltr_set_vsi_promisc(hw, vsi->idx, promisc_m, + vf->port_vlan_info & VLAN_VID_MASK); + else if (vsi->num_vlan > 1) + status = ice_fltr_set_vlan_vsi_promisc(hw, vsi, promisc_m); + else + status = ice_fltr_set_vsi_promisc(hw, vsi->idx, promisc_m, 0); + + if (status && status != -EEXIST) { + dev_err(ice_pf_to_dev(vsi->back), "enable Tx/Rx filter promiscuous mode on VF-%u failed, error: %d\n", + vf->vf_id, status); + return status; } - return status; + return 0; +} + +static int +ice_vf_clear_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m) +{ + struct ice_hw *hw = &vsi->back->hw; + int status; + + if (vf->port_vlan_info) + status = ice_fltr_clear_vsi_promisc(hw, vsi->idx, promisc_m, + vf->port_vlan_info & VLAN_VID_MASK); + else if (vsi->num_vlan > 1) + status = ice_fltr_clear_vlan_vsi_promisc(hw, vsi, promisc_m); + else + status = ice_fltr_clear_vsi_promisc(hw, vsi->idx, promisc_m, 0); + + if (status && status != -ENOENT) { + dev_err(ice_pf_to_dev(vsi->back), "disable Tx/Rx filter promiscuous mode on VF-%u failed, error: %d\n", + vf->vf_id, status); + return status; + } + + return 0; } static void ice_vf_clear_counters(struct ice_vf *vf) @@ -1415,8 +1300,8 @@ static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf) static void ice_vf_rebuild_aggregator_node_cfg(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; - enum ice_status status; struct device *dev; + int status; if (!vsi->agg_node) return; @@ -1617,6 +1502,7 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_vc_set_default_allowlist(vf); ice_vf_fdir_exit(vf); + ice_vf_fdir_init(vf); /* clean VF control VSI when resetting VFs since it should be * setup only when VF creates its first FDIR rule. */ @@ -1742,11 +1628,12 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) else promisc_m = ICE_UCAST_PROMISC_BITS; - if (ice_vf_set_vsi_promisc(vf, vsi, promisc_m, true)) + if (ice_vf_clear_vsi_promisc(vf, vsi, promisc_m)) dev_err(dev, "disabling promiscuous mode failed\n"); } ice_vf_fdir_exit(vf); + ice_vf_fdir_init(vf); /* clean VF control VSI when resetting VF since it should be setup * only when VF creates its first FDIR rule. */ @@ -1844,7 +1731,6 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) { struct ice_pf *pf = vf->pf; u8 broadcast[ETH_ALEN]; - enum ice_status status; struct ice_vsi *vsi; struct device *dev; int err; @@ -1864,11 +1750,10 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) } eth_broadcast_addr(broadcast); - status = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); - if (status) { - dev_err(dev, "Failed to add broadcast MAC filter for VF %d, status %s\n", - vf->vf_id, ice_stat_str(status)); - err = ice_status_to_errno(status); + err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); + if (err) { + dev_err(dev, "Failed to add broadcast MAC filter for VF %d, error %d\n", + vf->vf_id, err); goto release_vsi; } @@ -2021,6 +1906,10 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) if (ret) goto err_unroll_sriov; + /* rearm global interrupts */ + if (test_and_clear_bit(ICE_OICR_INTR_DIS, pf->state)) + ice_irq_dynamic_ena(hw, NULL, NULL); + return 0; err_unroll_sriov: @@ -2110,7 +1999,6 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) { struct ice_pf *pf = pci_get_drvdata(pdev); struct device *dev = ice_pf_to_dev(pf); - enum ice_status status; int err; err = ice_check_sriov_allowed(pf); @@ -2130,9 +2018,9 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) return -EBUSY; } - status = ice_mbx_init_snapshot(&pf->hw, num_vfs); - if (status) - return ice_status_to_errno(status); + err = ice_mbx_init_snapshot(&pf->hw, num_vfs); + if (err) + return err; err = ice_pci_sriov_ena(pf, num_vfs); if (err) { @@ -2266,9 +2154,9 @@ int ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, enum virtchnl_status_code v_retval, u8 *msg, u16 msglen) { - enum ice_status aq_ret; struct device *dev; struct ice_pf *pf; + int aq_ret; if (!vf) return -EINVAL; @@ -2300,8 +2188,8 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, msg, msglen, NULL); if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) { - dev_info(dev, "Unable to send the message to VF %d ret %s aq_err %s\n", - vf->vf_id, ice_stat_str(aq_ret), + dev_info(dev, "Unable to send the message to VF %d ret %d aq_err %s\n", + vf->vf_id, aq_ret, ice_aq_str(pf->hw.mailboxq.sq_last_status)); return -EIO; } @@ -2550,6 +2438,100 @@ static bool ice_vc_isvalid_ring_len(u16 ring_len) } /** + * ice_vc_validate_pattern + * @vf: pointer to the VF info + * @proto: virtchnl protocol headers + * + * validate the pattern is supported or not. + * + * Return: true on success, false on error. + */ +bool +ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto) +{ + bool is_ipv4 = false; + bool is_ipv6 = false; + bool is_udp = false; + u16 ptype = -1; + int i = 0; + + while (i < proto->count && + proto->proto_hdr[i].type != VIRTCHNL_PROTO_HDR_NONE) { + switch (proto->proto_hdr[i].type) { + case VIRTCHNL_PROTO_HDR_ETH: + ptype = ICE_PTYPE_MAC_PAY; + break; + case VIRTCHNL_PROTO_HDR_IPV4: + ptype = ICE_PTYPE_IPV4_PAY; + is_ipv4 = true; + break; + case VIRTCHNL_PROTO_HDR_IPV6: + ptype = ICE_PTYPE_IPV6_PAY; + is_ipv6 = true; + break; + case VIRTCHNL_PROTO_HDR_UDP: + if (is_ipv4) + ptype = ICE_PTYPE_IPV4_UDP_PAY; + else if (is_ipv6) + ptype = ICE_PTYPE_IPV6_UDP_PAY; + is_udp = true; + break; + case VIRTCHNL_PROTO_HDR_TCP: + if (is_ipv4) + ptype = ICE_PTYPE_IPV4_TCP_PAY; + else if (is_ipv6) + ptype = ICE_PTYPE_IPV6_TCP_PAY; + break; + case VIRTCHNL_PROTO_HDR_SCTP: + if (is_ipv4) + ptype = ICE_PTYPE_IPV4_SCTP_PAY; + else if (is_ipv6) + ptype = ICE_PTYPE_IPV6_SCTP_PAY; + break; + case VIRTCHNL_PROTO_HDR_GTPU_IP: + case VIRTCHNL_PROTO_HDR_GTPU_EH: + if (is_ipv4) + ptype = ICE_MAC_IPV4_GTPU; + else if (is_ipv6) + ptype = ICE_MAC_IPV6_GTPU; + goto out; + case VIRTCHNL_PROTO_HDR_L2TPV3: + if (is_ipv4) + ptype = ICE_MAC_IPV4_L2TPV3; + else if (is_ipv6) + ptype = ICE_MAC_IPV6_L2TPV3; + goto out; + case VIRTCHNL_PROTO_HDR_ESP: + if (is_ipv4) + ptype = is_udp ? ICE_MAC_IPV4_NAT_T_ESP : + ICE_MAC_IPV4_ESP; + else if (is_ipv6) + ptype = is_udp ? ICE_MAC_IPV6_NAT_T_ESP : + ICE_MAC_IPV6_ESP; + goto out; + case VIRTCHNL_PROTO_HDR_AH: + if (is_ipv4) + ptype = ICE_MAC_IPV4_AH; + else if (is_ipv6) + ptype = ICE_MAC_IPV6_AH; + goto out; + case VIRTCHNL_PROTO_HDR_PFCP: + if (is_ipv4) + ptype = ICE_MAC_IPV4_PFCP_SESSION; + else if (is_ipv6) + ptype = ICE_MAC_IPV6_PFCP_SESSION; + goto out; + default: + break; + } + i++; + } + +out: + return ice_hw_ptype_ena(&vf->pf->hw, ptype); +} + +/** * ice_vc_parse_rss_cfg - parses hash fields and headers from * a specific virtchnl RSS cfg * @hw: pointer to the hardware @@ -2572,18 +2554,10 @@ ice_vc_parse_rss_cfg(struct ice_hw *hw, struct virtchnl_rss_cfg *rss_cfg, const struct ice_vc_hdr_match_type *hdr_list; int i, hf_list_len, hdr_list_len; - if (!strncmp(hw->active_pkg_name, "ICE COMMS Package", - sizeof(hw->active_pkg_name))) { - hf_list = ice_vc_hash_field_list_comms; - hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list_comms); - hdr_list = ice_vc_hdr_list_comms; - hdr_list_len = ARRAY_SIZE(ice_vc_hdr_list_comms); - } else { - hf_list = ice_vc_hash_field_list_os; - hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list_os); - hdr_list = ice_vc_hdr_list_os; - hdr_list_len = ARRAY_SIZE(ice_vc_hdr_list_os); - } + hf_list = ice_vc_hash_field_list; + hf_list_len = ARRAY_SIZE(ice_vc_hash_field_list); + hdr_list = ice_vc_hdr_list; + hdr_list_len = ARRAY_SIZE(ice_vc_hdr_list); for (i = 0; i < rss_cfg->proto_hdrs.count; i++) { struct virtchnl_proto_hdr *proto_hdr = @@ -2685,10 +2659,15 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) goto error_param; } + if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_R_ASYMMETRIC) { struct ice_vsi_ctx *ctx; - enum ice_status status; u8 lut_type, hash_type; + int status; lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_XOR : @@ -2717,9 +2696,8 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) status = ice_update_vsi(hw, vsi->idx, ctx, NULL); if (status) { - dev_err(dev, "update VSI for RSS failed, err %s aq_err %s\n", - ice_stat_str(status), - ice_aq_str(hw->adminq.sq_last_status)); + dev_err(dev, "update VSI for RSS failed, err %d aq_err %s\n", + status, ice_aq_str(hw->adminq.sq_last_status)); v_ret = VIRTCHNL_STATUS_ERR_PARAM; } else { vsi->info.q_opt_rss = ctx->info.q_opt_rss; @@ -2744,19 +2722,18 @@ static int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) vsi->vsi_num, v_ret); } } else { - enum ice_status status; + int status; status = ice_rem_rss_cfg(hw, vsi->idx, hash_flds, addl_hdrs); - /* We just ignore ICE_ERR_DOES_NOT_EXIST, because - * if two configurations share the same profile remove - * one of them actually removes both, since the - * profile is deleted. + /* We just ignore -ENOENT, because if two configurations + * share the same profile remove one of them actually + * removes both, since the profile is deleted. */ - if (status && status != ICE_ERR_DOES_NOT_EXIST) { + if (status && status != -ENOENT) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, "ice_rem_rss_cfg failed for VF ID:%d, error:%s\n", - vf->vf_id, ice_stat_str(status)); + dev_err(dev, "ice_rem_rss_cfg failed for VF ID:%d, error:%d\n", + vf->vf_id, status); } } } @@ -2914,7 +2891,6 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) struct ice_pf *pf = np->vsi->back; struct ice_vsi_ctx *ctx; struct ice_vsi *vf_vsi; - enum ice_status status; struct device *dev; struct ice_vf *vf; int ret; @@ -2964,12 +2940,10 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S)); } - status = ice_update_vsi(&pf->hw, vf_vsi->idx, ctx, NULL); - if (status) { - dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %s\n", - ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num, - ice_stat_str(status)); - ret = -EIO; + ret = ice_update_vsi(&pf->hw, vf_vsi->idx, ctx, NULL); + if (ret) { + dev_err(dev, "Failed to %sable spoofchk on VF %d VSI %d\n error %d\n", + ena ? "en" : "dis", vf->vf_id, vf_vsi->vsi_num, ret); goto out; } @@ -3015,10 +2989,10 @@ bool ice_is_any_vf_in_promisc(struct ice_pf *pf) static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) { enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - enum ice_status mcast_status = 0, ucast_status = 0; bool rm_promisc, alluni = false, allmulti = false; struct virtchnl_promisc_info *info = (struct virtchnl_promisc_info *)msg; + int mcast_err = 0, ucast_err = 0; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; struct device *dev; @@ -3100,24 +3074,21 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) ucast_m = ICE_UCAST_PROMISC_BITS; } - ucast_status = ice_vf_set_vsi_promisc(vf, vsi, ucast_m, - !alluni); - if (ucast_status) { - dev_err(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d failed\n", - alluni ? "en" : "dis", vf->vf_id); - v_ret = ice_err_to_virt_err(ucast_status); - } + if (alluni) + ucast_err = ice_vf_set_vsi_promisc(vf, vsi, ucast_m); + else + ucast_err = ice_vf_clear_vsi_promisc(vf, vsi, ucast_m); - mcast_status = ice_vf_set_vsi_promisc(vf, vsi, mcast_m, - !allmulti); - if (mcast_status) { - dev_err(dev, "%sable Tx/Rx filter promiscuous mode on VF-%d failed\n", - allmulti ? "en" : "dis", vf->vf_id); - v_ret = ice_err_to_virt_err(mcast_status); - } + if (allmulti) + mcast_err = ice_vf_set_vsi_promisc(vf, vsi, mcast_m); + else + mcast_err = ice_vf_clear_vsi_promisc(vf, vsi, mcast_m); + + if (ucast_err || mcast_err) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; } - if (!mcast_status) { + if (!mcast_err) { if (allmulti && !test_and_set_bit(ICE_VF_STATE_MC_PROMISC, vf->vf_states)) dev_info(dev, "VF %u successfully set multicast promiscuous mode\n", @@ -3127,7 +3098,7 @@ static int ice_vc_cfg_promiscuous_mode_msg(struct ice_vf *vf, u8 *msg) vf->vf_id); } - if (!ucast_status) { + if (!ucast_err) { if (alluni && !test_and_set_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states)) dev_info(dev, "VF %u successfully set unicast promiscuous mode\n", vf->vf_id); @@ -3807,8 +3778,7 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, { struct device *dev = ice_pf_to_dev(vf->pf); u8 *mac_addr = vc_ether_addr->addr; - enum ice_status status; - int ret = 0; + int ret; /* device MAC already added */ if (ether_addr_equal(mac_addr, vf->dev_lan_addr.addr)) @@ -3819,18 +3789,17 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, return -EPERM; } - status = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI); - if (status == ICE_ERR_ALREADY_EXISTS) { + ret = ice_fltr_add_mac(vsi, mac_addr, ICE_FWD_TO_VSI); + if (ret == -EEXIST) { dev_dbg(dev, "MAC %pM already exists for VF %d\n", mac_addr, vf->vf_id); /* don't return since we might need to update * the primary MAC in ice_vfhw_mac_add() below */ - ret = -EEXIST; - } else if (status) { - dev_err(dev, "Failed to add MAC %pM for VF %d\n, error %s\n", - mac_addr, vf->vf_id, ice_stat_str(status)); - return -EIO; + } else if (ret) { + dev_err(dev, "Failed to add MAC %pM for VF %d\n, error %d\n", + mac_addr, vf->vf_id, ret); + return ret; } else { vf->num_mac++; } @@ -3907,20 +3876,20 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, { struct device *dev = ice_pf_to_dev(vf->pf); u8 *mac_addr = vc_ether_addr->addr; - enum ice_status status; + int status; if (!ice_can_vf_change_mac(vf) && ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) return 0; status = ice_fltr_remove_mac(vsi, mac_addr, ICE_FWD_TO_VSI); - if (status == ICE_ERR_DOES_NOT_EXIST) { + if (status == -ENOENT) { dev_err(dev, "MAC %pM does not exist for VF %d\n", mac_addr, vf->vf_id); return -ENOENT; } else if (status) { - dev_err(dev, "Failed to delete MAC %pM for VF %d, error %s\n", - mac_addr, vf->vf_id, ice_stat_str(status)); + dev_err(dev, "Failed to delete MAC %pM for VF %d, error %d\n", + mac_addr, vf->vf_id, status); return -EIO; } @@ -5283,9 +5252,9 @@ ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, s16 vf_id = le16_to_cpu(event->desc.retval); struct device *dev = ice_pf_to_dev(pf); struct ice_mbx_data mbxdata; - enum ice_status status; bool malvf = false; struct ice_vf *vf; + int status; if (ice_validate_vf_id(pf, vf_id)) return false; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 7e28ecbbe7af..752487a1bdd6 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -203,6 +203,8 @@ void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event); void ice_print_vfs_mdd_events(struct ice_pf *pf); void ice_print_vf_rx_mdd_event(struct ice_vf *vf); +bool +ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto); struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf); int ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index dd208930fbe4..219aac3e62f5 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -7648,6 +7648,20 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, struct vf_mac_filter *entry = NULL; int ret = 0; + if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && + !vf_data->trusted) { + dev_warn(&pdev->dev, + "VF %d requested MAC filter but is administratively denied\n", + vf); + return -EINVAL; + } + if (!is_valid_ether_addr(addr)) { + dev_warn(&pdev->dev, + "VF %d attempted to set invalid MAC filter\n", + vf); + return -EINVAL; + } + switch (info) { case E1000_VF_MAC_FILTER_CLR: /* remove all unicast MAC filters related to the current VF */ @@ -7661,20 +7675,6 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, } break; case E1000_VF_MAC_FILTER_ADD: - if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && - !vf_data->trusted) { - dev_warn(&pdev->dev, - "VF %d requested MAC filter but is administratively denied\n", - vf); - return -EINVAL; - } - if (!is_valid_ether_addr(addr)) { - dev_warn(&pdev->dev, - "VF %d attempted to set invalid MAC filter\n", - vf); - return -EINVAL; - } - /* try to find empty slot in the list */ list_for_each(pos, &adapter->vf_macs.l) { entry = list_entry(pos, struct vf_mac_filter, l); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 0011b15e678c..0ac4cc5eaa2d 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1015,10 +1015,6 @@ static int igb_ptp_set_timestamp_mode(struct igb_adapter *adapter, bool is_l2 = false; u32 regval; - /* reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: tsync_tx_ctl = 0; diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 74ccd622251a..4d988da68394 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2859,6 +2859,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_hw_init: + netif_napi_del(&adapter->rx_ring->napi); kfree(adapter->tx_ring); kfree(adapter->rx_ring); err_sw_init: diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index b2ef9fde97b3..b6807e16eea9 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -636,7 +636,7 @@ s32 igc_set_ltr_i225(struct igc_hw *hw, bool link) ltrv = rd32(IGC_LTRMAXV); if (ltr_max != (ltrv & IGC_LTRMAXV_LTRV_MASK)) { ltrv = IGC_LTRMAXV_LSNP_REQ | ltr_max | - (scale_min << IGC_LTRMAXV_SCALE_SHIFT); + (scale_max << IGC_LTRMAXV_SCALE_SHIFT); wr32(IGC_LTRMAXV, ltrv); } } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 30568e3544cd..71813fa8f928 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -560,10 +560,6 @@ static void igc_ptp_enable_tx_timestamp(struct igc_adapter *adapter) static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter, struct hwtstamp_config *config) { - /* reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: igc_ptp_disable_tx_timestamp(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0f9f022260d7..45e2ec4d264d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5531,6 +5531,10 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) if (!speed && hw->mac.ops.get_link_capabilities) { ret = hw->mac.ops.get_link_capabilities(hw, &speed, &autoneg); + /* remove NBASE-T speeds from default autonegotiation + * to accommodate broken network switches in the field + * which cannot cope with advertised NBASE-T speeds + */ speed &= ~(IXGBE_LINK_SPEED_5GB_FULL | IXGBE_LINK_SPEED_2_5GB_FULL); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 23ddfd79fc8b..336426a67ac1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -992,10 +992,6 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, bool is_l2 = false; u32 regval; - /* reserved for future extensions */ - if (config->flags) - return -EINVAL; - switch (config->tx_type) { case HWTSTAMP_TX_OFF: tsync_tx_ctl = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 9724ffb16518..e4b50c7781ff 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -3405,6 +3405,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) /* flush pending Tx transactions */ ixgbe_clear_tx_pending(hw); + /* set MDIO speed before talking to the PHY in case it's the 1st time */ + ixgbe_set_mdio_speed(hw); + /* PHY ops must be identified and initialized prior to reset */ status = hw->phy.ops.init(hw); if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index ce810fc3c1a2..e4c328f61188 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -526,6 +526,7 @@ struct mvneta_port { unsigned int tx_csum_limit; struct phylink *phylink; struct phylink_config phylink_config; + struct phylink_pcs phylink_pcs; struct phy *comphy; struct mvneta_bm *bm_priv; @@ -3846,9 +3847,14 @@ static int mvneta_set_mac_addr(struct net_device *dev, void *addr) return 0; } -static void mvneta_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state) +static struct mvneta_port *mvneta_pcs_to_port(struct phylink_pcs *pcs) +{ + return container_of(pcs, struct mvneta_port, phylink_pcs); +} + +static int mvneta_pcs_validate(struct phylink_pcs *pcs, + unsigned long *supported, + const struct phylink_link_state *state) { /* We only support QSGMII, SGMII, 802.3z and RGMII modes. * When in 802.3z mode, we must have AN enabled: @@ -3856,19 +3862,16 @@ static void mvneta_validate(struct phylink_config *config, * When <PortType> = 1 (1000BASE-X) this field must be set to 1." */ if (phy_interface_mode_is_8023z(state->interface) && - !phylink_test(state->advertising, Autoneg)) { - linkmode_zero(supported); - return; - } + !phylink_test(state->advertising, Autoneg)) + return -EINVAL; - phylink_generic_validate(config, supported, state); + return 0; } -static void mvneta_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) +static void mvneta_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) { - struct net_device *ndev = to_net_dev(config->dev); - struct mvneta_port *pp = netdev_priv(ndev); + struct mvneta_port *pp = mvneta_pcs_to_port(pcs); u32 gmac_stat; gmac_stat = mvreg_read(pp, MVNETA_GMAC_STATUS); @@ -3886,17 +3889,71 @@ static void mvneta_mac_pcs_get_state(struct phylink_config *config, state->link = !!(gmac_stat & MVNETA_GMAC_LINK_UP); state->duplex = !!(gmac_stat & MVNETA_GMAC_FULL_DUPLEX); - state->pause = 0; if (gmac_stat & MVNETA_GMAC_RX_FLOW_CTRL_ENABLE) state->pause |= MLO_PAUSE_RX; if (gmac_stat & MVNETA_GMAC_TX_FLOW_CTRL_ENABLE) state->pause |= MLO_PAUSE_TX; } -static void mvneta_mac_an_restart(struct phylink_config *config) +static int mvneta_pcs_config(struct phylink_pcs *pcs, + unsigned int mode, phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) { - struct net_device *ndev = to_net_dev(config->dev); - struct mvneta_port *pp = netdev_priv(ndev); + struct mvneta_port *pp = mvneta_pcs_to_port(pcs); + u32 mask, val, an, old_an, changed; + + mask = MVNETA_GMAC_INBAND_AN_ENABLE | + MVNETA_GMAC_INBAND_RESTART_AN | + MVNETA_GMAC_AN_SPEED_EN | + MVNETA_GMAC_AN_FLOW_CTRL_EN | + MVNETA_GMAC_AN_DUPLEX_EN; + + if (phylink_autoneg_inband(mode)) { + mask |= MVNETA_GMAC_CONFIG_MII_SPEED | + MVNETA_GMAC_CONFIG_GMII_SPEED | + MVNETA_GMAC_CONFIG_FULL_DUPLEX; + val = MVNETA_GMAC_INBAND_AN_ENABLE; + + if (interface == PHY_INTERFACE_MODE_SGMII) { + /* SGMII mode receives the speed and duplex from PHY */ + val |= MVNETA_GMAC_AN_SPEED_EN | + MVNETA_GMAC_AN_DUPLEX_EN; + } else { + /* 802.3z mode has fixed speed and duplex */ + val |= MVNETA_GMAC_CONFIG_GMII_SPEED | + MVNETA_GMAC_CONFIG_FULL_DUPLEX; + + /* The FLOW_CTRL_EN bit selects either the hardware + * automatically or the CONFIG_FLOW_CTRL manually + * controls the GMAC pause mode. + */ + if (permit_pause_to_mac) + val |= MVNETA_GMAC_AN_FLOW_CTRL_EN; + + /* Update the advertisement bits */ + mask |= MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL; + if (phylink_test(advertising, Pause)) + val |= MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL; + } + } else { + /* Phy or fixed speed - disable in-band AN modes */ + val = 0; + } + + old_an = an = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG); + an = (an & ~mask) | val; + changed = old_an ^ an; + if (changed) + mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, an); + + /* We are only interested in the advertisement bits changing */ + return !!(changed & MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL); +} + +static void mvneta_pcs_an_restart(struct phylink_pcs *pcs) +{ + struct mvneta_port *pp = mvneta_pcs_to_port(pcs); u32 gmac_an = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG); mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, @@ -3905,6 +3962,47 @@ static void mvneta_mac_an_restart(struct phylink_config *config) gmac_an & ~MVNETA_GMAC_INBAND_RESTART_AN); } +static const struct phylink_pcs_ops mvneta_phylink_pcs_ops = { + .pcs_validate = mvneta_pcs_validate, + .pcs_get_state = mvneta_pcs_get_state, + .pcs_config = mvneta_pcs_config, + .pcs_an_restart = mvneta_pcs_an_restart, +}; + +static int mvneta_mac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct net_device *ndev = to_net_dev(config->dev); + struct mvneta_port *pp = netdev_priv(ndev); + u32 val; + + if (pp->phy_interface != interface || + phylink_autoneg_inband(mode)) { + /* Force the link down when changing the interface or if in + * in-band mode. According to Armada 370 documentation, we + * can only change the port mode and in-band enable when the + * link is down. + */ + val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG); + val &= ~MVNETA_GMAC_FORCE_LINK_PASS; + val |= MVNETA_GMAC_FORCE_LINK_DOWN; + mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val); + } + + if (pp->phy_interface != interface) + WARN_ON(phy_power_off(pp->comphy)); + + /* Enable the 1ms clock */ + if (phylink_autoneg_inband(mode)) { + unsigned long rate = clk_get_rate(pp->clk); + + mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, + MVNETA_GMAC_1MS_CLOCK_ENABLE | (rate / 1000)); + } + + return 0; +} + static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { @@ -3913,20 +4011,11 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, u32 new_ctrl0, gmac_ctrl0 = mvreg_read(pp, MVNETA_GMAC_CTRL_0); u32 new_ctrl2, gmac_ctrl2 = mvreg_read(pp, MVNETA_GMAC_CTRL_2); u32 new_ctrl4, gmac_ctrl4 = mvreg_read(pp, MVNETA_GMAC_CTRL_4); - u32 new_clk, gmac_clk = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER); - u32 new_an, gmac_an = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG); new_ctrl0 = gmac_ctrl0 & ~MVNETA_GMAC0_PORT_1000BASE_X; new_ctrl2 = gmac_ctrl2 & ~(MVNETA_GMAC2_INBAND_AN_ENABLE | MVNETA_GMAC2_PORT_RESET); new_ctrl4 = gmac_ctrl4 & ~(MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE); - new_clk = gmac_clk & ~MVNETA_GMAC_1MS_CLOCK_ENABLE; - new_an = gmac_an & ~(MVNETA_GMAC_INBAND_AN_ENABLE | - MVNETA_GMAC_INBAND_RESTART_AN | - MVNETA_GMAC_AN_SPEED_EN | - MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL | - MVNETA_GMAC_AN_FLOW_CTRL_EN | - MVNETA_GMAC_AN_DUPLEX_EN); /* Even though it might look weird, when we're configured in * SGMII or QSGMII mode, the RGMII bit needs to be set. @@ -3938,9 +4027,6 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, phy_interface_mode_is_8023z(state->interface)) new_ctrl2 |= MVNETA_GMAC2_PCS_ENABLE; - if (phylink_test(state->advertising, Pause)) - new_an |= MVNETA_GMAC_ADVERT_SYM_FLOW_CTRL; - if (!phylink_autoneg_inband(mode)) { /* Phy or fixed speed - nothing to do, leave the * configured speed, duplex and flow control as-is. @@ -3948,70 +4034,23 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { /* SGMII mode receives the state from the PHY */ new_ctrl2 |= MVNETA_GMAC2_INBAND_AN_ENABLE; - new_clk = MVNETA_GMAC_1MS_CLOCK_ENABLE; - new_an = (new_an & ~(MVNETA_GMAC_FORCE_LINK_DOWN | - MVNETA_GMAC_FORCE_LINK_PASS | - MVNETA_GMAC_CONFIG_MII_SPEED | - MVNETA_GMAC_CONFIG_GMII_SPEED | - MVNETA_GMAC_CONFIG_FULL_DUPLEX)) | - MVNETA_GMAC_INBAND_AN_ENABLE | - MVNETA_GMAC_AN_SPEED_EN | - MVNETA_GMAC_AN_DUPLEX_EN; } else { /* 802.3z negotiation - only 1000base-X */ new_ctrl0 |= MVNETA_GMAC0_PORT_1000BASE_X; - new_clk = MVNETA_GMAC_1MS_CLOCK_ENABLE; - new_an = (new_an & ~(MVNETA_GMAC_FORCE_LINK_DOWN | - MVNETA_GMAC_FORCE_LINK_PASS | - MVNETA_GMAC_CONFIG_MII_SPEED)) | - MVNETA_GMAC_INBAND_AN_ENABLE | - MVNETA_GMAC_CONFIG_GMII_SPEED | - /* The MAC only supports FD mode */ - MVNETA_GMAC_CONFIG_FULL_DUPLEX; - - if (state->pause & MLO_PAUSE_AN && state->an_enabled) - new_an |= MVNETA_GMAC_AN_FLOW_CTRL_EN; } - /* Set the 1ms clock divisor */ - if (new_clk == MVNETA_GMAC_1MS_CLOCK_ENABLE) - new_clk |= clk_get_rate(pp->clk) / 1000; - - /* Armada 370 documentation says we can only change the port mode - * and in-band enable when the link is down, so force it down - * while making these changes. We also do this for GMAC_CTRL2 - */ - if ((new_ctrl0 ^ gmac_ctrl0) & MVNETA_GMAC0_PORT_1000BASE_X || - (new_ctrl2 ^ gmac_ctrl2) & MVNETA_GMAC2_INBAND_AN_ENABLE || - (new_an ^ gmac_an) & MVNETA_GMAC_INBAND_AN_ENABLE) { - mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, - (gmac_an & ~MVNETA_GMAC_FORCE_LINK_PASS) | - MVNETA_GMAC_FORCE_LINK_DOWN); - } - - /* When at 2.5G, the link partner can send frames with shortened * preambles. */ if (state->interface == PHY_INTERFACE_MODE_2500BASEX) new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE; - if (pp->phy_interface != state->interface) { - if (pp->comphy) - WARN_ON(phy_power_off(pp->comphy)); - WARN_ON(mvneta_config_interface(pp, state->interface)); - } - if (new_ctrl0 != gmac_ctrl0) mvreg_write(pp, MVNETA_GMAC_CTRL_0, new_ctrl0); if (new_ctrl2 != gmac_ctrl2) mvreg_write(pp, MVNETA_GMAC_CTRL_2, new_ctrl2); if (new_ctrl4 != gmac_ctrl4) mvreg_write(pp, MVNETA_GMAC_CTRL_4, new_ctrl4); - if (new_clk != gmac_clk) - mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, new_clk); - if (new_an != gmac_an) - mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, new_an); if (gmac_ctrl2 & MVNETA_GMAC2_PORT_RESET) { while ((mvreg_read(pp, MVNETA_GMAC_CTRL_2) & @@ -4020,6 +4059,36 @@ static void mvneta_mac_config(struct phylink_config *config, unsigned int mode, } } +static int mvneta_mac_finish(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct net_device *ndev = to_net_dev(config->dev); + struct mvneta_port *pp = netdev_priv(ndev); + u32 val, clk; + + /* Disable 1ms clock if not in in-band mode */ + if (!phylink_autoneg_inband(mode)) { + clk = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER); + clk &= ~MVNETA_GMAC_1MS_CLOCK_ENABLE; + mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, clk); + } + + if (pp->phy_interface != interface) + /* Enable the Serdes PHY */ + WARN_ON(mvneta_config_interface(pp, interface)); + + /* Allow the link to come up if in in-band mode, otherwise the + * link is forced via mac_link_down()/mac_link_up() + */ + if (phylink_autoneg_inband(mode)) { + val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG); + val &= ~MVNETA_GMAC_FORCE_LINK_DOWN; + mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val); + } + + return 0; +} + static void mvneta_set_eee(struct mvneta_port *pp, bool enable) { u32 lpi_ctl1; @@ -4106,10 +4175,10 @@ static void mvneta_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops mvneta_phylink_ops = { - .validate = mvneta_validate, - .mac_pcs_get_state = mvneta_mac_pcs_get_state, - .mac_an_restart = mvneta_mac_an_restart, + .validate = phylink_generic_validate, + .mac_prepare = mvneta_mac_prepare, .mac_config = mvneta_mac_config, + .mac_finish = mvneta_mac_finish, .mac_link_down = mvneta_mac_link_down, .mac_link_up = mvneta_mac_link_up, }; @@ -5349,6 +5418,9 @@ static int mvneta_probe(struct platform_device *pdev) goto err_clk; } + pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops; + phylink_set_pcs(phylink, &pp->phylink_pcs); + /* Alloc per-cpu port structure */ pp->ports = alloc_percpu(struct mvneta_pcpu_port); if (!pp->ports) { diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index cf8acabb90ac..ad73a488fc5f 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -1239,7 +1239,8 @@ struct mvpp2_port { phy_interface_t phy_interface; struct phylink *phylink; struct phylink_config phylink_config; - struct phylink_pcs phylink_pcs; + struct phylink_pcs pcs_gmac; + struct phylink_pcs pcs_xlg; struct phy *comphy; struct mvpp2_bm_pool *pool_long; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 252e215a14f1..339ae274021e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -2963,11 +2963,11 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, mvpp2_rxq_status_update(port, rxq->id, 0, rxq->size); if (priv->percpu_pools) { - err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->id, 0); + err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->logic_rxq, 0); if (err < 0) goto err_free_dma; - err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->id, 0); + err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->logic_rxq, 0); if (err < 0) goto err_unregister_rxq_short; @@ -5142,9 +5142,6 @@ static int mvpp2_set_ts_config(struct mvpp2_port *port, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) - return -EINVAL; - if (config.tx_type != HWTSTAMP_TX_OFF && config.tx_type != HWTSTAMP_TX_ON) return -ERANGE; @@ -6118,15 +6115,20 @@ static struct mvpp2_port *mvpp2_phylink_to_port(struct phylink_config *config) return container_of(config, struct mvpp2_port, phylink_config); } -static struct mvpp2_port *mvpp2_pcs_to_port(struct phylink_pcs *pcs) +static struct mvpp2_port *mvpp2_pcs_xlg_to_port(struct phylink_pcs *pcs) +{ + return container_of(pcs, struct mvpp2_port, pcs_xlg); +} + +static struct mvpp2_port *mvpp2_pcs_gmac_to_port(struct phylink_pcs *pcs) { - return container_of(pcs, struct mvpp2_port, phylink_pcs); + return container_of(pcs, struct mvpp2_port, pcs_gmac); } static void mvpp2_xlg_pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state) { - struct mvpp2_port *port = mvpp2_pcs_to_port(pcs); + struct mvpp2_port *port = mvpp2_pcs_xlg_to_port(pcs); u32 val; if (port->phy_interface == PHY_INTERFACE_MODE_5GBASER) @@ -6161,10 +6163,25 @@ static const struct phylink_pcs_ops mvpp2_phylink_xlg_pcs_ops = { .pcs_config = mvpp2_xlg_pcs_config, }; +static int mvpp2_gmac_pcs_validate(struct phylink_pcs *pcs, + unsigned long *supported, + const struct phylink_link_state *state) +{ + /* When in 802.3z mode, we must have AN enabled: + * Bit 2 Field InBandAnEn In-band Auto-Negotiation enable. ... + * When <PortType> = 1 (1000BASE-X) this field must be set to 1. + */ + if (phy_interface_mode_is_8023z(state->interface) && + !phylink_test(state->advertising, Autoneg)) + return -EINVAL; + + return 0; +} + static void mvpp2_gmac_pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state) { - struct mvpp2_port *port = mvpp2_pcs_to_port(pcs); + struct mvpp2_port *port = mvpp2_pcs_gmac_to_port(pcs); u32 val; val = readl(port->base + MVPP2_GMAC_STATUS0); @@ -6201,7 +6218,7 @@ static int mvpp2_gmac_pcs_config(struct phylink_pcs *pcs, unsigned int mode, const unsigned long *advertising, bool permit_pause_to_mac) { - struct mvpp2_port *port = mvpp2_pcs_to_port(pcs); + struct mvpp2_port *port = mvpp2_pcs_gmac_to_port(pcs); u32 mask, val, an, old_an, changed; mask = MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS | @@ -6255,7 +6272,7 @@ static int mvpp2_gmac_pcs_config(struct phylink_pcs *pcs, unsigned int mode, static void mvpp2_gmac_pcs_an_restart(struct phylink_pcs *pcs) { - struct mvpp2_port *port = mvpp2_pcs_to_port(pcs); + struct mvpp2_port *port = mvpp2_pcs_gmac_to_port(pcs); u32 val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); writel(val | MVPP2_GMAC_IN_BAND_RESTART_AN, @@ -6265,30 +6282,12 @@ static void mvpp2_gmac_pcs_an_restart(struct phylink_pcs *pcs) } static const struct phylink_pcs_ops mvpp2_phylink_gmac_pcs_ops = { + .pcs_validate = mvpp2_gmac_pcs_validate, .pcs_get_state = mvpp2_gmac_pcs_get_state, .pcs_config = mvpp2_gmac_pcs_config, .pcs_an_restart = mvpp2_gmac_pcs_an_restart, }; -static void mvpp2_phylink_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state) -{ - /* When in 802.3z mode, we must have AN enabled: - * Bit 2 Field InBandAnEn In-band Auto-Negotiation enable. ... - * When <PortType> = 1 (1000BASE-X) this field must be set to 1. - */ - if (phy_interface_mode_is_8023z(state->interface) && - !phylink_test(state->advertising, Autoneg)) - goto empty_set; - - phylink_generic_validate(config, supported, state); - return; - -empty_set: - linkmode_zero(supported); -} - static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, const struct phylink_link_state *state) { @@ -6368,8 +6367,23 @@ static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG); } -static int mvpp2__mac_prepare(struct phylink_config *config, unsigned int mode, - phy_interface_t interface) +static struct phylink_pcs *mvpp2_select_pcs(struct phylink_config *config, + phy_interface_t interface) +{ + struct mvpp2_port *port = mvpp2_phylink_to_port(config); + + /* Select the appropriate PCS operations depending on the + * configured interface mode. We will only switch to a mode + * that the validate() checks have already passed. + */ + if (mvpp2_is_xlg(interface)) + return &port->pcs_xlg; + else + return &port->pcs_gmac; +} + +static int mvpp2_mac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) { struct mvpp2_port *port = mvpp2_phylink_to_port(config); @@ -6418,31 +6432,9 @@ static int mvpp2__mac_prepare(struct phylink_config *config, unsigned int mode, } } - /* Select the appropriate PCS operations depending on the - * configured interface mode. We will only switch to a mode - * that the validate() checks have already passed. - */ - if (mvpp2_is_xlg(interface)) - port->phylink_pcs.ops = &mvpp2_phylink_xlg_pcs_ops; - else - port->phylink_pcs.ops = &mvpp2_phylink_gmac_pcs_ops; - return 0; } -static int mvpp2_mac_prepare(struct phylink_config *config, unsigned int mode, - phy_interface_t interface) -{ - struct mvpp2_port *port = mvpp2_phylink_to_port(config); - int ret; - - ret = mvpp2__mac_prepare(config, mode, interface); - if (ret == 0) - phylink_set_pcs(port->phylink, &port->phylink_pcs); - - return ret; -} - static void mvpp2_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { @@ -6613,7 +6605,8 @@ static void mvpp2_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops mvpp2_phylink_ops = { - .validate = mvpp2_phylink_validate, + .validate = phylink_generic_validate, + .mac_select_pcs = mvpp2_select_pcs, .mac_prepare = mvpp2_mac_prepare, .mac_config = mvpp2_mac_config, .mac_finish = mvpp2_mac_finish, @@ -6631,12 +6624,15 @@ static void mvpp2_acpi_start(struct mvpp2_port *port) struct phylink_link_state state = { .interface = port->phy_interface, }; - mvpp2__mac_prepare(&port->phylink_config, MLO_AN_INBAND, - port->phy_interface); + struct phylink_pcs *pcs; + + pcs = mvpp2_select_pcs(&port->phylink_config, port->phy_interface); + + mvpp2_mac_prepare(&port->phylink_config, MLO_AN_INBAND, + port->phy_interface); mvpp2_mac_config(&port->phylink_config, MLO_AN_INBAND, &state); - port->phylink_pcs.ops->pcs_config(&port->phylink_pcs, MLO_AN_INBAND, - port->phy_interface, - state.advertising, false); + pcs->ops->pcs_config(pcs, MLO_AN_INBAND, port->phy_interface, + state.advertising, false); mvpp2_mac_finish(&port->phylink_config, MLO_AN_INBAND, port->phy_interface); mvpp2_mac_link_up(&port->phylink_config, NULL, @@ -6944,6 +6940,9 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->phylink_config.supported_interfaces); } + port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops; + port->pcs_xlg.ops = &mvpp2_phylink_xlg_pcs_ops; + phylink = phylink_create(&port->phylink_config, port_fwnode, phy_mode, &mvpp2_phylink_ops); if (IS_ERR(phylink)) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 1333edf1c361..6080ebd9bd94 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -2002,10 +2002,6 @@ int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: otx2_config_hw_tx_tstamp(pfvf, false); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c index 0ef68fdd1f26..61c20907315f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c @@ -5,6 +5,8 @@ * */ +#include <linux/module.h> + #include "otx2_common.h" #include "otx2_ptp.h" diff --git a/drivers/net/ethernet/marvell/prestera/prestera_acl.c b/drivers/net/ethernet/marvell/prestera/prestera_acl.c index fc7f2fedafd7..f0d9f592173b 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_acl.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_acl.c @@ -88,8 +88,8 @@ prestera_acl_ruleset_create(struct prestera_acl *acl, struct prestera_flow_block *block) { struct prestera_acl_ruleset *ruleset; + u32 uid = 0; int err; - u32 uid; ruleset = kzalloc(sizeof(*ruleset), GFP_KERNEL); if (!ruleset) @@ -125,6 +125,12 @@ err_rhashtable_init: return ERR_PTR(err); } +void prestera_acl_ruleset_keymask_set(struct prestera_acl_ruleset *ruleset, + void *keymask) +{ + ruleset->keymask = kmemdup(keymask, ACL_KEYMASK_SIZE, GFP_KERNEL); +} + int prestera_acl_ruleset_offload(struct prestera_acl_ruleset *ruleset) { u32 vtcam_id; @@ -556,6 +562,49 @@ err_kzalloc: return NULL; } +static int __prestera_acl_vtcam_id_try_fit(struct prestera_acl *acl, u8 lookup, + void *keymask, u32 *vtcam_id) +{ + struct prestera_acl_vtcam *vtcam; + int i; + + list_for_each_entry(vtcam, &acl->vtcam_list, list) { + if (lookup != vtcam->lookup) + continue; + + if (!keymask && !vtcam->is_keymask_set) + goto vtcam_found; + + if (!(keymask && vtcam->is_keymask_set)) + continue; + + /* try to fit with vtcam keymask */ + for (i = 0; i < __PRESTERA_ACL_RULE_MATCH_TYPE_MAX; i++) { + __be32 __keymask = ((__be32 *)keymask)[i]; + + if (!__keymask) + /* vtcam keymask in not interested */ + continue; + + if (__keymask & ~vtcam->keymask[i]) + /* keymask does not fit the vtcam keymask */ + break; + } + + if (i == __PRESTERA_ACL_RULE_MATCH_TYPE_MAX) + /* keymask fits vtcam keymask, return it */ + goto vtcam_found; + } + + /* nothing is found */ + return -ENOENT; + +vtcam_found: + refcount_inc(&vtcam->refcount); + *vtcam_id = vtcam->id; + return 0; +} + int prestera_acl_vtcam_id_get(struct prestera_acl *acl, u8 lookup, void *keymask, u32 *vtcam_id) { @@ -592,7 +641,14 @@ int prestera_acl_vtcam_id_get(struct prestera_acl *acl, u8 lookup, PRESTERA_HW_VTCAM_DIR_INGRESS); if (err) { kfree(vtcam); - return err; + + /* cannot create new, try to fit into existing vtcam */ + if (__prestera_acl_vtcam_id_try_fit(acl, lookup, + keymask, &new_vtcam_id)) + return err; + + *vtcam_id = new_vtcam_id; + return 0; } vtcam->id = new_vtcam_id; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_acl.h b/drivers/net/ethernet/marvell/prestera/prestera_acl.h index 4e6006b4531f..40f6c1d961fa 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_acl.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_acl.h @@ -151,6 +151,8 @@ prestera_acl_ruleset_get(struct prestera_acl *acl, struct prestera_acl_ruleset * prestera_acl_ruleset_lookup(struct prestera_acl *acl, struct prestera_flow_block *block); +void prestera_acl_ruleset_keymask_set(struct prestera_acl_ruleset *ruleset, + void *keymask); bool prestera_acl_ruleset_is_offload(struct prestera_acl_ruleset *ruleset); int prestera_acl_ruleset_offload(struct prestera_acl_ruleset *ruleset); void prestera_acl_ruleset_put(struct prestera_acl_ruleset *ruleset); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flow.c b/drivers/net/ethernet/marvell/prestera/prestera_flow.c index 94a1feb3d9e1..d849f046ece7 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flow.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_flow.c @@ -40,6 +40,11 @@ static int prestera_flow_block_flower_cb(struct prestera_flow_block *block, return 0; case FLOW_CLS_STATS: return prestera_flower_stats(block, f); + case FLOW_CLS_TMPLT_CREATE: + return prestera_flower_tmplt_create(block, f); + case FLOW_CLS_TMPLT_DESTROY: + prestera_flower_tmplt_destroy(block, f); + return 0; default: return -EOPNOTSUPP; } @@ -64,6 +69,8 @@ static void prestera_flow_block_destroy(void *cb_priv) { struct prestera_flow_block *block = cb_priv; + prestera_flower_template_cleanup(block); + WARN_ON(!list_empty(&block->binding_list)); kfree(block); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flow.h b/drivers/net/ethernet/marvell/prestera/prestera_flow.h index 5863acf06005..1ea5b745bf72 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flow.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_flow.h @@ -8,6 +8,7 @@ struct prestera_port; struct prestera_switch; +struct prestera_flower_template; struct prestera_flow_block_binding { struct list_head list; @@ -18,10 +19,11 @@ struct prestera_flow_block_binding { struct prestera_flow_block { struct list_head binding_list; struct prestera_switch *sw; - unsigned int rule_count; struct net *net; struct prestera_acl_ruleset *ruleset_zero; struct flow_block_cb *block_cb; + struct prestera_flower_template *tmplt; + unsigned int rule_count; }; int prestera_flow_block_setup(struct prestera_port *port, diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.c b/drivers/net/ethernet/marvell/prestera/prestera_flower.c index c1dc4e49b07f..19c1417fd05f 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flower.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.c @@ -6,6 +6,21 @@ #include "prestera_flow.h" #include "prestera_flower.h" +struct prestera_flower_template { + struct prestera_acl_ruleset *ruleset; +}; + +void prestera_flower_template_cleanup(struct prestera_flow_block *block) +{ + if (block->tmplt) { + /* put the reference to the ruleset kept in create */ + prestera_acl_ruleset_put(block->tmplt->ruleset); + kfree(block->tmplt); + block->tmplt = NULL; + return; + } +} + static int prestera_flower_parse_actions(struct prestera_flow_block *block, struct prestera_acl_rule *rule, struct flow_action *flow_action, @@ -310,6 +325,61 @@ void prestera_flower_destroy(struct prestera_flow_block *block, } +int prestera_flower_tmplt_create(struct prestera_flow_block *block, + struct flow_cls_offload *f) +{ + struct prestera_flower_template *template; + struct prestera_acl_ruleset *ruleset; + struct prestera_acl_rule rule; + int err; + + memset(&rule, 0, sizeof(rule)); + err = prestera_flower_parse(block, &rule, f); + if (err) + return err; + + template = kmalloc(sizeof(*template), GFP_KERNEL); + if (!template) { + err = -ENOMEM; + goto err_malloc; + } + + prestera_acl_rule_keymask_pcl_id_set(&rule, 0); + ruleset = prestera_acl_ruleset_get(block->sw->acl, block); + if (IS_ERR_OR_NULL(ruleset)) { + err = -EINVAL; + goto err_ruleset_get; + } + + /* preserve keymask/template to this ruleset */ + prestera_acl_ruleset_keymask_set(ruleset, rule.re_key.match.mask); + + /* skip error, as it is not possible to reject template operation, + * so, keep the reference to the ruleset for rules to be added + * to that ruleset later. In case of offload fail, the ruleset + * will be offloaded again during adding a new rule. Also, + * unlikly possble that ruleset is already offloaded at this staage. + */ + prestera_acl_ruleset_offload(ruleset); + + /* keep the reference to the ruleset */ + template->ruleset = ruleset; + block->tmplt = template; + return 0; + +err_ruleset_get: + kfree(template); +err_malloc: + NL_SET_ERR_MSG_MOD(f->common.extack, "Create chain template failed"); + return err; +} + +void prestera_flower_tmplt_destroy(struct prestera_flow_block *block, + struct flow_cls_offload *f) +{ + prestera_flower_template_cleanup(block); +} + int prestera_flower_stats(struct prestera_flow_block *block, struct flow_cls_offload *f) { diff --git a/drivers/net/ethernet/marvell/prestera/prestera_flower.h b/drivers/net/ethernet/marvell/prestera/prestera_flower.h index c6182473efa5..dc3aa4280e9f 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_flower.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_flower.h @@ -15,5 +15,10 @@ void prestera_flower_destroy(struct prestera_flow_block *block, struct flow_cls_offload *f); int prestera_flower_stats(struct prestera_flow_block *block, struct flow_cls_offload *f); +int prestera_flower_tmplt_create(struct prestera_flow_block *block, + struct flow_cls_offload *f); +void prestera_flower_tmplt_destroy(struct prestera_flow_block *block, + struct flow_cls_offload *f); +void prestera_flower_template_cleanup(struct prestera_flow_block *block); #endif /* _PRESTERA_FLOWER_H_ */ diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig index c357c193378e..86d356b4388d 100644 --- a/drivers/net/ethernet/mediatek/Kconfig +++ b/drivers/net/ethernet/mediatek/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config NET_VENDOR_MEDIATEK bool "MediaTek devices" - depends on ARCH_MEDIATEK || SOC_MT7621 || SOC_MT7620 + depends on ARCH_MEDIATEK || SOC_MT7621 || SOC_MT7620 || COMPILE_TEST help If you have a Mediatek SoC with ethernet, say Y. @@ -10,6 +10,7 @@ if NET_VENDOR_MEDIATEK config NET_MEDIATEK_SOC tristate "MediaTek SoC Gigabit Ethernet support" depends on NET_DSA || !NET_DSA + select PINCTRL select PHYLINK select DIMLIB help diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index de4152e2e3e4..a068cf5c970f 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2923,6 +2923,10 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) mac->phylink_config.dev = ð->netdev[id]->dev; mac->phylink_config.type = PHYLINK_NETDEV; + /* This driver makes use of state->speed/state->duplex in + * mac_config + */ + mac->phylink_config.legacy_pre_march2020 = true; mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index f1c10f2bda78..ad1e4caf48bf 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2427,10 +2427,6 @@ static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - /* device doesn't support time stamping */ if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)) return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index e63bb9ceb9c0..e592e0955c71 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -46,6 +46,15 @@ mlx5_core-$(CONFIG_MLX5_CLS_ACT) += en_tc.o en/rep/tc.o en/rep/neigh.o \ en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \ en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o \ en/tc/post_act.o en/tc/int_port.o + +mlx5_core-$(CONFIG_MLX5_CLS_ACT) += en/tc/act/act.o en/tc/act/drop.o en/tc/act/trap.o \ + en/tc/act/accept.o en/tc/act/mark.o en/tc/act/goto.o \ + en/tc/act/tun.o en/tc/act/csum.o en/tc/act/pedit.o \ + en/tc/act/vlan.o en/tc/act/vlan_mangle.o en/tc/act/mpls.o \ + en/tc/act/mirred.o en/tc/act/mirred_nic.o \ + en/tc/act/ct.o en/tc/act/sample.o en/tc/act/ptype.o \ + en/tc/act/redirect_ingress.o + mlx5_core-$(CONFIG_MLX5_TC_CT) += en/tc_ct.o mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += en/tc/sample.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c new file mode 100644 index 000000000000..b0de6b999675 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/accept.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_priv.h" + +static bool +tc_act_can_offload_accept(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + return true; +} + +static int +tc_act_parse_accept(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + attr->flags |= MLX5_ESW_ATTR_FLAG_ACCEPT; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_accept = { + .can_offload = tc_act_can_offload_accept, + .parse_action = tc_act_parse_accept, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c new file mode 100644 index 000000000000..e600924e30ea --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_priv.h" +#include "mlx5_core.h" + +/* Must be aligned with enum flow_action_id. */ +static struct mlx5e_tc_act *tc_acts_fdb[NUM_FLOW_ACTIONS] = { + &mlx5e_tc_act_accept, + &mlx5e_tc_act_drop, + &mlx5e_tc_act_trap, + &mlx5e_tc_act_goto, + &mlx5e_tc_act_mirred, + &mlx5e_tc_act_mirred, + &mlx5e_tc_act_redirect_ingress, + NULL, /* FLOW_ACTION_MIRRED_INGRESS, */ + &mlx5e_tc_act_vlan, + &mlx5e_tc_act_vlan, + &mlx5e_tc_act_vlan_mangle, + &mlx5e_tc_act_tun_encap, + &mlx5e_tc_act_tun_decap, + &mlx5e_tc_act_pedit, + &mlx5e_tc_act_pedit, + &mlx5e_tc_act_csum, + NULL, /* FLOW_ACTION_MARK, */ + &mlx5e_tc_act_ptype, + NULL, /* FLOW_ACTION_PRIORITY, */ + NULL, /* FLOW_ACTION_WAKE, */ + NULL, /* FLOW_ACTION_QUEUE, */ + &mlx5e_tc_act_sample, + NULL, /* FLOW_ACTION_POLICE, */ + &mlx5e_tc_act_ct, + NULL, /* FLOW_ACTION_CT_METADATA, */ + &mlx5e_tc_act_mpls_push, + &mlx5e_tc_act_mpls_pop, +}; + +/* Must be aligned with enum flow_action_id. */ +static struct mlx5e_tc_act *tc_acts_nic[NUM_FLOW_ACTIONS] = { + &mlx5e_tc_act_accept, + &mlx5e_tc_act_drop, + NULL, /* FLOW_ACTION_TRAP, */ + &mlx5e_tc_act_goto, + &mlx5e_tc_act_mirred_nic, + NULL, /* FLOW_ACTION_MIRRED, */ + NULL, /* FLOW_ACTION_REDIRECT_INGRESS, */ + NULL, /* FLOW_ACTION_MIRRED_INGRESS, */ + NULL, /* FLOW_ACTION_VLAN_PUSH, */ + NULL, /* FLOW_ACTION_VLAN_POP, */ + NULL, /* FLOW_ACTION_VLAN_MANGLE, */ + NULL, /* FLOW_ACTION_TUNNEL_ENCAP, */ + NULL, /* FLOW_ACTION_TUNNEL_DECAP, */ + &mlx5e_tc_act_pedit, + &mlx5e_tc_act_pedit, + &mlx5e_tc_act_csum, + &mlx5e_tc_act_mark, + NULL, /* FLOW_ACTION_PTYPE, */ + NULL, /* FLOW_ACTION_PRIORITY, */ + NULL, /* FLOW_ACTION_WAKE, */ + NULL, /* FLOW_ACTION_QUEUE, */ + NULL, /* FLOW_ACTION_SAMPLE, */ + NULL, /* FLOW_ACTION_POLICE, */ + &mlx5e_tc_act_ct, +}; + +/** + * mlx5e_tc_act_get() - Get an action parser for an action id. + * @act_id: Flow action id. + * @ns_type: flow namespace type. + */ +struct mlx5e_tc_act * +mlx5e_tc_act_get(enum flow_action_id act_id, + enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5e_tc_act **tc_acts; + + tc_acts = ns_type == MLX5_FLOW_NAMESPACE_FDB ? tc_acts_fdb : tc_acts_nic; + + return tc_acts[act_id]; +} + +/** + * mlx5e_tc_act_init_parse_state() - Init a new parse_state. + * @parse_state: Parsing state. + * @flow: mlx5e tc flow being handled. + * @flow_action: flow action to parse. + * @extack: to set an error msg. + * + * The same parse_state should be passed to action parsers + * for tracking the current parsing state. + */ +void +mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, + struct mlx5e_tc_flow *flow, + struct flow_action *flow_action, + struct netlink_ext_ack *extack) +{ + memset(parse_state, 0, sizeof(*parse_state)); + parse_state->flow = flow; + parse_state->num_actions = flow_action->num_entries; + parse_state->extack = extack; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h new file mode 100644 index 000000000000..26efa33de56f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_EN_TC_ACT_H__ +#define __MLX5_EN_TC_ACT_H__ + +#include <net/tc_act/tc_pedit.h> +#include <net/flow_offload.h> +#include <linux/netlink.h> +#include "eswitch.h" +#include "pedit.h" + +struct mlx5_flow_attr; + +struct mlx5e_tc_act_parse_state { + unsigned int num_actions; + struct mlx5e_tc_flow *flow; + struct netlink_ext_ack *extack; + bool encap; + bool decap; + bool mpls_push; + bool ptype_host; + const struct ip_tunnel_info *tun_info; + struct pedit_headers_action hdrs[__PEDIT_CMD_MAX]; + int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS]; + int if_count; + struct mlx5_tc_ct_priv *ct_priv; +}; + +struct mlx5e_tc_act { + bool (*can_offload)(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index); + + int (*parse_action)(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr); + + int (*post_parse)(struct mlx5e_tc_act_parse_state *parse_state, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr); +}; + +extern struct mlx5e_tc_act mlx5e_tc_act_drop; +extern struct mlx5e_tc_act mlx5e_tc_act_trap; +extern struct mlx5e_tc_act mlx5e_tc_act_accept; +extern struct mlx5e_tc_act mlx5e_tc_act_mark; +extern struct mlx5e_tc_act mlx5e_tc_act_goto; +extern struct mlx5e_tc_act mlx5e_tc_act_tun_encap; +extern struct mlx5e_tc_act mlx5e_tc_act_tun_decap; +extern struct mlx5e_tc_act mlx5e_tc_act_csum; +extern struct mlx5e_tc_act mlx5e_tc_act_pedit; +extern struct mlx5e_tc_act mlx5e_tc_act_vlan; +extern struct mlx5e_tc_act mlx5e_tc_act_vlan_mangle; +extern struct mlx5e_tc_act mlx5e_tc_act_mpls_push; +extern struct mlx5e_tc_act mlx5e_tc_act_mpls_pop; +extern struct mlx5e_tc_act mlx5e_tc_act_mirred; +extern struct mlx5e_tc_act mlx5e_tc_act_mirred_nic; +extern struct mlx5e_tc_act mlx5e_tc_act_ct; +extern struct mlx5e_tc_act mlx5e_tc_act_sample; +extern struct mlx5e_tc_act mlx5e_tc_act_ptype; +extern struct mlx5e_tc_act mlx5e_tc_act_redirect_ingress; + +struct mlx5e_tc_act * +mlx5e_tc_act_get(enum flow_action_id act_id, + enum mlx5_flow_namespace_type ns_type); + +void +mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state, + struct mlx5e_tc_flow *flow, + struct flow_action *flow_action, + struct netlink_ext_ack *extack); + +#endif /* __MLX5_EN_TC_ACT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c new file mode 100644 index 000000000000..29920ef0180a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/csum.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include <linux/tc_act/tc_csum.h> +#include "act.h" +#include "en/tc_priv.h" + +static bool +csum_offload_supported(struct mlx5e_priv *priv, + u32 action, + u32 update_flags, + struct netlink_ext_ack *extack) +{ + u32 prot_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR | TCA_CSUM_UPDATE_FLAG_TCP | + TCA_CSUM_UPDATE_FLAG_UDP; + + /* The HW recalcs checksums only if re-writing headers */ + if (!(action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)) { + NL_SET_ERR_MSG_MOD(extack, + "TC csum action is only offloaded with pedit"); + netdev_warn(priv->netdev, + "TC csum action is only offloaded with pedit\n"); + return false; + } + + if (update_flags & ~prot_flags) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload TC csum action for some header/s"); + netdev_warn(priv->netdev, + "can't offload TC csum action for some header/s - flags %#x\n", + update_flags); + return false; + } + + return true; +} + +static bool +tc_act_can_offload_csum(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct mlx5e_tc_flow *flow = parse_state->flow; + + return csum_offload_supported(flow->priv, flow->attr->action, + act->csum_flags, parse_state->extack); +} + +static int +tc_act_parse_csum(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_csum = { + .can_offload = tc_act_can_offload_csum, + .parse_action = tc_act_parse_csum, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c new file mode 100644 index 000000000000..06ec30cdb269 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_priv.h" +#include "en/tc_ct.h" + +static bool +tc_act_can_offload_ct(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct netlink_ext_ack *extack = parse_state->extack; + + if (flow_flag_test(parse_state->flow, SAMPLE)) { + NL_SET_ERR_MSG_MOD(extack, + "Sample action with connection tracking is not supported"); + return false; + } + + return true; +} + +static int +tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + int err; + + err = mlx5_tc_ct_parse_action(parse_state->ct_priv, attr, + &attr->parse_attr->mod_hdr_acts, + act, parse_state->extack); + if (err) + return err; + + flow_flag_set(parse_state->flow, CT); + + if (mlx5e_is_eswitch_flow(parse_state->flow)) + attr->esw_attr->split_count = attr->esw_attr->out_count; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_ct = { + .can_offload = tc_act_can_offload_ct, + .parse_action = tc_act_parse_ct, +}; + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c new file mode 100644 index 000000000000..2e29a23bed12 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/drop.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_priv.h" + +static bool +tc_act_can_offload_drop(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + return true; +} + +static int +tc_act_parse_drop(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_drop = { + .can_offload = tc_act_can_offload_drop, + .parse_action = tc_act_parse_drop, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c new file mode 100644 index 000000000000..f44515061228 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/goto.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_priv.h" +#include "eswitch.h" + +static int +validate_goto_chain(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, + const struct flow_action_entry *act, + struct netlink_ext_ack *extack) +{ + bool is_esw = mlx5e_is_eswitch_flow(flow); + bool ft_flow = mlx5e_is_ft_flow(flow); + u32 dest_chain = act->chain_index; + struct mlx5_fs_chains *chains; + struct mlx5_eswitch *esw; + u32 reformat_and_fwd; + u32 max_chain; + + esw = priv->mdev->priv.eswitch; + chains = is_esw ? esw_chains(esw) : mlx5e_nic_chains(priv); + max_chain = mlx5_chains_get_chain_range(chains); + reformat_and_fwd = is_esw ? + MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, reformat_and_fwd_to_table) : + MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, reformat_and_fwd_to_table); + + if (ft_flow) { + NL_SET_ERR_MSG_MOD(extack, "Goto action is not supported"); + return -EOPNOTSUPP; + } + + if (!mlx5_chains_backwards_supported(chains) && + dest_chain <= flow->attr->chain) { + NL_SET_ERR_MSG_MOD(extack, "Goto lower numbered chain isn't supported"); + return -EOPNOTSUPP; + } + + if (dest_chain > max_chain) { + NL_SET_ERR_MSG_MOD(extack, + "Requested destination chain is out of supported range"); + return -EOPNOTSUPP; + } + + if (flow->attr->action & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | + MLX5_FLOW_CONTEXT_ACTION_DECAP) && + !reformat_and_fwd) { + NL_SET_ERR_MSG_MOD(extack, + "Goto chain is not allowed if action has reformat or decap"); + return -EOPNOTSUPP; + } + + return 0; +} + +static bool +tc_act_can_offload_goto(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_tc_flow *flow = parse_state->flow; + + if (validate_goto_chain(flow->priv, flow, act, extack)) + return false; + + return true; +} + +static int +tc_act_parse_goto(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + attr->dest_chain = act->chain_index; + + return 0; +} + +static int +tc_act_post_parse_goto(struct mlx5e_tc_act_parse_state *parse_state, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_tc_flow *flow = parse_state->flow; + + if (!attr->dest_chain) + return 0; + + if (parse_state->decap) { + /* It can be supported if we'll create a mapping for + * the tunnel device only (without tunnel), and set + * this tunnel id with this decap flow. + * + * On restore (miss), we'll just set this saved tunnel + * device. + */ + + NL_SET_ERR_MSG_MOD(extack, "Decap with goto isn't supported"); + netdev_warn(priv->netdev, "Decap with goto isn't supported"); + return -EOPNOTSUPP; + } + + if (!mlx5e_is_eswitch_flow(flow) && parse_attr->mirred_ifindex[0]) { + NL_SET_ERR_MSG_MOD(extack, "Mirroring goto chain rules isn't supported"); + return -EOPNOTSUPP; + } + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_goto = { + .can_offload = tc_act_can_offload_goto, + .parse_action = tc_act_parse_goto, + .post_parse = tc_act_post_parse_goto, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c new file mode 100644 index 000000000000..d775c3d9edf3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mark.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en_tc.h" + +static bool +tc_act_can_offload_mark(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + if (act->mark & ~MLX5E_TC_FLOW_ID_MASK) { + NL_SET_ERR_MSG_MOD(parse_state->extack, "Bad flow mark, only 16 bit supported"); + return false; + } + + return true; +} + +static int +tc_act_parse_mark(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + attr->nic_attr->flow_tag = act->mark; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_mark = { + .can_offload = tc_act_can_offload_mark, + .parse_action = tc_act_parse_mark, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c new file mode 100644 index 000000000000..a0832b86016c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include <linux/if_macvlan.h> +#include <linux/if_vlan.h> +#include <net/bareudp.h> +#include <net/bonding.h> +#include "act.h" +#include "vlan.h" +#include "en/tc_tun_encap.h" +#include "en/tc_priv.h" +#include "en_rep.h" + +static bool +same_vf_reps(struct mlx5e_priv *priv, struct net_device *out_dev) +{ + return mlx5e_eswitch_vf_rep(priv->netdev) && + priv->netdev == out_dev; +} + +static int +verify_uplink_forwarding(struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr, + struct net_device *out_dev, + struct netlink_ext_ack *extack) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_rep_priv *rep_priv; + + /* Forwarding non encapsulated traffic between + * uplink ports is allowed only if + * termination_table_raw_traffic cap is set. + * + * Input vport was stored attr->in_rep. + * In LAG case, *priv* is the private data of + * uplink which may be not the input vport. + */ + rep_priv = mlx5e_rep_to_rep_priv(attr->esw_attr->in_rep); + + if (!(mlx5e_eswitch_uplink_rep(rep_priv->netdev) && + mlx5e_eswitch_uplink_rep(out_dev))) + return 0; + + if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, + termination_table_raw_traffic)) { + NL_SET_ERR_MSG_MOD(extack, + "devices are both uplink, can't offload forwarding"); + pr_err("devices %s %s are both uplink, can't offload forwarding\n", + priv->netdev->name, out_dev->name); + return -EOPNOTSUPP; + } else if (out_dev != rep_priv->netdev) { + NL_SET_ERR_MSG_MOD(extack, + "devices are not the same uplink, can't offload forwarding"); + pr_err("devices %s %s are both uplink but not the same, can't offload forwarding\n", + priv->netdev->name, out_dev->name); + return -EOPNOTSUPP; + } + return 0; +} + +static bool +is_duplicated_output_device(struct net_device *dev, + struct net_device *out_dev, + int *ifindexes, int if_count, + struct netlink_ext_ack *extack) +{ + int i; + + for (i = 0; i < if_count; i++) { + if (ifindexes[i] == out_dev->ifindex) { + NL_SET_ERR_MSG_MOD(extack, "can't duplicate output to same device"); + netdev_err(dev, "can't duplicate output to same device: %s\n", + out_dev->name); + return true; + } + } + + return false; +} + +static struct net_device * +get_fdb_out_dev(struct net_device *uplink_dev, struct net_device *out_dev) +{ + struct net_device *fdb_out_dev = out_dev; + struct net_device *uplink_upper; + + rcu_read_lock(); + uplink_upper = netdev_master_upper_dev_get_rcu(uplink_dev); + if (uplink_upper && netif_is_lag_master(uplink_upper) && + uplink_upper == out_dev) { + fdb_out_dev = uplink_dev; + } else if (netif_is_lag_master(out_dev)) { + fdb_out_dev = bond_option_active_slave_get_rcu(netdev_priv(out_dev)); + if (fdb_out_dev && + (!mlx5e_eswitch_rep(fdb_out_dev) || + !netdev_port_same_parent_id(fdb_out_dev, uplink_dev))) + fdb_out_dev = NULL; + } + rcu_read_unlock(); + return fdb_out_dev; +} + +static bool +tc_act_can_offload_mirred(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_tc_flow *flow = parse_state->flow; + struct mlx5e_tc_flow_parse_attr *parse_attr; + struct net_device *out_dev = act->dev; + struct mlx5e_priv *priv = flow->priv; + struct mlx5_esw_flow_attr *esw_attr; + + parse_attr = flow->attr->parse_attr; + esw_attr = flow->attr->esw_attr; + + if (!out_dev) { + /* out_dev is NULL when filters with + * non-existing mirred device are replayed to + * the driver. + */ + return false; + } + + if (parse_state->mpls_push && !netif_is_bareudp(out_dev)) { + NL_SET_ERR_MSG_MOD(extack, "mpls is supported only through a bareudp device"); + return false; + } + + if (mlx5e_is_ft_flow(flow) && out_dev == priv->netdev) { + /* Ignore forward to self rules generated + * by adding both mlx5 devs to the flow table + * block on a normal nft offload setup. + */ + return false; + } + + if (esw_attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) { + NL_SET_ERR_MSG_MOD(extack, + "can't support more output ports, can't offload forwarding"); + netdev_warn(priv->netdev, + "can't support more than %d output ports, can't offload forwarding\n", + esw_attr->out_count); + return false; + } + + if (parse_state->encap || + netdev_port_same_parent_id(priv->netdev, out_dev) || + netif_is_ovs_master(out_dev)) + return true; + + if (parse_attr->filter_dev != priv->netdev) { + /* All mlx5 devices are called to configure + * high level device filters. Therefore, the + * *attempt* to install a filter on invalid + * eswitch should not trigger an explicit error + */ + return false; + } + + NL_SET_ERR_MSG_MOD(extack, "devices are not on same switch HW, can't offload forwarding"); + netdev_warn(priv->netdev, + "devices %s %s not on same switch HW, can't offload forwarding\n", + netdev_name(priv->netdev), + out_dev->name); + + return false; +} + +static int +parse_mirred_encap(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5_flow_attr *attr) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + struct net_device *out_dev = act->dev; + + parse_attr->mirred_ifindex[esw_attr->out_count] = out_dev->ifindex; + parse_attr->tun_info[esw_attr->out_count] = + mlx5e_dup_tun_info(parse_state->tun_info); + + if (!parse_attr->tun_info[esw_attr->out_count]) + return -ENOMEM; + + parse_state->encap = false; + esw_attr->dests[esw_attr->out_count].flags |= MLX5_ESW_DEST_ENCAP; + esw_attr->out_count++; + /* attr->dests[].rep is resolved when we handle encap */ + + return 0; +} + +static int +parse_mirred(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct net_device *out_dev = act->dev; + struct net_device *uplink_dev; + struct mlx5e_priv *out_priv; + struct mlx5_eswitch *esw; + int *ifindexes; + int if_count; + int err; + + esw = priv->mdev->priv.eswitch; + uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); + ifindexes = parse_state->ifindexes; + if_count = parse_state->if_count; + + if (is_duplicated_output_device(priv->netdev, out_dev, ifindexes, if_count, extack)) + return -EOPNOTSUPP; + + parse_state->ifindexes[if_count] = out_dev->ifindex; + parse_state->if_count++; + + out_dev = get_fdb_out_dev(uplink_dev, out_dev); + if (!out_dev) + return -ENODEV; + + if (is_vlan_dev(out_dev)) { + err = mlx5e_tc_act_vlan_add_push_action(priv, attr, &out_dev, extack); + if (err) + return err; + } + + if (is_vlan_dev(parse_attr->filter_dev)) { + err = mlx5e_tc_act_vlan_add_pop_action(priv, attr, extack); + if (err) + return err; + } + + if (netif_is_macvlan(out_dev)) + out_dev = macvlan_dev_real_dev(out_dev); + + err = verify_uplink_forwarding(priv, attr, out_dev, extack); + if (err) + return err; + + if (!mlx5e_is_valid_eswitch_fwd_dev(priv, out_dev)) { + NL_SET_ERR_MSG_MOD(extack, + "devices are not on same switch HW, can't offload forwarding"); + return -EOPNOTSUPP; + } + + if (same_vf_reps(priv, out_dev)) { + NL_SET_ERR_MSG_MOD(extack, "can't forward from a VF to itself"); + return -EOPNOTSUPP; + } + + out_priv = netdev_priv(out_dev); + rpriv = out_priv->ppriv; + esw_attr->dests[esw_attr->out_count].rep = rpriv->rep; + esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev; + esw_attr->out_count++; + + return 0; +} + +static int +parse_mirred_ovs_master(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + struct net_device *out_dev = act->dev; + int err; + + err = mlx5e_set_fwd_to_int_port_actions(priv, attr, out_dev->ifindex, + MLX5E_TC_INT_PORT_EGRESS, + &attr->action, esw_attr->out_count); + if (err) + return err; + + esw_attr->out_count++; + return 0; +} + +static int +tc_act_parse_mirred(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct net_device *out_dev = act->dev; + int err = -EOPNOTSUPP; + + if (parse_state->encap) + err = parse_mirred_encap(parse_state, act, attr); + else if (netdev_port_same_parent_id(priv->netdev, out_dev)) + err = parse_mirred(parse_state, act, priv, attr); + else if (netif_is_ovs_master(out_dev)) + err = parse_mirred_ovs_master(parse_state, act, priv, attr); + + if (err) + return err; + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_mirred = { + .can_offload = tc_act_can_offload_mirred, + .parse_action = tc_act_parse_mirred, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c new file mode 100644 index 000000000000..2c74567b6d25 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred_nic.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_priv.h" + +static bool +tc_act_can_offload_mirred_nic(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_tc_flow *flow = parse_state->flow; + struct net_device *out_dev = act->dev; + struct mlx5e_priv *priv = flow->priv; + + if (act->id != FLOW_ACTION_REDIRECT) + return false; + + if (priv->netdev->netdev_ops != out_dev->netdev_ops || + !mlx5e_same_hw_devs(priv, netdev_priv(out_dev))) { + NL_SET_ERR_MSG_MOD(extack, + "devices are not on same switch HW, can't offload forwarding"); + netdev_warn(priv->netdev, + "devices %s %s not on same switch HW, can't offload forwarding\n", + netdev_name(priv->netdev), + out_dev->name); + return false; + } + + return true; +} + +static int +tc_act_parse_mirred_nic(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + attr->parse_attr->mirred_ifindex[0] = act->dev->ifindex; + flow_flag_set(parse_state->flow, HAIRPIN); + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_mirred_nic = { + .can_offload = tc_act_can_offload_mirred_nic, + .parse_action = tc_act_parse_mirred_nic, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c new file mode 100644 index 000000000000..784fc4f68b1e --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include <net/bareudp.h> +#include "act.h" +#include "en/tc_priv.h" + +static bool +tc_act_can_offload_mpls_push(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_priv *priv = parse_state->flow->priv; + + if (!MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, reformat_l2_to_l3_tunnel) || + act->mpls_push.proto != htons(ETH_P_MPLS_UC)) { + NL_SET_ERR_MSG_MOD(extack, "mpls push is supported only for mpls_uc protocol"); + return false; + } + + return true; +} + +static int +tc_act_parse_mpls_push(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + parse_state->mpls_push = true; + + return 0; +} + +static bool +tc_act_can_offload_mpls_pop(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_tc_flow *flow = parse_state->flow; + struct net_device *filter_dev; + + filter_dev = flow->attr->parse_attr->filter_dev; + + /* we only support mpls pop if it is the first action + * and the filter net device is bareudp. Subsequent + * actions can be pedit and the last can be mirred + * egress redirect. + */ + if (act_index) { + NL_SET_ERR_MSG_MOD(extack, "mpls pop supported only as first action"); + return false; + } + + if (!netif_is_bareudp(filter_dev)) { + NL_SET_ERR_MSG_MOD(extack, "mpls pop supported only on bareudp devices"); + return false; + } + + return true; +} + +static int +tc_act_parse_mpls_pop(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + attr->parse_attr->eth.h_proto = act->mpls_pop.proto; + attr->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_flag_set(parse_state->flow, L3_TO_L2_DECAP); + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_mpls_push = { + .can_offload = tc_act_can_offload_mpls_push, + .parse_action = tc_act_parse_mpls_push, +}; + +struct mlx5e_tc_act mlx5e_tc_act_mpls_pop = { + .can_offload = tc_act_can_offload_mpls_pop, + .parse_action = tc_act_parse_mpls_pop, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c new file mode 100644 index 000000000000..79addbbef087 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include <linux/if_vlan.h> +#include "act.h" +#include "pedit.h" +#include "en/tc_priv.h" +#include "en/mod_hdr.h" + +static int pedit_header_offsets[] = { + [FLOW_ACT_MANGLE_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth), + [FLOW_ACT_MANGLE_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4), + [FLOW_ACT_MANGLE_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6), + [FLOW_ACT_MANGLE_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp), + [FLOW_ACT_MANGLE_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp), +}; + +#define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype]) + +static int +set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset, + struct pedit_headers_action *hdrs, + struct netlink_ext_ack *extack) +{ + u32 *curr_pmask, *curr_pval; + + curr_pmask = (u32 *)(pedit_header(&hdrs->masks, hdr_type) + offset); + curr_pval = (u32 *)(pedit_header(&hdrs->vals, hdr_type) + offset); + + if (*curr_pmask & mask) { /* disallow acting twice on the same location */ + NL_SET_ERR_MSG_MOD(extack, + "curr_pmask and new mask same. Acting twice on same location"); + goto out_err; + } + + *curr_pmask |= mask; + *curr_pval |= (val & mask); + + return 0; + +out_err: + return -EOPNOTSUPP; +} + +static int +parse_pedit_to_modify_hdr(struct mlx5e_priv *priv, + const struct flow_action_entry *act, int namespace, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct pedit_headers_action *hdrs, + struct netlink_ext_ack *extack) +{ + u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1; + u8 htype = act->mangle.htype; + int err = -EOPNOTSUPP; + u32 mask, val, offset; + + if (htype == FLOW_ACT_MANGLE_UNSPEC) { + NL_SET_ERR_MSG_MOD(extack, "legacy pedit isn't offloaded"); + goto out_err; + } + + if (!mlx5e_mod_hdr_max_actions(priv->mdev, namespace)) { + NL_SET_ERR_MSG_MOD(extack, "The pedit offload action is not supported"); + goto out_err; + } + + mask = act->mangle.mask; + val = act->mangle.val; + offset = act->mangle.offset; + + err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd], extack); + if (err) + goto out_err; + + hdrs[cmd].pedits++; + + return 0; +out_err: + return err; +} + +static int +parse_pedit_to_reformat(const struct flow_action_entry *act, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct netlink_ext_ack *extack) +{ + u32 mask, val, offset; + u32 *p; + + if (act->id != FLOW_ACTION_MANGLE) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported action id"); + return -EOPNOTSUPP; + } + + if (act->mangle.htype != FLOW_ACT_MANGLE_HDR_TYPE_ETH) { + NL_SET_ERR_MSG_MOD(extack, "Only Ethernet modification is supported"); + return -EOPNOTSUPP; + } + + mask = ~act->mangle.mask; + val = act->mangle.val; + offset = act->mangle.offset; + p = (u32 *)&parse_attr->eth; + *(p + (offset >> 2)) |= (val & mask); + + return 0; +} + +int +mlx5e_tc_act_pedit_parse_action(struct mlx5e_priv *priv, + const struct flow_action_entry *act, int namespace, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct pedit_headers_action *hdrs, + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) +{ + if (flow && flow_flag_test(flow, L3_TO_L2_DECAP)) + return parse_pedit_to_reformat(act, parse_attr, extack); + + return parse_pedit_to_modify_hdr(priv, act, namespace, parse_attr, hdrs, extack); +} + +static bool +tc_act_can_offload_pedit(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + return true; +} + +static int +tc_act_parse_pedit(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + struct mlx5e_tc_flow *flow = parse_state->flow; + enum mlx5_flow_namespace_type ns_type; + int err; + + ns_type = mlx5e_get_flow_namespace(flow); + + err = mlx5e_tc_act_pedit_parse_action(flow->priv, act, ns_type, + attr->parse_attr, parse_state->hdrs, + flow, parse_state->extack); + if (err) + return err; + + if (flow_flag_test(flow, L3_TO_L2_DECAP)) + goto out; + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + + if (ns_type == MLX5_FLOW_NAMESPACE_FDB) + esw_attr->split_count = esw_attr->out_count; + +out: + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_pedit = { + .can_offload = tc_act_can_offload_pedit, + .parse_action = tc_act_parse_pedit, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h new file mode 100644 index 000000000000..da8ab03af58f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_EN_TC_ACT_PEDIT_H__ +#define __MLX5_EN_TC_ACT_PEDIT_H__ + +#include "en_tc.h" + +struct pedit_headers { + struct ethhdr eth; + struct vlan_hdr vlan; + struct iphdr ip4; + struct ipv6hdr ip6; + struct tcphdr tcp; + struct udphdr udp; +}; + +struct pedit_headers_action { + struct pedit_headers vals; + struct pedit_headers masks; + u32 pedits; +}; + +int +mlx5e_tc_act_pedit_parse_action(struct mlx5e_priv *priv, + const struct flow_action_entry *act, int namespace, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct pedit_headers_action *hdrs, + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack); + +#endif /* __MLX5_EN_TC_ACT_PEDIT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c new file mode 100644 index 000000000000..0819110193dc --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ptype.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_priv.h" + +static bool +tc_act_can_offload_ptype(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + return true; +} + +static int +tc_act_parse_ptype(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct netlink_ext_ack *extack = parse_state->extack; + + if (act->ptype != PACKET_HOST) { + NL_SET_ERR_MSG_MOD(extack, "skbedit ptype is only supported with type host"); + return -EOPNOTSUPP; + } + + parse_state->ptype_host = true; + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_ptype = { + .can_offload = tc_act_can_offload_ptype, + .parse_action = tc_act_parse_ptype, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c new file mode 100644 index 000000000000..1c32e24e528d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_priv.h" + +static bool +tc_act_can_offload_redirect_ingress(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_tc_flow *flow = parse_state->flow; + struct mlx5e_tc_flow_parse_attr *parse_attr; + struct net_device *out_dev = act->dev; + struct mlx5_esw_flow_attr *esw_attr; + + parse_attr = flow->attr->parse_attr; + esw_attr = flow->attr->esw_attr; + + if (!out_dev) + return false; + + if (!netif_is_ovs_master(out_dev)) { + NL_SET_ERR_MSG_MOD(extack, + "redirect to ingress is supported only for OVS internal ports"); + return false; + } + + if (netif_is_ovs_master(parse_attr->filter_dev)) { + NL_SET_ERR_MSG_MOD(extack, + "redirect to ingress is not supported from internal port"); + return false; + } + + if (!parse_state->ptype_host) { + NL_SET_ERR_MSG_MOD(extack, + "redirect to int port ingress requires ptype=host action"); + return false; + } + + if (esw_attr->out_count) { + NL_SET_ERR_MSG_MOD(extack, + "redirect to int port ingress is supported only as single destination"); + return false; + } + + return true; +} + +static int +tc_act_parse_redirect_ingress(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + struct net_device *out_dev = act->dev; + int err; + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + + err = mlx5e_set_fwd_to_int_port_actions(priv, attr, out_dev->ifindex, + MLX5E_TC_INT_PORT_INGRESS, + &attr->action, esw_attr->out_count); + if (err) + return err; + + esw_attr->out_count++; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_redirect_ingress = { + .can_offload = tc_act_can_offload_redirect_ingress, + .parse_action = tc_act_parse_redirect_ingress, +}; + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c new file mode 100644 index 000000000000..6699bdf5cf01 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/sample.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include <net/psample.h> +#include "act.h" +#include "en/tc_priv.h" + +static bool +tc_act_can_offload_sample(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct netlink_ext_ack *extack = parse_state->extack; + + if (flow_flag_test(parse_state->flow, CT)) { + NL_SET_ERR_MSG_MOD(extack, + "Sample action with connection tracking is not supported"); + return false; + } + + return true; +} + +static int +tc_act_parse_sample(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5e_sample_attr *sample_attr; + + sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL); + if (!sample_attr) + return -ENOMEM; + + sample_attr->rate = act->sample.rate; + sample_attr->group_num = act->sample.psample_group->group_num; + + if (act->sample.truncate) + sample_attr->trunc_size = act->sample.trunc_size; + + attr->sample_attr = sample_attr; + flow_flag_set(parse_state->flow, SAMPLE); + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_sample = { + .can_offload = tc_act_can_offload_sample, + .parse_action = tc_act_parse_sample, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c new file mode 100644 index 000000000000..046b64c2cec4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/trap.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_priv.h" + +static bool +tc_act_can_offload_trap(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + struct netlink_ext_ack *extack = parse_state->extack; + + if (parse_state->num_actions != 1) { + NL_SET_ERR_MSG_MOD(extack, "action trap is supported as a sole action only"); + return false; + } + + return true; +} + +static int +tc_act_parse_trap(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_trap = { + .can_offload = tc_act_can_offload_trap, + .parse_action = tc_act_parse_trap, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c new file mode 100644 index 000000000000..6f4a2cf46afd --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/tun.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include "act.h" +#include "en/tc_tun_encap.h" +#include "en/tc_priv.h" + +static bool +tc_act_can_offload_tun_encap(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + if (!act->tunnel) { + NL_SET_ERR_MSG_MOD(parse_state->extack, + "Zero tunnel attributes is not supported"); + return false; + } + + return true; +} + +static int +tc_act_parse_tun_encap(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + parse_state->tun_info = act->tunnel; + parse_state->encap = true; + + return 0; +} + +static bool +tc_act_can_offload_tun_decap(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + return true; +} + +static int +tc_act_parse_tun_decap(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + parse_state->decap = true; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_tun_encap = { + .can_offload = tc_act_can_offload_tun_encap, + .parse_action = tc_act_parse_tun_encap, +}; + +struct mlx5e_tc_act mlx5e_tc_act_tun_decap = { + .can_offload = tc_act_can_offload_tun_decap, + .parse_action = tc_act_parse_tun_decap, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c new file mode 100644 index 000000000000..70fc0c2d8813 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include <linux/if_vlan.h> +#include "act.h" +#include "vlan.h" +#include "en/tc_priv.h" + +static int +add_vlan_prio_tag_rewrite_action(struct mlx5e_priv *priv, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct pedit_headers_action *hdrs, + u32 *action, struct netlink_ext_ack *extack) +{ + const struct flow_action_entry prio_tag_act = { + .vlan.vid = 0, + .vlan.prio = + MLX5_GET(fte_match_set_lyr_2_4, + mlx5e_get_match_headers_value(*action, + &parse_attr->spec), + first_prio) & + MLX5_GET(fte_match_set_lyr_2_4, + mlx5e_get_match_headers_criteria(*action, + &parse_attr->spec), + first_prio), + }; + + return mlx5e_tc_act_vlan_add_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB, + &prio_tag_act, parse_attr, hdrs, action, + extack); +} + +static int +parse_tc_vlan_action(struct mlx5e_priv *priv, + const struct flow_action_entry *act, + struct mlx5_esw_flow_attr *attr, + u32 *action, + struct netlink_ext_ack *extack) +{ + u8 vlan_idx = attr->total_vlan; + + if (vlan_idx >= MLX5_FS_VLAN_DEPTH) { + NL_SET_ERR_MSG_MOD(extack, "Total vlans used is greater than supported"); + return -EOPNOTSUPP; + } + + switch (act->id) { + case FLOW_ACTION_VLAN_POP: + if (vlan_idx) { + if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, + MLX5_FS_VLAN_DEPTH)) { + NL_SET_ERR_MSG_MOD(extack, "vlan pop action is not supported"); + return -EOPNOTSUPP; + } + + *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2; + } else { + *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; + } + break; + case FLOW_ACTION_VLAN_PUSH: + attr->vlan_vid[vlan_idx] = act->vlan.vid; + attr->vlan_prio[vlan_idx] = act->vlan.prio; + attr->vlan_proto[vlan_idx] = act->vlan.proto; + if (!attr->vlan_proto[vlan_idx]) + attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q); + + if (vlan_idx) { + if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, + MLX5_FS_VLAN_DEPTH)) { + NL_SET_ERR_MSG_MOD(extack, + "vlan push action is not supported for vlan depth > 1"); + return -EOPNOTSUPP; + } + + *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2; + } else { + if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) && + (act->vlan.proto != htons(ETH_P_8021Q) || + act->vlan.prio)) { + NL_SET_ERR_MSG_MOD(extack, "vlan push action is not supported"); + return -EOPNOTSUPP; + } + + *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; + } + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unexpected action id for VLAN"); + return -EINVAL; + } + + attr->total_vlan = vlan_idx + 1; + + return 0; +} + +int +mlx5e_tc_act_vlan_add_push_action(struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr, + struct net_device **out_dev, + struct netlink_ext_ack *extack) +{ + struct net_device *vlan_dev = *out_dev; + struct flow_action_entry vlan_act = { + .id = FLOW_ACTION_VLAN_PUSH, + .vlan.vid = vlan_dev_vlan_id(vlan_dev), + .vlan.proto = vlan_dev_vlan_proto(vlan_dev), + .vlan.prio = 0, + }; + int err; + + err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, &attr->action, extack); + if (err) + return err; + + rcu_read_lock(); + *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), dev_get_iflink(vlan_dev)); + rcu_read_unlock(); + if (!*out_dev) + return -ENODEV; + + if (is_vlan_dev(*out_dev)) + err = mlx5e_tc_act_vlan_add_push_action(priv, attr, out_dev, extack); + + return err; +} + +int +mlx5e_tc_act_vlan_add_pop_action(struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack) +{ + struct flow_action_entry vlan_act = { + .id = FLOW_ACTION_VLAN_POP, + }; + int nest_level, err = 0; + + nest_level = attr->parse_attr->filter_dev->lower_level - + priv->netdev->lower_level; + while (nest_level--) { + err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, &attr->action, + extack); + if (err) + return err; + } + + return err; +} + +static bool +tc_act_can_offload_vlan(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + return true; +} + +static int +tc_act_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; + int err; + + if (act->id == FLOW_ACTION_VLAN_PUSH && + (attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP)) { + /* Replace vlan pop+push with vlan modify */ + attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; + err = mlx5e_tc_act_vlan_add_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB, act, + attr->parse_attr, parse_state->hdrs, + &attr->action, parse_state->extack); + } else { + err = parse_tc_vlan_action(priv, act, esw_attr, &attr->action, + parse_state->extack); + } + + if (err) + return err; + + esw_attr->split_count = esw_attr->out_count; + + return 0; +} + +static int +tc_act_post_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr; + struct pedit_headers_action *hdrs = parse_state->hdrs; + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + int err; + + if (MLX5_CAP_GEN(esw->dev, prio_tag_required) && + attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) { + /* For prio tag mode, replace vlan pop with rewrite vlan prio + * tag rewrite. + */ + attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; + err = add_vlan_prio_tag_rewrite_action(priv, parse_attr, hdrs, + &attr->action, extack); + if (err) + return err; + } + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_vlan = { + .can_offload = tc_act_can_offload_vlan, + .parse_action = tc_act_parse_vlan, + .post_parse = tc_act_post_parse_vlan, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h new file mode 100644 index 000000000000..3d62f13ab61f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef __MLX5_EN_TC_ACT_VLAN_H__ +#define __MLX5_EN_TC_ACT_VLAN_H__ + +#include <net/flow_offload.h> +#include "en/tc_priv.h" + +struct pedit_headers_action; + +int +mlx5e_tc_act_vlan_add_push_action(struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr, + struct net_device **out_dev, + struct netlink_ext_ack *extack); + +int +mlx5e_tc_act_vlan_add_pop_action(struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr, + struct netlink_ext_ack *extack); + +int +mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, + const struct flow_action_entry *act, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct pedit_headers_action *hdrs, + u32 *action, struct netlink_ext_ack *extack); + +#endif /* __MLX5_EN_TC_ACT_VLAN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c new file mode 100644 index 000000000000..63e36e7f53e3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +#include <linux/if_vlan.h> +#include "act.h" +#include "vlan.h" +#include "en/tc_priv.h" + +struct pedit_headers_action; + +int +mlx5e_tc_act_vlan_add_rewrite_action(struct mlx5e_priv *priv, int namespace, + const struct flow_action_entry *act, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct pedit_headers_action *hdrs, + u32 *action, struct netlink_ext_ack *extack) +{ + u16 mask16 = VLAN_VID_MASK; + u16 val16 = act->vlan.vid & VLAN_VID_MASK; + const struct flow_action_entry pedit_act = { + .id = FLOW_ACTION_MANGLE, + .mangle.htype = FLOW_ACT_MANGLE_HDR_TYPE_ETH, + .mangle.offset = offsetof(struct vlan_ethhdr, h_vlan_TCI), + .mangle.mask = ~(u32)be16_to_cpu(*(__be16 *)&mask16), + .mangle.val = (u32)be16_to_cpu(*(__be16 *)&val16), + }; + u8 match_prio_mask, match_prio_val; + void *headers_c, *headers_v; + int err; + + headers_c = mlx5e_get_match_headers_criteria(*action, &parse_attr->spec); + headers_v = mlx5e_get_match_headers_value(*action, &parse_attr->spec); + + if (!(MLX5_GET(fte_match_set_lyr_2_4, headers_c, cvlan_tag) && + MLX5_GET(fte_match_set_lyr_2_4, headers_v, cvlan_tag))) { + NL_SET_ERR_MSG_MOD(extack, "VLAN rewrite action must have VLAN protocol match"); + return -EOPNOTSUPP; + } + + match_prio_mask = MLX5_GET(fte_match_set_lyr_2_4, headers_c, first_prio); + match_prio_val = MLX5_GET(fte_match_set_lyr_2_4, headers_v, first_prio); + if (act->vlan.prio != (match_prio_val & match_prio_mask)) { + NL_SET_ERR_MSG_MOD(extack, "Changing VLAN prio is not supported"); + return -EOPNOTSUPP; + } + + err = mlx5e_tc_act_pedit_parse_action(priv, &pedit_act, namespace, parse_attr, hdrs, + NULL, extack); + *action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + + return err; +} + +static bool +tc_act_can_offload_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + int act_index) +{ + return true; +} + +static int +tc_act_parse_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state, + const struct flow_action_entry *act, + struct mlx5e_priv *priv, + struct mlx5_flow_attr *attr) +{ + enum mlx5_flow_namespace_type ns_type; + int err; + + ns_type = mlx5e_get_flow_namespace(parse_state->flow); + err = mlx5e_tc_act_vlan_add_rewrite_action(priv, ns_type, act, + attr->parse_attr, parse_state->hdrs, + &attr->action, parse_state->extack); + if (err) + return err; + + if (ns_type == MLX5_FLOW_NAMESPACE_FDB) + attr->esw_attr->split_count = attr->esw_attr->out_count; + + return 0; +} + +struct mlx5e_tc_act mlx5e_tc_act_vlan_mangle = { + .can_offload = tc_act_can_offload_vlan_mangle, + .parse_action = tc_act_parse_vlan_mangle, +}; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index b689701ac7d8..f832c26ff2c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -5,11 +5,14 @@ #define __MLX5_EN_TC_PRIV_H__ #include "en_tc.h" +#include "en/tc/act/act.h" #define MLX5E_TC_FLOW_BASE (MLX5E_TC_FLAG_LAST_EXPORTED_BIT + 1) #define MLX5E_TC_MAX_SPLITS 1 +#define mlx5e_nic_chains(priv) ((priv)->fs.tc.chains) + enum { MLX5E_TC_FLOW_FLAG_INGRESS = MLX5E_TC_FLAG_INGRESS_BIT, MLX5E_TC_FLOW_FLAG_EGRESS = MLX5E_TC_FLAG_EGRESS_BIT, @@ -37,6 +40,7 @@ struct mlx5e_tc_flow_parse_attr { struct mlx5e_tc_mod_hdr_acts mod_hdr_acts; int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS]; struct ethhdr eth; + struct mlx5e_tc_act_parse_state parse_state; }; /* Helper struct for accessing a struct containing list_head array. @@ -115,7 +119,11 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr); +bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow); +bool mlx5e_is_ft_flow(struct mlx5e_tc_flow *flow); bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow); +int mlx5e_get_flow_namespace(struct mlx5e_tc_flow *flow); +bool mlx5e_same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv); static inline void __flow_flag_set(struct mlx5e_tc_flow *flow, unsigned long flag) { @@ -176,4 +184,8 @@ struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow); struct mlx5e_tc_int_port_priv * mlx5e_get_int_port_priv(struct mlx5e_priv *priv); + +void *mlx5e_get_match_headers_value(u32 flags, struct mlx5_flow_spec *spec); +void *mlx5e_get_match_headers_criteria(u32 flags, struct mlx5_flow_spec *spec); + #endif /* __MLX5_EN_TC_PRIV_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3e3419190c55..eec919f1b476 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -39,10 +39,6 @@ #include <linux/rhashtable.h> #include <linux/refcount.h> #include <linux/completion.h> -#include <linux/if_macvlan.h> -#include <net/tc_act/tc_pedit.h> -#include <net/tc_act/tc_csum.h> -#include <net/psample.h> #include <net/arp.h> #include <net/ipv6_stubs.h> #include <net/bareudp.h> @@ -62,6 +58,7 @@ #include "en/mod_hdr.h" #include "en/tc_tun_encap.h" #include "en/tc/sample.h" +#include "en/tc/act/act.h" #include "lib/devcom.h" #include "lib/geneve.h" #include "lib/fs_chains.h" @@ -70,8 +67,6 @@ #include "lag/lag.h" #include "lag/mp.h" -#define nic_chains(priv) ((priv)->fs.tc.chains) - #define MLX5E_TC_TABLE_NUM_GROUPS 4 #define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(18) @@ -399,7 +394,7 @@ bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow) return flow_flag_test(flow, ESWITCH); } -static bool mlx5e_is_ft_flow(struct mlx5e_tc_flow *flow) +bool mlx5e_is_ft_flow(struct mlx5e_tc_flow *flow) { return flow_flag_test(flow, FT); } @@ -409,7 +404,7 @@ bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow) return flow_flag_test(flow, OFFLOADED); } -static int get_flow_name_space(struct mlx5e_tc_flow *flow) +int mlx5e_get_flow_namespace(struct mlx5e_tc_flow *flow) { return mlx5e_is_eswitch_flow(flow) ? MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; @@ -420,7 +415,7 @@ get_mod_hdr_table(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - return get_flow_name_space(flow) == MLX5_FLOW_NAMESPACE_FDB ? + return mlx5e_get_flow_namespace(flow) == MLX5_FLOW_NAMESPACE_FDB ? &esw->offloads.mod_hdr : &priv->fs.tc.mod_hdr; } @@ -433,7 +428,7 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_mod_hdr_handle *mh; mh = mlx5e_mod_hdr_attach(priv->mdev, get_mod_hdr_table(priv, flow), - get_flow_name_space(flow), + mlx5e_get_flow_namespace(flow), &parse_attr->mod_hdr_acts); if (IS_ERR(mh)) return PTR_ERR(mh); @@ -937,7 +932,7 @@ mlx5e_add_offloaded_nic_rule(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { struct mlx5_flow_context *flow_context = &spec->flow_context; - struct mlx5_fs_chains *nic_chains = nic_chains(priv); + struct mlx5_fs_chains *nic_chains = mlx5e_nic_chains(priv); struct mlx5_nic_flow_attr *nic_attr = attr->nic_attr; struct mlx5e_tc_table *tc = &priv->fs.tc; struct mlx5_flow_destination dest[2] = {}; @@ -1091,7 +1086,7 @@ void mlx5e_del_offloaded_nic_rule(struct mlx5e_priv *priv, struct mlx5_flow_handle *rule, struct mlx5_flow_attr *attr) { - struct mlx5_fs_chains *nic_chains = nic_chains(priv); + struct mlx5_fs_chains *nic_chains = mlx5e_nic_chains(priv); mlx5_del_flow_rules(rule); @@ -1123,7 +1118,7 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, mutex_lock(&priv->fs.tc.t_lock); if (!mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD)) && !IS_ERR_OR_NULL(tc->t)) { - mlx5_chains_put_table(nic_chains(priv), 0, 1, MLX5E_TC_FT_LEVEL); + mlx5_chains_put_table(mlx5e_nic_chains(priv), 0, 1, MLX5E_TC_FT_LEVEL); priv->fs.tc.t = NULL; } mutex_unlock(&priv->fs.tc.t_lock); @@ -1304,8 +1299,6 @@ static void remove_unready_flow(struct mlx5e_tc_flow *flow) mutex_unlock(&uplink_priv->unready_flows_lock); } -static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv); - bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_dev) { struct mlx5_core_dev *out_mdev, *route_mdev; @@ -1320,7 +1313,7 @@ bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_ route_mdev->coredev_type != MLX5_COREDEV_VF) return false; - return same_hw_devs(out_priv, route_priv); + return mlx5e_same_hw_devs(out_priv, route_priv); } int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *route_dev, u16 *vport) @@ -1367,7 +1360,7 @@ int mlx5e_tc_add_flow_mod_hdr(struct mlx5e_priv *priv, struct mlx5_modify_hdr *mod_hdr; mod_hdr = mlx5_modify_header_alloc(priv->mdev, - get_flow_name_space(flow), + mlx5e_get_flow_namespace(flow), mod_hdr_acts->num_actions, mod_hdr_acts->actions); if (IS_ERR(mod_hdr)) @@ -2053,16 +2046,14 @@ static void *get_match_outer_headers_value(struct mlx5_flow_spec *spec) outer_headers); } -static void *get_match_headers_value(u32 flags, - struct mlx5_flow_spec *spec) +void *mlx5e_get_match_headers_value(u32 flags, struct mlx5_flow_spec *spec) { return (flags & MLX5_FLOW_CONTEXT_ACTION_DECAP) ? get_match_inner_headers_value(spec) : get_match_outer_headers_value(spec); } -static void *get_match_headers_criteria(u32 flags, - struct mlx5_flow_spec *spec) +void *mlx5e_get_match_headers_criteria(u32 flags, struct mlx5_flow_spec *spec) { return (flags & MLX5_FLOW_CONTEXT_ACTION_DECAP) ? get_match_inner_headers_criteria(spec) : @@ -2607,55 +2598,6 @@ static int parse_cls_flower(struct mlx5e_priv *priv, return err; } -struct pedit_headers { - struct ethhdr eth; - struct vlan_hdr vlan; - struct iphdr ip4; - struct ipv6hdr ip6; - struct tcphdr tcp; - struct udphdr udp; -}; - -struct pedit_headers_action { - struct pedit_headers vals; - struct pedit_headers masks; - u32 pedits; -}; - -static int pedit_header_offsets[] = { - [FLOW_ACT_MANGLE_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth), - [FLOW_ACT_MANGLE_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4), - [FLOW_ACT_MANGLE_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6), - [FLOW_ACT_MANGLE_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp), - [FLOW_ACT_MANGLE_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp), -}; - -#define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype]) - -static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset, - struct pedit_headers_action *hdrs, - struct netlink_ext_ack *extack) -{ - u32 *curr_pmask, *curr_pval; - - curr_pmask = (u32 *)(pedit_header(&hdrs->masks, hdr_type) + offset); - curr_pval = (u32 *)(pedit_header(&hdrs->vals, hdr_type) + offset); - - if (*curr_pmask & mask) { /* disallow acting twice on the same location */ - NL_SET_ERR_MSG_MOD(extack, - "curr_pmask and new mask same. Acting twice on same location"); - goto out_err; - } - - *curr_pmask |= mask; - *curr_pval |= (val & mask); - - return 0; - -out_err: - return -EOPNOTSUPP; -} - struct mlx5_fields { u8 field; u8 field_bsize; @@ -2776,8 +2718,8 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, u8 cmd; mod_acts = &parse_attr->mod_hdr_acts; - headers_c = get_match_headers_criteria(*action_flags, &parse_attr->spec); - headers_v = get_match_headers_value(*action_flags, &parse_attr->spec); + headers_c = mlx5e_get_match_headers_criteria(*action_flags, &parse_attr->spec); + headers_v = mlx5e_get_match_headers_value(*action_flags, &parse_attr->spec); set_masks = &hdrs[0].masks; add_masks = &hdrs[1].masks; @@ -2892,88 +2834,6 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, static const struct pedit_headers zero_masks = {}; -static int -parse_pedit_to_modify_hdr(struct mlx5e_priv *priv, - const struct flow_action_entry *act, int namespace, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, - struct netlink_ext_ack *extack) -{ - u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1; - int err = -EOPNOTSUPP; - u32 mask, val, offset; - u8 htype; - - htype = act->mangle.htype; - err = -EOPNOTSUPP; /* can't be all optimistic */ - - if (htype == FLOW_ACT_MANGLE_UNSPEC) { - NL_SET_ERR_MSG_MOD(extack, "legacy pedit isn't offloaded"); - goto out_err; - } - - if (!mlx5e_mod_hdr_max_actions(priv->mdev, namespace)) { - NL_SET_ERR_MSG_MOD(extack, - "The pedit offload action is not supported"); - goto out_err; - } - - mask = act->mangle.mask; - val = act->mangle.val; - offset = act->mangle.offset; - - err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd], extack); - if (err) - goto out_err; - - hdrs[cmd].pedits++; - - return 0; -out_err: - return err; -} - -static int -parse_pedit_to_reformat(const struct flow_action_entry *act, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct netlink_ext_ack *extack) -{ - u32 mask, val, offset; - u32 *p; - - if (act->id != FLOW_ACTION_MANGLE) { - NL_SET_ERR_MSG_MOD(extack, "Unsupported action id"); - return -EOPNOTSUPP; - } - - if (act->mangle.htype != FLOW_ACT_MANGLE_HDR_TYPE_ETH) { - NL_SET_ERR_MSG_MOD(extack, "Only Ethernet modification is supported"); - return -EOPNOTSUPP; - } - - mask = ~act->mangle.mask; - val = act->mangle.val; - offset = act->mangle.offset; - p = (u32 *)&parse_attr->eth; - *(p + (offset >> 2)) |= (val & mask); - - return 0; -} - -static int parse_tc_pedit_action(struct mlx5e_priv *priv, - const struct flow_action_entry *act, int namespace, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, - struct mlx5e_tc_flow *flow, - struct netlink_ext_ack *extack) -{ - if (flow && flow_flag_test(flow, L3_TO_L2_DECAP)) - return parse_pedit_to_reformat(act, parse_attr, extack); - - return parse_pedit_to_modify_hdr(priv, act, namespace, - parse_attr, hdrs, extack); -} - static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace, struct mlx5e_tc_flow_parse_attr *parse_attr, struct pedit_headers_action *hdrs, @@ -3009,35 +2869,6 @@ out_dealloc_parsed_actions: return err; } -static bool csum_offload_supported(struct mlx5e_priv *priv, - u32 action, - u32 update_flags, - struct netlink_ext_ack *extack) -{ - u32 prot_flags = TCA_CSUM_UPDATE_FLAG_IPV4HDR | TCA_CSUM_UPDATE_FLAG_TCP | - TCA_CSUM_UPDATE_FLAG_UDP; - - /* The HW recalcs checksums only if re-writing headers */ - if (!(action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)) { - NL_SET_ERR_MSG_MOD(extack, - "TC csum action is only offloaded with pedit"); - netdev_warn(priv->netdev, - "TC csum action is only offloaded with pedit\n"); - return false; - } - - if (update_flags & ~prot_flags) { - NL_SET_ERR_MSG_MOD(extack, - "can't offload TC csum action for some header/s"); - netdev_warn(priv->netdev, - "can't offload TC csum action for some header/s - flags %#x\n", - update_flags); - return false; - } - - return true; -} - struct ip_ttl_word { __u8 ttl; __u8 protocol; @@ -3160,8 +2991,8 @@ static bool modify_header_match_supported(struct mlx5e_priv *priv, u8 ip_proto; int i; - headers_c = get_match_headers_criteria(actions, spec); - headers_v = get_match_headers_value(actions, spec); + headers_c = mlx5e_get_match_headers_criteria(actions, spec); + headers_v = mlx5e_get_match_headers_value(actions, spec); ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype); /* for non-IP we only re-write MACs, so we're okay */ @@ -3268,7 +3099,7 @@ static bool same_port_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv return priv->mdev == peer_priv->mdev; } -static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) +bool mlx5e_same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) { struct mlx5_core_dev *fmdev, *pmdev; u64 fsystem_guid, psystem_guid; @@ -3282,124 +3113,45 @@ static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) return (fsystem_guid == psystem_guid); } -static bool same_vf_reps(struct mlx5e_priv *priv, - struct net_device *out_dev) -{ - return mlx5e_eswitch_vf_rep(priv->netdev) && - priv->netdev == out_dev; -} - -static int add_vlan_rewrite_action(struct mlx5e_priv *priv, int namespace, - const struct flow_action_entry *act, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, - u32 *action, struct netlink_ext_ack *extack) -{ - u16 mask16 = VLAN_VID_MASK; - u16 val16 = act->vlan.vid & VLAN_VID_MASK; - const struct flow_action_entry pedit_act = { - .id = FLOW_ACTION_MANGLE, - .mangle.htype = FLOW_ACT_MANGLE_HDR_TYPE_ETH, - .mangle.offset = offsetof(struct vlan_ethhdr, h_vlan_TCI), - .mangle.mask = ~(u32)be16_to_cpu(*(__be16 *)&mask16), - .mangle.val = (u32)be16_to_cpu(*(__be16 *)&val16), - }; - u8 match_prio_mask, match_prio_val; - void *headers_c, *headers_v; - int err; - - headers_c = get_match_headers_criteria(*action, &parse_attr->spec); - headers_v = get_match_headers_value(*action, &parse_attr->spec); - - if (!(MLX5_GET(fte_match_set_lyr_2_4, headers_c, cvlan_tag) && - MLX5_GET(fte_match_set_lyr_2_4, headers_v, cvlan_tag))) { - NL_SET_ERR_MSG_MOD(extack, - "VLAN rewrite action must have VLAN protocol match"); - return -EOPNOTSUPP; - } - - match_prio_mask = MLX5_GET(fte_match_set_lyr_2_4, headers_c, first_prio); - match_prio_val = MLX5_GET(fte_match_set_lyr_2_4, headers_v, first_prio); - if (act->vlan.prio != (match_prio_val & match_prio_mask)) { - NL_SET_ERR_MSG_MOD(extack, - "Changing VLAN prio is not supported"); - return -EOPNOTSUPP; - } - - err = parse_tc_pedit_action(priv, &pedit_act, namespace, parse_attr, hdrs, NULL, extack); - *action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - - return err; -} - static int -add_vlan_prio_tag_rewrite_action(struct mlx5e_priv *priv, - struct mlx5e_tc_flow_parse_attr *parse_attr, - struct pedit_headers_action *hdrs, - u32 *action, struct netlink_ext_ack *extack) -{ - const struct flow_action_entry prio_tag_act = { - .vlan.vid = 0, - .vlan.prio = - MLX5_GET(fte_match_set_lyr_2_4, - get_match_headers_value(*action, - &parse_attr->spec), - first_prio) & - MLX5_GET(fte_match_set_lyr_2_4, - get_match_headers_criteria(*action, - &parse_attr->spec), - first_prio), - }; +parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state, + struct flow_action *flow_action) +{ + struct netlink_ext_ack *extack = parse_state->extack; + struct mlx5e_tc_flow *flow = parse_state->flow; + struct mlx5_flow_attr *attr = flow->attr; + enum mlx5_flow_namespace_type ns_type; + struct mlx5e_priv *priv = flow->priv; + const struct flow_action_entry *act; + struct mlx5e_tc_act *tc_act; + int err, i; - return add_vlan_rewrite_action(priv, MLX5_FLOW_NAMESPACE_FDB, - &prio_tag_act, parse_attr, hdrs, action, - extack); -} + ns_type = mlx5e_get_flow_namespace(flow); -static int validate_goto_chain(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - const struct flow_action_entry *act, - struct netlink_ext_ack *extack) -{ - bool is_esw = mlx5e_is_eswitch_flow(flow); - bool ft_flow = mlx5e_is_ft_flow(flow); - u32 dest_chain = act->chain_index; - struct mlx5_fs_chains *chains; - struct mlx5_eswitch *esw; - u32 reformat_and_fwd; - u32 max_chain; + flow_action_for_each(i, act, flow_action) { + tc_act = mlx5e_tc_act_get(act->id, ns_type); + if (!tc_act) { + NL_SET_ERR_MSG_MOD(extack, "Not implemented offload action"); + return -EOPNOTSUPP; + } - esw = priv->mdev->priv.eswitch; - chains = is_esw ? esw_chains(esw) : nic_chains(priv); - max_chain = mlx5_chains_get_chain_range(chains); - reformat_and_fwd = is_esw ? - MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, reformat_and_fwd_to_table) : - MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, reformat_and_fwd_to_table); - - if (ft_flow) { - NL_SET_ERR_MSG_MOD(extack, "Goto action is not supported"); - return -EOPNOTSUPP; - } + if (!tc_act->can_offload(parse_state, act, i)) + return -EOPNOTSUPP; - if (!mlx5_chains_backwards_supported(chains) && - dest_chain <= flow->attr->chain) { - NL_SET_ERR_MSG_MOD(extack, - "Goto lower numbered chain isn't supported"); - return -EOPNOTSUPP; + err = tc_act->parse_action(parse_state, act, priv, attr); + if (err) + return err; } - if (dest_chain > max_chain) { - NL_SET_ERR_MSG_MOD(extack, - "Requested destination chain is out of supported range"); - return -EOPNOTSUPP; - } + flow_action_for_each(i, act, flow_action) { + tc_act = mlx5e_tc_act_get(act->id, ns_type); + if (!tc_act || !tc_act->post_parse || + !tc_act->can_offload(parse_state, act, i)) + continue; - if (flow->attr->action & (MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | - MLX5_FLOW_CONTEXT_ACTION_DECAP) && - !reformat_and_fwd) { - NL_SET_ERR_MSG_MOD(extack, - "Goto chain is not allowed if action has reformat or decap"); - return -EOPNOTSUPP; + err = tc_act->post_parse(parse_state, priv, attr); + if (err) + return err; } return 0; @@ -3420,7 +3172,7 @@ actions_prepare_mod_hdr_actions(struct mlx5e_priv *priv, !hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) return 0; - ns_type = get_flow_name_space(flow); + ns_type = mlx5e_get_flow_namespace(flow); err = alloc_tc_pedit_action(priv, ns_type, parse_attr, hdrs, &attr->action, extack); @@ -3468,116 +3220,26 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { + struct mlx5e_tc_act_parse_state *parse_state; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; - struct pedit_headers_action hdrs[2] = {}; - const struct flow_action_entry *act; - struct mlx5_nic_flow_attr *nic_attr; - int err, i; + struct pedit_headers_action *hdrs; + int err; err = flow_action_supported(flow_action, extack); if (err) return err; - nic_attr = attr->nic_attr; - nic_attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; + attr->nic_attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; parse_attr = attr->parse_attr; + parse_state = &parse_attr->parse_state; + mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack); + parse_state->ct_priv = get_ct_priv(priv); + hdrs = parse_state->hdrs; - flow_action_for_each(i, act, flow_action) { - switch (act->id) { - case FLOW_ACTION_ACCEPT: - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - break; - case FLOW_ACTION_DROP: - attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - break; - case FLOW_ACTION_MANGLE: - case FLOW_ACTION_ADD: - err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_KERNEL, - parse_attr, hdrs, NULL, extack); - if (err) - return err; - - attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - break; - case FLOW_ACTION_VLAN_MANGLE: - err = add_vlan_rewrite_action(priv, - MLX5_FLOW_NAMESPACE_KERNEL, - act, parse_attr, hdrs, - &attr->action, extack); - if (err) - return err; - - break; - case FLOW_ACTION_CSUM: - if (csum_offload_supported(priv, attr->action, - act->csum_flags, - extack)) - break; - - return -EOPNOTSUPP; - case FLOW_ACTION_REDIRECT: { - struct net_device *peer_dev = act->dev; - - if (priv->netdev->netdev_ops == peer_dev->netdev_ops && - same_hw_devs(priv, netdev_priv(peer_dev))) { - parse_attr->mirred_ifindex[0] = peer_dev->ifindex; - flow_flag_set(flow, HAIRPIN); - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - } else { - NL_SET_ERR_MSG_MOD(extack, - "device is not on same HW, can't offload"); - netdev_warn(priv->netdev, "device %s not on same HW, can't offload\n", - peer_dev->name); - return -EOPNOTSUPP; - } - } - break; - case FLOW_ACTION_MARK: { - u32 mark = act->mark; - - if (mark & ~MLX5E_TC_FLOW_ID_MASK) { - NL_SET_ERR_MSG_MOD(extack, - "Bad flow mark - only 16 bit is supported"); - return -EOPNOTSUPP; - } - - nic_attr->flow_tag = mark; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - } - break; - case FLOW_ACTION_GOTO: - err = validate_goto_chain(priv, flow, act, extack); - if (err) - return err; - - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - attr->dest_chain = act->chain_index; - break; - case FLOW_ACTION_CT: - err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, - &parse_attr->mod_hdr_acts, - act, extack); - if (err) - return err; - - flow_flag_set(flow, CT); - break; - default: - NL_SET_ERR_MSG_MOD(extack, - "The offload action is not supported in NIC action"); - return -EOPNOTSUPP; - } - } - - if (attr->dest_chain && parse_attr->mirred_ifindex[0]) { - NL_SET_ERR_MSG(extack, "Mirroring goto chain rules isn't supported"); - return -EOPNOTSUPP; - } + err = parse_tc_actions(parse_state, flow_action); + if (err) + return err; err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack); if (err) @@ -3599,146 +3261,7 @@ static bool is_merged_eswitch_vfs(struct mlx5e_priv *priv, return (MLX5_CAP_ESW(priv->mdev, merged_eswitch) && mlx5e_eswitch_vf_rep(priv->netdev) && mlx5e_eswitch_vf_rep(peer_netdev) && - same_hw_devs(priv, peer_priv)); -} - -static int parse_tc_vlan_action(struct mlx5e_priv *priv, - const struct flow_action_entry *act, - struct mlx5_esw_flow_attr *attr, - u32 *action, - struct netlink_ext_ack *extack) -{ - u8 vlan_idx = attr->total_vlan; - - if (vlan_idx >= MLX5_FS_VLAN_DEPTH) { - NL_SET_ERR_MSG_MOD(extack, "Total vlans used is greater than supported"); - return -EOPNOTSUPP; - } - - switch (act->id) { - case FLOW_ACTION_VLAN_POP: - if (vlan_idx) { - if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) { - NL_SET_ERR_MSG_MOD(extack, - "vlan pop action is not supported"); - return -EOPNOTSUPP; - } - - *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2; - } else { - *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; - } - break; - case FLOW_ACTION_VLAN_PUSH: - attr->vlan_vid[vlan_idx] = act->vlan.vid; - attr->vlan_prio[vlan_idx] = act->vlan.prio; - attr->vlan_proto[vlan_idx] = act->vlan.proto; - if (!attr->vlan_proto[vlan_idx]) - attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q); - - if (vlan_idx) { - if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) { - NL_SET_ERR_MSG_MOD(extack, - "vlan push action is not supported for vlan depth > 1"); - return -EOPNOTSUPP; - } - - *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2; - } else { - if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) && - (act->vlan.proto != htons(ETH_P_8021Q) || - act->vlan.prio)) { - NL_SET_ERR_MSG_MOD(extack, - "vlan push action is not supported"); - return -EOPNOTSUPP; - } - - *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; - } - break; - default: - NL_SET_ERR_MSG_MOD(extack, "Unexpected action id for VLAN"); - return -EINVAL; - } - - attr->total_vlan = vlan_idx + 1; - - return 0; -} - -static struct net_device *get_fdb_out_dev(struct net_device *uplink_dev, - struct net_device *out_dev) -{ - struct net_device *fdb_out_dev = out_dev; - struct net_device *uplink_upper; - - rcu_read_lock(); - uplink_upper = netdev_master_upper_dev_get_rcu(uplink_dev); - if (uplink_upper && netif_is_lag_master(uplink_upper) && - uplink_upper == out_dev) { - fdb_out_dev = uplink_dev; - } else if (netif_is_lag_master(out_dev)) { - fdb_out_dev = bond_option_active_slave_get_rcu(netdev_priv(out_dev)); - if (fdb_out_dev && - (!mlx5e_eswitch_rep(fdb_out_dev) || - !netdev_port_same_parent_id(fdb_out_dev, uplink_dev))) - fdb_out_dev = NULL; - } - rcu_read_unlock(); - return fdb_out_dev; -} - -static int add_vlan_push_action(struct mlx5e_priv *priv, - struct mlx5_flow_attr *attr, - struct net_device **out_dev, - struct netlink_ext_ack *extack) -{ - struct net_device *vlan_dev = *out_dev; - struct flow_action_entry vlan_act = { - .id = FLOW_ACTION_VLAN_PUSH, - .vlan.vid = vlan_dev_vlan_id(vlan_dev), - .vlan.proto = vlan_dev_vlan_proto(vlan_dev), - .vlan.prio = 0, - }; - int err; - - err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, &attr->action, extack); - if (err) - return err; - - rcu_read_lock(); - *out_dev = dev_get_by_index_rcu(dev_net(vlan_dev), dev_get_iflink(vlan_dev)); - rcu_read_unlock(); - if (!*out_dev) - return -ENODEV; - - if (is_vlan_dev(*out_dev)) - err = add_vlan_push_action(priv, attr, out_dev, extack); - - return err; -} - -static int add_vlan_pop_action(struct mlx5e_priv *priv, - struct mlx5_flow_attr *attr, - struct netlink_ext_ack *extack) -{ - struct flow_action_entry vlan_act = { - .id = FLOW_ACTION_VLAN_POP, - }; - int nest_level, err = 0; - - nest_level = attr->parse_attr->filter_dev->lower_level - - priv->netdev->lower_level; - while (nest_level--) { - err = parse_tc_vlan_action(priv, &vlan_act, attr->esw_attr, - &attr->action, extack); - if (err) - return err; - } - - return err; + mlx5e_same_hw_devs(priv, peer_priv)); } static bool same_hw_reps(struct mlx5e_priv *priv, @@ -3750,7 +3273,7 @@ static bool same_hw_reps(struct mlx5e_priv *priv, return mlx5e_eswitch_rep(priv->netdev) && mlx5e_eswitch_rep(peer_netdev) && - same_hw_devs(priv, peer_priv); + mlx5e_same_hw_devs(priv, peer_priv); } static bool is_lag_dev(struct mlx5e_priv *priv, @@ -3774,66 +3297,6 @@ bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv, same_port_devs(priv, netdev_priv(out_dev)); } -static bool is_duplicated_output_device(struct net_device *dev, - struct net_device *out_dev, - int *ifindexes, int if_count, - struct netlink_ext_ack *extack) -{ - int i; - - for (i = 0; i < if_count; i++) { - if (ifindexes[i] == out_dev->ifindex) { - NL_SET_ERR_MSG_MOD(extack, - "can't duplicate output to same device"); - netdev_err(dev, "can't duplicate output to same device: %s\n", - out_dev->name); - return true; - } - } - - return false; -} - -static int verify_uplink_forwarding(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, - struct net_device *out_dev, - struct netlink_ext_ack *extack) -{ - struct mlx5_esw_flow_attr *attr = flow->attr->esw_attr; - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct mlx5e_rep_priv *rep_priv; - - /* Forwarding non encapsulated traffic between - * uplink ports is allowed only if - * termination_table_raw_traffic cap is set. - * - * Input vport was stored attr->in_rep. - * In LAG case, *priv* is the private data of - * uplink which may be not the input vport. - */ - rep_priv = mlx5e_rep_to_rep_priv(attr->in_rep); - - if (!(mlx5e_eswitch_uplink_rep(rep_priv->netdev) && - mlx5e_eswitch_uplink_rep(out_dev))) - return 0; - - if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, - termination_table_raw_traffic)) { - NL_SET_ERR_MSG_MOD(extack, - "devices are both uplink, can't offload forwarding"); - pr_err("devices %s %s are both uplink, can't offload forwarding\n", - priv->netdev->name, out_dev->name); - return -EOPNOTSUPP; - } else if (out_dev != rep_priv->netdev) { - NL_SET_ERR_MSG_MOD(extack, - "devices are not the same uplink, can't offload forwarding"); - pr_err("devices %s %s are both uplink but not the same, can't offload forwarding\n", - priv->netdev->name, out_dev->name); - return -EOPNOTSUPP; - } - return 0; -} - int mlx5e_set_fwd_to_int_port_actions(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr, int ifindex, @@ -3873,26 +3336,18 @@ int mlx5e_set_fwd_to_int_port_actions(struct mlx5e_priv *priv, return 0; } -static int parse_tc_fdb_actions(struct mlx5e_priv *priv, - struct flow_action *flow_action, - struct mlx5e_tc_flow *flow, - struct netlink_ext_ack *extack) +static int +parse_tc_fdb_actions(struct mlx5e_priv *priv, + struct flow_action *flow_action, + struct mlx5e_tc_flow *flow, + struct netlink_ext_ack *extack) { - struct pedit_headers_action hdrs[2] = {}; - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_tc_act_parse_state *parse_state; struct mlx5e_tc_flow_parse_attr *parse_attr; - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5e_sample_attr sample_attr = {}; - const struct ip_tunnel_info *info = NULL; struct mlx5_flow_attr *attr = flow->attr; - int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS]; - bool ft_flow = mlx5e_is_ft_flow(flow); - const struct flow_action_entry *act; struct mlx5_esw_flow_attr *esw_attr; - bool encap = false, decap = false; - int err, i, if_count = 0; - bool ptype_host = false; - bool mpls_push = false; + struct pedit_headers_action *hdrs; + int err; err = flow_action_supported(flow_action, extack); if (err) @@ -3900,348 +3355,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, esw_attr = attr->esw_attr; parse_attr = attr->parse_attr; + parse_state = &parse_attr->parse_state; + mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack); + parse_state->ct_priv = get_ct_priv(priv); + hdrs = parse_state->hdrs; - flow_action_for_each(i, act, flow_action) { - switch (act->id) { - case FLOW_ACTION_ACCEPT: - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - attr->flags |= MLX5_ESW_ATTR_FLAG_ACCEPT; - break; - case FLOW_ACTION_PTYPE: - if (act->ptype != PACKET_HOST) { - NL_SET_ERR_MSG_MOD(extack, - "skbedit ptype is only supported with type host"); - return -EOPNOTSUPP; - } - - ptype_host = true; - break; - case FLOW_ACTION_DROP: - attr->action |= MLX5_FLOW_CONTEXT_ACTION_DROP | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - break; - case FLOW_ACTION_TRAP: - if (!flow_offload_has_one_action(flow_action)) { - NL_SET_ERR_MSG_MOD(extack, - "action trap is supported as a sole action only"); - return -EOPNOTSUPP; - } - attr->action |= (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT); - attr->flags |= MLX5_ESW_ATTR_FLAG_SLOW_PATH; - break; - case FLOW_ACTION_MPLS_PUSH: - if (!MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, - reformat_l2_to_l3_tunnel) || - act->mpls_push.proto != htons(ETH_P_MPLS_UC)) { - NL_SET_ERR_MSG_MOD(extack, - "mpls push is supported only for mpls_uc protocol"); - return -EOPNOTSUPP; - } - mpls_push = true; - break; - case FLOW_ACTION_MPLS_POP: - /* we only support mpls pop if it is the first action - * and the filter net device is bareudp. Subsequent - * actions can be pedit and the last can be mirred - * egress redirect. - */ - if (i) { - NL_SET_ERR_MSG_MOD(extack, - "mpls pop supported only as first action"); - return -EOPNOTSUPP; - } - if (!netif_is_bareudp(parse_attr->filter_dev)) { - NL_SET_ERR_MSG_MOD(extack, - "mpls pop supported only on bareudp devices"); - return -EOPNOTSUPP; - } - - parse_attr->eth.h_proto = act->mpls_pop.proto; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - flow_flag_set(flow, L3_TO_L2_DECAP); - break; - case FLOW_ACTION_MANGLE: - case FLOW_ACTION_ADD: - err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_FDB, - parse_attr, hdrs, flow, extack); - if (err) - return err; - - if (!flow_flag_test(flow, L3_TO_L2_DECAP)) { - attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - esw_attr->split_count = esw_attr->out_count; - } - break; - case FLOW_ACTION_CSUM: - if (csum_offload_supported(priv, attr->action, - act->csum_flags, extack)) - break; - - return -EOPNOTSUPP; - case FLOW_ACTION_REDIRECT_INGRESS: { - struct net_device *out_dev; - - out_dev = act->dev; - if (!out_dev) - return -EOPNOTSUPP; - - if (!netif_is_ovs_master(out_dev)) { - NL_SET_ERR_MSG_MOD(extack, - "redirect to ingress is supported only for OVS internal ports"); - return -EOPNOTSUPP; - } - - if (netif_is_ovs_master(parse_attr->filter_dev)) { - NL_SET_ERR_MSG_MOD(extack, - "redirect to ingress is not supported from internal port"); - return -EOPNOTSUPP; - } - - if (!ptype_host) { - NL_SET_ERR_MSG_MOD(extack, - "redirect to int port ingress requires ptype=host action"); - return -EOPNOTSUPP; - } - - if (esw_attr->out_count) { - NL_SET_ERR_MSG_MOD(extack, - "redirect to int port ingress is supported only as single destination"); - return -EOPNOTSUPP; - } - - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - - err = mlx5e_set_fwd_to_int_port_actions(priv, attr, out_dev->ifindex, - MLX5E_TC_INT_PORT_INGRESS, - &attr->action, esw_attr->out_count); - if (err) - return err; - - esw_attr->out_count++; - - break; - } - case FLOW_ACTION_REDIRECT: - case FLOW_ACTION_MIRRED: { - struct mlx5e_priv *out_priv; - struct net_device *out_dev; - - out_dev = act->dev; - if (!out_dev) { - /* out_dev is NULL when filters with - * non-existing mirred device are replayed to - * the driver. - */ - return -EINVAL; - } - - if (mpls_push && !netif_is_bareudp(out_dev)) { - NL_SET_ERR_MSG_MOD(extack, - "mpls is supported only through a bareudp device"); - return -EOPNOTSUPP; - } - - if (ft_flow && out_dev == priv->netdev) { - /* Ignore forward to self rules generated - * by adding both mlx5 devs to the flow table - * block on a normal nft offload setup. - */ - return -EOPNOTSUPP; - } - - if (esw_attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) { - NL_SET_ERR_MSG_MOD(extack, - "can't support more output ports, can't offload forwarding"); - netdev_warn(priv->netdev, - "can't support more than %d output ports, can't offload forwarding\n", - esw_attr->out_count); - return -EOPNOTSUPP; - } - - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - if (encap) { - parse_attr->mirred_ifindex[esw_attr->out_count] = - out_dev->ifindex; - parse_attr->tun_info[esw_attr->out_count] = - mlx5e_dup_tun_info(info); - if (!parse_attr->tun_info[esw_attr->out_count]) - return -ENOMEM; - encap = false; - esw_attr->dests[esw_attr->out_count].flags |= - MLX5_ESW_DEST_ENCAP; - esw_attr->out_count++; - /* attr->dests[].rep is resolved when we - * handle encap - */ - } else if (netdev_port_same_parent_id(priv->netdev, out_dev)) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); - - if (is_duplicated_output_device(priv->netdev, - out_dev, - ifindexes, - if_count, - extack)) - return -EOPNOTSUPP; - - ifindexes[if_count] = out_dev->ifindex; - if_count++; - - out_dev = get_fdb_out_dev(uplink_dev, out_dev); - if (!out_dev) - return -ENODEV; - - if (is_vlan_dev(out_dev)) { - err = add_vlan_push_action(priv, attr, &out_dev, extack); - if (err) - return err; - } - - if (is_vlan_dev(parse_attr->filter_dev)) { - err = add_vlan_pop_action(priv, attr, extack); - if (err) - return err; - } - - if (netif_is_macvlan(out_dev)) - out_dev = macvlan_dev_real_dev(out_dev); - - err = verify_uplink_forwarding(priv, flow, out_dev, extack); - if (err) - return err; - - if (!mlx5e_is_valid_eswitch_fwd_dev(priv, out_dev)) { - NL_SET_ERR_MSG_MOD(extack, - "devices are not on same switch HW, can't offload forwarding"); - return -EOPNOTSUPP; - } - - if (same_vf_reps(priv, out_dev)) { - NL_SET_ERR_MSG_MOD(extack, - "can't forward from a VF to itself"); - return -EOPNOTSUPP; - } - - out_priv = netdev_priv(out_dev); - rpriv = out_priv->ppriv; - esw_attr->dests[esw_attr->out_count].rep = rpriv->rep; - esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev; - esw_attr->out_count++; - } else if (netif_is_ovs_master(out_dev)) { - err = mlx5e_set_fwd_to_int_port_actions(priv, attr, - out_dev->ifindex, - MLX5E_TC_INT_PORT_EGRESS, - &attr->action, - esw_attr->out_count); - if (err) - return err; - - esw_attr->out_count++; - } else if (parse_attr->filter_dev != priv->netdev) { - /* All mlx5 devices are called to configure - * high level device filters. Therefore, the - * *attempt* to install a filter on invalid - * eswitch should not trigger an explicit error - */ - return -EINVAL; - } else { - NL_SET_ERR_MSG_MOD(extack, - "devices are not on same switch HW, can't offload forwarding"); - netdev_warn(priv->netdev, - "devices %s %s not on same switch HW, can't offload forwarding\n", - priv->netdev->name, - out_dev->name); - return -EOPNOTSUPP; - } - } - break; - case FLOW_ACTION_TUNNEL_ENCAP: - info = act->tunnel; - if (info) { - encap = true; - } else { - NL_SET_ERR_MSG_MOD(extack, - "Zero tunnel attributes is not supported"); - return -EOPNOTSUPP; - } - - break; - case FLOW_ACTION_VLAN_PUSH: - case FLOW_ACTION_VLAN_POP: - if (act->id == FLOW_ACTION_VLAN_PUSH && - (attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP)) { - /* Replace vlan pop+push with vlan modify */ - attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; - err = add_vlan_rewrite_action(priv, - MLX5_FLOW_NAMESPACE_FDB, - act, parse_attr, hdrs, - &attr->action, extack); - } else { - err = parse_tc_vlan_action(priv, act, esw_attr, &attr->action, - extack); - } - if (err) - return err; - - esw_attr->split_count = esw_attr->out_count; - break; - case FLOW_ACTION_VLAN_MANGLE: - err = add_vlan_rewrite_action(priv, - MLX5_FLOW_NAMESPACE_FDB, - act, parse_attr, hdrs, - &attr->action, extack); - if (err) - return err; - - esw_attr->split_count = esw_attr->out_count; - break; - case FLOW_ACTION_TUNNEL_DECAP: - decap = true; - break; - case FLOW_ACTION_GOTO: - err = validate_goto_chain(priv, flow, act, extack); - if (err) - return err; - - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - attr->dest_chain = act->chain_index; - break; - case FLOW_ACTION_CT: - if (flow_flag_test(flow, SAMPLE)) { - NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported"); - return -EOPNOTSUPP; - } - err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, - &parse_attr->mod_hdr_acts, - act, extack); - if (err) - return err; - - flow_flag_set(flow, CT); - esw_attr->split_count = esw_attr->out_count; - break; - case FLOW_ACTION_SAMPLE: - if (flow_flag_test(flow, CT)) { - NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported"); - return -EOPNOTSUPP; - } - sample_attr.rate = act->sample.rate; - sample_attr.group_num = act->sample.psample_group->group_num; - if (act->sample.truncate) - sample_attr.trunc_size = act->sample.trunc_size; - flow_flag_set(flow, SAMPLE); - break; - default: - NL_SET_ERR_MSG_MOD(extack, - "The offload action is not supported in FDB action"); - return -EOPNOTSUPP; - } - } + err = parse_tc_actions(parse_state, flow_action); + if (err) + return err; /* Forward to/from internal port can only have 1 dest */ if ((netif_is_ovs_master(parse_attr->filter_dev) || esw_attr->dest_int_port) && @@ -4251,18 +3372,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (MLX5_CAP_GEN(esw->dev, prio_tag_required) && - attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) { - /* For prio tag mode, replace vlan pop with rewrite vlan prio - * tag rewrite. - */ - attr->action &= ~MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; - err = add_vlan_prio_tag_rewrite_action(priv, parse_attr, hdrs, - &attr->action, extack); - if (err) - return err; - } - err = actions_prepare_mod_hdr_actions(priv, flow, attr, hdrs, extack); if (err) return err; @@ -4270,30 +3379,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) return -EOPNOTSUPP; - if (attr->dest_chain && decap) { - /* It can be supported if we'll create a mapping for - * the tunnel device only (without tunnel), and set - * this tunnel id with this decap flow. - * - * On restore (miss), we'll just set this saved tunnel - * device. - */ - - NL_SET_ERR_MSG(extack, "Decap with goto isn't supported"); - netdev_warn(priv->netdev, "Decap with goto isn't supported"); - return -EOPNOTSUPP; - } - - /* Allocate sample attribute only when there is a sample action and - * no errors after parsing. - */ - if (flow_flag_test(flow, SAMPLE)) { - attr->sample_attr = kzalloc(sizeof(*attr->sample_attr), GFP_KERNEL); - if (!attr->sample_attr) - return -ENOMEM; - *attr->sample_attr = sample_attr; - } - return 0; } @@ -4390,7 +3475,7 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, flow->cookie = f->cookie; flow->priv = priv; - attr = mlx5_alloc_flow_attr(get_flow_name_space(flow)); + attr = mlx5_alloc_flow_attr(mlx5e_get_flow_namespace(flow)); if (!attr) goto err_free; @@ -4992,7 +4077,7 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, u16 peer_vhca_id; int bkt; - if (!same_hw_devs(priv, peer_priv)) + if (!mlx5e_same_hw_devs(priv, peer_priv)) return; peer_vhca_id = MLX5_CAP_GEN(peer_mdev, vhca_id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index eb042f0f5a41..5ffae9b13066 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -151,7 +151,6 @@ enum { int mlx5e_tc_esw_init(struct rhashtable *tc_ht); void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht); -bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow); int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, struct flow_cls_offload *f, unsigned long flags); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 750b21124a1a..762b9730a897 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -788,7 +788,8 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, int err; u32 *in; - if (namespace == MLX5_FLOW_NAMESPACE_FDB) + if (namespace == MLX5_FLOW_NAMESPACE_FDB || + namespace == MLX5_FLOW_NAMESPACE_FDB_BYPASS) max_encap_size = MLX5_CAP_ESW(dev, max_encap_header_size); else max_encap_size = MLX5_CAP_FLOWTABLE(dev, max_encap_header_size); @@ -860,6 +861,7 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns, switch (namespace) { case MLX5_FLOW_NAMESPACE_FDB: + case MLX5_FLOW_NAMESPACE_FDB_BYPASS: max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(dev, max_modify_header_actions); table_type = FS_FT_FDB; break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 386ab9a2d490..a8671d7b7ca8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2206,6 +2206,22 @@ struct mlx5_flow_namespace *mlx5_get_fdb_sub_ns(struct mlx5_core_dev *dev, } EXPORT_SYMBOL(mlx5_get_fdb_sub_ns); +static bool is_nic_rx_ns(enum mlx5_flow_namespace_type type) +{ + switch (type) { + case MLX5_FLOW_NAMESPACE_BYPASS: + case MLX5_FLOW_NAMESPACE_LAG: + case MLX5_FLOW_NAMESPACE_OFFLOADS: + case MLX5_FLOW_NAMESPACE_ETHTOOL: + case MLX5_FLOW_NAMESPACE_KERNEL: + case MLX5_FLOW_NAMESPACE_LEFTOVERS: + case MLX5_FLOW_NAMESPACE_ANCHOR: + return true; + default: + return false; + } +} + struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type) { @@ -2235,31 +2251,39 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, if (steering->sniffer_tx_root_ns) return &steering->sniffer_tx_root_ns->ns; return NULL; - default: + case MLX5_FLOW_NAMESPACE_FDB_BYPASS: + root_ns = steering->fdb_root_ns; + prio = FDB_BYPASS_PATH; break; - } - - if (type == MLX5_FLOW_NAMESPACE_EGRESS || - type == MLX5_FLOW_NAMESPACE_EGRESS_KERNEL) { + case MLX5_FLOW_NAMESPACE_EGRESS: + case MLX5_FLOW_NAMESPACE_EGRESS_KERNEL: root_ns = steering->egress_root_ns; prio = type - MLX5_FLOW_NAMESPACE_EGRESS; - } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX) { + break; + case MLX5_FLOW_NAMESPACE_RDMA_RX: root_ns = steering->rdma_rx_root_ns; prio = RDMA_RX_BYPASS_PRIO; - } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL) { + break; + case MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL: root_ns = steering->rdma_rx_root_ns; prio = RDMA_RX_KERNEL_PRIO; - } else if (type == MLX5_FLOW_NAMESPACE_RDMA_TX) { + break; + case MLX5_FLOW_NAMESPACE_RDMA_TX: root_ns = steering->rdma_tx_root_ns; - } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS) { + break; + case MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS: root_ns = steering->rdma_rx_root_ns; prio = RDMA_RX_COUNTERS_PRIO; - } else if (type == MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS) { + break; + case MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS: root_ns = steering->rdma_tx_root_ns; prio = RDMA_TX_COUNTERS_PRIO; - } else { /* Must be NIC RX */ + break; + default: /* Must be NIC RX */ + WARN_ON(!is_nic_rx_ns(type)); root_ns = steering->root_ns; prio = type; + break; } if (!root_ns) @@ -2822,6 +2846,28 @@ static int create_fdb_fast_path(struct mlx5_flow_steering *steering) return 0; } +static int create_fdb_bypass(struct mlx5_flow_steering *steering) +{ + struct mlx5_flow_namespace *ns; + struct fs_prio *prio; + int i; + + prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BYPASS_PATH, 0); + if (IS_ERR(prio)) + return PTR_ERR(prio); + + ns = fs_create_namespace(prio, MLX5_FLOW_TABLE_MISS_ACTION_DEF); + if (IS_ERR(ns)) + return PTR_ERR(ns); + + for (i = 0; i < MLX5_BY_PASS_NUM_REGULAR_PRIOS; i++) { + prio = fs_create_prio(ns, i, 1); + if (IS_ERR(prio)) + return PTR_ERR(prio); + } + return 0; +} + static int init_fdb_root_ns(struct mlx5_flow_steering *steering) { struct fs_prio *maj_prio; @@ -2831,12 +2877,10 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) if (!steering->fdb_root_ns) return -ENOMEM; - maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BYPASS_PATH, - 1); - if (IS_ERR(maj_prio)) { - err = PTR_ERR(maj_prio); + err = create_fdb_bypass(steering); + if (err) goto out_err; - } + err = create_fdb_fast_path(steering); if (err) goto out_err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 5eaba2abf212..f748b537bdab 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -504,19 +504,43 @@ static inline void mlxsw_reg_sfd_uc_tunnel_pack(char *payload, int rec_index, enum mlxsw_reg_sfd_rec_policy policy, const char *mac, u16 fid, - enum mlxsw_reg_sfd_rec_action action, u32 uip, + enum mlxsw_reg_sfd_rec_action action, enum mlxsw_reg_sfd_uc_tunnel_protocol proto) { mlxsw_reg_sfd_rec_pack(payload, rec_index, MLXSW_REG_SFD_REC_TYPE_UNICAST_TUNNEL, mac, action); mlxsw_reg_sfd_rec_policy_set(payload, rec_index, policy); - mlxsw_reg_sfd_uc_tunnel_uip_msb_set(payload, rec_index, uip >> 24); - mlxsw_reg_sfd_uc_tunnel_uip_lsb_set(payload, rec_index, uip); mlxsw_reg_sfd_uc_tunnel_fid_set(payload, rec_index, fid); mlxsw_reg_sfd_uc_tunnel_protocol_set(payload, rec_index, proto); } +static inline void +mlxsw_reg_sfd_uc_tunnel_pack4(char *payload, int rec_index, + enum mlxsw_reg_sfd_rec_policy policy, + const char *mac, u16 fid, + enum mlxsw_reg_sfd_rec_action action, u32 uip) +{ + mlxsw_reg_sfd_uc_tunnel_uip_msb_set(payload, rec_index, uip >> 24); + mlxsw_reg_sfd_uc_tunnel_uip_lsb_set(payload, rec_index, uip); + mlxsw_reg_sfd_uc_tunnel_pack(payload, rec_index, policy, mac, fid, + action, + MLXSW_REG_SFD_UC_TUNNEL_PROTOCOL_IPV4); +} + +static inline void +mlxsw_reg_sfd_uc_tunnel_pack6(char *payload, int rec_index, const char *mac, + u16 fid, enum mlxsw_reg_sfd_rec_action action, + u32 uip_ptr) +{ + mlxsw_reg_sfd_uc_tunnel_uip_lsb_set(payload, rec_index, uip_ptr); + /* Only static policy is supported for IPv6 unicast tunnel entry. */ + mlxsw_reg_sfd_uc_tunnel_pack(payload, rec_index, + MLXSW_REG_SFD_REC_POLICY_STATIC_ENTRY, + mac, fid, action, + MLXSW_REG_SFD_UC_TUNNEL_PROTOCOL_IPV6); +} + enum mlxsw_reg_tunnel_port { MLXSW_REG_TUNNEL_PORT_NVE, MLXSW_REG_TUNNEL_PORT_VPLS, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index fb06b2ddfd6d..5251f33af0fb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2755,6 +2755,140 @@ static void mlxsw_sp_parsing_fini(struct mlxsw_sp *mlxsw_sp) mutex_destroy(&mlxsw_sp->parsing.lock); } +struct mlxsw_sp_ipv6_addr_node { + struct in6_addr key; + struct rhash_head ht_node; + u32 kvdl_index; + refcount_t refcount; +}; + +static const struct rhashtable_params mlxsw_sp_ipv6_addr_ht_params = { + .key_offset = offsetof(struct mlxsw_sp_ipv6_addr_node, key), + .head_offset = offsetof(struct mlxsw_sp_ipv6_addr_node, ht_node), + .key_len = sizeof(struct in6_addr), + .automatic_shrinking = true, +}; + +static int +mlxsw_sp_ipv6_addr_init(struct mlxsw_sp *mlxsw_sp, const struct in6_addr *addr6, + u32 *p_kvdl_index) +{ + struct mlxsw_sp_ipv6_addr_node *node; + char rips_pl[MLXSW_REG_RIPS_LEN]; + int err; + + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, + MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, + p_kvdl_index); + if (err) + return err; + + mlxsw_reg_rips_pack(rips_pl, *p_kvdl_index, addr6); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rips), rips_pl); + if (err) + goto err_rips_write; + + node = kzalloc(sizeof(*node), GFP_KERNEL); + if (!node) { + err = -ENOMEM; + goto err_node_alloc; + } + + node->key = *addr6; + node->kvdl_index = *p_kvdl_index; + refcount_set(&node->refcount, 1); + + err = rhashtable_insert_fast(&mlxsw_sp->ipv6_addr_ht, + &node->ht_node, + mlxsw_sp_ipv6_addr_ht_params); + if (err) + goto err_rhashtable_insert; + + return 0; + +err_rhashtable_insert: + kfree(node); +err_node_alloc: +err_rips_write: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, + *p_kvdl_index); + return err; +} + +static void mlxsw_sp_ipv6_addr_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipv6_addr_node *node) +{ + u32 kvdl_index = node->kvdl_index; + + rhashtable_remove_fast(&mlxsw_sp->ipv6_addr_ht, &node->ht_node, + mlxsw_sp_ipv6_addr_ht_params); + kfree(node); + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, + kvdl_index); +} + +int mlxsw_sp_ipv6_addr_kvdl_index_get(struct mlxsw_sp *mlxsw_sp, + const struct in6_addr *addr6, + u32 *p_kvdl_index) +{ + struct mlxsw_sp_ipv6_addr_node *node; + int err = 0; + + mutex_lock(&mlxsw_sp->ipv6_addr_ht_lock); + node = rhashtable_lookup_fast(&mlxsw_sp->ipv6_addr_ht, addr6, + mlxsw_sp_ipv6_addr_ht_params); + if (node) { + refcount_inc(&node->refcount); + *p_kvdl_index = node->kvdl_index; + goto out_unlock; + } + + err = mlxsw_sp_ipv6_addr_init(mlxsw_sp, addr6, p_kvdl_index); + +out_unlock: + mutex_unlock(&mlxsw_sp->ipv6_addr_ht_lock); + return err; +} + +void +mlxsw_sp_ipv6_addr_put(struct mlxsw_sp *mlxsw_sp, const struct in6_addr *addr6) +{ + struct mlxsw_sp_ipv6_addr_node *node; + + mutex_lock(&mlxsw_sp->ipv6_addr_ht_lock); + node = rhashtable_lookup_fast(&mlxsw_sp->ipv6_addr_ht, addr6, + mlxsw_sp_ipv6_addr_ht_params); + if (WARN_ON(!node)) + goto out_unlock; + + if (!refcount_dec_and_test(&node->refcount)) + goto out_unlock; + + mlxsw_sp_ipv6_addr_fini(mlxsw_sp, node); + +out_unlock: + mutex_unlock(&mlxsw_sp->ipv6_addr_ht_lock); +} + +static int mlxsw_sp_ipv6_addr_ht_init(struct mlxsw_sp *mlxsw_sp) +{ + int err; + + err = rhashtable_init(&mlxsw_sp->ipv6_addr_ht, + &mlxsw_sp_ipv6_addr_ht_params); + if (err) + return err; + + mutex_init(&mlxsw_sp->ipv6_addr_ht_lock); + return 0; +} + +static void mlxsw_sp_ipv6_addr_ht_fini(struct mlxsw_sp *mlxsw_sp) +{ + mutex_destroy(&mlxsw_sp->ipv6_addr_ht_lock); + rhashtable_destroy(&mlxsw_sp->ipv6_addr_ht); +} + static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, const struct mlxsw_bus_info *mlxsw_bus_info, struct netlink_ext_ack *extack) @@ -2843,6 +2977,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_afa_init; } + err = mlxsw_sp_ipv6_addr_ht_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize hash table for IPv6 addresses\n"); + goto err_ipv6_addr_ht_init; + } + err = mlxsw_sp_nve_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize NVE\n"); @@ -2944,6 +3084,8 @@ err_router_init: err_acl_init: mlxsw_sp_nve_fini(mlxsw_sp); err_nve_init: + mlxsw_sp_ipv6_addr_ht_fini(mlxsw_sp); +err_ipv6_addr_ht_init: mlxsw_sp_afa_fini(mlxsw_sp); err_afa_init: mlxsw_sp_counter_pool_fini(mlxsw_sp); @@ -3075,6 +3217,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_router_fini(mlxsw_sp); mlxsw_sp_acl_fini(mlxsw_sp); mlxsw_sp_nve_fini(mlxsw_sp); + mlxsw_sp_ipv6_addr_ht_fini(mlxsw_sp); mlxsw_sp_afa_fini(mlxsw_sp); mlxsw_sp_counter_pool_fini(mlxsw_sp); mlxsw_sp_switchdev_fini(mlxsw_sp); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index ef4188e203a0..8445fc5c9ea3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -203,6 +203,8 @@ struct mlxsw_sp { const struct mlxsw_listener *listeners; size_t listeners_count; u32 lowest_shaper_bs; + struct rhashtable ipv6_addr_ht; + struct mutex ipv6_addr_ht_lock; /* Protects ipv6_addr_ht */ }; struct mlxsw_sp_ptp_ops { @@ -587,6 +589,11 @@ mlxsw_sp_sample_trigger_params_set(struct mlxsw_sp *mlxsw_sp, void mlxsw_sp_sample_trigger_params_unset(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_sample_trigger *trigger); +int mlxsw_sp_ipv6_addr_kvdl_index_get(struct mlxsw_sp *mlxsw_sp, + const struct in6_addr *addr6, + u32 *p_kvdl_index); +void +mlxsw_sp_ipv6_addr_put(struct mlxsw_sp *mlxsw_sp, const struct in6_addr *addr6); extern const struct mlxsw_sp_sb_vals mlxsw_sp1_sb_vals; extern const struct mlxsw_sp_sb_vals mlxsw_sp2_sb_vals; @@ -1310,6 +1317,17 @@ void mlxsw_sp_nve_flood_ip_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid, enum mlxsw_sp_l3proto proto, union mlxsw_sp_l3addr *addr); +int mlxsw_sp_nve_ipv6_addr_kvdl_set(struct mlxsw_sp *mlxsw_sp, + const struct in6_addr *addr6, + u32 *p_kvdl_index); +void mlxsw_sp_nve_ipv6_addr_kvdl_unset(struct mlxsw_sp *mlxsw_sp, + const struct in6_addr *addr6); +int +mlxsw_sp_nve_ipv6_addr_map_replace(struct mlxsw_sp *mlxsw_sp, const char *mac, + u16 fid_index, + const struct in6_addr *new_addr6); +void mlxsw_sp_nve_ipv6_addr_map_del(struct mlxsw_sp *mlxsw_sp, const char *mac, + u16 fid_index); int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid, struct mlxsw_sp_nve_params *params, struct netlink_ext_ack *extack); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index ad3926de88f2..01cf5a6a26bd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -568,37 +568,21 @@ static int mlxsw_sp2_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry) { - char rips_pl[MLXSW_REG_RIPS_LEN]; struct __ip6_tnl_parm parms6; - int err; - - err = mlxsw_sp_kvdl_alloc(mlxsw_sp, - MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, - &ipip_entry->dip_kvdl_index); - if (err) - return err; parms6 = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); - mlxsw_reg_rips_pack(rips_pl, ipip_entry->dip_kvdl_index, - &parms6.raddr); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rips), rips_pl); - if (err) - goto err_rips_write; - - return 0; - -err_rips_write: - mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, - ipip_entry->dip_kvdl_index); - return err; + return mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp, &parms6.raddr, + &ipip_entry->dip_kvdl_index); } static void mlxsw_sp2_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_ipip_entry *ipip_entry) { - mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, - ipip_entry->dip_kvdl_index); + struct __ip6_tnl_parm parms6; + + parms6 = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); + mlxsw_sp_ipv6_addr_put(mlxsw_sp, &parms6.raddr); } static const struct mlxsw_sp_ipip_ops mlxsw_sp2_ipip_gre6_ops = { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index 9eba8fa684ae..d2b57a045aa4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -130,15 +130,25 @@ mlxsw_sp_nve_mc_record_ipv6_entry_add(struct mlxsw_sp_nve_mc_record *mc_record, struct mlxsw_sp_nve_mc_entry *mc_entry, const union mlxsw_sp_l3addr *addr) { - WARN_ON(1); + u32 kvdl_index; + int err; + + err = mlxsw_sp_ipv6_addr_kvdl_index_get(mc_record->mlxsw_sp, + &addr->addr6, &kvdl_index); + if (err) + return err; - return -EINVAL; + mc_entry->ipv6_entry.addr6 = addr->addr6; + mc_entry->ipv6_entry.addr6_kvdl_index = kvdl_index; + return 0; } static void mlxsw_sp_nve_mc_record_ipv6_entry_del(const struct mlxsw_sp_nve_mc_record *mc_record, const struct mlxsw_sp_nve_mc_entry *mc_entry) { + mlxsw_sp_ipv6_addr_put(mc_record->mlxsw_sp, + &mc_entry->ipv6_entry.addr6); } static void @@ -787,6 +797,142 @@ static void mlxsw_sp_nve_fdb_clear_offload(struct mlxsw_sp *mlxsw_sp, ops->fdb_clear_offload(nve_dev, vni); } +struct mlxsw_sp_nve_ipv6_ht_key { + u8 mac[ETH_ALEN]; + u16 fid_index; +}; + +struct mlxsw_sp_nve_ipv6_ht_node { + struct rhash_head ht_node; + struct list_head list; + struct mlxsw_sp_nve_ipv6_ht_key key; + struct in6_addr addr6; +}; + +static const struct rhashtable_params mlxsw_sp_nve_ipv6_ht_params = { + .key_len = sizeof(struct mlxsw_sp_nve_ipv6_ht_key), + .key_offset = offsetof(struct mlxsw_sp_nve_ipv6_ht_node, key), + .head_offset = offsetof(struct mlxsw_sp_nve_ipv6_ht_node, ht_node), +}; + +int mlxsw_sp_nve_ipv6_addr_kvdl_set(struct mlxsw_sp *mlxsw_sp, + const struct in6_addr *addr6, + u32 *p_kvdl_index) +{ + return mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp, addr6, p_kvdl_index); +} + +void mlxsw_sp_nve_ipv6_addr_kvdl_unset(struct mlxsw_sp *mlxsw_sp, + const struct in6_addr *addr6) +{ + mlxsw_sp_ipv6_addr_put(mlxsw_sp, addr6); +} + +static struct mlxsw_sp_nve_ipv6_ht_node * +mlxsw_sp_nve_ipv6_ht_node_lookup(struct mlxsw_sp *mlxsw_sp, const char *mac, + u16 fid_index) +{ + struct mlxsw_sp_nve_ipv6_ht_key key = {}; + + ether_addr_copy(key.mac, mac); + key.fid_index = fid_index; + return rhashtable_lookup_fast(&mlxsw_sp->nve->ipv6_ht, &key, + mlxsw_sp_nve_ipv6_ht_params); +} + +static int mlxsw_sp_nve_ipv6_ht_insert(struct mlxsw_sp *mlxsw_sp, + const char *mac, u16 fid_index, + const struct in6_addr *addr6) +{ + struct mlxsw_sp_nve_ipv6_ht_node *ipv6_ht_node; + struct mlxsw_sp_nve *nve = mlxsw_sp->nve; + int err; + + ipv6_ht_node = kzalloc(sizeof(*ipv6_ht_node), GFP_KERNEL); + if (!ipv6_ht_node) + return -ENOMEM; + + ether_addr_copy(ipv6_ht_node->key.mac, mac); + ipv6_ht_node->key.fid_index = fid_index; + ipv6_ht_node->addr6 = *addr6; + + err = rhashtable_insert_fast(&nve->ipv6_ht, &ipv6_ht_node->ht_node, + mlxsw_sp_nve_ipv6_ht_params); + if (err) + goto err_rhashtable_insert; + + list_add(&ipv6_ht_node->list, &nve->ipv6_addr_list); + + return 0; + +err_rhashtable_insert: + kfree(ipv6_ht_node); + return err; +} + +static void +mlxsw_sp_nve_ipv6_ht_remove(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_nve_ipv6_ht_node *ipv6_ht_node) +{ + struct mlxsw_sp_nve *nve = mlxsw_sp->nve; + + list_del(&ipv6_ht_node->list); + rhashtable_remove_fast(&nve->ipv6_ht, &ipv6_ht_node->ht_node, + mlxsw_sp_nve_ipv6_ht_params); + kfree(ipv6_ht_node); +} + +int +mlxsw_sp_nve_ipv6_addr_map_replace(struct mlxsw_sp *mlxsw_sp, const char *mac, + u16 fid_index, + const struct in6_addr *new_addr6) +{ + struct mlxsw_sp_nve_ipv6_ht_node *ipv6_ht_node; + + ASSERT_RTNL(); + + ipv6_ht_node = mlxsw_sp_nve_ipv6_ht_node_lookup(mlxsw_sp, mac, + fid_index); + if (!ipv6_ht_node) + return mlxsw_sp_nve_ipv6_ht_insert(mlxsw_sp, mac, fid_index, + new_addr6); + + mlxsw_sp_ipv6_addr_put(mlxsw_sp, &ipv6_ht_node->addr6); + ipv6_ht_node->addr6 = *new_addr6; + return 0; +} + +void mlxsw_sp_nve_ipv6_addr_map_del(struct mlxsw_sp *mlxsw_sp, const char *mac, + u16 fid_index) +{ + struct mlxsw_sp_nve_ipv6_ht_node *ipv6_ht_node; + + ASSERT_RTNL(); + + ipv6_ht_node = mlxsw_sp_nve_ipv6_ht_node_lookup(mlxsw_sp, mac, + fid_index); + if (WARN_ON(!ipv6_ht_node)) + return; + + mlxsw_sp_nve_ipv6_ht_remove(mlxsw_sp, ipv6_ht_node); +} + +static void mlxsw_sp_nve_ipv6_addr_flush_by_fid(struct mlxsw_sp *mlxsw_sp, + u16 fid_index) +{ + struct mlxsw_sp_nve_ipv6_ht_node *ipv6_ht_node, *tmp; + struct mlxsw_sp_nve *nve = mlxsw_sp->nve; + + list_for_each_entry_safe(ipv6_ht_node, tmp, &nve->ipv6_addr_list, + list) { + if (ipv6_ht_node->key.fid_index != fid_index) + continue; + + mlxsw_sp_ipv6_addr_put(mlxsw_sp, &ipv6_ht_node->addr6); + mlxsw_sp_nve_ipv6_ht_remove(mlxsw_sp, ipv6_ht_node); + } +} + int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid, struct mlxsw_sp_nve_params *params, struct netlink_ext_ack *extack) @@ -845,6 +991,7 @@ void mlxsw_sp_nve_fid_disable(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nve_flood_ip_flush(mlxsw_sp, fid); mlxsw_sp_nve_fdb_flush_by_fid(mlxsw_sp, fid_index); + mlxsw_sp_nve_ipv6_addr_flush_by_fid(mlxsw_sp, fid_index); if (WARN_ON(mlxsw_sp_fid_nve_ifindex(fid, &nve_ifindex) || mlxsw_sp_fid_vni(fid, &vni))) @@ -981,7 +1128,13 @@ int mlxsw_sp_nve_init(struct mlxsw_sp *mlxsw_sp) err = rhashtable_init(&nve->mc_list_ht, &mlxsw_sp_nve_mc_list_ht_params); if (err) - goto err_rhashtable_init; + goto err_mc_rhashtable_init; + + err = rhashtable_init(&nve->ipv6_ht, &mlxsw_sp_nve_ipv6_ht_params); + if (err) + goto err_ipv6_rhashtable_init; + + INIT_LIST_HEAD(&nve->ipv6_addr_list); err = mlxsw_sp_nve_qos_init(mlxsw_sp); if (err) @@ -1000,8 +1153,10 @@ int mlxsw_sp_nve_init(struct mlxsw_sp *mlxsw_sp) err_nve_resources_query: err_nve_ecn_init: err_nve_qos_init: + rhashtable_destroy(&nve->ipv6_ht); +err_ipv6_rhashtable_init: rhashtable_destroy(&nve->mc_list_ht); -err_rhashtable_init: +err_mc_rhashtable_init: mlxsw_sp->nve = NULL; kfree(nve); return err; @@ -1010,6 +1165,8 @@ err_rhashtable_init: void mlxsw_sp_nve_fini(struct mlxsw_sp *mlxsw_sp) { WARN_ON(mlxsw_sp->nve->num_nve_tunnels); + WARN_ON(!list_empty(&mlxsw_sp->nve->ipv6_addr_list)); + rhashtable_destroy(&mlxsw_sp->nve->ipv6_ht); rhashtable_destroy(&mlxsw_sp->nve->mc_list_ht); kfree(mlxsw_sp->nve); mlxsw_sp->nve = NULL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h index 98d1fdc25eac..0d21de1d0395 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h @@ -23,6 +23,8 @@ struct mlxsw_sp_nve_config { struct mlxsw_sp_nve { struct mlxsw_sp_nve_config config; struct rhashtable mc_list_ht; + struct rhashtable ipv6_ht; + struct list_head ipv6_addr_list; /* Saves hash table nodes. */ struct mlxsw_sp *mlxsw_sp; const struct mlxsw_sp_nve_ops **nve_ops_arr; unsigned int num_nve_tunnels; /* Protected by RTNL */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c index d018d2da5949..d309b77a0194 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c @@ -10,8 +10,48 @@ #include "spectrum.h" #include "spectrum_nve.h" -#define MLXSW_SP_NVE_VXLAN_SUPPORTED_FLAGS (VXLAN_F_UDP_ZERO_CSUM_TX | \ +#define MLXSW_SP_NVE_VXLAN_IPV4_SUPPORTED_FLAGS (VXLAN_F_UDP_ZERO_CSUM_TX | \ VXLAN_F_LEARN) +#define MLXSW_SP_NVE_VXLAN_IPV6_SUPPORTED_FLAGS (VXLAN_F_IPV6 | \ + VXLAN_F_UDP_ZERO_CSUM6_TX | \ + VXLAN_F_UDP_ZERO_CSUM6_RX) + +static bool mlxsw_sp_nve_vxlan_ipv4_flags_check(const struct vxlan_config *cfg, + struct netlink_ext_ack *extack) +{ + if (!(cfg->flags & VXLAN_F_UDP_ZERO_CSUM_TX)) { + NL_SET_ERR_MSG_MOD(extack, "VxLAN: Zero UDP checksum must be allowed for TX"); + return false; + } + + if (cfg->flags & ~MLXSW_SP_NVE_VXLAN_IPV4_SUPPORTED_FLAGS) { + NL_SET_ERR_MSG_MOD(extack, "VxLAN: Unsupported flag"); + return false; + } + + return true; +} + +static bool mlxsw_sp_nve_vxlan_ipv6_flags_check(const struct vxlan_config *cfg, + struct netlink_ext_ack *extack) +{ + if (!(cfg->flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) { + NL_SET_ERR_MSG_MOD(extack, "VxLAN: Zero UDP checksum must be allowed for TX"); + return false; + } + + if (!(cfg->flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) { + NL_SET_ERR_MSG_MOD(extack, "VxLAN: Zero UDP checksum must be allowed for RX"); + return false; + } + + if (cfg->flags & ~MLXSW_SP_NVE_VXLAN_IPV6_SUPPORTED_FLAGS) { + NL_SET_ERR_MSG_MOD(extack, "VxLAN: Unsupported flag"); + return false; + } + + return true; +} static bool mlxsw_sp_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve, const struct mlxsw_sp_nve_params *params, @@ -20,11 +60,6 @@ static bool mlxsw_sp_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve, struct vxlan_dev *vxlan = netdev_priv(params->dev); struct vxlan_config *cfg = &vxlan->cfg; - if (cfg->saddr.sa.sa_family != AF_INET) { - NL_SET_ERR_MSG_MOD(extack, "VxLAN: Only IPv4 underlay is supported"); - return false; - } - if (vxlan_addr_multicast(&cfg->remote_ip)) { NL_SET_ERR_MSG_MOD(extack, "VxLAN: Multicast destination IP is not supported"); return false; @@ -55,14 +90,15 @@ static bool mlxsw_sp_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve, return false; } - if (!(cfg->flags & VXLAN_F_UDP_ZERO_CSUM_TX)) { - NL_SET_ERR_MSG_MOD(extack, "VxLAN: UDP checksum is not supported"); - return false; - } - - if (cfg->flags & ~MLXSW_SP_NVE_VXLAN_SUPPORTED_FLAGS) { - NL_SET_ERR_MSG_MOD(extack, "VxLAN: Unsupported flag"); - return false; + switch (cfg->saddr.sa.sa_family) { + case AF_INET: + if (!mlxsw_sp_nve_vxlan_ipv4_flags_check(cfg, extack)) + return false; + break; + case AF_INET6: + if (!mlxsw_sp_nve_vxlan_ipv6_flags_check(cfg, extack)) + return false; + break; } if (cfg->ttl == 0) { @@ -90,6 +126,22 @@ static bool mlxsw_sp1_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve, return mlxsw_sp_nve_vxlan_can_offload(nve, params, extack); } +static void +mlxsw_sp_nve_vxlan_ul_proto_sip_config(const struct vxlan_config *cfg, + struct mlxsw_sp_nve_config *config) +{ + switch (cfg->saddr.sa.sa_family) { + case AF_INET: + config->ul_proto = MLXSW_SP_L3_PROTO_IPV4; + config->ul_sip.addr4 = cfg->saddr.sin.sin_addr.s_addr; + break; + case AF_INET6: + config->ul_proto = MLXSW_SP_L3_PROTO_IPV6; + config->ul_sip.addr6 = cfg->saddr.sin6.sin6_addr; + break; + } +} + static void mlxsw_sp_nve_vxlan_config(const struct mlxsw_sp_nve *nve, const struct mlxsw_sp_nve_params *params, struct mlxsw_sp_nve_config *config) @@ -102,8 +154,7 @@ static void mlxsw_sp_nve_vxlan_config(const struct mlxsw_sp_nve *nve, config->flowlabel = cfg->label; config->learning_en = cfg->flags & VXLAN_F_LEARN ? 1 : 0; config->ul_tb_id = RT_TABLE_MAIN; - config->ul_proto = MLXSW_SP_L3_PROTO_IPV4; - config->ul_sip.addr4 = cfg->saddr.sin.sin_addr.s_addr; + mlxsw_sp_nve_vxlan_ul_proto_sip_config(cfg, config); config->udp_dport = cfg->dst_port; } @@ -111,6 +162,7 @@ static void mlxsw_sp_nve_vxlan_config_prepare(char *tngcr_pl, const struct mlxsw_sp_nve_config *config) { + struct in6_addr addr6; u8 udp_sport; mlxsw_reg_tngcr_pack(tngcr_pl, MLXSW_REG_TNGCR_TYPE_VXLAN, true, @@ -122,7 +174,18 @@ mlxsw_sp_nve_vxlan_config_prepare(char *tngcr_pl, get_random_bytes(&udp_sport, sizeof(udp_sport)); udp_sport = (udp_sport % (0xee - 0x80 + 1)) + 0x80; mlxsw_reg_tngcr_nve_udp_sport_prefix_set(tngcr_pl, udp_sport); - mlxsw_reg_tngcr_usipv4_set(tngcr_pl, be32_to_cpu(config->ul_sip.addr4)); + + switch (config->ul_proto) { + case MLXSW_SP_L3_PROTO_IPV4: + mlxsw_reg_tngcr_usipv4_set(tngcr_pl, + be32_to_cpu(config->ul_sip.addr4)); + break; + case MLXSW_SP_L3_PROTO_IPV6: + addr6 = config->ul_sip.addr6; + mlxsw_reg_tngcr_usipv6_memcpy_to(tngcr_pl, + (const char *)&addr6); + break; + } } static int diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 2af0c6382609..d40762cfc453 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1307,6 +1307,10 @@ mlxsw_sp_router_ip2me_fib_entry_find(struct mlxsw_sp *mlxsw_sp, u32 tb_id, addr_prefix_len = 32; break; case MLXSW_SP_L3_PROTO_IPV6: + addrp = &addr->addr6; + addr_len = 16; + addr_prefix_len = 128; + break; default: WARN_ON(1); return NULL; @@ -7002,6 +7006,8 @@ mlxsw_sp_fib6_entry_type_set_local(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_nexthop_group_info *nhgi = fib_entry->nh_group->nhgi; union mlxsw_sp_l3addr dip = { .addr6 = rt->fib6_dst.addr }; + u32 tb_id = mlxsw_sp_fix_tb_id(rt->fib6_table->tb6_id); + struct mlxsw_sp_router *router = mlxsw_sp->router; int ifindex = nhgi->nexthops[0].ifindex; struct mlxsw_sp_ipip_entry *ipip_entry; @@ -7015,6 +7021,14 @@ mlxsw_sp_fib6_entry_type_set_local(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_fib_entry_decap_init(mlxsw_sp, fib_entry, ipip_entry); } + if (mlxsw_sp_router_nve_is_decap(mlxsw_sp, tb_id, + MLXSW_SP_L3_PROTO_IPV6, &dip)) { + u32 tunnel_index; + + tunnel_index = router->nve_decap_config.tunnel_index; + fib_entry->decap.tunnel_index = tunnel_index; + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP; + } return 0; } @@ -8491,7 +8505,8 @@ mlxsw_sp_rif_mac_profile_replace(struct mlxsw_sp *mlxsw_sp, u8 mac_profile; int err; - if (!mlxsw_sp_rif_mac_profile_is_shared(rif)) + if (!mlxsw_sp_rif_mac_profile_is_shared(rif) && + !mlxsw_sp_rif_mac_profile_find(mlxsw_sp, new_mac)) return mlxsw_sp_rif_mac_profile_edit(rif, new_mac); err = mlxsw_sp_rif_mac_profile_get(mlxsw_sp, new_mac, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index c5fd69a6bedd..65c1724c63b0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -1290,38 +1290,52 @@ static enum mlxsw_reg_sfd_op mlxsw_sp_sfd_op(bool adding) MLXSW_REG_SFD_OP_WRITE_REMOVE; } -static int mlxsw_sp_port_fdb_tunnel_uc_op(struct mlxsw_sp *mlxsw_sp, - const char *mac, u16 fid, - enum mlxsw_sp_l3proto proto, - const union mlxsw_sp_l3addr *addr, - bool adding, bool dynamic) +static int +mlxsw_sp_port_fdb_tun_uc_op4(struct mlxsw_sp *mlxsw_sp, bool dynamic, + const char *mac, u16 fid, __be32 addr, bool adding) { - enum mlxsw_reg_sfd_uc_tunnel_protocol sfd_proto; char *sfd_pl; u8 num_rec; u32 uip; int err; - switch (proto) { - case MLXSW_SP_L3_PROTO_IPV4: - uip = be32_to_cpu(addr->addr4); - sfd_proto = MLXSW_REG_SFD_UC_TUNNEL_PROTOCOL_IPV4; - break; - case MLXSW_SP_L3_PROTO_IPV6: - default: - WARN_ON(1); - return -EOPNOTSUPP; - } + sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); + if (!sfd_pl) + return -ENOMEM; + + uip = be32_to_cpu(addr); + mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0); + mlxsw_reg_sfd_uc_tunnel_pack4(sfd_pl, 0, + mlxsw_sp_sfd_rec_policy(dynamic), mac, + fid, MLXSW_REG_SFD_REC_ACTION_NOP, uip); + num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); + if (err) + goto out; + + if (num_rec != mlxsw_reg_sfd_num_rec_get(sfd_pl)) + err = -EBUSY; + +out: + kfree(sfd_pl); + return err; +} + +static int mlxsw_sp_port_fdb_tun_uc_op6_sfd_write(struct mlxsw_sp *mlxsw_sp, + const char *mac, u16 fid, + u32 kvdl_index, bool adding) +{ + char *sfd_pl; + u8 num_rec; + int err; sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL); if (!sfd_pl) return -ENOMEM; mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0); - mlxsw_reg_sfd_uc_tunnel_pack(sfd_pl, 0, - mlxsw_sp_sfd_rec_policy(dynamic), mac, fid, - MLXSW_REG_SFD_REC_ACTION_NOP, uip, - sfd_proto); + mlxsw_reg_sfd_uc_tunnel_pack6(sfd_pl, 0, mac, fid, + MLXSW_REG_SFD_REC_ACTION_NOP, kvdl_index); num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl); err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl); if (err) @@ -1335,6 +1349,79 @@ out: return err; } +static int mlxsw_sp_port_fdb_tun_uc_op6_add(struct mlxsw_sp *mlxsw_sp, + const char *mac, u16 fid, + const struct in6_addr *addr) +{ + u32 kvdl_index; + int err; + + err = mlxsw_sp_nve_ipv6_addr_kvdl_set(mlxsw_sp, addr, &kvdl_index); + if (err) + return err; + + err = mlxsw_sp_port_fdb_tun_uc_op6_sfd_write(mlxsw_sp, mac, fid, + kvdl_index, true); + if (err) + goto err_sfd_write; + + err = mlxsw_sp_nve_ipv6_addr_map_replace(mlxsw_sp, mac, fid, addr); + if (err) + /* Replace can fail only for creating new mapping, so removing + * the FDB entry in the error path is OK. + */ + goto err_addr_replace; + + return 0; + +err_addr_replace: + mlxsw_sp_port_fdb_tun_uc_op6_sfd_write(mlxsw_sp, mac, fid, kvdl_index, + false); +err_sfd_write: + mlxsw_sp_nve_ipv6_addr_kvdl_unset(mlxsw_sp, addr); + return err; +} + +static void mlxsw_sp_port_fdb_tun_uc_op6_del(struct mlxsw_sp *mlxsw_sp, + const char *mac, u16 fid, + const struct in6_addr *addr) +{ + mlxsw_sp_nve_ipv6_addr_map_del(mlxsw_sp, mac, fid); + mlxsw_sp_port_fdb_tun_uc_op6_sfd_write(mlxsw_sp, mac, fid, 0, false); + mlxsw_sp_nve_ipv6_addr_kvdl_unset(mlxsw_sp, addr); +} + +static int +mlxsw_sp_port_fdb_tun_uc_op6(struct mlxsw_sp *mlxsw_sp, const char *mac, + u16 fid, const struct in6_addr *addr, bool adding) +{ + if (adding) + return mlxsw_sp_port_fdb_tun_uc_op6_add(mlxsw_sp, mac, fid, + addr); + + mlxsw_sp_port_fdb_tun_uc_op6_del(mlxsw_sp, mac, fid, addr); + return 0; +} + +static int mlxsw_sp_port_fdb_tunnel_uc_op(struct mlxsw_sp *mlxsw_sp, + const char *mac, u16 fid, + enum mlxsw_sp_l3proto proto, + const union mlxsw_sp_l3addr *addr, + bool adding, bool dynamic) +{ + switch (proto) { + case MLXSW_SP_L3_PROTO_IPV4: + return mlxsw_sp_port_fdb_tun_uc_op4(mlxsw_sp, dynamic, mac, fid, + addr->addr4, adding); + case MLXSW_SP_L3_PROTO_IPV6: + return mlxsw_sp_port_fdb_tun_uc_op6(mlxsw_sp, mac, fid, + &addr->addr6, adding); + default: + WARN_ON(1); + return -EOPNOTSUPP; + } +} + static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u16 local_port, const char *mac, u16 fid, bool adding, enum mlxsw_reg_sfd_rec_action action, diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index 9380e396f648..8b7a8d879083 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -1305,12 +1305,6 @@ int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) return -EFAULT; - if (config.flags) { - netif_warn(adapter, drv, adapter->netdev, - "ignoring hwtstamp_config.flags == 0x%08X, expected 0\n", - config.flags); - } - switch (config.tx_type) { case HWTSTAMP_TX_OFF: for (index = 0; index < LAN743X_MAX_TX_CHANNELS; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c index 2ddb20585d40..237555845a52 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c @@ -331,7 +331,6 @@ int lan966x_port_pcs_set(struct lan966x_port *port, struct lan966x *lan966x = port->lan966x; bool inband_aneg = false; bool outband; - int err; if (config->inband) { if (config->portmode == PHY_INTERFACE_MODE_SGMII || @@ -341,11 +340,6 @@ int lan966x_port_pcs_set(struct lan966x_port *port, config->autoneg) inband_aneg = true; /* Clause-37 in-band-aneg */ - if (config->speed > 0) { - err = phy_set_speed(port->serdes, config->speed); - if (err) - return err; - } outband = false; } else { outband = true; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 34b971ff8ef8..078d6a5a0768 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -480,16 +480,16 @@ static int mana_hwc_create_wq(struct hw_channel_context *hwc, if (err) goto out; - err = mana_hwc_alloc_dma_buf(hwc, q_depth, max_msg_size, - &hwc_wq->msg_buf); - if (err) - goto out; - hwc_wq->hwc = hwc; hwc_wq->gdma_wq = queue; hwc_wq->queue_depth = q_depth; hwc_wq->hwc_cq = hwc_cq; + err = mana_hwc_alloc_dma_buf(hwc, q_depth, max_msg_size, + &hwc_wq->msg_buf); + if (err) + goto out; + *hwc_wq_ptr = hwc_wq; return 0; out: diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h index 0c5553887b75..9a12607fb511 100644 --- a/drivers/net/ethernet/microsoft/mana/mana.h +++ b/drivers/net/ethernet/microsoft/mana/mana.h @@ -289,6 +289,8 @@ struct mana_rxq { struct mana_cq rx_cq; + struct completion fence_event; + struct net_device *ndev; /* Total number of receive buffers to be allocated */ diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index c1d5a374b967..d37d35885579 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -750,6 +750,61 @@ out: return err; } +static int mana_fence_rq(struct mana_port_context *apc, struct mana_rxq *rxq) +{ + struct mana_fence_rq_resp resp = {}; + struct mana_fence_rq_req req = {}; + int err; + + init_completion(&rxq->fence_event); + + mana_gd_init_req_hdr(&req.hdr, MANA_FENCE_RQ, + sizeof(req), sizeof(resp)); + req.wq_obj_handle = rxq->rxobj; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + if (err) { + netdev_err(apc->ndev, "Failed to fence RQ %u: %d\n", + rxq->rxq_idx, err); + return err; + } + + err = mana_verify_resp_hdr(&resp.hdr, MANA_FENCE_RQ, sizeof(resp)); + if (err || resp.hdr.status) { + netdev_err(apc->ndev, "Failed to fence RQ %u: %d, 0x%x\n", + rxq->rxq_idx, err, resp.hdr.status); + if (!err) + err = -EPROTO; + + return err; + } + + if (wait_for_completion_timeout(&rxq->fence_event, 10 * HZ) == 0) { + netdev_err(apc->ndev, "Failed to fence RQ %u: timed out\n", + rxq->rxq_idx); + return -ETIMEDOUT; + } + + return 0; +} + +static void mana_fence_rqs(struct mana_port_context *apc) +{ + unsigned int rxq_idx; + struct mana_rxq *rxq; + int err; + + for (rxq_idx = 0; rxq_idx < apc->num_queues; rxq_idx++) { + rxq = apc->rxqs[rxq_idx]; + err = mana_fence_rq(apc, rxq); + + /* In case of any error, use sleep instead. */ + if (err) + msleep(100); + } +} + static int mana_move_wq_tail(struct gdma_queue *wq, u32 num_units) { u32 used_space_old; @@ -1023,7 +1078,7 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, return; case CQE_RX_OBJECT_FENCE: - netdev_err(ndev, "RX Fencing is unsupported\n"); + complete(&rxq->fence_event); return; default: @@ -1617,6 +1672,7 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, bool update_hash, bool update_tab) { u32 queue_idx; + int err; int i; if (update_tab) { @@ -1626,7 +1682,13 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, } } - return mana_cfg_vport_steering(apc, rx, true, update_hash, update_tab); + err = mana_cfg_vport_steering(apc, rx, true, update_hash, update_tab); + if (err) + return err; + + mana_fence_rqs(apc); + + return 0; } static int mana_init_port(struct net_device *ndev) @@ -1773,9 +1835,6 @@ static int mana_dealloc_queues(struct net_device *ndev) return err; } - /* TODO: Implement RX fencing */ - ssleep(1); - mana_destroy_vport(apc); return 0; diff --git a/drivers/net/ethernet/mscc/Makefile b/drivers/net/ethernet/mscc/Makefile index dfa939376d6c..41b34a509308 100644 --- a/drivers/net/ethernet/mscc/Makefile +++ b/drivers/net/ethernet/mscc/Makefile @@ -12,5 +12,6 @@ mscc_ocelot_switch_lib-y := \ mscc_ocelot_switch_lib-$(CONFIG_BRIDGE_MRP) += ocelot_mrp.o obj-$(CONFIG_MSCC_OCELOT_SWITCH) += mscc_ocelot.o mscc_ocelot-y := \ + ocelot_fdma.o \ ocelot_vsc7514.o \ ocelot_net.o diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index b1856d8c944b..9b42187a026a 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1054,14 +1054,34 @@ static int ocelot_xtr_poll_xfh(struct ocelot *ocelot, int grp, u32 *xfh) return 0; } -int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) +void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, + u64 timestamp) { struct skb_shared_hwtstamps *shhwtstamps; u64 tod_in_ns, full_ts_in_ns; + struct timespec64 ts; + + ocelot_ptp_gettime64(&ocelot->ptp_info, &ts); + + tod_in_ns = ktime_set(ts.tv_sec, ts.tv_nsec); + if ((tod_in_ns & 0xffffffff) < timestamp) + full_ts_in_ns = (((tod_in_ns >> 32) - 1) << 32) | + timestamp; + else + full_ts_in_ns = (tod_in_ns & GENMASK_ULL(63, 32)) | + timestamp; + + shhwtstamps = skb_hwtstamps(skb); + memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps)); + shhwtstamps->hwtstamp = full_ts_in_ns; +} +EXPORT_SYMBOL(ocelot_ptp_rx_timestamp); + +int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) +{ u64 timestamp, src_port, len; u32 xfh[OCELOT_TAG_LEN / 4]; struct net_device *dev; - struct timespec64 ts; struct sk_buff *skb; int sz, buf_len; u32 val, *buf; @@ -1117,21 +1137,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb) *buf = val; } - if (ocelot->ptp) { - ocelot_ptp_gettime64(&ocelot->ptp_info, &ts); - - tod_in_ns = ktime_set(ts.tv_sec, ts.tv_nsec); - if ((tod_in_ns & 0xffffffff) < timestamp) - full_ts_in_ns = (((tod_in_ns >> 32) - 1) << 32) | - timestamp; - else - full_ts_in_ns = (tod_in_ns & GENMASK_ULL(63, 32)) | - timestamp; - - shhwtstamps = skb_hwtstamps(skb); - memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps)); - shhwtstamps->hwtstamp = full_ts_in_ns; - } + if (ocelot->ptp) + ocelot_ptp_rx_timestamp(ocelot, skb, timestamp); /* Everything we see on an interface that is in the HW bridge * has already been forwarded. @@ -1164,6 +1171,18 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp) } EXPORT_SYMBOL(ocelot_can_inject); +void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag) +{ + ocelot_ifh_set_bypass(ifh, 1); + ocelot_ifh_set_dest(ifh, BIT_ULL(port)); + ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); + if (vlan_tag) + ocelot_ifh_set_vlan_tci(ifh, vlan_tag); + if (rew_op) + ocelot_ifh_set_rew_op(ifh, rew_op); +} +EXPORT_SYMBOL(ocelot_ifh_port_set); + void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb) { @@ -1173,11 +1192,7 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) | QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp); - ocelot_ifh_set_bypass(ifh, 1); - ocelot_ifh_set_dest(ifh, BIT_ULL(port)); - ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); - ocelot_ifh_set_vlan_tci(ifh, skb_vlan_tag_get(skb)); - ocelot_ifh_set_rew_op(ifh, rew_op); + ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); for (i = 0; i < OCELOT_TAG_LEN / 4; i++) ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp); @@ -1602,10 +1617,6 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - /* reserved for future extensions */ - if (cfg.flags) - return -EINVAL; - /* Tx type sanity check */ switch (cfg.tx_type) { case HWTSTAMP_TX_ON: diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index 1eb0b5ad51e9..bf4eff6d7086 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -32,6 +32,8 @@ #define OCELOT_PTP_QUEUE_SZ 128 +#define OCELOT_JUMBO_MTU 9000 + struct ocelot_port_tc { bool block_shared; unsigned long offload_cnt; diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c new file mode 100644 index 000000000000..dffa597bffe6 --- /dev/null +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -0,0 +1,894 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Microsemi SoCs FDMA driver + * + * Copyright (c) 2021 Microchip + * + * Page recycling code is mostly taken from gianfar driver. + */ + +#include <linux/align.h> +#include <linux/bitops.h> +#include <linux/dmapool.h> +#include <linux/dsa/ocelot.h> +#include <linux/netdevice.h> +#include <linux/of_platform.h> +#include <linux/skbuff.h> + +#include "ocelot_fdma.h" +#include "ocelot_qs.h" + +DEFINE_STATIC_KEY_FALSE(ocelot_fdma_enabled); + +static void ocelot_fdma_writel(struct ocelot *ocelot, u32 reg, u32 data) +{ + regmap_write(ocelot->targets[FDMA], reg, data); +} + +static u32 ocelot_fdma_readl(struct ocelot *ocelot, u32 reg) +{ + u32 retval; + + regmap_read(ocelot->targets[FDMA], reg, &retval); + + return retval; +} + +static dma_addr_t ocelot_fdma_idx_dma(dma_addr_t base, u16 idx) +{ + return base + idx * sizeof(struct ocelot_fdma_dcb); +} + +static u16 ocelot_fdma_dma_idx(dma_addr_t base, dma_addr_t dma) +{ + return (dma - base) / sizeof(struct ocelot_fdma_dcb); +} + +static u16 ocelot_fdma_idx_next(u16 idx, u16 ring_sz) +{ + return unlikely(idx == ring_sz - 1) ? 0 : idx + 1; +} + +static u16 ocelot_fdma_idx_prev(u16 idx, u16 ring_sz) +{ + return unlikely(idx == 0) ? ring_sz - 1 : idx - 1; +} + +static int ocelot_fdma_rx_ring_free(struct ocelot_fdma *fdma) +{ + struct ocelot_fdma_rx_ring *rx_ring = &fdma->rx_ring; + + if (rx_ring->next_to_use >= rx_ring->next_to_clean) + return OCELOT_FDMA_RX_RING_SIZE - + (rx_ring->next_to_use - rx_ring->next_to_clean) - 1; + else + return rx_ring->next_to_clean - rx_ring->next_to_use - 1; +} + +static int ocelot_fdma_tx_ring_free(struct ocelot_fdma *fdma) +{ + struct ocelot_fdma_tx_ring *tx_ring = &fdma->tx_ring; + + if (tx_ring->next_to_use >= tx_ring->next_to_clean) + return OCELOT_FDMA_TX_RING_SIZE - + (tx_ring->next_to_use - tx_ring->next_to_clean) - 1; + else + return tx_ring->next_to_clean - tx_ring->next_to_use - 1; +} + +static bool ocelot_fdma_tx_ring_empty(struct ocelot_fdma *fdma) +{ + struct ocelot_fdma_tx_ring *tx_ring = &fdma->tx_ring; + + return tx_ring->next_to_clean == tx_ring->next_to_use; +} + +static void ocelot_fdma_activate_chan(struct ocelot *ocelot, dma_addr_t dma, + int chan) +{ + ocelot_fdma_writel(ocelot, MSCC_FDMA_DCB_LLP(chan), dma); + /* Barrier to force memory writes to DCB to be completed before starting + * the channel. + */ + wmb(); + ocelot_fdma_writel(ocelot, MSCC_FDMA_CH_ACTIVATE, BIT(chan)); +} + +static int ocelot_fdma_wait_chan_safe(struct ocelot *ocelot, int chan) +{ + unsigned long timeout; + u32 safe; + + timeout = jiffies + usecs_to_jiffies(OCELOT_FDMA_CH_SAFE_TIMEOUT_US); + do { + safe = ocelot_fdma_readl(ocelot, MSCC_FDMA_CH_SAFE); + if (safe & BIT(chan)) + return 0; + } while (time_after(jiffies, timeout)); + + return -ETIMEDOUT; +} + +static void ocelot_fdma_dcb_set_data(struct ocelot_fdma_dcb *dcb, + dma_addr_t dma_addr, + size_t size) +{ + u32 offset = dma_addr & 0x3; + + dcb->llp = 0; + dcb->datap = ALIGN_DOWN(dma_addr, 4); + dcb->datal = ALIGN_DOWN(size, 4); + dcb->stat = MSCC_FDMA_DCB_STAT_BLOCKO(offset); +} + +static bool ocelot_fdma_rx_alloc_page(struct ocelot *ocelot, + struct ocelot_fdma_rx_buf *rxb) +{ + dma_addr_t mapping; + struct page *page; + + page = dev_alloc_page(); + if (unlikely(!page)) + return false; + + mapping = dma_map_page(ocelot->dev, page, 0, PAGE_SIZE, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(ocelot->dev, mapping))) { + __free_page(page); + return false; + } + + rxb->page = page; + rxb->page_offset = 0; + rxb->dma_addr = mapping; + + return true; +} + +static int ocelot_fdma_alloc_rx_buffs(struct ocelot *ocelot, u16 alloc_cnt) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + struct ocelot_fdma_rx_ring *rx_ring; + struct ocelot_fdma_rx_buf *rxb; + struct ocelot_fdma_dcb *dcb; + dma_addr_t dma_addr; + int ret = 0; + u16 idx; + + rx_ring = &fdma->rx_ring; + idx = rx_ring->next_to_use; + + while (alloc_cnt--) { + rxb = &rx_ring->bufs[idx]; + /* try reuse page */ + if (unlikely(!rxb->page)) { + if (unlikely(!ocelot_fdma_rx_alloc_page(ocelot, rxb))) { + dev_err_ratelimited(ocelot->dev, + "Failed to allocate rx\n"); + ret = -ENOMEM; + break; + } + } + + dcb = &rx_ring->dcbs[idx]; + dma_addr = rxb->dma_addr + rxb->page_offset; + ocelot_fdma_dcb_set_data(dcb, dma_addr, OCELOT_FDMA_RXB_SIZE); + + idx = ocelot_fdma_idx_next(idx, OCELOT_FDMA_RX_RING_SIZE); + /* Chain the DCB to the next one */ + dcb->llp = ocelot_fdma_idx_dma(rx_ring->dcbs_dma, idx); + } + + rx_ring->next_to_use = idx; + rx_ring->next_to_alloc = idx; + + return ret; +} + +static bool ocelot_fdma_tx_dcb_set_skb(struct ocelot *ocelot, + struct ocelot_fdma_tx_buf *tx_buf, + struct ocelot_fdma_dcb *dcb, + struct sk_buff *skb) +{ + dma_addr_t mapping; + + mapping = dma_map_single(ocelot->dev, skb->data, skb->len, + DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(ocelot->dev, mapping))) + return false; + + dma_unmap_addr_set(tx_buf, dma_addr, mapping); + + ocelot_fdma_dcb_set_data(dcb, mapping, OCELOT_FDMA_RX_SIZE); + tx_buf->skb = skb; + dcb->stat |= MSCC_FDMA_DCB_STAT_BLOCKL(skb->len); + dcb->stat |= MSCC_FDMA_DCB_STAT_SOF | MSCC_FDMA_DCB_STAT_EOF; + + return true; +} + +static bool ocelot_fdma_check_stop_rx(struct ocelot *ocelot) +{ + u32 llp; + + /* Check if the FDMA hits the DCB with LLP == NULL */ + llp = ocelot_fdma_readl(ocelot, MSCC_FDMA_DCB_LLP(MSCC_FDMA_XTR_CHAN)); + if (unlikely(llp)) + return false; + + ocelot_fdma_writel(ocelot, MSCC_FDMA_CH_DISABLE, + BIT(MSCC_FDMA_XTR_CHAN)); + + return true; +} + +static void ocelot_fdma_rx_set_llp(struct ocelot_fdma_rx_ring *rx_ring) +{ + struct ocelot_fdma_dcb *dcb; + unsigned int idx; + + idx = ocelot_fdma_idx_prev(rx_ring->next_to_use, + OCELOT_FDMA_RX_RING_SIZE); + dcb = &rx_ring->dcbs[idx]; + dcb->llp = 0; +} + +static void ocelot_fdma_rx_restart(struct ocelot *ocelot) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + struct ocelot_fdma_rx_ring *rx_ring; + const u8 chan = MSCC_FDMA_XTR_CHAN; + dma_addr_t new_llp, dma_base; + unsigned int idx; + u32 llp_prev; + int ret; + + rx_ring = &fdma->rx_ring; + ret = ocelot_fdma_wait_chan_safe(ocelot, chan); + if (ret) { + dev_err_ratelimited(ocelot->dev, + "Unable to stop RX channel\n"); + return; + } + + ocelot_fdma_rx_set_llp(rx_ring); + + /* FDMA stopped on the last DCB that contained a NULL LLP, since + * we processed some DCBs in RX, there is free space, and we must set + * DCB_LLP to point to the next DCB + */ + llp_prev = ocelot_fdma_readl(ocelot, MSCC_FDMA_DCB_LLP_PREV(chan)); + dma_base = rx_ring->dcbs_dma; + + /* Get the next DMA addr located after LLP == NULL DCB */ + idx = ocelot_fdma_dma_idx(dma_base, llp_prev); + idx = ocelot_fdma_idx_next(idx, OCELOT_FDMA_RX_RING_SIZE); + new_llp = ocelot_fdma_idx_dma(dma_base, idx); + + /* Finally reactivate the channel */ + ocelot_fdma_activate_chan(ocelot, new_llp, chan); +} + +static bool ocelot_fdma_add_rx_frag(struct ocelot_fdma_rx_buf *rxb, u32 stat, + struct sk_buff *skb, bool first) +{ + int size = MSCC_FDMA_DCB_STAT_BLOCKL(stat); + struct page *page = rxb->page; + + if (likely(first)) { + skb_put(skb, size); + } else { + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + rxb->page_offset, size, OCELOT_FDMA_RX_SIZE); + } + + /* Try to reuse page */ + if (unlikely(page_ref_count(page) != 1 || page_is_pfmemalloc(page))) + return false; + + /* Change offset to the other half */ + rxb->page_offset ^= OCELOT_FDMA_RX_SIZE; + + page_ref_inc(page); + + return true; +} + +static void ocelot_fdma_reuse_rx_page(struct ocelot *ocelot, + struct ocelot_fdma_rx_buf *old_rxb) +{ + struct ocelot_fdma_rx_ring *rx_ring = &ocelot->fdma->rx_ring; + struct ocelot_fdma_rx_buf *new_rxb; + + new_rxb = &rx_ring->bufs[rx_ring->next_to_alloc]; + rx_ring->next_to_alloc = ocelot_fdma_idx_next(rx_ring->next_to_alloc, + OCELOT_FDMA_RX_RING_SIZE); + + /* Copy page reference */ + *new_rxb = *old_rxb; + + /* Sync for use by the device */ + dma_sync_single_range_for_device(ocelot->dev, old_rxb->dma_addr, + old_rxb->page_offset, + OCELOT_FDMA_RX_SIZE, DMA_FROM_DEVICE); +} + +static struct sk_buff *ocelot_fdma_get_skb(struct ocelot *ocelot, u32 stat, + struct ocelot_fdma_rx_buf *rxb, + struct sk_buff *skb) +{ + bool first = false; + + /* Allocate skb head and data */ + if (likely(!skb)) { + void *buff_addr = page_address(rxb->page) + + rxb->page_offset; + + skb = build_skb(buff_addr, OCELOT_FDMA_SKBFRAG_SIZE); + if (unlikely(!skb)) { + dev_err_ratelimited(ocelot->dev, + "build_skb failed !\n"); + return NULL; + } + first = true; + } + + dma_sync_single_range_for_cpu(ocelot->dev, rxb->dma_addr, + rxb->page_offset, OCELOT_FDMA_RX_SIZE, + DMA_FROM_DEVICE); + + if (ocelot_fdma_add_rx_frag(rxb, stat, skb, first)) { + /* Reuse the free half of the page for the next_to_alloc DCB*/ + ocelot_fdma_reuse_rx_page(ocelot, rxb); + } else { + /* page cannot be reused, unmap it */ + dma_unmap_page(ocelot->dev, rxb->dma_addr, PAGE_SIZE, + DMA_FROM_DEVICE); + } + + /* clear rx buff content */ + rxb->page = NULL; + + return skb; +} + +static bool ocelot_fdma_receive_skb(struct ocelot *ocelot, struct sk_buff *skb) +{ + struct net_device *ndev; + void *xfh = skb->data; + u64 timestamp; + u64 src_port; + + skb_pull(skb, OCELOT_TAG_LEN); + + ocelot_xfh_get_src_port(xfh, &src_port); + if (unlikely(src_port >= ocelot->num_phys_ports)) + return false; + + ndev = ocelot_port_to_netdev(ocelot, src_port); + if (unlikely(!ndev)) + return false; + + pskb_trim(skb, skb->len - ETH_FCS_LEN); + + skb->dev = ndev; + skb->protocol = eth_type_trans(skb, skb->dev); + skb->dev->stats.rx_bytes += skb->len; + skb->dev->stats.rx_packets++; + + if (ocelot->ptp) { + ocelot_xfh_get_rew_val(xfh, ×tamp); + ocelot_ptp_rx_timestamp(ocelot, skb, timestamp); + } + + if (likely(!skb_defer_rx_timestamp(skb))) + netif_receive_skb(skb); + + return true; +} + +static int ocelot_fdma_rx_get(struct ocelot *ocelot, int budget) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + struct ocelot_fdma_rx_ring *rx_ring; + struct ocelot_fdma_rx_buf *rxb; + struct ocelot_fdma_dcb *dcb; + struct sk_buff *skb; + int work_done = 0; + int cleaned_cnt; + u32 stat; + u16 idx; + + cleaned_cnt = ocelot_fdma_rx_ring_free(fdma); + rx_ring = &fdma->rx_ring; + skb = rx_ring->skb; + + while (budget--) { + idx = rx_ring->next_to_clean; + dcb = &rx_ring->dcbs[idx]; + stat = dcb->stat; + if (MSCC_FDMA_DCB_STAT_BLOCKL(stat) == 0) + break; + + /* New packet is a start of frame but we already got a skb set, + * we probably lost an EOF packet, free skb + */ + if (unlikely(skb && (stat & MSCC_FDMA_DCB_STAT_SOF))) { + dev_kfree_skb(skb); + skb = NULL; + } + + rxb = &rx_ring->bufs[idx]; + /* Fetch next to clean buffer from the rx_ring */ + skb = ocelot_fdma_get_skb(ocelot, stat, rxb, skb); + if (unlikely(!skb)) + break; + + work_done++; + cleaned_cnt++; + + idx = ocelot_fdma_idx_next(idx, OCELOT_FDMA_RX_RING_SIZE); + rx_ring->next_to_clean = idx; + + if (unlikely(stat & MSCC_FDMA_DCB_STAT_ABORT || + stat & MSCC_FDMA_DCB_STAT_PD)) { + dev_err_ratelimited(ocelot->dev, + "DCB aborted or pruned\n"); + dev_kfree_skb(skb); + skb = NULL; + continue; + } + + /* We still need to process the other fragment of the packet + * before delivering it to the network stack + */ + if (!(stat & MSCC_FDMA_DCB_STAT_EOF)) + continue; + + if (unlikely(!ocelot_fdma_receive_skb(ocelot, skb))) + dev_kfree_skb(skb); + + skb = NULL; + } + + rx_ring->skb = skb; + + if (cleaned_cnt) + ocelot_fdma_alloc_rx_buffs(ocelot, cleaned_cnt); + + return work_done; +} + +static void ocelot_fdma_wakeup_netdev(struct ocelot *ocelot) +{ + struct ocelot_port_private *priv; + struct ocelot_port *ocelot_port; + struct net_device *dev; + int port; + + for (port = 0; port < ocelot->num_phys_ports; port++) { + ocelot_port = ocelot->ports[port]; + if (!ocelot_port) + continue; + priv = container_of(ocelot_port, struct ocelot_port_private, + port); + dev = priv->dev; + + if (unlikely(netif_queue_stopped(dev))) + netif_wake_queue(dev); + } +} + +static void ocelot_fdma_tx_cleanup(struct ocelot *ocelot, int budget) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + struct ocelot_fdma_tx_ring *tx_ring; + struct ocelot_fdma_tx_buf *buf; + unsigned int new_null_llp_idx; + struct ocelot_fdma_dcb *dcb; + bool end_of_list = false; + struct sk_buff *skb; + dma_addr_t dma; + u32 dcb_llp; + u16 ntc; + int ret; + + tx_ring = &fdma->tx_ring; + + /* Purge the TX packets that have been sent up to the NULL llp or the + * end of done list. + */ + while (!ocelot_fdma_tx_ring_empty(fdma)) { + ntc = tx_ring->next_to_clean; + dcb = &tx_ring->dcbs[ntc]; + if (!(dcb->stat & MSCC_FDMA_DCB_STAT_PD)) + break; + + buf = &tx_ring->bufs[ntc]; + skb = buf->skb; + dma_unmap_single(ocelot->dev, dma_unmap_addr(buf, dma_addr), + skb->len, DMA_TO_DEVICE); + napi_consume_skb(skb, budget); + dcb_llp = dcb->llp; + + /* Only update after accessing all dcb fields */ + tx_ring->next_to_clean = ocelot_fdma_idx_next(ntc, + OCELOT_FDMA_TX_RING_SIZE); + + /* If we hit the NULL LLP, stop, we might need to reload FDMA */ + if (dcb_llp == 0) { + end_of_list = true; + break; + } + } + + /* No need to try to wake if there were no TX cleaned_cnt up. */ + if (ocelot_fdma_tx_ring_free(fdma)) + ocelot_fdma_wakeup_netdev(ocelot); + + /* If there is still some DCBs to be processed by the FDMA or if the + * pending list is empty, there is no need to restart the FDMA. + */ + if (!end_of_list || ocelot_fdma_tx_ring_empty(fdma)) + return; + + ret = ocelot_fdma_wait_chan_safe(ocelot, MSCC_FDMA_INJ_CHAN); + if (ret) { + dev_warn(ocelot->dev, + "Failed to wait for TX channel to stop\n"); + return; + } + + /* Set NULL LLP to be the last DCB used */ + new_null_llp_idx = ocelot_fdma_idx_prev(tx_ring->next_to_use, + OCELOT_FDMA_TX_RING_SIZE); + dcb = &tx_ring->dcbs[new_null_llp_idx]; + dcb->llp = 0; + + dma = ocelot_fdma_idx_dma(tx_ring->dcbs_dma, tx_ring->next_to_clean); + ocelot_fdma_activate_chan(ocelot, dma, MSCC_FDMA_INJ_CHAN); +} + +static int ocelot_fdma_napi_poll(struct napi_struct *napi, int budget) +{ + struct ocelot_fdma *fdma = container_of(napi, struct ocelot_fdma, napi); + struct ocelot *ocelot = fdma->ocelot; + int work_done = 0; + bool rx_stopped; + + ocelot_fdma_tx_cleanup(ocelot, budget); + + rx_stopped = ocelot_fdma_check_stop_rx(ocelot); + + work_done = ocelot_fdma_rx_get(ocelot, budget); + + if (rx_stopped) + ocelot_fdma_rx_restart(ocelot); + + if (work_done < budget) { + napi_complete_done(&fdma->napi, work_done); + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_ENA, + BIT(MSCC_FDMA_INJ_CHAN) | + BIT(MSCC_FDMA_XTR_CHAN)); + } + + return work_done; +} + +static irqreturn_t ocelot_fdma_interrupt(int irq, void *dev_id) +{ + u32 ident, llp, frm, err, err_code; + struct ocelot *ocelot = dev_id; + + ident = ocelot_fdma_readl(ocelot, MSCC_FDMA_INTR_IDENT); + frm = ocelot_fdma_readl(ocelot, MSCC_FDMA_INTR_FRM); + llp = ocelot_fdma_readl(ocelot, MSCC_FDMA_INTR_LLP); + + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_LLP, llp & ident); + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_FRM, frm & ident); + if (frm || llp) { + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_ENA, 0); + napi_schedule(&ocelot->fdma->napi); + } + + err = ocelot_fdma_readl(ocelot, MSCC_FDMA_EVT_ERR); + if (unlikely(err)) { + err_code = ocelot_fdma_readl(ocelot, MSCC_FDMA_EVT_ERR_CODE); + dev_err_ratelimited(ocelot->dev, + "Error ! chans mask: %#x, code: %#x\n", + err, err_code); + + ocelot_fdma_writel(ocelot, MSCC_FDMA_EVT_ERR, err); + ocelot_fdma_writel(ocelot, MSCC_FDMA_EVT_ERR_CODE, err_code); + } + + return IRQ_HANDLED; +} + +static void ocelot_fdma_send_skb(struct ocelot *ocelot, + struct ocelot_fdma *fdma, struct sk_buff *skb) +{ + struct ocelot_fdma_tx_ring *tx_ring = &fdma->tx_ring; + struct ocelot_fdma_tx_buf *tx_buf; + struct ocelot_fdma_dcb *dcb; + dma_addr_t dma; + u16 next_idx; + + dcb = &tx_ring->dcbs[tx_ring->next_to_use]; + tx_buf = &tx_ring->bufs[tx_ring->next_to_use]; + if (!ocelot_fdma_tx_dcb_set_skb(ocelot, tx_buf, dcb, skb)) { + dev_kfree_skb_any(skb); + return; + } + + next_idx = ocelot_fdma_idx_next(tx_ring->next_to_use, + OCELOT_FDMA_TX_RING_SIZE); + skb_tx_timestamp(skb); + + /* If the FDMA TX chan is empty, then enqueue the DCB directly */ + if (ocelot_fdma_tx_ring_empty(fdma)) { + dma = ocelot_fdma_idx_dma(tx_ring->dcbs_dma, + tx_ring->next_to_use); + ocelot_fdma_activate_chan(ocelot, dma, MSCC_FDMA_INJ_CHAN); + } else { + /* Chain the DCBs */ + dcb->llp = ocelot_fdma_idx_dma(tx_ring->dcbs_dma, next_idx); + } + + tx_ring->next_to_use = next_idx; +} + +static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op, + struct sk_buff *skb, struct net_device *dev) +{ + int needed_headroom = max_t(int, OCELOT_TAG_LEN - skb_headroom(skb), 0); + int needed_tailroom = max_t(int, ETH_FCS_LEN - skb_tailroom(skb), 0); + void *ifh; + int err; + + if (unlikely(needed_headroom || needed_tailroom || + skb_header_cloned(skb))) { + err = pskb_expand_head(skb, needed_headroom, needed_tailroom, + GFP_ATOMIC); + if (unlikely(err)) { + dev_kfree_skb_any(skb); + return 1; + } + } + + err = skb_linearize(skb); + if (err) { + net_err_ratelimited("%s: skb_linearize error (%d)!\n", + dev->name, err); + dev_kfree_skb_any(skb); + return 1; + } + + ifh = skb_push(skb, OCELOT_TAG_LEN); + skb_put(skb, ETH_FCS_LEN); + memset(ifh, 0, OCELOT_TAG_LEN); + ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb)); + + return 0; +} + +int ocelot_fdma_inject_frame(struct ocelot *ocelot, int port, u32 rew_op, + struct sk_buff *skb, struct net_device *dev) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + int ret = NETDEV_TX_OK; + + spin_lock(&fdma->tx_ring.xmit_lock); + + if (ocelot_fdma_tx_ring_free(fdma) == 0) { + netif_stop_queue(dev); + ret = NETDEV_TX_BUSY; + goto out; + } + + if (ocelot_fdma_prepare_skb(ocelot, port, rew_op, skb, dev)) + goto out; + + ocelot_fdma_send_skb(ocelot, fdma, skb); + +out: + spin_unlock(&fdma->tx_ring.xmit_lock); + + return ret; +} + +static void ocelot_fdma_free_rx_ring(struct ocelot *ocelot) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + struct ocelot_fdma_rx_ring *rx_ring; + struct ocelot_fdma_rx_buf *rxb; + u16 idx; + + rx_ring = &fdma->rx_ring; + idx = rx_ring->next_to_clean; + + /* Free the pages held in the RX ring */ + while (idx != rx_ring->next_to_use) { + rxb = &rx_ring->bufs[idx]; + dma_unmap_page(ocelot->dev, rxb->dma_addr, PAGE_SIZE, + DMA_FROM_DEVICE); + __free_page(rxb->page); + idx = ocelot_fdma_idx_next(idx, OCELOT_FDMA_RX_RING_SIZE); + } + + if (fdma->rx_ring.skb) + dev_kfree_skb_any(fdma->rx_ring.skb); +} + +static void ocelot_fdma_free_tx_ring(struct ocelot *ocelot) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + struct ocelot_fdma_tx_ring *tx_ring; + struct ocelot_fdma_tx_buf *txb; + struct sk_buff *skb; + u16 idx; + + tx_ring = &fdma->tx_ring; + idx = tx_ring->next_to_clean; + + while (idx != tx_ring->next_to_use) { + txb = &tx_ring->bufs[idx]; + skb = txb->skb; + dma_unmap_single(ocelot->dev, dma_unmap_addr(txb, dma_addr), + skb->len, DMA_TO_DEVICE); + dev_kfree_skb_any(skb); + idx = ocelot_fdma_idx_next(idx, OCELOT_FDMA_TX_RING_SIZE); + } +} + +static int ocelot_fdma_rings_alloc(struct ocelot *ocelot) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + struct ocelot_fdma_dcb *dcbs; + unsigned int adjust; + dma_addr_t dcbs_dma; + int ret; + + /* Create a pool of consistent memory blocks for hardware descriptors */ + fdma->dcbs_base = dmam_alloc_coherent(ocelot->dev, + OCELOT_DCBS_HW_ALLOC_SIZE, + &fdma->dcbs_dma_base, GFP_KERNEL); + if (!fdma->dcbs_base) + return -ENOMEM; + + /* DCBs must be aligned on a 32bit boundary */ + dcbs = fdma->dcbs_base; + dcbs_dma = fdma->dcbs_dma_base; + if (!IS_ALIGNED(dcbs_dma, 4)) { + adjust = dcbs_dma & 0x3; + dcbs_dma = ALIGN(dcbs_dma, 4); + dcbs = (void *)dcbs + adjust; + } + + /* TX queue */ + fdma->tx_ring.dcbs = dcbs; + fdma->tx_ring.dcbs_dma = dcbs_dma; + spin_lock_init(&fdma->tx_ring.xmit_lock); + + /* RX queue */ + fdma->rx_ring.dcbs = dcbs + OCELOT_FDMA_TX_RING_SIZE; + fdma->rx_ring.dcbs_dma = dcbs_dma + OCELOT_FDMA_TX_DCB_SIZE; + ret = ocelot_fdma_alloc_rx_buffs(ocelot, + ocelot_fdma_tx_ring_free(fdma)); + if (ret) { + ocelot_fdma_free_rx_ring(ocelot); + return ret; + } + + /* Set the last DCB LLP as NULL, this is normally done when restarting + * the RX chan, but this is for the first run + */ + ocelot_fdma_rx_set_llp(&fdma->rx_ring); + + return 0; +} + +void ocelot_fdma_netdev_init(struct ocelot *ocelot, struct net_device *dev) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + + dev->needed_headroom = OCELOT_TAG_LEN; + dev->needed_tailroom = ETH_FCS_LEN; + + if (fdma->ndev) + return; + + fdma->ndev = dev; + netif_napi_add(dev, &fdma->napi, ocelot_fdma_napi_poll, + OCELOT_FDMA_WEIGHT); +} + +void ocelot_fdma_netdev_deinit(struct ocelot *ocelot, struct net_device *dev) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + + if (fdma->ndev == dev) { + netif_napi_del(&fdma->napi); + fdma->ndev = NULL; + } +} + +void ocelot_fdma_init(struct platform_device *pdev, struct ocelot *ocelot) +{ + struct device *dev = ocelot->dev; + struct ocelot_fdma *fdma; + int ret; + + fdma = devm_kzalloc(dev, sizeof(*fdma), GFP_KERNEL); + if (!fdma) + return; + + ocelot->fdma = fdma; + ocelot->dev->coherent_dma_mask = DMA_BIT_MASK(32); + + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_ENA, 0); + + fdma->ocelot = ocelot; + fdma->irq = platform_get_irq_byname(pdev, "fdma"); + ret = devm_request_irq(dev, fdma->irq, ocelot_fdma_interrupt, 0, + dev_name(dev), ocelot); + if (ret) + goto err_free_fdma; + + ret = ocelot_fdma_rings_alloc(ocelot); + if (ret) + goto err_free_irq; + + static_branch_enable(&ocelot_fdma_enabled); + + return; + +err_free_irq: + devm_free_irq(dev, fdma->irq, fdma); +err_free_fdma: + devm_kfree(dev, fdma); + + ocelot->fdma = NULL; +} + +void ocelot_fdma_start(struct ocelot *ocelot) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + + /* Reconfigure for extraction and injection using DMA */ + ocelot_write_rix(ocelot, QS_INJ_GRP_CFG_MODE(2), QS_INJ_GRP_CFG, 0); + ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(0), QS_INJ_CTRL, 0); + + ocelot_write_rix(ocelot, QS_XTR_GRP_CFG_MODE(2), QS_XTR_GRP_CFG, 0); + + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_LLP, 0xffffffff); + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_FRM, 0xffffffff); + + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_LLP_ENA, + BIT(MSCC_FDMA_INJ_CHAN) | BIT(MSCC_FDMA_XTR_CHAN)); + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_FRM_ENA, + BIT(MSCC_FDMA_XTR_CHAN)); + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_ENA, + BIT(MSCC_FDMA_INJ_CHAN) | BIT(MSCC_FDMA_XTR_CHAN)); + + napi_enable(&fdma->napi); + + ocelot_fdma_activate_chan(ocelot, ocelot->fdma->rx_ring.dcbs_dma, + MSCC_FDMA_XTR_CHAN); +} + +void ocelot_fdma_deinit(struct ocelot *ocelot) +{ + struct ocelot_fdma *fdma = ocelot->fdma; + + ocelot_fdma_writel(ocelot, MSCC_FDMA_INTR_ENA, 0); + ocelot_fdma_writel(ocelot, MSCC_FDMA_CH_FORCEDIS, + BIT(MSCC_FDMA_XTR_CHAN)); + ocelot_fdma_writel(ocelot, MSCC_FDMA_CH_FORCEDIS, + BIT(MSCC_FDMA_INJ_CHAN)); + napi_synchronize(&fdma->napi); + napi_disable(&fdma->napi); + + ocelot_fdma_free_rx_ring(ocelot); + ocelot_fdma_free_tx_ring(ocelot); +} diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.h b/drivers/net/ethernet/mscc/ocelot_fdma.h new file mode 100644 index 000000000000..2fc8e1dd7230 --- /dev/null +++ b/drivers/net/ethernet/mscc/ocelot_fdma.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Microsemi SoCs FDMA driver + * + * Copyright (c) 2021 Microchip + */ +#ifndef _MSCC_OCELOT_FDMA_H_ +#define _MSCC_OCELOT_FDMA_H_ + +#include "ocelot.h" + +#define MSCC_FDMA_DCB_STAT_BLOCKO(x) (((x) << 20) & GENMASK(31, 20)) +#define MSCC_FDMA_DCB_STAT_BLOCKO_M GENMASK(31, 20) +#define MSCC_FDMA_DCB_STAT_BLOCKO_X(x) (((x) & GENMASK(31, 20)) >> 20) +#define MSCC_FDMA_DCB_STAT_PD BIT(19) +#define MSCC_FDMA_DCB_STAT_ABORT BIT(18) +#define MSCC_FDMA_DCB_STAT_EOF BIT(17) +#define MSCC_FDMA_DCB_STAT_SOF BIT(16) +#define MSCC_FDMA_DCB_STAT_BLOCKL_M GENMASK(15, 0) +#define MSCC_FDMA_DCB_STAT_BLOCKL(x) ((x) & GENMASK(15, 0)) + +#define MSCC_FDMA_DCB_LLP(x) ((x) * 4 + 0x0) +#define MSCC_FDMA_DCB_LLP_PREV(x) ((x) * 4 + 0xA0) +#define MSCC_FDMA_CH_SAFE 0xcc +#define MSCC_FDMA_CH_ACTIVATE 0xd0 +#define MSCC_FDMA_CH_DISABLE 0xd4 +#define MSCC_FDMA_CH_FORCEDIS 0xd8 +#define MSCC_FDMA_EVT_ERR 0x164 +#define MSCC_FDMA_EVT_ERR_CODE 0x168 +#define MSCC_FDMA_INTR_LLP 0x16c +#define MSCC_FDMA_INTR_LLP_ENA 0x170 +#define MSCC_FDMA_INTR_FRM 0x174 +#define MSCC_FDMA_INTR_FRM_ENA 0x178 +#define MSCC_FDMA_INTR_ENA 0x184 +#define MSCC_FDMA_INTR_IDENT 0x188 + +#define MSCC_FDMA_INJ_CHAN 2 +#define MSCC_FDMA_XTR_CHAN 0 + +#define OCELOT_FDMA_WEIGHT 32 + +#define OCELOT_FDMA_CH_SAFE_TIMEOUT_US 10 + +#define OCELOT_FDMA_RX_RING_SIZE 512 +#define OCELOT_FDMA_TX_RING_SIZE 128 + +#define OCELOT_FDMA_RX_DCB_SIZE (OCELOT_FDMA_RX_RING_SIZE * \ + sizeof(struct ocelot_fdma_dcb)) +#define OCELOT_FDMA_TX_DCB_SIZE (OCELOT_FDMA_TX_RING_SIZE * \ + sizeof(struct ocelot_fdma_dcb)) +/* +4 allows for word alignment after allocation */ +#define OCELOT_DCBS_HW_ALLOC_SIZE (OCELOT_FDMA_RX_DCB_SIZE + \ + OCELOT_FDMA_TX_DCB_SIZE + \ + 4) + +#define OCELOT_FDMA_RX_SIZE (PAGE_SIZE / 2) + +#define OCELOT_FDMA_SKBFRAG_OVR (4 + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) +#define OCELOT_FDMA_RXB_SIZE ALIGN_DOWN(OCELOT_FDMA_RX_SIZE - OCELOT_FDMA_SKBFRAG_OVR, 4) +#define OCELOT_FDMA_SKBFRAG_SIZE (OCELOT_FDMA_RXB_SIZE + OCELOT_FDMA_SKBFRAG_OVR) + +DECLARE_STATIC_KEY_FALSE(ocelot_fdma_enabled); + +struct ocelot_fdma_dcb { + u32 llp; + u32 datap; + u32 datal; + u32 stat; +} __packed; + +/** + * struct ocelot_fdma_tx_buf - TX buffer structure + * @skb: SKB currently used in the corresponding DCB. + * @dma_addr: SKB DMA mapped address. + */ +struct ocelot_fdma_tx_buf { + struct sk_buff *skb; + DEFINE_DMA_UNMAP_ADDR(dma_addr); +}; + +/** + * struct ocelot_fdma_tx_ring - TX ring description of DCBs + * + * @dcbs: DCBs allocated for the ring + * @dcbs_dma: DMA base address of the DCBs + * @bufs: List of TX buffer associated to the DCBs + * @xmit_lock: lock for concurrent xmit access + * @next_to_clean: Next DCB to be cleaned in tx_cleanup + * @next_to_use: Next available DCB to send SKB + */ +struct ocelot_fdma_tx_ring { + struct ocelot_fdma_dcb *dcbs; + dma_addr_t dcbs_dma; + struct ocelot_fdma_tx_buf bufs[OCELOT_FDMA_TX_RING_SIZE]; + /* Protect concurrent xmit calls */ + spinlock_t xmit_lock; + u16 next_to_clean; + u16 next_to_use; +}; + +/** + * struct ocelot_fdma_rx_buf - RX buffer structure + * @page: Struct page used in this buffer + * @page_offset: Current page offset (either 0 or PAGE_SIZE/2) + * @dma_addr: DMA address of the page + */ +struct ocelot_fdma_rx_buf { + struct page *page; + u32 page_offset; + dma_addr_t dma_addr; +}; + +/** + * struct ocelot_fdma_rx_ring - TX ring description of DCBs + * + * @dcbs: DCBs allocated for the ring + * @dcbs_dma: DMA base address of the DCBs + * @bufs: List of RX buffer associated to the DCBs + * @skb: SKB currently received by the netdev + * @next_to_clean: Next DCB to be cleaned NAPI polling + * @next_to_use: Next available DCB to send SKB + * @next_to_alloc: Next buffer that needs to be allocated (page reuse or alloc) + */ +struct ocelot_fdma_rx_ring { + struct ocelot_fdma_dcb *dcbs; + dma_addr_t dcbs_dma; + struct ocelot_fdma_rx_buf bufs[OCELOT_FDMA_RX_RING_SIZE]; + struct sk_buff *skb; + u16 next_to_clean; + u16 next_to_use; + u16 next_to_alloc; +}; + +/** + * struct ocelot_fdma - FDMA context + * + * @irq: FDMA interrupt + * @ndev: Net device used to initialize NAPI + * @dcbs_base: Memory coherent DCBs + * @dcbs_dma_base: DMA base address of memory coherent DCBs + * @tx_ring: Injection ring + * @rx_ring: Extraction ring + * @napi: NAPI context + * @ocelot: Back-pointer to ocelot struct + */ +struct ocelot_fdma { + int irq; + struct net_device *ndev; + struct ocelot_fdma_dcb *dcbs_base; + dma_addr_t dcbs_dma_base; + struct ocelot_fdma_tx_ring tx_ring; + struct ocelot_fdma_rx_ring rx_ring; + struct napi_struct napi; + struct ocelot *ocelot; +}; + +void ocelot_fdma_init(struct platform_device *pdev, struct ocelot *ocelot); +void ocelot_fdma_start(struct ocelot *ocelot); +void ocelot_fdma_deinit(struct ocelot *ocelot); +int ocelot_fdma_inject_frame(struct ocelot *fdma, int port, u32 rew_op, + struct sk_buff *skb, struct net_device *dev); +void ocelot_fdma_netdev_init(struct ocelot *ocelot, struct net_device *dev); +void ocelot_fdma_netdev_deinit(struct ocelot *ocelot, + struct net_device *dev); + +#endif diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 0fcf359a6975..8115c3db252e 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -15,6 +15,7 @@ #include <net/pkt_cls.h> #include "ocelot.h" #include "ocelot_vcap.h" +#include "ocelot_fdma.h" #define OCELOT_MAC_QUIRKS OCELOT_QUIRK_QSGMII_PORTS_MUST_BE_UP @@ -457,7 +458,8 @@ static netdev_tx_t ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) int port = priv->chip_port; u32 rew_op = 0; - if (!ocelot_can_inject(ocelot, 0)) + if (!static_branch_unlikely(&ocelot_fdma_enabled) && + !ocelot_can_inject(ocelot, 0)) return NETDEV_TX_BUSY; /* Check if timestamping is needed */ @@ -475,9 +477,13 @@ static netdev_tx_t ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) rew_op = ocelot_ptp_rew_op(skb); } - ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + if (static_branch_unlikely(&ocelot_fdma_enabled)) { + ocelot_fdma_inject_frame(ocelot, port, rew_op, skb, dev); + } else { + ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); - kfree_skb(skb); + consume_skb(skb); + } return NETDEV_TX_OK; } @@ -764,10 +770,23 @@ static int ocelot_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return phy_mii_ioctl(dev->phydev, ifr, cmd); } +static int ocelot_change_mtu(struct net_device *dev, int new_mtu) +{ + struct ocelot_port_private *priv = netdev_priv(dev); + struct ocelot_port *ocelot_port = &priv->port; + struct ocelot *ocelot = ocelot_port->ocelot; + + ocelot_port_set_maxlen(ocelot, priv->chip_port, new_mtu); + WRITE_ONCE(dev->mtu, new_mtu); + + return 0; +} + static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_open = ocelot_port_open, .ndo_stop = ocelot_port_stop, .ndo_start_xmit = ocelot_port_xmit, + .ndo_change_mtu = ocelot_change_mtu, .ndo_set_rx_mode = ocelot_set_rx_mode, .ndo_set_mac_address = ocelot_port_set_mac_address, .ndo_get_stats64 = ocelot_get_stats64, @@ -1670,12 +1689,16 @@ int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target, dev->netdev_ops = &ocelot_port_netdev_ops; dev->ethtool_ops = &ocelot_ethtool_ops; + dev->max_mtu = OCELOT_JUMBO_MTU; dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXFCS | NETIF_F_HW_TC; dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_TC; - eth_hw_addr_gen(dev, ocelot->base_mac, port); + err = of_get_ethdev_address(portnp, dev); + if (err) + eth_hw_addr_gen(dev, ocelot->base_mac, port); + ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, OCELOT_VLAN_UNAWARE_PVID, ENTRYTYPE_LOCKED); @@ -1685,14 +1708,20 @@ int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target, if (err) goto out; + if (ocelot->fdma) + ocelot_fdma_netdev_init(ocelot, dev); + err = register_netdev(dev); if (err) { dev_err(ocelot->dev, "register_netdev failed\n"); - goto out; + goto out_fdma_deinit; } return 0; +out_fdma_deinit: + if (ocelot->fdma) + ocelot_fdma_netdev_deinit(ocelot, dev); out: ocelot->ports[port] = NULL; free_netdev(dev); @@ -1705,9 +1734,14 @@ void ocelot_release_port(struct ocelot_port *ocelot_port) struct ocelot_port_private *priv = container_of(ocelot_port, struct ocelot_port_private, port); + struct ocelot *ocelot = ocelot_port->ocelot; + struct ocelot_fdma *fdma = ocelot->fdma; unregister_netdev(priv->dev); + if (fdma) + ocelot_fdma_netdev_deinit(ocelot, priv->dev); + if (priv->phylink) { rtnl_lock(); phylink_disconnect_phy(priv->phylink); diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 2db59060f5ab..4f4a495a60ad 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -19,6 +19,7 @@ #include <soc/mscc/ocelot_vcap.h> #include <soc/mscc/ocelot_hsio.h> #include <soc/mscc/vsc7514_regs.h> +#include "ocelot_fdma.h" #include "ocelot.h" #define VSC7514_VCAP_POLICER_BASE 128 @@ -550,6 +551,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) { S1, "s1" }, { S2, "s2" }, { PTP, "ptp", 1 }, + { FDMA, "fdma", 1 }, }; if (!np && !pdev->dev.platform_data) @@ -585,6 +587,9 @@ static int mscc_ocelot_probe(struct platform_device *pdev) ocelot->targets[io_target[i].id] = target; } + if (ocelot->targets[FDMA]) + ocelot_fdma_init(pdev, ocelot); + hsio = syscon_regmap_lookup_by_compatible("mscc,ocelot-hsio"); if (IS_ERR(hsio)) { dev_err(&pdev->dev, "missing hsio syscon\n"); @@ -648,6 +653,9 @@ static int mscc_ocelot_probe(struct platform_device *pdev) if (err) goto out_ocelot_devlink_unregister; + if (ocelot->fdma) + ocelot_fdma_start(ocelot); + err = ocelot_devlink_sb_register(ocelot); if (err) goto out_ocelot_release_ports; @@ -688,6 +696,8 @@ static int mscc_ocelot_remove(struct platform_device *pdev) { struct ocelot *ocelot = platform_get_drvdata(pdev); + if (ocelot->fdma) + ocelot_fdma_deinit(ocelot); devlink_unregister(ocelot->devlink); ocelot_deinit_timestamp(ocelot); ocelot_devlink_sb_unregister(ocelot); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 1969009a91e7..2c2e9e56ed4e 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -3159,10 +3159,6 @@ static int vxge_hwtstamp_set(struct vxgedev *vdev, void __user *data) if (copy_from_user(&config, data, sizeof(config))) return -EFAULT; - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - /* Transmit HW Timestamp not supported */ switch (config.tx_type) { case HWTSTAMP_TX_OFF: diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index 0c60a436a8f2..f448c5682594 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -43,15 +43,14 @@ static int nfp_release_stats_entry(struct nfp_app *app, u32 stats_context_id) struct circ_buf *ring; ring = &priv->stats_ids.free_list; - /* Check if buffer is full. */ - if (!CIRC_SPACE(ring->head, ring->tail, - priv->stats_ring_size * NFP_FL_STATS_ELEM_RS - - NFP_FL_STATS_ELEM_RS + 1)) + /* Check if buffer is full, stats_ring_size must be power of 2 */ + if (!CIRC_SPACE(ring->head, ring->tail, priv->stats_ring_size)) return -ENOBUFS; - memcpy(&ring->buf[ring->head], &stats_context_id, NFP_FL_STATS_ELEM_RS); - ring->head = (ring->head + NFP_FL_STATS_ELEM_RS) % - (priv->stats_ring_size * NFP_FL_STATS_ELEM_RS); + /* Each increment of head represents size of NFP_FL_STATS_ELEM_RS */ + memcpy(&ring->buf[ring->head * NFP_FL_STATS_ELEM_RS], + &stats_context_id, NFP_FL_STATS_ELEM_RS); + ring->head = (ring->head + 1) & (priv->stats_ring_size - 1); return 0; } @@ -86,11 +85,14 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id) return -ENOENT; } - memcpy(&temp_stats_id, &ring->buf[ring->tail], NFP_FL_STATS_ELEM_RS); + /* Each increment of tail represents size of NFP_FL_STATS_ELEM_RS */ + memcpy(&temp_stats_id, &ring->buf[ring->tail * NFP_FL_STATS_ELEM_RS], + NFP_FL_STATS_ELEM_RS); *stats_context_id = temp_stats_id; - memcpy(&ring->buf[ring->tail], &freed_stats_id, NFP_FL_STATS_ELEM_RS); - ring->tail = (ring->tail + NFP_FL_STATS_ELEM_RS) % - (priv->stats_ring_size * NFP_FL_STATS_ELEM_RS); + memcpy(&ring->buf[ring->tail * NFP_FL_STATS_ELEM_RS], &freed_stats_id, + NFP_FL_STATS_ELEM_RS); + /* stats_ring_size must be power of 2 */ + ring->tail = (ring->tail + 1) & (priv->stats_ring_size - 1); return 0; } @@ -138,13 +140,18 @@ static int nfp_release_mask_id(struct nfp_app *app, u8 mask_id) struct circ_buf *ring; ring = &priv->mask_ids.mask_id_free_list; - /* Checking if buffer is full. */ + /* Checking if buffer is full, + * NFP_FLOWER_MASK_ENTRY_RS must be power of 2 + */ if (CIRC_SPACE(ring->head, ring->tail, NFP_FLOWER_MASK_ENTRY_RS) == 0) return -ENOBUFS; - memcpy(&ring->buf[ring->head], &mask_id, NFP_FLOWER_MASK_ELEMENT_RS); - ring->head = (ring->head + NFP_FLOWER_MASK_ELEMENT_RS) % - (NFP_FLOWER_MASK_ENTRY_RS * NFP_FLOWER_MASK_ELEMENT_RS); + /* Each increment of head represents size of + * NFP_FLOWER_MASK_ELEMENT_RS + */ + memcpy(&ring->buf[ring->head * NFP_FLOWER_MASK_ELEMENT_RS], &mask_id, + NFP_FLOWER_MASK_ELEMENT_RS); + ring->head = (ring->head + 1) & (NFP_FLOWER_MASK_ENTRY_RS - 1); priv->mask_ids.last_used[mask_id] = ktime_get(); @@ -171,7 +178,11 @@ static int nfp_mask_alloc(struct nfp_app *app, u8 *mask_id) if (ring->head == ring->tail) goto err_not_found; - memcpy(&temp_id, &ring->buf[ring->tail], NFP_FLOWER_MASK_ELEMENT_RS); + /* Each increment of tail represents size of + * NFP_FLOWER_MASK_ELEMENT_RS + */ + memcpy(&temp_id, &ring->buf[ring->tail * NFP_FLOWER_MASK_ELEMENT_RS], + NFP_FLOWER_MASK_ELEMENT_RS); *mask_id = temp_id; reuse_timeout = ktime_add_ns(priv->mask_ids.last_used[*mask_id], @@ -180,9 +191,10 @@ static int nfp_mask_alloc(struct nfp_app *app, u8 *mask_id) if (ktime_before(ktime_get(), reuse_timeout)) goto err_not_found; - memcpy(&ring->buf[ring->tail], &freed_id, NFP_FLOWER_MASK_ELEMENT_RS); - ring->tail = (ring->tail + NFP_FLOWER_MASK_ELEMENT_RS) % - (NFP_FLOWER_MASK_ENTRY_RS * NFP_FLOWER_MASK_ELEMENT_RS); + memcpy(&ring->buf[ring->tail * NFP_FLOWER_MASK_ELEMENT_RS], &freed_id, + NFP_FLOWER_MASK_ELEMENT_RS); + /* NFP_FLOWER_MASK_ENTRY_RS must be power of 2 */ + ring->tail = (ring->tail + 1) & (NFP_FLOWER_MASK_ENTRY_RS - 1); return 0; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c index d7ac0307797f..34c0d2ddf9ef 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c @@ -803,8 +803,10 @@ int nfp_cpp_area_cache_add(struct nfp_cpp *cpp, size_t size) return -ENOMEM; cache = kzalloc(sizeof(*cache), GFP_KERNEL); - if (!cache) + if (!cache) { + nfp_cpp_area_free(area); return -ENOMEM; + } cache->id = 0; cache->addr = 0; diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 71d234291fc5..1dc40c537281 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -210,9 +210,6 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) /* reserved for future extensions */ - return -EINVAL; - /* Get ieee1588's dev information */ pdev = adapter->ptp_pdev; diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index e113fbd56e86..5ea9cb4311a1 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1644,6 +1644,13 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev) data_split = true; } } else { + if (unlikely(skb->len > ETH_TX_MAX_NON_LSO_PKT_LEN)) { + DP_ERR(edev, "Unexpected non LSO skb length = 0x%x\n", skb->len); + qede_free_failed_tx_pkt(txq, first_bd, 0, false); + qede_update_tx_producer(txq); + return NETDEV_TX_OK; + } + val |= ((skb->len & ETH_TX_DATA_1ST_BD_PKT_LEN_MASK) << ETH_TX_DATA_1ST_BD_PKT_LEN_SHIFT); } diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index 8c28fabb0ff6..39176e765767 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -304,11 +304,6 @@ int qede_ptp_hw_ts(struct qede_dev *edev, struct ifreq *ifr) "HWTSTAMP IOCTL: Requested tx_type = %d, requested rx_filters = %d\n", config.tx_type, config.rx_filter); - if (config.flags) { - DP_ERR(edev, "config.flags is reserved for future use\n"); - return -EINVAL; - } - ptp->hw_ts_ioctl_called = 1; ptp->tx_type = config.tx_type; ptp->rx_filter = config.rx_filter; diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index 1e6d72adfe43..71523d747e93 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -3480,20 +3480,19 @@ static int ql_adapter_up(struct ql3_adapter *qdev) spin_lock_irqsave(&qdev->hw_lock, hw_flags); - err = ql_wait_for_drvr_lock(qdev); - if (err) { - err = ql_adapter_initialize(qdev); - if (err) { - netdev_err(ndev, "Unable to initialize adapter\n"); - goto err_init; - } - netdev_err(ndev, "Releasing driver lock\n"); - ql_sem_unlock(qdev, QL_DRVR_SEM_MASK); - } else { + if (!ql_wait_for_drvr_lock(qdev)) { netdev_err(ndev, "Could not acquire driver lock\n"); + err = -ENODEV; goto err_lock; } + err = ql_adapter_initialize(qdev); + if (err) { + netdev_err(ndev, "Unable to initialize adapter\n"); + goto err_init; + } + ql_sem_unlock(qdev, QL_DRVR_SEM_MASK); + spin_unlock_irqrestore(&qdev->hw_lock, hw_flags); set_bit(QL_ADAPTER_UP, &qdev->flags); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ce09bd45527e..b215cde68e10 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2221,10 +2221,6 @@ static int ravb_hwtstamp_set(struct net_device *ndev, struct ifreq *req) if (copy_from_user(&config, req->ifr_data, sizeof(config))) return -EFAULT; - /* Reserved for future extensions */ - if (config.flags) - return -EINVAL; - switch (config.tx_type) { case HWTSTAMP_TX_OFF: tstamp_tx_ctrl = 0; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 223626290ce0..d947a628e166 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3368,8 +3368,7 @@ static int sh_eth_drv_probe(struct platform_device *pdev) /* MDIO bus init */ ret = sh_mdio_init(mdp, pd); if (ret) { - if (ret != -EPROBE_DEFER) - dev_err(&pdev->dev, "MDIO init failed: %d\n", ret); + dev_err_probe(&pdev->dev, ret, "MDIO init failed\n"); goto out_release; } diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 5a6fed33a1d7..f79b14a119ae 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -609,6 +609,9 @@ static size_t ef100_update_stats(struct efx_nic *efx, ef100_common_stat_mask(mask); ef100_ethtool_stat_mask(mask); + if (!mc_stats) + return 0; + efx_nic_copy_stats(efx, mc_stats); efx_nic_update_stats(ef100_stat_desc, EF100_STAT_COUNT, mask, stats, mc_stats, false); diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 797e51802ccb..f0ef515e2ade 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1765,9 +1765,6 @@ static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init) { int rc; - if (init->flags) - return -EINVAL; - if ((init->tx_type != HWTSTAMP_TX_OFF) && (init->tx_type != HWTSTAMP_TX_ON)) return -ERANGE; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 9160f9ed363a..6b5d96bced47 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -317,6 +317,7 @@ enum tx_frame_status { tx_not_ls = 0x1, tx_err = 0x2, tx_dma_own = 0x4, + tx_err_bump_tc = 0x8, }; enum dma_irq_status { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 6924a6aacbd5..c469abc91fa1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -33,6 +33,7 @@ struct rk_gmac_ops { void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed); void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed); void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv); + bool regs_valid; u32 regs[]; }; @@ -1092,6 +1093,7 @@ static const struct rk_gmac_ops rk3568_ops = { .set_to_rmii = rk3568_set_to_rmii, .set_rgmii_speed = rk3568_set_gmac_speed, .set_rmii_speed = rk3568_set_gmac_speed, + .regs_valid = true, .regs = { 0xfe2a0000, /* gmac0 */ 0xfe010000, /* gmac1 */ @@ -1383,7 +1385,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev, * to be distinguished. */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (res) { + if (res && ops->regs_valid) { int i = 0; while (ops->regs[i]) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index cbf4429fb1d2..d3b4765c1a5b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -32,6 +32,8 @@ static int dwmac4_wrback_get_tx_status(void *data, struct stmmac_extra_stats *x, return tx_not_ls; if (unlikely(tdes3 & TDES3_ERROR_SUMMARY)) { + ret = tx_err; + if (unlikely(tdes3 & TDES3_JABBER_TIMEOUT)) x->tx_jabber++; if (unlikely(tdes3 & TDES3_PACKET_FLUSHED)) @@ -53,16 +55,16 @@ static int dwmac4_wrback_get_tx_status(void *data, struct stmmac_extra_stats *x, if (unlikely(tdes3 & TDES3_EXCESSIVE_DEFERRAL)) x->tx_deferred++; - if (unlikely(tdes3 & TDES3_UNDERFLOW_ERROR)) + if (unlikely(tdes3 & TDES3_UNDERFLOW_ERROR)) { x->tx_underflow++; + ret |= tx_err_bump_tc; + } if (unlikely(tdes3 & TDES3_IP_HDR_ERROR)) x->tx_ip_header_error++; if (unlikely(tdes3 & TDES3_PAYLOAD_ERROR)) x->tx_payload_error++; - - ret = tx_err; } if (unlikely(tdes3 & TDES3_DEFERRED)) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 4f5292cadf54..18a262ef17f6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -171,6 +171,19 @@ struct stmmac_flow_entry { int is_l4; }; +/* Rx Frame Steering */ +enum stmmac_rfs_type { + STMMAC_RFS_T_VLAN, + STMMAC_RFS_T_MAX, +}; + +struct stmmac_rfs_entry { + unsigned long cookie; + int in_use; + int type; + int tc; +}; + struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ u32 tx_coal_frames[MTL_MAX_TX_QUEUES]; @@ -288,6 +301,10 @@ struct stmmac_priv { struct stmmac_tc_entry *tc_entries; unsigned int flow_entries_max; struct stmmac_flow_entry *flow_entries; + unsigned int rfs_entries_max[STMMAC_RFS_T_MAX]; + unsigned int rfs_entries_cnt[STMMAC_RFS_T_MAX]; + unsigned int rfs_entries_total; + struct stmmac_rfs_entry *rfs_entries; /* Pulse Per Second output */ struct stmmac_pps_cfg pps[STMMAC_PPS_MAX]; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4e05c1d92935..fd50e5783e8f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -132,6 +132,8 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data); static irqreturn_t stmmac_msi_intr_rx(int irq, void *data); static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue); static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue); +static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, + u32 rxmode, u32 chan); #ifdef CONFIG_DEBUG_FS static const struct net_device_ops stmmac_netdev_ops; @@ -636,10 +638,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) netdev_dbg(priv->dev, "%s config flags:0x%x, tx_type:0x%x, rx_filter:0x%x\n", __func__, config.flags, config.tx_type, config.rx_filter); - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - if (config.tx_type != HWTSTAMP_TX_OFF && config.tx_type != HWTSTAMP_TX_ON) return -ERANGE; @@ -1453,16 +1451,20 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i]; + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + if (priv->dma_cap.addr64 <= 32) + gfp |= GFP_DMA32; if (!buf->page) { - buf->page = page_pool_dev_alloc_pages(rx_q->page_pool); + buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->page) return -ENOMEM; buf->page_offset = stmmac_rx_offset(priv); } if (priv->sph && !buf->sec_page) { - buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool); + buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->sec_page) return -ENOMEM; @@ -2466,6 +2468,21 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) return !!budget && work_done; } +static void stmmac_bump_dma_threshold(struct stmmac_priv *priv, u32 chan) +{ + if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && tc <= 256) { + tc += 64; + + if (priv->plat->force_thresh_dma_mode) + stmmac_set_dma_operation_mode(priv, tc, tc, chan); + else + stmmac_set_dma_operation_mode(priv, tc, SF_DMA_MODE, + chan); + + priv->xstats.threshold = tc; + } +} + /** * stmmac_tx_clean - to manage the transmission completion * @priv: driver private structure @@ -2531,6 +2548,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) /* ... verify the status error condition */ if (unlikely(status & tx_err)) { priv->dev->stats.tx_errors++; + if (unlikely(status & tx_err_bump_tc)) + stmmac_bump_dma_threshold(priv, queue); } else { priv->dev->stats.tx_packets++; priv->xstats.tx_pkt_n++; @@ -2781,21 +2800,7 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) for (chan = 0; chan < tx_channel_count; chan++) { if (unlikely(status[chan] & tx_hard_error_bump_tc)) { /* Try to bump up the dma threshold on this failure */ - if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && - (tc <= 256)) { - tc += 64; - if (priv->plat->force_thresh_dma_mode) - stmmac_set_dma_operation_mode(priv, - tc, - tc, - chan); - else - stmmac_set_dma_operation_mode(priv, - tc, - SF_DMA_MODE, - chan); - priv->xstats.threshold = tc; - } + stmmac_bump_dma_threshold(priv, chan); } else if (unlikely(status[chan] == tx_hard_error)) { stmmac_tx_err(priv, chan); } @@ -4474,6 +4479,10 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; int dirty = stmmac_rx_dirty(priv, queue); unsigned int entry = rx_q->dirty_rx; + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + if (priv->dma_cap.addr64 <= 32) + gfp |= GFP_DMA32; while (dirty-- > 0) { struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry]; @@ -4486,13 +4495,13 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) p = rx_q->dma_rx + entry; if (!buf->page) { - buf->page = page_pool_dev_alloc_pages(rx_q->page_pool); + buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->page) break; } if (priv->sph && !buf->sec_page) { - buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool); + buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp); if (!buf->sec_page) break; @@ -5745,21 +5754,7 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data) if (unlikely(status & tx_hard_error_bump_tc)) { /* Try to bump up the dma threshold on this failure */ - if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && - tc <= 256) { - tc += 64; - if (priv->plat->force_thresh_dma_mode) - stmmac_set_dma_operation_mode(priv, - tc, - tc, - chan); - else - stmmac_set_dma_operation_mode(priv, - tc, - SF_DMA_MODE, - chan); - priv->xstats.threshold = tc; - } + stmmac_bump_dma_threshold(priv, chan); } else if (unlikely(status == tx_hard_error)) { stmmac_tx_err(priv, chan); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 1c4ea0b1b845..d0a2b289f460 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -232,11 +232,33 @@ static int tc_setup_cls_u32(struct stmmac_priv *priv, } } +static int tc_rfs_init(struct stmmac_priv *priv) +{ + int i; + + priv->rfs_entries_max[STMMAC_RFS_T_VLAN] = 8; + + for (i = 0; i < STMMAC_RFS_T_MAX; i++) + priv->rfs_entries_total += priv->rfs_entries_max[i]; + + priv->rfs_entries = devm_kcalloc(priv->device, + priv->rfs_entries_total, + sizeof(*priv->rfs_entries), + GFP_KERNEL); + if (!priv->rfs_entries) + return -ENOMEM; + + dev_info(priv->device, "Enabled RFS Flow TC (entries=%d)\n", + priv->rfs_entries_total); + + return 0; +} + static int tc_init(struct stmmac_priv *priv) { struct dma_features *dma_cap = &priv->dma_cap; unsigned int count; - int i; + int ret, i; if (dma_cap->l3l4fnum) { priv->flow_entries_max = dma_cap->l3l4fnum; @@ -250,10 +272,14 @@ static int tc_init(struct stmmac_priv *priv) for (i = 0; i < priv->flow_entries_max; i++) priv->flow_entries[i].idx = i; - dev_info(priv->device, "Enabled Flow TC (entries=%d)\n", + dev_info(priv->device, "Enabled L3L4 Flow TC (entries=%d)\n", priv->flow_entries_max); } + ret = tc_rfs_init(priv); + if (ret) + return -ENOMEM; + if (!priv->plat->fpe_cfg) { priv->plat->fpe_cfg = devm_kzalloc(priv->device, sizeof(*priv->plat->fpe_cfg), @@ -607,16 +633,45 @@ static int tc_del_flow(struct stmmac_priv *priv, return ret; } +static struct stmmac_rfs_entry *tc_find_rfs(struct stmmac_priv *priv, + struct flow_cls_offload *cls, + bool get_free) +{ + int i; + + for (i = 0; i < priv->rfs_entries_total; i++) { + struct stmmac_rfs_entry *entry = &priv->rfs_entries[i]; + + if (entry->cookie == cls->cookie) + return entry; + if (get_free && entry->in_use == false) + return entry; + } + + return NULL; +} + #define VLAN_PRIO_FULL_MASK (0x07) static int tc_add_vlan_flow(struct stmmac_priv *priv, struct flow_cls_offload *cls) { + struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false); struct flow_rule *rule = flow_cls_offload_flow_rule(cls); struct flow_dissector *dissector = rule->match.dissector; int tc = tc_classid_to_hwtc(priv->dev, cls->classid); struct flow_match_vlan match; + if (!entry) { + entry = tc_find_rfs(priv, cls, true); + if (!entry) + return -ENOENT; + } + + if (priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN] >= + priv->rfs_entries_max[STMMAC_RFS_T_VLAN]) + return -ENOENT; + /* Nothing to do here */ if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) return -EINVAL; @@ -638,6 +693,12 @@ static int tc_add_vlan_flow(struct stmmac_priv *priv, prio = BIT(match.key->vlan_priority); stmmac_rx_queue_prio(priv, priv->hw, prio, tc); + + entry->in_use = true; + entry->cookie = cls->cookie; + entry->tc = tc; + entry->type = STMMAC_RFS_T_VLAN; + priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]++; } return 0; @@ -646,20 +707,19 @@ static int tc_add_vlan_flow(struct stmmac_priv *priv, static int tc_del_vlan_flow(struct stmmac_priv *priv, struct flow_cls_offload *cls) { - struct flow_rule *rule = flow_cls_offload_flow_rule(cls); - struct flow_dissector *dissector = rule->match.dissector; - int tc = tc_classid_to_hwtc(priv->dev, cls->classid); + struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false); - /* Nothing to do here */ - if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) - return -EINVAL; + if (!entry || !entry->in_use || entry->type != STMMAC_RFS_T_VLAN) + return -ENOENT; - if (tc < 0) { - netdev_err(priv->dev, "Invalid traffic class\n"); - return -EINVAL; - } + stmmac_rx_queue_prio(priv, priv->hw, 0, entry->tc); + + entry->in_use = false; + entry->cookie = 0; + entry->tc = 0; + entry->type = 0; - stmmac_rx_queue_prio(priv, priv->hw, 0, tc); + priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]--; return 0; } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 750cea23e9cd..8251d7eb001b 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1844,13 +1844,14 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) if (ret < 0) { dev_err(dev, "%pOF error reading port_id %d\n", port_np, ret); - return ret; + goto of_node_put; } if (!port_id || port_id > common->port_num) { dev_err(dev, "%pOF has invalid port_id %u %s\n", port_np, port_id, port_np->name); - return -EINVAL; + ret = -EINVAL; + goto of_node_put; } port = am65_common_get_port(common, port_id); @@ -1866,8 +1867,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) (AM65_CPSW_NU_FRAM_PORT_OFFSET * (port_id - 1)); port->slave.mac_sl = cpsw_sl_get("am65", dev, port->port_base); - if (IS_ERR(port->slave.mac_sl)) - return PTR_ERR(port->slave.mac_sl); + if (IS_ERR(port->slave.mac_sl)) { + ret = PTR_ERR(port->slave.mac_sl); + goto of_node_put; + } port->disabled = !of_device_is_available(port_np); if (port->disabled) { @@ -1880,7 +1883,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) ret = PTR_ERR(port->slave.ifphy); dev_err(dev, "%pOF error retrieving port phy: %d\n", port_np, ret); - return ret; + goto of_node_put; } port->slave.mac_only = @@ -1889,10 +1892,12 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) /* get phy/link info */ if (of_phy_is_fixed_link(port_np)) { ret = of_phy_register_fixed_link(port_np); - if (ret) - return dev_err_probe(dev, ret, + if (ret) { + ret = dev_err_probe(dev, ret, "failed to register fixed-link phy %pOF\n", port_np); + goto of_node_put; + } port->slave.phy_node = of_node_get(port_np); } else { port->slave.phy_node = @@ -1902,14 +1907,15 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) if (!port->slave.phy_node) { dev_err(dev, "slave[%d] no phy found\n", port_id); - return -ENODEV; + ret = -ENODEV; + goto of_node_put; } ret = of_get_phy_mode(port_np, &port->slave.phy_if); if (ret) { dev_err(dev, "%pOF read phy-mode err %d\n", port_np, ret); - return ret; + goto of_node_put; } ret = of_get_mac_address(port_np, port->slave.mac_addr); @@ -1932,6 +1938,11 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) } return 0; + +of_node_put: + of_node_put(port_np); + of_node_put(node); + return ret; } static void am65_cpsw_pcpu_stats_free(void *data) diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index c99dd9735087..8624a044776f 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -626,10 +626,6 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - /* reserved for future extensions */ - if (cfg.flags) - return -EINVAL; - if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON) return -ERANGE; diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 33c1592d5381..751fb0bc65c5 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2654,10 +2654,6 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - /* reserved for future extensions */ - if (cfg.flags) - return -EINVAL; - switch (cfg.tx_type) { case HWTSTAMP_TX_OFF: gbe_dev->tx_ts_enabled = 0; diff --git a/drivers/net/ethernet/vertexcom/Kconfig b/drivers/net/ethernet/vertexcom/Kconfig new file mode 100644 index 000000000000..4184a635fe01 --- /dev/null +++ b/drivers/net/ethernet/vertexcom/Kconfig @@ -0,0 +1,25 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Vertexcom network device configuration +# + +config NET_VENDOR_VERTEXCOM + bool "Vertexcom devices" + default y + help + If you have a network (Ethernet) card belonging to this class, say Y. + + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about Vertexcom cards. If you say Y, you will be asked + for your specific card in the following questions. + +if NET_VENDOR_VERTEXCOM + +config MSE102X + tristate "Vertexcom MSE102x SPI" + depends on SPI + help + SPI driver for Vertexcom MSE102x SPI attached network chip. + +endif # NET_VENDOR_VERTEXCOM diff --git a/drivers/net/ethernet/vertexcom/Makefile b/drivers/net/ethernet/vertexcom/Makefile new file mode 100644 index 000000000000..f8b12e312637 --- /dev/null +++ b/drivers/net/ethernet/vertexcom/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the Vertexcom network device drivers. +# + +obj-$(CONFIG_MSE102X) += mse102x.o diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c new file mode 100644 index 000000000000..89a31783fbb4 --- /dev/null +++ b/drivers/net/ethernet/vertexcom/mse102x.c @@ -0,0 +1,769 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2021 in-tech smart charging GmbH + * + * driver is based on micrel/ks8851_spi.c + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/ethtool.h> +#include <linux/cache.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> + +#include <linux/spi/spi.h> +#include <linux/of_net.h> + +#define MSG_DEFAULT (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | \ + NETIF_MSG_TIMER) + +#define DRV_NAME "mse102x" + +#define DET_CMD 0x0001 +#define DET_SOF 0x0002 +#define DET_DFT 0x55AA + +#define CMD_SHIFT 12 +#define CMD_RTS (0x1 << CMD_SHIFT) +#define CMD_CTR (0x2 << CMD_SHIFT) + +#define CMD_MASK GENMASK(15, CMD_SHIFT) +#define LEN_MASK GENMASK(CMD_SHIFT - 1, 0) + +#define DET_CMD_LEN 4 +#define DET_SOF_LEN 2 +#define DET_DFT_LEN 2 + +#define MIN_FREQ_HZ 6000000 +#define MAX_FREQ_HZ 7142857 + +struct mse102x_stats { + u64 xfer_err; + u64 invalid_cmd; + u64 invalid_ctr; + u64 invalid_dft; + u64 invalid_len; + u64 invalid_rts; + u64 invalid_sof; + u64 tx_timeout; +}; + +static const char mse102x_gstrings_stats[][ETH_GSTRING_LEN] = { + "SPI transfer errors", + "Invalid command", + "Invalid CTR", + "Invalid DFT", + "Invalid frame length", + "Invalid RTS", + "Invalid SOF", + "TX timeout", +}; + +struct mse102x_net { + struct net_device *ndev; + + u8 rxd[8]; + u8 txd[8]; + + u32 msg_enable ____cacheline_aligned; + + struct sk_buff_head txq; + struct mse102x_stats stats; +}; + +struct mse102x_net_spi { + struct mse102x_net mse102x; + struct mutex lock; /* Protect SPI frame transfer */ + struct work_struct tx_work; + struct spi_device *spidev; + struct spi_message spi_msg; + struct spi_transfer spi_xfer; + +#ifdef CONFIG_DEBUG_FS + struct dentry *device_root; +#endif +}; + +#define to_mse102x_spi(mse) container_of((mse), struct mse102x_net_spi, mse102x) + +#ifdef CONFIG_DEBUG_FS + +static int mse102x_info_show(struct seq_file *s, void *what) +{ + struct mse102x_net_spi *mses = s->private; + + seq_printf(s, "TX ring size : %u\n", + skb_queue_len(&mses->mse102x.txq)); + + seq_printf(s, "IRQ : %d\n", + mses->spidev->irq); + + seq_printf(s, "SPI effective speed : %lu\n", + (unsigned long)mses->spi_xfer.effective_speed_hz); + seq_printf(s, "SPI mode : %x\n", + mses->spidev->mode); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(mse102x_info); + +static void mse102x_init_device_debugfs(struct mse102x_net_spi *mses) +{ + mses->device_root = debugfs_create_dir(dev_name(&mses->mse102x.ndev->dev), + NULL); + + debugfs_create_file("info", S_IFREG | 0444, mses->device_root, mses, + &mse102x_info_fops); +} + +static void mse102x_remove_device_debugfs(struct mse102x_net_spi *mses) +{ + debugfs_remove_recursive(mses->device_root); +} + +#else /* CONFIG_DEBUG_FS */ + +static void mse102x_init_device_debugfs(struct mse102x_net_spi *mses) +{ +} + +static void mse102x_remove_device_debugfs(struct mse102x_net_spi *mses) +{ +} + +#endif + +/* SPI register read/write calls. + * + * All these calls issue SPI transactions to access the chip's registers. They + * all require that the necessary lock is held to prevent accesses when the + * chip is busy transferring packet data. + */ + +static void mse102x_tx_cmd_spi(struct mse102x_net *mse, u16 cmd) +{ + struct mse102x_net_spi *mses = to_mse102x_spi(mse); + struct spi_transfer *xfer = &mses->spi_xfer; + struct spi_message *msg = &mses->spi_msg; + __be16 txb[2]; + int ret; + + txb[0] = cpu_to_be16(DET_CMD); + txb[1] = cpu_to_be16(cmd); + + xfer->tx_buf = txb; + xfer->rx_buf = NULL; + xfer->len = DET_CMD_LEN; + + ret = spi_sync(mses->spidev, msg); + if (ret < 0) { + netdev_err(mse->ndev, "%s: spi_sync() failed: %d\n", + __func__, ret); + mse->stats.xfer_err++; + } +} + +static int mse102x_rx_cmd_spi(struct mse102x_net *mse, u8 *rxb) +{ + struct mse102x_net_spi *mses = to_mse102x_spi(mse); + struct spi_transfer *xfer = &mses->spi_xfer; + struct spi_message *msg = &mses->spi_msg; + __be16 *txb = (__be16 *)mse->txd; + __be16 *cmd = (__be16 *)mse->rxd; + u8 *trx = mse->rxd; + int ret; + + txb[0] = 0; + txb[1] = 0; + + xfer->tx_buf = txb; + xfer->rx_buf = trx; + xfer->len = DET_CMD_LEN; + + ret = spi_sync(mses->spidev, msg); + if (ret < 0) { + netdev_err(mse->ndev, "%s: spi_sync() failed: %d\n", + __func__, ret); + mse->stats.xfer_err++; + } else if (*cmd != cpu_to_be16(DET_CMD)) { + net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n", + __func__, *cmd); + mse->stats.invalid_cmd++; + ret = -EIO; + } else { + memcpy(rxb, trx + 2, 2); + } + + return ret; +} + +static inline void mse102x_push_header(struct sk_buff *skb) +{ + __be16 *header = skb_push(skb, DET_SOF_LEN); + + *header = cpu_to_be16(DET_SOF); +} + +static inline void mse102x_put_footer(struct sk_buff *skb) +{ + __be16 *footer = skb_put(skb, DET_DFT_LEN); + + *footer = cpu_to_be16(DET_DFT); +} + +static int mse102x_tx_frame_spi(struct mse102x_net *mse, struct sk_buff *txp, + unsigned int pad) +{ + struct mse102x_net_spi *mses = to_mse102x_spi(mse); + struct spi_transfer *xfer = &mses->spi_xfer; + struct spi_message *msg = &mses->spi_msg; + struct sk_buff *tskb; + int ret; + + netif_dbg(mse, tx_queued, mse->ndev, "%s: skb %p, %d@%p\n", + __func__, txp, txp->len, txp->data); + + if ((skb_headroom(txp) < DET_SOF_LEN) || + (skb_tailroom(txp) < DET_DFT_LEN + pad)) { + tskb = skb_copy_expand(txp, DET_SOF_LEN, DET_DFT_LEN + pad, + GFP_KERNEL); + if (!tskb) + return -ENOMEM; + + dev_kfree_skb(txp); + txp = tskb; + } + + mse102x_push_header(txp); + + if (pad) + skb_put_zero(txp, pad); + + mse102x_put_footer(txp); + + xfer->tx_buf = txp->data; + xfer->rx_buf = NULL; + xfer->len = txp->len; + + ret = spi_sync(mses->spidev, msg); + if (ret < 0) { + netdev_err(mse->ndev, "%s: spi_sync() failed: %d\n", + __func__, ret); + mse->stats.xfer_err++; + } + + return ret; +} + +static int mse102x_rx_frame_spi(struct mse102x_net *mse, u8 *buff, + unsigned int frame_len) +{ + struct mse102x_net_spi *mses = to_mse102x_spi(mse); + struct spi_transfer *xfer = &mses->spi_xfer; + struct spi_message *msg = &mses->spi_msg; + __be16 *sof = (__be16 *)buff; + __be16 *dft = (__be16 *)(buff + DET_SOF_LEN + frame_len); + int ret; + + xfer->rx_buf = buff; + xfer->tx_buf = NULL; + xfer->len = DET_SOF_LEN + frame_len + DET_DFT_LEN; + + ret = spi_sync(mses->spidev, msg); + if (ret < 0) { + netdev_err(mse->ndev, "%s: spi_sync() failed: %d\n", + __func__, ret); + mse->stats.xfer_err++; + } else if (*sof != cpu_to_be16(DET_SOF)) { + netdev_dbg(mse->ndev, "%s: SPI start of frame is invalid (0x%04x)\n", + __func__, *sof); + mse->stats.invalid_sof++; + ret = -EIO; + } else if (*dft != cpu_to_be16(DET_DFT)) { + netdev_dbg(mse->ndev, "%s: SPI frame tail is invalid (0x%04x)\n", + __func__, *dft); + mse->stats.invalid_dft++; + ret = -EIO; + } + + return ret; +} + +static void mse102x_dump_packet(const char *msg, int len, const char *data) +{ + printk(KERN_DEBUG ": %s - packet len:%d\n", msg, len); + print_hex_dump(KERN_DEBUG, "pk data: ", DUMP_PREFIX_OFFSET, 16, 1, + data, len, true); +} + +static void mse102x_rx_pkt_spi(struct mse102x_net *mse) +{ + struct sk_buff *skb; + unsigned int rxalign; + unsigned int rxlen; + __be16 rx = 0; + u16 cmd_resp; + u8 *rxpkt; + int ret; + + mse102x_tx_cmd_spi(mse, CMD_CTR); + ret = mse102x_rx_cmd_spi(mse, (u8 *)&rx); + cmd_resp = be16_to_cpu(rx); + + if (ret || ((cmd_resp & CMD_MASK) != CMD_RTS)) { + usleep_range(50, 100); + + mse102x_tx_cmd_spi(mse, CMD_CTR); + ret = mse102x_rx_cmd_spi(mse, (u8 *)&rx); + if (ret) + return; + + cmd_resp = be16_to_cpu(rx); + if ((cmd_resp & CMD_MASK) != CMD_RTS) { + net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n", + __func__, cmd_resp); + mse->stats.invalid_rts++; + return; + } + + net_dbg_ratelimited("%s: Unexpected response to first CMD\n", + __func__); + } + + rxlen = cmd_resp & LEN_MASK; + if (!rxlen) { + net_dbg_ratelimited("%s: No frame length defined\n", __func__); + mse->stats.invalid_len++; + return; + } + + rxalign = ALIGN(rxlen + DET_SOF_LEN + DET_DFT_LEN, 4); + skb = netdev_alloc_skb_ip_align(mse->ndev, rxalign); + if (!skb) + return; + + /* 2 bytes Start of frame (before ethernet header) + * 2 bytes Data frame tail (after ethernet frame) + * They are copied, but ignored. + */ + rxpkt = skb_put(skb, rxlen) - DET_SOF_LEN; + if (mse102x_rx_frame_spi(mse, rxpkt, rxlen)) { + mse->ndev->stats.rx_errors++; + dev_kfree_skb(skb); + return; + } + + if (netif_msg_pktdata(mse)) + mse102x_dump_packet(__func__, skb->len, skb->data); + + skb->protocol = eth_type_trans(skb, mse->ndev); + netif_rx_ni(skb); + + mse->ndev->stats.rx_packets++; + mse->ndev->stats.rx_bytes += rxlen; +} + +static int mse102x_tx_pkt_spi(struct mse102x_net *mse, struct sk_buff *txb, + unsigned long work_timeout) +{ + unsigned int pad = 0; + __be16 rx = 0; + u16 cmd_resp; + int ret; + bool first = true; + + if (txb->len < 60) + pad = 60 - txb->len; + + while (1) { + mse102x_tx_cmd_spi(mse, CMD_RTS | (txb->len + pad)); + ret = mse102x_rx_cmd_spi(mse, (u8 *)&rx); + cmd_resp = be16_to_cpu(rx); + + if (!ret) { + /* ready to send frame ? */ + if (cmd_resp == CMD_CTR) + break; + + net_dbg_ratelimited("%s: Unexpected response (0x%04x)\n", + __func__, cmd_resp); + mse->stats.invalid_ctr++; + } + + /* It's not predictable how long / many retries it takes to + * send at least one packet, so TX timeouts are possible. + * That's the reason why the netdev watchdog is not used here. + */ + if (time_after(jiffies, work_timeout)) + return -ETIMEDOUT; + + if (first) { + /* throttle at first issue */ + netif_stop_queue(mse->ndev); + /* fast retry */ + usleep_range(50, 100); + first = false; + } else { + msleep(20); + } + } + + ret = mse102x_tx_frame_spi(mse, txb, pad); + if (ret) + net_dbg_ratelimited("%s: Failed to send (%d), drop frame\n", + __func__, ret); + + return ret; +} + +#define TX_QUEUE_MAX 10 + +static void mse102x_tx_work(struct work_struct *work) +{ + /* Make sure timeout is sufficient to transfer TX_QUEUE_MAX frames */ + unsigned long work_timeout = jiffies + msecs_to_jiffies(1000); + struct mse102x_net_spi *mses; + struct mse102x_net *mse; + struct sk_buff *txb; + int ret = 0; + + mses = container_of(work, struct mse102x_net_spi, tx_work); + mse = &mses->mse102x; + + while ((txb = skb_dequeue(&mse->txq))) { + mutex_lock(&mses->lock); + ret = mse102x_tx_pkt_spi(mse, txb, work_timeout); + mutex_unlock(&mses->lock); + if (ret) { + mse->ndev->stats.tx_dropped++; + } else { + mse->ndev->stats.tx_bytes += txb->len; + mse->ndev->stats.tx_packets++; + } + + dev_kfree_skb(txb); + } + + if (ret == -ETIMEDOUT) { + if (netif_msg_timer(mse)) + netdev_err(mse->ndev, "tx work timeout\n"); + + mse->stats.tx_timeout++; + } + + netif_wake_queue(mse->ndev); +} + +static netdev_tx_t mse102x_start_xmit_spi(struct sk_buff *skb, + struct net_device *ndev) +{ + struct mse102x_net *mse = netdev_priv(ndev); + struct mse102x_net_spi *mses = to_mse102x_spi(mse); + + netif_dbg(mse, tx_queued, ndev, + "%s: skb %p, %d@%p\n", __func__, skb, skb->len, skb->data); + + skb_queue_tail(&mse->txq, skb); + + if (skb_queue_len(&mse->txq) >= TX_QUEUE_MAX) + netif_stop_queue(ndev); + + schedule_work(&mses->tx_work); + + return NETDEV_TX_OK; +} + +static void mse102x_init_mac(struct mse102x_net *mse, struct device_node *np) +{ + struct net_device *ndev = mse->ndev; + int ret = of_get_ethdev_address(np, ndev); + + if (ret) { + eth_hw_addr_random(ndev); + netdev_err(ndev, "Using random MAC address: %pM\n", + ndev->dev_addr); + } +} + +/* Assumption: this is called for every incoming packet */ +static irqreturn_t mse102x_irq(int irq, void *_mse) +{ + struct mse102x_net *mse = _mse; + struct mse102x_net_spi *mses = to_mse102x_spi(mse); + + mutex_lock(&mses->lock); + mse102x_rx_pkt_spi(mse); + mutex_unlock(&mses->lock); + + return IRQ_HANDLED; +} + +static int mse102x_net_open(struct net_device *ndev) +{ + struct mse102x_net *mse = netdev_priv(ndev); + int ret; + + ret = request_threaded_irq(ndev->irq, NULL, mse102x_irq, IRQF_ONESHOT, + ndev->name, mse); + if (ret < 0) { + netdev_err(ndev, "Failed to get irq: %d\n", ret); + return ret; + } + + netif_dbg(mse, ifup, ndev, "opening\n"); + + netif_start_queue(ndev); + + netif_carrier_on(ndev); + + netif_dbg(mse, ifup, ndev, "network device up\n"); + + return 0; +} + +static int mse102x_net_stop(struct net_device *ndev) +{ + struct mse102x_net *mse = netdev_priv(ndev); + struct mse102x_net_spi *mses = to_mse102x_spi(mse); + + netif_info(mse, ifdown, ndev, "shutting down\n"); + + netif_carrier_off(mse->ndev); + + /* stop any outstanding work */ + flush_work(&mses->tx_work); + + netif_stop_queue(ndev); + + skb_queue_purge(&mse->txq); + + free_irq(ndev->irq, mse); + + return 0; +} + +static const struct net_device_ops mse102x_netdev_ops = { + .ndo_open = mse102x_net_open, + .ndo_stop = mse102x_net_stop, + .ndo_start_xmit = mse102x_start_xmit_spi, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +}; + +/* ethtool support */ + +static void mse102x_get_drvinfo(struct net_device *ndev, + struct ethtool_drvinfo *di) +{ + strscpy(di->driver, DRV_NAME, sizeof(di->driver)); + strscpy(di->bus_info, dev_name(ndev->dev.parent), sizeof(di->bus_info)); +} + +static u32 mse102x_get_msglevel(struct net_device *ndev) +{ + struct mse102x_net *mse = netdev_priv(ndev); + + return mse->msg_enable; +} + +static void mse102x_set_msglevel(struct net_device *ndev, u32 to) +{ + struct mse102x_net *mse = netdev_priv(ndev); + + mse->msg_enable = to; +} + +static void mse102x_get_ethtool_stats(struct net_device *ndev, + struct ethtool_stats *estats, u64 *data) +{ + struct mse102x_net *mse = netdev_priv(ndev); + struct mse102x_stats *st = &mse->stats; + + memcpy(data, st, ARRAY_SIZE(mse102x_gstrings_stats) * sizeof(u64)); +} + +static void mse102x_get_strings(struct net_device *ndev, u32 stringset, u8 *buf) +{ + switch (stringset) { + case ETH_SS_STATS: + memcpy(buf, &mse102x_gstrings_stats, + sizeof(mse102x_gstrings_stats)); + break; + default: + WARN_ON(1); + break; + } +} + +static int mse102x_get_sset_count(struct net_device *ndev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return ARRAY_SIZE(mse102x_gstrings_stats); + default: + return -EINVAL; + } +} + +static const struct ethtool_ops mse102x_ethtool_ops = { + .get_drvinfo = mse102x_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_msglevel = mse102x_get_msglevel, + .set_msglevel = mse102x_set_msglevel, + .get_ethtool_stats = mse102x_get_ethtool_stats, + .get_strings = mse102x_get_strings, + .get_sset_count = mse102x_get_sset_count, +}; + +/* driver bus management functions */ + +#ifdef CONFIG_PM_SLEEP + +static int mse102x_suspend(struct device *dev) +{ + struct mse102x_net *mse = dev_get_drvdata(dev); + struct net_device *ndev = mse->ndev; + + if (netif_running(ndev)) { + netif_device_detach(ndev); + mse102x_net_stop(ndev); + } + + return 0; +} + +static int mse102x_resume(struct device *dev) +{ + struct mse102x_net *mse = dev_get_drvdata(dev); + struct net_device *ndev = mse->ndev; + + if (netif_running(ndev)) { + mse102x_net_open(ndev); + netif_device_attach(ndev); + } + + return 0; +} +#endif + +static SIMPLE_DEV_PM_OPS(mse102x_pm_ops, mse102x_suspend, mse102x_resume); + +static int mse102x_probe_spi(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct mse102x_net_spi *mses; + struct net_device *ndev; + struct mse102x_net *mse; + int ret; + + spi->bits_per_word = 8; + spi->mode |= SPI_MODE_3; + /* enforce minimum speed to ensure device functionality */ + spi->master->min_speed_hz = MIN_FREQ_HZ; + + if (!spi->max_speed_hz) + spi->max_speed_hz = MAX_FREQ_HZ; + + if (spi->max_speed_hz < MIN_FREQ_HZ || + spi->max_speed_hz > MAX_FREQ_HZ) { + dev_err(&spi->dev, "SPI max frequency out of range (min: %u, max: %u)\n", + MIN_FREQ_HZ, MAX_FREQ_HZ); + return -EINVAL; + } + + ret = spi_setup(spi); + if (ret < 0) { + dev_err(&spi->dev, "Unable to setup SPI device: %d\n", ret); + return ret; + } + + ndev = devm_alloc_etherdev(dev, sizeof(struct mse102x_net_spi)); + if (!ndev) + return -ENOMEM; + + ndev->needed_tailroom += ALIGN(DET_DFT_LEN, 4); + ndev->needed_headroom += ALIGN(DET_SOF_LEN, 4); + ndev->priv_flags &= ~IFF_TX_SKB_SHARING; + ndev->tx_queue_len = 100; + + mse = netdev_priv(ndev); + mses = to_mse102x_spi(mse); + + mses->spidev = spi; + mutex_init(&mses->lock); + INIT_WORK(&mses->tx_work, mse102x_tx_work); + + /* initialise pre-made spi transfer messages */ + spi_message_init(&mses->spi_msg); + spi_message_add_tail(&mses->spi_xfer, &mses->spi_msg); + + ndev->irq = spi->irq; + mse->ndev = ndev; + + /* set the default message enable */ + mse->msg_enable = netif_msg_init(-1, MSG_DEFAULT); + + skb_queue_head_init(&mse->txq); + + SET_NETDEV_DEV(ndev, dev); + + dev_set_drvdata(dev, mse); + + netif_carrier_off(mse->ndev); + ndev->netdev_ops = &mse102x_netdev_ops; + ndev->ethtool_ops = &mse102x_ethtool_ops; + + mse102x_init_mac(mse, dev->of_node); + + ret = register_netdev(ndev); + if (ret) { + dev_err(dev, "failed to register network device: %d\n", ret); + return ret; + } + + mse102x_init_device_debugfs(mses); + + return 0; +} + +static int mse102x_remove_spi(struct spi_device *spi) +{ + struct mse102x_net *mse = dev_get_drvdata(&spi->dev); + struct mse102x_net_spi *mses = to_mse102x_spi(mse); + + if (netif_msg_drv(mse)) + dev_info(&spi->dev, "remove\n"); + + mse102x_remove_device_debugfs(mses); + unregister_netdev(mse->ndev); + + return 0; +} + +static const struct of_device_id mse102x_match_table[] = { + { .compatible = "vertexcom,mse1021" }, + { .compatible = "vertexcom,mse1022" }, + { } +}; +MODULE_DEVICE_TABLE(of, mse102x_match_table); + +static struct spi_driver mse102x_driver = { + .driver = { + .name = DRV_NAME, + .of_match_table = mse102x_match_table, + .pm = &mse102x_pm_ops, + }, + .probe = mse102x_probe_spi, + .remove = mse102x_remove_spi, +}; +module_spi_driver(mse102x_driver); + +MODULE_DESCRIPTION("MSE102x Network driver"); +MODULE_AUTHOR("Stefan Wahren <stefan.wahren@in-tech.com>"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("spi:" DRV_NAME); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index e39356364f33..23ac353b35fe 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2051,6 +2051,7 @@ static int axienet_probe(struct platform_device *pdev) lp->phylink_config.dev = &ndev->dev; lp->phylink_config.type = PHYLINK_NETDEV; + lp->phylink_config.legacy_pre_march2020 = true; lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10FD | MAC_100FD | MAC_1000FD; diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index 65fdad1107fc..df77a22d1b81 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -382,9 +382,6 @@ static int hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) /* reserved for future extensions */ - return -EINVAL; - ret = ixp46x_ptp_find(&port->timesync_regs, &port->phc_index); if (ret) return ret; diff --git a/drivers/net/ipa/ipa_data-v4.5.c b/drivers/net/ipa/ipa_data-v4.5.c index e62ab9c3ac67..2da2c4194f2e 100644 --- a/drivers/net/ipa/ipa_data-v4.5.c +++ b/drivers/net/ipa/ipa_data-v4.5.c @@ -420,15 +420,10 @@ static const struct ipa_mem_data ipa_mem_data = { /* Interconnect rates are in 1000 byte/second units */ static const struct ipa_interconnect_data ipa_interconnect_data[] = { { - .name = "memory-a", + .name = "memory", .peak_bandwidth = 600000, /* 600 MBps */ .average_bandwidth = 150000, /* 150 MBps */ }, - { - .name = "memory-b", - .peak_bandwidth = 1804000, /* 1.804 GBps */ - .average_bandwidth = 150000, /* 150 MBps */ - }, /* Average rate is unused for the next two interconnects */ { .name = "imem", diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 90aafb56f140..a43820212932 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -514,6 +514,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) goto err_free; key = nmap->entry[i].key; *key = i; + memset(nmap->entry[i].value, 0, offmap->map.value_size); } } diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index 2b84169bf3a2..ffd9f84b6644 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -81,7 +81,10 @@ static int nsim_set_ringparam(struct net_device *dev, { struct netdevsim *ns = netdev_priv(dev); - memcpy(&ns->ethtool.ring, ring, sizeof(ns->ethtool.ring)); + ns->ethtool.ring.rx_pending = ring->rx_pending; + ns->ethtool.ring.rx_jumbo_pending = ring->rx_jumbo_pending; + ns->ethtool.ring.rx_mini_pending = ring->rx_mini_pending; + ns->ethtool.ring.tx_pending = ring->tx_pending; return 0; } diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 705c16675b80..c2d1a85ec559 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1235,9 +1235,6 @@ static int dp83640_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) /* reserved for future extensions */ - return -EINVAL; - if (cfg.tx_type < 0 || cfg.tx_type > HWTSTAMP_TX_ONESTEP_SYNC) return -ERANGE; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 9b6f2df07211..f52da568cce3 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -462,6 +462,9 @@ static void of_mdiobus_link_mdiodev(struct mii_bus *bus, if (addr == mdiodev->addr) { device_set_node(dev, of_fwnode_handle(child)); + /* The refcount on "child" is passed to the mdio + * device. Do _not_ use of_node_put(child) here. + */ return; } } diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c index edb951695b13..34f829845d06 100644 --- a/drivers/net/phy/mscc/mscc_ptp.c +++ b/drivers/net/phy/mscc/mscc_ptp.c @@ -1057,9 +1057,6 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) - return -EINVAL; - switch (cfg.tx_type) { case HWTSTAMP_TX_ONESTEP_SYNC: one_step = true; diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 2870c33b8975..271fc01f7f7f 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -162,11 +162,11 @@ static const struct phy_setting settings[] = { PHY_SETTING( 2500, FULL, 2500baseT_Full ), PHY_SETTING( 2500, FULL, 2500baseX_Full ), /* 1G */ - PHY_SETTING( 1000, FULL, 1000baseKX_Full ), PHY_SETTING( 1000, FULL, 1000baseT_Full ), PHY_SETTING( 1000, HALF, 1000baseT_Half ), PHY_SETTING( 1000, FULL, 1000baseT1_Full ), PHY_SETTING( 1000, FULL, 1000baseX_Full ), + PHY_SETTING( 1000, FULL, 1000baseKX_Full ), /* 100M */ PHY_SETTING( 100, FULL, 100baseT_Full ), PHY_SETTING( 100, FULL, 100baseT1_Full ), diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 8e3861f09b4f..420201858564 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -419,6 +419,54 @@ void phylink_generic_validate(struct phylink_config *config, } EXPORT_SYMBOL_GPL(phylink_generic_validate); +static int phylink_validate_mac_and_pcs(struct phylink *pl, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct phylink_pcs *pcs; + int ret; + + /* Get the PCS for this interface mode */ + if (pl->mac_ops->mac_select_pcs) { + pcs = pl->mac_ops->mac_select_pcs(pl->config, state->interface); + if (IS_ERR(pcs)) + return PTR_ERR(pcs); + } else { + pcs = pl->pcs; + } + + if (pcs) { + /* The PCS, if present, must be setup before phylink_create() + * has been called. If the ops is not initialised, print an + * error and backtrace rather than oopsing the kernel. + */ + if (!pcs->ops) { + phylink_err(pl, "interface %s: uninitialised PCS\n", + phy_modes(state->interface)); + dump_stack(); + return -EINVAL; + } + + /* Validate the link parameters with the PCS */ + if (pcs->ops->pcs_validate) { + ret = pcs->ops->pcs_validate(pcs, supported, state); + if (ret < 0 || phylink_is_empty_linkmode(supported)) + return -EINVAL; + + /* Ensure the advertising mask is a subset of the + * supported mask. + */ + linkmode_and(state->advertising, state->advertising, + supported); + } + } + + /* Then validate the link parameters with the MAC */ + pl->mac_ops->validate(pl->config, supported, state); + + return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; +} + static int phylink_validate_any(struct phylink *pl, unsigned long *supported, struct phylink_link_state *state) { @@ -434,9 +482,10 @@ static int phylink_validate_any(struct phylink *pl, unsigned long *supported, t = *state; t.interface = intf; - pl->mac_ops->validate(pl->config, s, &t); - linkmode_or(all_s, all_s, s); - linkmode_or(all_adv, all_adv, t.advertising); + if (!phylink_validate_mac_and_pcs(pl, s, &t)) { + linkmode_or(all_s, all_s, s); + linkmode_or(all_adv, all_adv, t.advertising); + } } } @@ -458,9 +507,7 @@ static int phylink_validate(struct phylink *pl, unsigned long *supported, return -EINVAL; } - pl->mac_ops->validate(pl->config, supported, state); - - return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; + return phylink_validate_mac_and_pcs(pl, supported, state); } static int phylink_parse_fixedlink(struct phylink *pl, @@ -742,7 +789,7 @@ static void phylink_mac_pcs_an_restart(struct phylink *pl) phylink_autoneg_inband(pl->cur_link_an_mode)) { if (pl->pcs_ops) pl->pcs_ops->pcs_an_restart(pl->pcs); - else + else if (pl->config->legacy_pre_march2020) pl->mac_ops->mac_an_restart(pl->config); } } @@ -750,10 +797,21 @@ static void phylink_mac_pcs_an_restart(struct phylink *pl) static void phylink_major_config(struct phylink *pl, bool restart, const struct phylink_link_state *state) { + struct phylink_pcs *pcs = NULL; int err; phylink_dbg(pl, "major config %s\n", phy_modes(state->interface)); + if (pl->mac_ops->mac_select_pcs) { + pcs = pl->mac_ops->mac_select_pcs(pl->config, state->interface); + if (IS_ERR(pcs)) { + phylink_err(pl, + "mac_select_pcs unexpectedly failed: %pe\n", + pcs); + return; + } + } + if (pl->mac_ops->mac_prepare) { err = pl->mac_ops->mac_prepare(pl->config, pl->cur_link_an_mode, state->interface); @@ -764,6 +822,12 @@ static void phylink_major_config(struct phylink *pl, bool restart, } } + /* If we have a new PCS, switch to the new PCS after preparing the MAC + * for the change. + */ + if (pcs) + phylink_set_pcs(pl, pcs); + phylink_mac_config(pl, state); if (pl->pcs_ops) { @@ -803,7 +867,7 @@ static int phylink_change_inband_advert(struct phylink *pl) if (test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) return 0; - if (!pl->pcs_ops) { + if (!pl->pcs_ops && pl->config->legacy_pre_march2020) { /* Legacy method */ phylink_mac_config(pl, &pl->link_config); phylink_mac_pcs_an_restart(pl); @@ -854,7 +918,8 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, if (pl->pcs_ops) pl->pcs_ops->pcs_get_state(pl->pcs, state); - else if (pl->mac_ops->mac_pcs_get_state) + else if (pl->mac_ops->mac_pcs_get_state && + pl->config->legacy_pre_march2020) pl->mac_ops->mac_pcs_get_state(pl->config, state); else state->link = 0; @@ -1048,12 +1113,11 @@ static void phylink_resolve(struct work_struct *w) } phylink_major_config(pl, false, &link_state); pl->link_config.interface = link_state.interface; - } else if (!pl->pcs_ops) { + } else if (!pl->pcs_ops && pl->config->legacy_pre_march2020) { /* The interface remains unchanged, only the speed, * duplex or pause settings have changed. Call the * old mac_config() method to configure the MAC/PCS - * only if we do not have a PCS installed (an - * unconverted user.) + * only if we do not have a legacy MAC driver. */ phylink_mac_config(pl, &link_state); } @@ -1155,6 +1219,14 @@ struct phylink *phylink_create(struct phylink_config *config, struct phylink *pl; int ret; + /* Validate the supplied configuration */ + if (mac_ops->mac_select_pcs && + phy_interface_empty(config->supported_interfaces)) { + dev_err(config->dev, + "phylink: error: empty supported_interfaces but mac_select_pcs() method present\n"); + return ERR_PTR(-EINVAL); + } + pl = kzalloc(sizeof(*pl), GFP_KERNEL); if (!pl) return ERR_PTR(-ENOMEM); @@ -1222,9 +1294,10 @@ EXPORT_SYMBOL_GPL(phylink_create); * @pl: a pointer to a &struct phylink returned from phylink_create() * @pcs: a pointer to the &struct phylink_pcs * - * Bind the MAC PCS to phylink. This may be called after phylink_create(), - * in mac_prepare() or mac_config() methods if it is desired to dynamically - * change the PCS. + * Bind the MAC PCS to phylink. This may be called after phylink_create(). + * If it is desired to dynamically change the PCS, then the preferred method + * is to use mac_select_pcs(), but it may also be called in mac_prepare() + * or mac_config(). * * Please note that there are behavioural changes with the mac_config() * callback if a PCS is present (denoting a newer setup) so removing a PCS @@ -1235,6 +1308,14 @@ void phylink_set_pcs(struct phylink *pl, struct phylink_pcs *pcs) { pl->pcs = pcs; pl->pcs_ops = pcs->ops; + + if (!pl->phylink_disable_state && + pl->cfg_link_an_mode == MLO_AN_INBAND) { + if (pl->config->pcs_poll || pcs->poll) + mod_timer(&pl->link_poll, jiffies + HZ); + else + del_timer(&pl->link_poll); + } } EXPORT_SYMBOL_GPL(phylink_set_pcs); @@ -1653,6 +1734,7 @@ EXPORT_SYMBOL_GPL(phylink_stop); * @mac_wol: true if the MAC needs to receive packets for Wake-on-Lan * * Handle a network device suspend event. There are several cases: + * * - If Wake-on-Lan is not active, we can bring down the link between * the MAC and PHY by calling phylink_stop(). * - If Wake-on-Lan is active, and being handled only by the PHY, we diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 1180a0e2445f..9e52c5d2d77f 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -173,6 +173,7 @@ struct channel { spinlock_t downl; /* protects `chan', file.xq dequeue */ struct ppp *ppp; /* ppp unit we're connected to */ struct net *chan_net; /* the net channel belongs to */ + netns_tracker ns_tracker; struct list_head clist; /* link in list of channels per unit */ rwlock_t upl; /* protects `ppp' and 'bridge' */ struct channel __rcu *bridge; /* "bridged" ppp channel */ @@ -2879,7 +2880,7 @@ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan) pch->ppp = NULL; pch->chan = chan; - pch->chan_net = get_net(net); + pch->chan_net = get_net_track(net, &pch->ns_tracker, GFP_KERNEL); chan->ppp = pch; init_ppp_file(&pch->file, CHANNEL); pch->file.hdrlen = chan->hdrlen; @@ -3519,7 +3520,7 @@ ppp_disconnect_channel(struct channel *pch) */ static void ppp_destroy_channel(struct channel *pch) { - put_net(pch->chan_net); + put_net_track(pch->chan_net, &pch->ns_tracker); pch->chan_net = NULL; atomic_dec(&channel_count); diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 24753a4da7e6..e303b522efb5 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -181,6 +181,8 @@ static u32 cdc_ncm_check_tx_max(struct usbnet *dev, u32 new_tx) min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32); max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize)); + if (max == 0) + max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */ /* some devices set dwNtbOutMaxSize too low for the above default */ min = min(min, max); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 185e08c1af31..b8e20a3f2b84 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -76,6 +76,8 @@ #define LAN7801_USB_PRODUCT_ID (0x7801) #define LAN78XX_EEPROM_MAGIC (0x78A5) #define LAN78XX_OTP_MAGIC (0x78F3) +#define AT29M2AF_USB_VENDOR_ID (0x07C9) +#define AT29M2AF_USB_PRODUCT_ID (0x0012) #define MII_READ 1 #define MII_WRITE 0 @@ -5060,6 +5062,10 @@ static const struct usb_device_id products[] = { /* LAN7801 USB Gigabit Ethernet Device */ USB_DEVICE(LAN78XX_USB_VENDOR_ID, LAN7801_USB_PRODUCT_ID), }, + { + /* ATM2-AF USB Gigabit Ethernet Device */ + USB_DEVICE(AT29M2AF_USB_VENDOR_ID, AT29M2AF_USB_PRODUCT_ID), + }, {}, }; MODULE_DEVICE_TABLE(usb, products); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 86b814e99224..f510e8219470 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1358,6 +1358,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990 */ {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 088d9404c93d..87f8c896238f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -733,7 +733,7 @@ static struct sk_buff *receive_small(struct net_device *dev, pr_debug("%s: rx error: len %u exceeds max size %d\n", dev->name, len, GOOD_PACKET_LEN); dev->stats.rx_length_errors++; - goto err_len; + goto err; } if (likely(!vi->xdp_enabled)) { @@ -825,10 +825,8 @@ static struct sk_buff *receive_small(struct net_device *dev, skip_xdp: skb = build_skb(buf, buflen); - if (!skb) { - put_page(page); + if (!skb) goto err; - } skb_reserve(skb, headroom - delta); skb_put(skb, len); if (!xdp_prog) { @@ -839,13 +837,12 @@ skip_xdp: if (metasize) skb_metadata_set(skb, metasize); -err: return skb; err_xdp: rcu_read_unlock(); stats->xdp_drops++; -err_len: +err: stats->drops++; put_page(page); xdp_xmit: diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 14fae317bc70..fd407c0e2856 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -3261,7 +3261,7 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter) #ifdef CONFIG_PCI_MSI if (adapter->intr.type == VMXNET3_IT_MSIX) { - int i, nvec; + int i, nvec, nvec_allocated; nvec = adapter->share_intr == VMXNET3_INTR_TXSHARE ? 1 : adapter->num_tx_queues; @@ -3274,14 +3274,15 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter) for (i = 0; i < nvec; i++) adapter->intr.msix_entries[i].entry = i; - nvec = vmxnet3_acquire_msix_vectors(adapter, nvec); - if (nvec < 0) + nvec_allocated = vmxnet3_acquire_msix_vectors(adapter, nvec); + if (nvec_allocated < 0) goto msix_err; /* If we cannot allocate one MSIx vector per queue * then limit the number of rx queues to 1 */ - if (nvec == VMXNET3_LINUX_MIN_MSIX_VECT) { + if (nvec_allocated == VMXNET3_LINUX_MIN_MSIX_VECT && + nvec != VMXNET3_LINUX_MIN_MSIX_VECT) { if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE || adapter->num_rx_queues != 1) { adapter->share_intr = VMXNET3_INTR_TXSHARE; @@ -3291,14 +3292,14 @@ vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter) } } - adapter->intr.num_intrs = nvec; + adapter->intr.num_intrs = nvec_allocated; return; msix_err: /* If we cannot allocate MSIx vectors use only one rx queue */ dev_info(&adapter->pdev->dev, "Failed to enable MSI-X, error %d. " - "Limiting #rx queues to 1, try MSI.\n", nvec); + "Limiting #rx queues to 1, try MSI.\n", nvec_allocated); adapter->intr.type = VMXNET3_IT_MSI; } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index dbfa124d1c1c..b4c64226b7ca 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -770,8 +770,6 @@ static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, skb->dev = vrf_dev; - vrf_nf_set_untracked(skb); - err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip6_out_direct_finish); @@ -792,6 +790,8 @@ static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, if (rt6_need_strict(&ipv6_hdr(skb)->daddr)) return skb; + vrf_nf_set_untracked(skb); + if (qdisc_tx_is_default(vrf_dev) || IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) return vrf_ip6_out_direct(vrf_dev, sk, skb); @@ -1000,8 +1000,6 @@ static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, skb->dev = vrf_dev; - vrf_nf_set_untracked(skb); - err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, skb, NULL, vrf_dev, vrf_ip_out_direct_finish); @@ -1023,6 +1021,8 @@ static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, ipv4_is_lbcast(ip_hdr(skb)->daddr)) return skb; + vrf_nf_set_untracked(skb); + if (qdisc_tx_is_default(vrf_dev) || IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) return vrf_ip_out_direct(vrf_dev, sk, skb); diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index 38af8ec69d4c..e4250ba8dfee 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -574,7 +574,11 @@ static int ath11k_mhi_set_state(struct ath11k_pci *ab_pci, ret = mhi_pm_suspend(ab_pci->mhi_ctrl); break; case ATH11K_MHI_RESUME: - ret = mhi_pm_resume(ab_pci->mhi_ctrl); + /* Do force MHI resume as some devices like QCA6390, WCN6855 + * are not in M3 state but they are functional. So just ignore + * the MHI state while resuming. + */ + ret = mhi_pm_resume_force(ab_pci->mhi_ctrl); break; case ATH11K_MHI_TRIGGER_RDDM: ret = mhi_force_rddm_mode(ab_pci->mhi_ctrl); diff --git a/drivers/net/wireless/broadcom/brcm80211/Kconfig b/drivers/net/wireless/broadcom/brcm80211/Kconfig index 5bf2318763c5..3a1a35b5672f 100644 --- a/drivers/net/wireless/broadcom/brcm80211/Kconfig +++ b/drivers/net/wireless/broadcom/brcm80211/Kconfig @@ -7,16 +7,20 @@ config BRCMSMAC depends on MAC80211 depends on BCMA_POSSIBLE select BCMA - select NEW_LEDS if BCMA_DRIVER_GPIO - select LEDS_CLASS if BCMA_DRIVER_GPIO select BRCMUTIL select FW_LOADER select CORDIC help This module adds support for PCIe wireless adapters based on Broadcom - IEEE802.11n SoftMAC chipsets. It also has WLAN led support, which will - be available if you select BCMA_DRIVER_GPIO. If you choose to build a - module, the driver will be called brcmsmac.ko. + IEEE802.11n SoftMAC chipsets. If you choose to build a module, the + driver will be called brcmsmac.ko. + +config BRCMSMAC_LEDS + def_bool BRCMSMAC && BCMA_DRIVER_GPIO && MAC80211_LEDS + help + The brcmsmac LED support depends on the presence of the + BCMA_DRIVER_GPIO driver, and it only works if LED support + is enabled and reachable from the driver module. source "drivers/net/wireless/broadcom/brcm80211/brcmfmac/Kconfig" diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile index 482d7737764d..090757730ba6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile @@ -42,6 +42,6 @@ brcmsmac-y := \ brcms_trace_events.o \ debug.o -brcmsmac-$(CONFIG_BCMA_DRIVER_GPIO) += led.o +brcmsmac-$(CONFIG_BRCMSMAC_LEDS) += led.o obj-$(CONFIG_BRCMSMAC) += brcmsmac.o diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h index d65f5c268fd7..2a5cbeb9e783 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/led.h @@ -24,7 +24,7 @@ struct brcms_led { struct gpio_desc *gpiod; }; -#ifdef CONFIG_BCMA_DRIVER_GPIO +#ifdef CONFIG_BRCMSMAC_LEDS void brcms_led_unregister(struct brcms_info *wl); int brcms_led_register(struct brcms_info *wl); #else diff --git a/drivers/net/wireless/intel/iwlegacy/Kconfig b/drivers/net/wireless/intel/iwlegacy/Kconfig index 24fe3f63c321..7eacc8e58ee1 100644 --- a/drivers/net/wireless/intel/iwlegacy/Kconfig +++ b/drivers/net/wireless/intel/iwlegacy/Kconfig @@ -2,14 +2,13 @@ config IWLEGACY tristate select FW_LOADER - select NEW_LEDS - select LEDS_CLASS select LEDS_TRIGGERS select MAC80211_LEDS config IWL4965 tristate "Intel Wireless WiFi 4965AGN (iwl4965)" depends on PCI && MAC80211 + depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211 select IWLEGACY help This option enables support for @@ -38,6 +37,7 @@ config IWL4965 config IWL3945 tristate "Intel PRO/Wireless 3945ABG/BG Network Connection (iwl3945)" depends on PCI && MAC80211 + depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211 select IWLEGACY help Select to build the driver supporting the: diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig index cafdb458b067..c21c0c68849a 100644 --- a/drivers/net/wireless/intel/iwlwifi/Kconfig +++ b/drivers/net/wireless/intel/iwlwifi/Kconfig @@ -48,7 +48,7 @@ if IWLWIFI config IWLWIFI_LEDS bool - depends on LEDS_CLASS=y || LEDS_CLASS=IWLWIFI + depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211 depends on IWLMVM || IWLDVM select LEDS_TRIGGERS select MAC80211_LEDS diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 1883d98abb2f..ce73cb8b06ee 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -269,17 +269,18 @@ static u32 iwl_mvm_get_tx_rate(struct iwl_mvm *mvm, u8 rate_plcp; u32 rate_flags = 0; bool is_cck; - struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); /* info->control is only relevant for non HW rate control */ if (!ieee80211_hw_check(mvm->hw, HAS_RATE_CONTROL)) { + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + /* HT rate doesn't make sense for a non data frame */ WARN_ONCE(info->control.rates[0].flags & IEEE80211_TX_RC_MCS && !ieee80211_is_data(fc), "Got a HT rate (flags:0x%x/mcs:%d/fc:0x%x/state:%d) for a non data frame\n", info->control.rates[0].flags, info->control.rates[0].idx, - le16_to_cpu(fc), mvmsta->sta_state); + le16_to_cpu(fc), sta ? mvmsta->sta_state : -1); rate_idx = info->control.rates[0].idx; } diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile index 79ab850a45a2..c78ae4b89761 100644 --- a/drivers/net/wireless/mediatek/mt76/Makefile +++ b/drivers/net/wireless/mediatek/mt76/Makefile @@ -34,4 +34,4 @@ obj-$(CONFIG_MT76x2_COMMON) += mt76x2/ obj-$(CONFIG_MT7603E) += mt7603/ obj-$(CONFIG_MT7615_COMMON) += mt7615/ obj-$(CONFIG_MT7915E) += mt7915/ -obj-$(CONFIG_MT7921E) += mt7921/ +obj-$(CONFIG_MT7921_COMMON) += mt7921/ diff --git a/drivers/net/wireless/mediatek/mt76/debugfs.c b/drivers/net/wireless/mediatek/mt76/debugfs.c index b8bcf22a07fd..027d9ea17d04 100644 --- a/drivers/net/wireless/mediatek/mt76/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/debugfs.c @@ -74,13 +74,12 @@ EXPORT_SYMBOL_GPL(mt76_queues_read); static int mt76_rx_queues_read(struct seq_file *s, void *data) { struct mt76_dev *dev = dev_get_drvdata(s->private); - int i, queued; + int i; seq_puts(s, " queue | hw-queued | head | tail |\n"); mt76_for_each_q_rx(dev, i) { struct mt76_queue *q = &dev->q_rx[i]; - queued = mt76_is_usb(dev) ? q->ndesc - q->queued : q->queued; seq_printf(s, " %9d | %9d | %9d | %9d |\n", i, q->queued, q->head, q->tail); } diff --git a/drivers/net/wwan/Kconfig b/drivers/net/wwan/Kconfig index 9f5111a77da9..609fd4a2c865 100644 --- a/drivers/net/wwan/Kconfig +++ b/drivers/net/wwan/Kconfig @@ -16,6 +16,17 @@ config WWAN if WWAN +config WWAN_DEBUGFS + bool "WWAN devices debugfs interface" if EXPERT + depends on DEBUG_FS + default y + help + Enables debugfs infrastructure for the WWAN core and device drivers. + + If this option is selected, then you can find the debug interface + elements for each WWAN device in a directory that is corresponding to + the device name: debugfs/wwan/wwanX. + config WWAN_HWSIM tristate "Simulated WWAN device" help @@ -85,7 +96,7 @@ config IOSM tristate "IOSM Driver for Intel M.2 WWAN Device" depends on INTEL_IOMMU select NET_DEVLINK - select RELAY + select RELAY if WWAN_DEBUGFS help This driver enables Intel M.2 WWAN Device communication. diff --git a/drivers/net/wwan/iosm/Makefile b/drivers/net/wwan/iosm/Makefile index 5c2528beca2a..fa8d6afd18e1 100644 --- a/drivers/net/wwan/iosm/Makefile +++ b/drivers/net/wwan/iosm/Makefile @@ -21,7 +21,10 @@ iosm-y = \ iosm_ipc_mux_codec.o \ iosm_ipc_devlink.o \ iosm_ipc_flash.o \ - iosm_ipc_coredump.o \ + iosm_ipc_coredump.o + +iosm-$(CONFIG_WWAN_DEBUGFS) += \ + iosm_ipc_debugfs.o \ iosm_ipc_trace.o obj-$(CONFIG_IOSM) := iosm.o diff --git a/drivers/net/wwan/iosm/iosm_ipc_debugfs.c b/drivers/net/wwan/iosm/iosm_ipc_debugfs.c new file mode 100644 index 000000000000..f2f57751a7d2 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_debugfs.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-2021 Intel Corporation. + */ + +#include <linux/debugfs.h> +#include <linux/wwan.h> + +#include "iosm_ipc_imem.h" +#include "iosm_ipc_trace.h" +#include "iosm_ipc_debugfs.h" + +void ipc_debugfs_init(struct iosm_imem *ipc_imem) +{ + struct dentry *debugfs_pdev = wwan_get_debugfs_dir(ipc_imem->dev); + + ipc_imem->debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, + debugfs_pdev); + + ipc_imem->trace = ipc_trace_init(ipc_imem); + if (!ipc_imem->trace) + dev_warn(ipc_imem->dev, "trace channel init failed"); +} + +void ipc_debugfs_deinit(struct iosm_imem *ipc_imem) +{ + ipc_trace_deinit(ipc_imem->trace); + debugfs_remove_recursive(ipc_imem->debugfs_dir); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_debugfs.h b/drivers/net/wwan/iosm/iosm_ipc_debugfs.h new file mode 100644 index 000000000000..8a84bfa2c14a --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_debugfs.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-2021 Intel Corporation. + */ + +#ifndef IOSM_IPC_DEBUGFS_H +#define IOSM_IPC_DEBUGFS_H + +#ifdef CONFIG_WWAN_DEBUGFS +void ipc_debugfs_init(struct iosm_imem *ipc_imem); +void ipc_debugfs_deinit(struct iosm_imem *ipc_imem); +#else +static inline void ipc_debugfs_init(struct iosm_imem *ipc_imem) {} +static inline void ipc_debugfs_deinit(struct iosm_imem *ipc_imem) {} +#endif + +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index 1be07114c85d..f9e8e0ee4de3 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -11,6 +11,7 @@ #include "iosm_ipc_imem.h" #include "iosm_ipc_port.h" #include "iosm_ipc_trace.h" +#include "iosm_ipc_debugfs.h" /* Check the wwan ips if it is valid with Channel as input. */ static int ipc_imem_check_wwan_ips(struct ipc_mem_channel *chnl) @@ -133,7 +134,6 @@ static int ipc_imem_setup_cp_mux_cap_init(struct iosm_imem *ipc_imem, * for channel alloc function. */ cfg->instance_id = IPC_MEM_MUX_IP_CH_IF_ID; - cfg->nr_sessions = IPC_MEM_MUX_IP_SESSION_ENTRIES; return 0; } @@ -182,9 +182,9 @@ void ipc_imem_hrtimer_stop(struct hrtimer *hr_timer) bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem) { struct ipc_mem_channel *channel; + bool hpda_ctrl_pending = false; struct sk_buff_head *ul_list; bool hpda_pending = false; - bool forced_hpdu = false; struct ipc_pipe *pipe; int i; @@ -201,15 +201,19 @@ bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem) ul_list = &channel->ul_list; /* Fill the transfer descriptor with the uplink buffer info. */ - hpda_pending |= ipc_protocol_ul_td_send(ipc_imem->ipc_protocol, + if (!ipc_imem_check_wwan_ips(channel)) { + hpda_ctrl_pending |= + ipc_protocol_ul_td_send(ipc_imem->ipc_protocol, pipe, ul_list); - - /* forced HP update needed for non data channels */ - if (hpda_pending && !ipc_imem_check_wwan_ips(channel)) - forced_hpdu = true; + } else { + hpda_pending |= + ipc_protocol_ul_td_send(ipc_imem->ipc_protocol, + pipe, ul_list); + } } - if (forced_hpdu) { + /* forced HP update needed for non data channels */ + if (hpda_ctrl_pending) { hpda_pending = false; ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol, IPC_HP_UL_WRITE_TD); @@ -272,8 +276,8 @@ static void ipc_imem_dl_skb_process(struct iosm_imem *ipc_imem, if (port_id == IPC_MEM_CTRL_CHL_ID_7) ipc_imem_sys_devlink_notify_rx(ipc_imem->ipc_devlink, skb); - else if (port_id == ipc_imem->trace->chl_id) - ipc_trace_port_rx(ipc_imem->trace, skb); + else if (ipc_is_trace_channel(ipc_imem, port_id)) + ipc_trace_port_rx(ipc_imem, skb); else wwan_port_rx(ipc_imem->ipc_port[port_id]->iosm_port, skb); @@ -533,6 +537,9 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) return; } + if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag)) + ipc_devlink_deinit(ipc_imem->ipc_devlink); + if (!ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg)) ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem); @@ -554,11 +561,7 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) ctrl_chl_idx++; } - ipc_imem->trace = ipc_imem_trace_channel_init(ipc_imem); - if (!ipc_imem->trace) { - dev_err(ipc_imem->dev, "trace channel init failed"); - return; - } + ipc_debugfs_init(ipc_imem); ipc_task_queue_send_task(ipc_imem, ipc_imem_send_mdm_rdy_cb, 0, NULL, 0, false); @@ -1175,12 +1178,12 @@ void ipc_imem_cleanup(struct iosm_imem *ipc_imem) if (test_and_clear_bit(FULLY_FUNCTIONAL, &ipc_imem->flag)) { ipc_mux_deinit(ipc_imem->mux); - ipc_trace_deinit(ipc_imem->trace); + ipc_debugfs_deinit(ipc_imem); ipc_wwan_deinit(ipc_imem->wwan); ipc_port_deinit(ipc_imem->ipc_port); } - if (ipc_imem->ipc_devlink) + if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag)) ipc_devlink_deinit(ipc_imem->ipc_devlink); ipc_imem_device_ipc_uninit(ipc_imem); @@ -1276,7 +1279,6 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, ipc_imem->pci_device_id = device_id; - ipc_imem->ev_cdev_write_pending = false; ipc_imem->cp_version = 0; ipc_imem->device_sleep = IPC_HOST_SLEEP_ENTER_SLEEP; @@ -1344,6 +1346,8 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, if (ipc_flash_link_establish(ipc_imem)) goto devlink_channel_fail; + + set_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag); } return ipc_imem; devlink_channel_fail: diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h index cec38009c44a..98554e9beb01 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h @@ -101,6 +101,7 @@ struct ipc_chnl_cfg; #define IOSM_CHIP_INFO_SIZE_MAX 100 #define FULLY_FUNCTIONAL 0 +#define IOSM_DEVLINK_INIT 1 /* List of the supported UL/DL pipes. */ enum ipc_mem_pipes { @@ -336,11 +337,10 @@ enum ipc_phase { * process the irq actions. * @flag: Flag to monitor the state of driver * @td_update_timer_suspended: if true then td update timer suspend - * @ev_cdev_write_pending: 0 means inform the IPC tasklet to pass - * the accumulated uplink buffers to CP. * @ev_mux_net_transmit_pending:0 means inform the IPC tasklet to pass * @reset_det_n: Reset detect flag * @pcie_wake_n: Pcie wake flag + * @debugfs_dir: Debug FS directory for driver-specific entries */ struct iosm_imem { struct iosm_mmio *mmio; @@ -350,7 +350,9 @@ struct iosm_imem { struct iosm_mux *mux; struct iosm_cdev *ipc_port[IPC_MEM_MAX_CHANNELS]; struct iosm_pcie *pcie; +#ifdef CONFIG_WWAN_DEBUGFS struct iosm_trace *trace; +#endif struct device *dev; enum ipc_mem_device_ipc_state ipc_requested_state; struct ipc_mem_channel channels[IPC_MEM_MAX_CHANNELS]; @@ -376,10 +378,12 @@ struct iosm_imem { u8 ev_irq_pending[IPC_IRQ_VECTORS]; unsigned long flag; u8 td_update_timer_suspended:1, - ev_cdev_write_pending:1, ev_mux_net_transmit_pending:1, reset_det_n:1, pcie_wake_n:1; +#ifdef CONFIG_WWAN_DEBUGFS + struct dentry *debugfs_dir; +#endif }; /** diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index 43f1796a8984..57304a5adf68 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -11,7 +11,6 @@ #include "iosm_ipc_imem_ops.h" #include "iosm_ipc_port.h" #include "iosm_ipc_task_queue.h" -#include "iosm_ipc_trace.h" /* Open a packet data online channel between the network layer and CP. */ int ipc_imem_sys_wwan_open(struct iosm_imem *ipc_imem, int if_id) @@ -42,7 +41,6 @@ void ipc_imem_sys_wwan_close(struct iosm_imem *ipc_imem, int if_id, static int ipc_imem_tq_cdev_write(struct iosm_imem *ipc_imem, int arg, void *msg, size_t size) { - ipc_imem->ev_cdev_write_pending = false; ipc_imem_ul_send(ipc_imem); return 0; @@ -51,11 +49,6 @@ static int ipc_imem_tq_cdev_write(struct iosm_imem *ipc_imem, int arg, /* Through tasklet to do sio write. */ static int ipc_imem_call_cdev_write(struct iosm_imem *ipc_imem) { - if (ipc_imem->ev_cdev_write_pending) - return -1; - - ipc_imem->ev_cdev_write_pending = true; - return ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_cdev_write, 0, NULL, 0, false); } @@ -108,23 +101,6 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, "failed to register the ipc_wwan interfaces"); } -/** - * ipc_imem_trace_channel_init - Initializes trace channel. - * @ipc_imem: Pointer to iosm_imem struct. - * - * Returns: Pointer to trace instance on success else NULL - */ -struct iosm_trace *ipc_imem_trace_channel_init(struct iosm_imem *ipc_imem) -{ - struct ipc_chnl_cfg chnl_cfg = { 0 }; - - ipc_chnl_cfg_get(&chnl_cfg, IPC_MEM_CTRL_CHL_ID_3); - ipc_imem_channel_init(ipc_imem, IPC_CTYPE_CTRL, chnl_cfg, - IRQ_MOD_OFF); - - return ipc_trace_init(ipc_imem); -} - /* Map SKB to DMA for transfer */ static int ipc_imem_map_skb_to_dma(struct iosm_imem *ipc_imem, struct sk_buff *skb) @@ -471,6 +447,7 @@ void ipc_imem_sys_devlink_close(struct iosm_devlink *ipc_devlink) /* Release the pipe resources */ ipc_imem_pipe_cleanup(ipc_imem, &channel->ul_pipe); ipc_imem_pipe_cleanup(ipc_imem, &channel->dl_pipe); + ipc_imem->nr_of_channels--; } void ipc_imem_sys_devlink_notify_rx(struct iosm_devlink *ipc_devlink, diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h index e36ee2782629..f8afb217d9e2 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -141,5 +141,5 @@ int ipc_imem_sys_devlink_read(struct iosm_devlink *ipc_devlink, u8 *data, */ int ipc_imem_sys_devlink_write(struct iosm_devlink *ipc_devlink, unsigned char *buf, int count); -struct iosm_trace *ipc_imem_trace_channel_init(struct iosm_imem *ipc_imem); + #endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_mmio.c b/drivers/net/wwan/iosm/iosm_ipc_mmio.c index 09f94c123531..f09e5e77a2a5 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mmio.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mmio.c @@ -192,7 +192,7 @@ void ipc_mmio_config(struct iosm_mmio *ipc_mmio) iowrite64(0, ipc_mmio->base + ipc_mmio->offset.ap_win_end); iowrite64(ipc_mmio->context_info_addr, - ipc_mmio->base + ipc_mmio->offset.context_info); + ipc_mmio->base + ipc_mmio->offset.context_info); } void ipc_mmio_set_psi_addr_and_size(struct iosm_mmio *ipc_mmio, dma_addr_t addr, diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.c b/drivers/net/wwan/iosm/iosm_ipc_mux.c index c1c77ce699da..8e66ffe92055 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.c @@ -97,7 +97,7 @@ static bool ipc_mux_session_open(struct iosm_mux *ipc_mux, /* Search for a free session interface id. */ if_id = le32_to_cpu(session_open->if_id); - if (if_id < 0 || if_id >= ipc_mux->nr_sessions) { + if (if_id < 0 || if_id >= IPC_MEM_MUX_IP_SESSION_ENTRIES) { dev_err(ipc_mux->dev, "invalid interface id=%d", if_id); return false; } @@ -129,6 +129,7 @@ static bool ipc_mux_session_open(struct iosm_mux *ipc_mux, /* Save and return the assigned if id. */ session_open->if_id = cpu_to_le32(if_id); + ipc_mux->nr_sessions++; return true; } @@ -151,7 +152,7 @@ static void ipc_mux_session_close(struct iosm_mux *ipc_mux, /* Copy the session interface id. */ if_id = le32_to_cpu(msg->if_id); - if (if_id < 0 || if_id >= ipc_mux->nr_sessions) { + if (if_id < 0 || if_id >= IPC_MEM_MUX_IP_SESSION_ENTRIES) { dev_err(ipc_mux->dev, "invalid session id %d", if_id); return; } @@ -170,6 +171,7 @@ static void ipc_mux_session_close(struct iosm_mux *ipc_mux, ipc_mux->session[if_id].flow_ctl_mask = 0; ipc_mux_session_reset(ipc_mux, if_id); + ipc_mux->nr_sessions--; } static void ipc_mux_channel_close(struct iosm_mux *ipc_mux, @@ -178,7 +180,7 @@ static void ipc_mux_channel_close(struct iosm_mux *ipc_mux, int i; /* Free pending session UL packet. */ - for (i = 0; i < ipc_mux->nr_sessions; i++) + for (i = 0; i < IPC_MEM_MUX_IP_SESSION_ENTRIES; i++) if (ipc_mux->session[i].wwan) ipc_mux_session_reset(ipc_mux, i); @@ -244,6 +246,11 @@ static int ipc_mux_schedule(struct iosm_mux *ipc_mux, union mux_msg *msg) /* Release an IP session. */ ipc_mux->event = MUX_E_MUX_SESSION_CLOSE; ipc_mux_session_close(ipc_mux, &msg->session_close); + if (!ipc_mux->nr_sessions) { + ipc_mux->event = MUX_E_MUX_CHANNEL_CLOSE; + ipc_mux_channel_close(ipc_mux, + &msg->channel_close); + } ret = ipc_mux->channel_id; goto out; @@ -281,7 +288,6 @@ struct iosm_mux *ipc_mux_init(struct ipc_mux_config *mux_cfg, ipc_mux->protocol = mux_cfg->protocol; ipc_mux->ul_flow = mux_cfg->ul_flow; - ipc_mux->nr_sessions = mux_cfg->nr_sessions; ipc_mux->instance_id = mux_cfg->instance_id; ipc_mux->wwan_q_offset = 0; @@ -340,7 +346,7 @@ static void ipc_mux_restart_tx_for_all_sessions(struct iosm_mux *ipc_mux) struct mux_session *session; int idx; - for (idx = 0; idx < ipc_mux->nr_sessions; idx++) { + for (idx = 0; idx < IPC_MEM_MUX_IP_SESSION_ENTRIES; idx++) { session = &ipc_mux->session[idx]; if (!session->wwan) @@ -365,7 +371,7 @@ static void ipc_mux_stop_netif_for_all_sessions(struct iosm_mux *ipc_mux) struct mux_session *session; int idx; - for (idx = 0; idx < ipc_mux->nr_sessions; idx++) { + for (idx = 0; idx < IPC_MEM_MUX_IP_SESSION_ENTRIES; idx++) { session = &ipc_mux->session[idx]; if (!session->wwan) @@ -387,7 +393,7 @@ void ipc_mux_check_n_restart_tx(struct iosm_mux *ipc_mux) int ipc_mux_get_max_sessions(struct iosm_mux *ipc_mux) { - return ipc_mux ? ipc_mux->nr_sessions : -EFAULT; + return ipc_mux ? IPC_MEM_MUX_IP_SESSION_ENTRIES : -EFAULT; } enum ipc_mux_protocol ipc_mux_get_active_protocol(struct iosm_mux *ipc_mux) @@ -435,9 +441,11 @@ void ipc_mux_deinit(struct iosm_mux *ipc_mux) return; ipc_mux_stop_netif_for_all_sessions(ipc_mux); - channel_close = &mux_msg.channel_close; - channel_close->event = MUX_E_MUX_CHANNEL_CLOSE; - ipc_mux_schedule(ipc_mux, &mux_msg); + if (ipc_mux->state == MUX_S_ACTIVE) { + channel_close = &mux_msg.channel_close; + channel_close->event = MUX_E_MUX_CHANNEL_CLOSE; + ipc_mux_schedule(ipc_mux, &mux_msg); + } /* Empty the ADB free list. */ free_list = &ipc_mux->ul_adb.free_list; diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.h b/drivers/net/wwan/iosm/iosm_ipc_mux.h index ddd2cd0bd911..88debaa1ed31 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.h +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.h @@ -278,7 +278,6 @@ struct iosm_mux { struct ipc_mux_config { enum ipc_mux_protocol protocol; enum ipc_mux_ul_flow ul_flow; - int nr_sessions; int instance_id; }; diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c index bdb2d32cdb6d..40fb54a0513e 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux_codec.c @@ -175,7 +175,7 @@ static int ipc_mux_dl_dlcmds_decode_process(struct iosm_mux *ipc_mux, switch (le32_to_cpu(cmdh->command_type)) { case MUX_LITE_CMD_FLOW_CTL: - if (cmdh->if_id >= ipc_mux->nr_sessions) { + if (cmdh->if_id >= IPC_MEM_MUX_IP_SESSION_ENTRIES) { dev_err(ipc_mux->dev, "if_id [%d] not valid", cmdh->if_id); return -EINVAL; /* No session interface id. */ @@ -307,13 +307,13 @@ static void ipc_mux_dl_fcth_decode(struct iosm_mux *ipc_mux, } if_id = fct->if_id; - if (if_id >= ipc_mux->nr_sessions) { + if (if_id >= IPC_MEM_MUX_IP_SESSION_ENTRIES) { dev_err(ipc_mux->dev, "not supported if_id: %d", if_id); return; } /* Is the session active ? */ - if_id = array_index_nospec(if_id, ipc_mux->nr_sessions); + if_id = array_index_nospec(if_id, IPC_MEM_MUX_IP_SESSION_ENTRIES); wwan = ipc_mux->session[if_id].wwan; if (!wwan) { dev_err(ipc_mux->dev, "session Net ID is NULL"); @@ -355,13 +355,13 @@ static void ipc_mux_dl_adgh_decode(struct iosm_mux *ipc_mux, } if_id = adgh->if_id; - if (if_id >= ipc_mux->nr_sessions) { + if (if_id >= IPC_MEM_MUX_IP_SESSION_ENTRIES) { dev_err(ipc_mux->dev, "invalid if_id while decoding %d", if_id); return; } /* Is the session active ? */ - if_id = array_index_nospec(if_id, ipc_mux->nr_sessions); + if_id = array_index_nospec(if_id, IPC_MEM_MUX_IP_SESSION_ENTRIES); wwan = ipc_mux->session[if_id].wwan; if (!wwan) { dev_err(ipc_mux->dev, "session Net ID is NULL"); @@ -538,7 +538,7 @@ static void ipc_mux_stop_tx_for_all_sessions(struct iosm_mux *ipc_mux) struct mux_session *session; int idx; - for (idx = 0; idx < ipc_mux->nr_sessions; idx++) { + for (idx = 0; idx < IPC_MEM_MUX_IP_SESSION_ENTRIES; idx++) { session = &ipc_mux->session[idx]; if (!session->wwan) @@ -563,7 +563,7 @@ static bool ipc_mux_lite_send_qlt(struct iosm_mux *ipc_mux) qlt_size = offsetof(struct ipc_mem_lite_gen_tbl, vfl) + MUX_QUEUE_LEVEL * sizeof(struct mux_lite_vfl); - for (i = 0; i < ipc_mux->nr_sessions; i++) { + for (i = 0; i < IPC_MEM_MUX_IP_SESSION_ENTRIES; i++) { session = &ipc_mux->session[i]; if (!session->wwan || session->flow_ctl_mask) @@ -777,13 +777,13 @@ bool ipc_mux_ul_data_encode(struct iosm_mux *ipc_mux) ipc_mux->adb_prep_ongoing = true; - for (i = 0; i < ipc_mux->nr_sessions; i++) { + for (i = 0; i < IPC_MEM_MUX_IP_SESSION_ENTRIES; i++) { session_id = ipc_mux->rr_next_session; session = &ipc_mux->session[session_id]; /* Go to next handle rr_next_session overflow */ ipc_mux->rr_next_session++; - if (ipc_mux->rr_next_session >= ipc_mux->nr_sessions) + if (ipc_mux->rr_next_session >= IPC_MEM_MUX_IP_SESSION_ENTRIES) ipc_mux->rr_next_session = 0; if (!session->wwan || session->flow_ctl_mask || diff --git a/drivers/net/wwan/iosm/iosm_ipc_trace.c b/drivers/net/wwan/iosm/iosm_ipc_trace.c index c5fa12599c2b..eeecfa3d10c5 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_trace.c +++ b/drivers/net/wwan/iosm/iosm_ipc_trace.c @@ -17,11 +17,13 @@ /** * ipc_trace_port_rx - Receive trace packet from cp and write to relay buffer - * @ipc_trace: Pointer to the ipc trace data-struct + * @ipc_imem: Pointer to iosm_imem structure * @skb: Pointer to struct sk_buff */ -void ipc_trace_port_rx(struct iosm_trace *ipc_trace, struct sk_buff *skb) +void ipc_trace_port_rx(struct iosm_imem *ipc_imem, struct sk_buff *skb) { + struct iosm_trace *ipc_trace = ipc_imem->trace; + if (ipc_trace->ipc_rchan) relay_write(ipc_trace->ipc_rchan, skb->data, skb->len); @@ -132,9 +134,14 @@ static const struct file_operations ipc_trace_fops = { */ struct iosm_trace *ipc_trace_init(struct iosm_imem *ipc_imem) { - struct iosm_trace *ipc_trace = kzalloc(sizeof(*ipc_trace), GFP_KERNEL); - struct dentry *debugfs_pdev; + struct ipc_chnl_cfg chnl_cfg = { 0 }; + struct iosm_trace *ipc_trace; + + ipc_chnl_cfg_get(&chnl_cfg, IPC_MEM_CTRL_CHL_ID_3); + ipc_imem_channel_init(ipc_imem, IPC_CTYPE_CTRL, chnl_cfg, + IRQ_MOD_OFF); + ipc_trace = kzalloc(sizeof(*ipc_trace), GFP_KERNEL); if (!ipc_trace) return NULL; @@ -144,15 +151,14 @@ struct iosm_trace *ipc_trace_init(struct iosm_imem *ipc_imem) ipc_trace->chl_id = IPC_MEM_CTRL_CHL_ID_3; mutex_init(&ipc_trace->trc_mutex); - debugfs_pdev = wwan_get_debugfs_dir(ipc_imem->dev); ipc_trace->ctrl_file = debugfs_create_file(IOSM_TRC_DEBUGFS_TRACE_CTRL, IOSM_TRC_FILE_PERM, - debugfs_pdev, + ipc_imem->debugfs_dir, ipc_trace, &ipc_trace_fops); ipc_trace->ipc_rchan = relay_open(IOSM_TRC_DEBUGFS_TRACE, - debugfs_pdev, + ipc_imem->debugfs_dir, IOSM_TRC_SUB_BUFF_SIZE, IOSM_TRC_N_SUB_BUFF, &relay_callbacks, NULL); @@ -166,6 +172,9 @@ struct iosm_trace *ipc_trace_init(struct iosm_imem *ipc_imem) */ void ipc_trace_deinit(struct iosm_trace *ipc_trace) { + if (!ipc_trace) + return; + debugfs_remove(ipc_trace->ctrl_file); relay_close(ipc_trace->ipc_rchan); mutex_destroy(&ipc_trace->trc_mutex); diff --git a/drivers/net/wwan/iosm/iosm_ipc_trace.h b/drivers/net/wwan/iosm/iosm_ipc_trace.h index 53346183af9c..5ebe7790585c 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_trace.h +++ b/drivers/net/wwan/iosm/iosm_ipc_trace.h @@ -45,7 +45,30 @@ struct iosm_trace { enum trace_ctrl_mode mode; }; +#ifdef CONFIG_WWAN_DEBUGFS + +static inline bool ipc_is_trace_channel(struct iosm_imem *ipc_mem, u16 chl_id) +{ + return ipc_mem->trace && ipc_mem->trace->chl_id == chl_id; +} + struct iosm_trace *ipc_trace_init(struct iosm_imem *ipc_imem); void ipc_trace_deinit(struct iosm_trace *ipc_trace); -void ipc_trace_port_rx(struct iosm_trace *ipc_trace, struct sk_buff *skb); +void ipc_trace_port_rx(struct iosm_imem *ipc_imem, struct sk_buff *skb); + +#else + +static inline bool ipc_is_trace_channel(struct iosm_imem *ipc_mem, u16 chl_id) +{ + return false; +} + +static inline void ipc_trace_port_rx(struct iosm_imem *ipc_imem, + struct sk_buff *skb) +{ + dev_kfree_skb(skb); +} + +#endif + #endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index b571d9cedba4..27151148c782 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -8,6 +8,7 @@ #include <linux/if_link.h> #include <linux/rtnetlink.h> #include <linux/wwan.h> +#include <net/pkt_sched.h> #include "iosm_ipc_chnl_cfg.h" #include "iosm_ipc_imem_ops.h" @@ -159,7 +160,7 @@ static void ipc_wwan_setup(struct net_device *iosm_dev) { iosm_dev->header_ops = NULL; iosm_dev->hard_header_len = 0; - iosm_dev->priv_flags |= IFF_NO_QUEUE; + iosm_dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; iosm_dev->type = ARPHRD_NONE; iosm_dev->mtu = ETH_DATA_LEN; diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.h b/drivers/net/wwan/iosm/iosm_ipc_wwan.h index 4925f22dff0a..a23e926398ff 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.h +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.h @@ -42,14 +42,4 @@ int ipc_wwan_receive(struct iosm_wwan *ipc_wwan, struct sk_buff *skb_arg, * */ void ipc_wwan_tx_flowctrl(struct iosm_wwan *ipc_wwan, int id, bool on); - -/** - * ipc_wwan_is_tx_stopped - Checks if Tx stopped for a Interface id. - * @ipc_wwan: Pointer to wwan instance - * @id: Ipc mux channel session id - * - * Return: true if stopped, false otherwise - */ -bool ipc_wwan_is_tx_stopped(struct iosm_wwan *ipc_wwan, int id); - #endif diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 5bf62dc35ac7..1508dc2a497b 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -50,7 +50,9 @@ struct wwan_device { atomic_t port_id; const struct wwan_ops *ops; void *ops_ctxt; +#ifdef CONFIG_WWAN_DEBUGFS struct dentry *debugfs_dir; +#endif }; /** @@ -146,6 +148,7 @@ static struct wwan_device *wwan_dev_get_by_name(const char *name) return to_wwan_dev(dev); } +#ifdef CONFIG_WWAN_DEBUGFS struct dentry *wwan_get_debugfs_dir(struct device *parent) { struct wwan_device *wwandev; @@ -157,6 +160,7 @@ struct dentry *wwan_get_debugfs_dir(struct device *parent) return wwandev->debugfs_dir; } EXPORT_SYMBOL_GPL(wwan_get_debugfs_dir); +#endif /* This function allocates and registers a new WWAN device OR if a WWAN device * already exist for the given parent, it gets a reference and return it. @@ -166,7 +170,6 @@ EXPORT_SYMBOL_GPL(wwan_get_debugfs_dir); static struct wwan_device *wwan_create_dev(struct device *parent) { struct wwan_device *wwandev; - const char *wwandev_name; int err, id; /* The 'find-alloc-register' operation must be protected against @@ -206,9 +209,11 @@ static struct wwan_device *wwan_create_dev(struct device *parent) goto done_unlock; } - wwandev_name = kobject_name(&wwandev->dev.kobj); - wwandev->debugfs_dir = debugfs_create_dir(wwandev_name, - wwan_debugfs_dir); +#ifdef CONFIG_WWAN_DEBUGFS + wwandev->debugfs_dir = + debugfs_create_dir(kobject_name(&wwandev->dev.kobj), + wwan_debugfs_dir); +#endif done_unlock: mutex_unlock(&wwan_register_lock); @@ -240,7 +245,9 @@ static void wwan_remove_dev(struct wwan_device *wwandev) ret = device_for_each_child(&wwandev->dev, NULL, is_wwan_child); if (!ret) { +#ifdef CONFIG_WWAN_DEBUGFS debugfs_remove_recursive(wwandev->debugfs_dir); +#endif device_unregister(&wwandev->dev); } else { put_device(&wwandev->dev); @@ -1140,7 +1147,9 @@ static int __init wwan_init(void) goto destroy; } +#ifdef CONFIG_WWAN_DEBUGFS wwan_debugfs_dir = debugfs_create_dir("wwan", NULL); +#endif return 0; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 4c63564adeaa..1af8a4513708 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -666,6 +666,7 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl, struct request *rq) { if (ctrl->state != NVME_CTRL_DELETING_NOIO && + ctrl->state != NVME_CTRL_DELETING && ctrl->state != NVME_CTRL_DEAD && !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) && !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) @@ -1749,9 +1750,20 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) */ if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT))) return -EINVAL; - if (ctrl->max_integrity_segments) - ns->features |= - (NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS); + + ns->features |= NVME_NS_EXT_LBAS; + + /* + * The current fabrics transport drivers support namespace + * metadata formats only if nvme_ns_has_pi() returns true. + * Suppress support for all other formats so the namespace will + * have a 0 capacity and not be usable through the block stack. + * + * Note, this check will need to be modified if any drivers + * gain the ability to use other metadata formats. + */ + if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns)) + ns->features |= NVME_NS_METADATA_SUPPORTED; } else { /* * For PCIe controllers, we can't easily remap the separate @@ -2696,8 +2708,9 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys, if (tmp->cntlid == ctrl->cntlid) { dev_err(ctrl->device, - "Duplicate cntlid %u with %s, rejecting\n", - ctrl->cntlid, dev_name(tmp->device)); + "Duplicate cntlid %u with %s, subsys %s, rejecting\n", + ctrl->cntlid, dev_name(tmp->device), + subsys->subnqn); return false; } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 7f2071f2460c..13e5d503ed07 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -866,7 +866,7 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) } if (ana_log_size > ctrl->ana_log_size) { nvme_mpath_stop(ctrl); - kfree(ctrl->ana_log_buf); + nvme_mpath_uninit(ctrl); ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL); if (!ctrl->ana_log_buf) return -ENOMEM; @@ -886,4 +886,5 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl) { kfree(ctrl->ana_log_buf); ctrl->ana_log_buf = NULL; + ctrl->ana_log_size = 0; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index b334af8aa264..9b095ee01364 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -709,7 +709,7 @@ static inline bool nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq, return true; if (ctrl->ops->flags & NVME_F_FABRICS && ctrl->state == NVME_CTRL_DELETING) - return true; + return queue_live; return __nvme_check_ready(ctrl, rq, queue_live); } int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd, diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index bfc259e0d7b8..9f81beb4df4e 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -166,7 +166,10 @@ static int nvme_zone_parse_entry(struct nvme_ns *ns, zone.len = ns->zsze; zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap)); zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba)); - zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp)); + if (zone.cond == BLK_ZONE_COND_FULL) + zone.wp = zone.start + zone.len; + else + zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp)); return cb(&zone, idx, data); } diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index cb6a473c3eaf..7c1c43ce466b 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -922,7 +922,14 @@ static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length); int ret; - if (!nvme_is_write(cmd->req.cmd) || + /* + * This command has not been processed yet, hence we are trying to + * figure out if there is still pending data left to receive. If + * we don't, we can simply prepare for the next pdu and bail out, + * otherwise we will need to prepare a buffer and receive the + * stale data before continuing forward. + */ + if (!nvme_is_write(cmd->req.cmd) || !data_len || data_len > cmd->req.port->inline_data_size) { nvmet_prepare_receive_pdu(queue); return; diff --git a/drivers/of/irq.c b/drivers/of/irq.c index b10f015b2e37..2b07677a386b 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -76,6 +76,26 @@ struct device_node *of_irq_find_parent(struct device_node *child) } EXPORT_SYMBOL_GPL(of_irq_find_parent); +/* + * These interrupt controllers abuse interrupt-map for unspeakable + * reasons and rely on the core code to *ignore* it (the drivers do + * their own parsing of the property). + * + * If you think of adding to the list for something *new*, think + * again. There is a high chance that you will be sent back to the + * drawing board. + */ +static const char * const of_irq_imap_abusers[] = { + "CBEA,platform-spider-pic", + "sti,platform-spider-pic", + "realtek,rtl-intc", + "fsl,ls1021a-extirq", + "fsl,ls1043a-extirq", + "fsl,ls1088a-extirq", + "renesas,rza1-irqc", + NULL, +}; + /** * of_irq_parse_raw - Low level interrupt tree parsing * @addr: address specifier (start of "reg" property of the device) in be32 format @@ -159,12 +179,15 @@ int of_irq_parse_raw(const __be32 *addr, struct of_phandle_args *out_irq) /* * Now check if cursor is an interrupt-controller and * if it is then we are done, unless there is an - * interrupt-map which takes precedence. + * interrupt-map which takes precedence except on one + * of these broken platforms that want to parse + * interrupt-map themselves for $reason. */ bool intc = of_property_read_bool(ipar, "interrupt-controller"); imap = of_get_property(ipar, "interrupt-map", &imaplen); - if (imap == NULL && intc) { + if (intc && + (!imap || of_device_compatible_match(ipar, of_irq_imap_abusers))) { pr_debug(" -> got it !\n"); return 0; } diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 93b141110537..7fc5135ffbbf 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -332,8 +332,8 @@ config PCIE_APPLE If unsure, say Y if you have an Apple Silicon system. config PCIE_MT7621 - tristate "MediaTek MT7621 PCIe Controller" - depends on (RALINK && SOC_MT7621) || (MIPS && COMPILE_TEST) + bool "MediaTek MT7621 PCIe Controller" + depends on SOC_MT7621 || (MIPS && COMPILE_TEST) select PHY_MT7621_PCI default SOC_MT7621 help diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c index c24dab383654..722dacdd5a17 100644 --- a/drivers/pci/controller/dwc/pci-exynos.c +++ b/drivers/pci/controller/dwc/pci-exynos.c @@ -19,6 +19,7 @@ #include <linux/platform_device.h> #include <linux/phy/phy.h> #include <linux/regulator/consumer.h> +#include <linux/module.h> #include "pcie-designware.h" diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c index 7b17da2f9b3f..cfe66bf04c1d 100644 --- a/drivers/pci/controller/dwc/pcie-qcom-ep.c +++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c @@ -18,6 +18,7 @@ #include <linux/pm_domain.h> #include <linux/regmap.h> #include <linux/reset.h> +#include <linux/module.h> #include "pcie-designware.h" diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index c5300d49807a..c3b725afa11f 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -32,7 +32,6 @@ #define PCIE_CORE_DEV_ID_REG 0x0 #define PCIE_CORE_CMD_STATUS_REG 0x4 #define PCIE_CORE_DEV_REV_REG 0x8 -#define PCIE_CORE_EXP_ROM_BAR_REG 0x30 #define PCIE_CORE_PCIEXP_CAP 0xc0 #define PCIE_CORE_ERR_CAPCTL_REG 0x118 #define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX BIT(5) @@ -774,10 +773,6 @@ advk_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge, *value = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); return PCI_BRIDGE_EMUL_HANDLED; - case PCI_ROM_ADDRESS1: - *value = advk_readl(pcie, PCIE_CORE_EXP_ROM_BAR_REG); - return PCI_BRIDGE_EMUL_HANDLED; - case PCI_INTERRUPT_LINE: { /* * From the whole 32bit register we support reading from HW only @@ -810,10 +805,6 @@ advk_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge, advk_writel(pcie, new, PCIE_CORE_CMD_STATUS_REG); break; - case PCI_ROM_ADDRESS1: - advk_writel(pcie, new, PCIE_CORE_EXP_ROM_BAR_REG); - break; - case PCI_INTERRUPT_LINE: if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) { u32 val = advk_readl(pcie, PCIE_CORE_CTRL1_REG); diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c index 1bf4d75b61be..b090924b41fe 100644 --- a/drivers/pci/controller/pcie-apple.c +++ b/drivers/pci/controller/pcie-apple.c @@ -516,7 +516,7 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, int ret, i; reset = gpiod_get_from_of_node(np, "reset-gpios", 0, - GPIOD_OUT_LOW, "#PERST"); + GPIOD_OUT_LOW, "PERST#"); if (IS_ERR(reset)) return PTR_ERR(reset); @@ -539,12 +539,22 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK); + /* Assert PERST# before setting up the clock */ + gpiod_set_value(reset, 1); + ret = apple_pcie_setup_refclk(pcie, port); if (ret < 0) return ret; + /* The minimal Tperst-clk value is 100us (PCIe CEM r5.0, 2.9.2) */ + usleep_range(100, 200); + + /* Deassert PERST# */ rmw_set(PORT_PERST_OFF, port->base + PORT_PERST); - gpiod_set_value(reset, 1); + gpiod_set_value(reset, 0); + + /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */ + msleep(100); ret = readl_relaxed_poll_timeout(port->base + PORT_STATUS, stat, stat & PORT_STATUS_READY, 100, 250000); diff --git a/drivers/phy/hisilicon/phy-hi3670-pcie.c b/drivers/phy/hisilicon/phy-hi3670-pcie.c index c64c6679b1b9..0ac9634b398d 100644 --- a/drivers/phy/hisilicon/phy-hi3670-pcie.c +++ b/drivers/phy/hisilicon/phy-hi3670-pcie.c @@ -757,8 +757,8 @@ static int hi3670_pcie_phy_get_resources(struct hi3670_pcie_phy *phy, return PTR_ERR(phy->sysctrl); phy->pmctrl = syscon_regmap_lookup_by_compatible("hisilicon,hi3670-pmctrl"); - if (IS_ERR(phy->sysctrl)) - return PTR_ERR(phy->sysctrl); + if (IS_ERR(phy->pmctrl)) + return PTR_ERR(phy->pmctrl); /* clocks */ phy->phy_ref_clk = devm_clk_get(dev, "phy_ref"); diff --git a/drivers/phy/marvell/phy-mvebu-cp110-utmi.c b/drivers/phy/marvell/phy-mvebu-cp110-utmi.c index 08d178a4dc13..aa27c7994610 100644 --- a/drivers/phy/marvell/phy-mvebu-cp110-utmi.c +++ b/drivers/phy/marvell/phy-mvebu-cp110-utmi.c @@ -82,9 +82,9 @@ * struct mvebu_cp110_utmi - PHY driver data * * @regs: PHY registers - * @syscom: Regmap with system controller registers + * @syscon: Regmap with system controller registers * @dev: device driver handle - * @caps: PHY capabilities + * @ops: phy ops */ struct mvebu_cp110_utmi { void __iomem *regs; diff --git a/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c b/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c index bfff0c8c9130..fec1da470d26 100644 --- a/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-ipq806x-usb.c @@ -127,12 +127,13 @@ struct phy_drvdata { }; /** - * Write register and read back masked value to confirm it is written + * usb_phy_write_readback() - Write register and read back masked value to + * confirm it is written * - * @base - QCOM DWC3 PHY base virtual address. - * @offset - register offset. - * @mask - register bitmask specifying what should be updated - * @val - value to write. + * @phy_dwc3: QCOM DWC3 phy context + * @offset: register offset. + * @mask: register bitmask specifying what should be updated + * @val: value to write. */ static inline void usb_phy_write_readback(struct usb_phy *phy_dwc3, u32 offset, @@ -171,11 +172,11 @@ static int wait_for_latch(void __iomem *addr) } /** - * Write SSPHY register + * usb_ss_write_phycreg() - Write SSPHY register * - * @base - QCOM DWC3 PHY base virtual address. - * @addr - SSPHY address to write. - * @val - value to write. + * @phy_dwc3: QCOM DWC3 phy context + * @addr: SSPHY address to write. + * @val: value to write. */ static int usb_ss_write_phycreg(struct usb_phy *phy_dwc3, u32 addr, u32 val) @@ -209,10 +210,11 @@ err_wait: } /** - * Read SSPHY register. + * usb_ss_read_phycreg() - Read SSPHY register. * - * @base - QCOM DWC3 PHY base virtual address. - * @addr - SSPHY address to read. + * @phy_dwc3: QCOM DWC3 phy context + * @addr: SSPHY address to read. + * @val: pointer in which read is store. */ static int usb_ss_read_phycreg(struct usb_phy *phy_dwc3, u32 addr, u32 *val) diff --git a/drivers/phy/qualcomm/phy-qcom-qmp.c b/drivers/phy/qualcomm/phy-qcom-qmp.c index 456a59d8c7d0..c96639d5f581 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp.c @@ -2973,6 +2973,9 @@ struct qmp_phy_combo_cfg { * @qmp: QMP phy to which this lane belongs * @lane_rst: lane's reset controller * @mode: current PHY mode + * @dp_aux_cfg: Display port aux config + * @dp_opts: Display port optional config + * @dp_clks: Display port clocks */ struct qmp_phy { struct phy *phy; diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hsic.c b/drivers/phy/qualcomm/phy-qcom-usb-hsic.c index 04d18d52f700..716a77748ed8 100644 --- a/drivers/phy/qualcomm/phy-qcom-usb-hsic.c +++ b/drivers/phy/qualcomm/phy-qcom-usb-hsic.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * Copyright (C) 2016 Linaro Ltd */ #include <linux/module.h> diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c index 7df6a63ad37b..e4f4a9be5132 100644 --- a/drivers/phy/st/phy-stm32-usbphyc.c +++ b/drivers/phy/st/phy-stm32-usbphyc.c @@ -478,7 +478,7 @@ static void stm32_usbphyc_phy_tuning(struct stm32_usbphyc *usbphyc, if (!of_property_read_bool(np, "st,no-lsfs-fb-cap")) usbphyc_phy->tune |= LFSCAPEN; - if (of_property_read_bool(np, "st,slow-hs-slew-rate")) + if (of_property_read_bool(np, "st,decrease-hs-slew-rate")) usbphyc_phy->tune |= HSDRVSLEW; ret = of_property_read_u32(np, "st,tune-hs-dc-level", &val); diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c index 2ff56ce77b30..c1211c4f863c 100644 --- a/drivers/phy/ti/phy-am654-serdes.c +++ b/drivers/phy/ti/phy-am654-serdes.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * PCIe SERDES driver for AM654x SoC * * Copyright (C) 2018 - 2019 Texas Instruments Incorporated - http://www.ti.com/ diff --git a/drivers/phy/ti/phy-j721e-wiz.c b/drivers/phy/ti/phy-j721e-wiz.c index 126f5b8735cc..b3384c31637a 100644 --- a/drivers/phy/ti/phy-j721e-wiz.c +++ b/drivers/phy/ti/phy-j721e-wiz.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * Wrapper driver for SERDES used in J721E * * Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/ diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index ebceb1520ce8..3a505fe5715a 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -89,9 +89,9 @@ static inline void omap_usb_writel(void __iomem *addr, unsigned int offset, } /** - * omap_usb2_set_comparator - links the comparator present in the system with - * this phy - * @comparator - the companion phy(comparator) for this phy + * omap_usb2_set_comparator() - links the comparator present in the system with this phy + * + * @comparator: the companion phy(comparator) for this phy * * The phy companion driver should call this API passing the phy_companion * filled with set_vbus and start_srp to be used by usb phy. diff --git a/drivers/phy/ti/phy-tusb1210.c b/drivers/phy/ti/phy-tusb1210.c index a63213f5972a..15c1c79e5c29 100644 --- a/drivers/phy/ti/phy-tusb1210.c +++ b/drivers/phy/ti/phy-tusb1210.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * tusb1210.c - TUSB1210 USB ULPI PHY driver * * Copyright (C) 2015 Intel Corporation diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index b7e50ed050a8..841c44cd64c2 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -76,7 +76,7 @@ #define AMD_CPU_ID_CZN AMD_CPU_ID_RN #define AMD_CPU_ID_YC 0x14B5 -#define PMC_MSG_DELAY_MIN_US 100 +#define PMC_MSG_DELAY_MIN_US 50 #define RESPONSE_REGISTER_LOOP_MAX 20000 #define SOC_SUBSYSTEM_IP_MAX 12 diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index 08598942a6d7..13f8cf70b9ae 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -99,6 +99,13 @@ static const struct dmi_system_id button_array_table[] = { DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"), }, }, + { + .ident = "Microsoft Surface Go 3", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 3"), + }, + }, { } }; diff --git a/drivers/platform/x86/lg-laptop.c b/drivers/platform/x86/lg-laptop.c index ae9293024c77..a91847a551a7 100644 --- a/drivers/platform/x86/lg-laptop.c +++ b/drivers/platform/x86/lg-laptop.c @@ -657,6 +657,18 @@ static int acpi_add(struct acpi_device *device) if (product && strlen(product) > 4) switch (product[4]) { case '5': + if (strlen(product) > 5) + switch (product[5]) { + case 'N': + year = 2021; + break; + case '0': + year = 2016; + break; + default: + year = 2022; + } + break; case '6': year = 2016; break; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index b3ac9c3f3b7c..bb1abb947e1e 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -3015,6 +3015,8 @@ static struct attribute *hotkey_attributes[] = { &dev_attr_hotkey_all_mask.attr, &dev_attr_hotkey_adaptive_all_mask.attr, &dev_attr_hotkey_recommended_mask.attr, + &dev_attr_hotkey_tablet_mode.attr, + &dev_attr_hotkey_radio_sw.attr, #ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL &dev_attr_hotkey_source_mask.attr, &dev_attr_hotkey_poll_freq.attr, @@ -5726,11 +5728,11 @@ static const char * const tpacpi_led_names[TPACPI_LED_NUMLEDS] = { "tpacpi::standby", "tpacpi::dock_status1", "tpacpi::dock_status2", - "tpacpi::unknown_led2", + "tpacpi::lid_logo_dot", "tpacpi::unknown_led3", "tpacpi::thinkvantage", }; -#define TPACPI_SAFE_LEDS 0x1081U +#define TPACPI_SAFE_LEDS 0x1481U static inline bool tpacpi_is_led_restricted(const unsigned int led) { diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index fa8812039b82..17dd54d4b783 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -905,6 +905,16 @@ static const struct ts_dmi_data trekstor_primetab_t13b_data = { .properties = trekstor_primetab_t13b_props, }; +static const struct property_entry trekstor_surftab_duo_w1_props[] = { + PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"), + { } +}; + +static const struct ts_dmi_data trekstor_surftab_duo_w1_data = { + .acpi_name = "GDIX1001:00", + .properties = trekstor_surftab_duo_w1_props, +}; + static const struct property_entry trekstor_surftab_twin_10_1_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 20), PROPERTY_ENTRY_U32("touchscreen-min-y", 0), @@ -1503,6 +1513,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* TrekStor SurfTab duo W1 10.1 ST10432-10b */ + .driver_data = (void *)&trekstor_surftab_duo_w1_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TrekStor"), + DMI_MATCH(DMI_PRODUCT_NAME, "SurfTab duo W1 10.1 (VT4)"), + }, + }, + { /* TrekStor SurfTab twin 10.1 ST10432-8 */ .driver_data = (void *)&trekstor_surftab_twin_10_1_data, .matches = { diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index b9fac786246a..2a5c1829aab7 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -463,17 +463,12 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent) static int __init init_dtpm(void) { - struct dtpm_descr *dtpm_descr; - pct = powercap_register_control_type(NULL, "dtpm", NULL); if (IS_ERR(pct)) { pr_err("Failed to register control type\n"); return PTR_ERR(pct); } - for_each_dtpm_table(dtpm_descr) - dtpm_descr->init(); - return 0; } late_initcall(init_dtpm); diff --git a/drivers/ptp/ptp_ines.c b/drivers/ptp/ptp_ines.c index 6c7c2843ba0b..61f47fb9d997 100644 --- a/drivers/ptp/ptp_ines.c +++ b/drivers/ptp/ptp_ines.c @@ -338,10 +338,6 @@ static int ines_hwtstamp(struct mii_timestamper *mii_ts, struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - /* reserved for future extensions */ - if (cfg.flags) - return -EINVAL; - switch (cfg.tx_type) { case HWTSTAMP_TX_OFF: ts_stat_tx = 0; diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c index 4c5bba52b105..24d3395964cc 100644 --- a/drivers/reset/tegra/reset-bpmp.c +++ b/drivers/reset/tegra/reset-bpmp.c @@ -20,7 +20,6 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc); struct mrq_reset_request request; struct tegra_bpmp_message msg; - int err; memset(&request, 0, sizeof(request)); request.cmd = command; @@ -31,13 +30,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc, msg.tx.data = &request; msg.tx.size = sizeof(request); - err = tegra_bpmp_transfer(bpmp, &msg); - if (err) - return err; - if (msg.rx.ret) - return -EINVAL; - - return 0; + return tegra_bpmp_transfer(bpmp, &msg); } static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc, diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c index b940e0268f96..e83453bea2ae 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -5095,14 +5095,9 @@ lpfc_cmpl_els_logo_acc(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb, /* NPort Recovery mode or node is just allocated */ if (!lpfc_nlp_not_used(ndlp)) { /* A LOGO is completing and the node is in NPR state. - * If this a fabric node that cleared its transport - * registration, release the rpi. + * Just unregister the RPI because the node is still + * required. */ - spin_lock_irq(&ndlp->lock); - ndlp->nlp_flag &= ~NLP_NPR_2B_DISC; - if (phba->sli_rev == LPFC_SLI_REV4) - ndlp->nlp_flag |= NLP_RELEASE_RPI; - spin_unlock_irq(&ndlp->lock); lpfc_unreg_rpi(vport, ndlp); } else { /* Indicate the node has already released, should diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c index bed8cc125544..fbfeb0b046dd 100644 --- a/drivers/scsi/pm8001/pm8001_init.c +++ b/drivers/scsi/pm8001/pm8001_init.c @@ -282,12 +282,12 @@ static int pm8001_alloc(struct pm8001_hba_info *pm8001_ha, if (rc) { pm8001_dbg(pm8001_ha, FAIL, "pm8001_setup_irq failed [ret: %d]\n", rc); - goto err_out_shost; + goto err_out; } /* Request Interrupt */ rc = pm8001_request_irq(pm8001_ha); if (rc) - goto err_out_shost; + goto err_out; count = pm8001_ha->max_q_num; /* Queues are chosen based on the number of cores/msix availability */ @@ -423,8 +423,6 @@ static int pm8001_alloc(struct pm8001_hba_info *pm8001_ha, pm8001_tag_init(pm8001_ha); return 0; -err_out_shost: - scsi_remove_host(pm8001_ha->shost); err_out_nodev: for (i = 0; i < pm8001_ha->max_memcnt; i++) { if (pm8001_ha->memoryMap.region[i].virt_ptr != NULL) { diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index 84a4204a2cb4..5916ed7662d5 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -732,7 +732,6 @@ static void qedi_process_cmd_cleanup_resp(struct qedi_ctx *qedi, { struct qedi_work_map *work, *work_tmp; u32 proto_itt = cqe->itid; - itt_t protoitt = 0; int found = 0; struct qedi_cmd *qedi_cmd = NULL; u32 iscsi_cid; @@ -812,16 +811,12 @@ unlock: return; check_cleanup_reqs: - if (qedi_conn->cmd_cleanup_req > 0) { - QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID, + if (atomic_inc_return(&qedi_conn->cmd_cleanup_cmpl) == + qedi_conn->cmd_cleanup_req) { + QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "Freeing tid=0x%x for cid=0x%x\n", cqe->itid, qedi_conn->iscsi_conn_id); - qedi_conn->cmd_cleanup_cmpl++; wake_up(&qedi_conn->wait_queue); - } else { - QEDI_ERR(&qedi->dbg_ctx, - "Delayed or untracked cleanup response, itt=0x%x, tid=0x%x, cid=0x%x\n", - protoitt, cqe->itid, qedi_conn->iscsi_conn_id); } } @@ -1163,7 +1158,7 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn, } qedi_conn->cmd_cleanup_req = 0; - qedi_conn->cmd_cleanup_cmpl = 0; + atomic_set(&qedi_conn->cmd_cleanup_cmpl, 0); QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "active_cmd_count=%d, cid=0x%x, in_recovery=%d, lun_reset=%d\n", @@ -1215,16 +1210,15 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn, qedi_conn->iscsi_conn_id); rval = wait_event_interruptible_timeout(qedi_conn->wait_queue, - ((qedi_conn->cmd_cleanup_req == - qedi_conn->cmd_cleanup_cmpl) || - test_bit(QEDI_IN_RECOVERY, - &qedi->flags)), - 5 * HZ); + (qedi_conn->cmd_cleanup_req == + atomic_read(&qedi_conn->cmd_cleanup_cmpl)) || + test_bit(QEDI_IN_RECOVERY, &qedi->flags), + 5 * HZ); if (rval) { QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "i/o cmd_cleanup_req=%d, equal to cmd_cleanup_cmpl=%d, cid=0x%x\n", qedi_conn->cmd_cleanup_req, - qedi_conn->cmd_cleanup_cmpl, + atomic_read(&qedi_conn->cmd_cleanup_cmpl), qedi_conn->iscsi_conn_id); return 0; @@ -1233,7 +1227,7 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn, QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM, "i/o cmd_cleanup_req=%d, not equal to cmd_cleanup_cmpl=%d, cid=0x%x\n", qedi_conn->cmd_cleanup_req, - qedi_conn->cmd_cleanup_cmpl, + atomic_read(&qedi_conn->cmd_cleanup_cmpl), qedi_conn->iscsi_conn_id); iscsi_host_for_each_session(qedi->shost, @@ -1242,11 +1236,10 @@ int qedi_cleanup_all_io(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn, /* Enable IOs for all other sessions except current.*/ if (!wait_event_interruptible_timeout(qedi_conn->wait_queue, - (qedi_conn->cmd_cleanup_req == - qedi_conn->cmd_cleanup_cmpl) || - test_bit(QEDI_IN_RECOVERY, - &qedi->flags), - 5 * HZ)) { + (qedi_conn->cmd_cleanup_req == + atomic_read(&qedi_conn->cmd_cleanup_cmpl)) || + test_bit(QEDI_IN_RECOVERY, &qedi->flags), + 5 * HZ)) { iscsi_host_for_each_session(qedi->shost, qedi_mark_device_available); return -1; @@ -1266,7 +1259,7 @@ void qedi_clearsq(struct qedi_ctx *qedi, struct qedi_conn *qedi_conn, qedi_ep = qedi_conn->ep; qedi_conn->cmd_cleanup_req = 0; - qedi_conn->cmd_cleanup_cmpl = 0; + atomic_set(&qedi_conn->cmd_cleanup_cmpl, 0); if (!qedi_ep) { QEDI_WARN(&qedi->dbg_ctx, diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 88aa7d8b11c9..282ecb4e39bb 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -412,7 +412,7 @@ static int qedi_conn_bind(struct iscsi_cls_session *cls_session, qedi_conn->iscsi_conn_id = qedi_ep->iscsi_cid; qedi_conn->fw_cid = qedi_ep->fw_cid; qedi_conn->cmd_cleanup_req = 0; - qedi_conn->cmd_cleanup_cmpl = 0; + atomic_set(&qedi_conn->cmd_cleanup_cmpl, 0); if (qedi_bind_conn_to_iscsi_cid(qedi, qedi_conn)) { rc = -EINVAL; diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h index a282860da0aa..9b9f2e44fdde 100644 --- a/drivers/scsi/qedi/qedi_iscsi.h +++ b/drivers/scsi/qedi/qedi_iscsi.h @@ -155,7 +155,7 @@ struct qedi_conn { spinlock_t list_lock; /* internal conn lock */ u32 active_cmd_count; u32 cmd_cleanup_req; - u32 cmd_cleanup_cmpl; + atomic_t cmd_cleanup_cmpl; u32 iscsi_conn_id; int itt; diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index 25549a8a2d72..7cf1f78cbaee 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -2491,6 +2491,9 @@ ql_dbg(uint level, scsi_qla_host_t *vha, uint id, const char *fmt, ...) struct va_format vaf; char pbuf[64]; + if (!ql_mask_match(level) && !trace_ql_dbg_log_enabled()) + return; + va_start(va, fmt); vaf.fmt = fmt; diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 3c0da3770edf..2104973a35cd 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -4342,7 +4342,7 @@ static int resp_report_zones(struct scsi_cmnd *scp, rep_max_zones = min((alloc_len - 64) >> ilog2(RZONES_DESC_HD), max_zones); - arr = kcalloc(RZONES_DESC_HD, alloc_len, GFP_ATOMIC); + arr = kzalloc(alloc_len, GFP_ATOMIC); if (!arr) { mk_sense_buffer(scp, ILLEGAL_REQUEST, INSUFF_RES_ASC, INSUFF_RES_ASCQ); diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index 51424557810d..f725248ba57f 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -421,6 +421,13 @@ static int ufs_intel_lkf_init(struct ufs_hba *hba) return err; } +static int ufs_intel_adl_init(struct ufs_hba *hba) +{ + hba->nop_out_timeout = 200; + hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8; + return ufs_intel_common_init(hba); +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .init = ufs_intel_common_init, @@ -449,6 +456,15 @@ static struct ufs_hba_variant_ops ufs_intel_lkf_hba_vops = { .device_reset = ufs_intel_device_reset, }; +static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_adl_init, + .exit = ufs_intel_common_exit, + .link_startup_notify = ufs_intel_link_startup_notify, + .resume = ufs_intel_resume, + .device_reset = ufs_intel_device_reset, +}; + #ifdef CONFIG_PM_SLEEP static int ufshcd_pci_restore(struct device *dev) { @@ -563,6 +579,8 @@ static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, { PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, { PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops }, + { PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/soc/imx/imx8m-blk-ctrl.c b/drivers/soc/imx/imx8m-blk-ctrl.c index 519b3651d1d9..c2f076b56e24 100644 --- a/drivers/soc/imx/imx8m-blk-ctrl.c +++ b/drivers/soc/imx/imx8m-blk-ctrl.c @@ -17,6 +17,7 @@ #define BLK_SFT_RSTN 0x0 #define BLK_CLK_EN 0x4 +#define BLK_MIPI_RESET_DIV 0x8 /* Mini/Nano DISPLAY_BLK_CTRL only */ struct imx8m_blk_ctrl_domain; @@ -36,6 +37,15 @@ struct imx8m_blk_ctrl_domain_data { const char *gpc_name; u32 rst_mask; u32 clk_mask; + + /* + * i.MX8M Mini and Nano have a third DISPLAY_BLK_CTRL register + * which is used to control the reset for the MIPI Phy. + * Since it's only present in certain circumstances, + * an if-statement should be used before setting and clearing this + * register. + */ + u32 mipi_phy_rst_mask; }; #define DOMAIN_MAX_CLKS 3 @@ -78,6 +88,8 @@ static int imx8m_blk_ctrl_power_on(struct generic_pm_domain *genpd) /* put devices into reset */ regmap_clear_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask); + if (data->mipi_phy_rst_mask) + regmap_clear_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask); /* enable upstream and blk-ctrl clocks to allow reset to propagate */ ret = clk_bulk_prepare_enable(data->num_clks, domain->clks); @@ -99,6 +111,8 @@ static int imx8m_blk_ctrl_power_on(struct generic_pm_domain *genpd) /* release reset */ regmap_set_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask); + if (data->mipi_phy_rst_mask) + regmap_set_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask); /* disable upstream clocks */ clk_bulk_disable_unprepare(data->num_clks, domain->clks); @@ -120,6 +134,9 @@ static int imx8m_blk_ctrl_power_off(struct generic_pm_domain *genpd) struct imx8m_blk_ctrl *bc = domain->bc; /* put devices into reset and disable clocks */ + if (data->mipi_phy_rst_mask) + regmap_clear_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask); + regmap_clear_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask); regmap_clear_bits(bc->regmap, BLK_CLK_EN, data->clk_mask); @@ -480,6 +497,7 @@ static const struct imx8m_blk_ctrl_domain_data imx8mm_disp_blk_ctl_domain_data[] .gpc_name = "mipi-dsi", .rst_mask = BIT(5), .clk_mask = BIT(8) | BIT(9), + .mipi_phy_rst_mask = BIT(17), }, [IMX8MM_DISPBLK_PD_MIPI_CSI] = { .name = "dispblk-mipi-csi", @@ -488,6 +506,7 @@ static const struct imx8m_blk_ctrl_domain_data imx8mm_disp_blk_ctl_domain_data[] .gpc_name = "mipi-csi", .rst_mask = BIT(3) | BIT(4), .clk_mask = BIT(10) | BIT(11), + .mipi_phy_rst_mask = BIT(16), }, }; diff --git a/drivers/soc/imx/soc-imx.c b/drivers/soc/imx/soc-imx.c index ac6d856ba228..77bc12039c3d 100644 --- a/drivers/soc/imx/soc-imx.c +++ b/drivers/soc/imx/soc-imx.c @@ -36,6 +36,10 @@ static int __init imx_soc_device_init(void) int ret; int i; + /* Return early if this is running on devices with different SoCs */ + if (!__mxc_cpu_type) + return 0; + if (of_machine_is_compatible("fsl,ls1021a")) return 0; diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c index f2151815db58..e714ed3b61bc 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra.c +++ b/drivers/soc/tegra/fuse/fuse-tegra.c @@ -320,7 +320,7 @@ static struct platform_driver tegra_fuse_driver = { }; builtin_platform_driver(tegra_fuse_driver); -bool __init tegra_fuse_read_spare(unsigned int spare) +u32 __init tegra_fuse_read_spare(unsigned int spare) { unsigned int offset = fuse->soc->info->spare + spare * 4; diff --git a/drivers/soc/tegra/fuse/fuse.h b/drivers/soc/tegra/fuse/fuse.h index de58feba0435..ecff0c08e959 100644 --- a/drivers/soc/tegra/fuse/fuse.h +++ b/drivers/soc/tegra/fuse/fuse.h @@ -65,7 +65,7 @@ struct tegra_fuse { void tegra_init_revision(void); void tegra_init_apbmisc(void); -bool __init tegra_fuse_read_spare(unsigned int spare); +u32 __init tegra_fuse_read_spare(unsigned int spare); u32 __init tegra_fuse_read_early(unsigned int offset); u8 tegra_get_major_rev(void); diff --git a/drivers/tee/amdtee/core.c b/drivers/tee/amdtee/core.c index da6b88e80dc0..297dc62bca29 100644 --- a/drivers/tee/amdtee/core.c +++ b/drivers/tee/amdtee/core.c @@ -203,9 +203,8 @@ static int copy_ta_binary(struct tee_context *ctx, void *ptr, void **ta, *ta_size = roundup(fw->size, PAGE_SIZE); *ta = (void *)__get_free_pages(GFP_KERNEL, get_order(*ta_size)); - if (IS_ERR(*ta)) { - pr_err("%s: get_free_pages failed 0x%llx\n", __func__, - (u64)*ta); + if (!*ta) { + pr_err("%s: get_free_pages failed\n", __func__); rc = -ENOMEM; goto rel_fw; } diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c index b25b54d4bac1..e693ec8234fb 100644 --- a/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c +++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c @@ -29,7 +29,7 @@ static const char * const fivr_strings[] = { }; static const struct mmio_reg tgl_fivr_mmio_regs[] = { - { 0, 0x5A18, 3, 0x7, 12}, /* vco_ref_code_lo */ + { 0, 0x5A18, 3, 0x7, 11}, /* vco_ref_code_lo */ { 0, 0x5A18, 8, 0xFF, 16}, /* vco_ref_code_hi */ { 0, 0x5A08, 8, 0xFF, 0}, /* spread_spectrum_pct */ { 0, 0x5A08, 1, 0x1, 8}, /* spread_spectrum_clk_enable */ diff --git a/drivers/tty/serial/8250/8250_bcm7271.c b/drivers/tty/serial/8250/8250_bcm7271.c index 7f656fac503f..5163d60756b7 100644 --- a/drivers/tty/serial/8250/8250_bcm7271.c +++ b/drivers/tty/serial/8250/8250_bcm7271.c @@ -237,6 +237,7 @@ struct brcmuart_priv { u32 rx_err; u32 rx_timeout; u32 rx_abort; + u32 saved_mctrl; }; static struct dentry *brcmuart_debugfs_root; @@ -1133,16 +1134,27 @@ static int brcmuart_remove(struct platform_device *pdev) static int __maybe_unused brcmuart_suspend(struct device *dev) { struct brcmuart_priv *priv = dev_get_drvdata(dev); + struct uart_8250_port *up = serial8250_get_port(priv->line); + struct uart_port *port = &up->port; serial8250_suspend_port(priv->line); clk_disable_unprepare(priv->baud_mux_clk); + /* + * This will prevent resume from enabling RTS before the + * baud rate has been resored. + */ + priv->saved_mctrl = port->mctrl; + port->mctrl = 0; + return 0; } static int __maybe_unused brcmuart_resume(struct device *dev) { struct brcmuart_priv *priv = dev_get_drvdata(dev); + struct uart_8250_port *up = serial8250_get_port(priv->line); + struct uart_port *port = &up->port; int ret; ret = clk_prepare_enable(priv->baud_mux_clk); @@ -1165,6 +1177,7 @@ static int __maybe_unused brcmuart_resume(struct device *dev) start_rx_dma(serial8250_get_port(priv->line)); } serial8250_resume_port(priv->line); + port->mctrl = priv->saved_mctrl; return 0; } diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index 5d43de143f33..60f8fffdfd77 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -1324,29 +1324,33 @@ pericom_do_set_divisor(struct uart_port *port, unsigned int baud, { int scr; int lcr; - int actual_baud; - int tolerance; - for (scr = 5 ; scr <= 15 ; scr++) { - actual_baud = 921600 * 16 / scr; - tolerance = actual_baud / 50; + for (scr = 16; scr > 4; scr--) { + unsigned int maxrate = port->uartclk / scr; + unsigned int divisor = max(maxrate / baud, 1U); + int delta = maxrate / divisor - baud; - if ((baud < actual_baud + tolerance) && - (baud > actual_baud - tolerance)) { + if (baud > maxrate + baud / 50) + continue; + if (delta > baud / 50) + divisor++; + + if (divisor > 0xffff) + continue; + + /* Update delta due to possible divisor change */ + delta = maxrate / divisor - baud; + if (abs(delta) < baud / 50) { lcr = serial_port_in(port, UART_LCR); serial_port_out(port, UART_LCR, lcr | 0x80); - - serial_port_out(port, UART_DLL, 1); - serial_port_out(port, UART_DLM, 0); + serial_port_out(port, UART_DLL, divisor & 0xff); + serial_port_out(port, UART_DLM, divisor >> 8 & 0xff); serial_port_out(port, 2, 16 - scr); serial_port_out(port, UART_LCR, lcr); return; - } else if (baud > actual_baud) { - break; } } - serial8250_do_set_divisor(port, baud, quot, quot_frac); } static int pci_pericom_setup(struct serial_private *priv, const struct pciserial_board *board, @@ -2291,7 +2295,7 @@ static struct pci_serial_quirk pci_serial_quirks[] = { .setup = pci_pericom_setup_four_at_eight, }, { - .vendor = PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S, + .vendor = PCI_VENDOR_ID_ACCESIO, .device = PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, @@ -2299,6 +2303,13 @@ static struct pci_serial_quirk pci_serial_quirks[] = { }, { .vendor = PCI_VENDOR_ID_ACCESIO, + .device = PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .setup = pci_pericom_setup_four_at_eight, + }, + { + .vendor = PCI_VENDOR_ID_ACCESIO, .device = PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 5775cbff8f6e..46e2079ad1aa 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2024,13 +2024,6 @@ void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl) struct uart_8250_port *up = up_to_u8250p(port); unsigned char mcr; - if (port->rs485.flags & SER_RS485_ENABLED) { - if (serial8250_in_MCR(up) & UART_MCR_RTS) - mctrl |= TIOCM_RTS; - else - mctrl &= ~TIOCM_RTS; - } - mcr = serial8250_TIOCM_to_MCR(mctrl); mcr = (mcr & up->mcr_mask) | up->mcr_force | up->mcr; diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 6ff94cfcd9db..fc543ac97c13 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1533,7 +1533,7 @@ config SERIAL_LITEUART tristate "LiteUART serial port support" depends on HAS_IOMEM depends on OF || COMPILE_TEST - depends on LITEX + depends on LITEX || COMPILE_TEST select SERIAL_CORE help This driver is for the FPGA-based LiteUART serial controller from LiteX diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index d361cd84ff8c..52518a606c06 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2947,6 +2947,7 @@ MODULE_DEVICE_TABLE(of, sbsa_uart_of_match); static const struct acpi_device_id __maybe_unused sbsa_uart_acpi_match[] = { { "ARMH0011", 0 }, + { "ARMHB000", 0 }, {}, }; MODULE_DEVICE_TABLE(acpi, sbsa_uart_acpi_match); diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index b1e7190ae483..ac5112def40d 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2625,6 +2625,7 @@ OF_EARLYCON_DECLARE(lpuart, "fsl,vf610-lpuart", lpuart_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1021a-lpuart", lpuart32_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1028a-lpuart", ls1028a_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,imx7ulp-lpuart", lpuart32_imx_early_console_setup); +OF_EARLYCON_DECLARE(lpuart32, "fsl,imx8qxp-lpuart", lpuart32_imx_early_console_setup); EARLYCON_DECLARE(lpuart, lpuart_early_console_setup); EARLYCON_DECLARE(lpuart32, lpuart32_early_console_setup); diff --git a/drivers/tty/serial/liteuart.c b/drivers/tty/serial/liteuart.c index dbc0559a9157..2941659e5274 100644 --- a/drivers/tty/serial/liteuart.c +++ b/drivers/tty/serial/liteuart.c @@ -270,8 +270,10 @@ static int liteuart_probe(struct platform_device *pdev) /* get membase */ port->membase = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); - if (IS_ERR(port->membase)) - return PTR_ERR(port->membase); + if (IS_ERR(port->membase)) { + ret = PTR_ERR(port->membase); + goto err_erase_id; + } /* values not from device tree */ port->dev = &pdev->dev; @@ -285,7 +287,18 @@ static int liteuart_probe(struct platform_device *pdev) port->line = dev_id; spin_lock_init(&port->lock); - return uart_add_one_port(&liteuart_driver, &uart->port); + platform_set_drvdata(pdev, port); + + ret = uart_add_one_port(&liteuart_driver, &uart->port); + if (ret) + goto err_erase_id; + + return 0; + +err_erase_id: + xa_erase(&liteuart_array, uart->id); + + return ret; } static int liteuart_remove(struct platform_device *pdev) @@ -293,6 +306,7 @@ static int liteuart_remove(struct platform_device *pdev) struct uart_port *port = platform_get_drvdata(pdev); struct liteuart_port *uart = to_liteuart_port(port); + uart_remove_one_port(&liteuart_driver, port); xa_erase(&liteuart_array, uart->id); return 0; diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c index fcef7a961430..489d19274f9a 100644 --- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -598,6 +598,9 @@ static void msm_start_rx_dma(struct msm_port *msm_port) u32 val; int ret; + if (IS_ENABLED(CONFIG_CONSOLE_POLL)) + return; + if (!dma->chan) return; diff --git a/drivers/tty/serial/serial-tegra.c b/drivers/tty/serial/serial-tegra.c index 45e2e4109acd..b6223fab0687 100644 --- a/drivers/tty/serial/serial-tegra.c +++ b/drivers/tty/serial/serial-tegra.c @@ -1506,7 +1506,7 @@ static struct tegra_uart_chip_data tegra20_uart_chip_data = { .fifo_mode_enable_status = false, .uart_max_port = 5, .max_dma_burst_bytes = 4, - .error_tolerance_low_range = 0, + .error_tolerance_low_range = -4, .error_tolerance_high_range = 4, }; @@ -1517,7 +1517,7 @@ static struct tegra_uart_chip_data tegra30_uart_chip_data = { .fifo_mode_enable_status = false, .uart_max_port = 5, .max_dma_burst_bytes = 4, - .error_tolerance_low_range = 0, + .error_tolerance_low_range = -4, .error_tolerance_high_range = 4, }; diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 1e738f265eea..61e3dd0222af 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -1075,6 +1075,11 @@ uart_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) goto out; if (!tty_io_error(tty)) { + if (uport->rs485.flags & SER_RS485_ENABLED) { + set &= ~TIOCM_RTS; + clear &= ~TIOCM_RTS; + } + uart_update_mctrl(uport, set, clear); ret = 0; } @@ -1549,6 +1554,7 @@ static void uart_tty_port_shutdown(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = uart_port_check(state); + char *buf; /* * At this point, we stop accepting input. To do this, we @@ -1570,8 +1576,18 @@ static void uart_tty_port_shutdown(struct tty_port *port) */ tty_port_set_suspended(port, 0); - uart_change_pm(state, UART_PM_STATE_OFF); + /* + * Free the transmit buffer. + */ + spin_lock_irq(&uport->lock); + buf = state->xmit.buf; + state->xmit.buf = NULL; + spin_unlock_irq(&uport->lock); + if (buf) + free_page((unsigned long)buf); + + uart_change_pm(state, UART_PM_STATE_OFF); } static void uart_wait_until_sent(struct tty_struct *tty, int timeout) diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index 1f3b4a142212..f9af7ebe003d 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -337,19 +337,6 @@ static void cdns3_ep_inc_deq(struct cdns3_endpoint *priv_ep) cdns3_ep_inc_trb(&priv_ep->dequeue, &priv_ep->ccs, priv_ep->num_trbs); } -static void cdns3_move_deq_to_next_trb(struct cdns3_request *priv_req) -{ - struct cdns3_endpoint *priv_ep = priv_req->priv_ep; - int current_trb = priv_req->start_trb; - - while (current_trb != priv_req->end_trb) { - cdns3_ep_inc_deq(priv_ep); - current_trb = priv_ep->dequeue; - } - - cdns3_ep_inc_deq(priv_ep); -} - /** * cdns3_allow_enable_l1 - enable/disable permits to transition to L1. * @priv_dev: Extended gadget object @@ -1517,10 +1504,11 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev, trb = priv_ep->trb_pool + priv_ep->dequeue; - /* Request was dequeued and TRB was changed to TRB_LINK. */ - if (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) { + /* The TRB was changed as link TRB, and the request was handled at ep_dequeue */ + while (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) { trace_cdns3_complete_trb(priv_ep, trb); - cdns3_move_deq_to_next_trb(priv_req); + cdns3_ep_inc_deq(priv_ep); + trb = priv_ep->trb_pool + priv_ep->dequeue; } if (!request->stream_id) { diff --git a/drivers/usb/cdns3/cdnsp-mem.c b/drivers/usb/cdns3/cdnsp-mem.c index ad9aee3f1e39..97866bfb2da9 100644 --- a/drivers/usb/cdns3/cdnsp-mem.c +++ b/drivers/usb/cdns3/cdnsp-mem.c @@ -987,6 +987,9 @@ int cdnsp_endpoint_init(struct cdnsp_device *pdev, /* Set up the endpoint ring. */ pep->ring = cdnsp_ring_alloc(pdev, 2, ring_type, max_packet, mem_flags); + if (!pep->ring) + return -ENOMEM; + pep->skip = false; /* Fill the endpoint context */ diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c index 84dadfa726aa..9643b905e2d8 100644 --- a/drivers/usb/cdns3/host.c +++ b/drivers/usb/cdns3/host.c @@ -10,6 +10,7 @@ */ #include <linux/platform_device.h> +#include <linux/slab.h> #include "core.h" #include "drd.h" #include "host-export.h" diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 16b1fd9dc60c..48bc8a4814ac 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -406,7 +406,7 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, * the USB-2 spec requires such endpoints to have wMaxPacketSize = 0 * (see the end of section 5.6.3), so don't warn about them. */ - maxp = usb_endpoint_maxp(&endpoint->desc); + maxp = le16_to_cpu(endpoint->desc.wMaxPacketSize); if (maxp == 0 && !(usb_endpoint_xfer_isoc(d) && asnum == 0)) { dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid wMaxPacketSize 0\n", cfgno, inum, asnum, d->bEndpointAddress); @@ -422,9 +422,9 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, maxpacket_maxes = full_speed_maxpacket_maxes; break; case USB_SPEED_HIGH: - /* Bits 12..11 are allowed only for HS periodic endpoints */ + /* Multiple-transactions bits are allowed only for HS periodic endpoints */ if (usb_endpoint_xfer_int(d) || usb_endpoint_xfer_isoc(d)) { - i = maxp & (BIT(12) | BIT(11)); + i = maxp & USB_EP_MAXP_MULT_MASK; maxp &= ~i; } fallthrough; diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index 9abbd01028c5..3cb01cdd02c2 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -649,7 +649,6 @@ static int dwc3_qcom_of_register_core(struct platform_device *pdev) struct dwc3_qcom *qcom = platform_get_drvdata(pdev); struct device_node *np = pdev->dev.of_node, *dwc3_np; struct device *dev = &pdev->dev; - struct property *prop; int ret; dwc3_np = of_get_compatible_child(np, "snps,dwc3"); @@ -658,20 +657,6 @@ static int dwc3_qcom_of_register_core(struct platform_device *pdev) return -ENODEV; } - prop = devm_kzalloc(dev, sizeof(*prop), GFP_KERNEL); - if (!prop) { - ret = -ENOMEM; - dev_err(dev, "unable to allocate memory for property\n"); - goto node_put; - } - - prop->name = "tx-fifo-resize"; - ret = of_add_property(dwc3_np, prop); - if (ret) { - dev_err(dev, "unable to add property\n"); - goto node_put; - } - ret = of_platform_populate(np, NULL, NULL, dev); if (ret) { dev_err(dev, "failed to register dwc3 core - %d\n", ret); diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 504c1cbc255d..284eea9f6e4d 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1679,6 +1679,18 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) struct usb_function *f = NULL; u8 endp; + if (w_length > USB_COMP_EP0_BUFSIZ) { + if (ctrl->bRequestType == USB_DIR_OUT) { + goto done; + } else { + /* Cast away the const, we are going to overwrite on purpose. */ + __le16 *temp = (__le16 *)&ctrl->wLength; + + *temp = cpu_to_le16(USB_COMP_EP0_BUFSIZ); + w_length = USB_COMP_EP0_BUFSIZ; + } + } + /* partial re-init of the response message; the function or the * gadget might need to intercept e.g. a control-OUT completion * when we delegate to it. @@ -2209,7 +2221,7 @@ int composite_dev_prepare(struct usb_composite_driver *composite, if (!cdev->req) return -ENOMEM; - cdev->req->buf = kmalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL); + cdev->req->buf = kzalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL); if (!cdev->req->buf) goto fail; diff --git a/drivers/usb/gadget/legacy/dbgp.c b/drivers/usb/gadget/legacy/dbgp.c index e1d566c9918a..355bc7dab9d5 100644 --- a/drivers/usb/gadget/legacy/dbgp.c +++ b/drivers/usb/gadget/legacy/dbgp.c @@ -137,7 +137,7 @@ static int dbgp_enable_ep_req(struct usb_ep *ep) goto fail_1; } - req->buf = kmalloc(DBGP_REQ_LEN, GFP_KERNEL); + req->buf = kzalloc(DBGP_REQ_LEN, GFP_KERNEL); if (!req->buf) { err = -ENOMEM; stp = 2; @@ -345,6 +345,19 @@ static int dbgp_setup(struct usb_gadget *gadget, void *data = NULL; u16 len = 0; + if (length > DBGP_REQ_LEN) { + if (ctrl->bRequestType == USB_DIR_OUT) { + return err; + } else { + /* Cast away the const, we are going to overwrite on purpose. */ + __le16 *temp = (__le16 *)&ctrl->wLength; + + *temp = cpu_to_le16(DBGP_REQ_LEN); + length = DBGP_REQ_LEN; + } + } + + if (request == USB_REQ_GET_DESCRIPTOR) { switch (value>>8) { case USB_DT_DEVICE: diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 78be94750232..63150e3889ef 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -110,6 +110,8 @@ enum ep0_state { /* enough for the whole queue: most events invalidate others */ #define N_EVENT 5 +#define RBUF_SIZE 256 + struct dev_data { spinlock_t lock; refcount_t count; @@ -144,7 +146,7 @@ struct dev_data { struct dentry *dentry; /* except this scratch i/o buffer for ep0 */ - u8 rbuf [256]; + u8 rbuf[RBUF_SIZE]; }; static inline void get_dev (struct dev_data *data) @@ -1331,6 +1333,18 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) u16 w_value = le16_to_cpu(ctrl->wValue); u16 w_length = le16_to_cpu(ctrl->wLength); + if (w_length > RBUF_SIZE) { + if (ctrl->bRequestType == USB_DIR_OUT) { + return value; + } else { + /* Cast away the const, we are going to overwrite on purpose. */ + __le16 *temp = (__le16 *)&ctrl->wLength; + + *temp = cpu_to_le16(RBUF_SIZE); + w_length = RBUF_SIZE; + } + } + spin_lock (&dev->lock); dev->setup_abort = 0; if (dev->state == STATE_DEV_UNCONNECTED) { diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index af946c42b6f0..df3522dab31b 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -717,6 +717,7 @@ static int xhci_enter_test_mode(struct xhci_hcd *xhci, continue; retval = xhci_disable_slot(xhci, i); + xhci_free_virt_device(xhci, i); if (retval) xhci_err(xhci, "Failed to disable slot %d, %d. Enter test mode anyway\n", i, retval); diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 311597bba80e..d0b6806275e0 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -366,7 +366,9 @@ static void xhci_handle_stopped_cmd_ring(struct xhci_hcd *xhci, /* Must be called with xhci->lock held, releases and aquires lock back */ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags) { - u32 temp_32; + struct xhci_segment *new_seg = xhci->cmd_ring->deq_seg; + union xhci_trb *new_deq = xhci->cmd_ring->dequeue; + u64 crcr; int ret; xhci_dbg(xhci, "Abort command ring\n"); @@ -375,13 +377,18 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci, unsigned long flags) /* * The control bits like command stop, abort are located in lower - * dword of the command ring control register. Limit the write - * to the lower dword to avoid corrupting the command ring pointer - * in case if the command ring is stopped by the time upper dword - * is written. + * dword of the command ring control register. + * Some controllers require all 64 bits to be written to abort the ring. + * Make sure the upper dword is valid, pointing to the next command, + * avoiding corrupting the command ring pointer in case the command ring + * is stopped by the time the upper dword is written. */ - temp_32 = readl(&xhci->op_regs->cmd_ring); - writel(temp_32 | CMD_RING_ABORT, &xhci->op_regs->cmd_ring); + next_trb(xhci, NULL, &new_seg, &new_deq); + if (trb_is_link(new_deq)) + next_trb(xhci, NULL, &new_seg, &new_deq); + + crcr = xhci_trb_virt_to_dma(new_seg, new_deq); + xhci_write_64(xhci, crcr | CMD_RING_ABORT, &xhci->op_regs->cmd_ring); /* Section 4.6.1.2 of xHCI 1.0 spec says software should also time the * completion of the Command Abort operation. If CRR is not negated in 5 @@ -1518,7 +1525,6 @@ static void xhci_handle_cmd_disable_slot(struct xhci_hcd *xhci, int slot_id) if (xhci->quirks & XHCI_EP_LIMIT_QUIRK) /* Delete default control endpoint resources */ xhci_free_device_endpoint_resources(xhci, virt_dev, true); - xhci_free_virt_device(xhci, slot_id); } static void xhci_handle_cmd_config_ep(struct xhci_hcd *xhci, int slot_id, diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 902f410874e8..f5b1bcc875de 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3934,7 +3934,6 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) struct xhci_slot_ctx *slot_ctx; int i, ret; -#ifndef CONFIG_USB_DEFAULT_PERSIST /* * We called pm_runtime_get_noresume when the device was attached. * Decrement the counter here to allow controller to runtime suspend @@ -3942,7 +3941,6 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) */ if (xhci->quirks & XHCI_RESET_ON_RESUME) pm_runtime_put_noidle(hcd->self.controller); -#endif ret = xhci_check_args(hcd, udev, NULL, 0, true, __func__); /* If the host is halted due to driver unload, we still need to free the @@ -3961,9 +3959,8 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) del_timer_sync(&virt_dev->eps[i].stop_cmd_timer); } virt_dev->udev = NULL; - ret = xhci_disable_slot(xhci, udev->slot_id); - if (ret) - xhci_free_virt_device(xhci, udev->slot_id); + xhci_disable_slot(xhci, udev->slot_id); + xhci_free_virt_device(xhci, udev->slot_id); } int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) @@ -3973,7 +3970,7 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) u32 state; int ret = 0; - command = xhci_alloc_command(xhci, false, GFP_KERNEL); + command = xhci_alloc_command(xhci, true, GFP_KERNEL); if (!command) return -ENOMEM; @@ -3998,6 +3995,15 @@ int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) } xhci_ring_cmd_db(xhci); spin_unlock_irqrestore(&xhci->lock, flags); + + wait_for_completion(command->completion); + + if (command->status != COMP_SUCCESS) + xhci_warn(xhci, "Unsuccessful disable slot %u command, status %d\n", + slot_id, command->status); + + xhci_free_command(xhci, command); + return ret; } @@ -4094,23 +4100,20 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev) xhci_debugfs_create_slot(xhci, slot_id); -#ifndef CONFIG_USB_DEFAULT_PERSIST /* * If resetting upon resume, we can't put the controller into runtime * suspend if there is a device attached. */ if (xhci->quirks & XHCI_RESET_ON_RESUME) pm_runtime_get_noresume(hcd->self.controller); -#endif /* Is this a LS or FS device under a HS hub? */ /* Hub or peripherial? */ return 1; disable_slot: - ret = xhci_disable_slot(xhci, udev->slot_id); - if (ret) - xhci_free_virt_device(xhci, udev->slot_id); + xhci_disable_slot(xhci, udev->slot_id); + xhci_free_virt_device(xhci, udev->slot_id); return 0; } @@ -4240,6 +4243,7 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev, mutex_unlock(&xhci->mutex); ret = xhci_disable_slot(xhci, udev->slot_id); + xhci_free_virt_device(xhci, udev->slot_id); if (!ret) xhci_alloc_dev(hcd, udev); kfree(command->completion); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 7f2f3ff1b391..6010b9901126 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4110,11 +4110,7 @@ static void run_state_machine(struct tcpm_port *port) tcpm_try_src(port) ? SRC_TRY : SNK_ATTACHED, 0); - else - /* Wait for VBUS, but not forever */ - tcpm_set_state(port, PORT_RESET, PD_T_PS_SOURCE_ON); break; - case SRC_TRY: port->try_src_count++; tcpm_set_cc(port, tcpm_rp_cc(port)); diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 7332a74a4b00..09bbe53c3ac4 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -404,7 +404,8 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m goto msg_err; while (mdev->id_table[i].device) { - supported_classes |= BIT(mdev->id_table[i].device); + if (mdev->id_table[i].device <= 63) + supported_classes |= BIT_ULL(mdev->id_table[i].device); i++; } diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index c9204c62f339..eddcb64a910a 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -655,7 +655,8 @@ static void vduse_vdpa_get_config(struct vdpa_device *vdpa, unsigned int offset, { struct vduse_dev *dev = vdpa_to_vduse(vdpa); - if (len > dev->config_size - offset) + if (offset > dev->config_size || + len > dev->config_size - offset) return; memcpy(buf, dev->config + offset, len); @@ -975,7 +976,8 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd, break; ret = -EINVAL; - if (config.length == 0 || + if (config.offset > dev->config_size || + config.length == 0 || config.length > dev->config_size - config.offset) break; diff --git a/drivers/vfio/pci/vfio_pci_igd.c b/drivers/vfio/pci/vfio_pci_igd.c index 56cd551e0e04..362f91ec8845 100644 --- a/drivers/vfio/pci/vfio_pci_igd.c +++ b/drivers/vfio/pci/vfio_pci_igd.c @@ -98,7 +98,8 @@ static ssize_t vfio_pci_igd_rw(struct vfio_pci_core_device *vdev, version = cpu_to_le16(0x0201); if (igd_opregion_shift_copy(buf, &off, - &version + (pos - OPREGION_VERSION), + (u8 *)&version + + (pos - OPREGION_VERSION), &pos, &remaining, bytes)) return -EFAULT; } @@ -121,7 +122,7 @@ static ssize_t vfio_pci_igd_rw(struct vfio_pci_core_device *vdev, OPREGION_SIZE : 0); if (igd_opregion_shift_copy(buf, &off, - &rvda + (pos - OPREGION_RVDA), + (u8 *)&rvda + (pos - OPREGION_RVDA), &pos, &remaining, bytes)) return -EFAULT; } diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 82fb75464f92..735d1d344af9 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -232,7 +232,7 @@ static inline bool vfio_iommu_driver_allowed(struct vfio_container *container, } #endif /* CONFIG_VFIO_NOIOMMU */ -/** +/* * IOMMU driver registration */ int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops) @@ -285,7 +285,7 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb, unsigned long action, void *data); static void vfio_group_get(struct vfio_group *group); -/** +/* * Container objects - containers are created when /dev/vfio/vfio is * opened, but their lifecycle extends until the last user is done, so * it's freed via kref. Must support container/group/device being @@ -309,7 +309,7 @@ static void vfio_container_put(struct vfio_container *container) kref_put(&container->kref, vfio_container_release); } -/** +/* * Group objects - create, release, get, put, search */ static struct vfio_group * @@ -488,7 +488,7 @@ static struct vfio_group *vfio_group_get_from_dev(struct device *dev) return group; } -/** +/* * Device objects - create, release, get, put, search */ /* Device reference always implies a group reference */ @@ -595,7 +595,7 @@ static int vfio_dev_viable(struct device *dev, void *data) return ret; } -/** +/* * Async device support */ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev) @@ -689,7 +689,7 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb, return NOTIFY_OK; } -/** +/* * VFIO driver API */ void vfio_init_group_dev(struct vfio_device *device, struct device *dev, @@ -831,7 +831,7 @@ int vfio_register_emulated_iommu_dev(struct vfio_device *device) } EXPORT_SYMBOL_GPL(vfio_register_emulated_iommu_dev); -/** +/* * Get a reference to the vfio_device for a device. Even if the * caller thinks they own the device, they could be racing with a * release call path, so we can't trust drvdata for the shortcut. @@ -965,7 +965,7 @@ void vfio_unregister_group_dev(struct vfio_device *device) } EXPORT_SYMBOL_GPL(vfio_unregister_group_dev); -/** +/* * VFIO base fd, /dev/vfio/vfio */ static long vfio_ioctl_check_extension(struct vfio_container *container, @@ -1183,7 +1183,7 @@ static const struct file_operations vfio_fops = { .compat_ioctl = compat_ptr_ioctl, }; -/** +/* * VFIO Group fd, /dev/vfio/$GROUP */ static void __vfio_group_unset_container(struct vfio_group *group) @@ -1536,7 +1536,7 @@ static const struct file_operations vfio_group_fops = { .release = vfio_group_fops_release, }; -/** +/* * VFIO Device fd */ static int vfio_device_fops_release(struct inode *inode, struct file *filep) @@ -1611,7 +1611,7 @@ static const struct file_operations vfio_device_fops = { .mmap = vfio_device_fops_mmap, }; -/** +/* * External user API, exported by symbols to be linked dynamically. * * The protocol includes: @@ -1659,7 +1659,7 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep) } EXPORT_SYMBOL_GPL(vfio_group_get_external_user); -/** +/* * External user API, exported by symbols to be linked dynamically. * The external user passes in a device pointer * to verify that: @@ -1725,7 +1725,7 @@ long vfio_external_check_extension(struct vfio_group *group, unsigned long arg) } EXPORT_SYMBOL_GPL(vfio_external_check_extension); -/** +/* * Sub-module support */ /* @@ -2272,7 +2272,7 @@ struct iommu_domain *vfio_group_iommu_domain(struct vfio_group *group) } EXPORT_SYMBOL_GPL(vfio_group_iommu_domain); -/** +/* * Module/class support */ static char *vfio_devnode(struct device *dev, umode_t *mode) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 29cced1cd277..e3c4f059b21a 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -197,7 +197,7 @@ static int vhost_vdpa_config_validate(struct vhost_vdpa *v, struct vdpa_device *vdpa = v->vdpa; long size = vdpa->config->get_config_size(vdpa); - if (c->len == 0) + if (c->len == 0 || c->off > size) return -EINVAL; if (c->len > size - c->off) diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index ef9c57ce0906..9a49ea6b5112 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -366,11 +366,17 @@ static void vgacon_init(struct vc_data *c, int init) struct uni_pagedir *p; /* - * We cannot be loaded as a module, therefore init is always 1, - * but vgacon_init can be called more than once, and init will - * not be 1. + * We cannot be loaded as a module, therefore init will be 1 + * if we are the default console, however if we are a fallback + * console, for example if fbcon has failed registration, then + * init will be 0, so we need to make sure our boot parameters + * have been copied to the console structure for vgacon_resize + * ultimately called by vc_resize. Any subsequent calls to + * vgacon_init init will have init set to 0 too. */ c->vc_can_do_color = vga_can_do_color; + c->vc_scan_lines = vga_scan_lines; + c->vc_font.height = c->vc_cell_height = vga_video_font_height; /* set dimensions manually if init != 0 since vc_resize() will fail */ if (init) { @@ -379,8 +385,6 @@ static void vgacon_init(struct vc_data *c, int init) } else vc_resize(c, vga_video_num_columns, vga_video_num_lines); - c->vc_scan_lines = vga_scan_lines; - c->vc_font.height = c->vc_cell_height = vga_video_font_height; c->vc_complement_mask = 0x7700; if (vga_512_chars) c->vc_hi_font_mask = 0x0800; diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 6d2614e34470..028b05d44546 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -268,7 +268,7 @@ size_t virtio_max_dma_size(struct virtio_device *vdev) size_t max_segment_size = SIZE_MAX; if (vring_use_dma_api(vdev)) - max_segment_size = dma_max_mapping_size(&vdev->dev); + max_segment_size = dma_max_mapping_size(vdev->dev.parent); return max_segment_size; } diff --git a/fs/afs/file.c b/fs/afs/file.c index cb6ad61eec3b..afe4b803f84b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -514,8 +514,9 @@ static void afs_add_open_mmap(struct afs_vnode *vnode) if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) { down_write(&vnode->volume->cell->fs_open_mmaps_lock); - list_add_tail(&vnode->cb_mmap_link, - &vnode->volume->cell->fs_open_mmaps); + if (list_empty(&vnode->cb_mmap_link)) + list_add_tail(&vnode->cb_mmap_link, + &vnode->volume->cell->fs_open_mmaps); up_write(&vnode->volume->cell->fs_open_mmaps_lock); } diff --git a/fs/afs/super.c b/fs/afs/super.c index d110def8aa8e..34c68724c98b 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -667,6 +667,7 @@ static void afs_i_init_once(void *_vnode) INIT_LIST_HEAD(&vnode->pending_locks); INIT_LIST_HEAD(&vnode->granted_locks); INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work); + INIT_LIST_HEAD(&vnode->cb_mmap_link); seqlock_init(&vnode->cb_lock); } @@ -181,8 +181,9 @@ struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; - bool done; bool cancelled; + bool work_scheduled; + bool work_need_resched; struct wait_queue_entry wait; struct work_struct work; }; @@ -1619,6 +1620,51 @@ static void aio_poll_put_work(struct work_struct *work) iocb_put(iocb); } +/* + * Safely lock the waitqueue which the request is on, synchronizing with the + * case where the ->poll() provider decides to free its waitqueue early. + * + * Returns true on success, meaning that req->head->lock was locked, req->wait + * is on req->head, and an RCU read lock was taken. Returns false if the + * request was already removed from its waitqueue (which might no longer exist). + */ +static bool poll_iocb_lock_wq(struct poll_iocb *req) +{ + wait_queue_head_t *head; + + /* + * While we hold the waitqueue lock and the waitqueue is nonempty, + * wake_up_pollfree() will wait for us. However, taking the waitqueue + * lock in the first place can race with the waitqueue being freed. + * + * We solve this as eventpoll does: by taking advantage of the fact that + * all users of wake_up_pollfree() will RCU-delay the actual free. If + * we enter rcu_read_lock() and see that the pointer to the queue is + * non-NULL, we can then lock it without the memory being freed out from + * under us, then check whether the request is still on the queue. + * + * Keep holding rcu_read_lock() as long as we hold the queue lock, in + * case the caller deletes the entry from the queue, leaving it empty. + * In that case, only RCU prevents the queue memory from being freed. + */ + rcu_read_lock(); + head = smp_load_acquire(&req->head); + if (head) { + spin_lock(&head->lock); + if (!list_empty(&req->wait.entry)) + return true; + spin_unlock(&head->lock); + } + rcu_read_unlock(); + return false; +} + +static void poll_iocb_unlock_wq(struct poll_iocb *req) +{ + spin_unlock(&req->head->lock); + rcu_read_unlock(); +} + static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1638,14 +1684,27 @@ static void aio_poll_complete_work(struct work_struct *work) * avoid further branches in the fast path. */ spin_lock_irq(&ctx->ctx_lock); - if (!mask && !READ_ONCE(req->cancelled)) { - add_wait_queue(req->head, &req->wait); - spin_unlock_irq(&ctx->ctx_lock); - return; - } + if (poll_iocb_lock_wq(req)) { + if (!mask && !READ_ONCE(req->cancelled)) { + /* + * The request isn't actually ready to be completed yet. + * Reschedule completion if another wakeup came in. + */ + if (req->work_need_resched) { + schedule_work(&req->work); + req->work_need_resched = false; + } else { + req->work_scheduled = false; + } + poll_iocb_unlock_wq(req); + spin_unlock_irq(&ctx->ctx_lock); + return; + } + list_del_init(&req->wait.entry); + poll_iocb_unlock_wq(req); + } /* else, POLLFREE has freed the waitqueue, so we must complete */ list_del_init(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); - req->done = true; spin_unlock_irq(&ctx->ctx_lock); iocb_put(iocb); @@ -1657,13 +1716,14 @@ static int aio_poll_cancel(struct kiocb *iocb) struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw); struct poll_iocb *req = &aiocb->poll; - spin_lock(&req->head->lock); - WRITE_ONCE(req->cancelled, true); - if (!list_empty(&req->wait.entry)) { - list_del_init(&req->wait.entry); - schedule_work(&aiocb->poll.work); - } - spin_unlock(&req->head->lock); + if (poll_iocb_lock_wq(req)) { + WRITE_ONCE(req->cancelled, true); + if (!req->work_scheduled) { + schedule_work(&aiocb->poll.work); + req->work_scheduled = true; + } + poll_iocb_unlock_wq(req); + } /* else, the request was force-cancelled by POLLFREE already */ return 0; } @@ -1680,21 +1740,27 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (mask && !(mask & req->events)) return 0; - list_del_init(&req->wait.entry); - - if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { + /* + * Complete the request inline if possible. This requires that three + * conditions be met: + * 1. An event mask must have been passed. If a plain wakeup was done + * instead, then mask == 0 and we have to call vfs_poll() to get + * the events, so inline completion isn't possible. + * 2. The completion work must not have already been scheduled. + * 3. ctx_lock must not be busy. We have to use trylock because we + * already hold the waitqueue lock, so this inverts the normal + * locking order. Use irqsave/irqrestore because not all + * filesystems (e.g. fuse) call this function with IRQs disabled, + * yet IRQs have to be disabled before ctx_lock is obtained. + */ + if (mask && !req->work_scheduled && + spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { struct kioctx *ctx = iocb->ki_ctx; - /* - * Try to complete the iocb inline if we can. Use - * irqsave/irqrestore because not all filesystems (e.g. fuse) - * call this function with IRQs disabled and because IRQs - * have to be disabled before ctx_lock is obtained. - */ + list_del_init(&req->wait.entry); list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); - req->done = true; - if (iocb->ki_eventfd && eventfd_signal_allowed()) { + if (iocb->ki_eventfd && !eventfd_signal_allowed()) { iocb = NULL; INIT_WORK(&req->work, aio_poll_put_work); schedule_work(&req->work); @@ -1703,7 +1769,43 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (iocb) iocb_put(iocb); } else { - schedule_work(&req->work); + /* + * Schedule the completion work if needed. If it was already + * scheduled, record that another wakeup came in. + * + * Don't remove the request from the waitqueue here, as it might + * not actually be complete yet (we won't know until vfs_poll() + * is called), and we must not miss any wakeups. POLLFREE is an + * exception to this; see below. + */ + if (req->work_scheduled) { + req->work_need_resched = true; + } else { + schedule_work(&req->work); + req->work_scheduled = true; + } + + /* + * If the waitqueue is being freed early but we can't complete + * the request inline, we have to tear down the request as best + * we can. That means immediately removing the request from its + * waitqueue and preventing all further accesses to the + * waitqueue via the request. We also need to schedule the + * completion work (done above). Also mark the request as + * cancelled, to potentially skip an unneeded call to ->poll(). + */ + if (mask & POLLFREE) { + WRITE_ONCE(req->cancelled, true); + list_del_init(&req->wait.entry); + + /* + * Careful: this *must* be the last step, since as soon + * as req->head is NULL'ed out, the request can be + * completed and freed, since aio_poll_complete_work() + * will no longer need to take the waitqueue lock. + */ + smp_store_release(&req->head, NULL); + } } return 1; } @@ -1711,6 +1813,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct aio_poll_table { struct poll_table_struct pt; struct aio_kiocb *iocb; + bool queued; int error; }; @@ -1721,11 +1824,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt); /* multiple wait queues per file are not supported */ - if (unlikely(pt->iocb->poll.head)) { + if (unlikely(pt->queued)) { pt->error = -EINVAL; return; } + pt->queued = true; pt->error = 0; pt->iocb->poll.head = head; add_wait_queue(head, &pt->iocb->poll.wait); @@ -1750,12 +1854,14 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; - req->done = false; req->cancelled = false; + req->work_scheduled = false; + req->work_need_resched = false; apt.pt._qproc = aio_poll_queue_proc; apt.pt._key = req->events; apt.iocb = aiocb; + apt.queued = false; apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ /* initialized the list so that we can do list_empty checks */ @@ -1764,23 +1870,35 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) mask = vfs_poll(req->file, &apt.pt) & req->events; spin_lock_irq(&ctx->ctx_lock); - if (likely(req->head)) { - spin_lock(&req->head->lock); - if (unlikely(list_empty(&req->wait.entry))) { - if (apt.error) + if (likely(apt.queued)) { + bool on_queue = poll_iocb_lock_wq(req); + + if (!on_queue || req->work_scheduled) { + /* + * aio_poll_wake() already either scheduled the async + * completion work, or completed the request inline. + */ + if (apt.error) /* unsupported case: multiple queues */ cancel = true; apt.error = 0; mask = 0; } if (mask || apt.error) { + /* Steal to complete synchronously. */ list_del_init(&req->wait.entry); } else if (cancel) { + /* Cancel if possible (may be too late though). */ WRITE_ONCE(req->cancelled, true); - } else if (!req->done) { /* actually waiting for an event */ + } else if (on_queue) { + /* + * Actually waiting for an event, so add the request to + * active_reqs so that it can be cancelled if needed. + */ list_add_tail(&aiocb->ki_list, &ctx->active_reqs); aiocb->ki_cancel = aio_poll_cancel; } - spin_unlock(&req->head->lock); + if (on_queue) + poll_iocb_unlock_wq(req); } if (mask) { /* no async, we'd stolen it */ aiocb->ki_res.res = mangle_poll(mask); diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 2059d1504149..40c4d6ba3fb9 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -143,10 +143,13 @@ int btrfs_check_data_free_space(struct btrfs_inode *inode, /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */ ret = btrfs_qgroup_reserve_data(inode, reserved, start, len); - if (ret < 0) + if (ret < 0) { btrfs_free_reserved_data_space_noquota(fs_info, len); - else + extent_changeset_free(*reserved); + *reserved = NULL; + } else { ret = 0; + } return ret; } @@ -452,8 +455,11 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, if (ret < 0) return ret; ret = btrfs_delalloc_reserve_metadata(inode, len); - if (ret < 0) + if (ret < 0) { btrfs_free_reserved_data_space(inode, *reserved, start, len); + extent_changeset_free(*reserved); + *reserved = NULL; + } return ret; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 3fd736a02c1e..fc4895e6a62c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6051,6 +6051,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) int dev_ret = 0; int ret = 0; + if (range->start == U64_MAX) + return -EINVAL; + /* * Check range overflow if range->len is set. * The default range->len is U64_MAX. diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4e03a6d3aa32..3258b6f01e85 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4314,6 +4314,20 @@ static void set_btree_ioerr(struct page *page, struct extent_buffer *eb) return; /* + * A read may stumble upon this buffer later, make sure that it gets an + * error and knows there was an error. + */ + clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + + /* + * We need to set the mapping with the io error as well because a write + * error will flip the file system readonly, and then syncfs() will + * return a 0 because we are readonly if we don't modify the err seq for + * the superblock. + */ + mapping_set_error(page->mapping, -EIO); + + /* * If we error out, we should add back the dirty_metadata_bytes * to make it consistent. */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 92138ac2a4e2..2b84846ed934 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3187,10 +3187,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) return -EPERM; vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) { - ret = PTR_ERR(vol_args); - goto out; - } + if (IS_ERR(vol_args)) + return PTR_ERR(vol_args); if (vol_args->flags & ~BTRFS_DEVICE_REMOVE_ARGS_MASK) { ret = -EOPNOTSUPP; diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 12ceb14a1141..d20166336557 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -334,7 +334,8 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, key.offset = ref_id; again: ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); - BUG_ON(ret < 0); + if (ret < 0) + goto out; if (ret == 0) { leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 8ab33caf016f..3e6f14e13918 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2908,6 +2908,8 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, path->nodes[*level]->len); if (ret) return ret; + btrfs_redirty_list_add(trans->transaction, + next); } else { if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) clear_extent_buffer_dirty(next); @@ -2988,6 +2990,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, next->start, next->len); if (ret) goto out; + btrfs_redirty_list_add(trans->transaction, next); } else { if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) clear_extent_buffer_dirty(next); @@ -3438,8 +3441,6 @@ static void free_log_tree(struct btrfs_trans_handle *trans, EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); extent_io_tree_release(&log->log_csum_range); - if (trans && log->node) - btrfs_redirty_list_add(trans->transaction, log->node); btrfs_put_root(log); } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 67d932d70798..678a29469511 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1860,6 +1860,7 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) block_group->alloc_offset = block_group->zone_capacity; block_group->free_space_ctl->free_space = 0; btrfs_clear_treelog_bg(block_group); + btrfs_clear_data_reloc_bg(block_group); spin_unlock(&block_group->lock); ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, @@ -1942,6 +1943,7 @@ void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 len ASSERT(block_group->alloc_offset == block_group->zone_capacity); ASSERT(block_group->free_space_ctl->free_space == 0); btrfs_clear_treelog_bg(block_group); + btrfs_clear_data_reloc_bg(block_group); spin_unlock(&block_group->lock); map = block_group->physical_map; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index b9460b6fb76f..c447fa2e2d1f 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4350,7 +4350,7 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb); int bits = (fmode << 1) | 1; - bool is_opened = false; + bool already_opened = false; int i; if (count == 1) @@ -4358,19 +4358,19 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count) spin_lock(&ci->i_ceph_lock); for (i = 0; i < CEPH_FILE_MODE_BITS; i++) { - if (bits & (1 << i)) - ci->i_nr_by_mode[i] += count; - /* - * If any of the mode ref is larger than 1, + * If any of the mode ref is larger than 0, * that means it has been already opened by * others. Just skip checking the PIN ref. */ - if (i && ci->i_nr_by_mode[i] > 1) - is_opened = true; + if (i && ci->i_nr_by_mode[i]) + already_opened = true; + + if (bits & (1 << i)) + ci->i_nr_by_mode[i] += count; } - if (!is_opened) + if (!already_opened) percpu_counter_inc(&mdsc->metric.opened_inodes); spin_unlock(&ci->i_ceph_lock); } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 02a0a0fd9ccd..c138e8126286 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -605,13 +605,25 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, in.cap.realm = cpu_to_le64(ci->i_snap_realm->ino); in.cap.flags = CEPH_CAP_FLAG_AUTH; in.ctime = in.mtime = in.atime = iinfo.btime; - in.mode = cpu_to_le32((u32)mode); in.truncate_seq = cpu_to_le32(1); in.truncate_size = cpu_to_le64(-1ULL); in.xattr_version = cpu_to_le64(1); in.uid = cpu_to_le32(from_kuid(&init_user_ns, current_fsuid())); - in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_mode & S_ISGID ? - dir->i_gid : current_fsgid())); + if (dir->i_mode & S_ISGID) { + in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_gid)); + + /* Directories always inherit the setgid bit. */ + if (S_ISDIR(mode)) + mode |= S_ISGID; + else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && + !in_group_p(dir->i_gid) && + !capable_wrt_inode_uidgid(&init_user_ns, dir, CAP_FSETID)) + mode &= ~S_ISGID; + } else { + in.gid = cpu_to_le32(from_kgid(&init_user_ns, current_fsgid())); + } + in.mode = cpu_to_le32((u32)mode); + in.nlink = cpu_to_le32(1); in.max_size = cpu_to_le64(lo->stripe_unit); @@ -847,7 +859,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, ssize_t ret; u64 off = iocb->ki_pos; u64 len = iov_iter_count(to); - u64 i_size; + u64 i_size = i_size_read(inode); dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len, (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 250aad330a10..c30eefc0ac19 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3683,7 +3683,7 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, struct ceph_pagelist *pagelist = recon_state->pagelist; struct dentry *dentry; char *path; - int pathlen, err; + int pathlen = 0, err; u64 pathbase; u64 snap_follows; @@ -3703,7 +3703,6 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, } } else { path = NULL; - pathlen = 0; pathbase = 0; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 6b705026da1a..18448dbd762a 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1562,6 +1562,10 @@ smbd_connected: /* fscache server cookies are based on primary channel only */ if (!CIFS_SERVER_IS_CHAN(tcp_ses)) cifs_fscache_get_client_cookie(tcp_ses); +#ifdef CONFIG_CIFS_FSCACHE + else + tcp_ses->fscache = tcp_ses->primary_server->fscache; +#endif /* CONFIG_CIFS_FSCACHE */ /* queue echo request delayed work */ queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval); @@ -3046,12 +3050,6 @@ static int mount_get_conns(struct mount_ctx *mnt_ctx) cifs_dbg(VFS, "read only mount of RW share\n"); /* no need to log a RW mount of a typical RW share */ } - /* - * The cookie is initialized from volume info returned above. - * Inside cifs_fscache_get_super_cookie it checks - * that we do not get super cookie twice. - */ - cifs_fscache_get_super_cookie(tcon); } /* @@ -3426,6 +3424,7 @@ static int connect_dfs_root(struct mount_ctx *mnt_ctx, struct dfs_cache_tgt_list */ mount_put_conns(mnt_ctx); mount_get_dfs_conns(mnt_ctx); + set_root_ses(mnt_ctx); full_path = build_unc_path_to_root(ctx, cifs_sb, true); if (IS_ERR(full_path)) diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 7e409a38a2d7..003c5f1f4dfb 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -16,14 +16,7 @@ * Key layout of CIFS server cache index object */ struct cifs_server_key { - struct { - uint16_t family; /* address family */ - __be16 port; /* IP port */ - } hdr; - union { - struct in_addr ipv4_addr; - struct in6_addr ipv6_addr; - }; + __u64 conn_id; } __packed; /* @@ -31,42 +24,23 @@ struct cifs_server_key { */ void cifs_fscache_get_client_cookie(struct TCP_Server_Info *server) { - const struct sockaddr *sa = (struct sockaddr *) &server->dstaddr; - const struct sockaddr_in *addr = (struct sockaddr_in *) sa; - const struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *) sa; struct cifs_server_key key; - uint16_t key_len = sizeof(key.hdr); - - memset(&key, 0, sizeof(key)); /* - * Should not be a problem as sin_family/sin6_family overlays - * sa_family field + * Check if cookie was already initialized so don't reinitialize it. + * In the future, as we integrate with newer fscache features, + * we may want to instead add a check if cookie has changed */ - key.hdr.family = sa->sa_family; - switch (sa->sa_family) { - case AF_INET: - key.hdr.port = addr->sin_port; - key.ipv4_addr = addr->sin_addr; - key_len += sizeof(key.ipv4_addr); - break; - - case AF_INET6: - key.hdr.port = addr6->sin6_port; - key.ipv6_addr = addr6->sin6_addr; - key_len += sizeof(key.ipv6_addr); - break; - - default: - cifs_dbg(VFS, "Unknown network family '%d'\n", sa->sa_family); - server->fscache = NULL; + if (server->fscache) return; - } + + memset(&key, 0, sizeof(key)); + key.conn_id = server->conn_id; server->fscache = fscache_acquire_cookie(cifs_fscache_netfs.primary_index, &cifs_fscache_server_index_def, - &key, key_len, + &key, sizeof(key), NULL, 0, server, 0, true); cifs_dbg(FYI, "%s: (0x%p/0x%p)\n", @@ -92,7 +66,7 @@ void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) * In the future, as we integrate with newer fscache features, * we may want to instead add a check if cookie has changed */ - if (tcon->fscache == NULL) + if (tcon->fscache) return; sharename = extract_sharename(tcon->treeName); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 82848412ad85..96d083db1737 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1376,6 +1376,13 @@ iget_no_retry: inode = ERR_PTR(rc); } + /* + * The cookie is initialized from volume info returned above. + * Inside cifs_fscache_get_super_cookie it checks + * that we do not get super cookie twice. + */ + cifs_fscache_get_super_cookie(tcon); + out: kfree(path); free_xid(xid); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index af63548eaf26..035dc3e245dc 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -590,8 +590,8 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, { unsigned int tioffset; /* challenge message target info area */ unsigned int tilen; /* challenge message target info area length */ - CHALLENGE_MESSAGE *pblob = (CHALLENGE_MESSAGE *)bcc_ptr; + __u32 server_flags; if (blob_len < sizeof(CHALLENGE_MESSAGE)) { cifs_dbg(VFS, "challenge blob len %d too small\n", blob_len); @@ -609,12 +609,37 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, return -EINVAL; } + server_flags = le32_to_cpu(pblob->NegotiateFlags); + cifs_dbg(FYI, "%s: negotiate=0x%08x challenge=0x%08x\n", __func__, + ses->ntlmssp->client_flags, server_flags); + + if ((ses->ntlmssp->client_flags & (NTLMSSP_NEGOTIATE_SEAL | NTLMSSP_NEGOTIATE_SIGN)) && + (!(server_flags & NTLMSSP_NEGOTIATE_56) && !(server_flags & NTLMSSP_NEGOTIATE_128))) { + cifs_dbg(VFS, "%s: requested signing/encryption but server did not return either 56-bit or 128-bit session key size\n", + __func__); + return -EINVAL; + } + if (!(server_flags & NTLMSSP_NEGOTIATE_NTLM) && !(server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) { + cifs_dbg(VFS, "%s: server does not seem to support either NTLMv1 or NTLMv2\n", __func__); + return -EINVAL; + } + if (ses->server->sign && !(server_flags & NTLMSSP_NEGOTIATE_SIGN)) { + cifs_dbg(VFS, "%s: forced packet signing but server does not seem to support it\n", + __func__); + return -EOPNOTSUPP; + } + if ((ses->ntlmssp->client_flags & NTLMSSP_NEGOTIATE_KEY_XCH) && + !(server_flags & NTLMSSP_NEGOTIATE_KEY_XCH)) + pr_warn_once("%s: authentication has been weakened as server does not support key exchange\n", + __func__); + + ses->ntlmssp->server_flags = server_flags; + memcpy(ses->ntlmssp->cryptkey, pblob->Challenge, CIFS_CRYPTO_KEY_SIZE); - /* BB we could decode pblob->NegotiateFlags; some may be useful */ /* In particular we can examine sign flags */ /* BB spec says that if AvId field of MsvAvTimestamp is populated then we must set the MIC field of the AUTHENTICATE_MESSAGE */ - ses->ntlmssp->server_flags = le32_to_cpu(pblob->NegotiateFlags); + tioffset = le32_to_cpu(pblob->TargetInfoArray.BufferOffset); tilen = le16_to_cpu(pblob->TargetInfoArray.Length); if (tioffset > blob_len || tioffset + tilen > blob_len) { @@ -721,13 +746,13 @@ int build_ntlmssp_negotiate_blob(unsigned char **pbuffer, flags = NTLMSSP_NEGOTIATE_56 | NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC | - NTLMSSP_NEGOTIATE_SEAL; - if (server->sign) - flags |= NTLMSSP_NEGOTIATE_SIGN; + NTLMSSP_NEGOTIATE_ALWAYS_SIGN | NTLMSSP_NEGOTIATE_SEAL | + NTLMSSP_NEGOTIATE_SIGN; if (!server->session_estab || ses->ntlmssp->sesskey_per_smbsess) flags |= NTLMSSP_NEGOTIATE_KEY_XCH; tmp = *pbuffer + sizeof(NEGOTIATE_MESSAGE); + ses->ntlmssp->client_flags = flags; sec_blob->NegotiateFlags = cpu_to_le32(flags); /* these fields should be null in negotiate phase MS-NLMP 3.1.5.1.1 */ @@ -779,15 +804,8 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8); sec_blob->MessageType = NtLmAuthenticate; - flags = NTLMSSP_NEGOTIATE_56 | - NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO | - NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | - NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC | - NTLMSSP_NEGOTIATE_SEAL | NTLMSSP_NEGOTIATE_WORKSTATION_SUPPLIED; - if (ses->server->sign) - flags |= NTLMSSP_NEGOTIATE_SIGN; - if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess) - flags |= NTLMSSP_NEGOTIATE_KEY_XCH; + flags = ses->ntlmssp->server_flags | NTLMSSP_REQUEST_TARGET | + NTLMSSP_NEGOTIATE_TARGET_INFO | NTLMSSP_NEGOTIATE_WORKSTATION_SUPPLIED; tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE); sec_blob->NegotiateFlags = cpu_to_le32(flags); @@ -834,9 +852,9 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, *pbuffer, &tmp, nls_cp); - if (((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) || - (ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) - && !calc_seckey(ses)) { + if ((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) && + (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess) && + !calc_seckey(ses)) { memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE); sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE); diff --git a/fs/file.c b/fs/file.c index 8627dacfc424..97d212a9b814 100644 --- a/fs/file.c +++ b/fs/file.c @@ -841,24 +841,68 @@ void do_close_on_exec(struct files_struct *files) spin_unlock(&files->file_lock); } +static inline struct file *__fget_files_rcu(struct files_struct *files, + unsigned int fd, fmode_t mask, unsigned int refs) +{ + for (;;) { + struct file *file; + struct fdtable *fdt = rcu_dereference_raw(files->fdt); + struct file __rcu **fdentry; + + if (unlikely(fd >= fdt->max_fds)) + return NULL; + + fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); + file = rcu_dereference_raw(*fdentry); + if (unlikely(!file)) + return NULL; + + if (unlikely(file->f_mode & mask)) + return NULL; + + /* + * Ok, we have a file pointer. However, because we do + * this all locklessly under RCU, we may be racing with + * that file being closed. + * + * Such a race can take two forms: + * + * (a) the file ref already went down to zero, + * and get_file_rcu_many() fails. Just try + * again: + */ + if (unlikely(!get_file_rcu_many(file, refs))) + continue; + + /* + * (b) the file table entry has changed under us. + * Note that we don't need to re-check the 'fdt->fd' + * pointer having changed, because it always goes + * hand-in-hand with 'fdt'. + * + * If so, we need to put our refs and try again. + */ + if (unlikely(rcu_dereference_raw(files->fdt) != fdt) || + unlikely(rcu_dereference_raw(*fdentry) != file)) { + fput_many(file, refs); + continue; + } + + /* + * Ok, we have a ref to the file, and checked that it + * still exists. + */ + return file; + } +} + static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask, unsigned int refs) { struct file *file; rcu_read_lock(); -loop: - file = files_lookup_fd_rcu(files, fd); - if (file) { - /* File object ref couldn't be taken. - * dup2() atomicity guarantee is the reason - * we loop to catch the new file (or NULL pointer) - */ - if (file->f_mode & mask) - file = NULL; - else if (!get_file_rcu_many(file, refs)) - goto loop; - } + file = __fget_files_rcu(files, fd, mask, refs); rcu_read_unlock(); return file; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 8dbd6fe66420..44a7a4288956 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1857,7 +1857,6 @@ void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs) void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) { - struct gfs2_holder mock_gh = { .gh_gl = gl, .gh_state = state, }; unsigned long delay = 0; unsigned long holdtime; unsigned long now = jiffies; @@ -1890,8 +1889,13 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) * keep the glock until the last strong holder is done with it. */ if (!find_first_strong_holder(gl)) { - if (state == LM_ST_UNLOCKED) - mock_gh.gh_state = LM_ST_EXCLUSIVE; + struct gfs2_holder mock_gh = { + .gh_gl = gl, + .gh_state = (state == LM_ST_UNLOCKED) ? + LM_ST_EXCLUSIVE : state, + .gh_iflags = BIT(HIF_HOLDER) + }; + demote_incompat_holders(gl, &mock_gh); } handle_callback(gl, state, delay, true); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 6424b903e885..89905f4f29bb 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -40,37 +40,6 @@ static const struct inode_operations gfs2_file_iops; static const struct inode_operations gfs2_dir_iops; static const struct inode_operations gfs2_symlink_iops; -static int iget_test(struct inode *inode, void *opaque) -{ - u64 no_addr = *(u64 *)opaque; - - return GFS2_I(inode)->i_no_addr == no_addr; -} - -static int iget_set(struct inode *inode, void *opaque) -{ - u64 no_addr = *(u64 *)opaque; - - GFS2_I(inode)->i_no_addr = no_addr; - inode->i_ino = no_addr; - return 0; -} - -static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr) -{ - struct inode *inode; - -repeat: - inode = iget5_locked(sb, no_addr, iget_test, iget_set, &no_addr); - if (!inode) - return inode; - if (is_bad_inode(inode)) { - iput(inode); - goto repeat; - } - return inode; -} - /** * gfs2_set_iop - Sets inode operations * @inode: The inode with correct i_mode filled in @@ -104,6 +73,22 @@ static void gfs2_set_iop(struct inode *inode) } } +static int iget_test(struct inode *inode, void *opaque) +{ + u64 no_addr = *(u64 *)opaque; + + return GFS2_I(inode)->i_no_addr == no_addr; +} + +static int iget_set(struct inode *inode, void *opaque) +{ + u64 no_addr = *(u64 *)opaque; + + GFS2_I(inode)->i_no_addr = no_addr; + inode->i_ino = no_addr; + return 0; +} + /** * gfs2_inode_lookup - Lookup an inode * @sb: The super block @@ -132,12 +117,11 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, { struct inode *inode; struct gfs2_inode *ip; - struct gfs2_glock *io_gl = NULL; struct gfs2_holder i_gh; int error; gfs2_holder_mark_uninitialized(&i_gh); - inode = gfs2_iget(sb, no_addr); + inode = iget5_locked(sb, no_addr, iget_test, iget_set, &no_addr); if (!inode) return ERR_PTR(-ENOMEM); @@ -145,22 +129,16 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, if (inode->i_state & I_NEW) { struct gfs2_sbd *sdp = GFS2_SB(inode); + struct gfs2_glock *io_gl; error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (unlikely(error)) goto fail; - flush_delayed_work(&ip->i_gl->gl_work); - - error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); - if (unlikely(error)) - goto fail; - if (blktype != GFS2_BLKST_UNLINKED) - gfs2_cancel_delete_work(io_gl); if (type == DT_UNKNOWN || blktype != GFS2_BLKST_FREE) { /* * The GL_SKIP flag indicates to skip reading the inode - * block. We read the inode with gfs2_inode_refresh + * block. We read the inode when instantiating it * after possibly checking the block type. */ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, @@ -181,24 +159,31 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, } } - glock_set_object(ip->i_gl, ip); set_bit(GLF_INSTANTIATE_NEEDED, &ip->i_gl->gl_flags); - error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); + + error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (unlikely(error)) goto fail; - glock_set_object(ip->i_iopen_gh.gh_gl, ip); + if (blktype != GFS2_BLKST_UNLINKED) + gfs2_cancel_delete_work(io_gl); + error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); gfs2_glock_put(io_gl); - io_gl = NULL; + if (unlikely(error)) + goto fail; /* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */ inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1); inode->i_atime.tv_nsec = 0; + glock_set_object(ip->i_gl, ip); + if (type == DT_UNKNOWN) { /* Inode glock must be locked already */ error = gfs2_instantiate(&i_gh); - if (error) + if (error) { + glock_clear_object(ip->i_gl, ip); goto fail; + } } else { ip->i_no_formal_ino = no_formal_ino; inode->i_mode = DT2IF(type); @@ -206,31 +191,23 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); + glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_set_iop(inode); + unlock_new_inode(inode); } if (no_formal_ino && ip->i_no_formal_ino && no_formal_ino != ip->i_no_formal_ino) { - error = -ESTALE; - if (inode->i_state & I_NEW) - goto fail; iput(inode); - return ERR_PTR(error); + return ERR_PTR(-ESTALE); } - if (inode->i_state & I_NEW) - unlock_new_inode(inode); - return inode; fail: - if (gfs2_holder_initialized(&ip->i_iopen_gh)) { - glock_clear_object(ip->i_iopen_gh.gh_gl, ip); + if (gfs2_holder_initialized(&ip->i_iopen_gh)) gfs2_glock_dq_uninit(&ip->i_iopen_gh); - } - if (io_gl) - gfs2_glock_put(io_gl); if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); iget_failed(inode); @@ -730,18 +707,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (error) goto fail_free_inode; - flush_delayed_work(&ip->i_gl->gl_work); error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) goto fail_free_inode; gfs2_cancel_delete_work(io_gl); + error = insert_inode_locked4(inode, ip->i_no_addr, iget_test, &ip->i_no_addr); + BUG_ON(error); + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); if (error) goto fail_gunlock2; - glock_set_object(ip->i_gl, ip); error = gfs2_trans_begin(sdp, blocks, 0); if (error) goto fail_gunlock2; @@ -757,9 +735,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_gunlock2; + glock_set_object(ip->i_gl, ip); glock_set_object(io_gl, ip); gfs2_set_iop(inode); - insert_inode_hash(inode); free_vfs_inode = 0; /* After this point, the inode is no longer considered free. Any failures need to undo @@ -801,17 +779,17 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_glock_dq_uninit(ghs + 1); gfs2_glock_put(io_gl); gfs2_qa_put(dip); + unlock_new_inode(inode); return error; fail_gunlock3: + glock_clear_object(ip->i_gl, ip); glock_clear_object(io_gl, ip); gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_gunlock2: - glock_clear_object(io_gl, ip); gfs2_glock_put(io_gl); fail_free_inode: if (ip->i_gl) { - glock_clear_object(ip->i_gl, ip); if (free_vfs_inode) /* else evict will do the put for us */ gfs2_glock_put(ip->i_gl); } @@ -829,7 +807,10 @@ fail_gunlock: mark_inode_dirty(inode); set_bit(free_vfs_inode ? GIF_FREE_VFS_INODE : GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags); - iput(inode); + if (inode->i_state & I_NEW) + iget_failed(inode); + else + iput(inode); } if (gfs2_holder_initialized(ghs + 1)) gfs2_glock_dq_uninit(ghs + 1); diff --git a/fs/io-wq.c b/fs/io-wq.c index 88202de519f6..8d2bb818a3bb 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -142,6 +142,7 @@ static bool io_acct_cancel_pending_work(struct io_wqe *wqe, struct io_wqe_acct *acct, struct io_cb_cancel_data *match); static void create_worker_cb(struct callback_head *cb); +static void io_wq_cancel_tw_create(struct io_wq *wq); static bool io_worker_get(struct io_worker *worker) { @@ -357,12 +358,22 @@ static bool io_queue_worker_create(struct io_worker *worker, test_and_set_bit_lock(0, &worker->create_state)) goto fail_release; + atomic_inc(&wq->worker_refs); init_task_work(&worker->create_work, func); worker->create_index = acct->index; if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) { - clear_bit_unlock(0, &worker->create_state); + /* + * EXIT may have been set after checking it above, check after + * adding the task_work and remove any creation item if it is + * now set. wq exit does that too, but we can have added this + * work item after we canceled in io_wq_exit_workers(). + */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) + io_wq_cancel_tw_create(wq); + io_worker_ref_put(wq); return true; } + io_worker_ref_put(wq); clear_bit_unlock(0, &worker->create_state); fail_release: io_worker_release(worker); @@ -714,6 +725,13 @@ static bool io_wq_work_match_all(struct io_wq_work *work, void *data) static inline bool io_should_retry_thread(long err) { + /* + * Prevent perpetual task_work retry, if the task (or its group) is + * exiting. + */ + if (fatal_signal_pending(current)) + return false; + switch (err) { case -EAGAIN: case -ERESTARTSYS: @@ -1191,13 +1209,9 @@ void io_wq_exit_start(struct io_wq *wq) set_bit(IO_WQ_BIT_EXIT, &wq->state); } -static void io_wq_exit_workers(struct io_wq *wq) +static void io_wq_cancel_tw_create(struct io_wq *wq) { struct callback_head *cb; - int node; - - if (!wq->task) - return; while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) { struct io_worker *worker; @@ -1205,6 +1219,16 @@ static void io_wq_exit_workers(struct io_wq *wq) worker = container_of(cb, struct io_worker, create_work); io_worker_cancel_cb(worker); } +} + +static void io_wq_exit_workers(struct io_wq *wq) +{ + int node; + + if (!wq->task) + return; + + io_wq_cancel_tw_create(wq); rcu_read_lock(); for_each_node(node) { diff --git a/fs/io_uring.c b/fs/io_uring.c index c4f217613f56..d5ab0e9a3f29 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -9824,7 +9824,7 @@ static __cold void io_uring_drop_tctx_refs(struct task_struct *task) /* * Find any io_uring ctx that this task has registered or done IO on, and cancel - * requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation. + * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation. */ static __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) @@ -9866,8 +9866,10 @@ static __cold void io_uring_cancel_generic(bool cancel_all, cancel_all); } - prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE); + io_run_task_work(); io_uring_drop_tctx_refs(current); + /* * If we've seen completions, retry without waiting. This * avoids a race where a completion comes in before we did diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 7046f9bdd8dc..75c76cbb27cc 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -354,16 +354,11 @@ static void netfs_rreq_write_to_cache_work(struct work_struct *work) netfs_rreq_do_write_to_cache(rreq); } -static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq, - bool was_async) +static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq) { - if (was_async) { - rreq->work.func = netfs_rreq_write_to_cache_work; - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); - } else { - netfs_rreq_do_write_to_cache(rreq); - } + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); } /* @@ -558,7 +553,7 @@ again: wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags)) - return netfs_rreq_write_to_cache(rreq, was_async); + return netfs_rreq_write_to_cache(rreq); netfs_rreq_completed(rreq, was_async); } @@ -960,7 +955,7 @@ int netfs_readpage(struct file *file, rreq = netfs_alloc_read_request(ops, netfs_priv, file); if (!rreq) { if (netfs_priv) - ops->cleanup(netfs_priv, folio_file_mapping(folio)); + ops->cleanup(folio_file_mapping(folio), netfs_priv); folio_unlock(folio); return -ENOMEM; } @@ -1191,7 +1186,7 @@ have_folio: goto error; have_folio_no_wait: if (netfs_priv) - ops->cleanup(netfs_priv, mapping); + ops->cleanup(mapping, netfs_priv); *_folio = folio; _leave(" = 0"); return 0; @@ -1202,7 +1197,7 @@ error: folio_unlock(folio); folio_put(folio); if (netfs_priv) - ops->cleanup(netfs_priv, mapping); + ops->cleanup(mapping, netfs_priv); _leave(" = %d", ret); return ret; } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 6fedc49726bf..c634483d85d2 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -2156,6 +2156,7 @@ static struct notifier_block nfsd4_cld_block = { int register_cld_notifier(void) { + WARN_ON(!nfsd_net_id); return rpc_pipefs_notifier_register(&nfsd4_cld_block); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index bfad94c70b84..1956d377d1a6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1207,6 +1207,11 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) return 0; } +static bool delegation_hashed(struct nfs4_delegation *dp) +{ + return !(list_empty(&dp->dl_perfile)); +} + static bool unhash_delegation_locked(struct nfs4_delegation *dp) { @@ -1214,7 +1219,7 @@ unhash_delegation_locked(struct nfs4_delegation *dp) lockdep_assert_held(&state_lock); - if (list_empty(&dp->dl_perfile)) + if (!delegation_hashed(dp)) return false; dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID; @@ -4598,7 +4603,7 @@ static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) * queued for a lease break. Don't queue it again. */ spin_lock(&state_lock); - if (dp->dl_time == 0) { + if (delegation_hashed(dp) && dp->dl_time == 0) { dp->dl_time = ktime_get_boottime_seconds(); list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru); } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index af8531c3854a..51a49e0cfe37 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1521,12 +1521,9 @@ static int __init init_nfsd(void) int retval; printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n"); - retval = register_cld_notifier(); - if (retval) - return retval; retval = nfsd4_init_slabs(); if (retval) - goto out_unregister_notifier; + return retval; retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; @@ -1545,9 +1542,14 @@ static int __init init_nfsd(void) goto out_free_exports; retval = register_pernet_subsys(&nfsd_net_ops); if (retval < 0) + goto out_free_filesystem; + retval = register_cld_notifier(); + if (retval) goto out_free_all; return 0; out_free_all: + unregister_pernet_subsys(&nfsd_net_ops); +out_free_filesystem: unregister_filesystem(&nfsd_fs_type); out_free_exports: remove_proc_entry("fs/nfs/exports", NULL); @@ -1561,13 +1563,12 @@ out_free_pnfs: nfsd4_exit_pnfs(); out_free_slabs: nfsd4_free_slabs(); -out_unregister_notifier: - unregister_cld_notifier(); return retval; } static void __exit exit_nfsd(void) { + unregister_cld_notifier(); unregister_pernet_subsys(&nfsd_net_ops); nfsd_drc_slab_free(); remove_proc_entry("fs/nfs/exports", NULL); @@ -1577,7 +1578,6 @@ static void __exit exit_nfsd(void) nfsd4_free_slabs(); nfsd4_exit_pnfs(); unregister_filesystem(&nfsd_fs_type); - unregister_cld_notifier(); } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 15c2e55d2ed2..39b823ab2564 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -61,15 +61,27 @@ static int seq_open_net(struct inode *inode, struct file *file) } #ifdef CONFIG_NET_NS p->net = net; + netns_tracker_alloc(net, &p->ns_tracker, GFP_KERNEL); #endif return 0; } +static void seq_file_net_put_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + struct seq_net_private *priv = seq->private; + + put_net_track(priv->net, &priv->ns_tracker); +#else + put_net(&init_net); +#endif +} + static int seq_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; - put_net(seq_file_net(seq)); + seq_file_net_put_net(seq); seq_release_private(ino, f); return 0; } @@ -87,7 +99,8 @@ int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux) #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; - p->net = get_net(current->nsproxy->net_ns); + p->net = get_net_track(current->nsproxy->net_ns, &p->ns_tracker, + GFP_KERNEL); #endif return 0; } @@ -97,7 +110,7 @@ void bpf_iter_fini_seq_net(void *priv_data) #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; - put_net(p->net); + put_net_track(p->net, &p->ns_tracker); #endif } diff --git a/fs/signalfd.c b/fs/signalfd.c index 040e1cf90528..65ce0e72e7b9 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -35,17 +35,7 @@ void signalfd_cleanup(struct sighand_struct *sighand) { - wait_queue_head_t *wqh = &sighand->signalfd_wqh; - /* - * The lockless check can race with remove_wait_queue() in progress, - * but in this case its caller should run under rcu_read_lock() and - * sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return. - */ - if (likely(!waitqueue_active(wqh))) - return; - - /* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */ - wake_up_poll(wqh, EPOLLHUP | POLLFREE); + wake_up_pollfree(&sighand->signalfd_wqh); } struct signalfd_ctx { diff --git a/fs/smbfs_common/cifs_arc4.c b/fs/smbfs_common/cifs_arc4.c index 85ba15a60b13..043e4cb839fa 100644 --- a/fs/smbfs_common/cifs_arc4.c +++ b/fs/smbfs_common/cifs_arc4.c @@ -72,16 +72,3 @@ void cifs_arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int l ctx->y = y; } EXPORT_SYMBOL_GPL(cifs_arc4_crypt); - -static int __init -init_smbfs_common(void) -{ - return 0; -} -static void __init -exit_smbfs_common(void) -{ -} - -module_init(init_smbfs_common) -module_exit(exit_smbfs_common) diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 925a621b432e..3616839c5c4b 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -161,6 +161,77 @@ struct tracefs_fs_info { struct tracefs_mount_opts mount_opts; }; +static void change_gid(struct dentry *dentry, kgid_t gid) +{ + if (!dentry->d_inode) + return; + dentry->d_inode->i_gid = gid; +} + +/* + * Taken from d_walk, but without he need for handling renames. + * Nothing can be renamed while walking the list, as tracefs + * does not support renames. This is only called when mounting + * or remounting the file system, to set all the files to + * the given gid. + */ +static void set_gid(struct dentry *parent, kgid_t gid) +{ + struct dentry *this_parent; + struct list_head *next; + + this_parent = parent; + spin_lock(&this_parent->d_lock); + + change_gid(this_parent, gid); +repeat: + next = this_parent->d_subdirs.next; +resume: + while (next != &this_parent->d_subdirs) { + struct list_head *tmp = next; + struct dentry *dentry = list_entry(tmp, struct dentry, d_child); + next = tmp->next; + + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + + change_gid(dentry, gid); + + if (!list_empty(&dentry->d_subdirs)) { + spin_unlock(&this_parent->d_lock); + spin_release(&dentry->d_lock.dep_map, _RET_IP_); + this_parent = dentry; + spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); + goto repeat; + } + spin_unlock(&dentry->d_lock); + } + /* + * All done at this level ... ascend and resume the search. + */ + rcu_read_lock(); +ascend: + if (this_parent != parent) { + struct dentry *child = this_parent; + this_parent = child->d_parent; + + spin_unlock(&child->d_lock); + spin_lock(&this_parent->d_lock); + + /* go into the first sibling still alive */ + do { + next = child->d_child.next; + if (next == &this_parent->d_subdirs) + goto ascend; + child = list_entry(next, struct dentry, d_child); + } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); + rcu_read_unlock(); + goto resume; + } + rcu_read_unlock(); + spin_unlock(&this_parent->d_lock); + return; +} + static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) { substring_t args[MAX_OPT_ARGS]; @@ -193,6 +264,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) if (!gid_valid(gid)) return -EINVAL; opts->gid = gid; + set_gid(tracefs_mount->mnt_root, gid); break; case Opt_mode: if (match_octal(&args[0], &option)) @@ -414,6 +486,8 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, inode->i_mode = mode; inode->i_fop = fops ? fops : &tracefs_file_operations; inode->i_private = data; + inode->i_uid = d_inode(dentry->d_parent)->i_uid; + inode->i_gid = d_inode(dentry->d_parent)->i_gid; d_instantiate(dentry, inode); fsnotify_create(dentry->d_parent->d_inode, dentry); return end_creating(dentry); @@ -436,6 +510,8 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent, inode->i_mode = S_IFDIR | S_IRWXU | S_IRUSR| S_IRGRP | S_IXUSR | S_IXGRP; inode->i_op = ops; inode->i_fop = &simple_dir_operations; + inode->i_uid = d_inode(dentry->d_parent)->i_uid; + inode->i_gid = d_inode(dentry->d_parent)->i_gid; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 64b9bf334806..6771f357ad2c 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3122,7 +3122,6 @@ xfs_rename( * appropriately. */ if (flags & RENAME_WHITEOUT) { - ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE))); error = xfs_rename_alloc_whiteout(mnt_userns, target_dp, &wip); if (error) return error; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index e21459f9923a..778b57b1f020 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1765,7 +1765,10 @@ static int xfs_remount_ro( struct xfs_mount *mp) { - int error; + struct xfs_icwalk icw = { + .icw_flags = XFS_ICWALK_FLAG_SYNC, + }; + int error; /* * Cancel background eofb scanning so it cannot race with the final @@ -1773,8 +1776,13 @@ xfs_remount_ro( */ xfs_blockgc_stop(mp); - /* Get rid of any leftover CoW reservations... */ - error = xfs_blockgc_free_space(mp, NULL); + /* + * Clear out all remaining COW staging extents and speculative post-EOF + * preallocations so that we don't leave inodes requiring inactivation + * cleanups during reclaim on a read-only mount. We must process every + * cached inode, so this requires a synchronous cache scan. + */ + error = xfs_blockgc_free_space(mp, &icw); if (error) { xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3de38d7f0ced..0ceb54c6342f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -732,6 +732,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); +int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs); #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ @@ -1081,7 +1082,7 @@ struct bpf_array { }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ -#define MAX_TAIL_CALL_CNT 32 +#define MAX_TAIL_CALL_CNT 33 #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ @@ -1352,28 +1353,16 @@ extern struct mutex bpf_stats_enabled_mutex; * kprobes, tracepoints) to prevent deadlocks on map operations as any of * these events can happen inside a region which holds a map bucket lock * and can deadlock on it. - * - * Use the preemption safe inc/dec variants on RT because migrate disable - * is preemptible on RT and preemption in the middle of the RMW operation - * might lead to inconsistent state. Use the raw variants for non RT - * kernels as migrate_disable() maps to preempt_disable() so the slightly - * more expensive save operation can be avoided. */ static inline void bpf_disable_instrumentation(void) { migrate_disable(); - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - this_cpu_inc(bpf_prog_active); - else - __this_cpu_inc(bpf_prog_active); + this_cpu_inc(bpf_prog_active); } static inline void bpf_enable_instrumentation(void) { - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - this_cpu_dec(bpf_prog_active); - else - __this_cpu_dec(bpf_prog_active); + this_cpu_dec(bpf_prog_active); migrate_enable(); } @@ -1733,6 +1722,14 @@ bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); +struct bpf_core_ctx { + struct bpf_verifier_log *log; + const struct btf *btf; +}; + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -2165,6 +2162,7 @@ extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; extern const struct bpf_func_proto bpf_find_vma_proto; +extern const struct bpf_func_proto bpf_loop_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c8a78e830fca..182b16a91084 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -396,6 +396,13 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) log->level == BPF_LOG_KERNEL); } +static inline bool +bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) +{ + return log->len_total >= 128 && log->len_total <= UINT_MAX >> 2 && + log->level && log->ubuf && !(log->level & ~BPF_LOG_MASK); +} + #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_info { diff --git a/include/linux/btf.h b/include/linux/btf.h index 203eef993d76..0c74348cbc9d 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -144,6 +144,53 @@ static inline bool btf_type_is_enum(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } +static inline bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +static inline u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +static inline bool btf_is_enum(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM; +} + +static inline bool btf_is_composite(const struct btf_type *t) +{ + u16 kind = btf_kind(t); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static inline bool btf_is_array(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ARRAY; +} + +static inline bool btf_is_int(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_INT; +} + +static inline bool btf_is_ptr(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_PTR; +} + +static inline u8 btf_int_offset(const struct btf_type *t) +{ + return BTF_INT_OFFSET(*(u32 *)(t + 1)); +} + +static inline u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(u32 *)(t + 1)); +} + static inline bool btf_type_is_scalar(const struct btf_type *t) { return btf_type_is_int(t) || btf_type_is_enum(t); @@ -184,6 +231,11 @@ static inline u16 btf_type_vlen(const struct btf_type *t) return BTF_INFO_VLEN(t->info); } +static inline u16 btf_vlen(const struct btf_type *t) +{ + return btf_type_vlen(t); +} + static inline u16 btf_func_linkage(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); @@ -194,25 +246,54 @@ static inline bool btf_type_kflag(const struct btf_type *t) return BTF_INFO_KFLAG(t->info); } -static inline u32 btf_member_bit_offset(const struct btf_type *struct_type, - const struct btf_member *member) +static inline u32 __btf_member_bit_offset(const struct btf_type *struct_type, + const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) : member->offset; } -static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type, - const struct btf_member *member) +static inline u32 __btf_member_bitfield_size(const struct btf_type *struct_type, + const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) : 0; } +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +static inline u32 btf_member_bit_offset(const struct btf_type *t, u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + + return __btf_member_bit_offset(t, m); +} + +static inline u32 btf_member_bitfield_size(const struct btf_type *t, u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + + return __btf_member_bitfield_size(t, m); +} + static inline const struct btf_member *btf_type_member(const struct btf_type *t) { return (const struct btf_member *)(t + 1); } +static inline struct btf_array *btf_array(const struct btf_type *t) +{ + return (struct btf_array *)(t + 1); +} + +static inline struct btf_enum *btf_enum(const struct btf_type *t) +{ + return (struct btf_enum *)(t + 1); +} + static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { @@ -245,7 +326,10 @@ struct kfunc_btf_id_set { struct module *owner; }; -struct kfunc_btf_id_list; +struct kfunc_btf_id_list { + struct list_head list; + struct mutex mutex; +}; #ifdef CONFIG_DEBUG_INFO_BTF_MODULES void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, @@ -254,6 +338,9 @@ void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, struct kfunc_btf_id_set *s); bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, struct module *owner); + +extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; +extern struct kfunc_btf_id_list prog_test_kfunc_list; #else static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, struct kfunc_btf_id_set *s) @@ -268,13 +355,13 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, { return false; } + +static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused; +static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused; #endif #define DEFINE_KFUNC_BTF_ID_SET(set, name) \ struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ THIS_MODULE } -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; - #endif diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 2f909ed084c6..4ff37cb763ae 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -3,7 +3,6 @@ #define _LINUX_CACHEINFO_H #include <linux/bitops.h> -#include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/smp.h> diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 20b50baf3a02..a81652d1c6f3 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -12,13 +12,6 @@ #define CAN_SYNC_SEG 1 -/* Kilobits and Megabits per second */ -#define CAN_KBPS 1000UL -#define CAN_MBPS 1000000UL - -/* Megahertz */ -#define CAN_MHZ 1000000UL - #define CAN_CTRLMODE_TDC_MASK \ (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) diff --git a/include/linux/delay.h b/include/linux/delay.h index 8eacf67eb212..039e7e0c7378 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -20,6 +20,7 @@ */ #include <linux/math.h> +#include <linux/sched.h> extern unsigned long loops_per_jiffy; @@ -58,7 +59,18 @@ void calibrate_delay(void); void __attribute__((weak)) calibration_delay_done(void); void msleep(unsigned int msecs); unsigned long msleep_interruptible(unsigned int msecs); -void usleep_range(unsigned long min, unsigned long max); +void usleep_range_state(unsigned long min, unsigned long max, + unsigned int state); + +static inline void usleep_range(unsigned long min, unsigned long max) +{ + usleep_range_state(min, max, TASK_UNINTERRUPTIBLE); +} + +static inline void usleep_idle_range(unsigned long min, unsigned long max) +{ + usleep_range_state(min, max, TASK_IDLE); +} static inline void ssleep(unsigned int seconds) { diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index a498ebcf4993..15e7c5e15d62 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -18,6 +18,7 @@ #include <linux/klist.h> #include <linux/pm.h> #include <linux/device/bus.h> +#include <linux/module.h> /** * enum probe_type - device driver probe type to try diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 254b165f2b44..939a1beaddf7 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -7,6 +7,7 @@ #include <linux/refcount.h> #include <linux/types.h> +#include <net/dsa.h> struct dsa_switch; struct dsa_port; @@ -37,14 +38,12 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num); + struct dsa_bridge bridge); void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num); + struct dsa_bridge bridge); -u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num); +u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num); u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp); diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 7ee708ad7df2..dca2969015d8 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -8,6 +8,7 @@ #include <linux/kthread.h> #include <linux/packing.h> #include <linux/skbuff.h> +#include <net/dsa.h> struct ocelot_skb_cb { struct sk_buff *clone; @@ -168,11 +169,18 @@ struct felix_deferred_xmit_work { struct kthread_work work; }; -struct felix_port { +struct ocelot_8021q_tagger_data { void (*xmit_work_fn)(struct kthread_work *work); - struct kthread_worker *xmit_worker; }; +static inline struct ocelot_8021q_tagger_data * +ocelot_8021q_tagger_data(struct dsa_switch *ds) +{ + BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_OCELOT_8021Q); + + return ds->tagger_data; +} + static inline void ocelot_xfh_get_rew_val(void *extraction, u64 *rew_val) { packing(extraction, rew_val, 116, 85, OCELOT_TAG_LEN, UNPACK, 0); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index e6c78be40bde..159e43171ccc 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -35,23 +35,26 @@ #define SJA1105_META_SMAC 0x222222222222ull #define SJA1105_META_DMAC 0x0180C200000Eull -#define SJA1105_HWTS_RX_EN 0 +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; -/* Global tagger data: each struct sja1105_port has a reference to - * the structure defined in struct sja1105_private. - */ +struct sja1105_deferred_xmit_work { + struct dsa_port *dp; + struct sk_buff *skb; + struct kthread_work work; +}; + +/* Global tagger data */ struct sja1105_tagger_data { - struct sk_buff *stampable_skb; - /* Protects concurrent access to the meta state machine - * from taggers running on multiple ports on SMP systems - */ - spinlock_t meta_lock; - unsigned long state; - u8 ts_id; - /* Used on SJA1110 where meta frames are generated only for - * 2-step TX timestamps - */ - struct sk_buff_head skb_txtstamp_queue; + /* Tagger to switch */ + void (*xmit_work_fn)(struct kthread_work *work); + void (*meta_tstamp_handler)(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + /* Switch to tagger */ + bool (*rxtstamp_get_state)(struct dsa_switch *ds); + void (*rxtstamp_set_state)(struct dsa_switch *ds, bool on); }; struct sja1105_skb_cb { @@ -64,32 +67,13 @@ struct sja1105_skb_cb { #define SJA1105_SKB_CB(skb) \ ((struct sja1105_skb_cb *)((skb)->cb)) -struct sja1105_port { - struct kthread_worker *xmit_worker; - struct kthread_work xmit_work; - struct sk_buff_head xmit_queue; - struct sja1105_tagger_data *data; - bool hwts_tx_en; -}; - -/* Timestamps are in units of 8 ns clock ticks (equivalent to - * a fixed 125 MHz clock). - */ -#define SJA1105_TICK_NS 8 - -static inline s64 ns_to_sja1105_ticks(s64 ns) +static inline struct sja1105_tagger_data * +sja1105_tagger_data(struct dsa_switch *ds) { - return ns / SJA1105_TICK_NS; -} + BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1105 && + ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1110); -static inline s64 sja1105_ticks_to_ns(s64 ticks) -{ - return ticks * SJA1105_TICK_NS; -} - -static inline bool dsa_port_is_sja1105(struct dsa_port *dp) -{ - return true; + return ds->tagger_data; } #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index b6a216eb217a..68c6b5c208e7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -6,6 +6,7 @@ #define __LINUX_FILTER_H__ #include <linux/atomic.h> +#include <linux/bpf.h> #include <linux/refcount.h> #include <linux/compat.h> #include <linux/skbuff.h> @@ -26,7 +27,6 @@ #include <asm/byteorder.h> #include <uapi/linux/filter.h> -#include <uapi/linux/bpf.h> struct sk_buff; struct sock; @@ -640,9 +640,6 @@ static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. - * - * For non RT enabled kernels migrate_disable/enable() maps to - * preempt_disable/enable(), i.e. it disables also preemption. */ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx) diff --git a/include/linux/hid.h b/include/linux/hid.h index 9e067f937dbc..f453be385bd4 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -840,6 +840,11 @@ static inline bool hid_is_using_ll_driver(struct hid_device *hdev, return hdev->ll_driver == driver; } +static inline bool hid_is_usb(struct hid_device *hdev) +{ + return hid_is_using_ll_driver(hdev, &usb_hid_driver); +} + #define PM_HINT_FULLON 1<<5 #define PM_HINT_NORMAL 1<<1 diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 723985879035..a5cc4cdf9cc8 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -664,6 +664,19 @@ int mhi_pm_suspend(struct mhi_controller *mhi_cntrl); int mhi_pm_resume(struct mhi_controller *mhi_cntrl); /** + * mhi_pm_resume_force - Force resume MHI from suspended state + * @mhi_cntrl: MHI controller + * + * Resume the device irrespective of its MHI state. As per the MHI spec, devices + * has to be in M3 state during resume. But some devices seem to be in a + * different MHI state other than M3 but they continue working fine if allowed. + * This API is intented to be used for such devices. + * + * Return: 0 if the resume succeeds, a negative error code otherwise + */ +int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl); + +/** * mhi_download_rddm_image - Download ramdump image from device for * debugging purpose. * @mhi_cntrl: MHI controller diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index cd2d4c572367..b1aad14689e3 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -73,6 +73,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_KERNEL, MLX5_FLOW_NAMESPACE_LEFTOVERS, MLX5_FLOW_NAMESPACE_ANCHOR, + MLX5_FLOW_NAMESPACE_FDB_BYPASS, MLX5_FLOW_NAMESPACE_FDB, MLX5_FLOW_NAMESPACE_ESW_EGRESS, MLX5_FLOW_NAMESPACE_ESW_INGRESS, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fbaab440a484..e9db12aae8f9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1621,7 +1621,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 ext_stride_num_range[0x1]; u8 roce_rw_supported[0x1]; - u8 reserved_at_3a2[0x1]; + u8 log_max_current_uc_list_wr_supported[0x1]; u8 log_max_stride_sz_rq[0x5]; u8 reserved_at_3a8[0x3]; u8 log_min_stride_sz_rq[0x5]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1a748ee9a421..a419718612c6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -48,7 +48,7 @@ #include <uapi/linux/pkt_cls.h> #include <linux/hashtable.h> #include <linux/rbtree.h> -#include <linux/ref_tracker.h> +#include <net/net_trackers.h> struct netpoll_info; struct device; @@ -300,13 +300,6 @@ enum netdev_state_t { __LINK_STATE_TESTING, }; - -#ifdef CONFIG_NET_DEV_REFCNT_TRACKER -typedef struct ref_tracker *netdevice_tracker; -#else -typedef struct {} netdevice_tracker; -#endif - struct gro_list { struct list_head list; int count; @@ -2540,6 +2533,7 @@ struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ + netdevice_tracker dev_tracker; int (*func) (struct sk_buff *, struct net_device *, struct packet_type *, @@ -3892,16 +3886,14 @@ static inline void dev_replace_track(struct net_device *odev, netdevice_tracker *tracker, gfp_t gfp) { -#ifdef CONFIG_NET_DEV_REFCNT_TRACKER if (odev) - ref_tracker_free(&odev->refcnt_tracker, tracker); -#endif + netdev_tracker_free(odev, tracker); + dev_hold(ndev); dev_put(odev); -#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + if (ndev) - ref_tracker_alloc(&ndev->refcnt_tracker, tracker, gfp); -#endif + netdev_tracker_alloc(ndev, tracker, gfp); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index b31d3f3312ce..d73a1c08c3e3 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -51,9 +51,9 @@ #define _LINUX_PERCPU_REFCOUNT_H #include <linux/atomic.h> -#include <linux/kernel.h> #include <linux/percpu.h> #include <linux/rcupdate.h> +#include <linux/types.h> #include <linux/gfp.h> struct percpu_ref; diff --git a/include/linux/phy.h b/include/linux/phy.h index 1e57cdd95da3..6de8d7a90d78 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -538,11 +538,12 @@ struct macsec_ops; * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. - * Bits [15:0] are free to use by the PHY driver to communicate - * driver specific behavior. - * Bits [23:16] are currently reserved for future use. - * Bits [31:24] are reserved for defining generic - * PHY driver behavior. + * + * - Bits [15:0] are free to use by the PHY driver to communicate + * driver specific behavior. + * - Bits [23:16] are currently reserved for future use. + * - Bits [31:24] are reserved for defining generic + * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 01224235df0f..713a0c928b7c 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -84,6 +84,8 @@ enum phylink_op_type { * struct phylink_config - PHYLINK configuration structure * @dev: a pointer to a struct device associated with the MAC * @type: operation type of PHYLINK instance + * @legacy_pre_march2020: driver has not been updated for March 2020 updates + * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @pcs_poll: MAC PCS cannot provide link change interrupt * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. @@ -97,6 +99,7 @@ enum phylink_op_type { struct phylink_config { struct device *dev; enum phylink_op_type type; + bool legacy_pre_march2020; bool pcs_poll; bool poll_fixed_state; bool ovr_an_inband; @@ -109,6 +112,7 @@ struct phylink_config { /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. + * @mac_select_pcs: Select a PCS for the interface mode. * @mac_pcs_get_state: Read the current link state from the hardware. * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. @@ -123,6 +127,8 @@ struct phylink_mac_ops { void (*validate)(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); + struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, + phy_interface_t interface); void (*mac_pcs_get_state)(struct phylink_config *config, struct phylink_link_state *state); int (*mac_prepare)(struct phylink_config *config, unsigned int mode, @@ -175,6 +181,21 @@ struct phylink_mac_ops { */ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); +/** + * mac_select_pcs: Select a PCS for the interface mode. + * @config: a pointer to a &struct phylink_config. + * @interface: PHY interface mode for PCS + * + * Return the &struct phylink_pcs for the specified interface mode, or + * NULL if none is required, or an error pointer on error. + * + * This must not modify any state. It is used to query which PCS should + * be used. Phylink will use this during validation to ensure that the + * configuration is valid, and when setting a configuration to internally + * set the PCS that will be used. + */ +struct phylink_pcs *mac_select_pcs(struct phylink_config *config, + phy_interface_t interface); /** * mac_pcs_get_state() - Read the current inband link state from the hardware @@ -187,6 +208,10 @@ void validate(struct phylink_config *config, unsigned long *supported, * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. + * + * Note: This is a legacy method. This function will not be called unless + * legacy_pre_march2020 is set in &struct phylink_config and there is no + * PCS attached. */ void mac_pcs_get_state(struct phylink_config *config, struct phylink_link_state *state); @@ -227,6 +252,15 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * guaranteed to be correct, and so any mac_config() implementation must * never reference these fields. * + * Note: For legacy March 2020 drivers (drivers with legacy_pre_march2020 set + * in their &phylnk_config and which don't have a PCS), this function will be + * called on each link up event, and to also change the in-band advert. For + * non-legacy drivers, it will only be called to reconfigure the MAC for a + * "major" change in e.g. interface mode. It will not be called for changes + * in speed, duplex or pause modes or to change the in-band advertisement. + * In any case, it is strongly preferred that speed, duplex and pause settings + * are handled in the mac_link_up() method and not in this method. + * * (this requires a rewrite - please refer to mac_link_up() for situations * where the PCS and MAC are not tightly integrated.) * @@ -311,6 +345,10 @@ int mac_finish(struct phylink_config *config, unsigned int mode, /** * mac_an_restart() - restart 802.3z BaseX autonegotiation * @config: a pointer to a &struct phylink_config. + * + * Note: This is a legacy method. This function will not be called unless + * legacy_pre_march2020 is set in &struct phylink_config and there is no + * PCS attached. */ void mac_an_restart(struct phylink_config *config); @@ -378,6 +416,7 @@ struct phylink_pcs { /** * struct phylink_pcs_ops - MAC PCS operations structure. + * @pcs_validate: validate the link configuration. * @pcs_get_state: read the current MAC PCS link state from the hardware. * @pcs_config: configure the MAC PCS for the selected mode and state. * @pcs_an_restart: restart 802.3z BaseX autonegotiation. @@ -385,6 +424,8 @@ struct phylink_pcs { * (where necessary). */ struct phylink_pcs_ops { + int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state); void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int mode, @@ -398,6 +439,23 @@ struct phylink_pcs_ops { #if 0 /* For kernel-doc purposes only. */ /** + * pcs_validate() - validate the link configuration. + * @pcs: a pointer to a &struct phylink_pcs. + * @supported: ethtool bitmask for supported link modes. + * @state: a const pointer to a &struct phylink_link_state. + * + * Validate the interface mode, and advertising's autoneg bit, removing any + * media ethtool link modes that would not be supportable from the supported + * mask. Phylink will propagate the changes to the advertising mask. See the + * &struct phylink_mac_ops validate() method. + * + * Returns -EINVAL if the interface mode/autoneg mode is not supported. + * Returns non-zero positive if the link state can be supported. + */ +int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state); + +/** * pcs_get_state() - Read the current inband link state from the hardware * @pcs: a pointer to a &struct phylink_pcs. * @state: a pointer to a &struct phylink_link_state. diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 222da43b7096..eddd66d426ca 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -129,7 +129,7 @@ static inline bool pm_runtime_suspended(struct device *dev) * pm_runtime_active - Check whether or not a device is runtime-active. * @dev: Target device. * - * Return %true if runtime PM is enabled for @dev and its runtime PM status is + * Return %true if runtime PM is disabled for @dev or its runtime PM status is * %RPM_ACTIVE, or %false otherwise. * * Note that the return value of this function can only be trusted if it is diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index bd7a73db2e66..54cf566616ae 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -499,7 +499,8 @@ struct regulator_irq_data { * best to shut-down regulator(s) or reboot the SOC if error * handling is repeatedly failing. If fatal_cnt is given the IRQ * handling is aborted if it fails for fatal_cnt times and die() - * callback (if populated) or BUG() is called to try to prevent + * callback (if populated) is called. If die() is not populated + * poweroff for the system is attempted in order to prevent any * further damage. * @reread_ms: The time which is waited before attempting to re-read status * at the worker if IC reading fails. Immediate re-read is done @@ -516,11 +517,12 @@ struct regulator_irq_data { * @data: Driver private data pointer which will be passed as such to * the renable, map_event and die callbacks in regulator_irq_data. * @die: Protection callback. If IC status reading or recovery actions - * fail fatal_cnt times this callback or BUG() is called. This - * callback should implement a final protection attempt like - * disabling the regulator. If protection succeeded this may - * return 0. If anything else is returned the core assumes final - * protection failed and calls BUG() as a last resort. + * fail fatal_cnt times this callback is called or system is + * powered off. This callback should implement a final protection + * attempt like disabling the regulator. If protection succeeded + * die() may return 0. If anything else is returned the core + * assumes final protection failed and attempts to perform a + * poweroff as a last resort. * @map_event: Driver callback to map IRQ status into regulator devices with * events / errors. NOTE: callback MUST initialize both the * errors and notifs for all rdevs which it signals having diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h index 6c9f19a33865..ce3c58286062 100644 --- a/include/linux/sched/cputime.h +++ b/include/linux/sched/cputime.h @@ -18,15 +18,16 @@ #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void task_cputime(struct task_struct *t, +extern bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime); extern u64 task_gtime(struct task_struct *t); #else -static inline void task_cputime(struct task_struct *t, +static inline bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { *utime = t->utime; *stime = t->stime; + return false; } static inline u64 task_gtime(struct task_struct *t) diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h index 0fdbe1ddd8d1..b97912fdbae7 100644 --- a/include/linux/seq_file_net.h +++ b/include/linux/seq_file_net.h @@ -9,7 +9,8 @@ extern struct net init_net; struct seq_net_private { #ifdef CONFIG_NET_NS - struct net *net; + struct net *net; + netns_tracker ns_tracker; #endif }; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dd262bd8ddbe..6535294f6a48 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -292,9 +292,11 @@ struct tc_skb_ext { #endif struct sk_buff_head { - /* These two members must be first. */ - struct sk_buff *next; - struct sk_buff *prev; + /* These two members must be first to match sk_buff. */ + struct_group_tagged(sk_buff_list, list, + struct sk_buff *next; + struct sk_buff *prev; + ); __u32 qlen; spinlock_t lock; @@ -730,7 +732,7 @@ typedef unsigned char *sk_buff_data_t; struct sk_buff { union { struct { - /* These two members must be first. */ + /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; @@ -1976,8 +1978,8 @@ static inline void __skb_insert(struct sk_buff *newsk, */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); - WRITE_ONCE(next->prev, newsk); - WRITE_ONCE(prev->next, newsk); + WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); + WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } @@ -2073,7 +2075,7 @@ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { - __skb_insert(newsk, prev, prev->next, list); + __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, @@ -2083,7 +2085,7 @@ static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { - __skb_insert(newsk, next->prev, next, list); + __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index e8ec116c916b..6ad4e9032d53 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -66,7 +66,7 @@ #include <linux/seqlock.h> struct u64_stats_sync { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) seqcount_t seq; #endif }; @@ -125,7 +125,7 @@ static inline void u64_stats_inc(u64_stats_t *p) } #endif -#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) #define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) #else static inline void u64_stats_init(struct u64_stats_sync *syncp) @@ -135,15 +135,19 @@ static inline void u64_stats_init(struct u64_stats_sync *syncp) static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); write_seqcount_begin(&syncp->seq); #endif } static inline void u64_stats_update_end(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); #endif } @@ -152,8 +156,11 @@ u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) { unsigned long flags = 0; -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - local_irq_save(flags); +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + local_irq_save(flags); write_seqcount_begin(&syncp->seq); #endif return flags; @@ -163,15 +170,18 @@ static inline void u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, unsigned long flags) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); - local_irq_restore(flags); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + local_irq_restore(flags); #endif } static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_begin(&syncp->seq); #else return 0; @@ -180,7 +190,7 @@ static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync * static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -189,7 +199,7 @@ static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *sy static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_retry(&syncp->seq, start); #else return false; @@ -199,7 +209,7 @@ static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_enable(); #endif return __u64_stats_fetch_retry(syncp, start); @@ -213,7 +223,9 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, */ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_disable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -222,7 +234,9 @@ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_enable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_enable(); #endif return __u64_stats_fetch_retry(syncp, start); diff --git a/include/linux/wait.h b/include/linux/wait.h index 2d0df57c9902..851e07da2583 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -217,6 +217,7 @@ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); +void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) @@ -245,6 +246,31 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); #define wake_up_interruptible_sync_poll_locked(x, m) \ __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) +/** + * wake_up_pollfree - signal that a polled waitqueue is going away + * @wq_head: the wait queue head + * + * In the very rare cases where a ->poll() implementation uses a waitqueue whose + * lifetime is tied to a task rather than to the 'struct file' being polled, + * this function must be called before the waitqueue is freed so that + * non-blocking polls (e.g. epoll) are notified that the queue is going away. + * + * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via + * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU. + */ +static inline void wake_up_pollfree(struct wait_queue_head *wq_head) +{ + /* + * For performance reasons, we don't always take the queue lock here. + * Therefore, we might race with someone removing the last entry from + * the queue, and proceed while they still hold the queue lock. + * However, rcu_read_lock() is required to be held in such cases, so we + * can safely proceed with an RCU-delayed free. + */ + if (waitqueue_active(wq_head)) + __wake_up_pollfree(wq_head); +} + #define ___wait_cond_timeout(condition) \ ({ \ bool __cond = (condition); \ diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 1646aa3e6779..e143c88bf4b0 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -171,6 +171,13 @@ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, void wwan_unregister_ops(struct device *parent); +#ifdef CONFIG_WWAN_DEBUGFS struct dentry *wwan_get_debugfs_dir(struct device *parent); +#else +static inline struct dentry *wwan_get_debugfs_dir(struct device *parent) +{ + return ERR_PTR(-ENODEV); +} +#endif #endif /* __WWAN_H */ diff --git a/include/net/bareudp.h b/include/net/bareudp.h index dc65a0d71d9b..17610c8d6361 100644 --- a/include/net/bareudp.h +++ b/include/net/bareudp.h @@ -3,21 +3,10 @@ #ifndef __NET_BAREUDP_H #define __NET_BAREUDP_H +#include <linux/netdevice.h> #include <linux/types.h> -#include <linux/skbuff.h> #include <net/rtnetlink.h> -struct bareudp_conf { - __be16 ethertype; - __be16 port; - u16 sport_min; - bool multi_proto_mode; -}; - -struct net_device *bareudp_dev_create(struct net *net, const char *name, - u8 name_assign_type, - struct bareudp_conf *info); - static inline bool netif_is_bareudp(const struct net_device *dev) { return dev->rtnl_link_ops && diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index f6af76c87a6c..191c36afa1f4 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -126,7 +126,7 @@ struct tlb_slave_info { struct alb_bond_info { struct tlb_client_info *tx_hashtbl; /* Dynamically allocated */ u32 unbalanced_load; - int tx_rebalance_counter; + atomic_t tx_rebalance_counter; int lp_counter; /* -------- rlb parameters -------- */ int rlb_enabled; diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 7994455ec714..c4898fcbf923 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -136,6 +136,19 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) sk_rx_queue_update(sk, skb); } +/* Variant of sk_mark_napi_id() for passive flow setup, + * as sk->sk_napi_id and sk->sk_rx_queue_mapping content + * needs to be set. + */ +static inline void sk_mark_napi_id_set(struct sock *sk, + const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + WRITE_ONCE(sk->sk_napi_id, skb->napi_id); +#endif + sk_rx_queue_set(sk, skb); +} + static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id) { #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/include/net/dsa.h b/include/net/dsa.h index 8ca9d50cbbc2..f16959444ae1 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -88,6 +88,8 @@ struct dsa_device_ops { struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); + int (*connect)(struct dsa_switch *ds); + void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; @@ -219,6 +221,12 @@ struct dsa_mall_tc_entry { }; }; +struct dsa_bridge { + struct net_device *dev; + unsigned int num; + bool tx_fwd_offload; + refcount_t refcount; +}; struct dsa_port { /* A CPU port is physically connected to a master device. @@ -256,8 +264,7 @@ struct dsa_port { /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ bool learning; u8 stp_state; - struct net_device *bridge_dev; - int bridge_num; + struct dsa_bridge *bridge; struct devlink_port devlink_port; bool devlink_port_setup; struct phylink *pl; @@ -269,12 +276,6 @@ struct dsa_port { struct list_head list; /* - * Give the switch driver somewhere to hang its per-port private data - * structures (accessible from the tagger). - */ - void *priv; - - /* * Original copy of the master netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; @@ -332,6 +333,8 @@ struct dsa_switch { */ void *priv; + void *tagger_data; + /* * Configuration data for this switch. */ @@ -413,12 +416,12 @@ struct dsa_switch { */ unsigned int num_lag_ids; - /* Drivers that support bridge forwarding offload should set this to - * the maximum number of bridges spanning the same switch tree (or all - * trees, in the case of cross-tree bridging support) that can be - * offloaded. + /* Drivers that support bridge forwarding offload or FDB isolation + * should set this to the maximum number of bridges spanning the same + * switch tree (or all trees, in the case of cross-tree bridging + * support) that can be offloaded. */ - unsigned int num_fwd_offloading_bridges; + unsigned int max_num_bridges; size_t num_ports; }; @@ -588,7 +591,7 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { - if (!dp->bridge_dev) + if (!dp->bridge) return NULL; if (dp->lag_dev) @@ -599,6 +602,76 @@ struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) return dp->slave; } +static inline struct net_device * +dsa_port_bridge_dev_get(const struct dsa_port *dp) +{ + return dp->bridge ? dp->bridge->dev : NULL; +} + +static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) +{ + return dp->bridge ? dp->bridge->num : 0; +} + +static inline bool dsa_port_bridge_same(const struct dsa_port *a, + const struct dsa_port *b) +{ + struct net_device *br_a = dsa_port_bridge_dev_get(a); + struct net_device *br_b = dsa_port_bridge_dev_get(b); + + /* Standalone ports are not in the same bridge with one another */ + return (!br_a || !br_b) ? false : (br_a == br_b); +} + +static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, + const struct net_device *dev) +{ + return dsa_port_to_bridge_port(dp) == dev; +} + +static inline bool +dsa_port_offloads_bridge_dev(struct dsa_port *dp, + const struct net_device *bridge_dev) +{ + /* DSA ports connected to a bridge, and event was emitted + * for the bridge. + */ + return dsa_port_bridge_dev_get(dp) == bridge_dev; +} + +static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, + const struct dsa_bridge *bridge) +{ + return dsa_port_bridge_dev_get(dp) == bridge->dev; +} + +/* Returns true if any port of this tree offloads the given net_device */ +static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, + const struct net_device *dev) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_offloads_bridge_port(dp, dev)) + return true; + + return false; +} + +/* Returns true if any port of this tree offloads the given bridge */ +static inline bool +dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, + const struct net_device *bridge_dev) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) + return true; + + return false; +} + typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { @@ -614,6 +687,13 @@ struct dsa_switch_ops { enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol proto); + /* + * Method for switch drivers to connect to the tagging protocol driver + * in current use. The switch driver can provide handlers for certain + * types of packets for switch management. + */ + int (*connect_tag_protocol)(struct dsa_switch *ds, + enum dsa_tag_protocol proto); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); @@ -748,17 +828,10 @@ struct dsa_switch_ops { */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, - struct net_device *bridge); + struct dsa_bridge bridge, + bool *tx_fwd_offload); void (*port_bridge_leave)(struct dsa_switch *ds, int port, - struct net_device *bridge); - /* Called right after .port_bridge_join() */ - int (*port_bridge_tx_fwd_offload)(struct dsa_switch *ds, int port, - struct net_device *bridge, - int bridge_num); - /* Called right before .port_bridge_leave() */ - void (*port_bridge_tx_fwd_unoffload)(struct dsa_switch *ds, int port, - struct net_device *bridge, - int bridge_num); + struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); void (*port_fast_age)(struct dsa_switch *ds, int port); @@ -830,10 +903,10 @@ struct dsa_switch_ops { */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, - struct net_device *br); + struct dsa_bridge bridge); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, - struct net_device *br); + struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index bd07484ab9dd..82da359bca03 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -91,7 +91,6 @@ struct fib_rules_ops { void (*flush_cache)(struct fib_rules_ops *ops); int nlgroup; - const struct nla_policy *policy; struct list_head rules_list; struct module *owner; struct net *fro_net; @@ -103,26 +102,6 @@ struct fib_rule_notifier_info { struct fib_rule *rule; }; -#define FRA_GENERIC_POLICY \ - [FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 }, \ - [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ - [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ - [FRA_PRIORITY] = { .type = NLA_U32 }, \ - [FRA_FWMARK] = { .type = NLA_U32 }, \ - [FRA_TUN_ID] = { .type = NLA_U64 }, \ - [FRA_FWMASK] = { .type = NLA_U32 }, \ - [FRA_TABLE] = { .type = NLA_U32 }, \ - [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ - [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ - [FRA_GOTO] = { .type = NLA_U32 }, \ - [FRA_L3MDEV] = { .type = NLA_U8 }, \ - [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }, \ - [FRA_PROTOCOL] = { .type = NLA_U8 }, \ - [FRA_IP_PROTO] = { .type = NLA_U8 }, \ - [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, \ - [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) } - - static inline void fib_rule_get(struct fib_rule *rule) { refcount_inc(&rule->refcnt); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index bb5fa5914032..5b61c462e534 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -34,6 +34,7 @@ #include <net/netns/smc.h> #include <net/netns/bpf.h> #include <net/netns/mctp.h> +#include <net/net_trackers.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> @@ -87,6 +88,7 @@ struct net { struct idr netns_ids; struct ns_common ns; + struct ref_tracker_dir refcnt_tracker; struct list_head dev_base_head; struct proc_dir_entry *proc_net; @@ -240,6 +242,7 @@ void ipx_unregister_sysctl(void); #ifdef CONFIG_NET_NS void __put_net(struct net *net); +/* Try using get_net_track() instead */ static inline struct net *get_net(struct net *net) { refcount_inc(&net->ns.count); @@ -258,6 +261,7 @@ static inline struct net *maybe_get_net(struct net *net) return net; } +/* Try using put_net_track() instead */ static inline void put_net(struct net *net) { if (refcount_dec_and_test(&net->ns.count)) @@ -308,6 +312,36 @@ static inline int check_net(const struct net *net) #endif +static inline void netns_tracker_alloc(struct net *net, + netns_tracker *tracker, gfp_t gfp) +{ +#ifdef CONFIG_NET_NS_REFCNT_TRACKER + ref_tracker_alloc(&net->refcnt_tracker, tracker, gfp); +#endif +} + +static inline void netns_tracker_free(struct net *net, + netns_tracker *tracker) +{ +#ifdef CONFIG_NET_NS_REFCNT_TRACKER + ref_tracker_free(&net->refcnt_tracker, tracker); +#endif +} + +static inline struct net *get_net_track(struct net *net, + netns_tracker *tracker, gfp_t gfp) +{ + get_net(net); + netns_tracker_alloc(net, tracker, gfp); + return net; +} + +static inline void put_net_track(struct net *net, netns_tracker *tracker) +{ + netns_tracker_free(net, tracker); + put_net(net); +} + typedef struct { #ifdef CONFIG_NET_NS struct net *net; diff --git a/include/net/net_trackers.h b/include/net/net_trackers.h new file mode 100644 index 000000000000..d94c76cf15a9 --- /dev/null +++ b/include/net/net_trackers.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_NET_TRACKERS_H +#define __NET_NET_TRACKERS_H +#include <linux/ref_tracker.h> + +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER +typedef struct ref_tracker *netdevice_tracker; +#else +typedef struct {} netdevice_tracker; +#endif + +#ifdef CONFIG_NET_NS_REFCNT_TRACKER +typedef struct ref_tracker *netns_tracker; +#else +typedef struct {} netns_tracker; +#endif + +#endif /* __NET_NET_TRACKERS_H */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index cc663c68ddc4..d24b0a34c8f0 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -276,14 +276,14 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb) /* jiffies until ct expires, 0 if already expired */ static inline unsigned long nf_ct_expires(const struct nf_conn *ct) { - s32 timeout = ct->timeout - nfct_time_stamp; + s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp; return timeout > 0 ? timeout : 0; } static inline bool nf_ct_is_expired(const struct nf_conn *ct) { - return (__s32)(ct->timeout - nfct_time_stamp) <= 0; + return (__s32)(READ_ONCE(ct->timeout) - nfct_time_stamp) <= 0; } /* use after obtaining a reference count */ @@ -302,7 +302,7 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct) static inline void nf_ct_offload_timeout(struct nf_conn *ct) { if (nf_ct_expires(ct) < NF_CT_DAY / 2) - ct->timeout = nfct_time_stamp + NF_CT_DAY; + WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY); } struct kernel_param; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 193f88ebf629..cebc1bd713b6 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -202,7 +202,8 @@ struct tcf_exts { __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ int nr_actions; struct tc_action **actions; - struct net *net; + struct net *net; + netns_tracker ns_tracker; #endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. @@ -218,6 +219,7 @@ static inline int tcf_exts_init(struct tcf_exts *exts, struct net *net, exts->type = 0; exts->nr_actions = 0; exts->net = net; + netns_tracker_alloc(net, &exts->ns_tracker, GFP_KERNEL); exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *), GFP_KERNEL); if (!exts->actions) @@ -236,6 +238,8 @@ static inline bool tcf_exts_get_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT exts->net = maybe_get_net(exts->net); + if (exts->net) + netns_tracker_alloc(exts->net, &exts->ns_tracker, GFP_KERNEL); return exts->net != NULL; #else return true; @@ -246,7 +250,7 @@ static inline void tcf_exts_put_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT if (exts->net) - put_net(exts->net); + put_net_track(exts->net, &exts->ns_tracker); #endif } diff --git a/include/net/sock.h b/include/net/sock.h index ae61cd0b650d..37f878564d25 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -350,6 +350,7 @@ struct bpf_local_storage; * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags + * @ns_tracker: tracker for netns reference */ struct sock { /* @@ -538,6 +539,7 @@ struct sock { struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; + netns_tracker ns_tracker; }; enum sk_pacing { @@ -1633,16 +1635,6 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) __sk_mem_reclaim(sk, SK_RECLAIM_CHUNK); } -static inline void sock_release_ownership(struct sock *sk) -{ - if (sk->sk_lock.owned) { - sk->sk_lock.owned = 0; - - /* The sk_lock has mutex_unlock() semantics: */ - mutex_release(&sk->sk_lock.dep_map, _RET_IP_); - } -} - /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. @@ -1769,12 +1761,23 @@ static inline bool sock_owned_by_user_nocheck(const struct sock *sk) return sk->sk_lock.owned; } +static inline void sock_release_ownership(struct sock *sk) +{ + if (sock_owned_by_user_nocheck(sk)) { + sk->sk_lock.owned = 0; + + /* The sk_lock has mutex_unlock() semantics: */ + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); + } +} + /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { struct sock *sk = (struct sock *)csk; - return !sk->sk_lock.owned && !spin_is_locked(&sk->sk_lock.slock); + return !sock_owned_by_user_nocheck(sk) && + !spin_is_locked(&sk->sk_lock.slock); } struct sock *sk_alloc(struct net *net, int family, gfp_t priority, diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 2308210793a0..83b46da8873d 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -128,6 +128,7 @@ struct xfrm_state_walk { struct xfrm_state_offload { struct net_device *dev; + netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; unsigned int num_exthdrs; @@ -1913,7 +1914,7 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(x); xso->dev = NULL; - dev_put(dev); + dev_put_track(dev, &xso->dev_tracker); } } #else diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 33f2e8c9e88b..3e9454b00562 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -118,6 +118,7 @@ enum ocelot_target { S2, HSIO, PTP, + FDMA, GCB, DEV_GMII, TARGET_MAX, @@ -732,6 +733,8 @@ struct ocelot { /* Protects the PTP clock */ spinlock_t ptp_clock_lock; struct ptp_pin_desc ptp_pins[OCELOT_PTP_PINS_NUM]; + + struct ocelot_fdma *fdma; }; struct ocelot_policer { @@ -794,8 +797,11 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); +void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag); int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); +void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, + u64 timestamp); /* Hardware initialization */ int ocelot_regfields_init(struct ocelot *ocelot, diff --git a/include/soc/mscc/vsc7514_regs.h b/include/soc/mscc/vsc7514_regs.h index 98743e252012..ceee26c96959 100644 --- a/include/soc/mscc/vsc7514_regs.h +++ b/include/soc/mscc/vsc7514_regs.h @@ -8,6 +8,8 @@ #ifndef VSC7514_REGS_H #define VSC7514_REGS_H +#include <soc/mscc/ocelot_vcap.h> + extern const u32 vsc7514_ana_regmap[]; extern const u32 vsc7514_qs_regmap[]; extern const u32 vsc7514_qsys_regmap[]; diff --git a/include/uapi/asm-generic/poll.h b/include/uapi/asm-generic/poll.h index 41b509f410bf..f9c520ce4bf4 100644 --- a/include/uapi/asm-generic/poll.h +++ b/include/uapi/asm-generic/poll.h @@ -29,7 +29,7 @@ #define POLLRDHUP 0x2000 #endif -#define POLLFREE (__force __poll_t)0x4000 /* currently only for epoll */ +#define POLLFREE (__force __poll_t)0x4000 #define POLL_BUSY_LOOP (__force __poll_t)0x8000 diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index a13e20cc66b4..0512fde5e697 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -196,6 +196,13 @@ struct drm_virtgpu_context_init { __u64 ctx_set_params; }; +/* + * Event code that's given when VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is in + * effect. The event size is sizeof(drm_event), since there is no additional + * payload. + */ +#define VIRTGPU_EVENT_FENCE_SIGNALED 0x90000000 + #define DRM_IOCTL_VIRTGPU_MAP \ DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6297eafdc40f..c26871263f1f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1342,8 +1342,10 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; - __u32 :32; /* pad */ + __u32 core_relo_cnt; /* number of bpf_core_relo */ __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1744,7 +1746,7 @@ union bpf_attr { * if the maximum number of tail calls has been reached for this * chain of programs. This limit is defined in the kernel by the * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), - * which is currently set to 32. + * which is currently set to 33. * Return * 0 on success, or a negative error in case of failure. * @@ -4957,6 +4959,30 @@ union bpf_attr { * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. * **-EBUSY** if failed to try lock mmap_lock. * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5140,6 +5166,7 @@ union bpf_attr { FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ FN(find_vma), \ + FN(loop), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -6349,4 +6376,78 @@ enum { BTF_F_ZERO = (1ULL << 3), }; +/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value + * has to be adjusted by relocations. It is emitted by llvm and passed to + * libbpf and later to the kernel. + */ +enum bpf_core_relo_kind { + BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */ + BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ + BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ + BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ + BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ + BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */ + BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */ + BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ + BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ + BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ +}; + +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index c8cc46f80a16..f106a3941cdf 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -136,19 +136,21 @@ struct mptcp_info { * MPTCP_EVENT_REMOVED: token, rem_id * An address has been lost by the peer. * - * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, - * if_idx [, error] + * MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, + * saddr4 | saddr6, daddr4 | daddr6, sport, + * dport, backup, if_idx [, error] * A new subflow has been established. 'error' should not be set. * - * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] + * MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] * A subflow has been closed. An error (copy of sk_err) could be set if an * error has been detected for this subflow. * - * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, backup, if_idx [, error] - * The priority of a subflow has changed. 'error' should not be set. + * MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx + * [, error] + * The priority of a subflow has changed. 'error' should not be set. */ enum mptcp_event_type { MPTCP_EVENT_UNSPEC = 0, diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index fcc61c73a666..e258e52cfd1f 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -62,7 +62,7 @@ struct so_timestamping { /** * struct hwtstamp_config - %SIOCGHWTSTAMP and %SIOCSHWTSTAMP parameter * - * @flags: no flags defined right now, must be zero for %SIOCSHWTSTAMP + * @flags: one of HWTSTAMP_FLAG_* * @tx_type: one of HWTSTAMP_TX_* * @rx_filter: one of HWTSTAMP_FILTER_* * @@ -78,6 +78,20 @@ struct hwtstamp_config { int rx_filter; }; +/* possible values for hwtstamp_config->flags */ +enum hwtstamp_flags { + /* + * With this flag, the user could get bond active interface's + * PHC index. Note this PHC index is not stable as when there + * is a failover, the bond active interface will be changed, so + * will be the PHC index. + */ + HWTSTAMP_FLAG_BONDED_PHC_INDEX = (1<<0), + + HWTSTAMP_FLAG_LAST = HWTSTAMP_FLAG_BONDED_PHC_INDEX, + HWTSTAMP_FLAG_MASK = (HWTSTAMP_FLAG_LAST - 1) | HWTSTAMP_FLAG_LAST +}; + /* possible values for hwtstamp_config->tx_type */ enum hwtstamp_tx_types { /* diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h index 74ef57b38f9f..ac5d6a3031db 100644 --- a/include/uapi/linux/resource.h +++ b/include/uapi/linux/resource.h @@ -66,10 +66,17 @@ struct rlimit64 { #define _STK_LIM (8*1024*1024) /* - * GPG2 wants 64kB of mlocked memory, to make sure pass phrases - * and other sensitive information are never written to disk. + * Limit the amount of locked memory by some sane default: + * root can always increase this limit if needed. + * + * The main use-cases are (1) preventing sensitive memory + * from being swapped; (2) real-time operations; (3) via + * IOURING_REGISTER_BUFFERS. + * + * The first two don't need much. The latter will take as + * much as it can get. 8MB is a reasonably sane default. */ -#define MLOCK_LIMIT ((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024) +#define MLOCK_LIMIT (8*1024*1024) /* * Due to binary compatibility, the actual resource numbers diff --git a/kernel/audit.c b/kernel/audit.c index 121d37e700a6..4cebadb5f30d 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -718,7 +718,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, { int rc = 0; struct sk_buff *skb; - static unsigned int failed = 0; + unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ @@ -735,32 +735,30 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, continue; } +retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { - /* fatal failure for our queue flush attempt? */ + /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { - /* yes - error processing for the queue */ sk = NULL; if (err_hook) (*err_hook)(skb); - if (!skb_hook) - goto out; - /* keep processing with the skb_hook */ + if (rc == -EAGAIN) + rc = 0; + /* continue to drain the queue */ continue; } else - /* no - requeue to preserve ordering */ - skb_queue_head(queue, skb); + goto retry; } else { - /* it worked - drop the extra reference and continue */ + /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } -out: return (rc >= 0 ? 0 : rc); } @@ -1609,7 +1607,8 @@ static int __net_init audit_net_init(struct net *net) audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } - aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; + /* limit the timeout in case auditd is blocked/stopped */ + aunet->sk->sk_sndtimeo = HZ / 10; return 0; } diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index cf6ca339f3cd..c1a9be6a4b9f 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -36,3 +36,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o obj-${CONFIG_BPF_LSM} += bpf_lsm.o endif obj-$(CONFIG_BPF_PRELOAD) += preload/ + +obj-$(CONFIG_BPF_SYSCALL) += relo_core.o +$(obj)/relo_core.o: $(srctree)/tools/lib/bpf/relo_core.c FORCE + $(call if_changed_rule,cc_o_c) diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index b2ee45064e06..b7aef5b3416d 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -714,3 +714,38 @@ const struct bpf_func_proto bpf_for_each_map_elem_proto = { .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; + +/* maximum number of loops */ +#define MAX_LOOPS BIT(23) + +BPF_CALL_4(bpf_loop, u32, nr_loops, void *, callback_fn, void *, callback_ctx, + u64, flags) +{ + bpf_callback_t callback = (bpf_callback_t)callback_fn; + u64 ret; + u32 i; + + if (flags) + return -EINVAL; + if (nr_loops > MAX_LOOPS) + return -E2BIG; + + for (i = 0; i < nr_loops; i++) { + ret = callback((u64)i, (u64)(long)callback_ctx, 0, 0, 0); + /* return value: 0 - continue, 1 - stop and return */ + if (ret) + return i + 1; + } + + return i; +} + +const struct bpf_func_proto bpf_loop_proto = { + .func = bpf_loop, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_FUNC, + .arg3_type = ARG_PTR_TO_STACK_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 8ecfe4752769..21069dbe9138 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -165,7 +165,7 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) break; } - if (btf_member_bitfield_size(t, member)) { + if (__btf_member_bitfield_size(t, member)) { pr_warn("bit field member %s in struct %s is not supported\n", mname, st_ops->name); break; @@ -296,7 +296,7 @@ static int check_zero_holes(const struct btf_type *t, void *data) const struct btf_type *mtype; for_each_member(i, t, member) { - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (moff > prev_mend && memchr_inv(data + prev_mend, 0, moff - prev_mend)) return -EINVAL; @@ -387,7 +387,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_prog *prog; u32 moff; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); if (ptype == module_type) { if (*(void **)(udata + moff)) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 6b9d23be1e99..8b00c6e4d6fb 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -25,6 +25,7 @@ #include <linux/kobject.h> #include <linux/sysfs.h> #include <net/sock.h> +#include "../tools/lib/bpf/relo_core.h" /* BTF (BPF Type Format) is the meta data format which describes * the data types of BPF program/map. Hence, it basically focus @@ -836,7 +837,7 @@ static const char *btf_show_name(struct btf_show *show) const char *ptr_suffix = &ptr_suffixes[strlen(ptr_suffixes)]; const char *name = NULL, *prefix = "", *parens = ""; const struct btf_member *m = show->state.member; - const struct btf_type *t = show->state.type; + const struct btf_type *t; const struct btf_array *array; u32 id = show->state.type_id; const char *member = NULL; @@ -2969,7 +2970,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } - offset = btf_member_bit_offset(t, member); + offset = __btf_member_bit_offset(t, member); if (is_union && offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); @@ -3094,7 +3095,7 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t if (off != -ENOENT) /* only one such field is allowed */ return -E2BIG; - off = btf_member_bit_offset(t, member); + off = __btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ return -EINVAL; @@ -3184,8 +3185,8 @@ static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, btf_show_start_member(show, member); - member_offset = btf_member_bit_offset(t, member); - bitfield_size = btf_member_bitfield_size(t, member); + member_offset = __btf_member_bit_offset(t, member); + bitfield_size = __btf_member_bitfield_size(t, member); bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); bits8_offset = BITS_PER_BYTE_MASKED(member_offset); if (bitfield_size) { @@ -4472,8 +4473,7 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, log->len_total = log_size; /* log attributes have to be sane */ - if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || - !log->level || !log->ubuf) { + if (!bpf_verifier_log_attr_valid(log)) { err = -EINVAL; goto errout; } @@ -5060,7 +5060,7 @@ again: if (array_elem->nelems != 0) goto error; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (off < moff) goto error; @@ -5083,14 +5083,14 @@ error: for_each_member(i, t, member) { /* offset of the field in bytes */ - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (off + size <= moff) /* won't find anything, field is already too far */ break; - if (btf_member_bitfield_size(t, member)) { - u32 end_bit = btf_member_bit_offset(t, member) + - btf_member_bitfield_size(t, member); + if (__btf_member_bitfield_size(t, member)) { + u32 end_bit = __btf_member_bit_offset(t, member) + + __btf_member_bitfield_size(t, member); /* off <= moff instead of off == moff because clang * does not generate a BTF member for anonymous @@ -6169,6 +6169,8 @@ btf_module_read(struct file *file, struct kobject *kobj, return len; } +static void purge_cand_cache(struct btf *btf); + static int btf_module_notify(struct notifier_block *nb, unsigned long op, void *module) { @@ -6203,6 +6205,7 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, goto out; } + purge_cand_cache(NULL); mutex_lock(&btf_module_mutex); btf_mod->module = module; btf_mod->btf = btf; @@ -6245,6 +6248,7 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, list_del(&btf_mod->list); if (btf_mod->sysfs_attr) sysfs_remove_bin_file(btf_kobj, btf_mod->sysfs_attr); + purge_cand_cache(btf_mod->btf); btf_put(btf_mod->btf); kfree(btf_mod->sysfs_attr); kfree(btf_mod); @@ -6361,11 +6365,6 @@ BTF_TRACING_TYPE_xxx /* BTF ID set registration API for modules */ -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - #ifdef CONFIG_DEBUG_INFO_BTF_MODULES void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, @@ -6391,8 +6390,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, { struct kfunc_btf_id_set *s; - if (!owner) - return false; mutex_lock(&klist->mutex); list_for_each_entry(s, &klist->list, list) { if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) { @@ -6404,8 +6401,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, return false; } -#endif - #define DEFINE_KFUNC_BTF_ID_LIST(name) \ struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ __MUTEX_INITIALIZER(name.mutex) }; \ @@ -6413,3 +6408,387 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); + +#endif + +int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id) +{ + return -EOPNOTSUPP; +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} + +struct bpf_cand_cache { + const char *name; + u32 name_len; + u16 kind; + u16 cnt; + struct { + const struct btf *btf; + u32 id; + } cands[]; +}; + +static void bpf_free_cands(struct bpf_cand_cache *cands) +{ + if (!cands->cnt) + /* empty candidate array was allocated on stack */ + return; + kfree(cands); +} + +static void bpf_free_cands_from_cache(struct bpf_cand_cache *cands) +{ + kfree(cands->name); + kfree(cands); +} + +#define VMLINUX_CAND_CACHE_SIZE 31 +static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE]; + +#define MODULE_CAND_CACHE_SIZE 31 +static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE]; + +static DEFINE_MUTEX(cand_cache_mutex); + +static void __print_cand_cache(struct bpf_verifier_log *log, + struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache *cc; + int i, j; + + for (i = 0; i < cache_size; i++) { + cc = cache[i]; + if (!cc) + continue; + bpf_log(log, "[%d]%s(", i, cc->name); + for (j = 0; j < cc->cnt; j++) { + bpf_log(log, "%d", cc->cands[j].id); + if (j < cc->cnt - 1) + bpf_log(log, " "); + } + bpf_log(log, "), "); + } +} + +static void print_cand_cache(struct bpf_verifier_log *log) +{ + mutex_lock(&cand_cache_mutex); + bpf_log(log, "vmlinux_cand_cache:"); + __print_cand_cache(log, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); + bpf_log(log, "\nmodule_cand_cache:"); + __print_cand_cache(log, module_cand_cache, MODULE_CAND_CACHE_SIZE); + bpf_log(log, "\n"); + mutex_unlock(&cand_cache_mutex); +} + +static u32 hash_cands(struct bpf_cand_cache *cands) +{ + return jhash(cands->name, cands->name_len, 0); +} + +static struct bpf_cand_cache *check_cand_cache(struct bpf_cand_cache *cands, + struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache *cc = cache[hash_cands(cands) % cache_size]; + + if (cc && cc->name_len == cands->name_len && + !strncmp(cc->name, cands->name, cands->name_len)) + return cc; + return NULL; +} + +static size_t sizeof_cands(int cnt) +{ + return offsetof(struct bpf_cand_cache, cands[cnt]); +} + +static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands, + struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache **cc = &cache[hash_cands(cands) % cache_size], *new_cands; + + if (*cc) { + bpf_free_cands_from_cache(*cc); + *cc = NULL; + } + new_cands = kmalloc(sizeof_cands(cands->cnt), GFP_KERNEL); + if (!new_cands) { + bpf_free_cands(cands); + return ERR_PTR(-ENOMEM); + } + memcpy(new_cands, cands, sizeof_cands(cands->cnt)); + /* strdup the name, since it will stay in cache. + * the cands->name points to strings in prog's BTF and the prog can be unloaded. + */ + new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL); + bpf_free_cands(cands); + if (!new_cands->name) { + kfree(new_cands); + return ERR_PTR(-ENOMEM); + } + *cc = new_cands; + return new_cands; +} + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES +static void __purge_cand_cache(struct btf *btf, struct bpf_cand_cache **cache, + int cache_size) +{ + struct bpf_cand_cache *cc; + int i, j; + + for (i = 0; i < cache_size; i++) { + cc = cache[i]; + if (!cc) + continue; + if (!btf) { + /* when new module is loaded purge all of module_cand_cache, + * since new module might have candidates with the name + * that matches cached cands. + */ + bpf_free_cands_from_cache(cc); + cache[i] = NULL; + continue; + } + /* when module is unloaded purge cache entries + * that match module's btf + */ + for (j = 0; j < cc->cnt; j++) + if (cc->cands[j].btf == btf) { + bpf_free_cands_from_cache(cc); + cache[i] = NULL; + break; + } + } + +} + +static void purge_cand_cache(struct btf *btf) +{ + mutex_lock(&cand_cache_mutex); + __purge_cand_cache(btf, module_cand_cache, MODULE_CAND_CACHE_SIZE); + mutex_unlock(&cand_cache_mutex); +} +#endif + +static struct bpf_cand_cache * +bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf, + int targ_start_id) +{ + struct bpf_cand_cache *new_cands; + const struct btf_type *t; + const char *targ_name; + size_t targ_essent_len; + int n, i; + + n = btf_nr_types(targ_btf); + for (i = targ_start_id; i < n; i++) { + t = btf_type_by_id(targ_btf, i); + if (btf_kind(t) != cands->kind) + continue; + + targ_name = btf_name_by_offset(targ_btf, t->name_off); + if (!targ_name) + continue; + + /* the resched point is before strncmp to make sure that search + * for non-existing name will have a chance to schedule(). + */ + cond_resched(); + + if (strncmp(cands->name, targ_name, cands->name_len) != 0) + continue; + + targ_essent_len = bpf_core_essential_name_len(targ_name); + if (targ_essent_len != cands->name_len) + continue; + + /* most of the time there is only one candidate for a given kind+name pair */ + new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL); + if (!new_cands) { + bpf_free_cands(cands); + return ERR_PTR(-ENOMEM); + } + + memcpy(new_cands, cands, sizeof_cands(cands->cnt)); + bpf_free_cands(cands); + cands = new_cands; + cands->cands[cands->cnt].btf = targ_btf; + cands->cands[cands->cnt].id = i; + cands->cnt++; + } + return cands; +} + +static struct bpf_cand_cache * +bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id) +{ + struct bpf_cand_cache *cands, *cc, local_cand = {}; + const struct btf *local_btf = ctx->btf; + const struct btf_type *local_type; + const struct btf *main_btf; + size_t local_essent_len; + struct btf *mod_btf; + const char *name; + int id; + + main_btf = bpf_get_btf_vmlinux(); + if (IS_ERR(main_btf)) + return (void *)main_btf; + + local_type = btf_type_by_id(local_btf, local_type_id); + if (!local_type) + return ERR_PTR(-EINVAL); + + name = btf_name_by_offset(local_btf, local_type->name_off); + if (str_is_empty(name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(name); + + cands = &local_cand; + cands->name = name; + cands->kind = btf_kind(local_type); + cands->name_len = local_essent_len; + + cc = check_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); + /* cands is a pointer to stack here */ + if (cc) { + if (cc->cnt) + return cc; + goto check_modules; + } + + /* Attempt to find target candidates in vmlinux BTF first */ + cands = bpf_core_add_cands(cands, main_btf, 1); + if (IS_ERR(cands)) + return cands; + + /* cands is a pointer to kmalloced memory here if cands->cnt > 0 */ + + /* populate cache even when cands->cnt == 0 */ + cc = populate_cand_cache(cands, vmlinux_cand_cache, VMLINUX_CAND_CACHE_SIZE); + if (IS_ERR(cc)) + return cc; + + /* if vmlinux BTF has any candidate, don't go for module BTFs */ + if (cc->cnt) + return cc; + +check_modules: + /* cands is a pointer to stack here and cands->cnt == 0 */ + cc = check_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); + if (cc) + /* if cache has it return it even if cc->cnt == 0 */ + return cc; + + /* If candidate is not found in vmlinux's BTF then search in module's BTFs */ + spin_lock_bh(&btf_idr_lock); + idr_for_each_entry(&btf_idr, mod_btf, id) { + if (!btf_is_module(mod_btf)) + continue; + /* linear search could be slow hence unlock/lock + * the IDR to avoiding holding it for too long + */ + btf_get(mod_btf); + spin_unlock_bh(&btf_idr_lock); + cands = bpf_core_add_cands(cands, mod_btf, btf_nr_types(main_btf)); + if (IS_ERR(cands)) { + btf_put(mod_btf); + return cands; + } + spin_lock_bh(&btf_idr_lock); + btf_put(mod_btf); + } + spin_unlock_bh(&btf_idr_lock); + /* cands is a pointer to kmalloced memory here if cands->cnt > 0 + * or pointer to stack if cands->cnd == 0. + * Copy it into the cache even when cands->cnt == 0 and + * return the result. + */ + return populate_cand_cache(cands, module_cand_cache, MODULE_CAND_CACHE_SIZE); +} + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn) +{ + bool need_cands = relo->kind != BPF_CORE_TYPE_ID_LOCAL; + struct bpf_core_cand_list cands = {}; + struct bpf_core_spec *specs; + int err; + + /* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5" + * into arrays of btf_ids of struct fields and array indices. + */ + specs = kcalloc(3, sizeof(*specs), GFP_KERNEL); + if (!specs) + return -ENOMEM; + + if (need_cands) { + struct bpf_cand_cache *cc; + int i; + + mutex_lock(&cand_cache_mutex); + cc = bpf_core_find_cands(ctx, relo->type_id); + if (IS_ERR(cc)) { + bpf_log(ctx->log, "target candidate search failed for %d\n", + relo->type_id); + err = PTR_ERR(cc); + goto out; + } + if (cc->cnt) { + cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL); + if (!cands.cands) { + err = -ENOMEM; + goto out; + } + } + for (i = 0; i < cc->cnt; i++) { + bpf_log(ctx->log, + "CO-RE relocating %s %s: found target candidate [%d]\n", + btf_kind_str[cc->kind], cc->name, cc->cands[i].id); + cands.cands[i].btf = cc->cands[i].btf; + cands.cands[i].id = cc->cands[i].id; + } + cands.len = cc->cnt; + /* cand_cache_mutex needs to span the cache lookup and + * copy of btf pointer into bpf_core_cand_list, + * since module can be unloaded while bpf_core_apply_relo_insn + * is working with module's btf. + */ + } + + err = bpf_core_apply_relo_insn((void *)ctx->log, insn, relo->insn_off / 8, + relo, relo_idx, ctx->btf, &cands, specs); +out: + kfree(specs); + if (need_cands) { + kfree(cands.cands); + mutex_unlock(&cand_cache_mutex); + if (ctx->log->level & BPF_LOG_LEVEL2) + print_cand_cache(ctx->log); + } + return err; +} diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 2405e39d800f..de3e5bc6781f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1574,7 +1574,8 @@ select_insn: if (unlikely(index >= array->map.max_entries)) goto out; - if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT)) + + if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; @@ -1891,7 +1892,7 @@ static void bpf_prog_select_func(struct bpf_prog *fp) /** * bpf_prog_select_runtime - select exec runtime for BPF program - * @fp: bpf_prog populated with internal BPF program + * @fp: bpf_prog populated with BPF program * @err: pointer to error variable * * Try to JIT eBPF program, if JIT is not available, use interpreter. @@ -2300,7 +2301,6 @@ static void bpf_prog_free_deferred(struct work_struct *work) } } -/* Free internal BPF program */ void bpf_prog_free(struct bpf_prog *fp) { struct bpf_prog_aux *aux = fp->aux; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 649f07623df6..19fecfeaa9c2 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1376,6 +1376,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ringbuf_query_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; + case BPF_FUNC_loop: + return &bpf_loop_proto; default: break; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1033ee8c0caf..ddd81d543203 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2198,7 +2198,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD fd_array +#define BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) { @@ -4819,7 +4819,7 @@ const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, - .arg2_type = ARG_CONST_SIZE, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 88fe97d35166..cd79bb12d076 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -293,13 +293,15 @@ void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, "verifier log line truncated - local buffer too short\n"); - n = min(log->len_total - log->len_used - 1, n); - log->kbuf[n] = '\0'; - if (log->level == BPF_LOG_KERNEL) { - pr_err("BPF:%s\n", log->kbuf); + bool newline = n > 0 && log->kbuf[n - 1] == '\n'; + + pr_err("BPF: %s%s", log->kbuf, newline ? "" : "\n"); return; } + + n = min(log->len_total - log->len_used - 1, n); + log->kbuf[n] = '\0'; if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) log->len_used += n; else @@ -1366,22 +1368,28 @@ static void __reg_bound_offset(struct bpf_reg_state *reg) reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); } +static bool __reg32_bound_s64(s32 a) +{ + return a >= 0 && a <= S32_MAX; +} + static void __reg_assign_32_into_64(struct bpf_reg_state *reg) { reg->umin_value = reg->u32_min_value; reg->umax_value = reg->u32_max_value; - /* Attempt to pull 32-bit signed bounds into 64-bit bounds - * but must be positive otherwise set to worse case bounds - * and refine later from tnum. + + /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must + * be positive otherwise set to worse case bounds and refine later + * from tnum. */ - if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0) - reg->smax_value = reg->s32_max_value; - else - reg->smax_value = U32_MAX; - if (reg->s32_min_value >= 0) + if (__reg32_bound_s64(reg->s32_min_value) && + __reg32_bound_s64(reg->s32_max_value)) { reg->smin_value = reg->s32_min_value; - else + reg->smax_value = reg->s32_max_value; + } else { reg->smin_value = 0; + reg->smax_value = U32_MAX; + } } static void __reg_combine_32_into_64(struct bpf_reg_state *reg) @@ -2379,8 +2387,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ if (insn->src_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; /* dreg = *(u64 *)[fp - off] was a fill from the stack. * that [fp - off] slot contains scalar that needs to be @@ -2403,8 +2409,6 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, /* scalars can only be spilled into stack */ if (insn->dst_reg != BPF_REG_FP) return 0; - if (BPF_SIZE(insn->code) != BPF_DW) - return 0; spi = (-insn->off - 1) / BPF_REG_SIZE; if (spi >= 64) { verbose(env, "BUG spi %d\n", spi); @@ -4551,9 +4555,16 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i if (insn->imm == BPF_CMPXCHG) { /* Check comparison of R0 with memory location */ - err = check_reg_arg(env, BPF_REG_0, SRC_OP); + const u32 aux_reg = BPF_REG_0; + + err = check_reg_arg(env, aux_reg, SRC_OP); if (err) return err; + + if (is_pointer_value(env, aux_reg)) { + verbose(env, "R%d leaks addr into mem\n", aux_reg); + return -EACCES; + } } if (is_pointer_value(env, insn->src_reg)) { @@ -4588,13 +4599,19 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i load_reg = -1; } - /* check whether we can read the memory */ + /* Check whether we can read the memory, with second call for fetch + * case to simulate the register fill. + */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, load_reg, true); + BPF_SIZE(insn->code), BPF_READ, -1, true); + if (!err && load_reg >= 0) + err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, + BPF_SIZE(insn->code), BPF_READ, load_reg, + true); if (err) return err; - /* check whether we can write into the same memory */ + /* Check whether we can write into the same memory. */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -1, true); if (err) @@ -6101,6 +6118,27 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_loop_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, + * u64 flags); + * callback_fn(u32 index, void *callback_ctx); + */ + callee->regs[BPF_REG_1].type = SCALAR_VALUE; + callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + + callee->in_callback_fn = true; + return 0; +} + static int set_timer_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, @@ -6474,13 +6512,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return err; } - if (func_id == BPF_FUNC_tail_call) { - err = check_reference_leak(env); - if (err) { - verbose(env, "tail_call would lead to reference leak\n"); - return err; - } - } else if (is_release_function(func_id)) { + if (is_release_function(func_id)) { err = release_reference(env, meta.ref_obj_id); if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", @@ -6491,42 +6523,47 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs = cur_regs(env); - /* check that flags argument in get_local_storage(map, flags) is 0, - * this is required because get_local_storage() can't return an error. - */ - if (func_id == BPF_FUNC_get_local_storage && - !register_is_null(®s[BPF_REG_2])) { - verbose(env, "get_local_storage() doesn't support non-zero flags\n"); - return -EINVAL; - } - - if (func_id == BPF_FUNC_for_each_map_elem) { + switch (func_id) { + case BPF_FUNC_tail_call: + err = check_reference_leak(env); + if (err) { + verbose(env, "tail_call would lead to reference leak\n"); + return err; + } + break; + case BPF_FUNC_get_local_storage: + /* check that flags argument in get_local_storage(map, flags) is 0, + * this is required because get_local_storage() can't return an error. + */ + if (!register_is_null(®s[BPF_REG_2])) { + verbose(env, "get_local_storage() doesn't support non-zero flags\n"); + return -EINVAL; + } + break; + case BPF_FUNC_for_each_map_elem: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_map_elem_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_timer_set_callback) { + break; + case BPF_FUNC_timer_set_callback: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_timer_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_find_vma) { + break; + case BPF_FUNC_find_vma: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_find_vma_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_snprintf) { + break; + case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); - if (err < 0) - return err; + break; + case BPF_FUNC_loop: + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_loop_callback_state); + break; } + if (err) + return err; + /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); @@ -8342,6 +8379,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->dst_reg); } zext_32_to_64(dst_reg); + + __update_reg_bounds(dst_reg); + __reg_deduce_bounds(dst_reg); + __reg_bound_offset(dst_reg); } } else { /* case: R = imm @@ -8456,7 +8497,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, new_range = dst_reg->off; if (range_right_open) - new_range--; + new_range++; /* Examples for register markings: * @@ -10267,6 +10308,78 @@ err_free: return err; } +#define MIN_CORE_RELO_SIZE sizeof(struct bpf_core_relo) +#define MAX_CORE_RELO_SIZE MAX_FUNCINFO_REC_SIZE + +static int check_core_relo(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) +{ + u32 i, nr_core_relo, ncopy, expected_size, rec_size; + struct bpf_core_relo core_relo = {}; + struct bpf_prog *prog = env->prog; + const struct btf *btf = prog->aux->btf; + struct bpf_core_ctx ctx = { + .log = &env->log, + .btf = btf, + }; + bpfptr_t u_core_relo; + int err; + + nr_core_relo = attr->core_relo_cnt; + if (!nr_core_relo) + return 0; + if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo)) + return -EINVAL; + + rec_size = attr->core_relo_rec_size; + if (rec_size < MIN_CORE_RELO_SIZE || + rec_size > MAX_CORE_RELO_SIZE || + rec_size % sizeof(u32)) + return -EINVAL; + + u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel); + expected_size = sizeof(struct bpf_core_relo); + ncopy = min_t(u32, expected_size, rec_size); + + /* Unlike func_info and line_info, copy and apply each CO-RE + * relocation record one at a time. + */ + for (i = 0; i < nr_core_relo; i++) { + /* future proofing when sizeof(bpf_core_relo) changes */ + err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size); + if (err) { + if (err == -E2BIG) { + verbose(env, "nonzero tailing record in core_relo"); + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, core_relo_rec_size), + &expected_size, sizeof(expected_size))) + err = -EFAULT; + } + break; + } + + if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) { + err = -EFAULT; + break; + } + + if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) { + verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n", + i, core_relo.insn_off, prog->len); + err = -EINVAL; + break; + } + + err = bpf_core_apply(&ctx, &core_relo, i, + &prog->insnsi[core_relo.insn_off / 8]); + if (err) + break; + bpfptr_add(&u_core_relo, rec_size); + } + return err; +} + static int check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) @@ -10297,6 +10410,10 @@ static int check_btf_info(struct bpf_verifier_env *env, if (err) return err; + err = check_core_relo(env, attr, uattr); + if (err) + return err; + return 0; } @@ -13975,11 +14092,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) log->ubuf = (char __user *) (unsigned long) attr->log_buf; log->len_total = attr->log_size; - ret = -EINVAL; /* log attributes have to be sane */ - if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 || - !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK) + if (!bpf_verifier_log_attr_valid(log)) { + ret = -EINVAL; goto err_unlock; + } } if (IS_ERR(btf_vmlinux)) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 76f9deeaa942..77563109c0ea 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1918,7 +1918,7 @@ static void __init init_uclamp_rq(struct rq *rq) }; } - rq->uclamp_flags = 0; + rq->uclamp_flags = UCLAMP_FLAG_IDLE; } static void __init init_uclamp(void) @@ -6617,11 +6617,11 @@ static int __init setup_preempt_mode(char *str) int mode = sched_dynamic_mode(str); if (mode < 0) { pr_warn("Dynamic Preempt: unsupported mode: %s\n", str); - return 1; + return 0; } sched_dynamic_update(mode); - return 0; + return 1; } __setup("preempt=", setup_preempt_mode); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 872e481d5098..9392aea1804e 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) .sum_exec_runtime = p->se.sum_exec_runtime, }; - task_cputime(p, &cputime.utime, &cputime.stime); + if (task_cputime(p, &cputime.utime, &cputime.stime)) + cputime.sum_exec_runtime = task_sched_runtime(p); cputime_adjust(&cputime, &p->prev_cputime, ut, st); } EXPORT_SYMBOL_GPL(task_cputime_adjusted); @@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t) * add up the pending nohz execution time since the last * cputime snapshot. */ -void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) +bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { struct vtime *vtime = &t->vtime; unsigned int seq; u64 delta; + int ret; if (!vtime_accounting_enabled()) { *utime = t->utime; *stime = t->stime; - return; + return false; } do { + ret = false; seq = read_seqcount_begin(&vtime->seqcount); *utime = t->utime; @@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) if (vtime->state < VTIME_SYS) continue; + ret = true; delta = vtime_delta(vtime); /* @@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) else *utime += vtime->utime + delta; } while (read_seqcount_retry(&vtime->seqcount, seq)); + + return ret; } static int vtime_state_fetch(struct vtime *vtime, int cpu) diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 76577d1642a5..eca38107b32f 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -238,6 +238,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode) } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ +void __wake_up_pollfree(struct wait_queue_head *wq_head) +{ + __wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE)); + /* POLLFREE must have cleared the queue. */ + WARN_ON_ONCE(waitqueue_active(wq_head)); +} + /* * Note: we use "set_current_state()" _after_ the wait-queue add, * because we need a memory barrier there on SMP, so that any diff --git a/kernel/softirq.c b/kernel/softirq.c index 322b65d45676..41f470929e99 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -595,7 +595,8 @@ void irq_enter_rcu(void) { __irq_enter_raw(); - if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)) + if (tick_nohz_full_cpu(smp_processor_id()) || + (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))) tick_irq_enter(); account_hardirq_enter(current); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6bffe5af8cb1..17a283ce2b20 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void) now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(ts, now); + /* + * If all CPUs are idle. We may need to update a stale jiffies value. + * Note nohz_full is a special case: a timekeeper is guaranteed to stay + * alive but it might be busy looping with interrupts disabled in some + * rare case (typically stop machine). So we must make sure we have a + * last resort. + */ if (ts->tick_stopped) tick_nohz_update_jiffies(now); } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index e3d2c23c413d..85f1021ad459 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsigned int msecs) EXPORT_SYMBOL(msleep_interruptible); /** - * usleep_range - Sleep for an approximate time - * @min: Minimum time in usecs to sleep - * @max: Maximum time in usecs to sleep + * usleep_range_state - Sleep for an approximate time in a given state + * @min: Minimum time in usecs to sleep + * @max: Maximum time in usecs to sleep + * @state: State of the current task that will be while sleeping * * In non-atomic context where the exact wakeup time is flexible, use - * usleep_range() instead of udelay(). The sleep improves responsiveness + * usleep_range_state() instead of udelay(). The sleep improves responsiveness * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces * power usage by allowing hrtimers to take advantage of an already- * scheduled interrupt instead of scheduling a new one just for this sleep. */ -void __sched usleep_range(unsigned long min, unsigned long max) +void __sched usleep_range_state(unsigned long min, unsigned long max, + unsigned int state) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; for (;;) { - __set_current_state(TASK_UNINTERRUPTIBLE); + __set_current_state(state); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } -EXPORT_SYMBOL(usleep_range); +EXPORT_SYMBOL(usleep_range_state); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1cd647c010da..623dd0684429 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1402,9 +1402,6 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, void *, buf, u32, size, u64, flags) { -#ifndef CONFIG_X86 - return -ENOENT; -#else static const u32 br_entry_size = sizeof(struct perf_branch_entry); struct perf_branch_stack *br_stack = ctx->data->br_stack; u32 to_copy; @@ -1413,7 +1410,7 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, return -EINVAL; if (unlikely(!br_stack)) - return -EINVAL; + return -ENOENT; if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE) return br_stack->nr * br_entry_size; @@ -1425,7 +1422,6 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, memcpy(buf, br_stack->entries, to_copy); return to_copy; -#endif } static const struct bpf_func_proto bpf_read_branch_records_proto = { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 30bc880c3849..be5f6b32a012 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5217,6 +5217,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) { struct ftrace_direct_func *direct; struct ftrace_func_entry *entry; + struct ftrace_hash *hash; int ret = -ENODEV; mutex_lock(&direct_mutex); @@ -5225,7 +5226,8 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) if (!entry) goto out_unlock; - if (direct_functions->count == 1) + hash = direct_ops.func_hash->filter_hash; + if (hash->count == 1) unregister_ftrace_function(&direct_ops); ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0); @@ -5540,6 +5542,10 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) err = unregister_ftrace_function(ops); remove_direct_functions_hash(hash, addr); mutex_unlock(&direct_mutex); + + /* cleanup for possible another register call */ + ops->func = NULL; + ops->trampoline = 0; return err; } EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi); diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 22db3ce95e74..ca9c13b2ecf4 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1237,9 +1237,8 @@ static int __create_synth_event(const char *name, const char *raw_fields) argv + consumed, &consumed, &field_version); if (IS_ERR(field)) { - argv_free(argv); ret = PTR_ERR(field); - goto err; + goto err_free_arg; } /* @@ -1262,18 +1261,19 @@ static int __create_synth_event(const char *name, const char *raw_fields) if (cmd_version > 1 && n_fields_this_loop >= 1) { synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str)); ret = -EINVAL; - goto err; + goto err_free_arg; } fields[n_fields++] = field; if (n_fields == SYNTH_FIELDS_MAX) { synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0); ret = -EINVAL; - goto err; + goto err_free_arg; } n_fields_this_loop++; } + argv_free(argv); if (consumed < argc) { synth_err(SYNTH_ERR_INVALID_CMD, 0); @@ -1281,7 +1281,6 @@ static int __create_synth_event(const char *name, const char *raw_fields) goto err; } - argv_free(argv); } if (n_fields == 0) { @@ -1307,6 +1306,8 @@ static int __create_synth_event(const char *name, const char *raw_fields) kfree(saved_fields); return ret; + err_free_arg: + argv_free(argv); err: for (i = 0; i < n_fields; i++) free_synth_field(fields[i]); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 6504b97f8dfd..c77fe36bb3d8 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -316,6 +316,7 @@ config DEBUG_INFO_BTF bool "Generate BTF typeinfo" depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST + depends on BPF_SYSCALL help Generate deduplicated BTF type information from DWARF debug info. Turning this on expects presence of pahole tool, which will convert diff --git a/lib/test_bpf.c b/lib/test_bpf.c index adae39567264..0c5cb2d6436a 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -14683,7 +14683,7 @@ static struct tail_call_test tail_call_tests[] = { BPF_EXIT_INSN(), }, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, - .result = (MAX_TAIL_CALL_CNT + 1 + 1) * MAX_TESTRUNS, + .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, }, { "Tail call count preserved across function calls", @@ -14705,7 +14705,7 @@ static struct tail_call_test tail_call_tests[] = { }, .stack_depth = 8, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, - .result = (MAX_TAIL_CALL_CNT + 1 + 1) * MAX_TESTRUNS, + .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, }, { "Tail call error path, NULL target", diff --git a/mm/Kconfig b/mm/Kconfig index 28edafc820ad..356f4f2c779e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -428,7 +428,7 @@ config THP_SWAP # UP and nommu archs use km based percpu allocator # config NEED_PER_CPU_KM - depends on !SMP + depends on !SMP || !MMU bool default y diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 1eead4761011..eae96dfe0261 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -945,6 +945,13 @@ void bdi_unregister(struct backing_dev_info *bdi) wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); + /* + * If this BDI's min ratio has been set, use bdi_set_min_ratio() to + * update the global bdi_min_ratio. + */ + if (bdi->min_ratio) + bdi_set_min_ratio(bdi, 0); + if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); diff --git a/mm/damon/core.c b/mm/damon/core.c index c381b3c525d0..e92497895202 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -282,7 +282,6 @@ int damon_set_targets(struct damon_ctx *ctx, for (i = 0; i < nr_ids; i++) { t = damon_new_target(ids[i]); if (!t) { - pr_err("Failed to alloc damon_target\n"); /* The caller should do cleanup of the ids itself */ damon_for_each_target_safe(t, next, ctx) damon_destroy_target(t); @@ -312,16 +311,10 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, unsigned long aggr_int, unsigned long primitive_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg) { - if (min_nr_reg < 3) { - pr_err("min_nr_regions (%lu) must be at least 3\n", - min_nr_reg); + if (min_nr_reg < 3) return -EINVAL; - } - if (min_nr_reg > max_nr_reg) { - pr_err("invalid nr_regions. min (%lu) > max (%lu)\n", - min_nr_reg, max_nr_reg); + if (min_nr_reg > max_nr_reg) return -EINVAL; - } ctx->sample_interval = sample_int; ctx->aggr_interval = aggr_int; @@ -980,10 +973,11 @@ static unsigned long damos_wmark_wait_us(struct damos *scheme) static void kdamond_usleep(unsigned long usecs) { - if (usecs > 100 * 1000) - schedule_timeout_interruptible(usecs_to_jiffies(usecs)); + /* See Documentation/timers/timers-howto.rst for the thresholds */ + if (usecs > 20 * USEC_PER_MSEC) + schedule_timeout_idle(usecs_to_jiffies(usecs)); else - usleep_range(usecs, usecs + 1); + usleep_idle_range(usecs, usecs + 1); } /* Returns negative error code if it's not activated but should return */ @@ -1038,7 +1032,7 @@ static int kdamond_fn(void *data) ctx->callback.after_sampling(ctx)) done = true; - usleep_range(ctx->sample_interval, ctx->sample_interval + 1); + kdamond_usleep(ctx->sample_interval); if (ctx->primitive.check_accesses) max_nr_accesses = ctx->primitive.check_accesses(ctx); diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 9b520bb4a3e7..1efac0022e9a 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -210,10 +210,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, &wmarks.low, &parsed); if (ret != 18) break; - if (!damos_action_valid(action)) { - pr_err("wrong action %d\n", action); + if (!damos_action_valid(action)) goto fail; - } pos += parsed; scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a, diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h index ecfd0b2ed222..6a1b9272ea12 100644 --- a/mm/damon/vaddr-test.h +++ b/mm/damon/vaddr-test.h @@ -135,7 +135,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test, struct damon_addr_range *three_regions, unsigned long *expected, int nr_expected) { - struct damon_ctx *ctx = damon_new_ctx(); struct damon_target *t; struct damon_region *r; int i; @@ -145,7 +144,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test, r = damon_new_region(regions[i * 2], regions[i * 2 + 1]); damon_add_region(r, t); } - damon_add_target(ctx, t); damon_va_apply_three_regions(t, three_regions); @@ -154,8 +152,6 @@ static void damon_do_test_apply_three_regions(struct kunit *test, KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]); KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]); } - - damon_destroy_ctx(ctx); } /* @@ -252,60 +248,59 @@ static void damon_test_apply_three_regions4(struct kunit *test) new_three_regions, expected, ARRAY_SIZE(expected)); } -static void damon_test_split_evenly(struct kunit *test) +static void damon_test_split_evenly_fail(struct kunit *test, + unsigned long start, unsigned long end, unsigned int nr_pieces) { - struct damon_ctx *c = damon_new_ctx(); - struct damon_target *t; - struct damon_region *r; - unsigned long i; - - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5), - -EINVAL); - - t = damon_new_target(42); - r = damon_new_region(0, 100); - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 0), -EINVAL); + struct damon_target *t = damon_new_target(42); + struct damon_region *r = damon_new_region(start, end); damon_add_region(r, t); - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 10), 0); - KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 10u); + KUNIT_EXPECT_EQ(test, + damon_va_evenly_split_region(t, r, nr_pieces), -EINVAL); + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u); - i = 0; damon_for_each_region(r, t) { - KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10); - KUNIT_EXPECT_EQ(test, r->ar.end, i * 10); + KUNIT_EXPECT_EQ(test, r->ar.start, start); + KUNIT_EXPECT_EQ(test, r->ar.end, end); } + damon_free_target(t); +} + +static void damon_test_split_evenly_succ(struct kunit *test, + unsigned long start, unsigned long end, unsigned int nr_pieces) +{ + struct damon_target *t = damon_new_target(42); + struct damon_region *r = damon_new_region(start, end); + unsigned long expected_width = (end - start) / nr_pieces; + unsigned long i = 0; - t = damon_new_target(42); - r = damon_new_region(5, 59); damon_add_region(r, t); - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 5), 0); - KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u); + KUNIT_EXPECT_EQ(test, + damon_va_evenly_split_region(t, r, nr_pieces), 0); + KUNIT_EXPECT_EQ(test, damon_nr_regions(t), nr_pieces); - i = 0; damon_for_each_region(r, t) { - if (i == 4) + if (i == nr_pieces - 1) break; - KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++); - KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i); + KUNIT_EXPECT_EQ(test, + r->ar.start, start + i++ * expected_width); + KUNIT_EXPECT_EQ(test, r->ar.end, start + i * expected_width); } - KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i); - KUNIT_EXPECT_EQ(test, r->ar.end, 59ul); + KUNIT_EXPECT_EQ(test, r->ar.start, start + i * expected_width); + KUNIT_EXPECT_EQ(test, r->ar.end, end); damon_free_target(t); +} - t = damon_new_target(42); - r = damon_new_region(5, 6); - damon_add_region(r, t); - KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 2), -EINVAL); - KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u); +static void damon_test_split_evenly(struct kunit *test) +{ + KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5), + -EINVAL); - damon_for_each_region(r, t) { - KUNIT_EXPECT_EQ(test, r->ar.start, 5ul); - KUNIT_EXPECT_EQ(test, r->ar.end, 6ul); - } - damon_free_target(t); - damon_destroy_ctx(c); + damon_test_split_evenly_fail(test, 0, 100, 0); + damon_test_split_evenly_succ(test, 0, 100, 10); + damon_test_split_evenly_succ(test, 5, 59, 5); + damon_test_split_evenly_fail(test, 5, 6, 2); } static struct kunit_case damon_test_cases[] = { diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 35fe49080ee9..20a9a9d69eb1 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -13,6 +13,7 @@ #include <linux/mmu_notifier.h> #include <linux/page_idle.h> #include <linux/pagewalk.h> +#include <linux/sched/mm.h> #include "prmtv-common.h" @@ -626,7 +627,6 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, case DAMOS_STAT: return 0; default: - pr_warn("Wrong action %d\n", scheme->action); return -EINVAL; } diff --git a/mm/filemap.c b/mm/filemap.c index daa0e23a6ee6..39c4c46c6133 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3253,8 +3253,6 @@ static struct page *next_uptodate_page(struct page *page, goto skip; if (!PageUptodate(page) || PageReadahead(page)) goto skip; - if (PageHWPoison(page)) - goto skip; if (!trylock_page(page)) goto skip; if (page->mapping != mapping) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index abcd1785c629..a1baa198519a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2973,7 +2973,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node; - if (nid >= nr_online_nodes) + if (nid != NUMA_NO_NODE && nid >= nr_online_nodes) return 0; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6863a834ed42..2ed5f2a0879d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -776,24 +776,6 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) rcu_read_unlock(); } -/* - * mod_objcg_mlstate() may be called with irq enabled, so - * mod_memcg_lruvec_state() should be used. - */ -static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, - struct pglist_data *pgdat, - enum node_stat_item idx, int nr) -{ - struct mem_cgroup *memcg; - struct lruvec *lruvec; - - rcu_read_lock(); - memcg = obj_cgroup_memcg(objcg); - lruvec = mem_cgroup_lruvec(memcg, pgdat); - mod_memcg_lruvec_state(lruvec, idx, nr); - rcu_read_unlock(); -} - /** * __count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup @@ -2137,41 +2119,6 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, } #endif -/* - * Most kmem_cache_alloc() calls are from user context. The irq disable/enable - * sequence used in this case to access content from object stock is slow. - * To optimize for user context access, there are now two object stocks for - * task context and interrupt context access respectively. - * - * The task context object stock can be accessed by disabling preemption only - * which is cheap in non-preempt kernel. The interrupt context object stock - * can only be accessed after disabling interrupt. User context code can - * access interrupt object stock, but not vice versa. - */ -static inline struct obj_stock *get_obj_stock(unsigned long *pflags) -{ - struct memcg_stock_pcp *stock; - - if (likely(in_task())) { - *pflags = 0UL; - preempt_disable(); - stock = this_cpu_ptr(&memcg_stock); - return &stock->task_obj; - } - - local_irq_save(*pflags); - stock = this_cpu_ptr(&memcg_stock); - return &stock->irq_obj; -} - -static inline void put_obj_stock(unsigned long flags) -{ - if (likely(in_task())) - preempt_enable(); - else - local_irq_restore(flags); -} - /** * consume_stock: Try to consume stocked charge on this cpu. * @memcg: memcg to consume from. @@ -2816,6 +2763,59 @@ retry: */ #define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT) +/* + * Most kmem_cache_alloc() calls are from user context. The irq disable/enable + * sequence used in this case to access content from object stock is slow. + * To optimize for user context access, there are now two object stocks for + * task context and interrupt context access respectively. + * + * The task context object stock can be accessed by disabling preemption only + * which is cheap in non-preempt kernel. The interrupt context object stock + * can only be accessed after disabling interrupt. User context code can + * access interrupt object stock, but not vice versa. + */ +static inline struct obj_stock *get_obj_stock(unsigned long *pflags) +{ + struct memcg_stock_pcp *stock; + + if (likely(in_task())) { + *pflags = 0UL; + preempt_disable(); + stock = this_cpu_ptr(&memcg_stock); + return &stock->task_obj; + } + + local_irq_save(*pflags); + stock = this_cpu_ptr(&memcg_stock); + return &stock->irq_obj; +} + +static inline void put_obj_stock(unsigned long flags) +{ + if (likely(in_task())) + preempt_enable(); + else + local_irq_restore(flags); +} + +/* + * mod_objcg_mlstate() may be called with irq enabled, so + * mod_memcg_lruvec_state() should be used. + */ +static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, + struct pglist_data *pgdat, + enum node_stat_item idx, int nr) +{ + struct mem_cgroup *memcg; + struct lruvec *lruvec; + + rcu_read_lock(); + memcg = obj_cgroup_memcg(objcg); + lruvec = mem_cgroup_lruvec(memcg, pgdat); + mod_memcg_lruvec_state(lruvec, idx, nr); + rcu_read_unlock(); +} + int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, gfp_t gfp, bool new_page) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 852041f6be41..2a9627dc784c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -35,6 +35,7 @@ #include <linux/memblock.h> #include <linux/compaction.h> #include <linux/rmap.h> +#include <linux/module.h> #include <asm/tlbflush.h> diff --git a/mm/slub.c b/mm/slub.c index a8626825a829..abe7db581d68 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5081,6 +5081,7 @@ struct loc_track { unsigned long max; unsigned long count; struct location *loc; + loff_t idx; }; static struct dentry *slab_debugfs_root; @@ -6052,11 +6053,11 @@ __initcall(slab_sysfs_init); #if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS) static int slab_debugfs_show(struct seq_file *seq, void *v) { - - struct location *l; - unsigned int idx = *(unsigned int *)v; struct loc_track *t = seq->private; + struct location *l; + unsigned long idx; + idx = (unsigned long) t->idx; if (idx < t->count) { l = &t->loc[idx]; @@ -6105,16 +6106,18 @@ static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos) { struct loc_track *t = seq->private; - v = ppos; - ++*ppos; + t->idx = ++(*ppos); if (*ppos <= t->count) - return v; + return ppos; return NULL; } static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos) { + struct loc_track *t = seq->private; + + t->idx = *ppos; return ppos; } diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 16f706c55d92..2b5531840583 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -30,6 +30,7 @@ #include <linux/swap_slots.h> #include <linux/cpu.h> #include <linux/cpumask.h> +#include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mutex.h> #include <linux/mm.h> diff --git a/net/Kconfig.debug b/net/Kconfig.debug index fb5c70e01cb3..2f50611df858 100644 --- a/net/Kconfig.debug +++ b/net/Kconfig.debug @@ -8,3 +8,12 @@ config NET_DEV_REFCNT_TRACKER help Enable debugging feature to track device references. This adds memory and cpu costs. + +config NET_NS_REFCNT_TRACKER + bool "Enable networking namespace refcount tracking" + depends on DEBUG_KERNEL && STACKTRACE_SUPPORT + select REF_TRACKER + default n + help + Enable debugging feature to track netns references. + This adds memory and cpu costs. diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index b5af68c105a8..4fd882686b04 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -743,6 +743,9 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu) mtu = nf_bridge->frag_max_size; + nf_bridge_update_protocol(skb); + nf_bridge_push_encap_header(skb); + if (skb_is_gso(skb) || skb->len + mtu_reserved <= mtu) { nf_bridge_info_free(skb); return br_dev_queue_push_xmit(net, sk, skb); @@ -760,8 +763,6 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; - nf_bridge_update_protocol(skb); - data = this_cpu_ptr(&brnf_frag_data_storage); if (skb_vlan_tag_present(skb)) { @@ -789,8 +790,6 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; - nf_bridge_update_protocol(skb); - data = this_cpu_ptr(&brnf_frag_data_storage); data->encap_size = nf_bridge_encap_header_len(skb); data->size = ETH_HLEN + data->encap_size; diff --git a/net/core/dev.c b/net/core/dev.c index 4420086f3aeb..a855e41bbe39 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3719,8 +3719,12 @@ no_lock_out: * separate lock before trying to get qdisc main lock. * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. + * On PREEMPT_RT it is possible to preempt the qdisc owner during xmit + * and then other tasks will only enqueue packets. The packets will be + * sent after the qdisc owner is scheduled again. To prevent this + * scenario the task always serialize on the lock. */ - contended = qdisc_is_running(q); + contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT); if (unlikely(contended)) spin_lock(&q->busylock); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 1d309a666932..1b807d119da5 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -192,7 +192,7 @@ static int net_hwtstamp_validate(struct ifreq *ifr) if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; - if (cfg.flags) /* reserved for future extensions */ + if (cfg.flags & ~HWTSTAMP_FLAG_MASK) return -EINVAL; tx_type = cfg.tx_type; diff --git a/net/core/devlink.c b/net/core/devlink.c index db3b52110cf2..0a9349a02cad 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4139,14 +4139,6 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return err; } - if (info->attrs[DEVLINK_ATTR_NETNS_PID] || - info->attrs[DEVLINK_ATTR_NETNS_FD] || - info->attrs[DEVLINK_ATTR_NETNS_ID]) { - dest_net = devlink_netns_get(skb, info); - if (IS_ERR(dest_net)) - return PTR_ERR(dest_net); - } - if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); else @@ -4189,6 +4181,14 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } } + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); if (dest_net) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 1bb567a3b329..75282222e0b4 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -750,6 +750,27 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, return 0; } +static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = { + [FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 }, + [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, + [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, + [FRA_PRIORITY] = { .type = NLA_U32 }, + [FRA_FWMARK] = { .type = NLA_U32 }, + [FRA_FLOW] = { .type = NLA_U32 }, + [FRA_TUN_ID] = { .type = NLA_U64 }, + [FRA_FWMASK] = { .type = NLA_U32 }, + [FRA_TABLE] = { .type = NLA_U32 }, + [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, + [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, + [FRA_GOTO] = { .type = NLA_U32 }, + [FRA_L3MDEV] = { .type = NLA_U8 }, + [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }, + [FRA_PROTOCOL] = { .type = NLA_U8 }, + [FRA_IP_PROTO] = { .type = NLA_U8 }, + [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, + [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) } +}; + int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -774,7 +795,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, - ops->policy, extack); + fib_rule_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; @@ -882,7 +903,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, } err = nlmsg_parse_deprecated(nlh, sizeof(*frh), tb, FRA_MAX, - ops->policy, extack); + fib_rule_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; diff --git a/net/core/filter.c b/net/core/filter.c index 8271624a19aa..e4cc3aff5bf7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1242,10 +1242,9 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) int err, new_len, old_len = fp->len; bool seen_ld_abs = false; - /* We are free to overwrite insns et al right here as it - * won't be used at this point in time anymore internally - * after the migration to the internal BPF instruction - * representation. + /* We are free to overwrite insns et al right here as it won't be used at + * this point in time anymore internally after the migration to the eBPF + * instruction representation. */ BUILD_BUG_ON(sizeof(struct sock_filter) != sizeof(struct bpf_insn)); @@ -1336,8 +1335,8 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, */ bpf_jit_compile(fp); - /* JIT compiler couldn't process this filter, so do the - * internal BPF translation for the optimized interpreter. + /* JIT compiler couldn't process this filter, so do the eBPF translation + * for the optimized interpreter. */ if (!fp->jited) fp = bpf_migrate_filter(fp); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index d7d089963b1d..b0f5344d1185 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -166,7 +166,10 @@ static void linkwatch_do_dev(struct net_device *dev) netdev_state_change(dev); } - dev_put_track(dev, &dev->linkwatch_dev_tracker); + /* Note: our callers are responsible for + * calling netdev_tracker_free(). + */ + dev_put(dev); } static void __linkwatch_run_queue(int urgent_only) @@ -209,6 +212,10 @@ static void __linkwatch_run_queue(int urgent_only) list_add_tail(&dev->link_watch_list, &lweventlist); continue; } + /* We must free netdev tracker under + * the spinlock protection. + */ + netdev_tracker_free(dev, &dev->linkwatch_dev_tracker); spin_unlock_irq(&lweventlist_lock); linkwatch_do_dev(dev); do_dev--; @@ -232,6 +239,10 @@ void linkwatch_forget_dev(struct net_device *dev) if (!list_empty(&dev->link_watch_list)) { list_del_init(&dev->link_watch_list); clean = 1; + /* We must release netdev tracker under + * the spinlock protection. + */ + netdev_tracker_free(dev, &dev->linkwatch_dev_tracker); } spin_unlock_irqrestore(&lweventlist_lock, flags); if (clean) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index dd271ffedf11..213cb7b26b7a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -763,11 +763,10 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, ASSERT_RTNL(); - n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL); + n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL); if (!n) goto out; - n->protocol = 0; write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; @@ -3771,10 +3770,6 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, neigh_proc_base_reachable_time; } - /* Don't export sysctls to unprivileged users */ - if (neigh_parms_net(p)->user_ns != &init_user_ns) - t->neigh_vars[0].procname = NULL; - switch (neigh_parms_family(p)) { case AF_INET: p_name = "ipv4"; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 3b2cdbbdc858..53ea262ecafd 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1694,6 +1694,13 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num) int i; int error = 0; + /* Tx queue kobjects are allowed to be updated when a device is being + * unregistered, but solely to remove queues from qdiscs. Any path + * adding queues should be fixed. + */ + WARN(dev->reg_state == NETREG_UNREGISTERING && new_num > old_num, + "New queues can't be registered after device unregistration."); + for (i = old_num; i < new_num; i++) { error = netdev_queue_add_kobject(dev, i); if (error) { @@ -1808,6 +1815,9 @@ static void remove_queue_kobjects(struct net_device *dev) net_rx_queue_update_kobjects(dev, real_rx, 0); netdev_queue_update_kobjects(dev, real_tx, 0); + + dev->real_num_rx_queues = 0; + dev->real_num_tx_queues = 0; #ifdef CONFIG_SYSFS kset_unregister(dev->queues_kset); #endif diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 202fa5eacd0f..9b7171c40434 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -311,6 +311,8 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) LIST_HEAD(net_exit_list); refcount_set(&net->ns.count, 1); + ref_tracker_dir_init(&net->refcnt_tracker, 128); + refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); preempt_disable(); @@ -635,6 +637,7 @@ static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { + ref_tracker_dir_exit(&net->refcnt_tracker); /* Cleanup the network namespace in process context */ if (llist_add(&net->cleanup_list, &cleanup_list)) queue_work(netns_wq, &net_cleanup_work); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a33247fdb8f5..275f7b8416fe 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -832,7 +832,7 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) ntohs(skb->protocol), skb->pkt_type, skb->skb_iif); if (dev) - printk("%sdev name=%s feat=0x%pNF\n", + printk("%sdev name=%s feat=%pNF\n", level, dev->name, &dev->features); if (sk) printk("%ssk family=%hu type=%u proto=%u\n", diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 1ae52ac943f6..8eb671c827f9 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1124,6 +1124,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) { + psock_set_prog(&psock->progs.stream_parser, NULL); + if (!psock->saved_data_ready) return; @@ -1212,6 +1214,9 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) { + psock_set_prog(&psock->progs.stream_verdict, NULL); + psock_set_prog(&psock->progs.skb_verdict, NULL); + if (!psock->saved_data_ready) return; diff --git a/net/core/sock.c b/net/core/sock.c index 4a499d255f40..e21485ab285d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1983,7 +1983,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) { - get_net(net); + get_net_track(net, &sk->ns_tracker, priority); sock_inuse_add(net, 1); } @@ -2039,7 +2039,7 @@ static void __sk_destruct(struct rcu_head *head) put_pid(sk->sk_peer_pid); if (likely(sk->sk_net_refcnt)) - put_net(sock_net(sk)); + put_net_track(sock_net(sk), &sk->ns_tracker); sk_prot_free(sk->sk_prot_creator, sk); } @@ -2126,7 +2126,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) /* SANITY */ if (likely(newsk->sk_net_refcnt)) { - get_net(sock_net(newsk)); + get_net_track(sock_net(newsk), &newsk->ns_tracker, priority); sock_inuse_add(sock_net(newsk), 1); } sk_node_init(&newsk->sk_node); @@ -3292,7 +3292,7 @@ void lock_sock_nested(struct sock *sk, int subclass) might_sleep(); spin_lock_bh(&sk->sk_lock.slock); - if (sk->sk_lock.owned) + if (sock_owned_by_user_nocheck(sk)) __lock_sock(sk); sk->sk_lock.owned = 1; spin_unlock_bh(&sk->sk_lock.slock); @@ -3323,7 +3323,7 @@ bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) might_sleep(); spin_lock_bh(&sk->sk_lock.slock); - if (!sk->sk_lock.owned) { + if (!sock_owned_by_user_nocheck(sk)) { /* * Fast path return with bottom halves disabled and * sock::sk_lock.slock held. diff --git a/net/core/sock_map.c b/net/core/sock_map.c index f39ef79ced67..4ca4b11f4e5f 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -167,8 +167,11 @@ static void sock_map_del_link(struct sock *sk, write_lock_bh(&sk->sk_callback_lock); if (strp_stop) sk_psock_stop_strp(sk, psock); - else + if (verdict_stop) sk_psock_stop_verdict(sk, psock); + + if (psock->psock_update_sk_prot) + psock->psock_update_sk_prot(sk, psock, false); write_unlock_bh(&sk->sk_callback_lock); } } @@ -282,6 +285,12 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) if (msg_parser) psock_set_prog(&psock->progs.msg_parser, msg_parser); + if (stream_parser) + psock_set_prog(&psock->progs.stream_parser, stream_parser); + if (stream_verdict) + psock_set_prog(&psock->progs.stream_verdict, stream_verdict); + if (skb_verdict) + psock_set_prog(&psock->progs.skb_verdict, skb_verdict); ret = sock_map_init_proto(sk, psock); if (ret < 0) @@ -292,14 +301,10 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) ret = sk_psock_init_strp(sk, psock); if (ret) goto out_unlock_drop; - psock_set_prog(&psock->progs.stream_verdict, stream_verdict); - psock_set_prog(&psock->progs.stream_parser, stream_parser); sk_psock_start_strp(sk, psock); } else if (!stream_parser && stream_verdict && !psock->saved_data_ready) { - psock_set_prog(&psock->progs.stream_verdict, stream_verdict); sk_psock_start_verdict(sk,psock); } else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) { - psock_set_prog(&psock->progs.skb_verdict, skb_verdict); sk_psock_start_verdict(sk, psock); } write_unlock_bh(&sk->sk_callback_lock); diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 4a4e3c17740c..ee73057529cf 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -101,10 +101,6 @@ errout: return err; } -static const struct nla_policy dn_fib_rule_policy[FRA_MAX+1] = { - FRA_GENERIC_POLICY, -}; - static int dn_fib_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { struct dn_fib_rule *r = (struct dn_fib_rule *)rule; @@ -235,7 +231,6 @@ static const struct fib_rules_ops __net_initconst dn_fib_rules_ops_template = { .fill = dn_fib_rule_fill, .flush_cache = dn_fib_rule_flush_cache, .nlgroup = RTNLGRP_DECnet_RULE, - .policy = dn_fib_rule_policy, .owner = THIS_MODULE, .fro_net = &init_net, }; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 826957b6442b..c18b22c0bf55 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -129,35 +129,52 @@ void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag) } } +struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, + const struct net_device *br) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_bridge_dev_get(dp) == br) + return dp->bridge; + + return NULL; +} + static int dsa_bridge_num_find(const struct net_device *bridge_dev) { struct dsa_switch_tree *dst; - struct dsa_port *dp; - /* When preparing the offload for a port, it will have a valid - * dp->bridge_dev pointer but a not yet valid dp->bridge_num. - * However there might be other ports having the same dp->bridge_dev - * and a valid dp->bridge_num, so just ignore this port. - */ - list_for_each_entry(dst, &dsa_tree_list, list) - list_for_each_entry(dp, &dst->ports, list) - if (dp->bridge_dev == bridge_dev && - dp->bridge_num != -1) - return dp->bridge_num; + list_for_each_entry(dst, &dsa_tree_list, list) { + struct dsa_bridge *bridge; + + bridge = dsa_tree_bridge_find(dst, bridge_dev); + if (bridge) + return bridge->num; + } - return -1; + return 0; } -int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) +unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) { - int bridge_num = dsa_bridge_num_find(bridge_dev); + unsigned int bridge_num = dsa_bridge_num_find(bridge_dev); + + /* Switches without FDB isolation support don't get unique + * bridge numbering + */ + if (!max) + return 0; - if (bridge_num < 0) { - /* First port that offloads TX forwarding for this bridge */ - bridge_num = find_first_zero_bit(&dsa_fwd_offloading_bridges, - DSA_MAX_NUM_OFFLOADING_BRIDGES); + if (!bridge_num) { + /* First port that requests FDB isolation or TX forwarding + * offload for this bridge + */ + bridge_num = find_next_zero_bit(&dsa_fwd_offloading_bridges, + DSA_MAX_NUM_OFFLOADING_BRIDGES, + 1); if (bridge_num >= max) - return -1; + return 0; set_bit(bridge_num, &dsa_fwd_offloading_bridges); } @@ -165,13 +182,14 @@ int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) return bridge_num; } -void dsa_bridge_num_put(const struct net_device *bridge_dev, int bridge_num) +void dsa_bridge_num_put(const struct net_device *bridge_dev, + unsigned int bridge_num) { - /* Check if the bridge is still in use, otherwise it is time - * to clean it up so we can reuse this bridge_num later. + /* Since we refcount bridges, we know that when we call this function + * it is no longer in use, so we can just go ahead and remove it from + * the bit mask. */ - if (dsa_bridge_num_find(bridge_dev) < 0) - clear_bit(bridge_num, &dsa_fwd_offloading_bridges); + clear_bit(bridge_num, &dsa_fwd_offloading_bridges); } struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) @@ -804,7 +822,7 @@ static int dsa_switch_setup_tag_protocol(struct dsa_switch *ds) int err; if (tag_ops->proto == dst->default_proto) - return 0; + goto connect; dsa_switch_for_each_cpu_port(cpu_dp, ds) { rtnl_lock(); @@ -818,7 +836,30 @@ static int dsa_switch_setup_tag_protocol(struct dsa_switch *ds) } } +connect: + if (tag_ops->connect) { + err = tag_ops->connect(ds); + if (err) + return err; + } + + if (ds->ops->connect_tag_protocol) { + err = ds->ops->connect_tag_protocol(ds, tag_ops->proto); + if (err) { + dev_err(ds->dev, + "Unable to connect to tag protocol \"%s\": %pe\n", + tag_ops->name, ERR_PTR(err)); + goto disconnect; + } + } + return 0; + +disconnect: + if (tag_ops->disconnect) + tag_ops->disconnect(ds); + + return err; } static int dsa_switch_setup(struct dsa_switch *ds) @@ -1118,6 +1159,37 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dst->setup = false; } +static int dsa_tree_bind_tag_proto(struct dsa_switch_tree *dst, + const struct dsa_device_ops *tag_ops) +{ + const struct dsa_device_ops *old_tag_ops = dst->tag_ops; + struct dsa_notifier_tag_proto_info info; + int err; + + dst->tag_ops = tag_ops; + + /* Notify the switches from this tree about the connection + * to the new tagger + */ + info.tag_ops = tag_ops; + err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_CONNECT, &info); + if (err && err != -EOPNOTSUPP) + goto out_disconnect; + + /* Notify the old tagger about the disconnection from this tree */ + info.tag_ops = old_tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_DISCONNECT, &info); + + return 0; + +out_disconnect: + info.tag_ops = tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_DISCONNECT, &info); + dst->tag_ops = old_tag_ops; + + return err; +} + /* Since the dsa/tagging sysfs device attribute is per master, the assumption * is that all DSA switches within a tree share the same tagger, otherwise * they would have formed disjoint trees (different "dsa,member" values). @@ -1150,12 +1222,15 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, goto out_unlock; } + /* Notify the tag protocol change */ info.tag_ops = tag_ops; err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); if (err) - goto out_unwind_tagger; + return err; - dst->tag_ops = tag_ops; + err = dsa_tree_bind_tag_proto(dst, tag_ops); + if (err) + goto out_unwind_tagger; rtnl_unlock(); @@ -1184,7 +1259,6 @@ static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) dp->ds = ds; dp->index = index; - dp->bridge_num = -1; INIT_LIST_HEAD(&dp->list); list_add_tail(&dp->list, &dst->ports); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 3fb2c37c9b88..edfaae7b5967 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -37,6 +37,8 @@ enum { DSA_NOTIFIER_VLAN_DEL, DSA_NOTIFIER_MTU, DSA_NOTIFIER_TAG_PROTO, + DSA_NOTIFIER_TAG_PROTO_CONNECT, + DSA_NOTIFIER_TAG_PROTO_DISCONNECT, DSA_NOTIFIER_MRP_ADD, DSA_NOTIFIER_MRP_DEL, DSA_NOTIFIER_MRP_ADD_RING_ROLE, @@ -52,10 +54,11 @@ struct dsa_notifier_ageing_time_info { /* DSA_NOTIFIER_BRIDGE_* */ struct dsa_notifier_bridge_info { - struct net_device *br; + struct dsa_bridge bridge; int tree_index; int sw_index; int port; + bool tx_fwd_offload; }; /* DSA_NOTIFIER_FDB_* */ @@ -266,47 +269,6 @@ void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast); void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast); -static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, - const struct net_device *dev) -{ - return dsa_port_to_bridge_port(dp) == dev; -} - -static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, - const struct net_device *bridge_dev) -{ - /* DSA ports connected to a bridge, and event was emitted - * for the bridge. - */ - return dp->bridge_dev == bridge_dev; -} - -/* Returns true if any port of this tree offloads the given net_device */ -static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, - const struct net_device *dev) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_offloads_bridge_port(dp, dev)) - return true; - - return false; -} - -/* Returns true if any port of this tree offloads the given bridge */ -static inline bool dsa_tree_offloads_bridge(struct dsa_switch_tree *dst, - const struct net_device *bridge_dev) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_offloads_bridge(dp, bridge_dev)) - return true; - - return false; -} - /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; extern struct notifier_block dsa_slave_switchdev_notifier; @@ -345,7 +307,7 @@ dsa_slave_to_master(const struct net_device *dev) static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct net_device *br = dp->bridge_dev; + struct net_device *br = dsa_port_bridge_dev_get(dp); struct net_device *dev = skb->dev; struct net_device *upper_dev; u16 vid, pvid, proto; @@ -415,7 +377,7 @@ dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) if (dp->type != DSA_PORT_TYPE_USER) continue; - if (!dp->bridge_dev) + if (!dp->bridge) continue; if (dp->stp_state != BR_STATE_LEARNING && @@ -444,7 +406,7 @@ dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) /* If the ingress port offloads the bridge, we mark the frame as autonomously * forwarded by hardware, so the software bridge doesn't forward in twice, back * to us, because we already did. However, if we're in fallback mode and we do - * software bridging, we are not offloading it, therefore the dp->bridge_dev + * software bridging, we are not offloading it, therefore the dp->bridge * pointer is not populated, and flooding needs to be done by software (we are * effectively operating in standalone ports mode). */ @@ -452,7 +414,7 @@ static inline void dsa_default_offload_fwd_mark(struct sk_buff *skb) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - skb->offload_fwd_mark = !!(dp->bridge_dev); + skb->offload_fwd_mark = !!(dp->bridge); } /* Helper for removing DSA header tags from packets in the RX path. @@ -546,8 +508,11 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, struct net_device *master, const struct dsa_device_ops *tag_ops, const struct dsa_device_ops *old_tag_ops); -int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); -void dsa_bridge_num_put(const struct net_device *bridge_dev, int bridge_num); +unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); +void dsa_bridge_num_put(const struct net_device *bridge_dev, + unsigned int bridge_num); +struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, + const struct net_device *br); /* tag_8021q.c */ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, diff --git a/net/dsa/port.c b/net/dsa/port.c index 6d5ebe61280b..05677e016982 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -130,7 +130,7 @@ int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy) return err; } - if (!dp->bridge_dev) + if (!dp->bridge) dsa_port_set_state_now(dp, BR_STATE_FORWARDING, false); if (dp->pl) @@ -158,7 +158,7 @@ void dsa_port_disable_rt(struct dsa_port *dp) if (dp->pl) phylink_stop(dp->pl); - if (!dp->bridge_dev) + if (!dp->bridge) dsa_port_set_state_now(dp, BR_STATE_DISABLED, false); if (ds->ops->port_disable) @@ -221,7 +221,7 @@ static int dsa_port_switchdev_sync_attrs(struct dsa_port *dp, struct netlink_ext_ack *extack) { struct net_device *brport_dev = dsa_port_to_bridge_port(dp); - struct net_device *br = dp->bridge_dev; + struct net_device *br = dsa_port_bridge_dev_get(dp); int err; err = dsa_port_inherit_brport_flags(dp, extack); @@ -270,52 +270,55 @@ static void dsa_port_switchdev_unsync_attrs(struct dsa_port *dp) */ } -static void dsa_port_bridge_tx_fwd_unoffload(struct dsa_port *dp, - struct net_device *bridge_dev) +static int dsa_port_bridge_create(struct dsa_port *dp, + struct net_device *br, + struct netlink_ext_ack *extack) { - int bridge_num = dp->bridge_num; struct dsa_switch *ds = dp->ds; + struct dsa_bridge *bridge; - /* No bridge TX forwarding offload => do nothing */ - if (!ds->ops->port_bridge_tx_fwd_unoffload || dp->bridge_num == -1) - return; + bridge = dsa_tree_bridge_find(ds->dst, br); + if (bridge) { + refcount_inc(&bridge->refcount); + dp->bridge = bridge; + return 0; + } - dp->bridge_num = -1; + bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return -ENOMEM; - dsa_bridge_num_put(bridge_dev, bridge_num); + refcount_set(&bridge->refcount, 1); - /* Notify the chips only once the offload has been deactivated, so - * that they can update their configuration accordingly. - */ - ds->ops->port_bridge_tx_fwd_unoffload(ds, dp->index, bridge_dev, - bridge_num); + bridge->dev = br; + + bridge->num = dsa_bridge_num_get(br, ds->max_num_bridges); + if (ds->max_num_bridges && !bridge->num) { + NL_SET_ERR_MSG_MOD(extack, + "Range of offloadable bridges exceeded"); + kfree(bridge); + return -EOPNOTSUPP; + } + + dp->bridge = bridge; + + return 0; } -static bool dsa_port_bridge_tx_fwd_offload(struct dsa_port *dp, - struct net_device *bridge_dev) +static void dsa_port_bridge_destroy(struct dsa_port *dp, + const struct net_device *br) { - struct dsa_switch *ds = dp->ds; - int bridge_num, err; + struct dsa_bridge *bridge = dp->bridge; - if (!ds->ops->port_bridge_tx_fwd_offload) - return false; - - bridge_num = dsa_bridge_num_get(bridge_dev, - ds->num_fwd_offloading_bridges); - if (bridge_num < 0) - return false; + dp->bridge = NULL; - dp->bridge_num = bridge_num; + if (!refcount_dec_and_test(&bridge->refcount)) + return; - /* Notify the driver */ - err = ds->ops->port_bridge_tx_fwd_offload(ds, dp->index, bridge_dev, - bridge_num); - if (err) { - dsa_port_bridge_tx_fwd_unoffload(dp, bridge_dev); - return false; - } + if (bridge->num) + dsa_bridge_num_put(br, bridge->num); - return true; + kfree(bridge); } int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, @@ -325,30 +328,32 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, .tree_index = dp->ds->dst->index, .sw_index = dp->ds->index, .port = dp->index, - .br = br, }; struct net_device *dev = dp->slave; struct net_device *brport_dev; - bool tx_fwd_offload; int err; /* Here the interface is already bridged. Reflect the current * configuration so that drivers can program their chips accordingly. */ - dp->bridge_dev = br; + err = dsa_port_bridge_create(dp, br, extack); + if (err) + return err; brport_dev = dsa_port_to_bridge_port(dp); + info.bridge = *dp->bridge; err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_JOIN, &info); if (err) goto out_rollback; - tx_fwd_offload = dsa_port_bridge_tx_fwd_offload(dp, br); + /* Drivers which support bridge TX forwarding should set this */ + dp->bridge->tx_fwd_offload = info.tx_fwd_offload; err = switchdev_bridge_port_offload(brport_dev, dev, dp, &dsa_slave_switchdev_notifier, &dsa_slave_switchdev_blocking_notifier, - tx_fwd_offload, extack); + dp->bridge->tx_fwd_offload, extack); if (err) goto out_rollback_unbridge; @@ -365,7 +370,7 @@ out_rollback_unoffload: out_rollback_unbridge: dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); out_rollback: - dp->bridge_dev = NULL; + dsa_port_bridge_destroy(dp, br); return err; } @@ -390,16 +395,14 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) .tree_index = dp->ds->dst->index, .sw_index = dp->ds->index, .port = dp->index, - .br = br, + .bridge = *dp->bridge, }; int err; /* Here the port is already unbridged. Reflect the current configuration * so that drivers can program their chips accordingly. */ - dp->bridge_dev = NULL; - - dsa_port_bridge_tx_fwd_unoffload(dp, br); + dsa_port_bridge_destroy(dp, br); err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); if (err) @@ -477,12 +480,15 @@ err_lag_join: void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag) { - if (dp->bridge_dev) - dsa_port_pre_bridge_leave(dp, dp->bridge_dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); + + if (br) + dsa_port_pre_bridge_leave(dp, br); } void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag) { + struct net_device *br = dsa_port_bridge_dev_get(dp); struct dsa_notifier_lag_info info = { .sw_index = dp->ds->index, .port = dp->index, @@ -496,8 +502,8 @@ void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag) /* Port might have been part of a LAG that in turn was * attached to a bridge. */ - if (dp->bridge_dev) - dsa_port_bridge_leave(dp, dp->bridge_dev); + if (br) + dsa_port_bridge_leave(dp, br); dp->lag_tx_enabled = false; dp->lag_dev = NULL; @@ -526,8 +532,8 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, * as long as we have 8021q uppers. */ if (vlan_filtering && dsa_port_is_user(dp)) { + struct net_device *br = dsa_port_bridge_dev_get(dp); struct net_device *upper_dev, *slave = dp->slave; - struct net_device *br = dp->bridge_dev; struct list_head *iter; netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) { @@ -561,17 +567,15 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, * different setting than what is being requested. */ dsa_switch_for_each_port(other_dp, ds) { - struct net_device *other_bridge; + struct net_device *other_br = dsa_port_bridge_dev_get(other_dp); - other_bridge = other_dp->bridge_dev; - if (!other_bridge) - continue; /* If it's the same bridge, it also has same * vlan_filtering setting => no need to check */ - if (other_bridge == dp->bridge_dev) + if (!other_br || other_br == dsa_port_bridge_dev_get(dp)) continue; - if (br_vlan_enabled(other_bridge) != vlan_filtering) { + + if (br_vlan_enabled(other_br) != vlan_filtering) { NL_SET_ERR_MSG_MOD(extack, "VLAN filtering is a global setting"); return false; @@ -655,13 +659,13 @@ restore: */ bool dsa_port_skip_vlan_configuration(struct dsa_port *dp) { + struct net_device *br = dsa_port_bridge_dev_get(dp); struct dsa_switch *ds = dp->ds; - if (!dp->bridge_dev) + if (!br) return false; - return (!ds->configure_vlan_while_not_filtering && - !br_vlan_enabled(dp->bridge_dev)); + return !ds->configure_vlan_while_not_filtering && !br_vlan_enabled(br); } int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock) @@ -1094,6 +1098,13 @@ int dsa_port_phylink_create(struct dsa_port *dp) if (err) mode = PHY_INTERFACE_MODE_NA; + /* Presence of phylink_mac_link_state or phylink_mac_an_restart is + * an indicator of a legacy phylink driver. + */ + if (ds->ops->phylink_mac_link_state || + ds->ops->phylink_mac_an_restart) + dp->pl_config.legacy_pre_march2020 = true; + if (ds->ops->phylink_get_caps) ds->ops->phylink_get_caps(ds, dp->index, &dp->pl_config); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 33b54eadc641..88f7b8686dac 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -289,14 +289,14 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, ret = dsa_port_set_state(dp, attr->u.stp_state, true); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: - if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) + if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: - if (!dsa_port_offloads_bridge(dp, attr->orig_dev)) + if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) return -EOPNOTSUPP; ret = dsa_port_ageing_time(dp, attr->u.ageing_time); @@ -363,7 +363,7 @@ static int dsa_slave_vlan_add(struct net_device *dev, /* Deny adding a bridge VLAN when there is already an 802.1Q upper with * the same VID. */ - if (br_vlan_enabled(dp->bridge_dev)) { + if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { rcu_read_lock(); err = dsa_slave_vlan_check_for_8021q_uppers(dev, &vlan); rcu_read_unlock(); @@ -409,7 +409,7 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: - if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); @@ -421,13 +421,13 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, err = dsa_slave_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: - if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: - if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_add_ring_role(dp, @@ -483,7 +483,7 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: - if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); @@ -495,13 +495,13 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, err = dsa_slave_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: - if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); break; case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: - if (!dsa_port_offloads_bridge(dp, obj->orig_dev)) + if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mrp_del_ring_role(dp, @@ -1564,7 +1564,7 @@ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) if (!dp->ds->mtu_enforcement_ingress) return; - if (!dp->bridge_dev) + if (!dp->bridge) return; INIT_LIST_HEAD(&hw_port_list); @@ -1580,7 +1580,7 @@ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) if (other_dp->type != DSA_PORT_TYPE_USER) continue; - if (other_dp->bridge_dev != dp->bridge_dev) + if (!dsa_port_bridge_same(dp, other_dp)) continue; if (!other_dp->ds->mtu_enforcement_ingress) @@ -2220,7 +2220,7 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *ext_ack; - struct net_device *slave; + struct net_device *slave, *br; struct dsa_port *dp; ext_ack = netdev_notifier_info_to_extack(&info->info); @@ -2233,11 +2233,12 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, return NOTIFY_DONE; dp = dsa_slave_to_port(slave); - if (!dp->bridge_dev) + br = dsa_port_bridge_dev_get(dp); + if (!br) return NOTIFY_DONE; /* Deny enslaving a VLAN device into a VLAN-aware bridge */ - if (br_vlan_enabled(dp->bridge_dev) && + if (br_vlan_enabled(br) && netif_is_bridge_master(info->upper_dev) && info->linking) { NL_SET_ERR_MSG_MOD(ext_ack, "Cannot enslave VLAN device into VLAN aware bridge"); @@ -2252,7 +2253,7 @@ dsa_slave_check_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct net_device *br = dp->bridge_dev; + struct net_device *br = dsa_port_bridge_dev_get(dp); struct bridge_vlan_info br_info; struct netlink_ext_ack *extack; int err = NOTIFY_DONE; @@ -2449,7 +2450,7 @@ static bool dsa_foreign_dev_check(const struct net_device *dev, struct dsa_switch_tree *dst = dp->ds->dst; if (netif_is_bridge_master(foreign_dev)) - return !dsa_tree_offloads_bridge(dst, foreign_dev); + return !dsa_tree_offloads_bridge_dev(dst, foreign_dev); if (netif_is_bridge_port(foreign_dev)) return !dsa_tree_offloads_bridge_port(dst, foreign_dev); diff --git a/net/dsa/switch.c b/net/dsa/switch.c index bb155a16d454..393f2d8a860a 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -95,7 +95,8 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds, if (!ds->ops->port_bridge_join) return -EOPNOTSUPP; - err = ds->ops->port_bridge_join(ds, info->port, info->br); + err = ds->ops->port_bridge_join(ds, info->port, info->bridge, + &info->tx_fwd_offload); if (err) return err; } @@ -104,7 +105,7 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds, ds->ops->crosschip_bridge_join) { err = ds->ops->crosschip_bridge_join(ds, info->tree_index, info->sw_index, - info->port, info->br); + info->port, info->bridge); if (err) return err; } @@ -124,19 +125,20 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, if (dst->index == info->tree_index && ds->index == info->sw_index && ds->ops->port_bridge_leave) - ds->ops->port_bridge_leave(ds, info->port, info->br); + ds->ops->port_bridge_leave(ds, info->port, info->bridge); if ((dst->index != info->tree_index || ds->index != info->sw_index) && ds->ops->crosschip_bridge_leave) ds->ops->crosschip_bridge_leave(ds, info->tree_index, info->sw_index, info->port, - info->br); + info->bridge); - if (ds->needs_standalone_vlan_filtering && !br_vlan_enabled(info->br)) { + if (ds->needs_standalone_vlan_filtering && + !br_vlan_enabled(info->bridge.dev)) { change_vlan_filtering = true; vlan_filtering = true; } else if (!ds->needs_standalone_vlan_filtering && - br_vlan_enabled(info->br)) { + br_vlan_enabled(info->bridge.dev)) { change_vlan_filtering = true; vlan_filtering = false; } @@ -151,11 +153,9 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, */ if (change_vlan_filtering && ds->vlan_filtering_is_global) { dsa_switch_for_each_port(dp, ds) { - struct net_device *bridge_dev; + struct net_device *br = dsa_port_bridge_dev_get(dp); - bridge_dev = dp->bridge_dev; - - if (bridge_dev && br_vlan_enabled(bridge_dev)) { + if (br && br_vlan_enabled(br)) { change_vlan_filtering = false; break; } @@ -647,6 +647,60 @@ static int dsa_switch_change_tag_proto(struct dsa_switch *ds, return 0; } +/* We use the same cross-chip notifiers to inform both the tagger side, as well + * as the switch side, of connection and disconnection events. + * Since ds->tagger_data is owned by the tagger, it isn't a hard error if the + * switch side doesn't support connecting to this tagger, and therefore, the + * fact that we don't disconnect the tagger side doesn't constitute a memory + * leak: the tagger will still operate with persistent per-switch memory, just + * with the switch side unconnected to it. What does constitute a hard error is + * when the switch side supports connecting but fails. + */ +static int +dsa_switch_connect_tag_proto(struct dsa_switch *ds, + struct dsa_notifier_tag_proto_info *info) +{ + const struct dsa_device_ops *tag_ops = info->tag_ops; + int err; + + /* Notify the new tagger about the connection to this switch */ + if (tag_ops->connect) { + err = tag_ops->connect(ds); + if (err) + return err; + } + + if (!ds->ops->connect_tag_protocol) + return -EOPNOTSUPP; + + /* Notify the switch about the connection to the new tagger */ + err = ds->ops->connect_tag_protocol(ds, tag_ops->proto); + if (err) { + /* Revert the new tagger's connection to this tree */ + if (tag_ops->disconnect) + tag_ops->disconnect(ds); + return err; + } + + return 0; +} + +static int +dsa_switch_disconnect_tag_proto(struct dsa_switch *ds, + struct dsa_notifier_tag_proto_info *info) +{ + const struct dsa_device_ops *tag_ops = info->tag_ops; + + /* Notify the tagger about the disconnection from this switch */ + if (tag_ops->disconnect && ds->tagger_data) + tag_ops->disconnect(ds); + + /* No need to notify the switch, since it shouldn't have any + * resources to tear down + */ + return 0; +} + static int dsa_switch_mrp_add(struct dsa_switch *ds, struct dsa_notifier_mrp_info *info) { @@ -766,6 +820,12 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_TAG_PROTO: err = dsa_switch_change_tag_proto(ds, info); break; + case DSA_NOTIFIER_TAG_PROTO_CONNECT: + err = dsa_switch_connect_tag_proto(ds, info); + break; + case DSA_NOTIFIER_TAG_PROTO_DISCONNECT: + err = dsa_switch_disconnect_tag_proto(ds, info); + break; case DSA_NOTIFIER_MRP_ADD: err = dsa_switch_mrp_add(ds, info); break; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 72cac2c0af7b..27712a81c967 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -67,10 +67,12 @@ #define DSA_8021Q_PORT(x) (((x) << DSA_8021Q_PORT_SHIFT) & \ DSA_8021Q_PORT_MASK) -u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num) +u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num) { - /* The VBID value of 0 is reserved for precise TX */ - return DSA_8021Q_DIR_TX | DSA_8021Q_VBID(bridge_num + 1); + /* The VBID value of 0 is reserved for precise TX, but it is also + * reserved/invalid for the bridge_num, so all is well. + */ + return DSA_8021Q_DIR_TX | DSA_8021Q_VBID(bridge_num); } EXPORT_SYMBOL_GPL(dsa_8021q_bridge_tx_fwd_offload_vid); @@ -335,7 +337,7 @@ dsa_port_tag_8021q_bridge_match(struct dsa_port *dp, return false; if (dsa_port_is_user(dp)) - return dp->bridge_dev == info->br; + return dsa_port_offloads_bridge(dp, &info->bridge); return false; } @@ -408,10 +410,9 @@ int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, } int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num) + struct dsa_bridge bridge) { - u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); + u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge.num); return dsa_port_tag_8021q_vlan_add(dsa_to_port(ds, port), tx_vid, true); @@ -419,10 +420,9 @@ int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_tx_fwd_offload); void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num) + struct dsa_bridge bridge) { - u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); + u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge.num); dsa_port_tag_8021q_vlan_del(dsa_to_port(ds, port), tx_vid, true); } diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index b3da4b2ea11c..8abf39dcac64 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -132,6 +132,7 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, u8 *dsa_header; if (skb->offload_fwd_mark) { + unsigned int bridge_num = dsa_port_bridge_num_get(dp); struct dsa_switch_tree *dst = dp->ds->dst; cmd = DSA_CMD_FORWARD; @@ -140,7 +141,7 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, * packets on behalf of a virtual switch device with an index * past the physical switches. */ - tag_dev = dst->last_switch + 1 + dp->bridge_num; + tag_dev = dst->last_switch + bridge_num; tag_port = 0; } else { cmd = DSA_CMD_FROM_CPU; @@ -165,7 +166,7 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, dsa_header[2] &= ~0x10; } } else { - struct net_device *br = dp->bridge_dev; + struct net_device *br = dsa_port_bridge_dev_get(dp); u16 vid; vid = br ? MV88E6XXX_VID_BRIDGED : MV88E6XXX_VID_STANDALONE; diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index de1c849a0a70..4ba460c5a880 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -12,7 +12,7 @@ static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, u64 *vlan_tci, u64 *tag_type) { - struct net_device *br = READ_ONCE(dp->bridge_dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); struct vlan_ethhdr *hdr; u16 proto, tci; diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index a1919ea5e828..68982b2789a5 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -12,25 +12,39 @@ #include <linux/dsa/ocelot.h> #include "dsa_priv.h" +struct ocelot_8021q_tagger_private { + struct ocelot_8021q_tagger_data data; /* Must be first */ + struct kthread_worker *xmit_worker; +}; + static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) { + struct ocelot_8021q_tagger_private *priv = dp->ds->tagger_data; + struct ocelot_8021q_tagger_data *data = &priv->data; + void (*xmit_work_fn)(struct kthread_work *work); struct felix_deferred_xmit_work *xmit_work; - struct felix_port *felix_port = dp->priv; + struct kthread_worker *xmit_worker; + + xmit_work_fn = data->xmit_work_fn; + xmit_worker = priv->xmit_worker; + + if (!xmit_work_fn || !xmit_worker) + return NULL; xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); if (!xmit_work) return NULL; /* Calls felix_port_deferred_xmit in felix.c */ - kthread_init_work(&xmit_work->work, felix_port->xmit_work_fn); + kthread_init_work(&xmit_work->work, xmit_work_fn); /* Increase refcount so the kfree_skb in dsa_slave_xmit * won't really free the packet. */ xmit_work->dp = dp; xmit_work->skb = skb_get(skb); - kthread_queue_work(felix_port->xmit_worker, &xmit_work->work); + kthread_queue_work(xmit_worker, &xmit_work->work); return NULL; } @@ -67,11 +81,43 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, return skb; } +static void ocelot_disconnect(struct dsa_switch *ds) +{ + struct ocelot_8021q_tagger_private *priv = ds->tagger_data; + + kthread_destroy_worker(priv->xmit_worker); + kfree(priv); + ds->tagger_data = NULL; +} + +static int ocelot_connect(struct dsa_switch *ds) +{ + struct ocelot_8021q_tagger_private *priv; + int err; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->xmit_worker = kthread_create_worker(0, "felix_xmit"); + if (IS_ERR(priv->xmit_worker)) { + err = PTR_ERR(priv->xmit_worker); + kfree(priv); + return err; + } + + ds->tagger_data = priv; + + return 0; +} + static const struct dsa_device_ops ocelot_8021q_netdev_ops = { .name = "ocelot-8021q", .proto = DSA_TAG_PROTO_OCELOT_8021Q, .xmit = ocelot_xmit, .rcv = ocelot_rcv, + .connect = ocelot_connect, + .disconnect = ocelot_disconnect, .needed_headroom = VLAN_HLEN, .promisc_on_master = true, }; diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 262c8833a910..72d5e0ef8dcf 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -4,7 +4,6 @@ #include <linux/if_vlan.h> #include <linux/dsa/sja1105.h> #include <linux/dsa/8021q.h> -#include <linux/skbuff.h> #include <linux/packing.h> #include "dsa_priv.h" @@ -54,11 +53,25 @@ #define SJA1110_TX_TRAILER_LEN 4 #define SJA1110_MAX_PADDING_LEN 15 -enum sja1110_meta_tstamp { - SJA1110_META_TSTAMP_TX = 0, - SJA1110_META_TSTAMP_RX = 1, +#define SJA1105_HWTS_RX_EN 0 + +struct sja1105_tagger_private { + struct sja1105_tagger_data data; /* Must be first */ + unsigned long state; + /* Protects concurrent access to the meta state machine + * from taggers running on multiple ports on SMP systems + */ + spinlock_t meta_lock; + struct sk_buff *stampable_skb; + struct kthread_worker *xmit_worker; }; +static struct sja1105_tagger_private * +sja1105_tagger_private(struct dsa_switch *ds) +{ + return ds->tagger_data; +} + /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ static inline bool sja1105_is_link_local(const struct sk_buff *skb) { @@ -125,16 +138,30 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) { - struct sja1105_port *sp = dp->priv; + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(dp->ds); + struct sja1105_tagger_private *priv = sja1105_tagger_private(dp->ds); + void (*xmit_work_fn)(struct kthread_work *work); + struct sja1105_deferred_xmit_work *xmit_work; + struct kthread_worker *xmit_worker; - if (!dsa_port_is_sja1105(dp)) - return skb; + xmit_work_fn = tagger_data->xmit_work_fn; + xmit_worker = priv->xmit_worker; + + if (!xmit_work_fn || !xmit_worker) + return NULL; + + xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); + if (!xmit_work) + return NULL; + kthread_init_work(&xmit_work->work, xmit_work_fn); /* Increase refcount so the kfree_skb in dsa_slave_xmit * won't really free the packet. */ - skb_queue_tail(&sp->xmit_queue, skb_get(skb)); - kthread_queue_work(sp->xmit_worker, &sp->xmit_work); + xmit_work->dp = dp; + xmit_work->skb = skb_get(skb); + + kthread_queue_work(xmit_worker, &xmit_work->work); return NULL; } @@ -159,14 +186,16 @@ static u16 sja1105_xmit_tpid(struct dsa_port *dp) * need to find it. */ dsa_switch_for_each_port(other_dp, ds) { - if (!other_dp->bridge_dev) + struct net_device *br = dsa_port_bridge_dev_get(other_dp); + + if (!br) continue; /* Error is returned only if CONFIG_BRIDGE_VLAN_FILTERING, * which seems pointless to handle, as our port cannot become * VLAN-aware in that case. */ - br_vlan_get_proto(other_dp->bridge_dev, &proto); + br_vlan_get_proto(br, &proto); return proto; } @@ -180,7 +209,8 @@ static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, struct net_device *netdev) { struct dsa_port *dp = dsa_slave_to_port(netdev); - struct net_device *br = dp->bridge_dev; + unsigned int bridge_num = dsa_port_bridge_num_get(dp); + struct net_device *br = dsa_port_bridge_dev_get(dp); u16 tx_vid; /* If the port is under a VLAN-aware bridge, just slide the @@ -196,7 +226,7 @@ static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, * TX VLAN that targets the bridge's entire broadcast domain, * instead of just the specific port. */ - tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(dp->bridge_num); + tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), tx_vid); } @@ -352,32 +382,32 @@ static struct sk_buff */ if (is_link_local) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_port *sp = dp->priv; + struct sja1105_tagger_private *priv; + struct dsa_switch *ds = dp->ds; - if (unlikely(!dsa_port_is_sja1105(dp))) - return skb; + priv = sja1105_tagger_private(ds); - if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) + if (!test_bit(SJA1105_HWTS_RX_EN, &priv->state)) /* Do normal processing. */ return skb; - spin_lock(&sp->data->meta_lock); + spin_lock(&priv->meta_lock); /* Was this a link-local frame instead of the meta * that we were expecting? */ - if (sp->data->stampable_skb) { - dev_err_ratelimited(dp->ds->dev, + if (priv->stampable_skb) { + dev_err_ratelimited(ds->dev, "Expected meta frame, is %12llx " "in the DSA master multicast filter?\n", SJA1105_META_DMAC); - kfree_skb(sp->data->stampable_skb); + kfree_skb(priv->stampable_skb); } /* Hold a reference to avoid dsa_switch_rcv * from freeing the skb. */ - sp->data->stampable_skb = skb_get(skb); - spin_unlock(&sp->data->meta_lock); + priv->stampable_skb = skb_get(skb); + spin_unlock(&priv->meta_lock); /* Tell DSA we got nothing */ return NULL; @@ -390,37 +420,37 @@ static struct sk_buff */ } else if (is_meta) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_port *sp = dp->priv; + struct sja1105_tagger_private *priv; + struct dsa_switch *ds = dp->ds; struct sk_buff *stampable_skb; - if (unlikely(!dsa_port_is_sja1105(dp))) - return skb; + priv = sja1105_tagger_private(ds); /* Drop the meta frame if we're not in the right state * to process it. */ - if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) + if (!test_bit(SJA1105_HWTS_RX_EN, &priv->state)) return NULL; - spin_lock(&sp->data->meta_lock); + spin_lock(&priv->meta_lock); - stampable_skb = sp->data->stampable_skb; - sp->data->stampable_skb = NULL; + stampable_skb = priv->stampable_skb; + priv->stampable_skb = NULL; /* Was this a meta frame instead of the link-local * that we were expecting? */ if (!stampable_skb) { - dev_err_ratelimited(dp->ds->dev, + dev_err_ratelimited(ds->dev, "Unexpected meta frame\n"); - spin_unlock(&sp->data->meta_lock); + spin_unlock(&priv->meta_lock); return NULL; } if (stampable_skb->dev != skb->dev) { - dev_err_ratelimited(dp->ds->dev, + dev_err_ratelimited(ds->dev, "Meta frame on wrong port\n"); - spin_unlock(&sp->data->meta_lock); + spin_unlock(&priv->meta_lock); return NULL; } @@ -431,12 +461,36 @@ static struct sk_buff skb = stampable_skb; sja1105_transfer_meta(skb, meta); - spin_unlock(&sp->data->meta_lock); + spin_unlock(&priv->meta_lock); } return skb; } +static bool sja1105_rxtstamp_get_state(struct dsa_switch *ds) +{ + struct sja1105_tagger_private *priv = sja1105_tagger_private(ds); + + return test_bit(SJA1105_HWTS_RX_EN, &priv->state); +} + +static void sja1105_rxtstamp_set_state(struct dsa_switch *ds, bool on) +{ + struct sja1105_tagger_private *priv = sja1105_tagger_private(ds); + + if (on) + set_bit(SJA1105_HWTS_RX_EN, &priv->state); + else + clear_bit(SJA1105_HWTS_RX_EN, &priv->state); + + /* Initialize the meta state machine to a known state */ + if (!priv->stampable_skb) + return; + + kfree_skb(priv->stampable_skb); + priv->stampable_skb = NULL; +} + static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) { u16 tpid = ntohs(eth_hdr(skb)->h_proto); @@ -523,48 +577,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } -static void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, - u8 ts_id, enum sja1110_meta_tstamp dir, - u64 tstamp) -{ - struct sk_buff *skb, *skb_tmp, *skb_match = NULL; - struct dsa_port *dp = dsa_to_port(ds, port); - struct skb_shared_hwtstamps shwt = {0}; - struct sja1105_port *sp = dp->priv; - - if (!dsa_port_is_sja1105(dp)) - return; - - /* We don't care about RX timestamps on the CPU port */ - if (dir == SJA1110_META_TSTAMP_RX) - return; - - spin_lock(&sp->data->skb_txtstamp_queue.lock); - - skb_queue_walk_safe(&sp->data->skb_txtstamp_queue, skb, skb_tmp) { - if (SJA1105_SKB_CB(skb)->ts_id != ts_id) - continue; - - __skb_unlink(skb, &sp->data->skb_txtstamp_queue); - skb_match = skb; - - break; - } - - spin_unlock(&sp->data->skb_txtstamp_queue.lock); - - if (WARN_ON(!skb_match)) - return; - - shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); - skb_complete_tx_timestamp(skb_match, &shwt); -} - static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) { u8 *buf = dsa_etype_header_pos_rx(skb) + SJA1110_HEADER_LEN; int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); + struct sja1105_tagger_data *tagger_data; struct net_device *master = skb->dev; struct dsa_port *cpu_dp; struct dsa_switch *ds; @@ -578,6 +596,10 @@ static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) return NULL; } + tagger_data = sja1105_tagger_data(ds); + if (!tagger_data->meta_tstamp_handler) + return NULL; + for (i = 0; i <= n_ts; i++) { u8 ts_id, source_port, dir; u64 tstamp; @@ -587,8 +609,8 @@ static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) dir = (buf[1] & BIT(3)) >> 3; tstamp = be64_to_cpu(*(__be64 *)(buf + 2)); - sja1110_process_meta_tstamp(ds, source_port, ts_id, dir, - tstamp); + tagger_data->meta_tstamp_handler(ds, source_port, ts_id, dir, + tstamp); buf += SJA1110_META_TSTAMP_SIZE; } @@ -719,11 +741,53 @@ static void sja1110_flow_dissect(const struct sk_buff *skb, __be16 *proto, *proto = ((__be16 *)skb->data)[(VLAN_HLEN / 2) - 1]; } +static void sja1105_disconnect(struct dsa_switch *ds) +{ + struct sja1105_tagger_private *priv = ds->tagger_data; + + kthread_destroy_worker(priv->xmit_worker); + kfree(priv); + ds->tagger_data = NULL; +} + +static int sja1105_connect(struct dsa_switch *ds) +{ + struct sja1105_tagger_data *tagger_data; + struct sja1105_tagger_private *priv; + struct kthread_worker *xmit_worker; + int err; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + spin_lock_init(&priv->meta_lock); + + xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit", + ds->dst->index, ds->index); + if (IS_ERR(xmit_worker)) { + err = PTR_ERR(xmit_worker); + kfree(priv); + return err; + } + + priv->xmit_worker = xmit_worker; + /* Export functions for switch driver use */ + tagger_data = &priv->data; + tagger_data->rxtstamp_get_state = sja1105_rxtstamp_get_state; + tagger_data->rxtstamp_set_state = sja1105_rxtstamp_set_state; + ds->tagger_data = priv; + + return 0; +} + static const struct dsa_device_ops sja1105_netdev_ops = { .name = "sja1105", .proto = DSA_TAG_PROTO_SJA1105, .xmit = sja1105_xmit, .rcv = sja1105_rcv, + .connect = sja1105_connect, + .disconnect = sja1105_disconnect, .needed_headroom = VLAN_HLEN, .flow_dissect = sja1105_flow_dissect, .promisc_on_master = true, @@ -737,6 +801,8 @@ static const struct dsa_device_ops sja1110_netdev_ops = { .proto = DSA_TAG_PROTO_SJA1110, .xmit = sja1110_xmit, .rcv = sja1110_rcv, + .connect = sja1105_connect, + .disconnect = sja1105_disconnect, .flow_dissect = sja1110_flow_dissect, .needed_headroom = SJA1110_HEADER_LEN + VLAN_HLEN, .needed_tailroom = SJA1110_RX_TRAILER_LEN + SJA1110_MAX_PADDING_LEN, diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 63560bbb7d1f..920aac02fe39 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -96,7 +96,7 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) out_rtnl: rtnl_unlock(); out_dev_put: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } @@ -353,7 +353,7 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) out_rtnl: rtnl_unlock(); out_dev_put: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 6a070dc8e4b0..403158862011 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -219,6 +219,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 46776ea42a92..487bdf345541 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -336,6 +336,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/debug.c b/net/ethtool/debug.c index f99912d7957e..d73888c7d19c 100644 --- a/net/ethtool/debug.c +++ b/net/ethtool/debug.c @@ -123,6 +123,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index e10bfcc07853..45c42b2d5f17 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -185,6 +185,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 2e7331b23996..55d449a2d3fc 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -283,6 +283,6 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) out_rtnl: rtnl_unlock(); - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/fec.c b/net/ethtool/fec.c index 8738dafd5417..9f5a134e2e01 100644 --- a/net/ethtool/fec.c +++ b/net/ethtool/fec.c @@ -305,6 +305,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c index b91839870efc..efa0f7f48836 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -149,6 +149,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index f9eda596f301..99b29b4fe947 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -358,6 +358,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/module.c b/net/ethtool/module.c index bc2cef11bbda..898ed436b9e4 100644 --- a/net/ethtool/module.c +++ b/net/ethtool/module.c @@ -175,6 +175,6 @@ out_ops: ethnl_ops_complete(dev); out_rtnl: rtnl_unlock(); - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index eaa50af074be..f09c62302a9a 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -40,7 +40,8 @@ int ethnl_ops_begin(struct net_device *dev) if (dev->dev.parent) pm_runtime_get_sync(dev->dev.parent); - if (!netif_device_present(dev)) { + if (!netif_device_present(dev) || + dev->reg_state == NETREG_UNREGISTERING) { ret = -ENODEV; goto err; } @@ -141,7 +142,8 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, } req_info->dev = dev; - netdev_tracker_alloc(dev, &req_info->dev_tracker, GFP_KERNEL); + if (dev) + netdev_tracker_alloc(dev, &req_info->dev_tracker, GFP_KERNEL); req_info->flags = flags; return 0; } diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index a779bbb0c524..75856db299e9 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -235,6 +235,11 @@ struct ethnl_req_info { u32 flags; }; +static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) +{ + dev_put_track(req_info->dev, &req_info->dev_tracker); +} + /** * struct ethnl_reply_data - base type of reply data for GET requests * @dev: device for current reply message; in single shot requests it is diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index ee1e5806bc93..a8c113d244db 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -181,6 +181,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/privflags.c b/net/ethtool/privflags.c index fc9f3be23a19..4c7bfa81e4ab 100644 --- a/net/ethtool/privflags.c +++ b/net/ethtool/privflags.c @@ -196,6 +196,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index 450b8866373d..c1d5f5e0fdc9 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -196,6 +196,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c index e7f2ee0d2471..efde33536687 100644 --- a/net/ethtool/tunnels.c +++ b/net/ethtool/tunnels.c @@ -195,7 +195,7 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto err_free_msg; rtnl_unlock(); - dev_put(req_info.dev); + ethnl_parse_header_dev_put(&req_info); genlmsg_end(rskb, reply_payload); return genlmsg_reply(rskb, info); @@ -204,7 +204,7 @@ err_free_msg: nlmsg_free(rskb); err_unlock_rtnl: rtnl_unlock(); - dev_put(req_info.dev); + ethnl_parse_header_dev_put(&req_info); return ret; } @@ -230,7 +230,7 @@ int ethnl_tunnel_info_start(struct netlink_callback *cb) sock_net(cb->skb->sk), cb->extack, false); if (ctx->req_info.dev) { - dev_put(ctx->req_info.dev); + ethnl_parse_header_dev_put(&ctx->req_info); ctx->req_info.dev = NULL; } diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c index ada7df2331d2..88f435e76481 100644 --- a/net/ethtool/wol.c +++ b/net/ethtool/wol.c @@ -165,6 +165,6 @@ out_ops: out_rtnl: rtnl_unlock(); out_dev: - dev_put(dev); + ethnl_parse_header_dev_put(&req_info); return ret; } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 4bb9401b0a3f..de610cb83694 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -169,7 +169,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) t = bpf_tcp_congestion_ops.type; m = &btf_type_member(t)[midx]; - return btf_member_bit_offset(t, m) / 8; + return __btf_member_bit_offset(t, m) / 8; } static const struct bpf_func_proto * @@ -246,7 +246,7 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, utcp_ca = (const struct tcp_congestion_ops *)udata; tcp_ca = (struct tcp_congestion_ops *)kdata; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; switch (moff) { case offsetof(struct tcp_congestion_ops, flags): if (utcp_ca->flags & ~TCP_CONG_MASK) @@ -276,7 +276,7 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, static int bpf_tcp_ca_check_member(const struct btf_type *t, const struct btf_member *member) { - if (is_unsupported(btf_member_bit_offset(t, member) / 8)) + if (is_unsupported(__btf_member_bit_offset(t, member) / 8)) return -ENOTSUPP; return 0; } diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index d279cb8ac158..e0b6c8b6de57 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -216,11 +216,6 @@ static struct fib_table *fib_empty_table(struct net *net) return NULL; } -static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { - FRA_GENERIC_POLICY, - [FRA_FLOW] = { .type = NLA_U32 }, -}; - static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, @@ -386,7 +381,6 @@ static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .nlmsg_payload = fib4_rule_nlmsg_payload, .flush_cache = fib4_rule_flush_cache, .nlgroup = RTNLGRP_IPV4_RULE, - .policy = fib4_rule_policy, .owner = THIS_MODULE, }; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 23da67a3fc06..fc2a985f6064 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -721,7 +721,7 @@ static struct request_sock *inet_reqsk_clone(struct request_sock *req, sk_node_init(&nreq_sk->sk_node); nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; -#ifdef CONFIG_XPS +#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping; #endif nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index c8fa6e7f7d12..581b5b2d72a5 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -261,6 +261,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_state = sk->sk_state; r->idiag_timer = 0; r->idiag_retrans = 0; + r->idiag_expires = 0; if (inet_diag_msg_attrs_fill(sk, skb, r, ext, sk_user_ns(NETLINK_CB(cb->skb).sk), @@ -314,9 +315,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies); - } else { - r->idiag_timer = 0; - r->idiag_expires = 0; } if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 4c7aca884fa9..07274619b9ea 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -195,10 +195,6 @@ static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) return 1; } -static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = { - FRA_GENERIC_POLICY, -}; - static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) @@ -231,7 +227,6 @@ static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = { .compare = ipmr_rule_compare, .fill = ipmr_rule_fill, .nlgroup = RTNLGRP_IPV4_RULE, - .policy = ipmr_rule_policy, .owner = THIS_MODULE, }; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index cf913a66df17..7c2d3ac2363a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -829,8 +829,8 @@ int tcp_child_process(struct sock *parent, struct sock *child, int ret = 0; int state = child->sk_state; - /* record NAPI ID of child */ - sk_mark_napi_id(child, skb); + /* record sk_napi_id and sk_rx_queue_mapping of child. */ + sk_mark_napi_id_set(child, skb); tcp_segs_in(tcp_sk(child), skb); if (!sock_owned_by_user(child)) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 799b663daf87..69d30053fed9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -916,7 +916,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, kfree_skb(skb); return -EINVAL; } - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 9ebd54752e03..9e83bcb6bc99 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -77,7 +77,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_iif = fl4->flowi4_iif; xdst->u.dst.dev = dev; - dev_hold(dev); + dev_hold_track(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index dcedfe29d9d9..ec029c86ae06 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -340,10 +340,6 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, return 1; } -static const struct nla_policy fib6_rule_policy[FRA_MAX+1] = { - FRA_GENERIC_POLICY, -}; - static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, @@ -459,7 +455,6 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, .nlgroup = RTNLGRP_IPV6_RULE, - .policy = fib6_rule_policy, .owner = THIS_MODULE, .fro_net = &init_net, }; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index a77a15a7f3dc..7cf73e60e619 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -182,10 +182,6 @@ static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags) return 1; } -static const struct nla_policy ip6mr_rule_policy[FRA_MAX + 1] = { - FRA_GENERIC_POLICY, -}; - static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, struct netlink_ext_ack *extack) @@ -218,7 +214,6 @@ static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = { .compare = ip6mr_rule_compare, .fill = ip6mr_rule_fill, .nlgroup = RTNLGRP_IPV6_RULE, - .policy = ip6mr_rule_policy, .owner = THIS_MODULE, }; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4d02a329ab60..03be0e6b4826 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -658,7 +658,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; - dev_hold_track(dev, &work->dev_tracker, GFP_KERNEL); + dev_hold_track(dev, &work->dev_tracker, GFP_ATOMIC); work->dev = dev; schedule_work(&work->work); } diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 3adc5d9211ad..d64855010948 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -161,6 +161,14 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + + /* the control block has been erased, so we have to set the + * iif once again. + * We read the receiving interface index directly from the + * skb->skb_iif as it is done in the IPv4 receiving path (i.e.: + * ip_rcv_core(...)). + */ + IP6CB(skb)->iif = skb->skb_iif; } hdr->nexthdr = NEXTHDR_ROUTING; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 057c0f83c800..a618dce7e0bc 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1933,7 +1933,6 @@ static int __net_init sit_init_net(struct net *net) return 0; err_reg_dev: - ipip6_dev_free(sitn->fb_tunnel_dev); free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index af7a4b8b1e9c..fad687ee6dd8 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -74,11 +74,11 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, struct rt6_info *rt = (struct rt6_info *)xdst->route; xdst->u.dst.dev = dev; - dev_hold(dev); + dev_hold_track(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); xdst->u.rt6.rt6i_idev = in6_dev_get(dev); if (!xdst->u.rt6.rt6i_idev) { - dev_put(dev); + dev_put_track(dev, &xdst->u.dst.dev_tracker); return -ENODEV; } diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index acf6e1343b88..9d1aafe75f92 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -32,7 +32,8 @@ static struct dentry *rootdir; struct l2tp_dfs_seq_data { - struct net *net; + struct net *net; + netns_tracker ns_tracker; int tunnel_idx; /* current tunnel */ int session_idx; /* index of session within current tunnel */ struct l2tp_tunnel *tunnel; @@ -281,7 +282,7 @@ static int l2tp_dfs_seq_open(struct inode *inode, struct file *file) rc = PTR_ERR(pd->net); goto err_free_pd; } - + netns_tracker_alloc(pd->net, &pd->ns_tracker, GFP_KERNEL); rc = seq_open(file, &l2tp_dfs_seq_ops); if (rc) goto err_free_net; @@ -293,7 +294,7 @@ out: return rc; err_free_net: - put_net(pd->net); + put_net_track(pd->net, &pd->ns_tracker); err_free_pd: kfree(pd); goto out; @@ -307,7 +308,7 @@ static int l2tp_dfs_seq_release(struct inode *inode, struct file *file) seq = file->private_data; pd = seq->private; if (pd->net) - put_net(pd->net); + put_net_track(pd->net, &pd->ns_tracker); kfree(pd); seq_release(inode, file); diff --git a/net/llc/llc_proc.c b/net/llc/llc_proc.c index 0ff490a73fae..07e9abb5978a 100644 --- a/net/llc/llc_proc.c +++ b/net/llc/llc_proc.c @@ -195,7 +195,7 @@ static int llc_seq_core_show(struct seq_file *seq, void *v) timer_pending(&llc->pf_cycle_timer.timer), timer_pending(&llc->rej_sent_timer.timer), timer_pending(&llc->busy_state_timer.timer), - !!sk->sk_backlog.tail, !!sk->sk_lock.owned); + !!sk->sk_backlog.tail, sock_owned_by_user_nocheck(sk)); out: return 0; } diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 470ff0ce3dc7..7d2925bb966e 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ /** @@ -191,7 +191,8 @@ static void ieee80211_add_addbaext(struct ieee80211_sub_if_data *sdata, sband = ieee80211_get_sband(sdata); if (!sband) return; - he_cap = ieee80211_get_he_iftype_cap(sband, sdata->vif.type); + he_cap = ieee80211_get_he_iftype_cap(sband, + ieee80211_vif_type_p2p(&sdata->vif)); if (!he_cap) return; diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 430a58587538..74a878f213d3 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2020 Intel Corporation + * Copyright (C) 2018 - 2021 Intel Corporation */ #include <linux/ieee80211.h> @@ -106,7 +106,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, mgmt->u.action.u.addba_req.start_seq_num = cpu_to_le16(start_seq_num << 4); - ieee80211_tx_skb(sdata, skb); + ieee80211_tx_skb_tid(sdata, skb, tid); } void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn) @@ -213,6 +213,8 @@ ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable) struct ieee80211_txq *txq = sta->sta.txq[tid]; struct txq_info *txqi; + lockdep_assert_held(&sta->ampdu_mlme.mtx); + if (!txq) return; @@ -290,7 +292,6 @@ static void ieee80211_remove_tid_tx(struct sta_info *sta, int tid) ieee80211_assign_tid_tx(sta, tid, NULL); ieee80211_agg_splice_finish(sta->sdata, tid); - ieee80211_agg_start_txq(sta, tid, false); kfree_rcu(tid_tx, rcu_head); } @@ -480,8 +481,7 @@ static void ieee80211_send_addba_with_timeout(struct sta_info *sta, /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, - tid_tx->dialog_token, - sta->tid_seq[tid] >> 4, + tid_tx->dialog_token, tid_tx->ssn, buf_size, tid_tx->timeout); WARN_ON(test_and_set_bit(HT_AGG_STATE_SENT_ADDBA, &tid_tx->state)); @@ -523,6 +523,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) params.ssn = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, ¶ms); + tid_tx->ssn = params.ssn; if (ret == IEEE80211_AMPDU_TX_START_DELAY_ADDBA) { return; } else if (ret == IEEE80211_AMPDU_TX_START_IMMEDIATE) { @@ -889,6 +890,7 @@ void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, { struct ieee80211_sub_if_data *sdata = sta->sdata; bool send_delba = false; + bool start_txq = false; ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n", sta->sta.addr, tid); @@ -906,10 +908,14 @@ void ieee80211_stop_tx_ba_cb(struct sta_info *sta, int tid, send_delba = true; ieee80211_remove_tid_tx(sta, tid); + start_txq = true; unlock_sta: spin_unlock_bh(&sta->lock); + if (start_txq) + ieee80211_agg_start_txq(sta, tid, false); + if (send_delba) ieee80211_send_delba(sdata, sta->sta.addr, tid, WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index cd3731cbf6c6..c336267f4599 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1219,8 +1219,11 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, { struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif); - if (local->in_reconfig) + /* In reconfig don't transmit now, but mark for waking later */ + if (local->in_reconfig) { + set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txq->flags); return; + } if (!check_sdata_in_driver(sdata)) return; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 54ab0e1ef6ca..37f7d975f3da 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2452,11 +2452,18 @@ static void ieee80211_sta_tx_wmm_ac_notify(struct ieee80211_sub_if_data *sdata, u16 tx_time) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - u16 tid = ieee80211_get_tid(hdr); - int ac = ieee80211_ac_from_tid(tid); - struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac]; + u16 tid; + int ac; + struct ieee80211_sta_tx_tspec *tx_tspec; unsigned long now = jiffies; + if (!ieee80211_is_data_qos(hdr->frame_control)) + return; + + tid = ieee80211_get_tid(hdr); + ac = ieee80211_ac_from_tid(tid); + tx_tspec = &ifmgd->tx_tspec[ac]; + if (likely(!tx_tspec->admitted_time)) return; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 9541a4c30aca..0544563ede52 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2944,6 +2944,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (!fwd_skb) goto out; + fwd_skb->dev = sdata->dev; fwd_hdr = (struct ieee80211_hdr *) fwd_skb->data; fwd_hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_RETRY); info = IEEE80211_SKB_CB(fwd_skb); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 51b49f0d3ad4..537535a88990 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -644,13 +644,13 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) /* check if STA exists already */ if (sta_info_get_bss(sdata, sta->sta.addr)) { err = -EEXIST; - goto out_err; + goto out_cleanup; } sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL); if (!sinfo) { err = -ENOMEM; - goto out_err; + goto out_cleanup; } local->num_sta++; @@ -667,6 +667,15 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) list_add_tail_rcu(&sta->list, &local->sta_list); + /* update channel context before notifying the driver about state + * change, this enables driver using the updated channel context right away. + */ + if (sta->sta_state >= IEEE80211_STA_ASSOC) { + ieee80211_recalc_min_chandef(sta->sdata); + if (!sta->sta.support_p2p_ps) + ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); + } + /* notify driver */ err = sta_info_insert_drv_state(local, sdata, sta); if (err) @@ -674,12 +683,6 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) set_sta_flag(sta, WLAN_STA_INSERTED); - if (sta->sta_state >= IEEE80211_STA_ASSOC) { - ieee80211_recalc_min_chandef(sta->sdata); - if (!sta->sta.support_p2p_ps) - ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); - } - /* accept BA sessions now */ clear_sta_flag(sta, WLAN_STA_BLOCK_BA); @@ -706,8 +709,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) out_drop_sta: local->num_sta--; synchronize_net(); + out_cleanup: cleanup_single_sta(sta); - out_err: mutex_unlock(&local->sta_mtx); kfree(sinfo); rcu_read_lock(); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index ba2796782008..379fd367197f 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -176,6 +176,7 @@ struct sta_info; * @failed_bar_ssn: ssn of the last failed BAR tx attempt * @bar_pending: BAR needs to be re-sent * @amsdu: support A-MSDU withing A-MDPU + * @ssn: starting sequence number of the session * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. @@ -199,6 +200,7 @@ struct tid_ampdu_tx { u8 stop_initiator; bool tx_stop; u16 buf_size; + u16 ssn; u16 failed_bar_ssn; bool bar_pending; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 278945e3e08a..86a54df3aabd 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1822,15 +1822,15 @@ static int invoke_tx_handlers_late(struct ieee80211_tx_data *tx) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb); ieee80211_tx_result res = TX_CONTINUE; + if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL)) + CALL_TXH(ieee80211_tx_h_rate_ctrl); + if (unlikely(info->flags & IEEE80211_TX_INTFL_RETRANSMISSION)) { __skb_queue_tail(&tx->skbs, tx->skb); tx->skb = NULL; goto txh_done; } - if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL)) - CALL_TXH(ieee80211_tx_h_rate_ctrl); - CALL_TXH(ieee80211_tx_h_michael_mic_add); CALL_TXH(ieee80211_tx_h_sequence); CALL_TXH(ieee80211_tx_h_fragment); @@ -4191,11 +4191,11 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, ieee80211_aggr_check(sdata, sta, skb); + sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift); + if (sta) { struct ieee80211_fast_tx *fast_tx; - sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift); - fast_tx = rcu_dereference(sta->fast_tx); if (fast_tx && diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 43df2f0c5db9..0e4e1956bcea 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -943,7 +943,12 @@ static void ieee80211_parse_extension_element(u32 *crc, struct ieee802_11_elems *elems) { const void *data = elem->data + 1; - u8 len = elem->datalen - 1; + u8 len; + + if (!elem->datalen) + return; + + len = elem->datalen - 1; switch (elem->data[0]) { case WLAN_EID_EXT_HE_MU_EDCA: @@ -2063,7 +2068,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, chandef.chan = chan; skb = ieee80211_probereq_get(&local->hw, src, ssid, ssid_len, - 100 + ie_len); + local->scan_ies_len + ie_len); if (!skb) return NULL; @@ -2646,6 +2651,13 @@ int ieee80211_reconfig(struct ieee80211_local *local) mutex_unlock(&local->sta_mtx); } + /* + * If this is for hw restart things are still running. + * We may want to change that later, however. + */ + if (local->open_count && (!suspended || reconfig_due_to_wowlan)) + drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART); + if (local->in_reconfig) { local->in_reconfig = false; barrier(); @@ -2664,13 +2676,6 @@ int ieee80211_reconfig(struct ieee80211_local *local) IEEE80211_QUEUE_STOP_REASON_SUSPEND, false); - /* - * If this is for hw restart things are still running. - * We may want to change that later, however. - */ - if (local->open_count && (!suspended || reconfig_due_to_wowlan)) - drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART); - if (!suspended) return 0; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 4ff8d55cbe82..3186d33b5208 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -700,6 +700,9 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, msk_owned_by_me(msk); + if (sk->sk_state == TCP_LISTEN) + return; + if (!rm_list->nr) return; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f124cca125d2..3e549f6190c0 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1527,7 +1527,7 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) int ret = 0; prev_ssk = ssk; - mptcp_flush_join_list(msk); + __mptcp_flush_join_list(msk); ssk = mptcp_subflow_get_send(msk); /* First check. If the ssk has changed since @@ -2914,7 +2914,7 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, */ if (WARN_ON_ONCE(!new_mptcp_sock)) { tcp_sk(newsk)->is_mptcp = 0; - return newsk; + goto out; } /* acquire the 2nd reference for the owning socket */ @@ -2926,6 +2926,8 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); } +out: + newsk->sk_kern_sock = kern; return newsk; } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 3c3db22fd36a..aa3fcd86dbe2 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -543,7 +543,6 @@ static bool mptcp_supported_sockopt(int level, int optname) case TCP_NODELAY: case TCP_THIN_LINEAR_TIMEOUTS: case TCP_CONGESTION: - case TCP_ULP: case TCP_CORK: case TCP_KEEPIDLE: case TCP_KEEPINTVL: diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index b8dd3441f7d0..24bc9d5e87be 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1534,7 +1534,7 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) * needs it. */ sf->sk->sk_net_refcnt = 1; - get_net(net); + get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); err = tcp_set_ulp(sf->sk, "mptcp"); release_sock(sf->sk); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 39c523bd775c..7f645328b47f 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -960,8 +960,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, * Create a destination for the given service */ static int -ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, - struct ip_vs_dest **dest_p) +ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) { struct ip_vs_dest *dest; unsigned int atype, i; @@ -1021,8 +1020,6 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, spin_lock_init(&dest->stats.lock); __ip_vs_update_dest(svc, dest, udest, 1); - *dest_p = dest; - LeaveFunction(2); return 0; @@ -1096,7 +1093,7 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) /* * Allocate and initialize the dest structure */ - ret = ip_vs_new_dest(svc, udest, &dest); + ret = ip_vs_new_dest(svc, udest); } LeaveFunction(2); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 054ee9d25efe..d7e313548066 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -684,7 +684,7 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report) tstamp = nf_conn_tstamp_find(ct); if (tstamp) { - s32 timeout = ct->timeout - nfct_time_stamp; + s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp; tstamp->stop = ktime_get_real_ns(); if (timeout < 0) @@ -1036,7 +1036,7 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) } /* We want the clashing entry to go away real soon: 1 second timeout. */ - loser_ct->timeout = nfct_time_stamp + HZ; + WRITE_ONCE(loser_ct->timeout, nfct_time_stamp + HZ); /* IPS_NAT_CLASH removes the entry automatically on the first * reply. Also prevents UDP tracker from moving the entry to @@ -1560,11 +1560,9 @@ __nf_conntrack_alloc(struct net *net, /* save hash for reusing when confirming */ *(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash; ct->status = 0; - ct->timeout = 0; + WRITE_ONCE(ct->timeout, 0); write_pnet(&ct->ct_net, net); - memset(&ct->__nfct_init_offset, 0, - offsetof(struct nf_conn, proto) - - offsetof(struct nf_conn, __nfct_init_offset)); + memset_after(ct, 0, __nfct_init_offset); nf_ct_zone_add(ct, zone); @@ -2590,7 +2588,6 @@ int nf_conntrack_hash_resize(unsigned int hashsize) hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]); } } - old_size = nf_conntrack_htable_size; old_hash = nf_conntrack_hash; nf_conntrack_hash = hash; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 849fa7f4353c..4f53d9480ed5 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1746,7 +1746,7 @@ restart: res = ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), - ct, dying ? true : false, 0); + ct, dying, 0); if (res < 0) { if (!atomic_inc_not_zero(&ct->ct_general.use)) continue; @@ -1998,7 +1998,7 @@ static int ctnetlink_change_timeout(struct nf_conn *ct, if (timeout > INT_MAX) timeout = INT_MAX; - ct->timeout = nfct_time_stamp + (u32)timeout; + WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout); if (test_bit(IPS_DYING_BIT, &ct->status)) return -ETIME; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 87a7388b6c89..ed37bb9b4e58 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -201,8 +201,8 @@ static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) if (timeout < 0) timeout = 0; - if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout) - ct->timeout = nfct_time_stamp + timeout; + if (nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout) + WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout); } static void flow_offload_fixup_ct_state(struct nf_conn *ct) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 4acc4b8e9fe5..08771f47d469 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -387,7 +387,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct net_device *indev; struct net_device *outdev; struct nf_conn *ct = NULL; - enum ip_conntrack_info ctinfo; + enum ip_conntrack_info ctinfo = 0; struct nfnl_ct_hook *nfnl_ct; bool csum_verify; char *secdata = NULL; @@ -1527,15 +1527,9 @@ static void __net_exit nfnl_queue_net_exit(struct net *net) WARN_ON_ONCE(!hlist_empty(&q->instance_table[i])); } -static void nfnl_queue_net_exit_batch(struct list_head *net_exit_list) -{ - synchronize_rcu(); -} - static struct pernet_operations nfnl_queue_net_ops = { .init = nfnl_queue_net_init, .exit = nfnl_queue_net_exit, - .exit_batch = nfnl_queue_net_exit_batch, .id = &nfnl_queue_net_id, .size = sizeof(struct nfnl_queue_net), }; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index af4ee874a067..dbe1f2e7dd9e 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -236,7 +236,7 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len); if (!tcph) - return; + goto err; opt = (u8 *)tcph; for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) { @@ -251,16 +251,16 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, continue; if (i + optl > tcphdr_len || priv->len + priv->offset > optl) - return; + goto err; if (skb_ensure_writable(pkt->skb, nft_thoff(pkt) + i + priv->len)) - return; + goto err; tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len); if (!tcph) - return; + goto err; offset = i + priv->offset; @@ -303,6 +303,9 @@ static void nft_exthdr_tcp_set_eval(const struct nft_expr *expr, return; } + return; +err: + regs->verdict.code = NFT_BREAK; } static void nft_exthdr_sctp_eval(const struct nft_expr *expr, diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index cd59afde5b2f..fa9301ca6033 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -27,9 +27,11 @@ static void nft_fwd_netdev_eval(const struct nft_expr *expr, { struct nft_fwd_netdev *priv = nft_expr_priv(expr); int oif = regs->data[priv->sreg_dev]; + struct sk_buff *skb = pkt->skb; /* This is used by ifb only. */ - skb_set_redirected(pkt->skb, true); + skb->skb_iif = skb->dev->ifindex; + skb_set_redirected(skb, nft_hook(pkt) == NF_NETDEV_INGRESS); nf_fwd_netdev_egress(pkt, oif); regs->verdict.code = NF_STOLEN; @@ -198,7 +200,8 @@ static int nft_fwd_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { - return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS)); + return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS) | + (1 << NF_NETDEV_EGRESS)); } static struct nft_expr_type nft_fwd_netdev_type; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index e517663e0cd1..6f4116e72958 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -886,7 +886,7 @@ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill, NFT_PIPAPO_AVX2_BUCKET_LOAD8(4, lt, 4, pkt[4], bsize); NFT_PIPAPO_AVX2_AND(5, 0, 1); - NFT_PIPAPO_AVX2_BUCKET_LOAD8(6, lt, 6, pkt[5], bsize); + NFT_PIPAPO_AVX2_BUCKET_LOAD8(6, lt, 5, pkt[5], bsize); NFT_PIPAPO_AVX2_AND(7, 2, 3); /* Stall */ diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 334f63c9529e..f184b0db79d4 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -636,8 +636,10 @@ static int nfc_genl_dump_devices_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; - nfc_device_iter_exit(iter); - kfree(iter); + if (iter) { + nfc_device_iter_exit(iter); + kfree(iter); + } return 0; } @@ -1392,8 +1394,10 @@ static int nfc_genl_dump_ses_done(struct netlink_callback *cb) { struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; - nfc_device_iter_exit(iter); - kfree(iter); + if (iter) { + nfc_device_iter_exit(iter); + kfree(iter); + } return 0; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a1ffdb48cc47..59c265b8ac26 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3109,7 +3109,7 @@ static int packet_release(struct socket *sock) packet_cached_dev_reset(po); if (po->prot_hook.dev) { - dev_put(po->prot_hook.dev); + dev_put_track(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); @@ -3217,18 +3217,25 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; + dev_put_track(dev_curr, &po->prot_hook.dev_tracker); + dev_curr = NULL; + if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { + if (dev) + netdev_tracker_alloc(dev, + &po->prot_hook.dev_tracker, + GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } - dev_put(dev_curr); + dev_put_track(dev_curr, &po->prot_hook.dev_tracker); if (proto == 0 || !need_rehook) goto out_unlock; @@ -4138,7 +4145,8 @@ static int packet_notifier(struct notifier_block *this, if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); - dev_put(po->prot_hook.dev); + dev_put_track(po->prot_hook.dev, + &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); @@ -4488,9 +4496,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } out_free_pg_vec: - bitmap_free(rx_owner_map); - if (pg_vec) + if (pg_vec) { + bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); + } out: return err; } diff --git a/net/phonet/pep.c b/net/phonet/pep.c index a1525916885a..b4f90afb0638 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -868,6 +868,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, err = pep_accept_conn(newsk, skb); if (err) { + __sock_put(sk); sock_put(newsk); newsk = NULL; goto drop; diff --git a/net/rds/connection.c b/net/rds/connection.c index a3bc4b54d491..b4cc699c5fad 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -253,6 +253,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, * should end up here, but if it * does, reset/destroy the connection. */ + kfree(conn->c_path); kmem_cache_free(rds_conn_slab, conn); conn = ERR_PTR(-EOPNOTSUPP); goto out; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 2ef8f5a6205a..e54f0a42270c 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3687,6 +3687,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->mpls_mangle.ttl = tcf_mpls_ttl(act); break; default: + err = -EOPNOTSUPP; goto err_out_locked; } } else if (is_tcf_skbedit_ptype(act)) { diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 3c2300d14468..857aaebd49f4 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2736,7 +2736,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) - goto nomem; + return -ENOMEM; for (i = 0; i < CAKE_MAX_TINS; i++) { struct cake_tin_data *b = q->tins + i; @@ -2766,10 +2766,6 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, q->min_netlen = ~0; q->min_adjlen = ~0; return 0; - -nomem: - cake_destroy(sch); - return -ENOMEM; } static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index e007fc75ef2f..d73393493553 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -666,9 +666,9 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, } } for (i = q->nbands; i < oldbands; i++) { - qdisc_tree_flush_backlog(q->classes[i].qdisc); - if (i >= q->nstrict) + if (i >= q->nstrict && q->classes[i].qdisc->q.qlen) list_del(&q->classes[i].alist); + qdisc_tree_flush_backlog(q->classes[i].qdisc); } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 830f3559f727..d6aba6edd16e 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -531,6 +531,7 @@ static void fq_pie_destroy(struct Qdisc *sch) struct fq_pie_sched_data *q = qdisc_priv(sch); tcf_block_put(q->block); + q->p_params.tupdate = 0; del_timer_sync(&q->adapt_timer); kvfree(q->flows); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 67a78bbf305f..ba9d1a8ebb4a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -194,7 +194,9 @@ static int smc_release(struct socket *sock) /* cleanup for a dangling non-blocking connect */ if (smc->connect_nonblock && sk->sk_state == SMC_INIT) tcp_abort(smc->clcsock->sk, ECONNABORTED); - flush_work(&smc->connect_work); + + if (cancel_work_sync(&smc->connect_work)) + sock_put(&smc->sk); /* sock_hold in smc_connect for passive closing */ if (sk->sk_state == SMC_LISTEN) /* smc_close_non_accepted() is called and acquires diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 60bc74b76adc..473a790f5894 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -787,7 +787,7 @@ int tipc_attach_loopback(struct net *net) if (!dev) return -ENODEV; - dev_hold(dev); + dev_hold_track(dev, &tn->loopback_pt.dev_tracker, GFP_KERNEL); tn->loopback_pt.dev = dev; tn->loopback_pt.type = htons(ETH_P_TIPC); tn->loopback_pt.func = tipc_loopback_rcv_pkt; @@ -800,7 +800,7 @@ void tipc_detach_loopback(struct net *net) struct tipc_net *tn = tipc_net(net); dev_remove_pack(&tn->loopback_pt); - dev_put(net->loopback_dev); + dev_put_track(net->loopback_dev, &tn->loopback_pt.dev_tracker); } /* Caller should hold rtnl_lock to protect the bearer */ diff --git a/net/tipc/link.c b/net/tipc/link.c index 09ae8448f394..8d9e09f48f4c 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1298,7 +1298,8 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, return false; #ifdef CONFIG_TIPC_CRYPTO case MSG_CRYPTO: - if (TIPC_SKB_CB(skb)->decrypted) { + if (sysctl_tipc_key_exchange_enabled && + TIPC_SKB_CB(skb)->decrypted) { tipc_crypto_msg_rcv(l->net, skb); return true; } diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c index c09bea89151b..01d44e2598e2 100644 --- a/net/unix/sysctl_net_unix.c +++ b/net/unix/sysctl_net_unix.c @@ -30,10 +30,6 @@ int __net_init unix_sysctl_register(struct net *net) if (table == NULL) goto err_alloc; - /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) - table[0].procname = NULL; - table[0].data = &net->unx.sysctl_max_dgram_qlen; net->unx.ctl = register_net_sysctl(net, "net/unix", table); if (net->unx.ctl == NULL) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 59ee1be5a6dd..ec2c2afbf0d0 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1299,7 +1299,8 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, space_available = virtio_transport_space_update(sk, pkt); /* Update CID in case it has changed after a transport reset event */ - vsk->local_addr.svm_cid = dst.svm_cid; + if (vsk->local_addr.svm_cid != VMADDR_CID_ANY) + vsk->local_addr.svm_cid = dst.svm_cid; if (space_available) sk->sk_write_space(sk); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index df87c7f3a049..f8f01a3e020b 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -133,6 +133,7 @@ static u32 reg_is_indoor_portid; static void restore_regulatory_settings(bool reset_user, bool cached); static void print_regdomain(const struct ieee80211_regdomain *rd); +static void reg_process_hint(struct regulatory_request *reg_request); static const struct ieee80211_regdomain *get_cfg80211_regdom(void) { @@ -1098,6 +1099,8 @@ int reg_reload_regdb(void) const struct firmware *fw; void *db; int err; + const struct ieee80211_regdomain *current_regdomain; + struct regulatory_request *request; err = request_firmware(&fw, "regulatory.db", ®_pdev->dev); if (err) @@ -1118,8 +1121,26 @@ int reg_reload_regdb(void) if (!IS_ERR_OR_NULL(regdb)) kfree(regdb); regdb = db; - rtnl_unlock(); + /* reset regulatory domain */ + current_regdomain = get_cfg80211_regdom(); + + request = kzalloc(sizeof(*request), GFP_KERNEL); + if (!request) { + err = -ENOMEM; + goto out_unlock; + } + + request->wiphy_idx = WIPHY_IDX_INVALID; + request->alpha2[0] = current_regdomain->alpha2[0]; + request->alpha2[1] = current_regdomain->alpha2[1]; + request->initiator = NL80211_REGDOM_SET_BY_CORE; + request->user_reg_hint_type = NL80211_USER_REG_HINT_USER; + + reg_process_hint(request); + +out_unlock: + rtnl_unlock(); out: release_firmware(fw); return err; @@ -2338,6 +2359,7 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) struct cfg80211_chan_def chandef = {}; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); enum nl80211_iftype iftype; + bool ret; wdev_lock(wdev); iftype = wdev->iftype; @@ -2387,7 +2409,11 @@ static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_ADHOC: - return cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype); + wiphy_lock(wiphy); + ret = cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype); + wiphy_unlock(wiphy); + + return ret; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: return cfg80211_chandef_usable(wiphy, &chandef, diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index e1c4197af468..b981a4828d08 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -41,7 +41,7 @@ static int x25_queue_rx_frame(struct sock *sk, struct sk_buff *skb, int more) return 0; } - if (!more && x25->fraglen > 0) { /* End of fragment */ + if (x25->fraglen > 0) { /* End of fragment */ int len = x25->fraglen + skb->len; if ((skbn = alloc_skb(len, GFP_ATOMIC)) == NULL){ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 28ef3f4465ae..e3d35850fdea 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -677,8 +677,6 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; - sock_poll_wait(file, sock, wait); - if (unlikely(!xsk_is_bound(xs))) return mask; @@ -690,6 +688,8 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, else /* Poll needs to drive Tx also in copy mode */ __xsk_sendmsg(sk); + } else { + sock_poll_wait(file, sock, wait); } if (xs->rx && !xskq_prod_is_empty(xs->rx)) diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index e843b0d9e2a6..3fa066419d37 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -259,6 +259,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, } xso->dev = dev; + netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); xso->real_dev = dev; xso->num_exthdrs = 1; xso->flags = xuo->flags; @@ -269,7 +270,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, xso->flags = 0; xso->dev = NULL; xso->real_dev = NULL; - dev_put(dev); + dev_put_track(dev, &xso->dev_tracker); if (err != -EOPNOTSUPP) return err; diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index a886dff1ba89..38638845db9d 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -215,6 +215,11 @@ TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib endif TPROGS_LDLIBS += $(LIBBPF) -lelf -lz +TPROGLDLIBS_xdp_monitor += -lm +TPROGLDLIBS_xdp_redirect += -lm +TPROGLDLIBS_xdp_redirect_cpu += -lm +TPROGLDLIBS_xdp_redirect_map += -lm +TPROGLDLIBS_xdp_redirect_map_multi += -lm TPROGLDLIBS_tracex4 += -lrt TPROGLDLIBS_trace_output += -lrt TPROGLDLIBS_map_perf_test += -lrt @@ -328,7 +333,7 @@ $(BPF_SAMPLES_PATH)/*.c: verify_target_bpf $(LIBBPF) $(src)/*.c: verify_target_bpf $(LIBBPF) libbpf_hdrs: $(LIBBPF) -$(obj)/$(TRACE_HELPERS): | libbpf_hdrs +$(obj)/$(TRACE_HELPERS) $(obj)/$(CGROUP_HELPERS) $(obj)/$(XDP_SAMPLE): | libbpf_hdrs .PHONY: libbpf_hdrs @@ -343,6 +348,17 @@ $(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h $(obj)/hbm.o: $(src)/hbm.h $(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h +# Override includes for xdp_sample_user.o because $(srctree)/usr/include in +# TPROGS_CFLAGS causes conflicts +XDP_SAMPLE_CFLAGS += -Wall -O2 \ + -I$(src)/../../tools/include \ + -I$(src)/../../tools/include/uapi \ + -I$(LIBBPF_INCLUDE) \ + -I$(src)/../../tools/testing/selftests/bpf + +$(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS) +$(obj)/$(XDP_SAMPLE): $(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h + -include $(BPF_SAMPLES_PATH)/Makefile.target VMLINUX_BTF_PATHS ?= $(abspath $(if $(O),$(O)/vmlinux)) \ diff --git a/samples/bpf/Makefile.target b/samples/bpf/Makefile.target index 5a368affa038..7621f55e2947 100644 --- a/samples/bpf/Makefile.target +++ b/samples/bpf/Makefile.target @@ -73,14 +73,3 @@ quiet_cmd_tprog-cobjs = CC $@ cmd_tprog-cobjs = $(CC) $(tprogc_flags) -c -o $@ $< $(tprog-cobjs): $(obj)/%.o: $(src)/%.c FORCE $(call if_changed_dep,tprog-cobjs) - -# Override includes for xdp_sample_user.o because $(srctree)/usr/include in -# TPROGS_CFLAGS causes conflicts -XDP_SAMPLE_CFLAGS += -Wall -O2 -lm \ - -I./tools/include \ - -I./tools/include/uapi \ - -I./tools/lib \ - -I./tools/testing/selftests/bpf -$(obj)/xdp_sample_user.o: $(src)/xdp_sample_user.c \ - $(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h - $(CC) $(XDP_SAMPLE_CFLAGS) -c -o $@ $< diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c index 54958802c032..f0df3dda4b1f 100644 --- a/samples/bpf/cookie_uid_helper_example.c +++ b/samples/bpf/cookie_uid_helper_example.c @@ -67,8 +67,8 @@ static bool test_finish; static void maps_create(void) { - map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(uint32_t), - sizeof(struct stats), 100, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(uint32_t), + sizeof(struct stats), 100, NULL); if (map_fd < 0) error(1, errno, "map create failed!\n"); } @@ -157,9 +157,13 @@ static void prog_load(void) offsetof(struct __sk_buff, len)), BPF_EXIT_INSN(), }; - prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, - ARRAY_SIZE(prog), "GPL", 0, - log_buf, sizeof(log_buf)); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = log_buf, + .log_size = sizeof(log_buf), + ); + + prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + prog, ARRAY_SIZE(prog), &opts); if (prog_fd < 0) error(1, errno, "failed to load prog\n%s\n", log_buf); } diff --git a/samples/bpf/fds_example.c b/samples/bpf/fds_example.c index 59f45fef5110..16dbf49e0f19 100644 --- a/samples/bpf/fds_example.c +++ b/samples/bpf/fds_example.c @@ -46,12 +46,6 @@ static void usage(void) printf(" -h Display this help.\n"); } -static int bpf_map_create(void) -{ - return bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(uint32_t), - sizeof(uint32_t), 1024, 0); -} - static int bpf_prog_create(const char *object) { static struct bpf_insn insns[] = { @@ -60,16 +54,22 @@ static int bpf_prog_create(const char *object) }; size_t insns_cnt = sizeof(insns) / sizeof(struct bpf_insn); struct bpf_object *obj; - int prog_fd; + int err; if (object) { - assert(!bpf_prog_load(object, BPF_PROG_TYPE_UNSPEC, - &obj, &prog_fd)); - return prog_fd; + obj = bpf_object__open_file(object, NULL); + assert(!libbpf_get_error(obj)); + err = bpf_object__load(obj); + assert(!err); + return bpf_program__fd(bpf_object__next_program(obj, NULL)); } else { - return bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, - insns, insns_cnt, "GPL", 0, - bpf_log_buf, BPF_LOG_BUF_SIZE); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = bpf_log_buf, + .log_size = BPF_LOG_BUF_SIZE, + ); + + return bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + insns, insns_cnt, &opts); } } @@ -79,7 +79,8 @@ static int bpf_do_map(const char *file, uint32_t flags, uint32_t key, int fd, ret; if (flags & BPF_F_PIN) { - fd = bpf_map_create(); + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(uint32_t), + sizeof(uint32_t), 1024, NULL); printf("bpf: map fd:%d (%s)\n", fd, strerror(errno)); assert(fd > 0); diff --git a/samples/bpf/lwt_len_hist_kern.c b/samples/bpf/lwt_len_hist_kern.c index 9ed63e10e170..1fa14c54963a 100644 --- a/samples/bpf/lwt_len_hist_kern.c +++ b/samples/bpf/lwt_len_hist_kern.c @@ -16,13 +16,6 @@ #include <uapi/linux/in.h> #include <bpf/bpf_helpers.h> -# define printk(fmt, ...) \ - ({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ - }) - struct bpf_elf_map { __u32 type; __u32 size_key; diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c index 9db949290a78..319fd31522f3 100644 --- a/samples/bpf/map_perf_test_user.c +++ b/samples/bpf/map_perf_test_user.c @@ -134,19 +134,22 @@ static void do_test_lru(enum test_type test, int cpu) */ int outer_fd = map_fd[array_of_lru_hashs_idx]; unsigned int mycpu, mynode; + LIBBPF_OPTS(bpf_map_create_opts, opts, + .map_flags = BPF_F_NUMA_NODE, + ); assert(cpu < MAX_NR_CPUS); ret = syscall(__NR_getcpu, &mycpu, &mynode, NULL); assert(!ret); + opts.numa_node = mynode; inner_lru_map_fds[cpu] = - bpf_create_map_node(BPF_MAP_TYPE_LRU_HASH, - test_map_names[INNER_LRU_HASH_PREALLOC], - sizeof(uint32_t), - sizeof(long), - inner_lru_hash_size, 0, - mynode); + bpf_map_create(BPF_MAP_TYPE_LRU_HASH, + test_map_names[INNER_LRU_HASH_PREALLOC], + sizeof(uint32_t), + sizeof(long), + inner_lru_hash_size, &opts); if (inner_lru_map_fds[cpu] == -1) { printf("cannot create BPF_MAP_TYPE_LRU_HASH %s(%d)\n", strerror(errno), errno); diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c index 23d1930e1927..a88f69504c08 100644 --- a/samples/bpf/sock_example.c +++ b/samples/bpf/sock_example.c @@ -37,8 +37,8 @@ static int test_sock(void) int sock = -1, map_fd, prog_fd, i, key; long long value = 0, tcp_cnt, udp_cnt, icmp_cnt; - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), - 256, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(key), sizeof(value), + 256, NULL); if (map_fd < 0) { printf("failed to create map '%s'\n", strerror(errno)); goto cleanup; @@ -59,9 +59,13 @@ static int test_sock(void) BPF_EXIT_INSN(), }; size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = bpf_log_buf, + .log_size = BPF_LOG_BUF_SIZE, + ); - prog_fd = bpf_load_program(BPF_PROG_TYPE_SOCKET_FILTER, prog, insns_cnt, - "GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE); + prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", + prog, insns_cnt, &opts); if (prog_fd < 0) { printf("failed to load prog '%s'\n", strerror(errno)); goto cleanup; diff --git a/samples/bpf/sockex1_user.c b/samples/bpf/sockex1_user.c index 3c83722877dc..9e8d39e245c1 100644 --- a/samples/bpf/sockex1_user.c +++ b/samples/bpf/sockex1_user.c @@ -11,17 +11,26 @@ int main(int ac, char **argv) { struct bpf_object *obj; + struct bpf_program *prog; int map_fd, prog_fd; char filename[256]; - int i, sock; + int i, sock, err; FILE *f; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER, - &obj, &prog_fd)) + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) return 1; + prog = bpf_object__next_program(obj, NULL); + bpf_program__set_type(prog, BPF_PROG_TYPE_SOCKET_FILTER); + + err = bpf_object__load(obj); + if (err) + return 1; + + prog_fd = bpf_program__fd(prog); map_fd = bpf_object__find_map_fd_by_name(obj, "my_map"); sock = open_raw_sock("lo"); diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c index bafa567b840c..6a3fd369d3fc 100644 --- a/samples/bpf/sockex2_user.c +++ b/samples/bpf/sockex2_user.c @@ -16,18 +16,26 @@ struct pair { int main(int ac, char **argv) { + struct bpf_program *prog; struct bpf_object *obj; int map_fd, prog_fd; char filename[256]; - int i, sock; + int i, sock, err; FILE *f; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) + return 1; + + prog = bpf_object__next_program(obj, NULL); + bpf_program__set_type(prog, BPF_PROG_TYPE_SOCKET_FILTER); - if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER, - &obj, &prog_fd)) + err = bpf_object__load(obj); + if (err) return 1; + prog_fd = bpf_program__fd(prog); map_fd = bpf_object__find_map_fd_by_name(obj, "hash_map"); sock = open_raw_sock("lo"); diff --git a/samples/bpf/test_cgrp2_array_pin.c b/samples/bpf/test_cgrp2_array_pin.c index 6d564aa75447..05e88aa63009 100644 --- a/samples/bpf/test_cgrp2_array_pin.c +++ b/samples/bpf/test_cgrp2_array_pin.c @@ -64,9 +64,9 @@ int main(int argc, char **argv) } if (create_array) { - array_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_ARRAY, + array_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_ARRAY, NULL, sizeof(uint32_t), sizeof(uint32_t), - 1, 0); + 1, NULL); if (array_fd < 0) { fprintf(stderr, "bpf_create_map(BPF_MAP_TYPE_CGROUP_ARRAY,...): %s(%d)\n", diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c index 390ff38d2ac6..6d90874b09c3 100644 --- a/samples/bpf/test_cgrp2_attach.c +++ b/samples/bpf/test_cgrp2_attach.c @@ -71,10 +71,13 @@ static int prog_load(int map_fd, int verdict) BPF_EXIT_INSN(), }; size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn); + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = bpf_log_buf, + .log_size = BPF_LOG_BUF_SIZE, + ); - return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB, - prog, insns_cnt, "GPL", 0, - bpf_log_buf, BPF_LOG_BUF_SIZE); + return bpf_prog_load(BPF_PROG_TYPE_CGROUP_SKB, NULL, "GPL", + prog, insns_cnt, &opts); } static int usage(const char *argv0) @@ -90,9 +93,9 @@ static int attach_filter(int cg_fd, int type, int verdict) int prog_fd, map_fd, ret, key; long long pkt_cnt, byte_cnt; - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(key), sizeof(byte_cnt), - 256, 0); + 256, NULL); if (map_fd < 0) { printf("Failed to create map: '%s'\n", strerror(errno)); return EXIT_FAILURE; diff --git a/samples/bpf/test_cgrp2_sock.c b/samples/bpf/test_cgrp2_sock.c index b0811da5a00f..a0811df888f4 100644 --- a/samples/bpf/test_cgrp2_sock.c +++ b/samples/bpf/test_cgrp2_sock.c @@ -70,6 +70,10 @@ static int prog_load(__u32 idx, __u32 mark, __u32 prio) BPF_MOV64_IMM(BPF_REG_2, offsetof(struct bpf_sock, priority)), BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, offsetof(struct bpf_sock, priority)), }; + LIBBPF_OPTS(bpf_prog_load_opts, opts, + .log_buf = bpf_log_buf, + .log_size = BPF_LOG_BUF_SIZE, + ); struct bpf_insn *prog; size_t insns_cnt; @@ -115,8 +119,8 @@ static int prog_load(__u32 idx, __u32 mark, __u32 prio) insns_cnt /= sizeof(struct bpf_insn); - ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SOCK, prog, insns_cnt, - "GPL", 0, bpf_log_buf, BPF_LOG_BUF_SIZE); + ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", + prog, insns_cnt, &opts); free(prog); diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c index c92c5c06b965..75e877853596 100644 --- a/samples/bpf/test_lru_dist.c +++ b/samples/bpf/test_lru_dist.c @@ -105,10 +105,10 @@ struct pfect_lru { static void pfect_lru_init(struct pfect_lru *lru, unsigned int lru_size, unsigned int nr_possible_elems) { - lru->map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, + lru->map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(unsigned long long), sizeof(struct pfect_lru_node *), - nr_possible_elems, 0); + nr_possible_elems, NULL); assert(lru->map_fd != -1); lru->free_nodes = malloc(lru_size * sizeof(struct pfect_lru_node)); @@ -207,10 +207,13 @@ static unsigned int read_keys(const char *dist_file, static int create_map(int map_type, int map_flags, unsigned int size) { + LIBBPF_OPTS(bpf_map_create_opts, opts, + .map_flags = map_flags, + ); int map_fd; - map_fd = bpf_create_map(map_type, sizeof(unsigned long long), - sizeof(unsigned long long), size, map_flags); + map_fd = bpf_map_create(map_type, NULL, sizeof(unsigned long long), + sizeof(unsigned long long), size, &opts); if (map_fd == -1) perror("bpf_create_map"); diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c index 364b98764d54..371732f9cf8e 100644 --- a/samples/bpf/trace_output_user.c +++ b/samples/bpf/trace_output_user.c @@ -43,7 +43,6 @@ static void print_bpf_output(void *ctx, int cpu, void *data, __u32 size) int main(int argc, char **argv) { - struct perf_buffer_opts pb_opts = {}; struct bpf_link *link = NULL; struct bpf_program *prog; struct perf_buffer *pb; @@ -84,8 +83,7 @@ int main(int argc, char **argv) goto cleanup; } - pb_opts.sample_cb = print_bpf_output; - pb = perf_buffer__new(map_fd, 8, &pb_opts); + pb = perf_buffer__new(map_fd, 8, print_bpf_output, NULL, NULL, NULL); ret = libbpf_get_error(pb); if (ret) { printf("failed to setup perf_buffer: %d\n", ret); diff --git a/samples/bpf/xdp_redirect_cpu.bpf.c b/samples/bpf/xdp_redirect_cpu.bpf.c index f10fe3cf25f6..25e3a405375f 100644 --- a/samples/bpf/xdp_redirect_cpu.bpf.c +++ b/samples/bpf/xdp_redirect_cpu.bpf.c @@ -100,7 +100,6 @@ u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off) void *data = (void *)(long)ctx->data; struct iphdr *iph = data + nh_off; struct udphdr *udph; - u16 dport; if (iph + 1 > data_end) return 0; @@ -111,8 +110,7 @@ u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off) if (udph + 1 > data_end) return 0; - dport = bpf_ntohs(udph->dest); - return dport; + return bpf_ntohs(udph->dest); } static __always_inline diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index f4382ccdcbb1..587eacb49103 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -110,12 +110,9 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_XDP, - }; - struct perf_buffer_opts pb_opts = {}; const char *optstr = "FS"; int prog_fd, map_fd, opt; + struct bpf_program *prog; struct bpf_object *obj; struct bpf_map *map; char filename[256]; @@ -144,15 +141,19 @@ int main(int argc, char **argv) } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - prog_load_attr.file = filename; - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) return 1; - if (!prog_fd) { - printf("bpf_prog_load_xattr: %s\n", strerror(errno)); + prog = bpf_object__next_program(obj, NULL); + bpf_program__set_type(prog, BPF_PROG_TYPE_XDP); + + err = bpf_object__load(obj); + if (err) return 1; - } + + prog_fd = bpf_program__fd(prog); map = bpf_object__next_map(obj, NULL); if (!map) { @@ -181,8 +182,7 @@ int main(int argc, char **argv) return 1; } - pb_opts.sample_cb = print_bpf_output; - pb = perf_buffer__new(map_fd, 8, &pb_opts); + pb = perf_buffer__new(map_fd, 8, print_bpf_output, NULL, NULL, NULL); err = libbpf_get_error(pb); if (err) { perror("perf_buffer setup failed"); diff --git a/samples/bpf/xdp_sample_user.h b/samples/bpf/xdp_sample_user.h index d97465ff8c62..5f44b877ecf5 100644 --- a/samples/bpf/xdp_sample_user.h +++ b/samples/bpf/xdp_sample_user.h @@ -45,7 +45,9 @@ const char *get_driver_name(int ifindex); int get_mac_addr(int ifindex, void *mac_addr); #pragma GCC diagnostic push +#ifndef __clang__ #pragma GCC diagnostic ignored "-Wstringop-truncation" +#endif __attribute__((unused)) static inline char *safe_strncpy(char *dst, const char *src, size_t size) { diff --git a/samples/bpf/xdpsock_ctrl_proc.c b/samples/bpf/xdpsock_ctrl_proc.c index 384e62e3c6d6..cc4408797ab7 100644 --- a/samples/bpf/xdpsock_ctrl_proc.c +++ b/samples/bpf/xdpsock_ctrl_proc.c @@ -15,6 +15,9 @@ #include <bpf/xsk.h> #include "xdpsock.h" +/* libbpf APIs for AF_XDP are deprecated starting from v0.7 */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + static const char *opt_if = ""; static struct option long_options[] = { diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 49d7a6ad7e39..616d663d55aa 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -36,6 +36,9 @@ #include <bpf/bpf.h> #include "xdpsock.h" +/* libbpf APIs for AF_XDP are deprecated starting from v0.7 */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + #ifndef SOL_XDP #define SOL_XDP 283 #endif diff --git a/samples/bpf/xsk_fwd.c b/samples/bpf/xsk_fwd.c index 1cd97c84c337..52e7c4ffd228 100644 --- a/samples/bpf/xsk_fwd.c +++ b/samples/bpf/xsk_fwd.c @@ -27,6 +27,9 @@ #include <bpf/xsk.h> #include <bpf/bpf.h> +/* libbpf APIs for AF_XDP are deprecated starting from v0.7 */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + #define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) typedef __u64 u64; diff --git a/samples/ftrace/Makefile b/samples/ftrace/Makefile index b9198e2eef28..faf8cdb79c5f 100644 --- a/samples/ftrace/Makefile +++ b/samples/ftrace/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct.o obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-too.o obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-modify.o obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace-direct-multi.o +obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace-direct-multi-modify.o CFLAGS_sample-trace-array.o := -I$(src) obj-$(CONFIG_SAMPLE_TRACE_ARRAY) += sample-trace-array.o diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c new file mode 100644 index 000000000000..91bc42a7adb9 --- /dev/null +++ b/samples/ftrace/ftrace-direct-multi-modify.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/module.h> +#include <linux/kthread.h> +#include <linux/ftrace.h> +#include <asm/asm-offsets.h> + +void my_direct_func1(unsigned long ip) +{ + trace_printk("my direct func1 ip %lx\n", ip); +} + +void my_direct_func2(unsigned long ip) +{ + trace_printk("my direct func2 ip %lx\n", ip); +} + +extern void my_tramp1(void *); +extern void my_tramp2(void *); + +#ifdef CONFIG_X86_64 + +asm ( +" .pushsection .text, \"ax\", @progbits\n" +" .type my_tramp1, @function\n" +" .globl my_tramp1\n" +" my_tramp1:" +" pushq %rbp\n" +" movq %rsp, %rbp\n" +" pushq %rdi\n" +" movq 8(%rbp), %rdi\n" +" call my_direct_func1\n" +" popq %rdi\n" +" leave\n" +" ret\n" +" .size my_tramp1, .-my_tramp1\n" +" .type my_tramp2, @function\n" +"\n" +" .globl my_tramp2\n" +" my_tramp2:" +" pushq %rbp\n" +" movq %rsp, %rbp\n" +" pushq %rdi\n" +" movq 8(%rbp), %rdi\n" +" call my_direct_func2\n" +" popq %rdi\n" +" leave\n" +" ret\n" +" .size my_tramp2, .-my_tramp2\n" +" .popsection\n" +); + +#endif /* CONFIG_X86_64 */ + +#ifdef CONFIG_S390 + +asm ( +" .pushsection .text, \"ax\", @progbits\n" +" .type my_tramp1, @function\n" +" .globl my_tramp1\n" +" my_tramp1:" +" lgr %r1,%r15\n" +" stmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n" +" stg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n" +" aghi %r15,"__stringify(-STACK_FRAME_OVERHEAD)"\n" +" stg %r1,"__stringify(__SF_BACKCHAIN)"(%r15)\n" +" lgr %r2,%r0\n" +" brasl %r14,my_direct_func1\n" +" aghi %r15,"__stringify(STACK_FRAME_OVERHEAD)"\n" +" lmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n" +" lg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n" +" lgr %r1,%r0\n" +" br %r1\n" +" .size my_tramp1, .-my_tramp1\n" +"\n" +" .type my_tramp2, @function\n" +" .globl my_tramp2\n" +" my_tramp2:" +" lgr %r1,%r15\n" +" stmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n" +" stg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n" +" aghi %r15,"__stringify(-STACK_FRAME_OVERHEAD)"\n" +" stg %r1,"__stringify(__SF_BACKCHAIN)"(%r15)\n" +" lgr %r2,%r0\n" +" brasl %r14,my_direct_func2\n" +" aghi %r15,"__stringify(STACK_FRAME_OVERHEAD)"\n" +" lmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n" +" lg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n" +" lgr %r1,%r0\n" +" br %r1\n" +" .size my_tramp2, .-my_tramp2\n" +" .popsection\n" +); + +#endif /* CONFIG_S390 */ + +static unsigned long my_tramp = (unsigned long)my_tramp1; +static unsigned long tramps[2] = { + (unsigned long)my_tramp1, + (unsigned long)my_tramp2, +}; + +static struct ftrace_ops direct; + +static int simple_thread(void *arg) +{ + static int t; + int ret = 0; + + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule_timeout(2 * HZ); + + if (ret) + continue; + t ^= 1; + ret = modify_ftrace_direct_multi(&direct, tramps[t]); + if (!ret) + my_tramp = tramps[t]; + WARN_ON_ONCE(ret); + } + + return 0; +} + +static struct task_struct *simple_tsk; + +static int __init ftrace_direct_multi_init(void) +{ + int ret; + + ftrace_set_filter_ip(&direct, (unsigned long) wake_up_process, 0, 0); + ftrace_set_filter_ip(&direct, (unsigned long) schedule, 0, 0); + + ret = register_ftrace_direct_multi(&direct, my_tramp); + + if (!ret) + simple_tsk = kthread_run(simple_thread, NULL, "event-sample-fn"); + return ret; +} + +static void __exit ftrace_direct_multi_exit(void) +{ + kthread_stop(simple_tsk); + unregister_ftrace_direct_multi(&direct, my_tramp); +} + +module_init(ftrace_direct_multi_init); +module_exit(ftrace_direct_multi_exit); + +MODULE_AUTHOR("Jiri Olsa"); +MODULE_DESCRIPTION("Example use case of using modify_ftrace_direct_multi()"); +MODULE_LICENSE("GPL"); diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index 7d631aaa0ae1..52a000b057a5 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -219,7 +219,7 @@ if ($arch eq "x86_64") { } elsif ($arch eq "s390" && $bits == 64) { if ($cc =~ /-DCC_USING_HOTPATCH/) { - $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*brcl\\s*0,[0-9a-f]+ <([^\+]*)>\$"; + $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*(bcrl\\s*0,|jgnop\\s*)[0-9a-f]+ <([^\+]*)>\$"; $mcount_adjust = 0; } $alignment = 8; diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index 470dabc60aa0..edff063e088d 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -264,6 +264,7 @@ static int copy_ctl_value_to_user(void __user *userdata, struct snd_ctl_elem_value *data, int type, int count) { + struct snd_ctl_elem_value32 __user *data32 = userdata; int i, size; if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN || @@ -280,6 +281,8 @@ static int copy_ctl_value_to_user(void __user *userdata, if (copy_to_user(valuep, data->value.bytes.data, size)) return -EFAULT; } + if (copy_to_user(&data32->id, &data->id, sizeof(data32->id))) + return -EFAULT; return 0; } diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c index 82a818734a5f..20a0a4771b9a 100644 --- a/sound/core/oss/pcm_oss.c +++ b/sound/core/oss/pcm_oss.c @@ -147,7 +147,7 @@ snd_pcm_hw_param_value_min(const struct snd_pcm_hw_params *params, * * Return the maximum value for field PAR. */ -static unsigned int +static int snd_pcm_hw_param_value_max(const struct snd_pcm_hw_params *params, snd_pcm_hw_param_t var, int *dir) { @@ -682,18 +682,24 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *oss_params, struct snd_pcm_hw_params *slave_params) { - size_t s; - size_t oss_buffer_size, oss_period_size, oss_periods; - size_t min_period_size, max_period_size; + ssize_t s; + ssize_t oss_buffer_size; + ssize_t oss_period_size, oss_periods; + ssize_t min_period_size, max_period_size; struct snd_pcm_runtime *runtime = substream->runtime; size_t oss_frame_size; oss_frame_size = snd_pcm_format_physical_width(params_format(oss_params)) * params_channels(oss_params) / 8; + oss_buffer_size = snd_pcm_hw_param_value_max(slave_params, + SNDRV_PCM_HW_PARAM_BUFFER_SIZE, + NULL); + if (oss_buffer_size <= 0) + return -EINVAL; oss_buffer_size = snd_pcm_plug_client_size(substream, - snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, NULL)) * oss_frame_size; - if (!oss_buffer_size) + oss_buffer_size * oss_frame_size); + if (oss_buffer_size <= 0) return -EINVAL; oss_buffer_size = rounddown_pow_of_two(oss_buffer_size); if (atomic_read(&substream->mmap_count)) { @@ -730,7 +736,7 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream, min_period_size = snd_pcm_plug_client_size(substream, snd_pcm_hw_param_value_min(slave_params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, NULL)); - if (min_period_size) { + if (min_period_size > 0) { min_period_size *= oss_frame_size; min_period_size = roundup_pow_of_two(min_period_size); if (oss_period_size < min_period_size) @@ -739,7 +745,7 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream, max_period_size = snd_pcm_plug_client_size(substream, snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, NULL)); - if (max_period_size) { + if (max_period_size > 0) { max_period_size *= oss_frame_size; max_period_size = rounddown_pow_of_two(max_period_size); if (oss_period_size > max_period_size) @@ -752,7 +758,7 @@ static int snd_pcm_oss_period_size(struct snd_pcm_substream *substream, oss_periods = substream->oss.setup.periods; s = snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_PERIODS, NULL); - if (runtime->oss.maxfrags && s > runtime->oss.maxfrags) + if (s > 0 && runtime->oss.maxfrags && s > runtime->oss.maxfrags) s = runtime->oss.maxfrags; if (oss_periods > s) oss_periods = s; @@ -878,8 +884,15 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream) err = -EINVAL; goto failure; } - choose_rate(substream, sparams, runtime->oss.rate); - snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_CHANNELS, runtime->oss.channels, NULL); + + err = choose_rate(substream, sparams, runtime->oss.rate); + if (err < 0) + goto failure; + err = snd_pcm_hw_param_near(substream, sparams, + SNDRV_PCM_HW_PARAM_CHANNELS, + runtime->oss.channels, NULL); + if (err < 0) + goto failure; format = snd_pcm_oss_format_from(runtime->oss.format); @@ -1956,7 +1969,7 @@ static int snd_pcm_oss_set_fragment1(struct snd_pcm_substream *substream, unsign if (runtime->oss.subdivision || runtime->oss.fragshift) return -EINVAL; fragshift = val & 0xffff; - if (fragshift >= 31) + if (fragshift >= 25) /* should be large enough */ return -EINVAL; runtime->oss.fragshift = fragshift; runtime->oss.maxfrags = (val >> 16) & 0xffff; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 9ce7457533c9..3599f4c85ebf 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6503,22 +6503,26 @@ static void alc287_fixup_legion_15imhg05_speakers(struct hda_codec *codec, /* for alc285_fixup_ideapad_s740_coef() */ #include "ideapad_s740_helper.c" -static void alc256_fixup_tongfang_reset_persistent_settings(struct hda_codec *codec, - const struct hda_fixup *fix, - int action) +static const struct coef_fw alc256_fixup_set_coef_defaults_coefs[] = { + WRITE_COEF(0x10, 0x0020), WRITE_COEF(0x24, 0x0000), + WRITE_COEF(0x26, 0x0000), WRITE_COEF(0x29, 0x3000), + WRITE_COEF(0x37, 0xfe05), WRITE_COEF(0x45, 0x5089), + {} +}; + +static void alc256_fixup_set_coef_defaults(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) { /* - * A certain other OS sets these coeffs to different values. On at least one TongFang - * barebone these settings might survive even a cold reboot. So to restore a clean slate the - * values are explicitly reset to default here. Without this, the external microphone is - * always in a plugged-in state, while the internal microphone is always in an unplugged - * state, breaking the ability to use the internal microphone. - */ - alc_write_coef_idx(codec, 0x24, 0x0000); - alc_write_coef_idx(codec, 0x26, 0x0000); - alc_write_coef_idx(codec, 0x29, 0x3000); - alc_write_coef_idx(codec, 0x37, 0xfe05); - alc_write_coef_idx(codec, 0x45, 0x5089); + * A certain other OS sets these coeffs to different values. On at least + * one TongFang barebone these settings might survive even a cold + * reboot. So to restore a clean slate the values are explicitly reset + * to default here. Without this, the external microphone is always in a + * plugged-in state, while the internal microphone is always in an + * unplugged state, breaking the ability to use the internal microphone. + */ + alc_process_coef_fw(codec, alc256_fixup_set_coef_defaults_coefs); } static const struct coef_fw alc233_fixup_no_audio_jack_coefs[] = { @@ -6759,7 +6763,7 @@ enum { ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, ALC287_FIXUP_13S_GEN2_SPEAKERS, - ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS, + ALC256_FIXUP_SET_COEF_DEFAULTS, ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE, ALC233_FIXUP_NO_AUDIO_JACK, }; @@ -8465,9 +8469,9 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE, }, - [ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS] = { + [ALC256_FIXUP_SET_COEF_DEFAULTS] = { .type = HDA_FIXUP_FUNC, - .v.func = alc256_fixup_tongfang_reset_persistent_settings, + .v.func = alc256_fixup_set_coef_defaults, }, [ALC245_FIXUP_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, @@ -8929,7 +8933,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), - SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS), + SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS), SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), @@ -10231,6 +10235,27 @@ static void alc671_fixup_hp_headset_mic2(struct hda_codec *codec, } } +static void alc897_hp_automute_hook(struct hda_codec *codec, + struct hda_jack_callback *jack) +{ + struct alc_spec *spec = codec->spec; + int vref; + + snd_hda_gen_hp_automute(codec, jack); + vref = spec->gen.hp_jack_present ? (PIN_HP | AC_PINCTL_VREF_100) : PIN_HP; + snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, + vref); +} + +static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + if (action == HDA_FIXUP_ACT_PRE_PROBE) { + spec->gen.hp_automute_hook = alc897_hp_automute_hook; + } +} + static const struct coef_fw alc668_coefs[] = { WRITE_COEF(0x01, 0xbebe), WRITE_COEF(0x02, 0xaaaa), WRITE_COEF(0x03, 0x0), WRITE_COEF(0x04, 0x0180), WRITE_COEF(0x06, 0x0), WRITE_COEF(0x07, 0x0f80), @@ -10311,6 +10336,8 @@ enum { ALC668_FIXUP_ASUS_NO_HEADSET_MIC, ALC668_FIXUP_HEADSET_MIC, ALC668_FIXUP_MIC_DET_COEF, + ALC897_FIXUP_LENOVO_HEADSET_MIC, + ALC897_FIXUP_HEADSET_MIC_PIN, }; static const struct hda_fixup alc662_fixups[] = { @@ -10717,6 +10744,19 @@ static const struct hda_fixup alc662_fixups[] = { {} }, }, + [ALC897_FIXUP_LENOVO_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc897_fixup_lenovo_headset_mic, + }, + [ALC897_FIXUP_HEADSET_MIC_PIN] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1a, 0x03a11050 }, + { } + }, + .chained = true, + .chain_id = ALC897_FIXUP_LENOVO_HEADSET_MIC + }, }; static const struct snd_pci_quirk alc662_fixup_tbl[] = { @@ -10761,6 +10801,10 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS), + SND_PCI_QUIRK(0x17aa, 0x32ca, "Lenovo ThinkCentre M80", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x1849, 0x5892, "ASRock B150M", ALC892_FIXUP_ASROCK_MOBO), diff --git a/sound/soc/amd/yc/pci-acp6x.c b/sound/soc/amd/yc/pci-acp6x.c index 957eeb6fb8e3..7e9a9a9d8ddd 100644 --- a/sound/soc/amd/yc/pci-acp6x.c +++ b/sound/soc/amd/yc/pci-acp6x.c @@ -146,10 +146,11 @@ static int snd_acp6x_probe(struct pci_dev *pci, { struct acp6x_dev_data *adata; struct platform_device_info pdevinfo[ACP6x_DEVS]; - int ret, index; + int index = 0; int val = 0x00; u32 addr; unsigned int irqflags; + int ret; irqflags = IRQF_SHARED; /* Yellow Carp device check */ diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 04cb747c2b12..5224123d0d3b 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -2858,6 +2858,8 @@ int rt5682_register_dai_clks(struct rt5682_priv *rt5682) for (i = 0; i < RT5682_DAI_NUM_CLKS; ++i) { struct clk_init_data init = { }; + struct clk_parent_data parent_data; + const struct clk_hw *parent; dai_clk_hw = &rt5682->dai_clks_hw[i]; @@ -2865,17 +2867,17 @@ int rt5682_register_dai_clks(struct rt5682_priv *rt5682) case RT5682_DAI_WCLK_IDX: /* Make MCLK the parent of WCLK */ if (rt5682->mclk) { - init.parent_data = &(struct clk_parent_data){ + parent_data = (struct clk_parent_data){ .fw_name = "mclk", }; + init.parent_data = &parent_data; init.num_parents = 1; } break; case RT5682_DAI_BCLK_IDX: /* Make WCLK the parent of BCLK */ - init.parent_hws = &(const struct clk_hw *){ - &rt5682->dai_clks_hw[RT5682_DAI_WCLK_IDX] - }; + parent = &rt5682->dai_clks_hw[RT5682_DAI_WCLK_IDX]; + init.parent_hws = &parent; init.num_parents = 1; break; default: diff --git a/sound/soc/codecs/rt5682s.c b/sound/soc/codecs/rt5682s.c index 470957fcad6b..d49a4f68566d 100644 --- a/sound/soc/codecs/rt5682s.c +++ b/sound/soc/codecs/rt5682s.c @@ -2693,6 +2693,8 @@ static int rt5682s_register_dai_clks(struct snd_soc_component *component) for (i = 0; i < RT5682S_DAI_NUM_CLKS; ++i) { struct clk_init_data init = { }; + struct clk_parent_data parent_data; + const struct clk_hw *parent; dai_clk_hw = &rt5682s->dai_clks_hw[i]; @@ -2700,17 +2702,17 @@ static int rt5682s_register_dai_clks(struct snd_soc_component *component) case RT5682S_DAI_WCLK_IDX: /* Make MCLK the parent of WCLK */ if (rt5682s->mclk) { - init.parent_data = &(struct clk_parent_data){ + parent_data = (struct clk_parent_data){ .fw_name = "mclk", }; + init.parent_data = &parent_data; init.num_parents = 1; } break; case RT5682S_DAI_BCLK_IDX: /* Make WCLK the parent of BCLK */ - init.parent_hws = &(const struct clk_hw *){ - &rt5682s->dai_clks_hw[RT5682S_DAI_WCLK_IDX] - }; + parent = &rt5682s->dai_clks_hw[RT5682S_DAI_WCLK_IDX]; + init.parent_hws = &parent; init.num_parents = 1; break; default: diff --git a/sound/soc/codecs/wcd934x.c b/sound/soc/codecs/wcd934x.c index 4f568abd59e2..e63c6b723d76 100644 --- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -3256,6 +3256,9 @@ static int wcd934x_compander_set(struct snd_kcontrol *kc, int value = ucontrol->value.integer.value[0]; int sel; + if (wcd->comp_enabled[comp] == value) + return 0; + wcd->comp_enabled[comp] = value; sel = value ? WCD934X_HPH_GAIN_SRC_SEL_COMPANDER : WCD934X_HPH_GAIN_SRC_SEL_REGISTER; @@ -3279,10 +3282,10 @@ static int wcd934x_compander_set(struct snd_kcontrol *kc, case COMPANDER_8: break; default: - break; + return 0; } - return 0; + return 1; } static int wcd934x_rx_hph_mode_get(struct snd_kcontrol *kc, @@ -3326,6 +3329,31 @@ static int slim_rx_mux_get(struct snd_kcontrol *kc, return 0; } +static int slim_rx_mux_to_dai_id(int mux) +{ + int aif_id; + + switch (mux) { + case 1: + aif_id = AIF1_PB; + break; + case 2: + aif_id = AIF2_PB; + break; + case 3: + aif_id = AIF3_PB; + break; + case 4: + aif_id = AIF4_PB; + break; + default: + aif_id = -1; + break; + } + + return aif_id; +} + static int slim_rx_mux_put(struct snd_kcontrol *kc, struct snd_ctl_elem_value *ucontrol) { @@ -3333,43 +3361,59 @@ static int slim_rx_mux_put(struct snd_kcontrol *kc, struct wcd934x_codec *wcd = dev_get_drvdata(w->dapm->dev); struct soc_enum *e = (struct soc_enum *)kc->private_value; struct snd_soc_dapm_update *update = NULL; + struct wcd934x_slim_ch *ch, *c; u32 port_id = w->shift; + bool found = false; + int mux_idx; + int prev_mux_idx = wcd->rx_port_value[port_id]; + int aif_id; - if (wcd->rx_port_value[port_id] == ucontrol->value.enumerated.item[0]) - return 0; + mux_idx = ucontrol->value.enumerated.item[0]; - wcd->rx_port_value[port_id] = ucontrol->value.enumerated.item[0]; + if (mux_idx == prev_mux_idx) + return 0; - switch (wcd->rx_port_value[port_id]) { + switch(mux_idx) { case 0: - list_del_init(&wcd->rx_chs[port_id].list); - break; - case 1: - list_add_tail(&wcd->rx_chs[port_id].list, - &wcd->dai[AIF1_PB].slim_ch_list); - break; - case 2: - list_add_tail(&wcd->rx_chs[port_id].list, - &wcd->dai[AIF2_PB].slim_ch_list); - break; - case 3: - list_add_tail(&wcd->rx_chs[port_id].list, - &wcd->dai[AIF3_PB].slim_ch_list); + aif_id = slim_rx_mux_to_dai_id(prev_mux_idx); + if (aif_id < 0) + return 0; + + list_for_each_entry_safe(ch, c, &wcd->dai[aif_id].slim_ch_list, list) { + if (ch->port == port_id + WCD934X_RX_START) { + found = true; + list_del_init(&ch->list); + break; + } + } + if (!found) + return 0; + break; - case 4: - list_add_tail(&wcd->rx_chs[port_id].list, - &wcd->dai[AIF4_PB].slim_ch_list); + case 1 ... 4: + aif_id = slim_rx_mux_to_dai_id(mux_idx); + if (aif_id < 0) + return 0; + + if (list_empty(&wcd->rx_chs[port_id].list)) { + list_add_tail(&wcd->rx_chs[port_id].list, + &wcd->dai[aif_id].slim_ch_list); + } else { + dev_err(wcd->dev ,"SLIM_RX%d PORT is busy\n", port_id); + return 0; + } break; + default: - dev_err(wcd->dev, "Unknown AIF %d\n", - wcd->rx_port_value[port_id]); + dev_err(wcd->dev, "Unknown AIF %d\n", mux_idx); goto err; } + wcd->rx_port_value[port_id] = mux_idx; snd_soc_dapm_mux_update_power(w->dapm, kc, wcd->rx_port_value[port_id], e, update); - return 0; + return 1; err: return -EINVAL; } @@ -3815,6 +3859,7 @@ static int slim_tx_mixer_put(struct snd_kcontrol *kc, struct soc_mixer_control *mixer = (struct soc_mixer_control *)kc->private_value; int enable = ucontrol->value.integer.value[0]; + struct wcd934x_slim_ch *ch, *c; int dai_id = widget->shift; int port_id = mixer->shift; @@ -3822,17 +3867,32 @@ static int slim_tx_mixer_put(struct snd_kcontrol *kc, if (enable == wcd->tx_port_value[port_id]) return 0; - wcd->tx_port_value[port_id] = enable; - - if (enable) - list_add_tail(&wcd->tx_chs[port_id].list, - &wcd->dai[dai_id].slim_ch_list); - else - list_del_init(&wcd->tx_chs[port_id].list); + if (enable) { + if (list_empty(&wcd->tx_chs[port_id].list)) { + list_add_tail(&wcd->tx_chs[port_id].list, + &wcd->dai[dai_id].slim_ch_list); + } else { + dev_err(wcd->dev ,"SLIM_TX%d PORT is busy\n", port_id); + return 0; + } + } else { + bool found = false; + + list_for_each_entry_safe(ch, c, &wcd->dai[dai_id].slim_ch_list, list) { + if (ch->port == port_id) { + found = true; + list_del_init(&wcd->tx_chs[port_id].list); + break; + } + } + if (!found) + return 0; + } + wcd->tx_port_value[port_id] = enable; snd_soc_dapm_mixer_update_power(widget->dapm, kc, enable, update); - return 0; + return 1; } static const struct snd_kcontrol_new aif1_slim_cap_mixer[] = { diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c index 2da4a5fa7a18..564b78f3cdd0 100644 --- a/sound/soc/codecs/wsa881x.c +++ b/sound/soc/codecs/wsa881x.c @@ -772,7 +772,8 @@ static int wsa881x_put_pa_gain(struct snd_kcontrol *kc, usleep_range(1000, 1010); } - return 0; + + return 1; } static int wsa881x_get_port(struct snd_kcontrol *kcontrol, @@ -816,15 +817,22 @@ static int wsa881x_set_port(struct snd_kcontrol *kcontrol, (struct soc_mixer_control *)kcontrol->private_value; int portidx = mixer->reg; - if (ucontrol->value.integer.value[0]) + if (ucontrol->value.integer.value[0]) { + if (data->port_enable[portidx]) + return 0; + data->port_enable[portidx] = true; - else + } else { + if (!data->port_enable[portidx]) + return 0; + data->port_enable[portidx] = false; + } if (portidx == WSA881X_PORT_BOOST) /* Boost Switch */ wsa881x_boost_ctrl(comp, data->port_enable[portidx]); - return 0; + return 1; } static const char * const smart_boost_lvl_text[] = { diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c index cd74681e811e..928fd23e2c27 100644 --- a/sound/soc/qcom/qdsp6/q6routing.c +++ b/sound/soc/qcom/qdsp6/q6routing.c @@ -498,14 +498,16 @@ static int msm_routing_put_audio_mixer(struct snd_kcontrol *kcontrol, struct session_data *session = &data->sessions[session_id]; if (ucontrol->value.integer.value[0]) { + if (session->port_id == be_id) + return 0; + session->port_id = be_id; snd_soc_dapm_mixer_update_power(dapm, kcontrol, 1, update); } else { - if (session->port_id == be_id) { - session->port_id = -1; + if (session->port_id == -1 || session->port_id != be_id) return 0; - } + session->port_id = -1; snd_soc_dapm_mixer_update_power(dapm, kcontrol, 0, update); } diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c index 17b9b287853a..5f9cb5c4c7f0 100644 --- a/sound/soc/rockchip/rockchip_i2s_tdm.c +++ b/sound/soc/rockchip/rockchip_i2s_tdm.c @@ -95,6 +95,7 @@ struct rk_i2s_tdm_dev { spinlock_t lock; /* xfer lock */ bool has_playback; bool has_capture; + struct snd_soc_dai_driver *dai; }; static int to_ch_num(unsigned int val) @@ -1310,19 +1311,14 @@ static const struct of_device_id rockchip_i2s_tdm_match[] = { {}, }; -static struct snd_soc_dai_driver i2s_tdm_dai = { +static const struct snd_soc_dai_driver i2s_tdm_dai = { .probe = rockchip_i2s_tdm_dai_probe, - .playback = { - .stream_name = "Playback", - }, - .capture = { - .stream_name = "Capture", - }, .ops = &rockchip_i2s_tdm_dai_ops, }; -static void rockchip_i2s_tdm_init_dai(struct rk_i2s_tdm_dev *i2s_tdm) +static int rockchip_i2s_tdm_init_dai(struct rk_i2s_tdm_dev *i2s_tdm) { + struct snd_soc_dai_driver *dai; struct property *dma_names; const char *dma_name; u64 formats = (SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_S16_LE | @@ -1337,19 +1333,33 @@ static void rockchip_i2s_tdm_init_dai(struct rk_i2s_tdm_dev *i2s_tdm) i2s_tdm->has_capture = true; } + dai = devm_kmemdup(i2s_tdm->dev, &i2s_tdm_dai, + sizeof(*dai), GFP_KERNEL); + if (!dai) + return -ENOMEM; + if (i2s_tdm->has_playback) { - i2s_tdm_dai.playback.channels_min = 2; - i2s_tdm_dai.playback.channels_max = 8; - i2s_tdm_dai.playback.rates = SNDRV_PCM_RATE_8000_192000; - i2s_tdm_dai.playback.formats = formats; + dai->playback.stream_name = "Playback"; + dai->playback.channels_min = 2; + dai->playback.channels_max = 8; + dai->playback.rates = SNDRV_PCM_RATE_8000_192000; + dai->playback.formats = formats; } if (i2s_tdm->has_capture) { - i2s_tdm_dai.capture.channels_min = 2; - i2s_tdm_dai.capture.channels_max = 8; - i2s_tdm_dai.capture.rates = SNDRV_PCM_RATE_8000_192000; - i2s_tdm_dai.capture.formats = formats; + dai->capture.stream_name = "Capture"; + dai->capture.channels_min = 2; + dai->capture.channels_max = 8; + dai->capture.rates = SNDRV_PCM_RATE_8000_192000; + dai->capture.formats = formats; } + + if (i2s_tdm->clk_trcm != TRCM_TXRX) + dai->symmetric_rate = 1; + + i2s_tdm->dai = dai; + + return 0; } static int rockchip_i2s_tdm_path_check(struct rk_i2s_tdm_dev *i2s_tdm, @@ -1541,8 +1551,6 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev) spin_lock_init(&i2s_tdm->lock); i2s_tdm->soc_data = (struct rk_i2s_soc_data *)of_id->data; - rockchip_i2s_tdm_init_dai(i2s_tdm); - i2s_tdm->frame_width = 64; i2s_tdm->clk_trcm = TRCM_TXRX; @@ -1555,8 +1563,10 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev) } i2s_tdm->clk_trcm = TRCM_RX; } - if (i2s_tdm->clk_trcm != TRCM_TXRX) - i2s_tdm_dai.symmetric_rate = 1; + + ret = rockchip_i2s_tdm_init_dai(i2s_tdm); + if (ret) + return ret; i2s_tdm->grf = syscon_regmap_lookup_by_phandle(node, "rockchip,grf"); if (IS_ERR(i2s_tdm->grf)) @@ -1678,7 +1688,7 @@ static int rockchip_i2s_tdm_probe(struct platform_device *pdev) ret = devm_snd_soc_register_component(&pdev->dev, &rockchip_i2s_tdm_component, - &i2s_tdm_dai, 1); + i2s_tdm->dai, 1); if (ret) { dev_err(&pdev->dev, "Could not register DAI\n"); diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 6744318de612..13cd96e6724a 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -22,6 +22,7 @@ #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC) #define IDISP_VID_INTEL 0x80860000 +#define CODEC_PROBE_RETRIES 3 /* load the legacy HDA codec driver */ static int request_codec_module(struct hda_codec *codec) @@ -121,12 +122,15 @@ static int hda_codec_probe(struct snd_sof_dev *sdev, int address, u32 hda_cmd = (address << 28) | (AC_NODE_ROOT << 20) | (AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID; u32 resp = -1; - int ret; + int ret, retry = 0; + + do { + mutex_lock(&hbus->core.cmd_mutex); + snd_hdac_bus_send_cmd(&hbus->core, hda_cmd); + snd_hdac_bus_get_response(&hbus->core, address, &resp); + mutex_unlock(&hbus->core.cmd_mutex); + } while (resp == -1 && retry++ < CODEC_PROBE_RETRIES); - mutex_lock(&hbus->core.cmd_mutex); - snd_hdac_bus_send_cmd(&hbus->core, hda_cmd); - snd_hdac_bus_get_response(&hbus->core, address, &resp); - mutex_unlock(&hbus->core.cmd_mutex); if (resp == -1) return -EIO; dev_dbg(sdev->dev, "HDA codec #%d probed OK: response: %x\n", diff --git a/sound/soc/tegra/tegra210_adx.c b/sound/soc/tegra/tegra210_adx.c index 933c4503fe50..3785cade2d9a 100644 --- a/sound/soc/tegra/tegra210_adx.c +++ b/sound/soc/tegra/tegra210_adx.c @@ -514,8 +514,8 @@ static int tegra210_adx_platform_remove(struct platform_device *pdev) static const struct dev_pm_ops tegra210_adx_pm_ops = { SET_RUNTIME_PM_OPS(tegra210_adx_runtime_suspend, tegra210_adx_runtime_resume, NULL) - SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) }; static struct platform_driver tegra210_adx_driver = { diff --git a/sound/soc/tegra/tegra210_amx.c b/sound/soc/tegra/tegra210_amx.c index 689576302ede..d064cc67fea6 100644 --- a/sound/soc/tegra/tegra210_amx.c +++ b/sound/soc/tegra/tegra210_amx.c @@ -583,8 +583,8 @@ static int tegra210_amx_platform_remove(struct platform_device *pdev) static const struct dev_pm_ops tegra210_amx_pm_ops = { SET_RUNTIME_PM_OPS(tegra210_amx_runtime_suspend, tegra210_amx_runtime_resume, NULL) - SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) }; static struct platform_driver tegra210_amx_driver = { diff --git a/sound/soc/tegra/tegra210_mixer.c b/sound/soc/tegra/tegra210_mixer.c index 51d375573cfa..16e679a95658 100644 --- a/sound/soc/tegra/tegra210_mixer.c +++ b/sound/soc/tegra/tegra210_mixer.c @@ -666,8 +666,8 @@ static int tegra210_mixer_platform_remove(struct platform_device *pdev) static const struct dev_pm_ops tegra210_mixer_pm_ops = { SET_RUNTIME_PM_OPS(tegra210_mixer_runtime_suspend, tegra210_mixer_runtime_resume, NULL) - SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) }; static struct platform_driver tegra210_mixer_driver = { diff --git a/sound/soc/tegra/tegra210_mvc.c b/sound/soc/tegra/tegra210_mvc.c index 85b155887ec2..acf59328dcb6 100644 --- a/sound/soc/tegra/tegra210_mvc.c +++ b/sound/soc/tegra/tegra210_mvc.c @@ -164,7 +164,7 @@ static int tegra210_mvc_put_mute(struct snd_kcontrol *kcontrol, if (err < 0) goto end; - return 1; + err = 1; end: pm_runtime_put(cmpnt->dev); @@ -236,7 +236,7 @@ static int tegra210_mvc_put_vol(struct snd_kcontrol *kcontrol, TEGRA210_MVC_VOLUME_SWITCH_MASK, TEGRA210_MVC_VOLUME_SWITCH_TRIGGER); - return 1; + err = 1; end: pm_runtime_put(cmpnt->dev); @@ -639,8 +639,8 @@ static int tegra210_mvc_platform_remove(struct platform_device *pdev) static const struct dev_pm_ops tegra210_mvc_pm_ops = { SET_RUNTIME_PM_OPS(tegra210_mvc_runtime_suspend, tegra210_mvc_runtime_resume, NULL) - SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) }; static struct platform_driver tegra210_mvc_driver = { diff --git a/sound/soc/tegra/tegra210_sfc.c b/sound/soc/tegra/tegra210_sfc.c index 7a2227ed3df6..368f077e7bee 100644 --- a/sound/soc/tegra/tegra210_sfc.c +++ b/sound/soc/tegra/tegra210_sfc.c @@ -3594,8 +3594,8 @@ static int tegra210_sfc_platform_remove(struct platform_device *pdev) static const struct dev_pm_ops tegra210_sfc_pm_ops = { SET_RUNTIME_PM_OPS(tegra210_sfc_runtime_suspend, tegra210_sfc_runtime_resume, NULL) - SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, - pm_runtime_force_resume) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) }; static struct platform_driver tegra210_sfc_driver = { diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index d489c1de3bae..823b6b8de942 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -3016,11 +3016,11 @@ static const struct snd_djm_ctl snd_djm_ctls_750mk2[] = { static const struct snd_djm_device snd_djm_devices[] = { - SND_DJM_DEVICE(250mk2), - SND_DJM_DEVICE(750), - SND_DJM_DEVICE(750mk2), - SND_DJM_DEVICE(850), - SND_DJM_DEVICE(900nxs2) + [SND_DJM_250MK2_IDX] = SND_DJM_DEVICE(250mk2), + [SND_DJM_750_IDX] = SND_DJM_DEVICE(750), + [SND_DJM_850_IDX] = SND_DJM_DEVICE(850), + [SND_DJM_900NXS2_IDX] = SND_DJM_DEVICE(900nxs2), + [SND_DJM_750MK2_IDX] = SND_DJM_DEVICE(750mk2), }; diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile index 692e1b947490..ac8487dcff1d 100644 --- a/tools/bpf/bpftool/Documentation/Makefile +++ b/tools/bpf/bpftool/Documentation/Makefile @@ -24,7 +24,7 @@ man: man8 man8: $(DOC_MAN8) RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null) -RST2MAN_OPTS += --verbose +RST2MAN_OPTS += --verbose --strip-comments list_pages = $(sort $(basename $(filter-out $(1),$(MAN8_RST)))) see_also = $(subst " ",, \ diff --git a/tools/bpf/bpftool/Documentation/bpftool-btf.rst b/tools/bpf/bpftool/Documentation/bpftool-btf.rst index 4425d942dd39..342716f74ec4 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-btf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-btf.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-btf ================ @@ -7,13 +9,14 @@ tool for inspection of BTF data :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **btf** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | {**-d** | **--debug** } | - { **-B** | **--base-btf** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-B** | **--base-btf** } } *COMMANDS* := { **dump** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 8069d37dd991..a17e9aa314fd 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-cgroup ================ @@ -7,13 +9,14 @@ tool for inspection and simple manipulation of eBPF progs :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **cgroup** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | - { **-f** | **--bpffs** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } } *COMMANDS* := { **show** | **list** | **tree** | **attach** | **detach** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index ab9f57ee4c3a..4ce9a77bc1e0 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + =============== bpftool-feature =============== @@ -7,12 +9,14 @@ tool for inspection of eBPF-related parameters for Linux kernel or net device :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **feature** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **probe** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst index 2a137f8a4cea..bc276388f432 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-gen ================ @@ -7,13 +9,14 @@ tool for BPF code-generation :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **gen** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | - { **-L** | **--use-loader** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-L** | **--use-loader** } } *COMMAND* := { **object** | **skeleton** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-iter.rst b/tools/bpf/bpftool/Documentation/bpftool-iter.rst index 471f363a725a..84839d488621 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-iter.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-iter.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ============ bpftool-iter ============ @@ -7,12 +9,14 @@ tool to create BPF iterators :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **iter** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **pin** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-link.rst b/tools/bpf/bpftool/Documentation/bpftool-link.rst index 9434349636a5..52a4eee4af54 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-link.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-link.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-link ================ @@ -7,13 +9,14 @@ tool for inspection and simple manipulation of eBPF links :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **link** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | - { **-f** | **--bpffs** } | { **-n** | **--nomount** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } *COMMANDS* := { **show** | **list** | **pin** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 991d18fd84f2..7c188a598444 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-map ================ @@ -7,13 +9,14 @@ tool for inspection and simple manipulation of eBPF maps :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **map** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | - { **-f** | **--bpffs** } | { **-n** | **--nomount** } } + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-n** | **--nomount** } } *COMMANDS* := { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 7ec57535a7c1..f4e0a516335a 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-net ================ @@ -7,12 +9,14 @@ tool for inspection of netdev/tc related bpf prog attachments :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **net** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index ce52798a917d..5fea633a82f1 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-perf ================ @@ -7,12 +9,14 @@ tool for inspection of perf related bpf prog attachments :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **perf** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **show** | **list** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index f27265bd589b..a2e9359e554c 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ bpftool-prog ================ @@ -7,12 +9,14 @@ tool for inspection and simple manipulation of eBPF progs :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **prog** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | + *OPTIONS* := { |COMMON_OPTIONS| | { **-f** | **--bpffs** } | { **-m** | **--mapcompat** } | { **-n** | **--nomount** } | { **-L** | **--use-loader** } } diff --git a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst index 02afc0fc14cb..ee53a122c0c7 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-struct_ops.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================== bpftool-struct_ops ================== @@ -7,12 +9,14 @@ tool to register/unregister/introspect BPF struct_ops :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== **bpftool** [*OPTIONS*] **struct_ops** *COMMAND* - *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { |COMMON_OPTIONS| } *COMMANDS* := { **show** | **list** | **dump** | **register** | **unregister** | **help** } diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 8ac86565c501..7084dd9fa2f8 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + ================ BPFTOOL ================ @@ -7,6 +9,8 @@ tool for inspection and simple manipulation of eBPF programs and maps :Manual section: 8 +.. include:: substitutions.rst + SYNOPSIS ======== @@ -18,8 +22,7 @@ SYNOPSIS *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** } - *OPTIONS* := { { **-V** | **--version** } | - { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } } + *OPTIONS* := { { **-V** | **--version** } | |COMMON_OPTIONS| } *MAP-COMMANDS* := { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** | diff --git a/tools/bpf/bpftool/Documentation/common_options.rst b/tools/bpf/bpftool/Documentation/common_options.rst index 75adf23202d8..908487b9c2ad 100644 --- a/tools/bpf/bpftool/Documentation/common_options.rst +++ b/tools/bpf/bpftool/Documentation/common_options.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + -h, --help Print short help message (similar to **bpftool help**). diff --git a/tools/bpf/bpftool/Documentation/substitutions.rst b/tools/bpf/bpftool/Documentation/substitutions.rst new file mode 100644 index 000000000000..ccf1ffa0686c --- /dev/null +++ b/tools/bpf/bpftool/Documentation/substitutions.rst @@ -0,0 +1,3 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +.. |COMMON_OPTIONS| replace:: { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-d** | **--debug** } | { **-l** | **--legacy** } diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 997a2865e04a..b4695df2ea3d 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -486,7 +486,6 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *header_guard) { - struct bpf_object_load_attr load_attr = {}; DECLARE_LIBBPF_OPTS(gen_loader_opts, opts); struct bpf_map *map; char ident[256]; @@ -496,12 +495,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h if (err) return err; - load_attr.obj = obj; - if (verifier_logs) - /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; - - err = bpf_object__load_xattr(&load_attr); + err = bpf_object__load(obj); if (err) { p_err("failed to load object file"); goto out; @@ -719,6 +713,9 @@ static int do_skeleton(int argc, char **argv) if (obj_name[0] == '\0') get_obj_name(obj_name, file); opts.object_name = obj_name; + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + opts.kernel_log_level = 1 + 2 + 4; obj = bpf_object__open_mem(obj_data, file_sz, &opts); err = libbpf_get_error(obj); if (err) { diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 473791e87f7d..8b71500e7cb2 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -93,6 +93,7 @@ static int do_version(int argc, char **argv) jsonw_name(json_wtr, "features"); jsonw_start_object(json_wtr); /* features */ jsonw_bool_field(json_wtr, "libbfd", has_libbfd); + jsonw_bool_field(json_wtr, "libbpf_strict", !legacy_libbpf); jsonw_bool_field(json_wtr, "skeletons", has_skeletons); jsonw_end_object(json_wtr); /* features */ @@ -106,6 +107,10 @@ static int do_version(int argc, char **argv) printf(" libbfd"); nb_features++; } + if (!legacy_libbpf) { + printf("%s libbpf_strict", nb_features++ ? "," : ""); + nb_features++; + } if (has_skeletons) printf("%s skeletons", nb_features++ ? "," : ""); printf("\n"); @@ -400,6 +405,7 @@ int main(int argc, char **argv) { "legacy", no_argument, NULL, 'l' }, { 0 } }; + bool version_requested = false; int opt, ret; last_do_help = do_help; @@ -414,7 +420,8 @@ int main(int argc, char **argv) options, NULL)) >= 0) { switch (opt) { case 'V': - return do_version(argc, argv); + version_requested = true; + break; case 'h': return do_help(argc, argv); case 'p': @@ -479,6 +486,9 @@ int main(int argc, char **argv) if (argc < 0) usage(); + if (version_requested) + return do_version(argc, argv); + ret = cmd_select(cmds, argc, argv, do_help); if (json_output) diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 25b258804f11..cc530a229812 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1261,7 +1261,10 @@ static int do_pin(int argc, char **argv) static int do_create(int argc, char **argv) { - struct bpf_create_map_attr attr = { NULL, }; + LIBBPF_OPTS(bpf_map_create_opts, attr); + enum bpf_map_type map_type = BPF_MAP_TYPE_UNSPEC; + __u32 key_size = 0, value_size = 0, max_entries = 0; + const char *map_name = NULL; const char *pinfile; int err = -1, fd; @@ -1276,30 +1279,30 @@ static int do_create(int argc, char **argv) if (is_prefix(*argv, "type")) { NEXT_ARG(); - if (attr.map_type) { + if (map_type) { p_err("map type already specified"); goto exit; } - attr.map_type = map_type_from_str(*argv); - if ((int)attr.map_type < 0) { + map_type = map_type_from_str(*argv); + if ((int)map_type < 0) { p_err("unrecognized map type: %s", *argv); goto exit; } NEXT_ARG(); } else if (is_prefix(*argv, "name")) { NEXT_ARG(); - attr.name = GET_ARG(); + map_name = GET_ARG(); } else if (is_prefix(*argv, "key")) { - if (parse_u32_arg(&argc, &argv, &attr.key_size, + if (parse_u32_arg(&argc, &argv, &key_size, "key size")) goto exit; } else if (is_prefix(*argv, "value")) { - if (parse_u32_arg(&argc, &argv, &attr.value_size, + if (parse_u32_arg(&argc, &argv, &value_size, "value size")) goto exit; } else if (is_prefix(*argv, "entries")) { - if (parse_u32_arg(&argc, &argv, &attr.max_entries, + if (parse_u32_arg(&argc, &argv, &max_entries, "max entries")) goto exit; } else if (is_prefix(*argv, "flags")) { @@ -1340,14 +1343,14 @@ static int do_create(int argc, char **argv) } } - if (!attr.name) { + if (!map_name) { p_err("map name not specified"); goto exit; } set_max_rlimit(); - fd = bpf_create_map_xattr(&attr); + fd = bpf_map_create(map_type, map_name, key_size, value_size, max_entries, &attr); if (fd < 0) { p_err("map create failed: %s", strerror(errno)); goto exit; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index e47e8b06cc3d..f874896c4154 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1464,7 +1464,6 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts, .relaxed_maps = relaxed_maps, ); - struct bpf_object_load_attr load_attr = { 0 }; enum bpf_attach_type expected_attach_type; struct map_replace *map_replace = NULL; struct bpf_program *prog = NULL, *pos; @@ -1598,6 +1597,10 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) set_max_rlimit(); + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + obj = bpf_object__open_file(file, &open_opts); if (libbpf_get_error(obj)) { p_err("failed to open object file"); @@ -1677,12 +1680,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only) goto err_close_obj; } - load_attr.obj = obj; - if (verifier_logs) - /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; - - err = bpf_object__load_xattr(&load_attr); + err = bpf_object__load(obj); if (err) { p_err("failed to load object file"); goto err_close_obj; @@ -1774,17 +1772,19 @@ static int try_loader(struct gen_loader_opts *gen) sizeof(struct bpf_prog_desc)); int log_buf_sz = (1u << 24) - 1; int err, fds_before, fd_delta; - char *log_buf; + char *log_buf = NULL; ctx = alloca(ctx_sz); memset(ctx, 0, ctx_sz); ctx->sz = ctx_sz; - ctx->log_level = 1; - ctx->log_size = log_buf_sz; - log_buf = malloc(log_buf_sz); - if (!log_buf) - return -ENOMEM; - ctx->log_buf = (long) log_buf; + if (verifier_logs) { + ctx->log_level = 1 + 2 + 4; + ctx->log_size = log_buf_sz; + log_buf = malloc(log_buf_sz); + if (!log_buf) + return -ENOMEM; + ctx->log_buf = (long) log_buf; + } opts.ctx = ctx; opts.data = gen->data; opts.data_sz = gen->data_sz; @@ -1793,9 +1793,9 @@ static int try_loader(struct gen_loader_opts *gen) fds_before = count_open_fds(); err = bpf_load_and_run(&opts); fd_delta = count_open_fds() - fds_before; - if (err < 0) { + if (err < 0 || verifier_logs) { fprintf(stderr, "err %d\n%s\n%s", err, opts.errstr, log_buf); - if (fd_delta) + if (fd_delta && err < 0) fprintf(stderr, "loader prog leaked %d FDs\n", fd_delta); } @@ -1807,7 +1807,6 @@ static int do_loader(int argc, char **argv) { DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts); DECLARE_LIBBPF_OPTS(gen_loader_opts, gen); - struct bpf_object_load_attr load_attr = {}; struct bpf_object *obj; const char *file; int err = 0; @@ -1816,6 +1815,10 @@ static int do_loader(int argc, char **argv) return -1; file = GET_ARG(); + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + obj = bpf_object__open_file(file, &open_opts); if (libbpf_get_error(obj)) { p_err("failed to open object file"); @@ -1826,12 +1829,7 @@ static int do_loader(int argc, char **argv) if (err) goto err_close_obj; - load_attr.obj = obj; - if (verifier_logs) - /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; - - err = bpf_object__load_xattr(&load_attr); + err = bpf_object__load(obj); if (err) { p_err("failed to load object file"); goto err_close_obj; diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index cbdca37a53f0..2f693b082bdb 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -479,7 +479,7 @@ static int do_unregister(int argc, char **argv) static int do_register(int argc, char **argv) { - struct bpf_object_load_attr load_attr = {}; + LIBBPF_OPTS(bpf_object_open_opts, open_opts); const struct bpf_map_def *def; struct bpf_map_info info = {}; __u32 info_len = sizeof(info); @@ -494,18 +494,17 @@ static int do_register(int argc, char **argv) file = GET_ARG(); - obj = bpf_object__open(file); + if (verifier_logs) + /* log_level1 + log_level2 + stats, but not stable UAPI */ + open_opts.kernel_log_level = 1 + 2 + 4; + + obj = bpf_object__open_file(file, &open_opts); if (libbpf_get_error(obj)) return -1; set_max_rlimit(); - load_attr.obj = obj; - if (verifier_logs) - /* log_level1 + log_level2 + stats, but not stable UAPI */ - load_attr.log_level = 1 + 2 + 4; - - if (bpf_object__load_xattr(&load_attr)) { + if (bpf_object__load(obj)) { bpf_object__close(obj); return -1; } diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index a59cb0ee609c..5d26f3c6f918 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -83,6 +83,7 @@ struct btf_id { int cnt; }; int addr_cnt; + bool is_set; Elf64_Addr addr[ADDR_CNT]; }; @@ -167,7 +168,7 @@ static struct btf_id *btf_id__find(struct rb_root *root, const char *name) return NULL; } -static struct btf_id* +static struct btf_id * btf_id__add(struct rb_root *root, char *name, bool unique) { struct rb_node **p = &root->rb_node; @@ -451,8 +452,10 @@ static int symbols_collect(struct object *obj) * in symbol's size, together with 'cnt' field hence * that - 1. */ - if (id) + if (id) { id->cnt = sym.st_size / sizeof(int) - 1; + id->is_set = true; + } } else { pr_err("FAILED unsupported prefix %s\n", prefix); return -1; @@ -568,9 +571,8 @@ static int id_patch(struct object *obj, struct btf_id *id) int *ptr = data->d_buf; int i; - if (!id->id) { + if (!id->id && !id->is_set) pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name); - } for (i = 0; i < id->addr_cnt; i++) { unsigned long addr = id->addr[i]; @@ -730,7 +732,8 @@ int main(int argc, const char **argv) if (obj.efile.idlist_shndx == -1 || obj.efile.symbols_shndx == -1) { pr_debug("Cannot find .BTF_ids or symbols sections, nothing to do\n"); - return 0; + err = 0; + goto out; } if (symbols_collect(&obj)) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 45a9a59828c3..ae61f464043a 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -48,7 +48,6 @@ FEATURE_TESTS_BASIC := \ numa_num_possible_cpus \ libperl \ libpython \ - libpython-version \ libslang \ libslang-include-subdir \ libtraceevent \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 0a3244ad9673..1480910c792e 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -32,7 +32,6 @@ FILES= \ test-numa_num_possible_cpus.bin \ test-libperl.bin \ test-libpython.bin \ - test-libpython-version.bin \ test-libslang.bin \ test-libslang-include-subdir.bin \ test-libtraceevent.bin \ @@ -227,9 +226,6 @@ $(OUTPUT)test-libperl.bin: $(OUTPUT)test-libpython.bin: $(BUILD) $(FLAGS_PYTHON_EMBED) -$(OUTPUT)test-libpython-version.bin: - $(BUILD) - $(OUTPUT)test-libbfd.bin: $(BUILD) -DPACKAGE='"perf"' -lbfd -ldl diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 0b243ce842be..5ffafb967b6e 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -14,10 +14,6 @@ # include "test-libpython.c" #undef main -#define main main_test_libpython_version -# include "test-libpython-version.c" -#undef main - #define main main_test_libperl # include "test-libperl.c" #undef main @@ -177,7 +173,6 @@ int main(int argc, char *argv[]) { main_test_libpython(); - main_test_libpython_version(); main_test_libperl(); main_test_hello(); main_test_libelf(); diff --git a/tools/build/feature/test-bpf.c b/tools/build/feature/test-bpf.c index 82070eadfc07..727d22e34a6e 100644 --- a/tools/build/feature/test-bpf.c +++ b/tools/build/feature/test-bpf.c @@ -14,6 +14,12 @@ # define __NR_bpf 349 # elif defined(__s390__) # define __NR_bpf 351 +# elif defined(__mips__) && defined(_ABIO32) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif diff --git a/tools/build/feature/test-libpython-version.c b/tools/build/feature/test-libpython-version.c deleted file mode 100644 index 47714b942d4d..000000000000 --- a/tools/build/feature/test-libpython-version.c +++ /dev/null @@ -1,11 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <Python.h> - -#if PY_VERSION_HEX >= 0x03000000 - #error -#endif - -int main(void) -{ - return 0; -} diff --git a/tools/include/linux/debug_locks.h b/tools/include/linux/debug_locks.h deleted file mode 100644 index 72d595ce764a..000000000000 --- a/tools/include/linux/debug_locks.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_ -#define _LIBLOCKDEP_DEBUG_LOCKS_H_ - -#include <stddef.h> -#include <linux/compiler.h> -#include <asm/bug.h> - -#define DEBUG_LOCKS_WARN_ON(x) WARN_ON(x) - -extern bool debug_locks; -extern bool debug_locks_silent; - -#endif diff --git a/tools/include/linux/hardirq.h b/tools/include/linux/hardirq.h deleted file mode 100644 index b25580b6a9be..000000000000 --- a/tools/include/linux/hardirq.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_ -#define _LIBLOCKDEP_LINUX_HARDIRQ_H_ - -#define SOFTIRQ_BITS 0UL -#define HARDIRQ_BITS 0UL -#define SOFTIRQ_SHIFT 0UL -#define HARDIRQ_SHIFT 0UL -#define hardirq_count() 0UL -#define softirq_count() 0UL - -#endif diff --git a/tools/include/linux/irqflags.h b/tools/include/linux/irqflags.h deleted file mode 100644 index 501262aee8ff..000000000000 --- a/tools/include/linux/irqflags.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ -#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_ - -# define lockdep_hardirq_context() 0 -# define lockdep_softirq_context(p) 0 -# define lockdep_hardirqs_enabled() 0 -# define lockdep_softirqs_enabled(p) 0 -# define lockdep_hardirq_enter() do { } while (0) -# define lockdep_hardirq_exit() do { } while (0) -# define lockdep_softirq_enter() do { } while (0) -# define lockdep_softirq_exit() do { } while (0) -# define INIT_TRACE_IRQFLAGS - -# define stop_critical_timings() do { } while (0) -# define start_critical_timings() do { } while (0) - -#define raw_local_irq_disable() do { } while (0) -#define raw_local_irq_enable() do { } while (0) -#define raw_local_irq_save(flags) ((flags) = 0) -#define raw_local_irq_restore(flags) ((void)(flags)) -#define raw_local_save_flags(flags) ((flags) = 0) -#define raw_irqs_disabled_flags(flags) ((void)(flags)) -#define raw_irqs_disabled() 0 -#define raw_safe_halt() - -#define local_irq_enable() do { } while (0) -#define local_irq_disable() do { } while (0) -#define local_irq_save(flags) ((flags) = 0) -#define local_irq_restore(flags) ((void)(flags)) -#define local_save_flags(flags) ((flags) = 0) -#define irqs_disabled() (1) -#define irqs_disabled_flags(flags) ((void)(flags), 0) -#define safe_halt() do { } while (0) - -#define trace_lock_release(x, y) -#define trace_lock_acquire(a, b, c, d, e, f, g) - -#endif diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h deleted file mode 100644 index e56997288f2b..000000000000 --- a/tools/include/linux/lockdep.h +++ /dev/null @@ -1,72 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LOCKDEP_H_ -#define _LIBLOCKDEP_LOCKDEP_H_ - -#include <sys/prctl.h> -#include <sys/syscall.h> -#include <string.h> -#include <limits.h> -#include <linux/utsname.h> -#include <linux/compiler.h> -#include <linux/export.h> -#include <linux/kern_levels.h> -#include <linux/err.h> -#include <linux/rcu.h> -#include <linux/list.h> -#include <linux/hardirq.h> -#include <unistd.h> - -#define MAX_LOCK_DEPTH 63UL - -#define asmlinkage -#define __visible - -#include "../../../include/linux/lockdep.h" - -struct task_struct { - u64 curr_chain_key; - int lockdep_depth; - unsigned int lockdep_recursion; - struct held_lock held_locks[MAX_LOCK_DEPTH]; - gfp_t lockdep_reclaim_gfp; - int pid; - int state; - char comm[17]; -}; - -#define TASK_RUNNING 0 - -extern struct task_struct *__curr(void); - -#define current (__curr()) - -static inline int debug_locks_off(void) -{ - return 1; -} - -#define task_pid_nr(tsk) ((tsk)->pid) - -#define KSYM_NAME_LEN 128 -#define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__) -#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__) -#define pr_warn pr_err -#define pr_cont pr_err - -#define list_del_rcu list_del - -#define atomic_t unsigned long -#define atomic_inc(x) ((*(x))++) - -#define print_tainted() "" -#define static_obj(x) 1 - -#define debug_show_all_locks() -extern void debug_check_no_locks_held(void); - -static __used bool __is_kernel_percpu_address(unsigned long addr, void *can_addr) -{ - return false; -} - -#endif diff --git a/tools/include/linux/proc_fs.h b/tools/include/linux/proc_fs.h deleted file mode 100644 index 8b3b03b64fda..000000000000 --- a/tools/include/linux/proc_fs.h +++ /dev/null @@ -1,4 +0,0 @@ -#ifndef _TOOLS_INCLUDE_LINUX_PROC_FS_H -#define _TOOLS_INCLUDE_LINUX_PROC_FS_H - -#endif /* _TOOLS_INCLUDE_LINUX_PROC_FS_H */ diff --git a/tools/include/linux/spinlock.h b/tools/include/linux/spinlock.h index c934572d935c..622266b197d0 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -37,6 +37,4 @@ static inline bool arch_spin_is_locked(arch_spinlock_t *mutex) return true; } -#include <linux/lockdep.h> - #endif diff --git a/tools/include/linux/stacktrace.h b/tools/include/linux/stacktrace.h deleted file mode 100644 index ae343ac35bfa..000000000000 --- a/tools/include/linux/stacktrace.h +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_STACKTRACE_H_ -#define _LIBLOCKDEP_LINUX_STACKTRACE_H_ - -#include <execinfo.h> - -struct stack_trace { - unsigned int nr_entries, max_entries; - unsigned long *entries; - int skip; -}; - -static inline void print_stack_trace(struct stack_trace *trace, int spaces) -{ - backtrace_symbols_fd((void **)trace->entries, trace->nr_entries, 1); -} - -#define save_stack_trace(trace) \ - ((trace)->nr_entries = \ - backtrace((void **)(trace)->entries, (trace)->max_entries)) - -static inline int dump_stack(void) -{ - void *array[64]; - size_t size; - - size = backtrace(array, 64); - backtrace_symbols_fd(array, size, 1); - - return 0; -} - -#endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6297eafdc40f..c26871263f1f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1342,8 +1342,10 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; - __u32 :32; /* pad */ + __u32 core_relo_cnt; /* number of bpf_core_relo */ __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1744,7 +1746,7 @@ union bpf_attr { * if the maximum number of tail calls has been reached for this * chain of programs. This limit is defined in the kernel by the * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), - * which is currently set to 32. + * which is currently set to 33. * Return * 0 on success, or a negative error in case of failure. * @@ -4957,6 +4959,30 @@ union bpf_attr { * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. * **-EBUSY** if failed to try lock mmap_lock. * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5140,6 +5166,7 @@ union bpf_attr { FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ FN(find_vma), \ + FN(loop), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -6349,4 +6376,78 @@ enum { BTF_F_ZERO = (1ULL << 3), }; +/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value + * has to be adjusted by relocations. It is emitted by llvm and passed to + * libbpf and later to the kernel. + */ +enum bpf_core_relo_kind { + BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */ + BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ + BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ + BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ + BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ + BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */ + BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */ + BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ + BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ + BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ +}; + +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 94560ba31724..6b2407e12060 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -50,6 +50,12 @@ # define __NR_bpf 351 # elif defined(__arc__) # define __NR_bpf 280 +# elif defined(__mips__) && defined(_ABIO32) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 # else # error __NR_bpf not defined. libbpf does not support your arch. # endif @@ -88,146 +94,122 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size, int return fd; } -int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr) +int bpf_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts) { + const size_t attr_sz = offsetofend(union bpf_attr, map_extra); union bpf_attr attr; int fd; - memset(&attr, '\0', sizeof(attr)); - - attr.map_type = create_attr->map_type; - attr.key_size = create_attr->key_size; - attr.value_size = create_attr->value_size; - attr.max_entries = create_attr->max_entries; - attr.map_flags = create_attr->map_flags; - if (create_attr->name) - memcpy(attr.map_name, create_attr->name, - min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1)); - attr.numa_node = create_attr->numa_node; - attr.btf_fd = create_attr->btf_fd; - attr.btf_key_type_id = create_attr->btf_key_type_id; - attr.btf_value_type_id = create_attr->btf_value_type_id; - attr.map_ifindex = create_attr->map_ifindex; - if (attr.map_type == BPF_MAP_TYPE_STRUCT_OPS) - attr.btf_vmlinux_value_type_id = - create_attr->btf_vmlinux_value_type_id; - else - attr.inner_map_fd = create_attr->inner_map_fd; - attr.map_extra = create_attr->map_extra; + memset(&attr, 0, attr_sz); + + if (!OPTS_VALID(opts, bpf_map_create_opts)) + return libbpf_err(-EINVAL); + + attr.map_type = map_type; + if (map_name) + strncat(attr.map_name, map_name, sizeof(attr.map_name) - 1); + attr.key_size = key_size; + attr.value_size = value_size; + attr.max_entries = max_entries; + + attr.btf_fd = OPTS_GET(opts, btf_fd, 0); + attr.btf_key_type_id = OPTS_GET(opts, btf_key_type_id, 0); + attr.btf_value_type_id = OPTS_GET(opts, btf_value_type_id, 0); + attr.btf_vmlinux_value_type_id = OPTS_GET(opts, btf_vmlinux_value_type_id, 0); - fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr)); + attr.inner_map_fd = OPTS_GET(opts, inner_map_fd, 0); + attr.map_flags = OPTS_GET(opts, map_flags, 0); + attr.map_extra = OPTS_GET(opts, map_extra, 0); + attr.numa_node = OPTS_GET(opts, numa_node, 0); + attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); + + fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) { - struct bpf_create_map_params p = {}; + LIBBPF_OPTS(bpf_map_create_opts, p); - p.map_type = create_attr->map_type; - p.key_size = create_attr->key_size; - p.value_size = create_attr->value_size; - p.max_entries = create_attr->max_entries; p.map_flags = create_attr->map_flags; - p.name = create_attr->name; p.numa_node = create_attr->numa_node; p.btf_fd = create_attr->btf_fd; p.btf_key_type_id = create_attr->btf_key_type_id; p.btf_value_type_id = create_attr->btf_value_type_id; p.map_ifindex = create_attr->map_ifindex; - if (p.map_type == BPF_MAP_TYPE_STRUCT_OPS) - p.btf_vmlinux_value_type_id = - create_attr->btf_vmlinux_value_type_id; + if (create_attr->map_type == BPF_MAP_TYPE_STRUCT_OPS) + p.btf_vmlinux_value_type_id = create_attr->btf_vmlinux_value_type_id; else p.inner_map_fd = create_attr->inner_map_fd; - return libbpf__bpf_create_map_xattr(&p); + return bpf_map_create(create_attr->map_type, create_attr->name, + create_attr->key_size, create_attr->value_size, + create_attr->max_entries, &p); } int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags, int node) { - struct bpf_create_map_attr map_attr = {}; - - map_attr.name = name; - map_attr.map_type = map_type; - map_attr.map_flags = map_flags; - map_attr.key_size = key_size; - map_attr.value_size = value_size; - map_attr.max_entries = max_entries; + LIBBPF_OPTS(bpf_map_create_opts, opts); + + opts.map_flags = map_flags; if (node >= 0) { - map_attr.numa_node = node; - map_attr.map_flags |= BPF_F_NUMA_NODE; + opts.numa_node = node; + opts.map_flags |= BPF_F_NUMA_NODE; } - return bpf_create_map_xattr(&map_attr); + return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts); } int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags) { - struct bpf_create_map_attr map_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags); - map_attr.map_type = map_type; - map_attr.map_flags = map_flags; - map_attr.key_size = key_size; - map_attr.value_size = value_size; - map_attr.max_entries = max_entries; - - return bpf_create_map_xattr(&map_attr); + return bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts); } int bpf_create_map_name(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags) { - struct bpf_create_map_attr map_attr = {}; - - map_attr.name = name; - map_attr.map_type = map_type; - map_attr.map_flags = map_flags; - map_attr.key_size = key_size; - map_attr.value_size = value_size; - map_attr.max_entries = max_entries; + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags); - return bpf_create_map_xattr(&map_attr); + return bpf_map_create(map_type, name, key_size, value_size, max_entries, &opts); } int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node) { - union bpf_attr attr; - int fd; - - memset(&attr, '\0', sizeof(attr)); - - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = 4; - attr.inner_map_fd = inner_map_fd; - attr.max_entries = max_entries; - attr.map_flags = map_flags; - if (name) - memcpy(attr.map_name, name, - min(strlen(name), BPF_OBJ_NAME_LEN - 1)); + LIBBPF_OPTS(bpf_map_create_opts, opts); + opts.inner_map_fd = inner_map_fd; + opts.map_flags = map_flags; if (node >= 0) { - attr.map_flags |= BPF_F_NUMA_NODE; - attr.numa_node = node; + opts.map_flags |= BPF_F_NUMA_NODE; + opts.numa_node = node; } - fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr)); - return libbpf_err_errno(fd); + return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts); } int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags) { - return bpf_create_map_in_map_node(map_type, name, key_size, - inner_map_fd, max_entries, map_flags, - -1); + LIBBPF_OPTS(bpf_map_create_opts, opts, + .inner_map_fd = inner_map_fd, + .map_flags = map_flags, + ); + + return bpf_map_create(map_type, name, key_size, 4, max_entries, &opts); } static void * @@ -321,10 +303,6 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type, if (log_level && !log_buf) return libbpf_err(-EINVAL); - attr.log_level = log_level; - attr.log_buf = ptr_to_u64(log_buf); - attr.log_size = log_size; - func_info_rec_size = OPTS_GET(opts, func_info_rec_size, 0); func_info = OPTS_GET(opts, func_info, NULL); attr.func_info_rec_size = func_info_rec_size; @@ -339,6 +317,12 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type, attr.fd_array = ptr_to_u64(OPTS_GET(opts, fd_array, NULL)); + if (log_level) { + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_size; + attr.log_level = log_level; + } + fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); if (fd >= 0) return fd; @@ -384,16 +368,17 @@ int bpf_prog_load_v0_6_0(enum bpf_prog_type prog_type, goto done; } - if (log_level || !log_buf) - goto done; + if (log_level == 0 && log_buf) { + /* log_level == 0 with non-NULL log_buf requires retrying on error + * with log_level == 1 and log_buf/log_buf_size set, to get details of + * failure + */ + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_size; + attr.log_level = 1; - /* Try again with log */ - log_buf[0] = 0; - attr.log_buf = ptr_to_u64(log_buf); - attr.log_size = log_size; - attr.log_level = 1; - - fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); + fd = sys_bpf_prog_load(&attr, sizeof(attr), attempts); + } done: /* free() doesn't affect errno, so we don't need to restore it */ free(finfo); @@ -1062,24 +1047,65 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) return libbpf_err_errno(fd); } -int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, - bool do_log) +int bpf_btf_load(const void *btf_data, size_t btf_size, const struct bpf_btf_load_opts *opts) { - union bpf_attr attr = {}; + const size_t attr_sz = offsetofend(union bpf_attr, btf_log_level); + union bpf_attr attr; + char *log_buf; + size_t log_size; + __u32 log_level; int fd; - attr.btf = ptr_to_u64(btf); + memset(&attr, 0, attr_sz); + + if (!OPTS_VALID(opts, bpf_btf_load_opts)) + return libbpf_err(-EINVAL); + + log_buf = OPTS_GET(opts, log_buf, NULL); + log_size = OPTS_GET(opts, log_size, 0); + log_level = OPTS_GET(opts, log_level, 0); + + if (log_size > UINT_MAX) + return libbpf_err(-EINVAL); + if (log_size && !log_buf) + return libbpf_err(-EINVAL); + + attr.btf = ptr_to_u64(btf_data); attr.btf_size = btf_size; + /* log_level == 0 and log_buf != NULL means "try loading without + * log_buf, but retry with log_buf and log_level=1 on error", which is + * consistent across low-level and high-level BTF and program loading + * APIs within libbpf and provides a sensible behavior in practice + */ + if (log_level) { + attr.btf_log_buf = ptr_to_u64(log_buf); + attr.btf_log_size = (__u32)log_size; + attr.btf_log_level = log_level; + } -retry: - if (do_log && log_buf && log_buf_size) { - attr.btf_log_level = 1; - attr.btf_log_size = log_buf_size; + fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); + if (fd < 0 && log_buf && log_level == 0) { attr.btf_log_buf = ptr_to_u64(log_buf); + attr.btf_log_size = (__u32)log_size; + attr.btf_log_level = 1; + fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, attr_sz); } + return libbpf_err_errno(fd); +} + +int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, bool do_log) +{ + LIBBPF_OPTS(bpf_btf_load_opts, opts); + int fd; - fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, sizeof(attr)); +retry: + if (do_log && log_buf && log_buf_size) { + opts.log_buf = log_buf; + opts.log_size = log_buf_size; + opts.log_level = 1; + } + fd = bpf_btf_load(btf, btf_size, &opts); if (fd < 0 && !do_log && log_buf && log_buf_size) { do_log = true; goto retry; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 079cc81ac51e..94e553a0ff9d 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -35,6 +35,30 @@ extern "C" { #endif +struct bpf_map_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + __u32 btf_fd; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 btf_vmlinux_value_type_id; + + __u32 inner_map_fd; + __u32 map_flags; + __u64 map_extra; + + __u32 numa_node; + __u32 map_ifindex; +}; +#define bpf_map_create_opts__last_field map_ifindex + +LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts); + struct bpf_create_map_attr { const char *name; enum bpf_map_type map_type; @@ -53,20 +77,25 @@ struct bpf_create_map_attr { }; }; -LIBBPF_API int -bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") +LIBBPF_API int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags, int node); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, __u32 map_flags, int node); +LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_map_create() instead") LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, int key_size, int inner_map_fd, int max_entries, @@ -166,8 +195,9 @@ struct bpf_load_program_attr { /* Flags to direct loading requirements */ #define MAPS_RELAX_COMPAT 0x01 -/* Recommend log buffer size */ +/* Recommended log buffer size */ #define BPF_LOG_BUF_SIZE (UINT32_MAX >> 8) /* verifier maximum in kernels <= 5.1 */ + LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_prog_load() instead") LIBBPF_API int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, char *log_buf, size_t log_buf_sz); @@ -184,6 +214,23 @@ LIBBPF_API int bpf_verify_program(enum bpf_prog_type type, char *log_buf, size_t log_buf_sz, int log_level); +struct bpf_btf_load_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + + /* kernel log options */ + char *log_buf; + __u32 log_level; + __u32 log_size; +}; +#define bpf_btf_load_opts__last_field log_size + +LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, + const struct bpf_btf_load_opts *opts); + +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_btf_load() instead") +LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, + __u32 log_buf_size, bool do_log); + LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); @@ -311,8 +358,6 @@ LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd); -LIBBPF_API int bpf_load_btf(const void *btf, __u32 btf_size, char *log_buf, - __u32 log_buf_size, bool do_log); LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, __u64 *probe_addr); diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index cc486a77db65..223308931d55 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -39,6 +39,8 @@ struct bpf_gen { int error; struct ksym_relo_desc *relos; int relo_cnt; + struct bpf_core_relo *core_relos; + int core_relo_cnt; char attach_target[128]; int attach_kind; struct ksym_desc *ksyms; @@ -51,7 +53,10 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps); void bpf_gen__free(struct bpf_gen *gen); void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); -void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx); +void bpf_gen__map_create(struct bpf_gen *gen, + enum bpf_map_type map_type, const char *map_name, + __u32 key_size, __u32 value_size, __u32 max_entries, + struct bpf_map_create_opts *map_attr, int map_idx); void bpf_gen__prog_load(struct bpf_gen *gen, enum bpf_prog_type prog_type, const char *prog_name, const char *license, struct bpf_insn *insns, size_t insn_cnt, @@ -61,5 +66,7 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx); void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type); void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, bool is_typeless, int kind, int insn_idx); +void bpf_gen__record_relo_core(struct bpf_gen *gen, const struct bpf_core_relo *core_relo); +void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int key, int inner_map_idx); #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index fadf089ae8fe..9aa19c89f758 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -454,7 +454,7 @@ const struct btf *btf__base_btf(const struct btf *btf) } /* internal helper returning non-const pointer to a type */ -struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id) +struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id) { if (type_id == 0) return &btf_void; @@ -610,6 +610,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_RESTRICT: case BTF_KIND_VAR: case BTF_KIND_DECL_TAG: + case BTF_KIND_TYPE_TAG: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -1123,54 +1124,86 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf) static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian); -int btf__load_into_kernel(struct btf *btf) +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level) { - __u32 log_buf_size = 0, raw_size; - char *log_buf = NULL; + LIBBPF_OPTS(bpf_btf_load_opts, opts); + __u32 buf_sz = 0, raw_size; + char *buf = NULL, *tmp; void *raw_data; int err = 0; if (btf->fd >= 0) return libbpf_err(-EEXIST); + if (log_sz && !log_buf) + return libbpf_err(-EINVAL); -retry_load: - if (log_buf_size) { - log_buf = malloc(log_buf_size); - if (!log_buf) - return libbpf_err(-ENOMEM); - - *log_buf = 0; - } - + /* cache native raw data representation */ raw_data = btf_get_raw_data(btf, &raw_size, false); if (!raw_data) { err = -ENOMEM; goto done; } - /* cache native raw data representation */ btf->raw_size = raw_size; btf->raw_data = raw_data; - btf->fd = bpf_load_btf(raw_data, raw_size, log_buf, log_buf_size, false); +retry_load: + /* if log_level is 0, we won't provide log_buf/log_size to the kernel, + * initially. Only if BTF loading fails, we bump log_level to 1 and + * retry, using either auto-allocated or custom log_buf. This way + * non-NULL custom log_buf provides a buffer just in case, but hopes + * for successful load and no need for log_buf. + */ + if (log_level) { + /* if caller didn't provide custom log_buf, we'll keep + * allocating our own progressively bigger buffers for BTF + * verification log + */ + if (!log_buf) { + buf_sz = max((__u32)BPF_LOG_BUF_SIZE, buf_sz * 2); + tmp = realloc(buf, buf_sz); + if (!tmp) { + err = -ENOMEM; + goto done; + } + buf = tmp; + buf[0] = '\0'; + } + + opts.log_buf = log_buf ? log_buf : buf; + opts.log_size = log_buf ? log_sz : buf_sz; + opts.log_level = log_level; + } + + btf->fd = bpf_btf_load(raw_data, raw_size, &opts); if (btf->fd < 0) { - if (!log_buf || errno == ENOSPC) { - log_buf_size = max((__u32)BPF_LOG_BUF_SIZE, - log_buf_size << 1); - free(log_buf); + /* time to turn on verbose mode and try again */ + if (log_level == 0) { + log_level = 1; goto retry_load; } + /* only retry if caller didn't provide custom log_buf, but + * make sure we can never overflow buf_sz + */ + if (!log_buf && errno == ENOSPC && buf_sz <= UINT_MAX / 2) + goto retry_load; err = -errno; - pr_warn("Error loading BTF: %s(%d)\n", strerror(errno), errno); - if (*log_buf) - pr_warn("%s\n", log_buf); - goto done; + pr_warn("BTF loading error: %d\n", err); + /* don't print out contents of custom log_buf */ + if (!log_buf && buf[0]) + pr_warn("-- BEGIN BTF LOAD LOG ---\n%s\n-- END BTF LOAD LOG --\n", buf); } done: - free(log_buf); + free(buf); return libbpf_err(err); } + +int btf__load_into_kernel(struct btf *btf) +{ + return btf_load_into_kernel(btf, NULL, 0, 0); +} + int btf__load(struct btf *) __attribute__((alias("btf__load_into_kernel"))); int btf__fd(const struct btf *btf) @@ -2730,15 +2763,11 @@ void btf_ext__free(struct btf_ext *btf_ext) free(btf_ext); } -struct btf_ext *btf_ext__new(__u8 *data, __u32 size) +struct btf_ext *btf_ext__new(const __u8 *data, __u32 size) { struct btf_ext *btf_ext; int err; - err = btf_ext_parse_hdr(data, size); - if (err) - return libbpf_err_ptr(err); - btf_ext = calloc(1, sizeof(struct btf_ext)); if (!btf_ext) return libbpf_err_ptr(-ENOMEM); @@ -2751,6 +2780,10 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size) } memcpy(btf_ext->data, data, size); + err = btf_ext_parse_hdr(btf_ext->data, size); + if (err) + goto done; + if (btf_ext->hdr->hdr_len < offsetofend(struct btf_ext_header, line_info_len)) { err = -EINVAL; goto done; @@ -3074,7 +3107,7 @@ done: return libbpf_err(err); } -COMPAT_VERSION(bpf__dedup_deprecated, btf__dedup, LIBBPF_0.0.2) +COMPAT_VERSION(btf__dedup_deprecated, btf__dedup, LIBBPF_0.0.2) int btf__dedup_deprecated(struct btf *btf, struct btf_ext *btf_ext, const void *unused_opts) { LIBBPF_OPTS(btf_dedup_opts, opts, .btf_ext = btf_ext); @@ -3476,8 +3509,8 @@ static long btf_hash_struct(struct btf_type *t) } /* - * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type - * IDs. This check is performed during type graph equivalence check and + * Check structural compatibility of two STRUCTs/UNIONs, ignoring referenced + * type IDs. This check is performed during type graph equivalence check and * referenced types equivalence is checked separately. */ static bool btf_shallow_equal_struct(struct btf_type *t1, struct btf_type *t2) @@ -3850,6 +3883,31 @@ static int btf_dedup_identical_arrays(struct btf_dedup *d, __u32 id1, __u32 id2) return btf_equal_array(t1, t2); } +/* Check if given two types are identical STRUCT/UNION definitions */ +static bool btf_dedup_identical_structs(struct btf_dedup *d, __u32 id1, __u32 id2) +{ + const struct btf_member *m1, *m2; + struct btf_type *t1, *t2; + int n, i; + + t1 = btf_type_by_id(d->btf, id1); + t2 = btf_type_by_id(d->btf, id2); + + if (!btf_is_composite(t1) || btf_kind(t1) != btf_kind(t2)) + return false; + + if (!btf_shallow_equal_struct(t1, t2)) + return false; + + m1 = btf_members(t1); + m2 = btf_members(t2); + for (i = 0, n = btf_vlen(t1); i < n; i++, m1++, m2++) { + if (m1->type != m2->type) + return false; + } + return true; +} + /* * Check equivalence of BTF type graph formed by candidate struct/union (we'll * call it "candidate graph" in this description for brevity) to a type graph @@ -3961,6 +4019,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, hypot_type_id = d->hypot_map[canon_id]; if (hypot_type_id <= BTF_MAX_NR_TYPES) { + if (hypot_type_id == cand_id) + return 1; /* In some cases compiler will generate different DWARF types * for *identical* array type definitions and use them for * different fields within the *same* struct. This breaks type @@ -3969,8 +4029,18 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, * types within a single CU. So work around that by explicitly * allowing identical array types here. */ - return hypot_type_id == cand_id || - btf_dedup_identical_arrays(d, hypot_type_id, cand_id); + if (btf_dedup_identical_arrays(d, hypot_type_id, cand_id)) + return 1; + /* It turns out that similar situation can happen with + * struct/union sometimes, sigh... Handle the case where + * structs/unions are exactly the same, down to the referenced + * type IDs. Anything more complicated (e.g., if referenced + * types are different, but equivalent) is *way more* + * complicated and requires a many-to-many equivalence mapping. + */ + if (btf_dedup_identical_structs(d, hypot_type_id, cand_id)) + return 1; + return 0; } if (btf_dedup_hypot_map_add(d, canon_id, cand_id)) @@ -4023,6 +4093,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, case BTF_KIND_PTR: case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: + case BTF_KIND_TYPE_TAG: if (cand_type->info != canon_type->info) return 0; return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 5c73a5b0a044..742a2bf71c5e 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -157,7 +157,7 @@ LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, __u32 expected_value_size, __u32 *key_type_id, __u32 *value_type_id); -LIBBPF_API struct btf_ext *btf_ext__new(__u8 *data, __u32 size); +LIBBPF_API struct btf_ext *btf_ext__new(const __u8 *data, __u32 size); LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 05f3e7dfec0a..f06a1d343c92 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -2216,7 +2216,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, __u8 bits_offset, __u8 bit_sz) { - int size, err; + int size, err = 0; size = btf_dump_type_data_check_overflow(d, t, id, data, bits_offset); if (size < 0) diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index c28ab24d1bff..8ed02e89c9a9 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -445,47 +445,33 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data, } void bpf_gen__map_create(struct bpf_gen *gen, - struct bpf_create_map_params *map_attr, int map_idx) + enum bpf_map_type map_type, + const char *map_name, + __u32 key_size, __u32 value_size, __u32 max_entries, + struct bpf_map_create_opts *map_attr, int map_idx) { - int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id); + int attr_size = offsetofend(union bpf_attr, map_extra); bool close_inner_map_fd = false; int map_create_attr, idx; union bpf_attr attr; memset(&attr, 0, attr_size); - attr.map_type = map_attr->map_type; - attr.key_size = map_attr->key_size; - attr.value_size = map_attr->value_size; + attr.map_type = map_type; + attr.key_size = key_size; + attr.value_size = value_size; attr.map_flags = map_attr->map_flags; attr.map_extra = map_attr->map_extra; - memcpy(attr.map_name, map_attr->name, - min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1)); + if (map_name) + memcpy(attr.map_name, map_name, + min((unsigned)strlen(map_name), BPF_OBJ_NAME_LEN - 1)); attr.numa_node = map_attr->numa_node; attr.map_ifindex = map_attr->map_ifindex; - attr.max_entries = map_attr->max_entries; - switch (attr.map_type) { - case BPF_MAP_TYPE_PERF_EVENT_ARRAY: - case BPF_MAP_TYPE_CGROUP_ARRAY: - case BPF_MAP_TYPE_STACK_TRACE: - case BPF_MAP_TYPE_ARRAY_OF_MAPS: - case BPF_MAP_TYPE_HASH_OF_MAPS: - case BPF_MAP_TYPE_DEVMAP: - case BPF_MAP_TYPE_DEVMAP_HASH: - case BPF_MAP_TYPE_CPUMAP: - case BPF_MAP_TYPE_XSKMAP: - case BPF_MAP_TYPE_SOCKMAP: - case BPF_MAP_TYPE_SOCKHASH: - case BPF_MAP_TYPE_QUEUE: - case BPF_MAP_TYPE_STACK: - case BPF_MAP_TYPE_RINGBUF: - break; - default: - attr.btf_key_type_id = map_attr->btf_key_type_id; - attr.btf_value_type_id = map_attr->btf_value_type_id; - } + attr.max_entries = max_entries; + attr.btf_key_type_id = map_attr->btf_key_type_id; + attr.btf_value_type_id = map_attr->btf_value_type_id; pr_debug("gen: map_create: %s idx %d type %d value_type_id %d\n", - attr.map_name, map_idx, map_attr->map_type, attr.btf_value_type_id); + attr.map_name, map_idx, map_type, attr.btf_value_type_id); map_create_attr = add_data(gen, &attr, attr_size); if (attr.btf_value_type_id) @@ -512,7 +498,7 @@ void bpf_gen__map_create(struct bpf_gen *gen, /* emit MAP_CREATE command */ emit_sys_bpf(gen, BPF_MAP_CREATE, map_create_attr, attr_size); debug_ret(gen, "map_create %s idx %d type %d value_size %d value_btf_id %d", - attr.map_name, map_idx, map_attr->map_type, attr.value_size, + attr.map_name, map_idx, map_type, value_size, attr.btf_value_type_id); emit_check_err(gen); /* remember map_fd in the stack, if successful */ @@ -701,27 +687,29 @@ static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo return; } kdesc->off = btf_fd_idx; - /* set a default value for imm */ + /* jump to success case */ + emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); + /* set value for imm, off as 0 */ emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0)); - /* skip success case store if ret < 0 */ - emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 1)); + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip success case for ret < 0 */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 10)); /* store btf_id into insn[insn_idx].imm */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm))); + /* obtain fd in BPF_REG_9 */ + emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7)); + emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); + /* jump to fd_array store if fd denotes module BTF */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 2)); + /* set the default value for off */ + emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); + /* skip BTF fd store for vmlinux BTF */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); /* load fd_array slot pointer */ emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx))); - /* skip store of BTF fd if ret < 0 */ - emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 3)); /* store BTF fd in slot */ - emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7)); - emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32)); emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0)); - /* set a default value for off */ - emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0)); - /* skip insn->off store if ret < 0 */ - emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 2)); - /* skip if vmlinux BTF */ - emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 0, 1)); /* store index into insn[insn_idx].off */ emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx)); log: @@ -820,9 +808,8 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, kdesc->insn + offsetof(struct bpf_insn, imm)); move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4, kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)); - emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_8, offsetof(struct bpf_insn, imm))); - /* jump over src_reg adjustment if imm is not 0 */ - emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 3)); + /* jump over src_reg adjustment if imm is not 0, reuse BPF_REG_0 from move_blob2blob */ + emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3)); goto clear_src_reg; } /* remember insn offset, so we can copy BTF ID and FD later */ @@ -830,17 +817,20 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, emit_bpf_find_by_name_kind(gen, relo); if (!relo->is_weak) emit_check_err(gen); - /* set default values as 0 */ + /* jump to success case */ + emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); + /* set values for insn[insn_idx].imm, insn[insn_idx + 1].imm as 0 */ emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0)); emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0)); - /* skip success case stores if ret < 0 */ - emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 4)); + /* skip success case for ret < 0 */ + emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, 4)); /* store btf_id into insn[insn_idx].imm */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm))); /* store btf_obj_fd into insn[insn_idx + 1].imm */ emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32)); emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm))); + /* skip src_reg adjustment */ emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3)); clear_src_reg: /* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */ @@ -852,6 +842,22 @@ clear_src_reg: emit_ksym_relo_log(gen, relo, kdesc->ref); } +void bpf_gen__record_relo_core(struct bpf_gen *gen, + const struct bpf_core_relo *core_relo) +{ + struct bpf_core_relo *relos; + + relos = libbpf_reallocarray(gen->core_relos, gen->core_relo_cnt + 1, sizeof(*relos)); + if (!relos) { + gen->error = -ENOMEM; + return; + } + gen->core_relos = relos; + relos += gen->core_relo_cnt; + memcpy(relos, core_relo, sizeof(*relos)); + gen->core_relo_cnt++; +} + static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns) { int insn; @@ -884,6 +890,15 @@ static void emit_relos(struct bpf_gen *gen, int insns) emit_relo(gen, gen->relos + i, insns); } +static void cleanup_core_relo(struct bpf_gen *gen) +{ + if (!gen->core_relo_cnt) + return; + free(gen->core_relos); + gen->core_relo_cnt = 0; + gen->core_relos = NULL; +} + static void cleanup_relos(struct bpf_gen *gen, int insns) { int i, insn; @@ -911,6 +926,7 @@ static void cleanup_relos(struct bpf_gen *gen, int insns) gen->relo_cnt = 0; gen->relos = NULL; } + cleanup_core_relo(gen); } void bpf_gen__prog_load(struct bpf_gen *gen, @@ -918,12 +934,13 @@ void bpf_gen__prog_load(struct bpf_gen *gen, const char *license, struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *load_attr, int prog_idx) { - int attr_size = offsetofend(union bpf_attr, fd_array); - int prog_load_attr, license_off, insns_off, func_info, line_info; + int prog_load_attr, license_off, insns_off, func_info, line_info, core_relos; + int attr_size = offsetofend(union bpf_attr, core_relo_rec_size); union bpf_attr attr; memset(&attr, 0, attr_size); - pr_debug("gen: prog_load: type %d insns_cnt %zd\n", prog_type, insn_cnt); + pr_debug("gen: prog_load: type %d insns_cnt %zd progi_idx %d\n", + prog_type, insn_cnt, prog_idx); /* add license string to blob of bytes */ license_off = add_data(gen, license, strlen(license) + 1); /* add insns to blob of bytes */ @@ -947,6 +964,11 @@ void bpf_gen__prog_load(struct bpf_gen *gen, line_info = add_data(gen, load_attr->line_info, attr.line_info_cnt * attr.line_info_rec_size); + attr.core_relo_rec_size = sizeof(struct bpf_core_relo); + attr.core_relo_cnt = gen->core_relo_cnt; + core_relos = add_data(gen, gen->core_relos, + attr.core_relo_cnt * attr.core_relo_rec_size); + memcpy(attr.prog_name, prog_name, min((unsigned)strlen(prog_name), BPF_OBJ_NAME_LEN - 1)); prog_load_attr = add_data(gen, &attr, attr_size); @@ -963,6 +985,9 @@ void bpf_gen__prog_load(struct bpf_gen *gen, /* populate union bpf_attr with a pointer to line_info */ emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info); + /* populate union bpf_attr with a pointer to core_relos */ + emit_rel_store(gen, attr_field(prog_load_attr, core_relos), core_relos); + /* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */ emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array); @@ -993,9 +1018,11 @@ void bpf_gen__prog_load(struct bpf_gen *gen, debug_ret(gen, "prog_load %s insn_cnt %d", attr.prog_name, attr.insn_cnt); /* successful or not, close btf module FDs used in extern ksyms and attach_btf_obj_fd */ cleanup_relos(gen, insns_off); - if (gen->attach_kind) + if (gen->attach_kind) { emit_sys_close_blob(gen, attr_field(prog_load_attr, attach_btf_obj_fd)); + gen->attach_kind = 0; + } emit_check_err(gen); /* remember prog_fd in the stack, if successful */ emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, @@ -1041,6 +1068,33 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue, emit_check_err(gen); } +void bpf_gen__populate_outer_map(struct bpf_gen *gen, int outer_map_idx, int slot, + int inner_map_idx) +{ + int attr_size = offsetofend(union bpf_attr, flags); + int map_update_attr, key; + union bpf_attr attr; + + memset(&attr, 0, attr_size); + pr_debug("gen: populate_outer_map: outer %d key %d inner %d\n", + outer_map_idx, slot, inner_map_idx); + + key = add_data(gen, &slot, sizeof(slot)); + + map_update_attr = add_data(gen, &attr, attr_size); + move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4, + blob_fd_array_off(gen, outer_map_idx)); + emit_rel_store(gen, attr_field(map_update_attr, key), key); + emit_rel_store(gen, attr_field(map_update_attr, value), + blob_fd_array_off(gen, inner_map_idx)); + + /* emit MAP_UPDATE_ELEM command */ + emit_sys_bpf(gen, BPF_MAP_UPDATE_ELEM, map_update_attr, attr_size); + debug_ret(gen, "populate_outer_map outer %d key %d inner %d", + outer_map_idx, slot, inner_map_idx); + emit_check_err(gen); +} + void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx) { int attr_size = offsetofend(union bpf_attr, map_fd); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index f6faa33c80fa..902f1ad5b7e6 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -168,6 +168,25 @@ int libbpf_set_strict_mode(enum libbpf_strict_mode mode) return 0; } +__u32 libbpf_major_version(void) +{ + return LIBBPF_MAJOR_VERSION; +} + +__u32 libbpf_minor_version(void) +{ + return LIBBPF_MINOR_VERSION; +} + +const char *libbpf_version_string(void) +{ +#define __S(X) #X +#define _S(X) __S(X) + return "v" _S(LIBBPF_MAJOR_VERSION) "." _S(LIBBPF_MINOR_VERSION); +#undef _S +#undef __S +} + enum kern_feature_id { /* v4.14: kernel support for program & map names. */ FEAT_PROG_NAME, @@ -211,13 +230,19 @@ enum reloc_type { RELO_EXTERN_VAR, RELO_EXTERN_FUNC, RELO_SUBPROG_ADDR, + RELO_CORE, }; struct reloc_desc { enum reloc_type type; int insn_idx; - int map_idx; - int sym_off; + union { + const struct bpf_core_relo *core_relo; /* used when type == RELO_CORE */ + struct { + int map_idx; + int sym_off; + }; + }; }; struct bpf_sec_def; @@ -306,7 +331,11 @@ struct bpf_program { struct reloc_desc *reloc_desc; int nr_reloc; - int log_level; + + /* BPF verifier log settings */ + char *log_buf; + size_t log_size; + __u32 log_level; struct { int nr; @@ -402,6 +431,7 @@ struct bpf_map { char *pin_path; bool pinned; bool reused; + bool skipped; __u64 map_extra; }; @@ -548,6 +578,11 @@ struct bpf_object { size_t btf_module_cnt; size_t btf_module_cap; + /* optional log settings passed to BPF_BTF_LOAD and BPF_PROG_LOAD commands */ + char *log_buf; + size_t log_size; + __u32 log_level; + void *priv; bpf_object_clear_priv_t clear_priv; @@ -683,6 +718,9 @@ bpf_object__init_prog(struct bpf_object *obj, struct bpf_program *prog, prog->instances.fds = NULL; prog->instances.nr = -1; + /* inherit object's log_level */ + prog->log_level = obj->log_level; + prog->sec_name = strdup(sec_name); if (!prog->sec_name) goto errout; @@ -2258,6 +2296,9 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_def->parts |= MAP_DEF_VALUE_SIZE | MAP_DEF_VALUE_TYPE; } else if (strcmp(name, "values") == 0) { + bool is_map_in_map = bpf_map_type__is_map_in_map(map_def->map_type); + bool is_prog_array = map_def->map_type == BPF_MAP_TYPE_PROG_ARRAY; + const char *desc = is_map_in_map ? "map-in-map inner" : "prog-array value"; char inner_map_name[128]; int err; @@ -2271,8 +2312,8 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_name, name); return -EINVAL; } - if (!bpf_map_type__is_map_in_map(map_def->map_type)) { - pr_warn("map '%s': should be map-in-map.\n", + if (!is_map_in_map && !is_prog_array) { + pr_warn("map '%s': should be map-in-map or prog-array.\n", map_name); return -ENOTSUP; } @@ -2284,22 +2325,30 @@ int parse_btf_map_def(const char *map_name, struct btf *btf, map_def->value_size = 4; t = btf__type_by_id(btf, m->type); if (!t) { - pr_warn("map '%s': map-in-map inner type [%d] not found.\n", - map_name, m->type); + pr_warn("map '%s': %s type [%d] not found.\n", + map_name, desc, m->type); return -EINVAL; } if (!btf_is_array(t) || btf_array(t)->nelems) { - pr_warn("map '%s': map-in-map inner spec is not a zero-sized array.\n", - map_name); + pr_warn("map '%s': %s spec is not a zero-sized array.\n", + map_name, desc); return -EINVAL; } t = skip_mods_and_typedefs(btf, btf_array(t)->type, NULL); if (!btf_is_ptr(t)) { - pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", - map_name, btf_kind_str(t)); + pr_warn("map '%s': %s def is of unexpected kind %s.\n", + map_name, desc, btf_kind_str(t)); return -EINVAL; } t = skip_mods_and_typedefs(btf, t->type, NULL); + if (is_prog_array) { + if (!btf_is_func_proto(t)) { + pr_warn("map '%s': prog-array value def is of unexpected kind %s.\n", + map_name, btf_kind_str(t)); + return -EINVAL; + } + continue; + } if (!btf_is_struct(t)) { pr_warn("map '%s': map-in-map inner def is of unexpected kind %s.\n", map_name, btf_kind_str(t)); @@ -2981,7 +3030,9 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) */ btf__set_fd(kern_btf, 0); } else { - err = btf__load_into_kernel(kern_btf); + /* currently BPF_BTF_LOAD only supports log_level 1 */ + err = btf_load_into_kernel(kern_btf, obj->log_buf, obj->log_size, + obj->log_level ? 1 : 0); } if (sanitize) { if (!err) { @@ -3350,7 +3401,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj) /* sort BPF programs by section name and in-section instruction offset * for faster search */ - qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs); + if (obj->nr_programs) + qsort(obj->programs, obj->nr_programs, sizeof(*obj->programs), cmp_progs); return bpf_object__init_btf(obj, btf_data, btf_ext_data); } @@ -4342,7 +4394,6 @@ static int probe_kern_prog_name(void) static int probe_kern_global_data(void) { - struct bpf_create_map_attr map_attr; char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_LD_MAP_VALUE(BPF_REG_1, 0, 16), @@ -4352,13 +4403,7 @@ static int probe_kern_global_data(void) }; int ret, map, insn_cnt = ARRAY_SIZE(insns); - memset(&map_attr, 0, sizeof(map_attr)); - map_attr.map_type = BPF_MAP_TYPE_ARRAY; - map_attr.key_size = sizeof(int); - map_attr.value_size = 32; - map_attr.max_entries = 1; - - map = bpf_create_map_xattr(&map_attr); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4488,15 +4533,11 @@ static int probe_kern_btf_type_tag(void) static int probe_kern_array_mmap(void) { - struct bpf_create_map_attr attr = { - .map_type = BPF_MAP_TYPE_ARRAY, - .map_flags = BPF_F_MMAPABLE, - .key_size = sizeof(int), - .value_size = sizeof(int), - .max_entries = 1, - }; + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_MMAPABLE); + int fd; - return probe_fd(bpf_create_map_xattr(&attr)); + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(int), 1, &opts); + return probe_fd(fd); } static int probe_kern_exp_attach_type(void) @@ -4535,7 +4576,6 @@ static int probe_kern_probe_read_kernel(void) static int probe_prog_bind_map(void) { - struct bpf_create_map_attr map_attr; char *cp, errmsg[STRERR_BUFSIZE]; struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), @@ -4543,13 +4583,7 @@ static int probe_prog_bind_map(void) }; int ret, map, prog, insn_cnt = ARRAY_SIZE(insns); - memset(&map_attr, 0, sizeof(map_attr)); - map_attr.map_type = BPF_MAP_TYPE_ARRAY; - map_attr.key_size = sizeof(int); - map_attr.value_size = 32; - map_attr.max_entries = 1; - - map = bpf_create_map_xattr(&map_attr); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), 32, 1, NULL); if (map < 0) { ret = -errno; cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); @@ -4820,19 +4854,16 @@ static void bpf_map__destroy(struct bpf_map *map); static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner) { - struct bpf_create_map_params create_attr; + LIBBPF_OPTS(bpf_map_create_opts, create_attr); struct bpf_map_def *def = &map->def; + const char *map_name = NULL; + __u32 max_entries; int err = 0; - memset(&create_attr, 0, sizeof(create_attr)); - if (kernel_supports(obj, FEAT_PROG_NAME)) - create_attr.name = map->name; + map_name = map->name; create_attr.map_ifindex = map->map_ifindex; - create_attr.map_type = def->type; create_attr.map_flags = def->map_flags; - create_attr.key_size = def->key_size; - create_attr.value_size = def->value_size; create_attr.numa_node = map->numa_node; create_attr.map_extra = map->map_extra; @@ -4846,18 +4877,14 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b return nr_cpus; } pr_debug("map '%s': setting size to %d\n", map->name, nr_cpus); - create_attr.max_entries = nr_cpus; + max_entries = nr_cpus; } else { - create_attr.max_entries = def->max_entries; + max_entries = def->max_entries; } if (bpf_map__is_struct_ops(map)) - create_attr.btf_vmlinux_value_type_id = - map->btf_vmlinux_value_type_id; + create_attr.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; - create_attr.btf_fd = 0; - create_attr.btf_key_type_id = 0; - create_attr.btf_value_type_id = 0; if (obj->btf && btf__fd(obj->btf) >= 0 && !bpf_map_find_btf_info(obj, map)) { create_attr.btf_fd = btf__fd(obj->btf); create_attr.btf_key_type_id = map->btf_key_type_id; @@ -4903,13 +4930,17 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b } if (obj->gen_loader) { - bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps); + bpf_gen__map_create(obj->gen_loader, def->type, map_name, + def->key_size, def->value_size, max_entries, + &create_attr, is_inner ? -1 : map - obj->maps); /* Pretend to have valid FD to pass various fd >= 0 checks. * This fd == 0 will not be used with any syscall and will be reset to -1 eventually. */ map->fd = 0; } else { - map->fd = libbpf__bpf_create_map_xattr(&create_attr); + map->fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + max_entries, &create_attr); } if (map->fd < 0 && (create_attr.btf_key_type_id || create_attr.btf_value_type_id)) { @@ -4924,7 +4955,9 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b create_attr.btf_value_type_id = 0; map->btf_key_type_id = 0; map->btf_value_type_id = 0; - map->fd = libbpf__bpf_create_map_xattr(&create_attr); + map->fd = bpf_map_create(def->type, map_name, + def->key_size, def->value_size, + max_entries, &create_attr); } err = map->fd < 0 ? -errno : 0; @@ -4939,7 +4972,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b return err; } -static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) +static int init_map_in_map_slots(struct bpf_object *obj, struct bpf_map *map) { const struct bpf_map *targ_map; unsigned int i; @@ -4951,18 +4984,18 @@ static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) targ_map = map->init_slots[i]; fd = bpf_map__fd(targ_map); + if (obj->gen_loader) { - pr_warn("// TODO map_update_elem: idx %td key %d value==map_idx %td\n", - map - obj->maps, i, targ_map - obj->maps); - return -ENOTSUP; + bpf_gen__populate_outer_map(obj->gen_loader, + map - obj->maps, i, + targ_map - obj->maps); } else { err = bpf_map_update_elem(map->fd, &i, &fd, 0); } if (err) { err = -errno; pr_warn("map '%s': failed to initialize slot [%d] to map '%s' fd=%d: %d\n", - map->name, i, targ_map->name, - fd, err); + map->name, i, targ_map->name, fd, err); return err; } pr_debug("map '%s': slot [%d] set to map '%s' fd=%d\n", @@ -4975,6 +5008,59 @@ static int init_map_slots(struct bpf_object *obj, struct bpf_map *map) return 0; } +static int init_prog_array_slots(struct bpf_object *obj, struct bpf_map *map) +{ + const struct bpf_program *targ_prog; + unsigned int i; + int fd, err; + + if (obj->gen_loader) + return -ENOTSUP; + + for (i = 0; i < map->init_slots_sz; i++) { + if (!map->init_slots[i]) + continue; + + targ_prog = map->init_slots[i]; + fd = bpf_program__fd(targ_prog); + + err = bpf_map_update_elem(map->fd, &i, &fd, 0); + if (err) { + err = -errno; + pr_warn("map '%s': failed to initialize slot [%d] to prog '%s' fd=%d: %d\n", + map->name, i, targ_prog->name, fd, err); + return err; + } + pr_debug("map '%s': slot [%d] set to prog '%s' fd=%d\n", + map->name, i, targ_prog->name, fd); + } + + zfree(&map->init_slots); + map->init_slots_sz = 0; + + return 0; +} + +static int bpf_object_init_prog_arrays(struct bpf_object *obj) +{ + struct bpf_map *map; + int i, err; + + for (i = 0; i < obj->nr_maps; i++) { + map = &obj->maps[i]; + + if (!map->init_slots_sz || map->def.type != BPF_MAP_TYPE_PROG_ARRAY) + continue; + + err = init_prog_array_slots(obj, map); + if (err < 0) { + zclose(map->fd); + return err; + } + } + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { @@ -4987,6 +5073,26 @@ bpf_object__create_maps(struct bpf_object *obj) for (i = 0; i < obj->nr_maps; i++) { map = &obj->maps[i]; + /* To support old kernels, we skip creating global data maps + * (.rodata, .data, .kconfig, etc); later on, during program + * loading, if we detect that at least one of the to-be-loaded + * programs is referencing any global data map, we'll error + * out with program name and relocation index logged. + * This approach allows to accommodate Clang emitting + * unnecessary .rodata.str1.1 sections for string literals, + * but also it allows to have CO-RE applications that use + * global variables in some of BPF programs, but not others. + * If those global variable-using programs are not loaded at + * runtime due to bpf_program__set_autoload(prog, false), + * bpf_object loading will succeed just fine even on old + * kernels. + */ + if (bpf_map__is_internal(map) && + !kernel_supports(obj, FEAT_GLOBAL_DATA)) { + map->skipped = true; + continue; + } + retried = false; retry: if (map->pin_path) { @@ -5023,8 +5129,8 @@ retry: } } - if (map->init_slots_sz) { - err = init_map_slots(obj, map); + if (map->init_slots_sz && map->def.type != BPF_MAP_TYPE_PROG_ARRAY) { + err = init_map_in_map_slots(obj, map); if (err < 0) { zclose(map->fd); goto err_out; @@ -5096,15 +5202,18 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand, struct bpf_core_cand_list *cands) { struct bpf_core_cand *new_cands, *cand; - const struct btf_type *t; - const char *targ_name; + const struct btf_type *t, *local_t; + const char *targ_name, *local_name; size_t targ_essent_len; int n, i; + local_t = btf__type_by_id(local_cand->btf, local_cand->id); + local_name = btf__str_by_offset(local_cand->btf, local_t->name_off); + n = btf__type_cnt(targ_btf); for (i = targ_start_id; i < n; i++) { t = btf__type_by_id(targ_btf, i); - if (btf_kind(t) != btf_kind(local_cand->t)) + if (btf_kind(t) != btf_kind(local_t)) continue; targ_name = btf__name_by_offset(targ_btf, t->name_off); @@ -5115,12 +5224,12 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand, if (targ_essent_len != local_essent_len) continue; - if (strncmp(local_cand->name, targ_name, local_essent_len) != 0) + if (strncmp(local_name, targ_name, local_essent_len) != 0) continue; pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s in [%s]\n", - local_cand->id, btf_kind_str(local_cand->t), - local_cand->name, i, btf_kind_str(t), targ_name, + local_cand->id, btf_kind_str(local_t), + local_name, i, btf_kind_str(t), targ_name, targ_btf_name); new_cands = libbpf_reallocarray(cands->cands, cands->len + 1, sizeof(*cands->cands)); @@ -5129,8 +5238,6 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand, cand = &new_cands[cands->len]; cand->btf = targ_btf; - cand->t = t; - cand->name = targ_name; cand->id = i; cands->cands = new_cands; @@ -5237,18 +5344,21 @@ bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 l struct bpf_core_cand local_cand = {}; struct bpf_core_cand_list *cands; const struct btf *main_btf; + const struct btf_type *local_t; + const char *local_name; size_t local_essent_len; int err, i; local_cand.btf = local_btf; - local_cand.t = btf__type_by_id(local_btf, local_type_id); - if (!local_cand.t) + local_cand.id = local_type_id; + local_t = btf__type_by_id(local_btf, local_type_id); + if (!local_t) return ERR_PTR(-EINVAL); - local_cand.name = btf__name_by_offset(local_btf, local_cand.t->name_off); - if (str_is_empty(local_cand.name)) + local_name = btf__name_by_offset(local_btf, local_t->name_off); + if (str_is_empty(local_name)) return ERR_PTR(-EINVAL); - local_essent_len = bpf_core_essential_name_len(local_cand.name); + local_essent_len = bpf_core_essential_name_len(local_name); cands = calloc(1, sizeof(*cands)); if (!cands) @@ -5398,12 +5508,31 @@ static void *u32_as_hash_key(__u32 x) return (void *)(uintptr_t)x; } +static int record_relo_core(struct bpf_program *prog, + const struct bpf_core_relo *core_relo, int insn_idx) +{ + struct reloc_desc *relos, *relo; + + relos = libbpf_reallocarray(prog->reloc_desc, + prog->nr_reloc + 1, sizeof(*relos)); + if (!relos) + return -ENOMEM; + relo = &relos[prog->nr_reloc]; + relo->type = RELO_CORE; + relo->insn_idx = insn_idx; + relo->core_relo = core_relo; + prog->reloc_desc = relos; + prog->nr_reloc++; + return 0; +} + static int bpf_core_apply_relo(struct bpf_program *prog, const struct bpf_core_relo *relo, int relo_idx, const struct btf *local_btf, struct hashmap *cand_cache) { + struct bpf_core_spec specs_scratch[3] = {}; const void *type_key = u32_as_hash_key(relo->type_id); struct bpf_core_cand_list *cands = NULL; const char *prog_name = prog->name; @@ -5434,13 +5563,15 @@ static int bpf_core_apply_relo(struct bpf_program *prog, return -EINVAL; if (prog->obj->gen_loader) { - pr_warn("// TODO core_relo: prog %td insn[%d] %s kind %d\n", + const char *spec_str = btf__name_by_offset(local_btf, relo->access_str_off); + + pr_debug("record_relo_core: prog %td insn[%d] %s %s %s final insn_idx %d\n", prog - prog->obj->programs, relo->insn_off / 8, - local_name, relo->kind); - return -ENOTSUP; + btf_kind_str(local_type), local_name, spec_str, insn_idx); + return record_relo_core(prog, relo, insn_idx); } - if (relo->kind != BPF_TYPE_ID_LOCAL && + if (relo->kind != BPF_CORE_TYPE_ID_LOCAL && !hashmap__find(cand_cache, type_key, (void **)&cands)) { cands = bpf_core_find_cands(prog->obj, local_btf, local_id); if (IS_ERR(cands)) { @@ -5456,7 +5587,8 @@ static int bpf_core_apply_relo(struct bpf_program *prog, } } - return bpf_core_apply_relo_insn(prog_name, insn, insn_idx, relo, relo_idx, local_btf, cands); + return bpf_core_apply_relo_insn(prog_name, insn, insn_idx, relo, + relo_idx, local_btf, cands, specs_scratch); } static int @@ -5586,6 +5718,13 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) insn[0].src_reg = BPF_PSEUDO_MAP_IDX_VALUE; insn[0].imm = relo->map_idx; } else { + const struct bpf_map *map = &obj->maps[relo->map_idx]; + + if (map->skipped) { + pr_warn("prog '%s': relo #%d: kernel doesn't support global data\n", + prog->name, i); + return -ENOTSUP; + } insn[0].src_reg = BPF_PSEUDO_MAP_VALUE; insn[0].imm = obj->maps[relo->map_idx].fd; } @@ -5634,6 +5773,9 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog) case RELO_CALL: /* handled already */ break; + case RELO_CORE: + /* will be handled by bpf_program_record_relos() */ + break; default: pr_warn("prog '%s': relo #%d: bad relo type %d\n", prog->name, i, relo->type); @@ -5797,6 +5939,8 @@ static int cmp_relo_by_insn_idx(const void *key, const void *elem) static struct reloc_desc *find_prog_insn_relo(const struct bpf_program *prog, size_t insn_idx) { + if (!prog->nr_reloc) + return NULL; return bsearch(&insn_idx, prog->reloc_desc, prog->nr_reloc, sizeof(*prog->reloc_desc), cmp_relo_by_insn_idx); } @@ -5812,8 +5956,9 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos)); if (!relos) return -ENOMEM; - memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, - sizeof(*relos) * subprog->nr_reloc); + if (subprog->nr_reloc) + memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc, + sizeof(*relos) * subprog->nr_reloc); for (i = main_prog->nr_reloc; i < new_cnt; i++) relos[i].insn_idx += subprog->sub_insn_off; @@ -6071,6 +6216,35 @@ bpf_object__free_relocs(struct bpf_object *obj) } } +static int cmp_relocs(const void *_a, const void *_b) +{ + const struct reloc_desc *a = _a; + const struct reloc_desc *b = _b; + + if (a->insn_idx != b->insn_idx) + return a->insn_idx < b->insn_idx ? -1 : 1; + + /* no two relocations should have the same insn_idx, but ... */ + if (a->type != b->type) + return a->type < b->type ? -1 : 1; + + return 0; +} + +static void bpf_object__sort_relos(struct bpf_object *obj) +{ + int i; + + for (i = 0; i < obj->nr_programs; i++) { + struct bpf_program *p = &obj->programs[i]; + + if (!p->nr_reloc) + continue; + + qsort(p->reloc_desc, p->nr_reloc, sizeof(*p->reloc_desc), cmp_relocs); + } +} + static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) { @@ -6085,6 +6259,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) err); return err; } + if (obj->gen_loader) + bpf_object__sort_relos(obj); } /* Before relocating calls pre-process relocations and mark @@ -6120,6 +6296,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) */ if (prog_is_subprog(obj, prog)) continue; + if (!prog->load) + continue; err = bpf_object__relocate_calls(obj, prog); if (err) { @@ -6133,6 +6311,8 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path) prog = &obj->programs[i]; if (prog_is_subprog(obj, prog)) continue; + if (!prog->load) + continue; err = bpf_object__relocate_data(obj, prog); if (err) { pr_warn("prog '%s': failed to relocate data references: %d\n", @@ -6155,9 +6335,11 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, int i, j, nrels, new_sz; const struct btf_var_secinfo *vi = NULL; const struct btf_type *sec, *var, *def; - struct bpf_map *map = NULL, *targ_map; + struct bpf_map *map = NULL, *targ_map = NULL; + struct bpf_program *targ_prog = NULL; + bool is_prog_array, is_map_in_map; const struct btf_member *member; - const char *name, *mname; + const char *name, *mname, *type; unsigned int moff; Elf64_Sym *sym; Elf64_Rel *rel; @@ -6184,11 +6366,6 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, return -LIBBPF_ERRNO__FORMAT; } name = elf_sym_str(obj, sym->st_name) ?: "<?>"; - if (sym->st_shndx != obj->efile.btf_maps_shndx) { - pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", - i, name); - return -LIBBPF_ERRNO__RELOC; - } pr_debug(".maps relo #%d: for %zd value %zd rel->r_offset %zu name %d ('%s')\n", i, (ssize_t)(rel->r_info >> 32), (size_t)sym->st_value, @@ -6210,19 +6387,45 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, return -EINVAL; } - if (!bpf_map_type__is_map_in_map(map->def.type)) - return -EINVAL; - if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS && - map->def.key_size != sizeof(int)) { - pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n", - i, map->name, sizeof(int)); + is_map_in_map = bpf_map_type__is_map_in_map(map->def.type); + is_prog_array = map->def.type == BPF_MAP_TYPE_PROG_ARRAY; + type = is_map_in_map ? "map" : "prog"; + if (is_map_in_map) { + if (sym->st_shndx != obj->efile.btf_maps_shndx) { + pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + if (map->def.type == BPF_MAP_TYPE_HASH_OF_MAPS && + map->def.key_size != sizeof(int)) { + pr_warn(".maps relo #%d: hash-of-maps '%s' should have key size %zu.\n", + i, map->name, sizeof(int)); + return -EINVAL; + } + targ_map = bpf_object__find_map_by_name(obj, name); + if (!targ_map) { + pr_warn(".maps relo #%d: '%s' isn't a valid map reference\n", + i, name); + return -ESRCH; + } + } else if (is_prog_array) { + targ_prog = bpf_object__find_program_by_name(obj, name); + if (!targ_prog) { + pr_warn(".maps relo #%d: '%s' isn't a valid program reference\n", + i, name); + return -ESRCH; + } + if (targ_prog->sec_idx != sym->st_shndx || + targ_prog->sec_insn_off * 8 != sym->st_value || + prog_is_subprog(obj, targ_prog)) { + pr_warn(".maps relo #%d: '%s' isn't an entry-point program\n", + i, name); + return -LIBBPF_ERRNO__RELOC; + } + } else { return -EINVAL; } - targ_map = bpf_object__find_map_by_name(obj, name); - if (!targ_map) - return -ESRCH; - var = btf__type_by_id(obj->btf, vi->type); def = skip_mods_and_typedefs(obj->btf, var->type, NULL); if (btf_vlen(def) == 0) @@ -6253,30 +6456,15 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, (new_sz - map->init_slots_sz) * host_ptr_sz); map->init_slots_sz = new_sz; } - map->init_slots[moff] = targ_map; + map->init_slots[moff] = is_map_in_map ? (void *)targ_map : (void *)targ_prog; - pr_debug(".maps relo #%d: map '%s' slot [%d] points to map '%s'\n", - i, map->name, moff, name); + pr_debug(".maps relo #%d: map '%s' slot [%d] points to %s '%s'\n", + i, map->name, moff, type, name); } return 0; } -static int cmp_relocs(const void *_a, const void *_b) -{ - const struct reloc_desc *a = _a; - const struct reloc_desc *b = _b; - - if (a->insn_idx != b->insn_idx) - return a->insn_idx < b->insn_idx ? -1 : 1; - - /* no two relocations should have the same insn_idx, but ... */ - if (a->type != b->type) - return a->type < b->type ? -1 : 1; - - return 0; -} - static int bpf_object__collect_relos(struct bpf_object *obj) { int i, err; @@ -6309,14 +6497,7 @@ static int bpf_object__collect_relos(struct bpf_object *obj) return err; } - for (i = 0; i < obj->nr_programs; i++) { - struct bpf_program *p = &obj->programs[i]; - - if (!p->nr_reloc) - continue; - - qsort(p->reloc_desc, p->nr_reloc, sizeof(*p->reloc_desc), cmp_relocs); - } + bpf_object__sort_relos(obj); return 0; } @@ -6419,8 +6600,10 @@ static int bpf_object_load_prog_instance(struct bpf_object *obj, struct bpf_prog const char *prog_name = NULL; char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; - char *log_buf = NULL; + char *log_buf = NULL, *tmp; int btf_fd, ret, err; + bool own_log_buf = true; + __u32 log_level = prog->log_level; if (prog->type == BPF_PROG_TYPE_UNSPEC) { /* @@ -6438,7 +6621,6 @@ static int bpf_object_load_prog_instance(struct bpf_object *obj, struct bpf_prog load_attr.expected_attach_type = prog->expected_attach_type; if (kernel_supports(obj, FEAT_PROG_NAME)) prog_name = prog->name; - load_attr.attach_btf_id = prog->attach_btf_id; load_attr.attach_prog_fd = prog->attach_prog_fd; load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; load_attr.attach_btf_id = prog->attach_btf_id; @@ -6456,7 +6638,7 @@ static int bpf_object_load_prog_instance(struct bpf_object *obj, struct bpf_prog load_attr.line_info_rec_size = prog->line_info_rec_size; load_attr.line_info_cnt = prog->line_info_cnt; } - load_attr.log_level = prog->log_level; + load_attr.log_level = log_level; load_attr.prog_flags = prog->prog_flags; load_attr.fd_array = obj->fd_array; @@ -6477,22 +6659,45 @@ static int bpf_object_load_prog_instance(struct bpf_object *obj, struct bpf_prog *prog_fd = -1; return 0; } -retry_load: - if (log_buf_size) { - log_buf = malloc(log_buf_size); - if (!log_buf) - return -ENOMEM; - *log_buf = 0; +retry_load: + /* if log_level is zero, we don't request logs initiallly even if + * custom log_buf is specified; if the program load fails, then we'll + * bump log_level to 1 and use either custom log_buf or we'll allocate + * our own and retry the load to get details on what failed + */ + if (log_level) { + if (prog->log_buf) { + log_buf = prog->log_buf; + log_buf_size = prog->log_size; + own_log_buf = false; + } else if (obj->log_buf) { + log_buf = obj->log_buf; + log_buf_size = obj->log_size; + own_log_buf = false; + } else { + log_buf_size = max((size_t)BPF_LOG_BUF_SIZE, log_buf_size * 2); + tmp = realloc(log_buf, log_buf_size); + if (!tmp) { + ret = -ENOMEM; + goto out; + } + log_buf = tmp; + log_buf[0] = '\0'; + own_log_buf = true; + } } load_attr.log_buf = log_buf; load_attr.log_size = log_buf_size; - ret = bpf_prog_load(prog->type, prog_name, license, insns, insns_cnt, &load_attr); + load_attr.log_level = log_level; + ret = bpf_prog_load(prog->type, prog_name, license, insns, insns_cnt, &load_attr); if (ret >= 0) { - if (log_buf && load_attr.log_level) - pr_debug("verifier log:\n%s", log_buf); + if (log_level && own_log_buf) { + pr_debug("prog '%s': -- BEGIN PROG LOAD LOG --\n%s-- END PROG LOAD LOG --\n", + prog->name, log_buf); + } if (obj->has_rodata && kernel_supports(obj, FEAT_PROG_BIND_MAP)) { struct bpf_map *map; @@ -6505,8 +6710,8 @@ retry_load: if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) { cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("prog '%s': failed to bind .rodata map: %s\n", - prog->name, cp); + pr_warn("prog '%s': failed to bind map '%s': %s\n", + prog->name, map->real_name, cp); /* Don't fail hard if can't bind rodata. */ } } @@ -6517,49 +6722,41 @@ retry_load: goto out; } - if (!log_buf || errno == ENOSPC) { - log_buf_size = max((size_t)BPF_LOG_BUF_SIZE, - log_buf_size << 1); - - free(log_buf); + if (log_level == 0) { + log_level = 1; goto retry_load; } - ret = errno ? -errno : -LIBBPF_ERRNO__LOAD; + /* On ENOSPC, increase log buffer size and retry, unless custom + * log_buf is specified. + * Be careful to not overflow u32, though. Kernel's log buf size limit + * isn't part of UAPI so it can always be bumped to full 4GB. So don't + * multiply by 2 unless we are sure we'll fit within 32 bits. + * Currently, we'll get -EINVAL when we reach (UINT_MAX >> 2). + */ + if (own_log_buf && errno == ENOSPC && log_buf_size <= UINT_MAX / 2) + goto retry_load; + + ret = -errno; cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); - pr_warn("load bpf program failed: %s\n", cp); + pr_warn("prog '%s': BPF program load failed: %s\n", prog->name, cp); pr_perm_msg(ret); - if (log_buf && log_buf[0] != '\0') { - ret = -LIBBPF_ERRNO__VERIFY; - pr_warn("-- BEGIN DUMP LOG ---\n"); - pr_warn("\n%s\n", log_buf); - pr_warn("-- END LOG --\n"); - } else if (insns_cnt >= BPF_MAXINSNS) { - pr_warn("Program too large (%d insns), at most %d insns\n", - insns_cnt, BPF_MAXINSNS); - ret = -LIBBPF_ERRNO__PROG2BIG; - } else if (prog->type != BPF_PROG_TYPE_KPROBE) { - /* Wrong program type? */ - int fd; - - load_attr.expected_attach_type = 0; - load_attr.log_buf = NULL; - load_attr.log_size = 0; - fd = bpf_prog_load(BPF_PROG_TYPE_KPROBE, prog_name, license, - insns, insns_cnt, &load_attr); - if (fd >= 0) { - close(fd); - ret = -LIBBPF_ERRNO__PROGTYPE; - goto out; - } + if (own_log_buf && log_buf && log_buf[0] != '\0') { + pr_warn("prog '%s': -- BEGIN PROG LOAD LOG --\n%s-- END PROG LOAD LOG --\n", + prog->name, log_buf); + } + if (insns_cnt >= BPF_MAXINSNS) { + pr_warn("prog '%s': program too large (%d insns), at most %d insns\n", + prog->name, insns_cnt, BPF_MAXINSNS); } out: - free(log_buf); + if (own_log_buf) + free(log_buf); return ret; } -static int bpf_program__record_externs(struct bpf_program *prog) +static int bpf_program_record_relos(struct bpf_program *prog) { struct bpf_object *obj = prog->obj; int i; @@ -6581,6 +6778,17 @@ static int bpf_program__record_externs(struct bpf_program *prog) ext->is_weak, false, BTF_KIND_FUNC, relo->insn_idx); break; + case RELO_CORE: { + struct bpf_core_relo cr = { + .insn_off = relo->insn_idx * 8, + .type_id = relo->core_relo->type_id, + .access_str_off = relo->core_relo->access_str_off, + .kind = relo->core_relo->kind, + }; + + bpf_gen__record_relo_core(obj->gen_loader, &cr); + break; + } default: continue; } @@ -6620,7 +6828,7 @@ static int bpf_object_load_prog(struct bpf_object *obj, struct bpf_program *prog prog->name, prog->instances.nr); } if (obj->gen_loader) - bpf_program__record_externs(prog); + bpf_program_record_relos(prog); err = bpf_object_load_prog_instance(obj, prog, prog->insns, prog->insns_cnt, license, kern_ver, &fd); @@ -6749,14 +6957,16 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object return 0; } -static struct bpf_object * -__bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, - const struct bpf_object_open_opts *opts) +static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz, + const struct bpf_object_open_opts *opts) { const char *obj_name, *kconfig, *btf_tmp_path; struct bpf_object *obj; char tmp_name[64]; int err; + char *log_buf; + size_t log_size; + __u32 log_level; if (elf_version(EV_CURRENT) == EV_NONE) { pr_warn("failed to init libelf for %s\n", @@ -6779,10 +6989,22 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, pr_debug("loading object '%s' from buffer\n", obj_name); } + log_buf = OPTS_GET(opts, kernel_log_buf, NULL); + log_size = OPTS_GET(opts, kernel_log_size, 0); + log_level = OPTS_GET(opts, kernel_log_level, 0); + if (log_size > UINT_MAX) + return ERR_PTR(-EINVAL); + if (log_size && !log_buf) + return ERR_PTR(-EINVAL); + obj = bpf_object__new(path, obj_buf, obj_buf_sz, obj_name); if (IS_ERR(obj)) return obj; + obj->log_buf = log_buf; + obj->log_size = log_size; + obj->log_level = log_level; + btf_tmp_path = OPTS_GET(opts, btf_custom_path, NULL); if (btf_tmp_path) { if (strlen(btf_tmp_path) >= PATH_MAX) { @@ -6836,7 +7058,7 @@ __bpf_object__open_xattr(struct bpf_object_open_attr *attr, int flags) return NULL; pr_debug("loading %s\n", attr->file); - return __bpf_object__open(attr->file, NULL, 0, &opts); + return bpf_object_open(attr->file, NULL, 0, &opts); } struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) @@ -6862,7 +7084,7 @@ bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts) pr_debug("loading %s\n", path); - return libbpf_ptr(__bpf_object__open(path, NULL, 0, opts)); + return libbpf_ptr(bpf_object_open(path, NULL, 0, opts)); } struct bpf_object * @@ -6872,7 +7094,7 @@ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, if (!obj_buf || obj_buf_sz == 0) return libbpf_err_ptr(-EINVAL); - return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, opts)); + return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts)); } struct bpf_object * @@ -6889,7 +7111,7 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz, if (!obj_buf || obj_buf_sz == 0) return errno = EINVAL, NULL; - return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, &opts)); + return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, &opts)); } static int bpf_object_unload(struct bpf_object *obj) @@ -6920,10 +7142,6 @@ static int bpf_object__sanitize_maps(struct bpf_object *obj) bpf_object__for_each_map(m, obj) { if (!bpf_map__is_internal(m)) continue; - if (!kernel_supports(obj, FEAT_GLOBAL_DATA)) { - pr_warn("kernel doesn't support global data\n"); - return -ENOTSUP; - } if (!kernel_supports(obj, FEAT_ARRAY_MMAP)) m->def.map_flags ^= BPF_F_MMAPABLE; } @@ -7246,14 +7464,10 @@ static int bpf_object__resolve_externs(struct bpf_object *obj, return 0; } -int bpf_object__load_xattr(struct bpf_object_load_attr *attr) +static int bpf_object_load(struct bpf_object *obj, int extra_log_level, const char *target_btf_path) { - struct bpf_object *obj; int err, i; - if (!attr) - return libbpf_err(-EINVAL); - obj = attr->obj; if (!obj) return libbpf_err(-EINVAL); @@ -7263,7 +7477,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) } if (obj->gen_loader) - bpf_gen__init(obj->gen_loader, attr->log_level, obj->nr_programs, obj->nr_maps); + bpf_gen__init(obj->gen_loader, extra_log_level, obj->nr_programs, obj->nr_maps); err = bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); @@ -7272,8 +7486,9 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) err = err ? : bpf_object__sanitize_maps(obj); err = err ? : bpf_object__init_kern_struct_ops_maps(obj); err = err ? : bpf_object__create_maps(obj); - err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : attr->target_btf_path); - err = err ? : bpf_object__load_progs(obj, attr->log_level); + err = err ? : bpf_object__relocate(obj, obj->btf_custom_path ? : target_btf_path); + err = err ? : bpf_object__load_progs(obj, extra_log_level); + err = err ? : bpf_object_init_prog_arrays(obj); if (obj->gen_loader) { /* reset FDs */ @@ -7317,13 +7532,14 @@ out: return libbpf_err(err); } -int bpf_object__load(struct bpf_object *obj) +int bpf_object__load_xattr(struct bpf_object_load_attr *attr) { - struct bpf_object_load_attr attr = { - .obj = obj, - }; + return bpf_object_load(attr->obj, attr->log_level, attr->target_btf_path); +} - return bpf_object__load_xattr(&attr); +int bpf_object__load(struct bpf_object *obj) +{ + return bpf_object_load(obj, 0, NULL); } static int make_parent_dir(const char *path) @@ -7712,6 +7928,9 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) char *pin_path = NULL; char buf[PATH_MAX]; + if (map->skipped) + continue; + if (path) { int len; @@ -8296,12 +8515,46 @@ __u32 bpf_program__flags(const struct bpf_program *prog) return prog->prog_flags; } -int bpf_program__set_extra_flags(struct bpf_program *prog, __u32 extra_flags) +int bpf_program__set_flags(struct bpf_program *prog, __u32 flags) +{ + if (prog->obj->loaded) + return libbpf_err(-EBUSY); + + prog->prog_flags = flags; + return 0; +} + +__u32 bpf_program__log_level(const struct bpf_program *prog) +{ + return prog->log_level; +} + +int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level) { if (prog->obj->loaded) return libbpf_err(-EBUSY); - prog->prog_flags |= extra_flags; + prog->log_level = log_level; + return 0; +} + +const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size) +{ + *log_size = prog->log_size; + return prog->log_buf; +} + +int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size) +{ + if (log_size && !log_buf) + return -EINVAL; + if (prog->log_size > UINT_MAX) + return -EINVAL; + if (prog->obj->loaded) + return -EBUSY; + + prog->log_buf = log_buf; + prog->log_size = log_size; return 0; } diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 4ec69f224342..a8b894dae633 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -24,6 +24,10 @@ extern "C" { #endif +LIBBPF_API __u32 libbpf_major_version(void); +LIBBPF_API __u32 libbpf_minor_version(void); +LIBBPF_API const char *libbpf_version_string(void); + enum libbpf_errno { __LIBBPF_ERRNO__START = 4000, @@ -104,12 +108,73 @@ struct bpf_object_open_opts { * struct_ops, etc) will need actual kernel BTF at /sys/kernel/btf/vmlinux. */ const char *btf_custom_path; + /* Pointer to a buffer for storing kernel logs for applicable BPF + * commands. Valid kernel_log_size has to be specified as well and are + * passed-through to bpf() syscall. Keep in mind that kernel might + * fail operation with -ENOSPC error if provided buffer is too small + * to contain entire log output. + * See the comment below for kernel_log_level for interaction between + * log_buf and log_level settings. + * + * If specified, this log buffer will be passed for: + * - each BPF progral load (BPF_PROG_LOAD) attempt, unless overriden + * with bpf_program__set_log() on per-program level, to get + * BPF verifier log output. + * - during BPF object's BTF load into kernel (BPF_BTF_LOAD) to get + * BTF sanity checking log. + * + * Each BPF command (BPF_BTF_LOAD or BPF_PROG_LOAD) will overwrite + * previous contents, so if you need more fine-grained control, set + * per-program buffer with bpf_program__set_log_buf() to preserve each + * individual program's verification log. Keep using kernel_log_buf + * for BTF verification log, if necessary. + */ + char *kernel_log_buf; + size_t kernel_log_size; + /* + * Log level can be set independently from log buffer. Log_level=0 + * means that libbpf will attempt loading BTF or program without any + * logging requested, but will retry with either its own or custom log + * buffer, if provided, and log_level=1 on any error. + * And vice versa, setting log_level>0 will request BTF or prog + * loading with verbose log from the first attempt (and as such also + * for successfully loaded BTF or program), and the actual log buffer + * could be either libbpf's own auto-allocated log buffer, if + * kernel_log_buffer is NULL, or user-provided custom kernel_log_buf. + * If user didn't provide custom log buffer, libbpf will emit captured + * logs through its print callback. + */ + __u32 kernel_log_level; + + size_t :0; }; -#define bpf_object_open_opts__last_field btf_custom_path +#define bpf_object_open_opts__last_field kernel_log_level LIBBPF_API struct bpf_object *bpf_object__open(const char *path); + +/** + * @brief **bpf_object__open_file()** creates a bpf_object by opening + * the BPF ELF object file pointed to by the passed path and loading it + * into memory. + * @param path BPF object file path + * @param opts options for how to load the bpf object, this parameter is + * optional and can be set to NULL + * @return pointer to the new bpf_object; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_object * bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts); + +/** + * @brief **bpf_object__open_mem()** creates a bpf_object by reading + * the BPF objects raw bytes from a memory buffer containing a valid + * BPF ELF object file. + * @param obj_buf pointer to the buffer containing ELF file bytes + * @param obj_buf_sz number of bytes in the buffer + * @param opts options for how to load the bpf object + * @return pointer to the new bpf_object; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_object * bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts); @@ -149,6 +214,7 @@ struct bpf_object_load_attr { /* Load/unload object into/from kernel */ LIBBPF_API int bpf_object__load(struct bpf_object *obj); +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__load() instead") LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr); LIBBPF_DEPRECATED_SINCE(0, 6, "bpf_object__unload() is deprecated, use bpf_object__close() instead") LIBBPF_API int bpf_object__unload(struct bpf_object *obj); @@ -344,10 +410,41 @@ struct bpf_uprobe_opts { }; #define bpf_uprobe_opts__last_field retprobe +/** + * @brief **bpf_program__attach_uprobe()** attaches a BPF program + * to the userspace function which is found by binary path and + * offset. You can optionally specify a particular proccess to attach + * to. You can also optionally attach the program to the function + * exit instead of entry. + * + * @param prog BPF program to attach + * @param retprobe Attach to function exit + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains the function symbol + * @param func_offset Offset within the binary of the function symbol + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_link * bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, size_t func_offset); + +/** + * @brief **bpf_program__attach_uprobe_opts()** is just like + * bpf_program__attach_uprobe() except with a options struct + * for various configurations. + * + * @param prog BPF program to attach + * @param pid Process ID to attach the uprobe to, 0 for self (own process), + * -1 for all processes + * @param binary_path Path to binary that contains the function symbol + * @param func_offset Offset within the binary of the function symbol + * @param opts Options for altering program attachment + * @return Reference to the newly created BPF link; or NULL is returned on error, + * error code is stored in errno + */ LIBBPF_API struct bpf_link * bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, @@ -494,7 +591,16 @@ bpf_program__set_expected_attach_type(struct bpf_program *prog, enum bpf_attach_type type); LIBBPF_API __u32 bpf_program__flags(const struct bpf_program *prog); -LIBBPF_API int bpf_program__set_extra_flags(struct bpf_program *prog, __u32 extra_flags); +LIBBPF_API int bpf_program__set_flags(struct bpf_program *prog, __u32 flags); + +/* Per-program log level and log buffer getters/setters. + * See bpf_object_open_opts comments regarding log_level and log_buf + * interactions. + */ +LIBBPF_API __u32 bpf_program__log_level(const struct bpf_program *prog); +LIBBPF_API int bpf_program__set_log_level(struct bpf_program *prog, __u32 log_level); +LIBBPF_API const char *bpf_program__log_buf(const struct bpf_program *prog, size_t *log_size); +LIBBPF_API int bpf_program__set_log_buf(struct bpf_program *prog, char *log_buf, size_t log_size); LIBBPF_API int bpf_program__set_attach_target(struct bpf_program *prog, int attach_prog_fd, @@ -676,6 +782,7 @@ struct bpf_prog_load_attr { int prog_flags; }; +LIBBPF_DEPRECATED_SINCE(0, 8, "use bpf_object__open() and bpf_object__load() instead") LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, struct bpf_object **pobj, int *prog_fd); LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__open() and bpf_object__load() instead") @@ -1031,11 +1138,11 @@ struct bpf_object_skeleton { struct bpf_object **obj; int map_cnt; - int map_skel_sz; /* sizeof(struct bpf_skeleton_map) */ + int map_skel_sz; /* sizeof(struct bpf_map_skeleton) */ struct bpf_map_skeleton *maps; int prog_cnt; - int prog_skel_sz; /* sizeof(struct bpf_skeleton_prog) */ + int prog_skel_sz; /* sizeof(struct bpf_prog_skeleton) */ struct bpf_prog_skeleton *progs; }; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 6a59514a48cf..4d483af7dba6 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -391,6 +391,7 @@ LIBBPF_0.6.0 { global: bpf_map__map_extra; bpf_map__set_map_extra; + bpf_map_create; bpf_object__next_map; bpf_object__next_program; bpf_object__prev_map; @@ -400,7 +401,7 @@ LIBBPF_0.6.0 { bpf_program__flags; bpf_program__insn_cnt; bpf_program__insns; - bpf_program__set_extra_flags; + bpf_program__set_flags; btf__add_btf; btf__add_decl_tag; btf__add_type_tag; @@ -410,8 +411,20 @@ LIBBPF_0.6.0 { btf__type_cnt; btf_dump__new; btf_dump__new_deprecated; + libbpf_major_version; + libbpf_minor_version; + libbpf_version_string; perf_buffer__new; perf_buffer__new_deprecated; perf_buffer__new_raw; perf_buffer__new_raw_deprecated; } LIBBPF_0.5.0; + +LIBBPF_0.7.0 { + global: + bpf_btf_load; + bpf_program__log_buf; + bpf_program__log_level; + bpf_program__set_log_buf; + bpf_program__set_log_level; +}; diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h index b21cefc9c3b6..000e37798ff2 100644 --- a/tools/lib/bpf/libbpf_common.h +++ b/tools/lib/bpf/libbpf_common.h @@ -40,6 +40,11 @@ #else #define __LIBBPF_MARK_DEPRECATED_0_7(X) #endif +#if __LIBBPF_CURRENT_VERSION_GEQ(0, 8) +#define __LIBBPF_MARK_DEPRECATED_0_8(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_0_8(X) +#endif /* This set of internal macros allows to do "function overloading" based on * number of arguments provided by used in backwards-compatible way during the diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index f7ac349650a1..355c41019aed 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -172,7 +172,7 @@ static inline void *libbpf_reallocarray(void *ptr, size_t nmemb, size_t size) struct btf; struct btf_type; -struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id); +struct btf_type *btf_type_by_id(const struct btf *btf, __u32 type_id); const char *btf_kind_str(const struct btf_type *t); const struct btf_type *skip_mods_and_typedefs(const struct btf *btf, __u32 id, __u32 *res_id); @@ -277,27 +277,7 @@ int parse_cpu_mask_str(const char *s, bool **mask, int *mask_sz); int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); - -struct bpf_create_map_params { - const char *name; - enum bpf_map_type map_type; - __u32 map_flags; - __u32 key_size; - __u32 value_size; - __u32 max_entries; - __u32 numa_node; - __u32 btf_fd; - __u32 btf_key_type_id; - __u32 btf_value_type_id; - __u32 map_ifindex; - union { - __u32 inner_map_fd; - __u32 btf_vmlinux_value_type_id; - }; - __u64 map_extra; -}; - -int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr); +int btf_load_into_kernel(struct btf *btf, char *log_buf, size_t log_sz, __u32 log_level); struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type, diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 02c401e314c7..4bdec69523a7 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -164,7 +164,7 @@ int libbpf__load_raw_btf(const char *raw_types, size_t types_len, memcpy(raw_btf + hdr.hdr_len, raw_types, hdr.type_len); memcpy(raw_btf + hdr.hdr_len + hdr.type_len, str_sec, hdr.str_len); - btf_fd = bpf_load_btf(raw_btf, btf_len, NULL, 0, false); + btf_fd = bpf_btf_load(raw_btf, btf_len, NULL); free(raw_btf); return btf_fd; @@ -201,7 +201,6 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) { int key_size, value_size, max_entries, map_flags; __u32 btf_key_type_id = 0, btf_value_type_id = 0; - struct bpf_create_map_attr attr = {}; int fd = -1, btf_fd = -1, fd_inner; key_size = sizeof(__u32); @@ -271,34 +270,35 @@ bool bpf_probe_map_type(enum bpf_map_type map_type, __u32 ifindex) if (map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS || map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { + LIBBPF_OPTS(bpf_map_create_opts, opts); + /* TODO: probe for device, once libbpf has a function to create * map-in-map for offload */ if (ifindex) return false; - fd_inner = bpf_create_map(BPF_MAP_TYPE_HASH, - sizeof(__u32), sizeof(__u32), 1, 0); + fd_inner = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, + sizeof(__u32), sizeof(__u32), 1, NULL); if (fd_inner < 0) return false; - fd = bpf_create_map_in_map(map_type, NULL, sizeof(__u32), - fd_inner, 1, 0); + + opts.inner_map_fd = fd_inner; + fd = bpf_map_create(map_type, NULL, sizeof(__u32), sizeof(__u32), 1, &opts); close(fd_inner); } else { + LIBBPF_OPTS(bpf_map_create_opts, opts); + /* Note: No other restriction on map type probes for offload */ - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = value_size; - attr.max_entries = max_entries; - attr.map_flags = map_flags; - attr.map_ifindex = ifindex; + opts.map_flags = map_flags; + opts.map_ifindex = ifindex; if (btf_fd >= 0) { - attr.btf_fd = btf_fd; - attr.btf_key_type_id = btf_key_type_id; - attr.btf_value_type_id = btf_value_type_id; + opts.btf_fd = btf_fd; + opts.btf_key_type_id = btf_key_type_id; + opts.btf_value_type_id = btf_value_type_id; } - fd = bpf_create_map_xattr(&attr); + fd = bpf_map_create(map_type, NULL, key_size, value_size, max_entries, &opts); } if (fd >= 0) close(fd); diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h index dd56d76f291c..0fefefc3500b 100644 --- a/tools/lib/bpf/libbpf_version.h +++ b/tools/lib/bpf/libbpf_version.h @@ -4,6 +4,6 @@ #define __LIBBPF_VERSION_H #define LIBBPF_MAJOR_VERSION 0 -#define LIBBPF_MINOR_VERSION 6 +#define LIBBPF_MINOR_VERSION 7 #endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c index 594b206fa674..9aa016fb55aa 100644 --- a/tools/lib/bpf/linker.c +++ b/tools/lib/bpf/linker.c @@ -210,6 +210,7 @@ void bpf_linker__free(struct bpf_linker *linker) } free(linker->secs); + free(linker->glob_syms); free(linker); } @@ -1999,7 +2000,7 @@ add_sym: static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *obj) { struct src_sec *src_symtab = &obj->secs[obj->symtab_sec_idx]; - struct dst_sec *dst_symtab = &linker->secs[linker->symtab_sec_idx]; + struct dst_sec *dst_symtab; int i, err; for (i = 1; i < obj->sec_cnt; i++) { @@ -2032,6 +2033,9 @@ static int linker_append_elf_relos(struct bpf_linker *linker, struct src_obj *ob return -1; } + /* add_dst_sec() above could have invalidated linker->secs */ + dst_symtab = &linker->secs[linker->symtab_sec_idx]; + /* shdr->sh_link points to SYMTAB */ dst_sec->shdr->sh_link = linker->symtab_sec_idx; diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index b5b8956a1be8..32464f0ab4b1 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -1,6 +1,60 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2019 Facebook */ +#ifdef __KERNEL__ +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/string.h> +#include <linux/bpf_verifier.h> +#include "relo_core.h" + +static const char *btf_kind_str(const struct btf_type *t) +{ + return btf_type_str(t); +} + +static bool is_ldimm64_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, u32 id, u32 *res_id) +{ + return btf_type_skip_modifiers(btf, id, res_id); +} + +static const char *btf__name_by_offset(const struct btf *btf, u32 offset) +{ + return btf_name_by_offset(btf, offset); +} + +static s64 btf__resolve_size(const struct btf *btf, u32 type_id) +{ + const struct btf_type *t; + int size; + + t = btf_type_by_id(btf, type_id); + t = btf_resolve_size(btf, t, &size); + if (IS_ERR(t)) + return PTR_ERR(t); + return size; +} + +enum libbpf_print_level { + LIBBPF_WARN, + LIBBPF_INFO, + LIBBPF_DEBUG, +}; + +#undef pr_warn +#undef pr_info +#undef pr_debug +#define pr_warn(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_info(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_debug(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define libbpf_print(level, fmt, ...) bpf_log((void *)prog_name, fmt, ##__VA_ARGS__) +#else #include <stdio.h> #include <string.h> #include <errno.h> @@ -12,33 +66,7 @@ #include "btf.h" #include "str_error.h" #include "libbpf_internal.h" - -#define BPF_CORE_SPEC_MAX_LEN 64 - -/* represents BPF CO-RE field or array element accessor */ -struct bpf_core_accessor { - __u32 type_id; /* struct/union type or array element type */ - __u32 idx; /* field index or array index */ - const char *name; /* field name or NULL for array accessor */ -}; - -struct bpf_core_spec { - const struct btf *btf; - /* high-level spec: named fields and array indices only */ - struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; - /* original unresolved (no skip_mods_or_typedefs) root type ID */ - __u32 root_type_id; - /* CO-RE relocation kind */ - enum bpf_core_relo_kind relo_kind; - /* high-level spec length */ - int len; - /* raw, low-level spec: 1-to-1 with accessor spec string */ - int raw_spec[BPF_CORE_SPEC_MAX_LEN]; - /* raw spec length */ - int raw_len; - /* field bit offset represented by spec */ - __u32 bit_offset; -}; +#endif static bool is_flex_arr(const struct btf *btf, const struct bpf_core_accessor *acc, @@ -51,25 +79,25 @@ static bool is_flex_arr(const struct btf *btf, return false; /* has to be the last member of enclosing struct */ - t = btf__type_by_id(btf, acc->type_id); + t = btf_type_by_id(btf, acc->type_id); return acc->idx == btf_vlen(t) - 1; } static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_FIELD_BYTE_OFFSET: return "byte_off"; - case BPF_FIELD_BYTE_SIZE: return "byte_sz"; - case BPF_FIELD_EXISTS: return "field_exists"; - case BPF_FIELD_SIGNED: return "signed"; - case BPF_FIELD_LSHIFT_U64: return "lshift_u64"; - case BPF_FIELD_RSHIFT_U64: return "rshift_u64"; - case BPF_TYPE_ID_LOCAL: return "local_type_id"; - case BPF_TYPE_ID_TARGET: return "target_type_id"; - case BPF_TYPE_EXISTS: return "type_exists"; - case BPF_TYPE_SIZE: return "type_size"; - case BPF_ENUMVAL_EXISTS: return "enumval_exists"; - case BPF_ENUMVAL_VALUE: return "enumval_value"; + case BPF_CORE_FIELD_BYTE_OFFSET: return "byte_off"; + case BPF_CORE_FIELD_BYTE_SIZE: return "byte_sz"; + case BPF_CORE_FIELD_EXISTS: return "field_exists"; + case BPF_CORE_FIELD_SIGNED: return "signed"; + case BPF_CORE_FIELD_LSHIFT_U64: return "lshift_u64"; + case BPF_CORE_FIELD_RSHIFT_U64: return "rshift_u64"; + case BPF_CORE_TYPE_ID_LOCAL: return "local_type_id"; + case BPF_CORE_TYPE_ID_TARGET: return "target_type_id"; + case BPF_CORE_TYPE_EXISTS: return "type_exists"; + case BPF_CORE_TYPE_SIZE: return "type_size"; + case BPF_CORE_ENUMVAL_EXISTS: return "enumval_exists"; + case BPF_CORE_ENUMVAL_VALUE: return "enumval_value"; default: return "unknown"; } } @@ -77,12 +105,12 @@ static const char *core_relo_kind_str(enum bpf_core_relo_kind kind) static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_FIELD_BYTE_OFFSET: - case BPF_FIELD_BYTE_SIZE: - case BPF_FIELD_EXISTS: - case BPF_FIELD_SIGNED: - case BPF_FIELD_LSHIFT_U64: - case BPF_FIELD_RSHIFT_U64: + case BPF_CORE_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_EXISTS: + case BPF_CORE_FIELD_SIGNED: + case BPF_CORE_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: return true; default: return false; @@ -92,10 +120,10 @@ static bool core_relo_is_field_based(enum bpf_core_relo_kind kind) static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_TYPE_ID_LOCAL: - case BPF_TYPE_ID_TARGET: - case BPF_TYPE_EXISTS: - case BPF_TYPE_SIZE: + case BPF_CORE_TYPE_ID_LOCAL: + case BPF_CORE_TYPE_ID_TARGET: + case BPF_CORE_TYPE_EXISTS: + case BPF_CORE_TYPE_SIZE: return true; default: return false; @@ -105,8 +133,8 @@ static bool core_relo_is_type_based(enum bpf_core_relo_kind kind) static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) { switch (kind) { - case BPF_ENUMVAL_EXISTS: - case BPF_ENUMVAL_VALUE: + case BPF_CORE_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_VALUE: return true; default: return false; @@ -150,7 +178,7 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access * string to specify enumerator's value index that need to be relocated. */ -static int bpf_core_parse_spec(const struct btf *btf, +static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, __u32 type_id, const char *spec_str, enum bpf_core_relo_kind relo_kind, @@ -272,8 +300,8 @@ static int bpf_core_parse_spec(const struct btf *btf, return sz; spec->bit_offset += access_idx * sz * 8; } else { - pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", - type_id, spec_str, i, id, btf_kind_str(t)); + pr_warn("prog '%s': relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", + prog_name, type_id, spec_str, i, id, btf_kind_str(t)); return -EINVAL; } } @@ -346,8 +374,6 @@ recur: targ_id = btf_array(targ_type)->type; goto recur; default: - pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n", - btf_kind(local_type), local_id, targ_id); return 0; } } @@ -388,7 +414,7 @@ static int bpf_core_match_member(const struct btf *local_btf, return 0; local_id = local_acc->type_id; - local_type = btf__type_by_id(local_btf, local_id); + local_type = btf_type_by_id(local_btf, local_id); local_member = btf_members(local_type) + local_acc->idx; local_name = btf__name_by_offset(local_btf, local_member->name_off); @@ -571,7 +597,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, *field_sz = 0; - if (relo->kind == BPF_FIELD_EXISTS) { + if (relo->kind == BPF_CORE_FIELD_EXISTS) { *val = spec ? 1 : 0; return 0; } @@ -580,11 +606,11 @@ static int bpf_core_calc_field_relo(const char *prog_name, return -EUCLEAN; /* request instruction poisoning */ acc = &spec->spec[spec->len - 1]; - t = btf__type_by_id(spec->btf, acc->type_id); + t = btf_type_by_id(spec->btf, acc->type_id); /* a[n] accessor needs special handling */ if (!acc->name) { - if (relo->kind == BPF_FIELD_BYTE_OFFSET) { + if (relo->kind == BPF_CORE_FIELD_BYTE_OFFSET) { *val = spec->bit_offset / 8; /* remember field size for load/store mem size */ sz = btf__resolve_size(spec->btf, acc->type_id); @@ -592,7 +618,7 @@ static int bpf_core_calc_field_relo(const char *prog_name, return -EINVAL; *field_sz = sz; *type_id = acc->type_id; - } else if (relo->kind == BPF_FIELD_BYTE_SIZE) { + } else if (relo->kind == BPF_CORE_FIELD_BYTE_SIZE) { sz = btf__resolve_size(spec->btf, acc->type_id); if (sz < 0) return -EINVAL; @@ -644,36 +670,36 @@ static int bpf_core_calc_field_relo(const char *prog_name, *validate = !bitfield; switch (relo->kind) { - case BPF_FIELD_BYTE_OFFSET: + case BPF_CORE_FIELD_BYTE_OFFSET: *val = byte_off; if (!bitfield) { *field_sz = byte_sz; *type_id = field_type_id; } break; - case BPF_FIELD_BYTE_SIZE: + case BPF_CORE_FIELD_BYTE_SIZE: *val = byte_sz; break; - case BPF_FIELD_SIGNED: + case BPF_CORE_FIELD_SIGNED: /* enums will be assumed unsigned */ *val = btf_is_enum(mt) || (btf_int_encoding(mt) & BTF_INT_SIGNED); if (validate) *validate = true; /* signedness is never ambiguous */ break; - case BPF_FIELD_LSHIFT_U64: + case BPF_CORE_FIELD_LSHIFT_U64: #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ *val = 64 - (bit_off + bit_sz - byte_off * 8); #else *val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8); #endif break; - case BPF_FIELD_RSHIFT_U64: + case BPF_CORE_FIELD_RSHIFT_U64: *val = 64 - bit_sz; if (validate) *validate = true; /* right shift is never ambiguous */ break; - case BPF_FIELD_EXISTS: + case BPF_CORE_FIELD_EXISTS: default: return -EOPNOTSUPP; } @@ -694,20 +720,20 @@ static int bpf_core_calc_type_relo(const struct bpf_core_relo *relo, } switch (relo->kind) { - case BPF_TYPE_ID_TARGET: + case BPF_CORE_TYPE_ID_TARGET: *val = spec->root_type_id; break; - case BPF_TYPE_EXISTS: + case BPF_CORE_TYPE_EXISTS: *val = 1; break; - case BPF_TYPE_SIZE: + case BPF_CORE_TYPE_SIZE: sz = btf__resolve_size(spec->btf, spec->root_type_id); if (sz < 0) return -EINVAL; *val = sz; break; - case BPF_TYPE_ID_LOCAL: - /* BPF_TYPE_ID_LOCAL is handled specially and shouldn't get here */ + case BPF_CORE_TYPE_ID_LOCAL: + /* BPF_CORE_TYPE_ID_LOCAL is handled specially and shouldn't get here */ default: return -EOPNOTSUPP; } @@ -723,13 +749,13 @@ static int bpf_core_calc_enumval_relo(const struct bpf_core_relo *relo, const struct btf_enum *e; switch (relo->kind) { - case BPF_ENUMVAL_EXISTS: + case BPF_CORE_ENUMVAL_EXISTS: *val = spec ? 1 : 0; break; - case BPF_ENUMVAL_VALUE: + case BPF_CORE_ENUMVAL_VALUE: if (!spec) return -EUCLEAN; /* request instruction poisoning */ - t = btf__type_by_id(spec->btf, spec->spec[0].type_id); + t = btf_type_by_id(spec->btf, spec->spec[0].type_id); e = btf_enum(t) + spec->spec[0].idx; *val = e->val; break; @@ -805,8 +831,8 @@ static int bpf_core_calc_relo(const char *prog_name, if (res->orig_sz != res->new_sz) { const struct btf_type *orig_t, *new_t; - orig_t = btf__type_by_id(local_spec->btf, res->orig_type_id); - new_t = btf__type_by_id(targ_spec->btf, res->new_type_id); + orig_t = btf_type_by_id(local_spec->btf, res->orig_type_id); + new_t = btf_type_by_id(targ_spec->btf, res->new_type_id); /* There are two use cases in which it's safe to * adjust load/store's mem size: @@ -1045,7 +1071,7 @@ poison: * [<type-id>] (<type-name>) + <raw-spec> => <offset>@<spec>, * where <spec> is a C-syntax view of recorded field access, e.g.: x.a[3].b */ -static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +static void bpf_core_dump_spec(const char *prog_name, int level, const struct bpf_core_spec *spec) { const struct btf_type *t; const struct btf_enum *e; @@ -1054,7 +1080,7 @@ static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) int i; type_id = spec->root_type_id; - t = btf__type_by_id(spec->btf, type_id); + t = btf_type_by_id(spec->btf, type_id); s = btf__name_by_offset(spec->btf, t->name_off); libbpf_print(level, "[%u] %s %s", type_id, btf_kind_str(t), str_is_empty(s) ? "<anon>" : s); @@ -1147,9 +1173,12 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, const struct bpf_core_relo *relo, int relo_idx, const struct btf *local_btf, - struct bpf_core_cand_list *cands) + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch) { - struct bpf_core_spec local_spec, cand_spec, targ_spec = {}; + struct bpf_core_spec *local_spec = &specs_scratch[0]; + struct bpf_core_spec *cand_spec = &specs_scratch[1]; + struct bpf_core_spec *targ_spec = &specs_scratch[2]; struct bpf_core_relo_res cand_res, targ_res; const struct btf_type *local_type; const char *local_name; @@ -1158,10 +1187,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, int i, j, err; local_id = relo->type_id; - local_type = btf__type_by_id(local_btf, local_id); - if (!local_type) - return -EINVAL; - + local_type = btf_type_by_id(local_btf, local_id); local_name = btf__name_by_offset(local_btf, local_type->name_off); if (!local_name) return -EINVAL; @@ -1170,7 +1196,8 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, if (str_is_empty(spec_str)) return -EINVAL; - err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec); + err = bpf_core_parse_spec(prog_name, local_btf, local_id, spec_str, + relo->kind, local_spec); if (err) { pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n", prog_name, relo_idx, local_id, btf_kind_str(local_type), @@ -1181,15 +1208,15 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog_name, relo_idx, core_relo_kind_str(relo->kind), relo->kind); - bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); + bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, local_spec); libbpf_print(LIBBPF_DEBUG, "\n"); /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ - if (relo->kind == BPF_TYPE_ID_LOCAL) { + if (relo->kind == BPF_CORE_TYPE_ID_LOCAL) { targ_res.validate = true; targ_res.poison = false; - targ_res.orig_val = local_spec.root_type_id; - targ_res.new_val = local_spec.root_type_id; + targ_res.orig_val = local_spec->root_type_id; + targ_res.new_val = local_spec->root_type_id; goto patch_insn; } @@ -1202,38 +1229,38 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, for (i = 0, j = 0; i < cands->len; i++) { - err = bpf_core_spec_match(&local_spec, cands->cands[i].btf, - cands->cands[i].id, &cand_spec); + err = bpf_core_spec_match(local_spec, cands->cands[i].btf, + cands->cands[i].id, cand_spec); if (err < 0) { pr_warn("prog '%s': relo #%d: error matching candidate #%d ", prog_name, relo_idx, i); - bpf_core_dump_spec(LIBBPF_WARN, &cand_spec); + bpf_core_dump_spec(prog_name, LIBBPF_WARN, cand_spec); libbpf_print(LIBBPF_WARN, ": %d\n", err); return err; } pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog_name, relo_idx, err == 0 ? "non-matching" : "matching", i); - bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, cand_spec); libbpf_print(LIBBPF_DEBUG, "\n"); if (err == 0) continue; - err = bpf_core_calc_relo(prog_name, relo, relo_idx, &local_spec, &cand_spec, &cand_res); + err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, cand_spec, &cand_res); if (err) return err; if (j == 0) { targ_res = cand_res; - targ_spec = cand_spec; - } else if (cand_spec.bit_offset != targ_spec.bit_offset) { + *targ_spec = *cand_spec; + } else if (cand_spec->bit_offset != targ_spec->bit_offset) { /* if there are many field relo candidates, they * should all resolve to the same bit offset */ pr_warn("prog '%s': relo #%d: field offset ambiguity: %u != %u\n", - prog_name, relo_idx, cand_spec.bit_offset, - targ_spec.bit_offset); + prog_name, relo_idx, cand_spec->bit_offset, + targ_spec->bit_offset); return -EINVAL; } else if (cand_res.poison != targ_res.poison || cand_res.new_val != targ_res.new_val) { /* all candidates should result in the same relocation @@ -1251,7 +1278,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, } /* - * For BPF_FIELD_EXISTS relo or when used BPF program has field + * For BPF_CORE_FIELD_EXISTS relo or when used BPF program has field * existence checks or kernel version/config checks, it's expected * that we might not find any candidates. In this case, if field * wasn't found in any candidate, the list of candidates shouldn't @@ -1277,7 +1304,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, prog_name, relo_idx); /* calculate single target relo result explicitly */ - err = bpf_core_calc_relo(prog_name, relo, relo_idx, &local_spec, NULL, &targ_res); + err = bpf_core_calc_relo(prog_name, relo, relo_idx, local_spec, NULL, &targ_res); if (err) return err; } diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 3b9f8f18346c..17799819ad7c 100644 --- a/tools/lib/bpf/relo_core.h +++ b/tools/lib/bpf/relo_core.h @@ -4,81 +4,10 @@ #ifndef __RELO_CORE_H #define __RELO_CORE_H -/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value - * has to be adjusted by relocations. - */ -enum bpf_core_relo_kind { - BPF_FIELD_BYTE_OFFSET = 0, /* field byte offset */ - BPF_FIELD_BYTE_SIZE = 1, /* field size in bytes */ - BPF_FIELD_EXISTS = 2, /* field existence in target kernel */ - BPF_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ - BPF_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ - BPF_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ - BPF_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ - BPF_TYPE_ID_TARGET = 7, /* type ID in target kernel */ - BPF_TYPE_EXISTS = 8, /* type existence in target kernel */ - BPF_TYPE_SIZE = 9, /* type size in bytes */ - BPF_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ - BPF_ENUMVAL_VALUE = 11, /* enum value integer value */ -}; - -/* The minimum bpf_core_relo checked by the loader - * - * CO-RE relocation captures the following data: - * - insn_off - instruction offset (in bytes) within a BPF program that needs - * its insn->imm field to be relocated with actual field info; - * - type_id - BTF type ID of the "root" (containing) entity of a relocatable - * type or field; - * - access_str_off - offset into corresponding .BTF string section. String - * interpretation depends on specific relocation kind: - * - for field-based relocations, string encodes an accessed field using - * a sequence of field and array indices, separated by colon (:). It's - * conceptually very close to LLVM's getelementptr ([0]) instruction's - * arguments for identifying offset to a field. - * - for type-based relocations, strings is expected to be just "0"; - * - for enum value-based relocations, string contains an index of enum - * value within its enum type; - * - * Example to provide a better feel. - * - * struct sample { - * int a; - * struct { - * int b[10]; - * }; - * }; - * - * struct sample *s = ...; - * int x = &s->a; // encoded as "0:0" (a is field #0) - * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, - * // b is field #0 inside anon struct, accessing elem #5) - * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) - * - * type_id for all relocs in this example will capture BTF type id of - * `struct sample`. - * - * Such relocation is emitted when using __builtin_preserve_access_index() - * Clang built-in, passing expression that captures field address, e.g.: - * - * bpf_probe_read(&dst, sizeof(dst), - * __builtin_preserve_access_index(&src->a.b.c)); - * - * In this case Clang will emit field relocation recording necessary data to - * be able to find offset of embedded `a.b.c` field within `src` struct. - * - * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction - */ -struct bpf_core_relo { - __u32 insn_off; - __u32 type_id; - __u32 access_str_off; - enum bpf_core_relo_kind kind; -}; +#include <linux/bpf.h> struct bpf_core_cand { const struct btf *btf; - const struct btf_type *t; - const char *name; __u32 id; }; @@ -88,11 +17,39 @@ struct bpf_core_cand_list { int len; }; +#define BPF_CORE_SPEC_MAX_LEN 64 + +/* represents BPF CO-RE field or array element accessor */ +struct bpf_core_accessor { + __u32 type_id; /* struct/union type or array element type */ + __u32 idx; /* field index or array index */ + const char *name; /* field name or NULL for array accessor */ +}; + +struct bpf_core_spec { + const struct btf *btf; + /* high-level spec: named fields and array indices only */ + struct bpf_core_accessor spec[BPF_CORE_SPEC_MAX_LEN]; + /* original unresolved (no skip_mods_or_typedefs) root type ID */ + __u32 root_type_id; + /* CO-RE relocation kind */ + enum bpf_core_relo_kind relo_kind; + /* high-level spec length */ + int len; + /* raw, low-level spec: 1-to-1 with accessor spec string */ + int raw_spec[BPF_CORE_SPEC_MAX_LEN]; + /* raw spec length */ + int raw_len; + /* field bit offset represented by spec */ + __u32 bit_offset; +}; + int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, int insn_idx, const struct bpf_core_relo *relo, int relo_idx, const struct btf *local_btf, - struct bpf_core_cand_list *cands); + struct bpf_core_cand_list *cands, + struct bpf_core_spec *specs_scratch); int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, const struct btf *targ_btf, __u32 targ_id); diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h index 9cf66702fa8d..0b84d8e6b72a 100644 --- a/tools/lib/bpf/skel_internal.h +++ b/tools/lib/bpf/skel_internal.h @@ -7,6 +7,16 @@ #include <sys/syscall.h> #include <sys/mman.h> +#ifndef __NR_bpf +# if defined(__mips__) && defined(_ABIO32) +# define __NR_bpf 4355 +# elif defined(__mips__) && defined(_ABIN32) +# define __NR_bpf 6319 +# elif defined(__mips__) && defined(_ABI64) +# define __NR_bpf 5315 +# endif +#endif + /* This file is a base header for auto-generated *.lskel.h files. * Its contents will change and may become part of auto-generation in the future. * @@ -65,8 +75,7 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts) int map_fd = -1, prog_fd = -1, key = 0, err; union bpf_attr attr; - map_fd = bpf_create_map_name(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, - opts->data_sz, 1, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "__loader.map", 4, opts->data_sz, 1, NULL); if (map_fd < 0) { opts->errstr = "failed to create loader map"; err = -errno; diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index fdb22f5405c9..e8d94c6dd3bc 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -35,6 +35,11 @@ #include "libbpf_internal.h" #include "xsk.h" +/* entire xsk.h and xsk.c is going away in libbpf 1.0, so ignore all internal + * uses of deprecated APIs + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + #ifndef SOL_XDP #define SOL_XDP 283 #endif @@ -364,7 +369,6 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, static enum xsk_prog get_xsk_prog(void) { enum xsk_prog detected = XSK_PROG_FALLBACK; - struct bpf_create_map_attr map_attr; __u32 size_out, retval, duration; char data_in = 0, data_out; struct bpf_insn insns[] = { @@ -376,13 +380,7 @@ static enum xsk_prog get_xsk_prog(void) }; int prog_fd, map_fd, ret, insn_cnt = ARRAY_SIZE(insns); - memset(&map_attr, 0, sizeof(map_attr)); - map_attr.map_type = BPF_MAP_TYPE_XSKMAP; - map_attr.key_size = sizeof(int); - map_attr.value_size = sizeof(int); - map_attr.max_entries = 1; - - map_fd = bpf_create_map_xattr(&map_attr); + map_fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, NULL, sizeof(int), sizeof(int), 1, NULL); if (map_fd < 0) return detected; @@ -586,8 +584,8 @@ static int xsk_create_bpf_maps(struct xsk_socket *xsk) if (max_queues < 0) return max_queues; - fd = bpf_create_map_name(BPF_MAP_TYPE_XSKMAP, "xsks_map", - sizeof(int), sizeof(int), max_queues, 0); + fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, "xsks_map", + sizeof(int), sizeof(int), max_queues, NULL); if (fd < 0) return fd; diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 81a4c543ff7e..4b384c907027 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -375,6 +375,7 @@ static int read_symbols(struct elf *elf) return -1; } memset(sym, 0, sizeof(*sym)); + INIT_LIST_HEAD(&sym->pv_target); sym->alias = sym; sym->idx = i; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index c90c7084e45a..bdf699f6552b 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -153,6 +153,10 @@ void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func) !strcmp(func->name, "_paravirt_ident_64")) return; + /* already added this function */ + if (!list_empty(&func->pv_target)) + return; + list_add(&func->pv_target, &f->pv_ops[idx].targets); f->pv_ops[idx].clean = false; } diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index afd144725a0b..3df74cf5651a 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -271,8 +271,6 @@ endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS) -FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS) -FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS) FEATURE_CHECK_LDFLAGS-libaio = -lrt diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 7bef917cc84e..15109af9d075 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -528,3 +528,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index df5261e5cfe1..ed9c5c2eafad 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -451,3 +451,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv sys_futex_waitv diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index fa0ff4ce2b74..488f6e6ba1a5 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -223,8 +223,6 @@ static unsigned int group(pthread_t *pth, snd_ctx->out_fds[i] = fds[1]; if (!thread_mode) close(fds[0]); - - free(ctx); } /* Now we have all the fds, fork the senders */ @@ -241,8 +239,6 @@ static unsigned int group(pthread_t *pth, for (i = 0; i < num_fds; i++) close(snd_ctx->out_fds[i]); - free(snd_ctx); - /* Return number of children to reap */ return num_fds * 2; } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index bc5259db5fd9..b9d6306cc14e 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -820,7 +820,7 @@ static int __cmd_inject(struct perf_inject *inject) inject->tool.ordered_events = true; inject->tool.ordering_requires_timestamps = true; /* Allow space in the header for new attributes */ - output_data_offset = 4096; + output_data_offset = roundup(8192 + session->header.data_offset, 4096); if (inject->strip) strip_init(inject); } diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index 329f77f592f4..573490530194 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -296,9 +296,13 @@ static int check_env(void) return err; } +/* temporarily disable libbpf deprecation warnings */ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns, ARRAY_SIZE(insns), license, kver_int, NULL, 0); +#pragma GCC diagnostic pop if (err < 0) { pr_err("Missing basic BPF support, skip this test: %s\n", strerror(errno)); diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index c895de481fe1..d54c5371c6a6 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -169,7 +169,9 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0); TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies); TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0); - TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); + + if (num_dies) // Some platforms do not have CPU die support, for example s390 + TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages); /* * Source count returns the number of events aggregating in a leader diff --git a/tools/perf/tests/parse-metric.c b/tools/perf/tests/parse-metric.c index 574b7e4efd3a..07b6f4ec024f 100644 --- a/tools/perf/tests/parse-metric.c +++ b/tools/perf/tests/parse-metric.c @@ -109,6 +109,7 @@ static void load_runtime_stat(struct runtime_stat *st, struct evlist *evlist, struct evsel *evsel; u64 count; + perf_stat__reset_shadow_stats(); evlist__for_each_entry(evlist, evsel) { count = find_value(evsel->name, vals); perf_stat__update_shadow_stats(evsel, count, 0, st); diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index fbb3c4057c30..528aeb0ab79d 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -29,6 +29,9 @@ #include <internal/xyarray.h> +/* temporarily disable libbpf deprecation warnings */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)), const char *fmt, va_list args) { diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index c17d4a43ce06..5a97fd7d0a71 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -307,6 +307,20 @@ static bool bperf_attr_map_compatible(int attr_map_fd) (map_info.value_size == sizeof(struct perf_event_attr_map_entry)); } +int __weak +bpf_map_create(enum bpf_map_type map_type, + const char *map_name __maybe_unused, + __u32 key_size, + __u32 value_size, + __u32 max_entries, + const struct bpf_map_create_opts *opts __maybe_unused) +{ +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + return bpf_create_map(map_type, key_size, value_size, max_entries, 0); +#pragma GCC diagnostic pop +} + static int bperf_lock_attr_map(struct target *target) { char path[PATH_MAX]; @@ -320,10 +334,10 @@ static int bperf_lock_attr_map(struct target *target) } if (access(path, F_OK)) { - map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, + map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(struct perf_event_attr), sizeof(struct perf_event_attr_map_entry), - ATTR_MAP_SIZE, 0); + ATTR_MAP_SIZE, NULL); if (map_fd < 0) return -1; diff --git a/tools/perf/util/bpf_skel/bperf.h b/tools/perf/util/bpf_skel/bperf.h deleted file mode 100644 index 186a5551ddb9..000000000000 --- a/tools/perf/util/bpf_skel/bperf.h +++ /dev/null @@ -1,14 +0,0 @@ -// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -// Copyright (c) 2021 Facebook - -#ifndef __BPERF_STAT_H -#define __BPERF_STAT_H - -typedef struct { - __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); - __uint(key_size, sizeof(__u32)); - __uint(value_size, sizeof(struct bpf_perf_event_value)); - __uint(max_entries, 1); -} reading_map; - -#endif /* __BPERF_STAT_H */ diff --git a/tools/perf/util/bpf_skel/bperf_follower.bpf.c b/tools/perf/util/bpf_skel/bperf_follower.bpf.c index b8fa3cb2da23..f193998530d4 100644 --- a/tools/perf/util/bpf_skel/bperf_follower.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_follower.bpf.c @@ -1,14 +1,23 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include <linux/bpf.h> -#include <linux/perf_event.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bperf.h" #include "bperf_u.h" -reading_map diff_readings SEC(".maps"); -reading_map accum_readings SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} diff_readings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} accum_readings SEC(".maps"); struct { __uint(type, BPF_MAP_TYPE_HASH); diff --git a/tools/perf/util/bpf_skel/bperf_leader.bpf.c b/tools/perf/util/bpf_skel/bperf_leader.bpf.c index 4f70d1459e86..e2a2d4cd7779 100644 --- a/tools/perf/util/bpf_skel/bperf_leader.bpf.c +++ b/tools/perf/util/bpf_skel/bperf_leader.bpf.c @@ -1,10 +1,8 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2021 Facebook -#include <linux/bpf.h> -#include <linux/perf_event.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "bperf.h" struct { __uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY); @@ -13,8 +11,19 @@ struct { __uint(map_flags, BPF_F_PRESERVE_ELEMS); } events SEC(".maps"); -reading_map prev_readings SEC(".maps"); -reading_map diff_readings SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} prev_readings SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_perf_event_value)); + __uint(max_entries, 1); +} diff_readings SEC(".maps"); SEC("raw_tp/sched_switch") int BPF_PROG(on_switch) diff --git a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c index ab12b4c4ece2..97037d3b3d9f 100644 --- a/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c +++ b/tools/perf/util/bpf_skel/bpf_prog_profiler.bpf.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) // Copyright (c) 2020 Facebook -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index 95ffed66369c..c59331eea1d9 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -44,13 +44,16 @@ struct perf_event_attr; /* perf sample has 16 bits size limit */ #define PERF_SAMPLE_MAX_SIZE (1 << 16) +/* number of register is bound by the number of bits in regs_dump::mask (64) */ +#define PERF_SAMPLE_REGS_CACHE_SIZE (8 * sizeof(u64)) + struct regs_dump { u64 abi; u64 mask; u64 *regs; /* Cached values/mask filled by first register access. */ - u64 cache_regs[PERF_REGS_MAX]; + u64 cache_regs[PERF_SAMPLE_REGS_CACHE_SIZE]; u64 cache_mask; }; diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 79cce216727e..e3c1a532d059 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2321,6 +2321,7 @@ out: #define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \ static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \ {\ + free(ff->ph->env.__feat_env); \ ff->ph->env.__feat_env = do_read_string(ff); \ return ff->ph->env.__feat_env ? 0 : -ENOMEM; \ } @@ -4124,6 +4125,7 @@ int perf_event__process_feature(struct perf_session *session, struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event; int type = fe->header.type; u64 feat = fe->feat_id; + int ret = 0; if (type < 0 || type >= PERF_RECORD_HEADER_MAX) { pr_warning("invalid record type %d in pipe-mode\n", type); @@ -4141,11 +4143,13 @@ int perf_event__process_feature(struct perf_session *session, ff.size = event->header.size - sizeof(*fe); ff.ph = &session->header; - if (feat_ops[feat].process(&ff, NULL)) - return -1; + if (feat_ops[feat].process(&ff, NULL)) { + ret = -1; + goto out; + } if (!feat_ops[feat].print || !tool->show_feat_hdr) - return 0; + goto out; if (!feat_ops[feat].full_only || tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) { @@ -4154,8 +4158,9 @@ int perf_event__process_feature(struct perf_session *session, fprintf(stdout, "# %s info available, use -I to display\n", feat_ops[feat].name); } - - return 0; +out: + free_event_desc(ff.events); + return ret; } size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 5f83937bf8f3..0e013c2d9eb4 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1205,61 +1205,69 @@ out_no_progress: static bool intel_pt_fup_event(struct intel_pt_decoder *decoder) { + enum intel_pt_sample_type type = decoder->state.type; bool ret = false; + decoder->state.type &= ~INTEL_PT_BRANCH; + if (decoder->set_fup_tx_flags) { decoder->set_fup_tx_flags = false; decoder->tx_flags = decoder->fup_tx_flags; - decoder->state.type = INTEL_PT_TRANSACTION; + decoder->state.type |= INTEL_PT_TRANSACTION; if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX) decoder->state.type |= INTEL_PT_BRANCH; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; decoder->state.flags = decoder->fup_tx_flags; - return true; + ret = true; } if (decoder->set_fup_ptw) { decoder->set_fup_ptw = false; - decoder->state.type = INTEL_PT_PTW; + decoder->state.type |= INTEL_PT_PTW; decoder->state.flags |= INTEL_PT_FUP_IP; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; decoder->state.ptw_payload = decoder->fup_ptw_payload; - return true; + ret = true; } if (decoder->set_fup_mwait) { decoder->set_fup_mwait = false; - decoder->state.type = INTEL_PT_MWAIT_OP; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; + decoder->state.type |= INTEL_PT_MWAIT_OP; decoder->state.mwait_payload = decoder->fup_mwait_payload; ret = true; } if (decoder->set_fup_pwre) { decoder->set_fup_pwre = false; decoder->state.type |= INTEL_PT_PWR_ENTRY; - decoder->state.type &= ~INTEL_PT_BRANCH; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; decoder->state.pwre_payload = decoder->fup_pwre_payload; ret = true; } if (decoder->set_fup_exstop) { decoder->set_fup_exstop = false; decoder->state.type |= INTEL_PT_EX_STOP; - decoder->state.type &= ~INTEL_PT_BRANCH; decoder->state.flags |= INTEL_PT_FUP_IP; - decoder->state.from_ip = decoder->ip; - decoder->state.to_ip = 0; ret = true; } if (decoder->set_fup_bep) { decoder->set_fup_bep = false; decoder->state.type |= INTEL_PT_BLK_ITEMS; - decoder->state.type &= ~INTEL_PT_BRANCH; + ret = true; + } + if (decoder->overflow) { + decoder->overflow = false; + if (!ret && !decoder->pge) { + if (decoder->hop) { + decoder->state.type = 0; + decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; + } + decoder->pge = true; + decoder->state.type |= INTEL_PT_BRANCH | INTEL_PT_TRACE_BEGIN; + decoder->state.from_ip = 0; + decoder->state.to_ip = decoder->ip; + return true; + } + } + if (ret) { decoder->state.from_ip = decoder->ip; decoder->state.to_ip = 0; - ret = true; + } else { + decoder->state.type = type; } return ret; } @@ -1608,7 +1616,16 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder) intel_pt_clear_tx_flags(decoder); intel_pt_set_nr(decoder); decoder->timestamp_insn_cnt = 0; - decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; + decoder->state.from_ip = decoder->ip; + decoder->ip = 0; + decoder->pge = false; + decoder->set_fup_tx_flags = false; + decoder->set_fup_ptw = false; + decoder->set_fup_mwait = false; + decoder->set_fup_pwre = false; + decoder->set_fup_exstop = false; + decoder->set_fup_bep = false; decoder->overflow = true; return -EOVERFLOW; } @@ -2666,6 +2683,8 @@ static int intel_pt_scan_for_psb(struct intel_pt_decoder *decoder); /* Hop mode: Ignore TNT, do not walk code, but get ip from FUPs and TIPs */ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, int *err) { + *err = 0; + /* Leap from PSB to PSB, getting ip from FUP within PSB+ */ if (decoder->leap && !decoder->in_psb && decoder->packet.type != INTEL_PT_PSB) { *err = intel_pt_scan_for_psb(decoder); @@ -2678,6 +2697,7 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in return HOP_IGNORE; case INTEL_PT_TIP_PGD: + decoder->pge = false; if (!decoder->packet.count) { intel_pt_set_nr(decoder); return HOP_IGNORE; @@ -2705,18 +2725,21 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in if (!decoder->packet.count) return HOP_IGNORE; intel_pt_set_ip(decoder); - if (intel_pt_fup_event(decoder)) - return HOP_RETURN; - if (!decoder->branch_enable) + if (decoder->set_fup_mwait || decoder->set_fup_pwre) + *no_tip = true; + if (!decoder->branch_enable || !decoder->pge) *no_tip = true; if (*no_tip) { decoder->state.type = INTEL_PT_INSTRUCTION; decoder->state.from_ip = decoder->ip; decoder->state.to_ip = 0; + intel_pt_fup_event(decoder); return HOP_RETURN; } + intel_pt_fup_event(decoder); + decoder->state.type |= INTEL_PT_INSTRUCTION | INTEL_PT_BRANCH; *err = intel_pt_walk_fup_tip(decoder); - if (!*err) + if (!*err && decoder->state.to_ip) decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; return HOP_RETURN; @@ -2897,7 +2920,7 @@ static bool intel_pt_psb_with_fup(struct intel_pt_decoder *decoder, int *err) { struct intel_pt_psb_info data = { .fup = false }; - if (!decoder->branch_enable || !decoder->pge) + if (!decoder->branch_enable) return false; intel_pt_pkt_lookahead(decoder, intel_pt_psb_lookahead_cb, &data); @@ -2924,6 +2947,7 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder) if (err) return err; next: + err = 0; if (decoder->cyc_threshold) { if (decoder->sample_cyc && last_packet_type != INTEL_PT_CYC) decoder->sample_cyc = false; @@ -2962,6 +2986,7 @@ next: case INTEL_PT_TIP_PGE: { decoder->pge = true; + decoder->overflow = false; intel_pt_mtc_cyc_cnt_pge(decoder); intel_pt_set_nr(decoder); if (decoder->packet.count == 0) { @@ -2999,7 +3024,7 @@ next: break; } intel_pt_set_last_ip(decoder); - if (!decoder->branch_enable) { + if (!decoder->branch_enable || !decoder->pge) { decoder->ip = decoder->last_ip; if (intel_pt_fup_event(decoder)) return 0; @@ -3467,10 +3492,10 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) decoder->set_fup_pwre = false; decoder->set_fup_exstop = false; decoder->set_fup_bep = false; + decoder->overflow = false; if (!decoder->branch_enable) { decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; - decoder->overflow = false; decoder->state.type = 0; /* Do not have a sample */ return 0; } @@ -3485,7 +3510,6 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder) decoder->pkt_state = INTEL_PT_STATE_RESAMPLE; else decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; - decoder->overflow = false; decoder->state.from_ip = 0; decoder->state.to_ip = decoder->ip; @@ -3607,7 +3631,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder) } decoder->have_last_ip = true; - decoder->pkt_state = INTEL_PT_STATE_NO_IP; + decoder->pkt_state = INTEL_PT_STATE_IN_SYNC; err = intel_pt_walk_psb(decoder); if (err) @@ -3704,7 +3728,8 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder) if (err) { decoder->state.err = intel_pt_ext_err(err); - decoder->state.from_ip = decoder->ip; + if (err != -EOVERFLOW) + decoder->state.from_ip = decoder->ip; intel_pt_update_sample_time(decoder); decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt; intel_pt_set_nr(decoder); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 556a893508da..10c3187e4c5a 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -2565,6 +2565,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp) ptq->sync_switch = false; intel_pt_next_tid(pt, ptq); } + ptq->timestamp = state->est_timestamp; if (pt->synth_opts.errors) { err = intel_ptq_synth_error(ptq, state); if (err) diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c index 5ee47ae1509c..06a7461ba864 100644 --- a/tools/perf/util/perf_regs.c +++ b/tools/perf/util/perf_regs.c @@ -25,6 +25,9 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id) int i, idx = 0; u64 mask = regs->mask; + if ((u64)id >= PERF_SAMPLE_REGS_CACHE_SIZE) + return -EINVAL; + if (regs->cache_mask & (1ULL << id)) goto out; diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index 563a9ba8954f..7f782a31bda3 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -461,7 +461,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name) struct tep_event *tp_format; tp_format = trace_event__tp_format_id(evsel->core.attr.config); - if (!tp_format) + if (IS_ERR_OR_NULL(tp_format)) return NULL; evsel->tp_format = tp_format; diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c index 20bacd5972ad..34f1b1b1176c 100644 --- a/tools/perf/util/smt.c +++ b/tools/perf/util/smt.c @@ -15,7 +15,7 @@ int smt_on(void) if (cached) return cached_result; - if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0) + if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) goto done; ncpu = sysconf(_SC_NPROCESSORS_CONF); diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config index 331f6d30f472..cd7106876a5f 100644 --- a/tools/power/acpi/Makefile.config +++ b/tools/power/acpi/Makefile.config @@ -69,6 +69,7 @@ KERNEL_INCLUDE := $(OUTPUT)include ACPICA_INCLUDE := $(srctree)/../../../drivers/acpi/acpica CFLAGS += -D_LINUX -I$(KERNEL_INCLUDE) -I$(ACPICA_INCLUDE) CFLAGS += $(WARNINGS) +MKDIR = mkdir ifeq ($(strip $(V)),false) QUIET=@ diff --git a/tools/power/acpi/Makefile.rules b/tools/power/acpi/Makefile.rules index 2a6c170b57cd..1d7616f5d0ae 100644 --- a/tools/power/acpi/Makefile.rules +++ b/tools/power/acpi/Makefile.rules @@ -21,6 +21,7 @@ $(KERNEL_INCLUDE): $(objdir)%.o: %.c $(KERNEL_INCLUDE) $(ECHO) " CC " $(subst $(OUTPUT),,$@) + $(QUIET) $(MKDIR) -p $(objdir) 2>/dev/null $(QUIET) $(CC) -c $(CFLAGS) -o $@ $< all: $(OUTPUT)$(TOOL) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 5d42db2e129a..a795bca4c8ec 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -192,22 +192,26 @@ TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL) $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ) -$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c testing_helpers.o -$(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c testing_helpers.o -$(OUTPUT)/test_sock: cgroup_helpers.c testing_helpers.o -$(OUTPUT)/test_sock_addr: cgroup_helpers.c testing_helpers.o -$(OUTPUT)/test_sockmap: cgroup_helpers.c testing_helpers.o -$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c testing_helpers.o -$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c testing_helpers.o -$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c testing_helpers.o -$(OUTPUT)/test_sock_fields: cgroup_helpers.c testing_helpers.o -$(OUTPUT)/test_sysctl: cgroup_helpers.c testing_helpers.o -$(OUTPUT)/test_tag: testing_helpers.o -$(OUTPUT)/test_lirc_mode2_user: testing_helpers.o -$(OUTPUT)/xdping: testing_helpers.o -$(OUTPUT)/flow_dissector_load: testing_helpers.o -$(OUTPUT)/test_maps: testing_helpers.o -$(OUTPUT)/test_verifier: testing_helpers.o +CGROUP_HELPERS := $(OUTPUT)/cgroup_helpers.o +TESTING_HELPERS := $(OUTPUT)/testing_helpers.o +TRACE_HELPERS := $(OUTPUT)/trace_helpers.o + +$(OUTPUT)/test_dev_cgroup: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_skb_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sock: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sock_addr: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS) +$(OUTPUT)/get_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_cgroup_storage: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_sysctl: $(CGROUP_HELPERS) $(TESTING_HELPERS) +$(OUTPUT)/test_tag: $(TESTING_HELPERS) +$(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS) +$(OUTPUT)/xdping: $(TESTING_HELPERS) +$(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS) +$(OUTPUT)/test_maps: $(TESTING_HELPERS) +$(OUTPUT)/test_verifier: $(TESTING_HELPERS) BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ @@ -325,9 +329,10 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ linked_vars.skel.h linked_maps.skel.h LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ - test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c + test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c \ + map_ptr_kern.c core_kern.c # Generate both light skeleton and libbpf skeleton for these -LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c +LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test_subprog.c SKEL_BLACKLIST += $$(LSKELS) test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o @@ -531,14 +536,18 @@ $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \ $(OUTPUT)/perfbuf_bench.skel.h $(OUTPUT)/bench_bloom_filter_map.o: $(OUTPUT)/bloom_filter_bench.skel.h +$(OUTPUT)/bench_bpf_loop.o: $(OUTPUT)/bpf_loop_bench.skel.h $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm -$(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ +$(OUTPUT)/bench: $(OUTPUT)/bench.o \ + $(TESTING_HELPERS) \ + $(TRACE_HELPERS) \ $(OUTPUT)/bench_count.o \ $(OUTPUT)/bench_rename.o \ $(OUTPUT)/bench_trigger.o \ $(OUTPUT)/bench_ringbufs.o \ - $(OUTPUT)/bench_bloom_filter_map.o + $(OUTPUT)/bench_bloom_filter_map.o \ + $(OUTPUT)/bench_bpf_loop.o $(call msg,BINARY,,$@) $(Q)$(CC) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index cc4722f693e9..3d6082b97a56 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -134,6 +134,39 @@ void hits_drops_report_final(struct bench_res res[], int res_cnt) total_ops_mean, total_ops_stddev); } +void ops_report_progress(int iter, struct bench_res *res, long delta_ns) +{ + double hits_per_sec, hits_per_prod; + + hits_per_sec = res->hits / 1000000.0 / (delta_ns / 1000000000.0); + hits_per_prod = hits_per_sec / env.producer_cnt; + + printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0); + + printf("hits %8.3lfM/s (%7.3lfM/prod)\n", hits_per_sec, hits_per_prod); +} + +void ops_report_final(struct bench_res res[], int res_cnt) +{ + double hits_mean = 0.0, hits_stddev = 0.0; + int i; + + for (i = 0; i < res_cnt; i++) + hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt); + + if (res_cnt > 1) { + for (i = 0; i < res_cnt; i++) + hits_stddev += (hits_mean - res[i].hits / 1000000.0) * + (hits_mean - res[i].hits / 1000000.0) / + (res_cnt - 1.0); + + hits_stddev = sqrt(hits_stddev); + } + printf("Summary: throughput %8.3lf \u00B1 %5.3lf M ops/s (%7.3lfM ops/prod), ", + hits_mean, hits_stddev, hits_mean / env.producer_cnt); + printf("latency %8.3lf ns/op\n", 1000.0 / hits_mean * env.producer_cnt); +} + const char *argp_program_version = "benchmark"; const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; const char argp_program_doc[] = @@ -171,10 +204,12 @@ static const struct argp_option opts[] = { extern struct argp bench_ringbufs_argp; extern struct argp bench_bloom_map_argp; +extern struct argp bench_bpf_loop_argp; static const struct argp_child bench_parsers[] = { { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, { &bench_bloom_map_argp, 0, "Bloom filter map benchmark", 0 }, + { &bench_bpf_loop_argp, 0, "bpf_loop helper benchmark", 0 }, {}, }; @@ -359,6 +394,11 @@ extern const struct bench bench_trig_kprobe; extern const struct bench bench_trig_fentry; extern const struct bench bench_trig_fentry_sleep; extern const struct bench bench_trig_fmodret; +extern const struct bench bench_trig_uprobe_base; +extern const struct bench bench_trig_uprobe_with_nop; +extern const struct bench bench_trig_uretprobe_with_nop; +extern const struct bench bench_trig_uprobe_without_nop; +extern const struct bench bench_trig_uretprobe_without_nop; extern const struct bench bench_rb_libbpf; extern const struct bench bench_rb_custom; extern const struct bench bench_pb_libbpf; @@ -368,6 +408,7 @@ extern const struct bench bench_bloom_update; extern const struct bench bench_bloom_false_positive; extern const struct bench bench_hashmap_without_bloom; extern const struct bench bench_hashmap_with_bloom; +extern const struct bench bench_bpf_loop; static const struct bench *benchs[] = { &bench_count_global, @@ -385,6 +426,11 @@ static const struct bench *benchs[] = { &bench_trig_fentry, &bench_trig_fentry_sleep, &bench_trig_fmodret, + &bench_trig_uprobe_base, + &bench_trig_uprobe_with_nop, + &bench_trig_uretprobe_with_nop, + &bench_trig_uprobe_without_nop, + &bench_trig_uretprobe_without_nop, &bench_rb_libbpf, &bench_rb_custom, &bench_pb_libbpf, @@ -394,6 +440,7 @@ static const struct bench *benchs[] = { &bench_bloom_false_positive, &bench_hashmap_without_bloom, &bench_hashmap_with_bloom, + &bench_bpf_loop, }; static void setup_benchmark() diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index 624c6b11501f..50785503756b 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -59,6 +59,8 @@ void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns); void hits_drops_report_final(struct bench_res res[], int res_cnt); void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns); void false_hits_report_final(struct bench_res res[], int res_cnt); +void ops_report_progress(int iter, struct bench_res *res, long delta_ns); +void ops_report_final(struct bench_res res[], int res_cnt); static inline __u64 get_time_ns() { struct timespec t; diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c new file mode 100644 index 000000000000..d0a6572bfab6 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <argp.h> +#include "bench.h" +#include "bpf_loop_bench.skel.h" + +/* BPF triggering benchmarks */ +static struct ctx { + struct bpf_loop_bench *skel; +} ctx; + +static struct { + __u32 nr_loops; +} args = { + .nr_loops = 10, +}; + +enum { + ARG_NR_LOOPS = 4000, +}; + +static const struct argp_option opts[] = { + { "nr_loops", ARG_NR_LOOPS, "nr_loops", 0, + "Set number of loops for the bpf_loop helper"}, + {}, +}; + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + switch (key) { + case ARG_NR_LOOPS: + args.nr_loops = strtol(arg, NULL, 10); + break; + default: + return ARGP_ERR_UNKNOWN; + } + + return 0; +} + +/* exported into benchmark runner */ +const struct argp bench_bpf_loop_argp = { + .options = opts, + .parser = parse_arg, +}; + +static void validate(void) +{ + if (env.consumer_cnt != 1) { + fprintf(stderr, "benchmark doesn't support multi-consumer!\n"); + exit(1); + } +} + +static void *producer(void *input) +{ + while (true) + /* trigger the bpf program */ + syscall(__NR_getpgid); + + return NULL; +} + +static void *consumer(void *input) +{ + return NULL; +} + +static void measure(struct bench_res *res) +{ + res->hits = atomic_swap(&ctx.skel->bss->hits, 0); +} + +static void setup(void) +{ + struct bpf_link *link; + + setup_libbpf(); + + ctx.skel = bpf_loop_bench__open_and_load(); + if (!ctx.skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + link = bpf_program__attach(ctx.skel->progs.benchmark); + if (!link) { + fprintf(stderr, "failed to attach program!\n"); + exit(1); + } + + ctx.skel->bss->nr_loops = args.nr_loops; +} + +const struct bench bench_bpf_loop = { + .name = "bpf-loop", + .validate = validate, + .setup = setup, + .producer_thread = producer, + .consumer_thread = consumer, + .measure = measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index f41a491a8cc0..049a5ad56f65 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -2,6 +2,7 @@ /* Copyright (c) 2020 Facebook */ #include "bench.h" #include "trigger_bench.skel.h" +#include "trace_helpers.h" /* BPF triggering benchmarks */ static struct trigger_ctx { @@ -107,6 +108,101 @@ static void *trigger_consumer(void *input) return NULL; } +/* make sure call is not inlined and not avoided by compiler, so __weak and + * inline asm volatile in the body of the function + * + * There is a performance difference between uprobing at nop location vs other + * instructions. So use two different targets, one of which starts with nop + * and another doesn't. + * + * GCC doesn't generate stack setup preample for these functions due to them + * having no input arguments and doing nothing in the body. + */ +__weak void uprobe_target_with_nop(void) +{ + asm volatile ("nop"); +} + +__weak void uprobe_target_without_nop(void) +{ + asm volatile (""); +} + +static void *uprobe_base_producer(void *input) +{ + while (true) { + uprobe_target_with_nop(); + atomic_inc(&base_hits.value); + } + return NULL; +} + +static void *uprobe_producer_with_nop(void *input) +{ + while (true) + uprobe_target_with_nop(); + return NULL; +} + +static void *uprobe_producer_without_nop(void *input) +{ + while (true) + uprobe_target_without_nop(); + return NULL; +} + +static void usetup(bool use_retprobe, bool use_nop) +{ + size_t uprobe_offset; + ssize_t base_addr; + struct bpf_link *link; + + setup_libbpf(); + + ctx.skel = trigger_bench__open_and_load(); + if (!ctx.skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + base_addr = get_base_addr(); + if (use_nop) + uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop, base_addr); + else + uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop, base_addr); + + link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe, + use_retprobe, + -1 /* all PIDs */, + "/proc/self/exe", + uprobe_offset); + if (!link) { + fprintf(stderr, "failed to attach uprobe!\n"); + exit(1); + } + ctx.skel->links.bench_trigger_uprobe = link; +} + +static void uprobe_setup_with_nop() +{ + usetup(false, true); +} + +static void uretprobe_setup_with_nop() +{ + usetup(true, true); +} + +static void uprobe_setup_without_nop() +{ + usetup(false, false); +} + +static void uretprobe_setup_without_nop() +{ + usetup(true, false); +} + const struct bench bench_trig_base = { .name = "trig-base", .validate = trigger_validate, @@ -182,3 +278,53 @@ const struct bench bench_trig_fmodret = { .report_progress = hits_drops_report_progress, .report_final = hits_drops_report_final, }; + +const struct bench bench_trig_uprobe_base = { + .name = "trig-uprobe-base", + .setup = NULL, /* no uprobe/uretprobe is attached */ + .producer_thread = uprobe_base_producer, + .consumer_thread = trigger_consumer, + .measure = trigger_base_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_uprobe_with_nop = { + .name = "trig-uprobe-with-nop", + .setup = uprobe_setup_with_nop, + .producer_thread = uprobe_producer_with_nop, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_uretprobe_with_nop = { + .name = "trig-uretprobe-with-nop", + .setup = uretprobe_setup_with_nop, + .producer_thread = uprobe_producer_with_nop, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_uprobe_without_nop = { + .name = "trig-uprobe-without-nop", + .setup = uprobe_setup_without_nop, + .producer_thread = uprobe_producer_without_nop, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; + +const struct bench bench_trig_uretprobe_without_nop = { + .name = "trig-uretprobe-without-nop", + .setup = uretprobe_setup_without_nop, + .producer_thread = uprobe_producer_without_nop, + .consumer_thread = trigger_consumer, + .measure = trigger_measure, + .report_progress = hits_drops_report_progress, + .report_final = hits_drops_report_final, +}; diff --git a/tools/testing/selftests/bpf/benchs/run_bench_bpf_loop.sh b/tools/testing/selftests/bpf/benchs/run_bench_bpf_loop.sh new file mode 100755 index 000000000000..d4f5f73b356b --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/run_bench_bpf_loop.sh @@ -0,0 +1,15 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source ./benchs/run_common.sh + +set -eufo pipefail + +for t in 1 4 8 12 16; do +for i in 10 100 500 1000 5000 10000 50000 100000 500000 1000000; do +subtitle "nr_loops: $i, nr_threads: $t" + summarize_ops "bpf_loop: " \ + "$($RUN_BENCH -p $t --nr_loops $i bpf-loop)" + printf "\n" +done +done diff --git a/tools/testing/selftests/bpf/benchs/run_common.sh b/tools/testing/selftests/bpf/benchs/run_common.sh index 9a16be78b180..6c5e6023a69f 100644 --- a/tools/testing/selftests/bpf/benchs/run_common.sh +++ b/tools/testing/selftests/bpf/benchs/run_common.sh @@ -33,6 +33,14 @@ function percentage() echo "$*" | sed -E "s/.*Percentage\s=\s+([0-9]+\.[0-9]+).*/\1/" } +function ops() +{ + echo -n "throughput: " + echo -n "$*" | sed -E "s/.*throughput\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+\sM\sops\/s).*/\1/" + echo -n -e ", latency: " + echo "$*" | sed -E "s/.*latency\s+([0-9]+\.[0-9]+\sns\/op).*/\1/" +} + function total() { echo "$*" | sed -E "s/.*total operations\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/" @@ -52,6 +60,13 @@ function summarize_percentage() printf "%-20s %s%%\n" "$bench" "$(percentage $summary)" } +function summarize_ops() +{ + bench="$1" + summary=$(echo $2 | tail -n1) + printf "%-20s %s\n" "$bench" "$(ops $summary)" +} + function summarize_total() { bench="$1" diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 5d52ea2768df..df3b292a8ffe 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -33,6 +33,22 @@ noinline int bpf_testmod_loop_test(int n) return sum; } +__weak noinline struct file *bpf_testmod_return_ptr(int arg) +{ + static struct file f = {}; + + switch (arg) { + case 1: return (void *)EINVAL; /* user addr */ + case 2: return (void *)0xcafe4a11; /* user addr */ + case 3: return (void *)-EINVAL; /* canonical, but invalid */ + case 4: return (void *)(1ull << 60); /* non-canonical and invalid */ + case 5: return (void *)~(1ull << 30); /* trigger extable */ + case 6: return &f; /* valid addr */ + case 7: return (void *)((long)&f | 1); /* kernel tricks */ + default: return NULL; + } +} + noinline ssize_t bpf_testmod_test_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, @@ -43,6 +59,10 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, .off = off, .len = len, }; + int i = 1; + + while (bpf_testmod_return_ptr(i)) + i++; /* This is always true. Use the check to make sure the compiler * doesn't remove bpf_testmod_loop_test. diff --git a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c index f4d870da7684..78c76496b14a 100644 --- a/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c +++ b/tools/testing/selftests/bpf/map_tests/array_map_batch_ops.c @@ -68,13 +68,6 @@ static void map_batch_verify(int *visited, __u32 max_entries, int *keys, static void __test_map_lookup_and_update_batch(bool is_pcpu) { - struct bpf_create_map_attr xattr = { - .name = "array_map", - .map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_ARRAY : - BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(int), - .value_size = sizeof(__s64), - }; int map_fd, *keys, *visited; __u32 count, total, total_success; const __u32 max_entries = 10; @@ -86,10 +79,10 @@ static void __test_map_lookup_and_update_batch(bool is_pcpu) .flags = 0, ); - xattr.max_entries = max_entries; - map_fd = bpf_create_map_xattr(&xattr); + map_fd = bpf_map_create(is_pcpu ? BPF_MAP_TYPE_PERCPU_ARRAY : BPF_MAP_TYPE_ARRAY, + "array_map", sizeof(int), sizeof(__s64), max_entries, NULL); CHECK(map_fd == -1, - "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + "bpf_map_create()", "error:%s\n", strerror(errno)); value_size = sizeof(__s64); if (is_pcpu) diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c index 976bf415fbdd..f807d53fd8dd 100644 --- a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c +++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c @@ -83,22 +83,15 @@ void __test_map_lookup_and_delete_batch(bool is_pcpu) int err, step, value_size; bool nospace_err; void *values; - struct bpf_create_map_attr xattr = { - .name = "hash_map", - .map_type = is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH : - BPF_MAP_TYPE_HASH, - .key_size = sizeof(int), - .value_size = sizeof(int), - }; DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts, .elem_flags = 0, .flags = 0, ); - xattr.max_entries = max_entries; - map_fd = bpf_create_map_xattr(&xattr); + map_fd = bpf_map_create(is_pcpu ? BPF_MAP_TYPE_PERCPU_HASH : BPF_MAP_TYPE_HASH, + "hash_map", sizeof(int), sizeof(int), max_entries, NULL); CHECK(map_fd == -1, - "bpf_create_map_xattr()", "error:%s\n", strerror(errno)); + "bpf_map_create()", "error:%s\n", strerror(errno)); value_size = is_pcpu ? sizeof(value) : sizeof(int); keys = malloc(max_entries * sizeof(int)); diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c index 2e986e5e4cac..87d07b596e17 100644 --- a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c +++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c @@ -64,13 +64,7 @@ static void map_batch_verify(int *visited, __u32 max_entries, void test_lpm_trie_map_batch_ops(void) { - struct bpf_create_map_attr xattr = { - .name = "lpm_trie_map", - .map_type = BPF_MAP_TYPE_LPM_TRIE, - .key_size = sizeof(struct test_lpm_key), - .value_size = sizeof(int), - .map_flags = BPF_F_NO_PREALLOC, - }; + LIBBPF_OPTS(bpf_map_create_opts, create_opts, .map_flags = BPF_F_NO_PREALLOC); struct test_lpm_key *keys, key; int map_fd, *values, *visited; __u32 step, count, total, total_success; @@ -82,9 +76,10 @@ void test_lpm_trie_map_batch_ops(void) .flags = 0, ); - xattr.max_entries = max_entries; - map_fd = bpf_create_map_xattr(&xattr); - CHECK(map_fd == -1, "bpf_create_map_xattr()", "error:%s\n", + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie_map", + sizeof(struct test_lpm_key), sizeof(int), + max_entries, &create_opts); + CHECK(map_fd == -1, "bpf_map_create()", "error:%s\n", strerror(errno)); keys = malloc(max_entries * sizeof(struct test_lpm_key)); diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c index e569edc679d8..099eb4dfd4f7 100644 --- a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c +++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c @@ -19,16 +19,12 @@ #include <test_btf.h> #include <test_maps.h> -static struct bpf_create_map_attr xattr = { - .name = "sk_storage_map", - .map_type = BPF_MAP_TYPE_SK_STORAGE, - .map_flags = BPF_F_NO_PREALLOC, - .max_entries = 0, - .key_size = 4, - .value_size = 8, +static struct bpf_map_create_opts map_opts = { + .sz = sizeof(map_opts), .btf_key_type_id = 1, .btf_value_type_id = 3, .btf_fd = -1, + .map_flags = BPF_F_NO_PREALLOC, }; static unsigned int nr_sk_threads_done; @@ -140,7 +136,7 @@ static int load_btf(void) memcpy(raw_btf + sizeof(btf_hdr) + sizeof(btf_raw_types), btf_str_sec, sizeof(btf_str_sec)); - return bpf_load_btf(raw_btf, sizeof(raw_btf), 0, 0, 0); + return bpf_btf_load(raw_btf, sizeof(raw_btf), NULL); } static int create_sk_storage_map(void) @@ -150,13 +146,13 @@ static int create_sk_storage_map(void) btf_fd = load_btf(); CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n", btf_fd, errno); - xattr.btf_fd = btf_fd; + map_opts.btf_fd = btf_fd; - map_fd = bpf_create_map_xattr(&xattr); - xattr.btf_fd = -1; + map_fd = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &map_opts); + map_opts.btf_fd = -1; close(btf_fd); CHECK(map_fd == -1, - "bpf_create_map_xattr()", "errno:%d\n", errno); + "bpf_map_create()", "errno:%d\n", errno); return map_fd; } @@ -463,20 +459,20 @@ static void test_sk_storage_map_basic(void) int cnt; int lock; } value = { .cnt = 0xeB9f, .lock = 0, }, lookup_value; - struct bpf_create_map_attr bad_xattr; + struct bpf_map_create_opts bad_xattr; int btf_fd, map_fd, sk_fd, err; btf_fd = load_btf(); CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n", btf_fd, errno); - xattr.btf_fd = btf_fd; + map_opts.btf_fd = btf_fd; sk_fd = socket(AF_INET6, SOCK_STREAM, 0); CHECK(sk_fd == -1, "socket()", "sk_fd:%d errno:%d\n", sk_fd, errno); - map_fd = bpf_create_map_xattr(&xattr); - CHECK(map_fd == -1, "bpf_create_map_xattr(good_xattr)", + map_fd = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &map_opts); + CHECK(map_fd == -1, "bpf_map_create(good_xattr)", "map_fd:%d errno:%d\n", map_fd, errno); /* Add new elem */ @@ -560,31 +556,29 @@ static void test_sk_storage_map_basic(void) CHECK(!err || errno != ENOENT, "bpf_map_delete_elem()", "err:%d errno:%d\n", err, errno); - memcpy(&bad_xattr, &xattr, sizeof(xattr)); + memcpy(&bad_xattr, &map_opts, sizeof(map_opts)); bad_xattr.btf_key_type_id = 0; - err = bpf_create_map_xattr(&bad_xattr); - CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &bad_xattr); + CHECK(!err || errno != EINVAL, "bpf_map_create(bad_xattr)", "err:%d errno:%d\n", err, errno); - memcpy(&bad_xattr, &xattr, sizeof(xattr)); + memcpy(&bad_xattr, &map_opts, sizeof(map_opts)); bad_xattr.btf_key_type_id = 3; - err = bpf_create_map_xattr(&bad_xattr); - CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &bad_xattr); + CHECK(!err || errno != EINVAL, "bpf_map_create(bad_xattr)", "err:%d errno:%d\n", err, errno); - memcpy(&bad_xattr, &xattr, sizeof(xattr)); - bad_xattr.max_entries = 1; - err = bpf_create_map_xattr(&bad_xattr); - CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", + err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 1, &map_opts); + CHECK(!err || errno != EINVAL, "bpf_map_create(bad_xattr)", "err:%d errno:%d\n", err, errno); - memcpy(&bad_xattr, &xattr, sizeof(xattr)); + memcpy(&bad_xattr, &map_opts, sizeof(map_opts)); bad_xattr.map_flags = 0; - err = bpf_create_map_xattr(&bad_xattr); + err = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "sk_storage_map", 4, 8, 0, &bad_xattr); CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)", "err:%d errno:%d\n", err, errno); - xattr.btf_fd = -1; + map_opts.btf_fd = -1; close(btf_fd); close(map_fd); close(sk_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c index 0f9525293881..86b7d5d84eec 100644 --- a/tools/testing/selftests/bpf/prog_tests/atomics.c +++ b/tools/testing/selftests/bpf/prog_tests/atomics.c @@ -167,7 +167,7 @@ static void test_cmpxchg(struct atomics_lskel *skel) prog_fd = skel->progs.cmpxchg.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run add", + if (CHECK(err || retval, "test_run cmpxchg", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) goto cleanup; @@ -196,7 +196,7 @@ static void test_xchg(struct atomics_lskel *skel) prog_fd = skel->progs.xchg.prog_fd; err = bpf_prog_test_run(prog_fd, 1, NULL, 0, NULL, NULL, &retval, &duration); - if (CHECK(err || retval, "test_run add", + if (CHECK(err || retval, "test_run xchg", "err %d errno %d retval %d duration %d\n", err, errno, retval, duration)) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c index be73e3de6668..d2d9e965eba5 100644 --- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c +++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c @@ -7,32 +7,33 @@ static void test_fail_cases(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts); __u32 value; int fd, err; /* Invalid key size */ - fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 4, sizeof(value), 100, 0); - if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid key size")) + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 4, sizeof(value), 100, NULL); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid key size")) close(fd); /* Invalid value size */ - fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, 0, 100, 0); - if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid value size 0")) + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, 0, 100, NULL); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value size 0")) close(fd); /* Invalid max entries size */ - fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 0, 0); - if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid max entries size")) + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 0, NULL); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid max entries size")) close(fd); /* Bloom filter maps do not support BPF_F_NO_PREALLOC */ - fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100, - BPF_F_NO_PREALLOC); - if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid flags")) + opts.map_flags = BPF_F_NO_PREALLOC; + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, &opts); + if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid flags")) close(fd); - fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100, 0); - if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter")) + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, NULL); + if (!ASSERT_GE(fd, 0, "bpf_map_create bloom filter")) return; /* Test invalid flags */ @@ -56,13 +57,14 @@ static void test_fail_cases(void) static void test_success_cases(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts); char value[11]; int fd, err; /* Create a map */ - fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100, - BPF_F_ZERO_SEED | BPF_F_NUMA_NODE); - if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter success case")) + opts.map_flags = BPF_F_ZERO_SEED | BPF_F_NUMA_NODE; + fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, &opts); + if (!ASSERT_GE(fd, 0, "bpf_map_create bloom filter success case")) return; /* Add a value to the bloom filter */ @@ -100,9 +102,9 @@ static void test_inner_map(struct bloom_filter_map *skel, const __u32 *rand_vals struct bpf_link *link; /* Create a bloom filter map that will be used as the inner map */ - inner_map_fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(*rand_vals), - nr_rand_vals, 0); - if (!ASSERT_GE(inner_map_fd, 0, "bpf_create_map bloom filter inner map")) + inner_map_fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(*rand_vals), + nr_rand_vals, NULL); + if (!ASSERT_GE(inner_map_fd, 0, "bpf_map_create bloom filter inner map")) return; for (i = 0; i < nr_rand_vals; i++) { diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 3e10abce3e5a..b84f859b1267 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -469,12 +469,12 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) * fills seq_file buffer and then the other will trigger * overflow and needs restart. */ - map1_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); - if (CHECK(map1_fd < 0, "bpf_create_map", + map1_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); + if (CHECK(map1_fd < 0, "bpf_map_create", "map_creation failed: %s\n", strerror(errno))) goto out; - map2_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); - if (CHECK(map2_fd < 0, "bpf_create_map", + map2_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); + if (CHECK(map2_fd < 0, "bpf_map_create", "map_creation failed: %s\n", strerror(errno))) goto free_map1; @@ -1206,13 +1206,14 @@ static void test_task_vma(void) goto out; /* Read CMP_BUFFER_SIZE (1kB) from bpf_iter. Read in small chunks - * to trigger seq_file corner cases. The expected output is much - * longer than 1kB, so the while loop will terminate. + * to trigger seq_file corner cases. */ len = 0; while (len < CMP_BUFFER_SIZE) { err = read_fd_into_buffer(iter_fd, task_vma_output + len, min(read_size, CMP_BUFFER_SIZE - len)); + if (!err) + break; if (CHECK(err < 0, "read_iter_fd", "read_iter_fd failed\n")) goto out; len += err; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_loop.c b/tools/testing/selftests/bpf/prog_tests/bpf_loop.c new file mode 100644 index 000000000000..380d7a2072e3 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/bpf_loop.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <test_progs.h> +#include <network_helpers.h> +#include "bpf_loop.skel.h" + +static void check_nr_loops(struct bpf_loop *skel) +{ + struct bpf_link *link; + + link = bpf_program__attach(skel->progs.test_prog); + if (!ASSERT_OK_PTR(link, "link")) + return; + + /* test 0 loops */ + skel->bss->nr_loops = 0; + + usleep(1); + + ASSERT_EQ(skel->bss->nr_loops_returned, skel->bss->nr_loops, + "0 loops"); + + /* test 500 loops */ + skel->bss->nr_loops = 500; + + usleep(1); + + ASSERT_EQ(skel->bss->nr_loops_returned, skel->bss->nr_loops, + "500 loops"); + ASSERT_EQ(skel->bss->g_output, (500 * 499) / 2, "g_output"); + + /* test exceeding the max limit */ + skel->bss->nr_loops = -1; + + usleep(1); + + ASSERT_EQ(skel->bss->err, -E2BIG, "over max limit"); + + bpf_link__destroy(link); +} + +static void check_callback_fn_stop(struct bpf_loop *skel) +{ + struct bpf_link *link; + + link = bpf_program__attach(skel->progs.test_prog); + if (!ASSERT_OK_PTR(link, "link")) + return; + + /* testing that loop is stopped when callback_fn returns 1 */ + skel->bss->nr_loops = 400; + skel->data->stop_index = 50; + + usleep(1); + + ASSERT_EQ(skel->bss->nr_loops_returned, skel->data->stop_index + 1, + "nr_loops_returned"); + ASSERT_EQ(skel->bss->g_output, (50 * 49) / 2, + "g_output"); + + bpf_link__destroy(link); +} + +static void check_null_callback_ctx(struct bpf_loop *skel) +{ + struct bpf_link *link; + + /* check that user is able to pass in a null callback_ctx */ + link = bpf_program__attach(skel->progs.prog_null_ctx); + if (!ASSERT_OK_PTR(link, "link")) + return; + + skel->bss->nr_loops = 10; + + usleep(1); + + ASSERT_EQ(skel->bss->nr_loops_returned, skel->bss->nr_loops, + "nr_loops_returned"); + + bpf_link__destroy(link); +} + +static void check_invalid_flags(struct bpf_loop *skel) +{ + struct bpf_link *link; + + /* check that passing in non-zero flags returns -EINVAL */ + link = bpf_program__attach(skel->progs.prog_invalid_flags); + if (!ASSERT_OK_PTR(link, "link")) + return; + + usleep(1); + + ASSERT_EQ(skel->bss->err, -EINVAL, "err"); + + bpf_link__destroy(link); +} + +static void check_nested_calls(struct bpf_loop *skel) +{ + __u32 nr_loops = 100, nested_callback_nr_loops = 4; + struct bpf_link *link; + + /* check that nested calls are supported */ + link = bpf_program__attach(skel->progs.prog_nested_calls); + if (!ASSERT_OK_PTR(link, "link")) + return; + + skel->bss->nr_loops = nr_loops; + skel->bss->nested_callback_nr_loops = nested_callback_nr_loops; + + usleep(1); + + ASSERT_EQ(skel->bss->nr_loops_returned, nr_loops * nested_callback_nr_loops + * nested_callback_nr_loops, "nr_loops_returned"); + ASSERT_EQ(skel->bss->g_output, (4 * 3) / 2 * nested_callback_nr_loops + * nr_loops, "g_output"); + + bpf_link__destroy(link); +} + +void test_bpf_loop(void) +{ + struct bpf_loop *skel; + + skel = bpf_loop__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_loop__open_and_load")) + return; + + skel->bss->pid = getpid(); + + if (test__start_subtest("check_nr_loops")) + check_nr_loops(skel); + if (test__start_subtest("check_callback_fn_stop")) + check_callback_fn_stop(skel); + if (test__start_subtest("check_null_callback_ctx")) + check_null_callback_ctx(skel); + if (test__start_subtest("check_invalid_flags")) + check_invalid_flags(skel); + if (test__start_subtest("check_nested_calls")) + check_nested_calls(skel); + + bpf_loop__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index 94e03df69d71..8daca0ac909f 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -217,14 +217,16 @@ static bool found; static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { - char *log_buf; + const char *log_buf; if (level != LIBBPF_WARN || - strcmp(format, "libbpf: \n%s\n")) { + !strstr(format, "-- BEGIN PROG LOAD LOG --")) { vprintf(format, args); return 0; } + /* skip prog_name */ + va_arg(args, char *); log_buf = va_arg(args, char *); if (!log_buf) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c index 27f5d8ea7964..ff6cce9fef06 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c @@ -19,16 +19,28 @@ extern int extra_prog_load_log_flags; static int check_load(const char *file, enum bpf_prog_type type) { - struct bpf_prog_load_attr attr; struct bpf_object *obj = NULL; - int err, prog_fd; - - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = file; - attr.prog_type = type; - attr.log_level = 4 | extra_prog_load_log_flags; - attr.prog_flags = BPF_F_TEST_RND_HI32; - err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + struct bpf_program *prog; + int err; + + obj = bpf_object__open_file(file, NULL); + err = libbpf_get_error(obj); + if (err) + return err; + + prog = bpf_object__next_program(obj, NULL); + if (!prog) { + err = -ENOENT; + goto err_out; + } + + bpf_program__set_type(prog, type); + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); + bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags); + + err = bpf_object__load(obj); + +err_out: bpf_object__close(obj); return err; } @@ -115,6 +127,12 @@ void test_verif_scale_pyperf600() scale_test("pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); } +void test_verif_scale_pyperf600_bpf_loop(void) +{ + /* use the bpf_loop helper*/ + scale_test("pyperf600_bpf_loop.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + void test_verif_scale_pyperf600_nounroll() { /* no unroll at all. @@ -165,6 +183,12 @@ void test_verif_scale_strobemeta() scale_test("strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); } +void test_verif_scale_strobemeta_bpf_loop(void) +{ + /* use the bpf_loop helper*/ + scale_test("strobemeta_bpf_loop.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false); +} + void test_verif_scale_strobemeta_nounroll1() { /* no unroll, tiny loops */ diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 4aa6343dc4c8..01b776a7beeb 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -4071,10 +4071,32 @@ done: return raw_btf; } +static int load_raw_btf(const void *raw_data, size_t raw_size) +{ + LIBBPF_OPTS(bpf_btf_load_opts, opts); + int btf_fd; + + if (always_log) { + opts.log_buf = btf_log_buf, + opts.log_size = BTF_LOG_BUF_SIZE, + opts.log_level = 1; + } + + btf_fd = bpf_btf_load(raw_data, raw_size, &opts); + if (btf_fd < 0 && !always_log) { + opts.log_buf = btf_log_buf, + opts.log_size = BTF_LOG_BUF_SIZE, + opts.log_level = 1; + btf_fd = bpf_btf_load(raw_data, raw_size, &opts); + } + + return btf_fd; +} + static void do_test_raw(unsigned int test_num) { struct btf_raw_test *test = &raw_tests[test_num - 1]; - struct bpf_create_map_attr create_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts); int map_fd = -1, btf_fd = -1; unsigned int raw_btf_size; struct btf_header *hdr; @@ -4100,16 +4122,14 @@ static void do_test_raw(unsigned int test_num) hdr->str_len = (int)hdr->str_len + test->str_len_delta; *btf_log_buf = '\0'; - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); free(raw_btf); err = ((btf_fd < 0) != test->btf_load_err); if (CHECK(err, "btf_fd:%d test->btf_load_err:%u", btf_fd, test->btf_load_err) || CHECK(test->err_str && !strstr(btf_log_buf, test->err_str), - "expected err_str:%s", test->err_str)) { + "expected err_str:%s\n", test->err_str)) { err = -1; goto done; } @@ -4117,16 +4137,11 @@ static void do_test_raw(unsigned int test_num) if (err || btf_fd < 0) goto done; - create_attr.name = test->map_name; - create_attr.map_type = test->map_type; - create_attr.key_size = test->key_size; - create_attr.value_size = test->value_size; - create_attr.max_entries = test->max_entries; - create_attr.btf_fd = btf_fd; - create_attr.btf_key_type_id = test->key_type_id; - create_attr.btf_value_type_id = test->value_type_id; - - map_fd = bpf_create_map_xattr(&create_attr); + opts.btf_fd = btf_fd; + opts.btf_key_type_id = test->key_type_id; + opts.btf_value_type_id = test->value_type_id; + map_fd = bpf_map_create(test->map_type, test->map_name, + test->key_size, test->value_size, test->max_entries, &opts); err = ((map_fd < 0) != test->map_create_err); CHECK(err, "map_fd:%d test->map_create_err:%u", @@ -4232,9 +4247,7 @@ static int test_big_btf_info(unsigned int test_num) goto done; } - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); if (CHECK(btf_fd < 0, "errno:%d", errno)) { err = -1; goto done; @@ -4290,7 +4303,7 @@ done: static int test_btf_id(unsigned int test_num) { const struct btf_get_info_test *test = &get_info_tests[test_num - 1]; - struct bpf_create_map_attr create_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts); uint8_t *raw_btf = NULL, *user_btf[2] = {}; int btf_fd[2] = {-1, -1}, map_fd = -1; struct bpf_map_info map_info = {}; @@ -4320,9 +4333,7 @@ static int test_btf_id(unsigned int test_num) info[i].btf_size = raw_btf_size; } - btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd[0] = load_raw_btf(raw_btf, raw_btf_size); if (CHECK(btf_fd[0] < 0, "errno:%d", errno)) { err = -1; goto done; @@ -4355,16 +4366,11 @@ static int test_btf_id(unsigned int test_num) } /* Test btf members in struct bpf_map_info */ - create_attr.name = "test_btf_id"; - create_attr.map_type = BPF_MAP_TYPE_ARRAY; - create_attr.key_size = sizeof(int); - create_attr.value_size = sizeof(unsigned int); - create_attr.max_entries = 4; - create_attr.btf_fd = btf_fd[0]; - create_attr.btf_key_type_id = 1; - create_attr.btf_value_type_id = 2; - - map_fd = bpf_create_map_xattr(&create_attr); + opts.btf_fd = btf_fd[0]; + opts.btf_key_type_id = 1; + opts.btf_value_type_id = 2; + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "test_btf_id", + sizeof(int), sizeof(int), 4, &opts); if (CHECK(map_fd < 0, "errno:%d", errno)) { err = -1; goto done; @@ -4457,9 +4463,7 @@ static void do_test_get_info(unsigned int test_num) goto done; } - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); if (CHECK(btf_fd <= 0, "errno:%d", errno)) { err = -1; goto done; @@ -5153,7 +5157,7 @@ static void do_test_pprint(int test_num) { const struct btf_raw_test *test = &pprint_test_template[test_num]; enum pprint_mapv_kind_t mapv_kind = test->mapv_kind; - struct bpf_create_map_attr create_attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts); bool ordered_map, lossless_map, percpu_map; int err, ret, num_cpus, rounded_value_size; unsigned int key, nr_read_elems; @@ -5179,26 +5183,19 @@ static void do_test_pprint(int test_num) return; *btf_log_buf = '\0'; - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); free(raw_btf); - if (CHECK(btf_fd < 0, "errno:%d", errno)) { + if (CHECK(btf_fd < 0, "errno:%d\n", errno)) { err = -1; goto done; } - create_attr.name = test->map_name; - create_attr.map_type = test->map_type; - create_attr.key_size = test->key_size; - create_attr.value_size = test->value_size; - create_attr.max_entries = test->max_entries; - create_attr.btf_fd = btf_fd; - create_attr.btf_key_type_id = test->key_type_id; - create_attr.btf_value_type_id = test->value_type_id; - - map_fd = bpf_create_map_xattr(&create_attr); + opts.btf_fd = btf_fd; + opts.btf_key_type_id = test->key_type_id; + opts.btf_value_type_id = test->value_type_id; + map_fd = bpf_map_create(test->map_type, test->map_name, + test->key_size, test->value_size, test->max_entries, &opts); if (CHECK(map_fd < 0, "errno:%d", errno)) { err = -1; goto done; @@ -6553,9 +6550,7 @@ static void do_test_info_raw(unsigned int test_num) return; *btf_log_buf = '\0'; - btf_fd = bpf_load_btf(raw_btf, raw_btf_size, - btf_log_buf, BTF_LOG_BUF_SIZE, - always_log); + btf_fd = load_raw_btf(raw_btf, raw_btf_size); free(raw_btf); if (CHECK(btf_fd < 0, "invalid btf_fd errno:%d", errno)) { @@ -7352,6 +7347,32 @@ static struct btf_dedup_test dedup_tests[] = { BTF_STR_SEC("\0tag1"), }, }, +{ + .descr = "dedup: btf_type_tag #5, struct", + .input = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_ENC(NAME_NTH(2), BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 1), 4), /* [3] */ + BTF_MEMBER_ENC(NAME_NTH(3), 2, BTF_MEMBER_OFFSET(0, 0)), + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [4] */ + BTF_TYPE_ENC(NAME_NTH(2), BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 1), 4), /* [5] */ + BTF_MEMBER_ENC(NAME_NTH(3), 4, BTF_MEMBER_OFFSET(0, 0)), + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0t\0m"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_TAG_ENC(NAME_NTH(1), 1), /* [2] */ + BTF_TYPE_ENC(NAME_NTH(2), BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 1), 4), /* [3] */ + BTF_MEMBER_ENC(NAME_NTH(3), 2, BTF_MEMBER_OFFSET(0, 0)), + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1\0t\0m"), + }, +}, }; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c index 9d3b8d7a1537..90aac437576d 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c @@ -314,6 +314,117 @@ cleanup: btf__free(btf1); } +static void btf_add_dup_struct_in_cu(struct btf *btf, int start_id) +{ +#define ID(n) (start_id + n) + btf__set_pointer_size(btf, 8); /* enforce 64-bit arch */ + + btf__add_int(btf, "int", 4, BTF_INT_SIGNED); /* [1] int */ + + btf__add_struct(btf, "s", 8); /* [2] struct s { */ + btf__add_field(btf, "a", ID(3), 0, 0); /* struct anon a; */ + btf__add_field(btf, "b", ID(4), 0, 0); /* struct anon b; */ + /* } */ + + btf__add_struct(btf, "(anon)", 8); /* [3] struct anon { */ + btf__add_field(btf, "f1", ID(1), 0, 0); /* int f1; */ + btf__add_field(btf, "f2", ID(1), 32, 0); /* int f2; */ + /* } */ + + btf__add_struct(btf, "(anon)", 8); /* [4] struct anon { */ + btf__add_field(btf, "f1", ID(1), 0, 0); /* int f1; */ + btf__add_field(btf, "f2", ID(1), 32, 0); /* int f2; */ + /* } */ +#undef ID +} + +static void test_split_dup_struct_in_cu() +{ + struct btf *btf1, *btf2 = NULL; + int err; + + /* generate the base data.. */ + btf1 = btf__new_empty(); + if (!ASSERT_OK_PTR(btf1, "empty_main_btf")) + return; + + btf_add_dup_struct_in_cu(btf1, 0); + + VALIDATE_RAW_BTF( + btf1, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=3 bits_offset=0\n" + "\t'b' type_id=4 bits_offset=0", + "[3] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32", + "[4] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32"); + + /* ..dedup them... */ + err = btf__dedup(btf1, NULL); + if (!ASSERT_OK(err, "btf_dedup")) + goto cleanup; + + VALIDATE_RAW_BTF( + btf1, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=3 bits_offset=0\n" + "\t'b' type_id=3 bits_offset=0", + "[3] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32"); + + /* and add the same data on top of it */ + btf2 = btf__new_empty_split(btf1); + if (!ASSERT_OK_PTR(btf2, "empty_split_btf")) + goto cleanup; + + btf_add_dup_struct_in_cu(btf2, 3); + + VALIDATE_RAW_BTF( + btf2, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=3 bits_offset=0\n" + "\t'b' type_id=3 bits_offset=0", + "[3] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32", + "[4] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[5] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=6 bits_offset=0\n" + "\t'b' type_id=7 bits_offset=0", + "[6] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=4 bits_offset=0\n" + "\t'f2' type_id=4 bits_offset=32", + "[7] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=4 bits_offset=0\n" + "\t'f2' type_id=4 bits_offset=32"); + + err = btf__dedup(btf2, NULL); + if (!ASSERT_OK(err, "btf_dedup")) + goto cleanup; + + /* after dedup it should match the original data */ + VALIDATE_RAW_BTF( + btf2, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's' size=8 vlen=2\n" + "\t'a' type_id=3 bits_offset=0\n" + "\t'b' type_id=3 bits_offset=0", + "[3] STRUCT '(anon)' size=8 vlen=2\n" + "\t'f1' type_id=1 bits_offset=0\n" + "\t'f2' type_id=1 bits_offset=32"); + +cleanup: + btf__free(btf2); + btf__free(btf1); +} + void test_btf_dedup_split() { if (test__start_subtest("split_simple")) @@ -322,4 +433,6 @@ void test_btf_dedup_split() test_split_struct_duped(); if (test__start_subtest("split_fwd_resolve")) test_split_fwd_resolve(); + if (test__start_subtest("split_dup_struct_in_cu")) + test_split_dup_struct_in_cu(); } diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index d6272013a5a3..9e26903f9170 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -323,7 +323,7 @@ static void test_btf_dump_int_data(struct btf *btf, struct btf_dump *d, char *str) { #ifdef __SIZEOF_INT128__ - __int128 i = 0xffffffffffffffff; + unsigned __int128 i = 0xffffffffffffffff; /* this dance is required because we cannot directly initialize * a 128-bit value to anything larger than a 64-bit value. @@ -756,7 +756,7 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d, /* overflow bpf_sock_ops struct with final element nonzero/zero. * Regardless of the value of the final field, we don't have all the * data we need to display it, so we should trigger an overflow. - * In other words oveflow checking should trump "is field zero?" + * In other words overflow checking should trump "is field zero?" * checks because if we've overflowed, it shouldn't matter what the * field is - we can't trust its value so shouldn't display it. */ diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c index 762f6a9da8b5..664ffc0364f4 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c @@ -90,7 +90,7 @@ static void print_err_line(void) static void test_conn(void) { - int listen_fd = -1, cli_fd = -1, err; + int listen_fd = -1, cli_fd = -1, srv_fd = -1, err; socklen_t addrlen = sizeof(srv_sa6); int srv_port; @@ -112,6 +112,10 @@ static void test_conn(void) if (CHECK_FAIL(cli_fd == -1)) goto done; + srv_fd = accept(listen_fd, NULL, NULL); + if (CHECK_FAIL(srv_fd == -1)) + goto done; + if (CHECK(skel->bss->listen_tp_sport != srv_port || skel->bss->req_sk_sport != srv_port, "Unexpected sk src port", @@ -134,11 +138,13 @@ done: close(listen_fd); if (cli_fd != -1) close(cli_fd); + if (srv_fd != -1) + close(srv_fd); } static void test_syncookie(void) { - int listen_fd = -1, cli_fd = -1, err; + int listen_fd = -1, cli_fd = -1, srv_fd = -1, err; socklen_t addrlen = sizeof(srv_sa6); int srv_port; @@ -161,6 +167,10 @@ static void test_syncookie(void) if (CHECK_FAIL(cli_fd == -1)) goto done; + srv_fd = accept(listen_fd, NULL, NULL); + if (CHECK_FAIL(srv_fd == -1)) + goto done; + if (CHECK(skel->bss->listen_tp_sport != srv_port, "Unexpected tp src port", "listen_tp_sport:%u expected:%u\n", @@ -188,6 +198,8 @@ done: close(listen_fd); if (cli_fd != -1) close(cli_fd); + if (srv_fd != -1) + close(srv_fd); } struct test { diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c index de9c3e12b0ea..d3e8f729c623 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c @@ -15,22 +15,22 @@ static int prog_load_cnt(int verdict, int val) int cgroup_storage_fd, percpu_cgroup_storage_fd; if (map_fd < 0) - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); if (map_fd < 0) { printf("failed to create map '%s'\n", strerror(errno)); return -1; } - cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + cgroup_storage_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_STORAGE, NULL, + sizeof(struct bpf_cgroup_storage_key), 8, 0, NULL); if (cgroup_storage_fd < 0) { printf("failed to create map '%s'\n", strerror(errno)); return -1; } - percpu_cgroup_storage_fd = bpf_create_map( - BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - sizeof(struct bpf_cgroup_storage_key), 8, 0, 0); + percpu_cgroup_storage_fd = bpf_map_create( + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, NULL, + sizeof(struct bpf_cgroup_storage_key), 8, 0, NULL); if (percpu_cgroup_storage_fd < 0) { printf("failed to create map '%s'\n", strerror(errno)); return -1; diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c index 9229db2f5ca5..ca574e1e30e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c +++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c @@ -51,19 +51,20 @@ static int run_test(int cgroup_fd, int server_fd, int family, int type) bool v4 = family == AF_INET; __u16 expected_local_port = v4 ? 22222 : 22223; __u16 expected_peer_port = 60000; - struct bpf_prog_load_attr attr = { - .file = v4 ? "./connect_force_port4.o" : - "./connect_force_port6.o", - }; struct bpf_program *prog; struct bpf_object *obj; - int xlate_fd, fd, err; + const char *obj_file = v4 ? "connect_force_port4.o" : "connect_force_port6.o"; + int fd, err; __u32 duration = 0; - err = bpf_prog_load_xattr(&attr, &obj, &xlate_fd); - if (err) { - log_err("Failed to load BPF object"); + obj = bpf_object__open_file(obj_file, NULL); + if (!ASSERT_OK_PTR(obj, "bpf_obj_open")) return -1; + + err = bpf_object__load(obj); + if (!ASSERT_OK(err, "bpf_obj_load")) { + err = -EIO; + goto close_bpf_object; } prog = bpf_object__find_program_by_title(obj, v4 ? diff --git a/tools/testing/selftests/bpf/prog_tests/core_kern.c b/tools/testing/selftests/bpf/prog_tests/core_kern.c new file mode 100644 index 000000000000..561c5185d886 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/core_kern.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "test_progs.h" +#include "core_kern.lskel.h" + +void test_core_kern_lskel(void) +{ + struct core_kern_lskel *skel; + + skel = core_kern_lskel__open_and_load(); + ASSERT_OK_PTR(skel, "open_and_load"); + core_kern_lskel__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 1041d0c593f6..44a9868c70ea 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -881,7 +881,8 @@ void test_core_reloc(void) data = mmap_data; memset(mmap_data, 0, sizeof(*data)); - memcpy(data->in, test_case->input, test_case->input_len); + if (test_case->input_len) + memcpy(data->in, test_case->input, test_case->input_len); data->my_pid_tgid = my_pid_tgid; link = bpf_program__attach_raw_tracepoint(prog, tp_name); diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c index 4184c399d4c6..977ab433a946 100644 --- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c +++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c @@ -24,13 +24,19 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) { bool good_kern_stack = false, good_user_stack = false; const char *nonjit_func = "___bpf_prog_run"; - struct get_stack_trace_t *e = data; + /* perfbuf-submitted data is 4-byte aligned, but we need 8-byte + * alignment, so copy data into a local variable, for simplicity + */ + struct get_stack_trace_t e; int i, num_stack; static __u64 cnt; struct ksym *ks; cnt++; + memset(&e, 0, sizeof(e)); + memcpy(&e, data, size <= sizeof(e) ? size : sizeof(e)); + if (size < sizeof(struct get_stack_trace_t)) { __u64 *raw_data = data; bool found = false; @@ -57,19 +63,19 @@ static void get_stack_print_output(void *ctx, int cpu, void *data, __u32 size) good_user_stack = true; } } else { - num_stack = e->kern_stack_size / sizeof(__u64); + num_stack = e.kern_stack_size / sizeof(__u64); if (env.jit_enabled) { good_kern_stack = num_stack > 0; } else { for (i = 0; i < num_stack; i++) { - ks = ksym_search(e->kern_stack[i]); + ks = ksym_search(e.kern_stack[i]); if (ks && (strcmp(ks->name, nonjit_func) == 0)) { good_kern_stack = true; break; } } } - if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0) + if (e.user_stack_size > 0 && e.user_stack_buildid_size > 0) good_user_stack = true; } diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index 2a49f8fcde06..ce10d2fc3a6c 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> #include <network_helpers.h> +#include "kfree_skb.skel.h" struct meta { int ifindex; @@ -58,16 +59,11 @@ void serial_test_kfree_skb(void) .ctx_in = &skb, .ctx_size_in = sizeof(skb), }; - struct bpf_prog_load_attr attr = { - .file = "./kfree_skb.o", - }; - - struct bpf_link *link = NULL, *link_fentry = NULL, *link_fexit = NULL; - struct bpf_map *perf_buf_map, *global_data; - struct bpf_program *prog, *fentry, *fexit; - struct bpf_object *obj, *obj2 = NULL; + struct kfree_skb *skel = NULL; + struct bpf_link *link; + struct bpf_object *obj; struct perf_buffer *pb = NULL; - int err, kfree_skb_fd; + int err; bool passed = false; __u32 duration = 0; const int zero = 0; @@ -78,40 +74,27 @@ void serial_test_kfree_skb(void) if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno)) return; - err = bpf_prog_load_xattr(&attr, &obj2, &kfree_skb_fd); - if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) - goto close_prog; - - prog = bpf_object__find_program_by_title(obj2, "tp_btf/kfree_skb"); - if (CHECK(!prog, "find_prog", "prog kfree_skb not found\n")) - goto close_prog; - fentry = bpf_object__find_program_by_title(obj2, "fentry/eth_type_trans"); - if (CHECK(!fentry, "find_prog", "prog eth_type_trans not found\n")) - goto close_prog; - fexit = bpf_object__find_program_by_title(obj2, "fexit/eth_type_trans"); - if (CHECK(!fexit, "find_prog", "prog eth_type_trans not found\n")) - goto close_prog; - - global_data = bpf_object__find_map_by_name(obj2, ".bss"); - if (CHECK(!global_data, "find global data", "not found\n")) + skel = kfree_skb__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kfree_skb_skel")) goto close_prog; - link = bpf_program__attach_raw_tracepoint(prog, NULL); + link = bpf_program__attach_raw_tracepoint(skel->progs.trace_kfree_skb, NULL); if (!ASSERT_OK_PTR(link, "attach_raw_tp")) goto close_prog; - link_fentry = bpf_program__attach_trace(fentry); - if (!ASSERT_OK_PTR(link_fentry, "attach fentry")) - goto close_prog; - link_fexit = bpf_program__attach_trace(fexit); - if (!ASSERT_OK_PTR(link_fexit, "attach fexit")) + skel->links.trace_kfree_skb = link; + + link = bpf_program__attach_trace(skel->progs.fentry_eth_type_trans); + if (!ASSERT_OK_PTR(link, "attach fentry")) goto close_prog; + skel->links.fentry_eth_type_trans = link; - perf_buf_map = bpf_object__find_map_by_name(obj2, "perf_buf_map"); - if (CHECK(!perf_buf_map, "find_perf_buf_map", "not found\n")) + link = bpf_program__attach_trace(skel->progs.fexit_eth_type_trans); + if (!ASSERT_OK_PTR(link, "attach fexit")) goto close_prog; + skel->links.fexit_eth_type_trans = link; /* set up perf buffer */ - pb = perf_buffer__new(bpf_map__fd(perf_buf_map), 1, + pb = perf_buffer__new(bpf_map__fd(skel->maps.perf_buf_map), 1, on_sample, NULL, &passed, NULL); if (!ASSERT_OK_PTR(pb, "perf_buf__new")) goto close_prog; @@ -133,7 +116,7 @@ void serial_test_kfree_skb(void) */ ASSERT_TRUE(passed, "passed"); - err = bpf_map_lookup_elem(bpf_map__fd(global_data), &zero, test_ok); + err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.bss), &zero, test_ok); if (CHECK(err, "get_result", "failed to get output data: %d\n", err)) goto close_prog; @@ -141,9 +124,6 @@ void serial_test_kfree_skb(void) CHECK_FAIL(!test_ok[0] || !test_ok[1]); close_prog: perf_buffer__free(pb); - bpf_link__destroy(link); - bpf_link__destroy(link_fentry); - bpf_link__destroy(link_fexit); bpf_object__close(obj); - bpf_object__close(obj2); + kfree_skb__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 5c9c0176991b..7d7445ccc141 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -4,6 +4,7 @@ #include <network_helpers.h> #include "kfunc_call_test.lskel.h" #include "kfunc_call_test_subprog.skel.h" +#include "kfunc_call_test_subprog.lskel.h" static void test_main(void) { @@ -49,6 +50,26 @@ static void test_subprog(void) kfunc_call_test_subprog__destroy(skel); } +static void test_subprog_lskel(void) +{ + struct kfunc_call_test_subprog_lskel *skel; + int prog_fd, retval, err; + + skel = kfunc_call_test_subprog_lskel__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel")) + return; + + prog_fd = skel->progs.kfunc_call_test1.prog_fd; + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, (__u32 *)&retval, NULL); + ASSERT_OK(err, "bpf_prog_test_run(test1)"); + ASSERT_EQ(retval, 10, "test1-retval"); + ASSERT_NEQ(skel->data->active_res, -1, "active_res"); + ASSERT_EQ(skel->data->sk_state_res, BPF_TCP_CLOSE, "sk_state_res"); + + kfunc_call_test_subprog_lskel__destroy(skel); +} + void test_kfunc_call(void) { if (test__start_subtest("main")) @@ -56,4 +77,7 @@ void test_kfunc_call(void) if (test__start_subtest("subprog")) test_subprog(); + + if (test__start_subtest("subprog_lskel")) + test_subprog_lskel(); } diff --git a/tools/testing/selftests/bpf/prog_tests/legacy_printk.c b/tools/testing/selftests/bpf/prog_tests/legacy_printk.c new file mode 100644 index 000000000000..ec6e45f2a644 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/legacy_printk.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <test_progs.h> +#include "test_legacy_printk.skel.h" + +static int execute_one_variant(bool legacy) +{ + struct test_legacy_printk *skel; + int err, zero = 0, my_pid = getpid(), res, map_fd; + + skel = test_legacy_printk__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return -errno; + + bpf_program__set_autoload(skel->progs.handle_legacy, legacy); + bpf_program__set_autoload(skel->progs.handle_modern, !legacy); + + err = test_legacy_printk__load(skel); + /* no ASSERT_OK, we expect one of two variants can fail here */ + if (err) + goto err_out; + + if (legacy) { + map_fd = bpf_map__fd(skel->maps.my_pid_map); + err = bpf_map_update_elem(map_fd, &zero, &my_pid, BPF_ANY); + if (!ASSERT_OK(err, "my_pid_map_update")) + goto err_out; + err = bpf_map_lookup_elem(map_fd, &zero, &res); + } else { + skel->bss->my_pid_var = my_pid; + } + + err = test_legacy_printk__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto err_out; + + usleep(1); /* trigger */ + + if (legacy) { + map_fd = bpf_map__fd(skel->maps.res_map); + err = bpf_map_lookup_elem(map_fd, &zero, &res); + if (!ASSERT_OK(err, "res_map_lookup")) + goto err_out; + } else { + res = skel->bss->res_var; + } + + if (!ASSERT_GT(res, 0, "res")) { + err = -EINVAL; + goto err_out; + } + +err_out: + test_legacy_printk__destroy(skel); + return err; +} + +void test_legacy_printk(void) +{ + /* legacy variant should work everywhere */ + ASSERT_OK(execute_one_variant(true /* legacy */), "legacy_case"); + + /* execute modern variant, can fail the load on old kernels */ + execute_one_variant(false); +} diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c new file mode 100644 index 000000000000..e469b023962b --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <test_progs.h> +#include <bpf/btf.h> + +#include "test_log_buf.skel.h" + +static size_t libbpf_log_pos; +static char libbpf_log_buf[1024 * 1024]; +static bool libbpf_log_error; + +static int libbpf_print_cb(enum libbpf_print_level level, const char *fmt, va_list args) +{ + int emitted_cnt; + size_t left_cnt; + + left_cnt = sizeof(libbpf_log_buf) - libbpf_log_pos; + emitted_cnt = vsnprintf(libbpf_log_buf + libbpf_log_pos, left_cnt, fmt, args); + + if (emitted_cnt < 0 || emitted_cnt + 1 > left_cnt) { + libbpf_log_error = true; + return 0; + } + + libbpf_log_pos += emitted_cnt; + return 0; +} + +static void obj_load_log_buf(void) +{ + libbpf_print_fn_t old_print_cb = libbpf_set_print(libbpf_print_cb); + LIBBPF_OPTS(bpf_object_open_opts, opts); + const size_t log_buf_sz = 1024 * 1024; + struct test_log_buf* skel; + char *obj_log_buf, *good_log_buf, *bad_log_buf; + int err; + + obj_log_buf = malloc(3 * log_buf_sz); + if (!ASSERT_OK_PTR(obj_log_buf, "obj_log_buf")) + return; + + good_log_buf = obj_log_buf + log_buf_sz; + bad_log_buf = obj_log_buf + 2 * log_buf_sz; + obj_log_buf[0] = good_log_buf[0] = bad_log_buf[0] = '\0'; + + opts.kernel_log_buf = obj_log_buf; + opts.kernel_log_size = log_buf_sz; + opts.kernel_log_level = 4; /* for BTF this will turn into 1 */ + + /* In the first round every prog has its own log_buf, so libbpf logs + * don't have program failure logs + */ + skel = test_log_buf__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + /* set very verbose level for good_prog so we always get detailed logs */ + bpf_program__set_log_buf(skel->progs.good_prog, good_log_buf, log_buf_sz); + bpf_program__set_log_level(skel->progs.good_prog, 2); + + bpf_program__set_log_buf(skel->progs.bad_prog, bad_log_buf, log_buf_sz); + /* log_level 0 with custom log_buf means that verbose logs are not + * requested if program load is successful, but libbpf should retry + * with log_level 1 on error and put program's verbose load log into + * custom log_buf + */ + bpf_program__set_log_level(skel->progs.bad_prog, 0); + + err = test_log_buf__load(skel); + if (!ASSERT_ERR(err, "unexpected_load_success")) + goto cleanup; + + ASSERT_FALSE(libbpf_log_error, "libbpf_log_error"); + + /* there should be no prog loading log because we specified per-prog log buf */ + ASSERT_NULL(strstr(libbpf_log_buf, "-- BEGIN PROG LOAD LOG --"), "unexp_libbpf_log"); + ASSERT_OK_PTR(strstr(libbpf_log_buf, "prog 'bad_prog': BPF program load failed"), + "libbpf_log_not_empty"); + ASSERT_OK_PTR(strstr(obj_log_buf, "DATASEC license"), "obj_log_not_empty"); + ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(id=0,off=0,imm=0) R10=fp0"), + "good_log_verbose"); + ASSERT_OK_PTR(strstr(bad_log_buf, "invalid access to map value, value_size=16 off=16000 size=4"), + "bad_log_not_empty"); + + if (env.verbosity > VERBOSE_NONE) { + printf("LIBBPF LOG: \n=================\n%s=================\n", libbpf_log_buf); + printf("OBJ LOG: \n=================\n%s=================\n", obj_log_buf); + printf("GOOD_PROG LOG:\n=================\n%s=================\n", good_log_buf); + printf("BAD_PROG LOG:\n=================\n%s=================\n", bad_log_buf); + } + + /* reset everything */ + test_log_buf__destroy(skel); + obj_log_buf[0] = good_log_buf[0] = bad_log_buf[0] = '\0'; + libbpf_log_buf[0] = '\0'; + libbpf_log_pos = 0; + libbpf_log_error = false; + + /* In the second round we let bad_prog's failure be logged through print callback */ + opts.kernel_log_buf = NULL; /* let everything through into print callback */ + opts.kernel_log_size = 0; + opts.kernel_log_level = 1; + + skel = test_log_buf__open_opts(&opts); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + /* set normal verbose level for good_prog to check log_level is taken into account */ + bpf_program__set_log_buf(skel->progs.good_prog, good_log_buf, log_buf_sz); + bpf_program__set_log_level(skel->progs.good_prog, 1); + + err = test_log_buf__load(skel); + if (!ASSERT_ERR(err, "unexpected_load_success")) + goto cleanup; + + ASSERT_FALSE(libbpf_log_error, "libbpf_log_error"); + + /* this time prog loading error should be logged through print callback */ + ASSERT_OK_PTR(strstr(libbpf_log_buf, "libbpf: prog 'bad_prog': -- BEGIN PROG LOAD LOG --"), + "libbpf_log_correct"); + ASSERT_STREQ(obj_log_buf, "", "obj_log__empty"); + ASSERT_STREQ(good_log_buf, "processed 4 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0\n", + "good_log_ok"); + ASSERT_STREQ(bad_log_buf, "", "bad_log_empty"); + + if (env.verbosity > VERBOSE_NONE) { + printf("LIBBPF LOG: \n=================\n%s=================\n", libbpf_log_buf); + printf("OBJ LOG: \n=================\n%s=================\n", obj_log_buf); + printf("GOOD_PROG LOG:\n=================\n%s=================\n", good_log_buf); + printf("BAD_PROG LOG:\n=================\n%s=================\n", bad_log_buf); + } + +cleanup: + free(obj_log_buf); + test_log_buf__destroy(skel); + libbpf_set_print(old_print_cb); +} + +static void bpf_prog_load_log_buf(void) +{ + const struct bpf_insn good_prog_insns[] = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + const size_t good_prog_insn_cnt = sizeof(good_prog_insns) / sizeof(struct bpf_insn); + const struct bpf_insn bad_prog_insns[] = { + BPF_EXIT_INSN(), + }; + size_t bad_prog_insn_cnt = sizeof(bad_prog_insns) / sizeof(struct bpf_insn); + LIBBPF_OPTS(bpf_prog_load_opts, opts); + const size_t log_buf_sz = 1024 * 1024; + char *log_buf; + int fd = -1; + + log_buf = malloc(log_buf_sz); + if (!ASSERT_OK_PTR(log_buf, "log_buf_alloc")) + return; + opts.log_buf = log_buf; + opts.log_size = log_buf_sz; + + /* with log_level == 0 log_buf shoud stay empty for good prog */ + log_buf[0] = '\0'; + opts.log_level = 0; + fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL", + good_prog_insns, good_prog_insn_cnt, &opts); + ASSERT_STREQ(log_buf, "", "good_log_0"); + ASSERT_GE(fd, 0, "good_fd1"); + if (fd >= 0) + close(fd); + fd = -1; + + /* log_level == 2 should always fill log_buf, even for good prog */ + log_buf[0] = '\0'; + opts.log_level = 2; + fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL", + good_prog_insns, good_prog_insn_cnt, &opts); + ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(id=0,off=0,imm=0) R10=fp0"), "good_log_2"); + ASSERT_GE(fd, 0, "good_fd2"); + if (fd >= 0) + close(fd); + fd = -1; + + /* log_level == 0 should fill log_buf for bad prog */ + log_buf[0] = '\0'; + opts.log_level = 0; + fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "bad_prog", "GPL", + bad_prog_insns, bad_prog_insn_cnt, &opts); + ASSERT_OK_PTR(strstr(log_buf, "R0 !read_ok"), "bad_log_0"); + ASSERT_LT(fd, 0, "bad_fd"); + if (fd >= 0) + close(fd); + fd = -1; + + free(log_buf); +} + +static void bpf_btf_load_log_buf(void) +{ + LIBBPF_OPTS(bpf_btf_load_opts, opts); + const size_t log_buf_sz = 1024 * 1024; + const void *raw_btf_data; + __u32 raw_btf_size; + struct btf *btf; + char *log_buf; + int fd = -1; + + btf = btf__new_empty(); + if (!ASSERT_OK_PTR(btf, "empty_btf")) + return; + + ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type"); + + raw_btf_data = btf__raw_data(btf, &raw_btf_size); + if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data_good")) + goto cleanup; + + log_buf = malloc(log_buf_sz); + if (!ASSERT_OK_PTR(log_buf, "log_buf_alloc")) + goto cleanup; + opts.log_buf = log_buf; + opts.log_size = log_buf_sz; + + /* with log_level == 0 log_buf shoud stay empty for good BTF */ + log_buf[0] = '\0'; + opts.log_level = 0; + fd = bpf_btf_load(raw_btf_data, raw_btf_size, &opts); + ASSERT_STREQ(log_buf, "", "good_log_0"); + ASSERT_GE(fd, 0, "good_fd1"); + if (fd >= 0) + close(fd); + fd = -1; + + /* log_level == 2 should always fill log_buf, even for good BTF */ + log_buf[0] = '\0'; + opts.log_level = 2; + fd = bpf_btf_load(raw_btf_data, raw_btf_size, &opts); + printf("LOG_BUF: %s\n", log_buf); + ASSERT_OK_PTR(strstr(log_buf, "magic: 0xeb9f"), "good_log_2"); + ASSERT_GE(fd, 0, "good_fd2"); + if (fd >= 0) + close(fd); + fd = -1; + + /* make BTF bad, add pointer pointing to non-existing type */ + ASSERT_GT(btf__add_ptr(btf, 100), 0, "bad_ptr_type"); + + raw_btf_data = btf__raw_data(btf, &raw_btf_size); + if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data_bad")) + goto cleanup; + + /* log_level == 0 should fill log_buf for bad BTF */ + log_buf[0] = '\0'; + opts.log_level = 0; + fd = bpf_btf_load(raw_btf_data, raw_btf_size, &opts); + printf("LOG_BUF: %s\n", log_buf); + ASSERT_OK_PTR(strstr(log_buf, "[2] PTR (anon) type_id=100 Invalid type_id"), "bad_log_0"); + ASSERT_LT(fd, 0, "bad_fd"); + if (fd >= 0) + close(fd); + fd = -1; + +cleanup: + free(log_buf); + btf__free(btf); +} + +void test_log_buf(void) +{ + if (test__start_subtest("obj_load_log_buf")) + obj_load_log_buf(); + if (test__start_subtest("bpf_prog_load_log_buf")) + bpf_prog_load_log_buf(); + if (test__start_subtest("bpf_btf_load_log_buf")) + bpf_btf_load_log_buf(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/map_ptr.c b/tools/testing/selftests/bpf/prog_tests/map_ptr.c index 4972f92205c7..273725504f11 100644 --- a/tools/testing/selftests/bpf/prog_tests/map_ptr.c +++ b/tools/testing/selftests/bpf/prog_tests/map_ptr.c @@ -4,31 +4,29 @@ #include <test_progs.h> #include <network_helpers.h> -#include "map_ptr_kern.skel.h" +#include "map_ptr_kern.lskel.h" void test_map_ptr(void) { - struct map_ptr_kern *skel; + struct map_ptr_kern_lskel *skel; __u32 duration = 0, retval; char buf[128]; int err; int page_size = getpagesize(); - skel = map_ptr_kern__open(); + skel = map_ptr_kern_lskel__open(); if (!ASSERT_OK_PTR(skel, "skel_open")) return; - err = bpf_map__set_max_entries(skel->maps.m_ringbuf, page_size); - if (!ASSERT_OK(err, "bpf_map__set_max_entries")) - goto cleanup; + skel->maps.m_ringbuf.max_entries = page_size; - err = map_ptr_kern__load(skel); + err = map_ptr_kern_lskel__load(skel); if (!ASSERT_OK(err, "skel_load")) goto cleanup; skel->bss->page_size = page_size; - err = bpf_prog_test_run(bpf_program__fd(skel->progs.cg_skb), 1, &pkt_v4, + err = bpf_prog_test_run(skel->progs.cg_skb.prog_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, NULL, &retval, NULL); if (CHECK(err, "test_run", "err=%d errno=%d\n", err, errno)) @@ -39,5 +37,5 @@ void test_map_ptr(void) goto cleanup; cleanup: - map_ptr_kern__destroy(skel); + map_ptr_kern_lskel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/pinning.c b/tools/testing/selftests/bpf/prog_tests/pinning.c index d4b953ae3407..31c09ba577eb 100644 --- a/tools/testing/selftests/bpf/prog_tests/pinning.c +++ b/tools/testing/selftests/bpf/prog_tests/pinning.c @@ -241,8 +241,8 @@ void test_pinning(void) goto out; } - map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(__u32), - sizeof(__u64), 1, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(__u32), + sizeof(__u64), 1, NULL); if (CHECK(map_fd < 0, "create pinmap manually", "fd %d\n", map_fd)) goto out; diff --git a/tools/testing/selftests/bpf/prog_tests/prog_array_init.c b/tools/testing/selftests/bpf/prog_tests/prog_array_init.c new file mode 100644 index 000000000000..fc4657619739 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/prog_array_init.c @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021 Hengqi Chen */ + +#include <test_progs.h> +#include "test_prog_array_init.skel.h" + +void test_prog_array_init(void) +{ + struct test_prog_array_init *skel; + int err; + + skel = test_prog_array_init__open(); + if (!ASSERT_OK_PTR(skel, "could not open BPF object")) + return; + + skel->rodata->my_pid = getpid(); + + err = test_prog_array_init__load(skel); + if (!ASSERT_OK(err, "could not load BPF object")) + goto cleanup; + + skel->links.entry = bpf_program__attach_raw_tracepoint(skel->progs.entry, "sys_enter"); + if (!ASSERT_OK_PTR(skel->links.entry, "could not attach BPF program")) + goto cleanup; + + usleep(1); + + ASSERT_EQ(skel->bss->value, 42, "unexpected value"); + +cleanup: + test_prog_array_init__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c index 8ccba3ab70ee..b9822f914eeb 100644 --- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c +++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c @@ -14,7 +14,7 @@ static void test_queue_stack_map_by_type(int type) int i, err, prog_fd, map_in_fd, map_out_fd; char file[32], buf[128]; struct bpf_object *obj; - struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + struct iphdr iph; /* Fill test values to be used */ for (i = 0; i < MAP_SIZE; i++) @@ -60,15 +60,17 @@ static void test_queue_stack_map_by_type(int type) err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); - if (err || retval || size != sizeof(pkt_v4) || - iph->daddr != val) + if (err || retval || size != sizeof(pkt_v4)) + break; + memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); + if (iph.daddr != val) break; } - CHECK(err || retval || size != sizeof(pkt_v4) || iph->daddr != val, + CHECK(err || retval || size != sizeof(pkt_v4) || iph.daddr != val, "bpf_map_pop_elem", "err %d errno %d retval %d size %d iph->daddr %u\n", - err, errno, retval, size, iph->daddr); + err, errno, retval, size, iph.daddr); /* Queue is empty, program should return TC_ACT_SHOT */ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c index 167cd8a2edfd..e945195b24c9 100644 --- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c @@ -62,8 +62,8 @@ void test_ringbuf_multi(void) if (CHECK(err != 0, "bpf_map__set_max_entries", "bpf_map__set_max_entries failed\n")) goto cleanup; - proto_fd = bpf_create_map(BPF_MAP_TYPE_RINGBUF, 0, 0, page_size, 0); - if (CHECK(proto_fd < 0, "bpf_create_map", "bpf_create_map failed\n")) + proto_fd = bpf_map_create(BPF_MAP_TYPE_RINGBUF, NULL, 0, 0, page_size, NULL); + if (CHECK(proto_fd < 0, "bpf_map_create", "bpf_map_create failed\n")) goto cleanup; err = bpf_map__set_inner_map_fd(skel->maps.ringbuf_hash, proto_fd); diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 3cfc910ab3c1..980ac0f2c0bb 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -66,29 +66,20 @@ static union sa46 { static int create_maps(enum bpf_map_type inner_type) { - struct bpf_create_map_attr attr = {}; + LIBBPF_OPTS(bpf_map_create_opts, opts); inner_map_type = inner_type; /* Creating reuseport_array */ - attr.name = "reuseport_array"; - attr.map_type = inner_type; - attr.key_size = sizeof(__u32); - attr.value_size = sizeof(__u32); - attr.max_entries = REUSEPORT_ARRAY_SIZE; - - reuseport_array = bpf_create_map_xattr(&attr); + reuseport_array = bpf_map_create(inner_type, "reuseport_array", + sizeof(__u32), sizeof(__u32), REUSEPORT_ARRAY_SIZE, NULL); RET_ERR(reuseport_array < 0, "creating reuseport_array", "reuseport_array:%d errno:%d\n", reuseport_array, errno); /* Creating outer_map */ - attr.name = "outer_map"; - attr.map_type = BPF_MAP_TYPE_ARRAY_OF_MAPS; - attr.key_size = sizeof(__u32); - attr.value_size = sizeof(__u32); - attr.max_entries = 1; - attr.inner_map_fd = reuseport_array; - outer_map = bpf_create_map_xattr(&attr); + opts.inner_map_fd = reuseport_array; + outer_map = bpf_map_create(BPF_MAP_TYPE_ARRAY_OF_MAPS, "outer_map", + sizeof(__u32), sizeof(__u32), 1, &opts); RET_ERR(outer_map < 0, "creating outer_map", "outer_map:%d errno:%d\n", outer_map, errno); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 1352ec104149..85db0f4cdd95 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -91,9 +91,9 @@ static void test_sockmap_create_update_free(enum bpf_map_type map_type) if (CHECK_FAIL(s < 0)) return; - map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); + map = bpf_map_create(map_type, NULL, sizeof(int), sizeof(int), 1, NULL); if (CHECK_FAIL(map < 0)) { - perror("bpf_create_map"); + perror("bpf_cmap_create"); goto out; } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index 7a0d64fdc192..af293ea1542c 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -97,7 +97,7 @@ static void run_tests(int family, enum bpf_map_type map_type) char test_name[MAX_TEST_NAME]; int map; - map = bpf_create_map(map_type, sizeof(int), sizeof(int), 1, 0); + map = bpf_map_create(map_type, NULL, sizeof(int), sizeof(int), 1, NULL); if (CHECK_FAIL(map < 0)) { perror("bpf_map_create"); return; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 2a9cb951bfd6..7e21bfab6358 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -502,8 +502,8 @@ static void test_lookup_32_bit_value(int family, int sotype, int mapfd) if (s < 0) return; - mapfd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP, sizeof(key), - sizeof(value32), 1, 0); + mapfd = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(key), + sizeof(value32), 1, NULL); if (mapfd < 0) { FAIL_ERRNO("map_create"); goto close; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c index 86f97681ad89..6a953f4adfdc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c @@ -167,20 +167,20 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) static void run_test(int cgroup_fd) { - struct bpf_prog_load_attr attr = { - .file = "./sockopt_inherit.o", - }; int server_fd = -1, client_fd; struct bpf_object *obj; void *server_err; pthread_t tid; - int ignored; int err; - err = bpf_prog_load_xattr(&attr, &obj, &ignored); - if (CHECK_FAIL(err)) + obj = bpf_object__open_file("sockopt_inherit.o", NULL); + if (!ASSERT_OK_PTR(obj, "obj_open")) return; + err = bpf_object__load(obj); + if (!ASSERT_OK(err, "obj_load")) + goto close_bpf_object; + err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt"); if (CHECK_FAIL(err)) goto close_bpf_object; diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c index bc34f7773444..abce12ddcc37 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c @@ -297,14 +297,10 @@ detach: void test_sockopt_multi(void) { - struct bpf_prog_load_attr attr = { - .file = "./sockopt_multi.o", - }; int cg_parent = -1, cg_child = -1; struct bpf_object *obj = NULL; int sock_fd = -1; int err = -1; - int ignored; cg_parent = test__join_cgroup("/parent"); if (CHECK_FAIL(cg_parent < 0)) @@ -314,8 +310,12 @@ void test_sockopt_multi(void) if (CHECK_FAIL(cg_child < 0)) goto out; - err = bpf_prog_load_xattr(&attr, &obj, &ignored); - if (CHECK_FAIL(err)) + obj = bpf_object__open_file("sockopt_multi.o", NULL); + if (!ASSERT_OK_PTR(obj, "obj_load")) + goto out; + + err = bpf_object__load(obj); + if (!ASSERT_OK(err, "obj_load")) goto out; sock_fd = socket(AF_INET, SOCK_STREAM, 0); diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c index 265b4fe33ec3..96ff2c20af81 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c +++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c @@ -2,6 +2,7 @@ #include <test_progs.h> #include "cgroup_helpers.h" #include "network_helpers.h" +#include "tcp_rtt.skel.h" struct tcp_rtt_storage { __u32 invoked; @@ -91,26 +92,18 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked, static int run_test(int cgroup_fd, int server_fd) { - struct bpf_prog_load_attr attr = { - .prog_type = BPF_PROG_TYPE_SOCK_OPS, - .file = "./tcp_rtt.o", - .expected_attach_type = BPF_CGROUP_SOCK_OPS, - }; - struct bpf_object *obj; - struct bpf_map *map; + struct tcp_rtt *skel; int client_fd; int prog_fd; int map_fd; int err; - err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); - if (err) { - log_err("Failed to load BPF object"); + skel = tcp_rtt__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_load")) return -1; - } - map = bpf_object__next_map(obj, NULL); - map_fd = bpf_map__fd(map); + map_fd = bpf_map__fd(skel->maps.socket_storage_map); + prog_fd = bpf_program__fd(skel->progs._sockops); err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0); if (err) { @@ -149,7 +142,7 @@ close_client_fd: close(client_fd); close_bpf_object: - bpf_object__close(obj); + tcp_rtt__destroy(skel); return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c index d29ebfeef9c5..214d9f4a94a5 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c @@ -19,11 +19,13 @@ static int read_iter(char *file) fd = open(file, 0); if (fd < 0) return -1; - while ((len = read(fd, buf, sizeof(buf))) > 0) + while ((len = read(fd, buf, sizeof(buf))) > 0) { + buf[sizeof(buf) - 1] = '\0'; if (strstr(buf, "iter")) { close(fd); return 0; } + } close(fd); return -1; } @@ -80,7 +82,7 @@ static int fn(void) if (!ASSERT_OK(err, "creating " TDIR "/fs1/b")) goto out; - map = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0); + map = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL); if (!ASSERT_GT(map, 0, "create_map(ARRAY)")) goto out; err = bpf_obj_pin(map, TDIR "/fs1/c"); diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 7e13129f593a..509e21d5cb9d 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -30,17 +30,29 @@ extern int extra_prog_load_log_flags; static int check_load(const char *file) { - struct bpf_prog_load_attr attr; struct bpf_object *obj = NULL; - int err, prog_fd; + struct bpf_program *prog; + int err; - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = file; - attr.prog_type = BPF_PROG_TYPE_UNSPEC; - attr.log_level = extra_prog_load_log_flags; - attr.prog_flags = BPF_F_TEST_RND_HI32; found = false; - err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + + obj = bpf_object__open_file(file, NULL); + err = libbpf_get_error(obj); + if (err) + return err; + + prog = bpf_object__next_program(obj, NULL); + if (!prog) { + err = -ENOENT; + goto err_out; + } + + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); + bpf_program__set_log_level(prog, extra_prog_load_log_flags); + + err = bpf_object__load(obj); + +err_out: bpf_object__close(obj); return err; } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp.c b/tools/testing/selftests/bpf/prog_tests/xdp.c index 7a7ef9d4e151..ac65456b7ab8 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp.c @@ -11,8 +11,8 @@ void test_xdp(void) const char *file = "./test_xdp.o"; struct bpf_object *obj; char buf[128]; - struct ipv6hdr *iph6 = (void *)buf + sizeof(struct ethhdr); - struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + struct ipv6hdr iph6; + struct iphdr iph; __u32 duration, retval, size; int err, prog_fd, map_fd; @@ -28,16 +28,17 @@ void test_xdp(void) err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); - + memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); CHECK(err || retval != XDP_TX || size != 74 || - iph->protocol != IPPROTO_IPIP, "ipv4", + iph.protocol != IPPROTO_IPIP, "ipv4", "err %d errno %d retval %d size %d\n", err, errno, retval, size); err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), buf, &size, &retval, &duration); + memcpy(&iph6, buf + sizeof(struct ethhdr), sizeof(iph6)); CHECK(err || retval != XDP_TX || size != 114 || - iph6->nexthdr != IPPROTO_IPV6, "ipv6", + iph6.nexthdr != IPPROTO_IPV6, "ipv6", "err %d errno %d retval %d size %d\n", err, errno, retval, size); out: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index faa22b84f2ee..5e3a26b15ec6 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -218,9 +218,9 @@ static int send_udp_packets(int vary_dst_ip) .h_dest = BOND2_MAC, .h_proto = htons(ETH_P_IP), }; - uint8_t buf[128] = {}; - struct iphdr *iph = (struct iphdr *)(buf + sizeof(eh)); - struct udphdr *uh = (struct udphdr *)(buf + sizeof(eh) + sizeof(*iph)); + struct iphdr iph = {}; + struct udphdr uh = {}; + uint8_t buf[128]; int i, s = -1; int ifindex; @@ -232,17 +232,16 @@ static int send_udp_packets(int vary_dst_ip) if (!ASSERT_GT(ifindex, 0, "get bond1 ifindex")) goto err; - memcpy(buf, &eh, sizeof(eh)); - iph->ihl = 5; - iph->version = 4; - iph->tos = 16; - iph->id = 1; - iph->ttl = 64; - iph->protocol = IPPROTO_UDP; - iph->saddr = 1; - iph->daddr = 2; - iph->tot_len = htons(sizeof(buf) - ETH_HLEN); - iph->check = 0; + iph.ihl = 5; + iph.version = 4; + iph.tos = 16; + iph.id = 1; + iph.ttl = 64; + iph.protocol = IPPROTO_UDP; + iph.saddr = 1; + iph.daddr = 2; + iph.tot_len = htons(sizeof(buf) - ETH_HLEN); + iph.check = 0; for (i = 1; i <= NPACKETS; i++) { int n; @@ -253,10 +252,15 @@ static int send_udp_packets(int vary_dst_ip) }; /* vary the UDP destination port for even distribution with roundrobin/xor modes */ - uh->dest++; + uh.dest++; if (vary_dst_ip) - iph->daddr++; + iph.daddr++; + + /* construct a packet */ + memcpy(buf, &eh, sizeof(eh)); + memcpy(buf + sizeof(eh), &iph, sizeof(iph)); + memcpy(buf + sizeof(eh) + sizeof(iph), &uh, sizeof(uh)); n = sendto(s, buf, sizeof(buf), 0, (struct sockaddr *)&saddr_ll, sizeof(saddr_ll)); if (!ASSERT_EQ(n, sizeof(buf), "sendto")) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c index f99386d1dc4c..c98a897ad692 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c @@ -42,7 +42,7 @@ void test_xdp_bpf2bpf(void) char buf[128]; int err, pkt_fd, map_fd; bool passed = false; - struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + struct iphdr iph; struct iptnl_info value4 = {.family = AF_INET}; struct test_xdp *pkt_skel = NULL; struct test_xdp_bpf2bpf *ftrace_skel = NULL; @@ -93,9 +93,9 @@ void test_xdp_bpf2bpf(void) /* Run test program */ err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4), buf, &size, &retval, &duration); - + memcpy(&iph, buf + sizeof(struct ethhdr), sizeof(iph)); if (CHECK(err || retval != XDP_TX || size != 74 || - iph->protocol != IPPROTO_IPIP, "ipv4", + iph.protocol != IPPROTO_IPIP, "ipv4", "err %d errno %d retval %d size %d\n", err, errno, retval, size)) goto out; diff --git a/tools/testing/selftests/bpf/progs/bpf_loop.c b/tools/testing/selftests/bpf/progs/bpf_loop.c new file mode 100644 index 000000000000..12349e4601e8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_loop.c @@ -0,0 +1,112 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +struct callback_ctx { + int output; +}; + +/* These should be set by the user program */ +u32 nested_callback_nr_loops; +u32 stop_index = -1; +u32 nr_loops; +int pid; + +/* Making these global variables so that the userspace program + * can verify the output through the skeleton + */ +int nr_loops_returned; +int g_output; +int err; + +static int callback(__u32 index, void *data) +{ + struct callback_ctx *ctx = data; + + if (index >= stop_index) + return 1; + + ctx->output += index; + + return 0; +} + +static int empty_callback(__u32 index, void *data) +{ + return 0; +} + +static int nested_callback2(__u32 index, void *data) +{ + nr_loops_returned += bpf_loop(nested_callback_nr_loops, callback, data, 0); + + return 0; +} + +static int nested_callback1(__u32 index, void *data) +{ + bpf_loop(nested_callback_nr_loops, nested_callback2, data, 0); + return 0; +} + +SEC("fentry/__x64_sys_nanosleep") +int test_prog(void *ctx) +{ + struct callback_ctx data = {}; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + nr_loops_returned = bpf_loop(nr_loops, callback, &data, 0); + + if (nr_loops_returned < 0) + err = nr_loops_returned; + else + g_output = data.output; + + return 0; +} + +SEC("fentry/__x64_sys_nanosleep") +int prog_null_ctx(void *ctx) +{ + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + nr_loops_returned = bpf_loop(nr_loops, empty_callback, NULL, 0); + + return 0; +} + +SEC("fentry/__x64_sys_nanosleep") +int prog_invalid_flags(void *ctx) +{ + struct callback_ctx data = {}; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + err = bpf_loop(nr_loops, callback, &data, 1); + + return 0; +} + +SEC("fentry/__x64_sys_nanosleep") +int prog_nested_calls(void *ctx) +{ + struct callback_ctx data = {}; + + if (bpf_get_current_pid_tgid() >> 32 != pid) + return 0; + + nr_loops_returned = 0; + bpf_loop(nr_loops, nested_callback1, &data, 0); + + g_output = data.output; + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c new file mode 100644 index 000000000000..9dafdc244462 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +char _license[] SEC("license") = "GPL"; + +u32 nr_loops; +long hits; + +static int empty_callback(__u32 index, void *data) +{ + return 0; +} + +SEC("fentry/__x64_sys_getpgid") +int benchmark(void *ctx) +{ + for (int i = 0; i < 1000; i++) { + bpf_loop(nr_loops, empty_callback, NULL, 0); + + __sync_add_and_fetch(&hits, nr_loops); + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/core_kern.c b/tools/testing/selftests/bpf/progs/core_kern.c new file mode 100644 index 000000000000..13499cc15c7d --- /dev/null +++ b/tools/testing/selftests/bpf/progs/core_kern.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +#define ATTR __always_inline +#include "test_jhash.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 256); +} array1 SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); + __type(value, u32); + __uint(max_entries, 256); +} array2 SEC(".maps"); + +static __noinline int randmap(int v, const struct net_device *dev) +{ + struct bpf_map *map = (struct bpf_map *)&array1; + int key = bpf_get_prandom_u32() & 0xff; + int *val; + + if (bpf_get_prandom_u32() & 1) + map = (struct bpf_map *)&array2; + + val = bpf_map_lookup_elem(map, &key); + if (val) + *val = bpf_get_prandom_u32() + v + dev->mtu; + + return 0; +} + +SEC("tp_btf/xdp_devmap_xmit") +int BPF_PROG(tp_xdp_devmap_xmit_multi, const struct net_device + *from_dev, const struct net_device *to_dev, int sent, int drops, + int err) +{ + return randmap(from_dev->ifindex, from_dev); +} + +SEC("fentry/eth_type_trans") +int BPF_PROG(fentry_eth_type_trans, struct sk_buff *skb, + struct net_device *dev, unsigned short protocol) +{ + return randmap(dev->ifindex + skb->len, dev); +} + +SEC("fexit/eth_type_trans") +int BPF_PROG(fexit_eth_type_trans, struct sk_buff *skb, + struct net_device *dev, unsigned short protocol) +{ + return randmap(dev->ifindex + skb->len, dev); +} + +volatile const int never; + +struct __sk_bUfF /* it will not exist in vmlinux */ { + int len; +} __attribute__((preserve_access_index)); + +struct bpf_testmod_test_read_ctx /* it exists in bpf_testmod */ { + size_t len; +} __attribute__((preserve_access_index)); + +SEC("tc") +int balancer_ingress(struct __sk_buff *ctx) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + void *ptr; + int ret = 0, nh_off, i = 0; + + nh_off = 14; + + /* pragma unroll doesn't work on large loops */ +#define C do { \ + ptr = data + i; \ + if (ptr + nh_off > data_end) \ + break; \ + ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \ + if (never) { \ + /* below is a dead code with unresolvable CO-RE relo */ \ + i += ((struct __sk_bUfF *)ctx)->len; \ + /* this CO-RE relo may or may not resolve + * depending on whether bpf_testmod is loaded. + */ \ + i += ((struct bpf_testmod_test_read_ctx *)ctx)->len; \ + } \ + } while (0); +#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C; + C30;C30;C30; /* 90 calls */ + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index b1b711d9b214..b64df94ec476 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -334,9 +334,11 @@ static inline int check_lpm_trie(void) return 1; } +#define INNER_MAX_ENTRIES 1234 + struct inner_map { __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); + __uint(max_entries, INNER_MAX_ENTRIES); __type(key, __u32); __type(value, __u32); } inner_map SEC(".maps"); @@ -348,7 +350,7 @@ struct { __type(value, __u32); __array(values, struct { __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); + __uint(max_entries, INNER_MAX_ENTRIES); __type(key, __u32); __type(value, __u32); }); @@ -360,8 +362,13 @@ static inline int check_array_of_maps(void) { struct bpf_array *array_of_maps = (struct bpf_array *)&m_array_of_maps; struct bpf_map *map = (struct bpf_map *)&m_array_of_maps; + struct bpf_array *inner_map; + int key = 0; VERIFY(check_default(&array_of_maps->map, map)); + inner_map = bpf_map_lookup_elem(array_of_maps, &key); + VERIFY(inner_map != 0); + VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; } @@ -382,8 +389,13 @@ static inline int check_hash_of_maps(void) { struct bpf_htab *hash_of_maps = (struct bpf_htab *)&m_hash_of_maps; struct bpf_map *map = (struct bpf_map *)&m_hash_of_maps; + struct bpf_htab *inner_map; + int key = 2; VERIFY(check_default(&hash_of_maps->map, map)); + inner_map = bpf_map_lookup_elem(hash_of_maps, &key); + VERIFY(inner_map != 0); + VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; } diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h index 2fb7adafb6b6..1ed28882daf3 100644 --- a/tools/testing/selftests/bpf/progs/pyperf.h +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -159,6 +159,59 @@ struct { __uint(value_size, sizeof(long long) * 127); } stackmap SEC(".maps"); +#ifdef USE_BPF_LOOP +struct process_frame_ctx { + int cur_cpu; + int32_t *symbol_counter; + void *frame_ptr; + FrameData *frame; + PidData *pidData; + Symbol *sym; + Event *event; + bool done; +}; + +#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var)) + +static int process_frame_callback(__u32 i, struct process_frame_ctx *ctx) +{ + int zero = 0; + void *frame_ptr = ctx->frame_ptr; + PidData *pidData = ctx->pidData; + FrameData *frame = ctx->frame; + int32_t *symbol_counter = ctx->symbol_counter; + int cur_cpu = ctx->cur_cpu; + Event *event = ctx->event; + Symbol *sym = ctx->sym; + + if (frame_ptr && get_frame_data(frame_ptr, pidData, frame, sym)) { + int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu; + int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, sym); + + if (!symbol_id) { + bpf_map_update_elem(&symbolmap, sym, &zero, 0); + symbol_id = bpf_map_lookup_elem(&symbolmap, sym); + if (!symbol_id) { + ctx->done = true; + return 1; + } + } + if (*symbol_id == new_symbol_id) + (*symbol_counter)++; + + barrier_var(i); + if (i >= STACK_MAX_LEN) + return 1; + + event->stack[i] = *symbol_id; + + event->stack_len = i + 1; + frame_ptr = frame->f_back; + } + return 0; +} +#endif /* USE_BPF_LOOP */ + #ifdef GLOBAL_FUNC __noinline #elif defined(SUBPROGS) @@ -228,11 +281,26 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx) int32_t* symbol_counter = bpf_map_lookup_elem(&symbolmap, &sym); if (symbol_counter == NULL) return 0; +#ifdef USE_BPF_LOOP + struct process_frame_ctx ctx = { + .cur_cpu = cur_cpu, + .symbol_counter = symbol_counter, + .frame_ptr = frame_ptr, + .frame = &frame, + .pidData = pidData, + .sym = &sym, + .event = event, + }; + + bpf_loop(STACK_MAX_LEN, process_frame_callback, &ctx, 0); + if (ctx.done) + return 0; +#else #ifdef NO_UNROLL #pragma clang loop unroll(disable) #else #pragma clang loop unroll(full) -#endif +#endif /* NO_UNROLL */ /* Unwind python stack */ for (int i = 0; i < STACK_MAX_LEN; ++i) { if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) { @@ -251,6 +319,7 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx) frame_ptr = frame.f_back; } } +#endif /* USE_BPF_LOOP */ event->stack_complete = frame_ptr == NULL; } else { event->stack_complete = 1; diff --git a/tools/testing/selftests/bpf/progs/pyperf600_bpf_loop.c b/tools/testing/selftests/bpf/progs/pyperf600_bpf_loop.c new file mode 100644 index 000000000000..5c2059dc01af --- /dev/null +++ b/tools/testing/selftests/bpf/progs/pyperf600_bpf_loop.c @@ -0,0 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#define STACK_MAX_LEN 600 +#define USE_BPF_LOOP +#include "pyperf.h" diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index 60c93aee2f4a..753718595c26 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -445,6 +445,48 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, return payload; } +#ifdef USE_BPF_LOOP +enum read_type { + READ_INT_VAR, + READ_MAP_VAR, + READ_STR_VAR, +}; + +struct read_var_ctx { + struct strobemeta_payload *data; + void *tls_base; + struct strobemeta_cfg *cfg; + void *payload; + /* value gets mutated */ + struct strobe_value_generic *value; + enum read_type type; +}; + +static int read_var_callback(__u32 index, struct read_var_ctx *ctx) +{ + switch (ctx->type) { + case READ_INT_VAR: + if (index >= STROBE_MAX_INTS) + return 1; + read_int_var(ctx->cfg, index, ctx->tls_base, ctx->value, ctx->data); + break; + case READ_MAP_VAR: + if (index >= STROBE_MAX_MAPS) + return 1; + ctx->payload = read_map_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload); + break; + case READ_STR_VAR: + if (index >= STROBE_MAX_STRS) + return 1; + ctx->payload += read_str_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload); + break; + } + return 0; +} +#endif /* USE_BPF_LOOP */ + /* * read_strobe_meta returns NULL, if no metadata was read; otherwise returns * pointer to *right after* payload ends @@ -475,11 +517,36 @@ static void *read_strobe_meta(struct task_struct *task, */ tls_base = (void *)task; +#ifdef USE_BPF_LOOP + struct read_var_ctx ctx = { + .cfg = cfg, + .tls_base = tls_base, + .value = &value, + .data = data, + .payload = payload, + }; + int err; + + ctx.type = READ_INT_VAR; + err = bpf_loop(STROBE_MAX_INTS, read_var_callback, &ctx, 0); + if (err != STROBE_MAX_INTS) + return NULL; + + ctx.type = READ_STR_VAR; + err = bpf_loop(STROBE_MAX_STRS, read_var_callback, &ctx, 0); + if (err != STROBE_MAX_STRS) + return NULL; + + ctx.type = READ_MAP_VAR; + err = bpf_loop(STROBE_MAX_MAPS, read_var_callback, &ctx, 0); + if (err != STROBE_MAX_MAPS) + return NULL; +#else #ifdef NO_UNROLL #pragma clang loop unroll(disable) #else #pragma unroll -#endif +#endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_INTS; ++i) { read_int_var(cfg, i, tls_base, &value, data); } @@ -487,7 +554,7 @@ static void *read_strobe_meta(struct task_struct *task, #pragma clang loop unroll(disable) #else #pragma unroll -#endif +#endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_STRS; ++i) { payload += read_str_var(cfg, i, tls_base, &value, data, payload); } @@ -495,10 +562,12 @@ static void *read_strobe_meta(struct task_struct *task, #pragma clang loop unroll(disable) #else #pragma unroll -#endif +#endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_MAPS; ++i) { payload = read_map_var(cfg, i, tls_base, &value, data, payload); } +#endif /* USE_BPF_LOOP */ + /* * return pointer right after end of payload, so it's possible to * calculate exact amount of useful data that needs to be sent diff --git a/tools/testing/selftests/bpf/progs/strobemeta_bpf_loop.c b/tools/testing/selftests/bpf/progs/strobemeta_bpf_loop.c new file mode 100644 index 000000000000..d18b992f0165 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/strobemeta_bpf_loop.c @@ -0,0 +1,9 @@ +// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) +/* Copyright (c) 2021 Facebook */ + +#define STROBE_MAX_INTS 2 +#define STROBE_MAX_STRS 25 +#define STROBE_MAX_MAPS 100 +#define STROBE_MAX_MAP_ENTRIES 20 +#define USE_BPF_LOOP +#include "strobemeta.h" diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c index 8eadbd4caf7a..5f8379aadb29 100644 --- a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c +++ b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c @@ -38,7 +38,7 @@ int pass_handler(const void *ctx) /* tests existing symbols. */ rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, 0); if (rq) - out__existing_typed = 0; + out__existing_typed = rq->cpu; out__existing_typeless = (__u64)&bpf_prog_active; /* tests non-existent symbols. */ diff --git a/tools/testing/selftests/bpf/progs/test_legacy_printk.c b/tools/testing/selftests/bpf/progs/test_legacy_printk.c new file mode 100644 index 000000000000..64c2d9ced529 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_legacy_printk.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bpf.h> +#define BPF_NO_GLOBAL_DATA +#include <bpf/bpf_helpers.h> + +char LICENSE[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); +} my_pid_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, int); + __type(value, int); + __uint(max_entries, 1); +} res_map SEC(".maps"); + +volatile int my_pid_var = 0; +volatile int res_var = 0; + +SEC("tp/raw_syscalls/sys_enter") +int handle_legacy(void *ctx) +{ + int zero = 0, *my_pid, cur_pid, *my_res; + + my_pid = bpf_map_lookup_elem(&my_pid_map, &zero); + if (!my_pid) + return 1; + + cur_pid = bpf_get_current_pid_tgid() >> 32; + if (cur_pid != *my_pid) + return 1; + + my_res = bpf_map_lookup_elem(&res_map, &zero); + if (!my_res) + return 1; + + if (*my_res == 0) + /* use bpf_printk() in combination with BPF_NO_GLOBAL_DATA to + * force .rodata.str1.1 section that previously caused + * problems on old kernels due to libbpf always tried to + * create a global data map for it + */ + bpf_printk("Legacy-case bpf_printk test, pid %d\n", cur_pid); + *my_res = 1; + + return *my_res; +} + +SEC("tp/raw_syscalls/sys_enter") +int handle_modern(void *ctx) +{ + int zero = 0, cur_pid; + + cur_pid = bpf_get_current_pid_tgid() >> 32; + if (cur_pid != my_pid_var) + return 1; + + if (res_var == 0) + /* we need bpf_printk() to validate libbpf logic around unused + * global maps and legacy kernels; see comment in handle_legacy() + */ + bpf_printk("Modern-case bpf_printk test, pid %d\n", cur_pid); + res_var = 1; + + return res_var; +} diff --git a/tools/testing/selftests/bpf/progs/test_log_buf.c b/tools/testing/selftests/bpf/progs/test_log_buf.c new file mode 100644 index 000000000000..199f459bd5ae --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_log_buf.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +int a[4]; +const volatile int off = 4000; + +SEC("raw_tp/sys_enter") +int good_prog(const void *ctx) +{ + a[0] = (int)(long)ctx; + return a[1]; +} + +SEC("raw_tp/sys_enter") +int bad_prog(const void *ctx) +{ + /* out of bounds access */ + return a[off]; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c index b36857093f71..50ce16d02da7 100644 --- a/tools/testing/selftests/bpf/progs/test_module_attach.c +++ b/tools/testing/selftests/bpf/progs/test_module_attach.c @@ -87,6 +87,18 @@ int BPF_PROG(handle_fexit, return 0; } +SEC("fexit/bpf_testmod_return_ptr") +int BPF_PROG(handle_fexit_ret, int arg, struct file *ret) +{ + long buf = 0; + + bpf_probe_read_kernel(&buf, 8, ret); + bpf_probe_read_kernel(&buf, 8, (char *)ret + 256); + *(volatile long long *)ret; + *(volatile int *)&ret->f_mode; + return 0; +} + __u32 fmod_ret_read_sz = 0; SEC("fmod_ret/bpf_testmod_test_read") diff --git a/tools/testing/selftests/bpf/progs/test_prog_array_init.c b/tools/testing/selftests/bpf/progs/test_prog_array_init.c new file mode 100644 index 000000000000..2cd138356126 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_prog_array_init.c @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021 Hengqi Chen */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +const volatile pid_t my_pid = 0; +int value = 0; + +SEC("raw_tp/sys_enter") +int tailcall_1(void *ctx) +{ + value = 42; + return 0; +} + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 2); + __uint(key_size, sizeof(__u32)); + __array(values, int (void *)); +} prog_array_init SEC(".maps") = { + .values = { + [1] = (void *)&tailcall_1, + }, +}; + +SEC("raw_tp/sys_enter") +int entry(void *ctx) +{ + pid_t pid = bpf_get_current_pid_tgid() >> 32; + + if (pid != my_pid) + return 0; + + bpf_tail_call(ctx, &prog_array_init, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c index f024154c7be7..f90ffcafd1e8 100644 --- a/tools/testing/selftests/bpf/progs/test_verif_scale2.c +++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #define ATTR __always_inline #include "test_jhash.h" -SEC("scale90_inline") +SEC("tc") int balancer_ingress(struct __sk_buff *ctx) { void *data_end = (void *)(long)ctx->data_end; diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c index 9a4d09590b3d..2098f3f27f18 100644 --- a/tools/testing/selftests/bpf/progs/trigger_bench.c +++ b/tools/testing/selftests/bpf/progs/trigger_bench.c @@ -52,3 +52,10 @@ int bench_trigger_fmodret(void *ctx) __sync_add_and_fetch(&hits, 1); return -22; } + +SEC("uprobe/self/uprobe_target") +int bench_trigger_uprobe(void *ctx) +{ + __sync_add_and_fetch(&hits, 1); + return 0; +} diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py index be54b7335a76..6bf21e47882a 100755 --- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py +++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py @@ -9,7 +9,15 @@ import os, sys LINUX_ROOT = os.path.abspath(os.path.join(__file__, os.pardir, os.pardir, os.pardir, os.pardir, os.pardir)) -BPFTOOL_DIR = os.path.join(LINUX_ROOT, 'tools/bpf/bpftool') +BPFTOOL_DIR = os.getenv('BPFTOOL_DIR', + os.path.join(LINUX_ROOT, 'tools/bpf/bpftool')) +BPFTOOL_BASHCOMP_DIR = os.getenv('BPFTOOL_BASHCOMP_DIR', + os.path.join(BPFTOOL_DIR, 'bash-completion')) +BPFTOOL_DOC_DIR = os.getenv('BPFTOOL_DOC_DIR', + os.path.join(BPFTOOL_DIR, 'Documentation')) +INCLUDE_DIR = os.getenv('INCLUDE_DIR', + os.path.join(LINUX_ROOT, 'tools/include')) + retval = 0 class BlockParser(object): @@ -242,12 +250,6 @@ class FileExtractor(object): end_marker = re.compile('}\\\\n') return self.__get_description_list(start_marker, pattern, end_marker) - def default_options(self): - """ - Return the default options contained in HELP_SPEC_OPTIONS - """ - return { '-j', '--json', '-p', '--pretty', '-d', '--debug' } - def get_bashcomp_list(self, block_name): """ Search for and parse a list of type names from a variable in bash @@ -274,7 +276,56 @@ class SourceFileExtractor(FileExtractor): defined in children classes. """ def get_options(self): - return self.default_options().union(self.get_help_list_macro('HELP_SPEC_OPTIONS')) + return self.get_help_list_macro('HELP_SPEC_OPTIONS') + +class MainHeaderFileExtractor(SourceFileExtractor): + """ + An extractor for bpftool's main.h + """ + filename = os.path.join(BPFTOOL_DIR, 'main.h') + + def get_common_options(self): + """ + Parse the list of common options in main.h (options that apply to all + commands), which looks to the lists of options in other source files + but has different start and end markers: + + "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-d|--debug} | {-l|--legacy}" + + Return a set containing all options, such as: + + {'-p', '-d', '--legacy', '--pretty', '--debug', '--json', '-l', '-j'} + """ + start_marker = re.compile(f'"OPTIONS :=') + pattern = re.compile('([\w-]+) ?(?:\||}[ }\]"])') + end_marker = re.compile('#define') + + parser = InlineListParser(self.reader) + parser.search_block(start_marker) + return parser.parse(pattern, end_marker) + +class ManSubstitutionsExtractor(SourceFileExtractor): + """ + An extractor for substitutions.rst + """ + filename = os.path.join(BPFTOOL_DOC_DIR, 'substitutions.rst') + + def get_common_options(self): + """ + Parse the list of common options in substitutions.rst (options that + apply to all commands). + + Return a set containing all options, such as: + + {'-p', '-d', '--legacy', '--pretty', '--debug', '--json', '-l', '-j'} + """ + start_marker = re.compile('\|COMMON_OPTIONS\| replace:: {') + pattern = re.compile('\*\*([\w/-]+)\*\*') + end_marker = re.compile('}$') + + parser = InlineListParser(self.reader) + parser.search_block(start_marker) + return parser.parse(pattern, end_marker) class ProgFileExtractor(SourceFileExtractor): """ @@ -350,7 +401,7 @@ class BpfHeaderExtractor(FileExtractor): """ An extractor for the UAPI BPF header. """ - filename = os.path.join(LINUX_ROOT, 'tools/include/uapi/linux/bpf.h') + filename = os.path.join(INCLUDE_DIR, 'uapi/linux/bpf.h') def get_prog_types(self): return self.get_enum('bpf_prog_type') @@ -374,7 +425,7 @@ class ManProgExtractor(ManPageExtractor): """ An extractor for bpftool-prog.rst. """ - filename = os.path.join(BPFTOOL_DIR, 'Documentation/bpftool-prog.rst') + filename = os.path.join(BPFTOOL_DOC_DIR, 'bpftool-prog.rst') def get_attach_types(self): return self.get_rst_list('ATTACH_TYPE') @@ -383,7 +434,7 @@ class ManMapExtractor(ManPageExtractor): """ An extractor for bpftool-map.rst. """ - filename = os.path.join(BPFTOOL_DIR, 'Documentation/bpftool-map.rst') + filename = os.path.join(BPFTOOL_DOC_DIR, 'bpftool-map.rst') def get_map_types(self): return self.get_rst_list('TYPE') @@ -392,7 +443,7 @@ class ManCgroupExtractor(ManPageExtractor): """ An extractor for bpftool-cgroup.rst. """ - filename = os.path.join(BPFTOOL_DIR, 'Documentation/bpftool-cgroup.rst') + filename = os.path.join(BPFTOOL_DOC_DIR, 'bpftool-cgroup.rst') def get_attach_types(self): return self.get_rst_list('ATTACH_TYPE') @@ -411,7 +462,7 @@ class BashcompExtractor(FileExtractor): """ An extractor for bpftool's bash completion file. """ - filename = os.path.join(BPFTOOL_DIR, 'bash-completion/bpftool') + filename = os.path.join(BPFTOOL_BASHCOMP_DIR, 'bpftool') def get_prog_attach_types(self): return self.get_bashcomp_list('BPFTOOL_PROG_ATTACH_TYPES') @@ -562,7 +613,7 @@ def main(): help_cmd_options = source_info.get_options() source_info.close() - man_cmd_info = ManGenericExtractor(os.path.join('Documentation', 'bpftool-' + cmd + '.rst')) + man_cmd_info = ManGenericExtractor(os.path.join(BPFTOOL_DOC_DIR, 'bpftool-' + cmd + '.rst')) man_cmd_options = man_cmd_info.get_options() man_cmd_info.close() @@ -573,13 +624,26 @@ def main(): help_main_options = source_main_info.get_options() source_main_info.close() - man_main_info = ManGenericExtractor(os.path.join('Documentation', 'bpftool.rst')) + man_main_info = ManGenericExtractor(os.path.join(BPFTOOL_DOC_DIR, 'bpftool.rst')) man_main_options = man_main_info.get_options() man_main_info.close() verify(help_main_options, man_main_options, f'Comparing {source_main_info.filename} (do_help() OPTIONS) and {man_main_info.filename} (OPTIONS):') + # Compare common options (options that apply to all commands) + + main_hdr_info = MainHeaderFileExtractor() + source_common_options = main_hdr_info.get_common_options() + main_hdr_info.close() + + man_substitutions = ManSubstitutionsExtractor() + man_common_options = man_substitutions.get_common_options() + man_substitutions.close() + + verify(source_common_options, man_common_options, + f'Comparing common options from {main_hdr_info.filename} (HELP_SPEC_OPTIONS) and {man_substitutions.filename}:') + sys.exit(retval) if __name__ == "__main__": diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index a63787e7bb1a..5b8314cd77fd 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -51,15 +51,15 @@ int main(int argc, char **argv) goto err; } - map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key), - sizeof(value), 0, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_STORAGE, NULL, sizeof(key), + sizeof(value), 0, NULL); if (map_fd < 0) { printf("Failed to create map: %s\n", strerror(errno)); goto out; } - percpu_map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, - sizeof(key), sizeof(value), 0, 0); + percpu_map_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, NULL, + sizeof(key), sizeof(value), 0, NULL); if (percpu_map_fd < 0) { printf("Failed to create map: %s\n", strerror(errno)); goto out; diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c index 006be3963977..baa3e3ecae82 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -208,6 +208,7 @@ static void test_lpm_order(void) static void test_lpm_map(int keysize) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); size_t i, j, n_matches, n_matches_after_delete, n_nodes, n_lookups; struct tlpm_node *t, *list = NULL; struct bpf_lpm_trie_key *key; @@ -233,11 +234,11 @@ static void test_lpm_map(int keysize) key = alloca(sizeof(*key) + keysize); memset(key, 0, sizeof(*key) + keysize); - map = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + map = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, sizeof(*key) + keysize, keysize + 1, 4096, - BPF_F_NO_PREALLOC); + &opts); assert(map >= 0); for (i = 0; i < n_nodes; ++i) { @@ -329,6 +330,7 @@ static void test_lpm_map(int keysize) static void test_lpm_ipaddr(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); struct bpf_lpm_trie_key *key_ipv4; struct bpf_lpm_trie_key *key_ipv6; size_t key_size_ipv4; @@ -342,14 +344,14 @@ static void test_lpm_ipaddr(void) key_ipv4 = alloca(key_size_ipv4); key_ipv6 = alloca(key_size_ipv6); - map_fd_ipv4 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + map_fd_ipv4 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size_ipv4, sizeof(value), - 100, BPF_F_NO_PREALLOC); + 100, &opts); assert(map_fd_ipv4 >= 0); - map_fd_ipv6 = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + map_fd_ipv6 = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size_ipv6, sizeof(value), - 100, BPF_F_NO_PREALLOC); + 100, &opts); assert(map_fd_ipv6 >= 0); /* Fill data some IPv4 and IPv6 address ranges */ @@ -423,6 +425,7 @@ static void test_lpm_ipaddr(void) static void test_lpm_delete(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); struct bpf_lpm_trie_key *key; size_t key_size; int map_fd; @@ -431,9 +434,9 @@ static void test_lpm_delete(void) key_size = sizeof(*key) + sizeof(__u32); key = alloca(key_size); - map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, sizeof(value), - 100, BPF_F_NO_PREALLOC); + 100, &opts); assert(map_fd >= 0); /* Add nodes: @@ -535,6 +538,7 @@ static void test_lpm_delete(void) static void test_lpm_get_next_key(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); struct bpf_lpm_trie_key *key_p, *next_key_p; size_t key_size; __u32 value = 0; @@ -544,8 +548,7 @@ static void test_lpm_get_next_key(void) key_p = alloca(key_size); next_key_p = alloca(key_size); - map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, sizeof(value), - 100, BPF_F_NO_PREALLOC); + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, sizeof(value), 100, &opts); assert(map_fd >= 0); /* empty tree. get_next_key should return ENOENT */ @@ -753,6 +756,7 @@ static void setup_lpm_mt_test_info(struct lpm_mt_test_info *info, int map_fd) static void test_lpm_multi_thread(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); struct lpm_mt_test_info info[4]; size_t key_size, value_size; pthread_t thread_id[4]; @@ -762,8 +766,7 @@ static void test_lpm_multi_thread(void) /* create a trie */ value_size = sizeof(__u32); key_size = sizeof(struct bpf_lpm_trie_key) + value_size; - map_fd = bpf_create_map(BPF_MAP_TYPE_LPM_TRIE, key_size, value_size, - 100, BPF_F_NO_PREALLOC); + map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, value_size, 100, &opts); /* create 4 threads to test update, delete, lookup and get_next_key */ setup_lpm_mt_test_info(&info[0], map_fd); diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c index 7f3d1d8460b4..b9f1bbbc8aba 100644 --- a/tools/testing/selftests/bpf/test_lru_map.c +++ b/tools/testing/selftests/bpf/test_lru_map.c @@ -28,13 +28,14 @@ static int nr_cpus; static int create_map(int map_type, int map_flags, unsigned int size) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = map_flags); int map_fd; - map_fd = bpf_create_map(map_type, sizeof(unsigned long long), - sizeof(unsigned long long), size, map_flags); + map_fd = bpf_map_create(map_type, NULL, sizeof(unsigned long long), + sizeof(unsigned long long), size, &opts); if (map_fd == -1) - perror("bpf_create_map"); + perror("bpf_map_create"); return map_fd; } @@ -42,7 +43,6 @@ static int create_map(int map_type, int map_flags, unsigned int size) static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, void *value) { - struct bpf_create_map_attr map; struct bpf_insn insns[] = { BPF_LD_MAP_VALUE(BPF_REG_9, 0, 0), BPF_LD_MAP_FD(BPF_REG_1, fd), @@ -63,13 +63,7 @@ static int bpf_map_lookup_elem_with_ref_bit(int fd, unsigned long long key, int mfd, pfd, ret, zero = 0; __u32 retval = 0; - memset(&map, 0, sizeof(map)); - map.map_type = BPF_MAP_TYPE_ARRAY; - map.key_size = sizeof(int); - map.value_size = sizeof(unsigned long long); - map.max_entries = 1; - - mfd = bpf_create_map_xattr(&map); + mfd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), sizeof(__u64), 1, NULL); if (mfd < 0) return -1; diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 8b31bc1a801d..f4cd658bbe00 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -33,15 +33,14 @@ static int skips; -static int map_flags; +static struct bpf_map_create_opts map_opts = { .sz = sizeof(map_opts) }; static void test_hashmap(unsigned int task, void *data) { long long key, next_key, first_key, value; int fd; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - 2, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), 2, &map_opts); if (fd < 0) { printf("Failed to create hashmap '%s'!\n", strerror(errno)); exit(1); @@ -138,8 +137,7 @@ static void test_hashmap_sizes(unsigned int task, void *data) for (i = 1; i <= 512; i <<= 1) for (j = 1; j <= 1 << 18; j <<= 1) { - fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j, - 2, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, i, j, 2, &map_opts); if (fd < 0) { if (errno == ENOMEM) return; @@ -160,8 +158,8 @@ static void test_hashmap_percpu(unsigned int task, void *data) int expected_key_mask = 0; int fd, i; - fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key), - sizeof(bpf_percpu(value, 0)), 2, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_HASH, NULL, sizeof(key), + sizeof(bpf_percpu(value, 0)), 2, &map_opts); if (fd < 0) { printf("Failed to create hashmap '%s'!\n", strerror(errno)); exit(1); @@ -272,11 +270,11 @@ static int helper_fill_hashmap(int max_entries) int i, fd, ret; long long key, value; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - max_entries, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + max_entries, &map_opts); CHECK(fd < 0, "failed to create hashmap", - "err: %s, flags: 0x%x\n", strerror(errno), map_flags); + "err: %s, flags: 0x%x\n", strerror(errno), map_opts.map_flags); for (i = 0; i < max_entries; i++) { key = i; value = key; @@ -332,8 +330,8 @@ static void test_hashmap_zero_seed(void) int i, first, second, old_flags; long long key, next_first, next_second; - old_flags = map_flags; - map_flags |= BPF_F_ZERO_SEED; + old_flags = map_opts.map_flags; + map_opts.map_flags |= BPF_F_ZERO_SEED; first = helper_fill_hashmap(3); second = helper_fill_hashmap(3); @@ -355,7 +353,7 @@ static void test_hashmap_zero_seed(void) key = next_first; } - map_flags = old_flags; + map_opts.map_flags = old_flags; close(first); close(second); } @@ -365,8 +363,7 @@ static void test_arraymap(unsigned int task, void *data) int key, next_key, fd; long long value; - fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(key), sizeof(value), - 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(key), sizeof(value), 2, NULL); if (fd < 0) { printf("Failed to create arraymap '%s'!\n", strerror(errno)); exit(1); @@ -421,8 +418,8 @@ static void test_arraymap_percpu(unsigned int task, void *data) BPF_DECLARE_PERCPU(long, values); int key, next_key, fd, i; - fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(bpf_percpu(values, 0)), 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, sizeof(key), + sizeof(bpf_percpu(values, 0)), 2, NULL); if (fd < 0) { printf("Failed to create arraymap '%s'!\n", strerror(errno)); exit(1); @@ -484,8 +481,8 @@ static void test_arraymap_percpu_many_keys(void) unsigned int nr_keys = 2000; int key, fd, i; - fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key), - sizeof(bpf_percpu(values, 0)), nr_keys, 0); + fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, sizeof(key), + sizeof(bpf_percpu(values, 0)), nr_keys, NULL); if (fd < 0) { printf("Failed to create per-cpu arraymap '%s'!\n", strerror(errno)); @@ -516,8 +513,7 @@ static void test_devmap(unsigned int task, void *data) int fd; __u32 key, value; - fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP, sizeof(key), sizeof(value), - 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_DEVMAP, NULL, sizeof(key), sizeof(value), 2, NULL); if (fd < 0) { printf("Failed to create devmap '%s'!\n", strerror(errno)); exit(1); @@ -531,8 +527,7 @@ static void test_devmap_hash(unsigned int task, void *data) int fd; __u32 key, value; - fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP_HASH, sizeof(key), sizeof(value), - 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_DEVMAP_HASH, NULL, sizeof(key), sizeof(value), 2, NULL); if (fd < 0) { printf("Failed to create devmap_hash '%s'!\n", strerror(errno)); exit(1); @@ -552,14 +547,12 @@ static void test_queuemap(unsigned int task, void *data) vals[i] = rand(); /* Invalid key size */ - fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 4, sizeof(val), MAP_SIZE, - map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_QUEUE, NULL, 4, sizeof(val), MAP_SIZE, &map_opts); assert(fd < 0 && errno == EINVAL); - fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 0, sizeof(val), MAP_SIZE, - map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_QUEUE, NULL, 0, sizeof(val), MAP_SIZE, &map_opts); /* Queue map does not support BPF_F_NO_PREALLOC */ - if (map_flags & BPF_F_NO_PREALLOC) { + if (map_opts.map_flags & BPF_F_NO_PREALLOC) { assert(fd < 0 && errno == EINVAL); return; } @@ -610,14 +603,12 @@ static void test_stackmap(unsigned int task, void *data) vals[i] = rand(); /* Invalid key size */ - fd = bpf_create_map(BPF_MAP_TYPE_STACK, 4, sizeof(val), MAP_SIZE, - map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_STACK, NULL, 4, sizeof(val), MAP_SIZE, &map_opts); assert(fd < 0 && errno == EINVAL); - fd = bpf_create_map(BPF_MAP_TYPE_STACK, 0, sizeof(val), MAP_SIZE, - map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_STACK, NULL, 0, sizeof(val), MAP_SIZE, &map_opts); /* Stack map does not support BPF_F_NO_PREALLOC */ - if (map_flags & BPF_F_NO_PREALLOC) { + if (map_opts.map_flags & BPF_F_NO_PREALLOC) { assert(fd < 0 && errno == EINVAL); return; } @@ -744,9 +735,9 @@ static void test_sockmap(unsigned int tasks, void *data) } /* Test sockmap with connected sockets */ - fd = bpf_create_map(BPF_MAP_TYPE_SOCKMAP, + fd = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(key), sizeof(value), - 6, 0); + 6, NULL); if (fd < 0) { if (!bpf_probe_map_type(BPF_MAP_TYPE_SOCKMAP, 0)) { printf("%s SKIP (unsupported map type BPF_MAP_TYPE_SOCKMAP)\n", @@ -1168,8 +1159,7 @@ static void test_map_in_map(void) obj = bpf_object__open(MAPINMAP_PROG); - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), sizeof(int), - 2, 0); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(int), sizeof(int), 2, NULL); if (fd < 0) { printf("Failed to create hashmap '%s'!\n", strerror(errno)); exit(1); @@ -1315,8 +1305,8 @@ static void test_map_large(void) } key; int fd, i, value; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + MAP_SIZE, &map_opts); if (fd < 0) { printf("Failed to create large map '%s'!\n", strerror(errno)); exit(1); @@ -1469,8 +1459,8 @@ static void test_map_parallel(void) int i, fd, key = 0, value = 0; int data[2]; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE, map_flags); + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + MAP_SIZE, &map_opts); if (fd < 0) { printf("Failed to create map for parallel test '%s'!\n", strerror(errno)); @@ -1518,9 +1508,13 @@ static void test_map_parallel(void) static void test_map_rdonly(void) { int fd, key = 0, value = 0; + __u32 old_flags; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE, map_flags | BPF_F_RDONLY); + old_flags = map_opts.map_flags; + map_opts.map_flags |= BPF_F_RDONLY; + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + MAP_SIZE, &map_opts); + map_opts.map_flags = old_flags; if (fd < 0) { printf("Failed to create map for read only test '%s'!\n", strerror(errno)); @@ -1543,9 +1537,13 @@ static void test_map_rdonly(void) static void test_map_wronly_hash(void) { int fd, key = 0, value = 0; + __u32 old_flags; - fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), - MAP_SIZE, map_flags | BPF_F_WRONLY); + old_flags = map_opts.map_flags; + map_opts.map_flags |= BPF_F_WRONLY; + fd = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(key), sizeof(value), + MAP_SIZE, &map_opts); + map_opts.map_flags = old_flags; if (fd < 0) { printf("Failed to create map for write only test '%s'!\n", strerror(errno)); @@ -1567,13 +1565,17 @@ static void test_map_wronly_hash(void) static void test_map_wronly_stack_or_queue(enum bpf_map_type map_type) { int fd, value = 0; + __u32 old_flags; + assert(map_type == BPF_MAP_TYPE_QUEUE || map_type == BPF_MAP_TYPE_STACK); - fd = bpf_create_map(map_type, 0, sizeof(value), MAP_SIZE, - map_flags | BPF_F_WRONLY); + old_flags = map_opts.map_flags; + map_opts.map_flags |= BPF_F_WRONLY; + fd = bpf_map_create(map_type, NULL, 0, sizeof(value), MAP_SIZE, &map_opts); + map_opts.map_flags = old_flags; /* Stack/Queue maps do not support BPF_F_NO_PREALLOC */ - if (map_flags & BPF_F_NO_PREALLOC) { + if (map_opts.map_flags & BPF_F_NO_PREALLOC) { assert(fd < 0 && errno == EINVAL); return; } @@ -1700,8 +1702,8 @@ static void test_reuseport_array(void) __u32 fds_idx = 0; int fd; - map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, - sizeof(__u32), sizeof(__u64), array_size, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, NULL, + sizeof(__u32), sizeof(__u64), array_size, NULL); CHECK(map_fd < 0, "reuseport array create", "map_fd:%d, errno:%d\n", map_fd, errno); @@ -1837,8 +1839,8 @@ static void test_reuseport_array(void) close(map_fd); /* Test 32 bit fd */ - map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, - sizeof(__u32), sizeof(__u32), array_size, 0); + map_fd = bpf_map_create(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, NULL, + sizeof(__u32), sizeof(__u32), array_size, NULL); CHECK(map_fd < 0, "reuseport array create", "map_fd:%d, errno:%d\n", map_fd, errno); prepare_reuseport_grp(SOCK_STREAM, map_fd, sizeof(__u32), &fd64, @@ -1896,10 +1898,10 @@ int main(void) libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - map_flags = 0; + map_opts.map_flags = 0; run_all_tests(); - map_flags = BPF_F_NO_PREALLOC; + map_opts.map_flags = BPF_F_NO_PREALLOC; run_all_tests(); #define DEFINE_TEST(name) test_##name(); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index c65986bd9d07..296928948bb9 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -473,11 +473,11 @@ static struct prog_test_def prog_test_defs[] = { #include <prog_tests/tests.h> #undef DEFINE_TEST }; -const int prog_test_cnt = ARRAY_SIZE(prog_test_defs); +static const int prog_test_cnt = ARRAY_SIZE(prog_test_defs); const char *argp_program_version = "test_progs 0.1"; const char *argp_program_bug_address = "<bpf@vger.kernel.org>"; -const char argp_program_doc[] = "BPF selftests test runner"; +static const char argp_program_doc[] = "BPF selftests test runner"; enum ARG_KEYS { ARG_TEST_NUM = 'n', @@ -939,7 +939,7 @@ static void *dispatch_thread(void *ctx) { struct dispatch_data *data = ctx; int sock_fd; - FILE *log_fd = NULL; + FILE *log_fp = NULL; sock_fd = data->sock_fd; @@ -1002,8 +1002,8 @@ static void *dispatch_thread(void *ctx) /* collect all logs */ if (msg_test_done.test_done.have_log) { - log_fd = open_memstream(&result->log_buf, &result->log_cnt); - if (!log_fd) + log_fp = open_memstream(&result->log_buf, &result->log_cnt); + if (!log_fp) goto error; while (true) { @@ -1014,12 +1014,12 @@ static void *dispatch_thread(void *ctx) if (msg_log.type != MSG_TEST_LOG) goto error; - fprintf(log_fd, "%s", msg_log.test_log.log_buf); + fprintf(log_fp, "%s", msg_log.test_log.log_buf); if (msg_log.test_log.is_last) break; } - fclose(log_fd); - log_fd = NULL; + fclose(log_fp); + log_fp = NULL; } /* output log */ { @@ -1045,8 +1045,8 @@ error: if (env.debug) fprintf(stderr, "[%d]: Protocol/IO error: %s.\n", data->worker_id, strerror(errno)); - if (log_fd) - fclose(log_fd); + if (log_fp) + fclose(log_fp); done: { struct msg msg_exit; @@ -1198,11 +1198,11 @@ static int server_main(void) env.sub_succ_cnt += result->sub_succ_cnt; } + print_all_error_logs(); + fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); - print_all_error_logs(); - /* reap all workers */ for (i = 0; i < env.workers; i++) { int wstatus, pid; @@ -1484,11 +1484,11 @@ int main(int argc, char **argv) if (env.list_test_names) goto out; + print_all_error_logs(); + fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n", env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt); - print_all_error_logs(); - close(env.saved_netns_fd); out: if (!env.list_test_names && env.has_testmod) diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 05c9e4944c01..f0c8d05ba6d1 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -663,23 +663,36 @@ static int load_insns(const struct sock_addr_test *test, static int load_path(const struct sock_addr_test *test, const char *path) { - struct bpf_prog_load_attr attr; struct bpf_object *obj; - int prog_fd; + struct bpf_program *prog; + int err; - memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); - attr.file = path; - attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - attr.expected_attach_type = test->expected_attach_type; - attr.prog_flags = BPF_F_TEST_RND_HI32; + obj = bpf_object__open_file(path, NULL); + err = libbpf_get_error(obj); + if (err) { + log_err(">>> Opening BPF object (%s) error.\n", path); + return -1; + } + + prog = bpf_object__next_program(obj, NULL); + if (!prog) + goto err_out; - if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) { + bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR); + bpf_program__set_expected_attach_type(prog, test->expected_attach_type); + bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32); + + err = bpf_object__load(obj); + if (err) { if (test->expected_result != LOAD_REJECT) log_err(">>> Loading program (%s) error.\n", path); - return -1; + goto err_out; } - return prog_fd; + return bpf_program__fd(prog); +err_out: + bpf_object__close(obj); + return -1; } static int bind4_prog_load(const struct sock_addr_test *test) diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c index 5c7bea525626..0851c42ee31c 100644 --- a/tools/testing/selftests/bpf/test_tag.c +++ b/tools/testing/selftests/bpf/test_tag.c @@ -185,11 +185,12 @@ static void do_test(uint32_t *tests, int start_insns, int fd_map, int main(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC); uint32_t tests = 0; int i, fd_map; - fd_map = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(int), - sizeof(int), 1, BPF_F_NO_PREALLOC); + fd_map = bpf_map_create(BPF_MAP_TYPE_HASH, NULL, sizeof(int), + sizeof(int), 1, &opts); assert(fd_map > 0); for (i = 0; i < 5; i++) { diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 9fbef396a716..4f1fe8af10a4 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -54,7 +54,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_TEST_INSNS 1000000 #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 21 +#define MAX_NR_MAPS 22 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -462,11 +462,11 @@ static int __create_map(uint32_t type, uint32_t size_key, uint32_t size_value, uint32_t max_elem, uint32_t extra_flags) { + LIBBPF_OPTS(bpf_map_create_opts, opts); int fd; - fd = bpf_create_map(type, size_key, size_value, max_elem, - (type == BPF_MAP_TYPE_HASH ? - BPF_F_NO_PREALLOC : 0) | extra_flags); + opts.map_flags = (type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0) | extra_flags; + fd = bpf_map_create(type, NULL, size_key, size_value, max_elem, &opts); if (fd < 0) { if (skip_unsupported_map(type)) return -1; @@ -522,8 +522,8 @@ static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, { int mfd, p1fd, p2fd, p3fd; - mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), - sizeof(int), max_elem, 0); + mfd = bpf_map_create(BPF_MAP_TYPE_PROG_ARRAY, NULL, sizeof(int), + sizeof(int), max_elem, NULL); if (mfd < 0) { if (skip_unsupported_map(BPF_MAP_TYPE_PROG_ARRAY)) return -1; @@ -553,10 +553,11 @@ err: static int create_map_in_map(void) { + LIBBPF_OPTS(bpf_map_create_opts, opts); int inner_map_fd, outer_map_fd; - inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), - sizeof(int), 1, 0); + inner_map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, sizeof(int), + sizeof(int), 1, NULL); if (inner_map_fd < 0) { if (skip_unsupported_map(BPF_MAP_TYPE_ARRAY)) return -1; @@ -564,8 +565,9 @@ static int create_map_in_map(void) return inner_map_fd; } - outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, - sizeof(int), inner_map_fd, 1, 0); + opts.inner_map_fd = inner_map_fd; + outer_map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, + sizeof(int), sizeof(int), 1, &opts); if (outer_map_fd < 0) { if (skip_unsupported_map(BPF_MAP_TYPE_ARRAY_OF_MAPS)) return -1; @@ -584,8 +586,8 @@ static int create_cgroup_storage(bool percpu) BPF_MAP_TYPE_CGROUP_STORAGE; int fd; - fd = bpf_create_map(type, sizeof(struct bpf_cgroup_storage_key), - TEST_DATA_LEN, 0, 0); + fd = bpf_map_create(type, NULL, sizeof(struct bpf_cgroup_storage_key), + TEST_DATA_LEN, 0, NULL); if (fd < 0) { if (skip_unsupported_map(type)) return -1; @@ -652,7 +654,7 @@ static int load_btf(void) memcpy(ptr, btf_str_sec, hdr.str_len); ptr += hdr.str_len; - btf_fd = bpf_load_btf(raw_btf, ptr - raw_btf, 0, 0, 0); + btf_fd = bpf_btf_load(raw_btf, ptr - raw_btf, NULL); free(raw_btf); if (btf_fd < 0) return -1; @@ -661,22 +663,17 @@ static int load_btf(void) static int create_map_spin_lock(void) { - struct bpf_create_map_attr attr = { - .name = "test_map", - .map_type = BPF_MAP_TYPE_ARRAY, - .key_size = 4, - .value_size = 8, - .max_entries = 1, + LIBBPF_OPTS(bpf_map_create_opts, opts, .btf_key_type_id = 1, .btf_value_type_id = 3, - }; + ); int fd, btf_fd; btf_fd = load_btf(); if (btf_fd < 0) return -1; - attr.btf_fd = btf_fd; - fd = bpf_create_map_xattr(&attr); + opts.btf_fd = btf_fd; + fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "test_map", 4, 8, 1, &opts); if (fd < 0) printf("Failed to create map with spin_lock\n"); return fd; @@ -684,24 +681,19 @@ static int create_map_spin_lock(void) static int create_sk_storage_map(void) { - struct bpf_create_map_attr attr = { - .name = "test_map", - .map_type = BPF_MAP_TYPE_SK_STORAGE, - .key_size = 4, - .value_size = 8, - .max_entries = 0, + LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC, .btf_key_type_id = 1, .btf_value_type_id = 3, - }; + ); int fd, btf_fd; btf_fd = load_btf(); if (btf_fd < 0) return -1; - attr.btf_fd = btf_fd; - fd = bpf_create_map_xattr(&attr); - close(attr.btf_fd); + opts.btf_fd = btf_fd; + fd = bpf_map_create(BPF_MAP_TYPE_SK_STORAGE, "test_map", 4, 8, 0, &opts); + close(opts.btf_fd); if (fd < 0) printf("Failed to create sk_storage_map\n"); return fd; diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 52c2f24e0898..795b6798ccee 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -88,12 +88,15 @@ int extra_prog_load_log_flags = 0; int bpf_prog_test_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd) { - struct bpf_object_load_attr attr = {}; + LIBBPF_OPTS(bpf_object_open_opts, opts, + .kernel_log_level = extra_prog_load_log_flags, + ); struct bpf_object *obj; struct bpf_program *prog; + __u32 flags; int err; - obj = bpf_object__open(file); + obj = bpf_object__open_file(file, &opts); if (!obj) return -errno; @@ -106,11 +109,10 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type, if (type != BPF_PROG_TYPE_UNSPEC) bpf_program__set_type(prog, type); - bpf_program__set_extra_flags(prog, BPF_F_TEST_RND_HI32); + flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32; + bpf_program__set_flags(prog, flags); - attr.obj = obj; - attr.log_level = extra_prog_load_log_flags; - err = bpf_object__load_xattr(&attr); + err = bpf_object__load(obj); if (err) goto err_out; diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c index c22dc83a41fd..b39665f33524 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c +++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c @@ -138,6 +138,8 @@ BPF_EXIT_INSN(), }, .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr into mem", }, { "Dest pointer in r0 - succeed", @@ -156,4 +158,88 @@ BPF_EXIT_INSN(), }, .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr into mem", +}, +{ + "Dest pointer in r0 - succeed, check 2", + .insns = { + /* r0 = &val */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + /* val = r0; */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + /* r5 = &val */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_10), + /* r0 = atomic_cmpxchg(&val, r0, r5); */ + BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8), + /* r1 = *r0 */ + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr into mem", +}, +{ + "Dest pointer in r0 - succeed, check 3", + .insns = { + /* r0 = &val */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + /* val = r0; */ + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + /* r5 = &val */ + BPF_MOV64_REG(BPF_REG_5, BPF_REG_10), + /* r0 = atomic_cmpxchg(&val, r0, r5); */ + BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid size of register fill", + .errstr_unpriv = "R0 leaks addr into mem", +}, +{ + "Dest pointer in r0 - succeed, check 4", + .insns = { + /* r0 = &val */ + BPF_MOV32_REG(BPF_REG_0, BPF_REG_10), + /* val = r0; */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8), + /* r5 = &val */ + BPF_MOV32_REG(BPF_REG_5, BPF_REG_10), + /* r0 = atomic_cmpxchg(&val, r0, r5); */ + BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8), + /* r1 = *r10 */ + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -8), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R10 partial copy of pointer", +}, +{ + "Dest pointer in r0 - succeed, check 5", + .insns = { + /* r0 = &val */ + BPF_MOV32_REG(BPF_REG_0, BPF_REG_10), + /* val = r0; */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8), + /* r5 = &val */ + BPF_MOV32_REG(BPF_REG_5, BPF_REG_10), + /* r0 = atomic_cmpxchg(&val, r0, r5); */ + BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8), + /* r1 = *r0 */ + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -8), + /* exit(0); */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "R0 invalid mem access", + .errstr_unpriv = "R10 partial copy of pointer", }, diff --git a/tools/testing/selftests/bpf/verifier/atomic_fetch.c b/tools/testing/selftests/bpf/verifier/atomic_fetch.c index 3bc9ff7a860b..5bf03fb4fa2b 100644 --- a/tools/testing/selftests/bpf/verifier/atomic_fetch.c +++ b/tools/testing/selftests/bpf/verifier/atomic_fetch.c @@ -1,3 +1,97 @@ +{ + "atomic dw/fetch and address leakage of (map ptr & -1) via stack slot", + .insns = { + BPF_LD_IMM64(BPF_REG_1, -1), + BPF_LD_MAP_FD(BPF_REG_8, 0), + BPF_LD_MAP_FD(BPF_REG_9, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0), + BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_2, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 2, 4 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "leaking pointer from stack off -8", +}, +{ + "atomic dw/fetch and address leakage of (map ptr & -1) via returned value", + .insns = { + BPF_LD_IMM64(BPF_REG_1, -1), + BPF_LD_MAP_FD(BPF_REG_8, 0), + BPF_LD_MAP_FD(BPF_REG_9, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0), + BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_9, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 2, 4 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "leaking pointer from stack off -8", +}, +{ + "atomic w/fetch and address leakage of (map ptr & -1) via stack slot", + .insns = { + BPF_LD_IMM64(BPF_REG_1, -1), + BPF_LD_MAP_FD(BPF_REG_8, 0), + BPF_LD_MAP_FD(BPF_REG_9, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0), + BPF_ATOMIC_OP(BPF_W, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_2, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 2, 4 }, + .result = REJECT, + .errstr = "invalid size of register fill", +}, +{ + "atomic w/fetch and address leakage of (map ptr & -1) via returned value", + .insns = { + BPF_LD_IMM64(BPF_REG_1, -1), + BPF_LD_MAP_FD(BPF_REG_8, 0), + BPF_LD_MAP_FD(BPF_REG_9, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0), + BPF_ATOMIC_OP(BPF_W, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_9, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 2, 4 }, + .result = REJECT, + .errstr = "invalid size of register fill", +}, #define __ATOMIC_FETCH_OP_TEST(src_reg, dst_reg, operand1, op, operand2, expect) \ { \ "atomic fetch " #op ", src=" #dst_reg " dst=" #dst_reg, \ diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 7e50cb80873a..682519769fe3 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -133,6 +133,77 @@ .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "precision tracking for u32 spill/fill", + .insns = { + BPF_MOV64_REG(BPF_REG_7, BPF_REG_1), + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV32_IMM(BPF_REG_6, 32), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV32_IMM(BPF_REG_6, 4), + /* Additional insns to introduce a pruning point. */ + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, 0), + /* u32 spill/fill */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -8), + BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_10, -8), + /* out-of-bound map value access for r6=32 */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 15 }, + .result = REJECT, + .errstr = "R0 min value is outside of the allowed memory range", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "precision tracking for u32 spills, u64 fill", + .insns = { + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV32_IMM(BPF_REG_7, 0xffffffff), + /* Additional insns to introduce a pruning point. */ + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0), + /* u32 spills, u64 fill */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, -8), + /* if r8 != X goto pc+1 r8 known in fallthrough branch */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_8, 0xffffffff, 1), + BPF_MOV64_IMM(BPF_REG_3, 1), + /* if r8 == X goto pc+1 condition always true on first + * traversal, so starts backtracking to mark r8 as requiring + * precision. r7 marked as needing precision. r6 not marked + * since it's not tracked. + */ + BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 0xffffffff, 1), + /* fails if r8 correctly marked unknown after fill. */ + BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "div by zero", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ "allocated_stack", .insns = { BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index 7ab3de108761..6c907144311f 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -176,6 +176,38 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { + "Spill u32 const scalars. Refill as u64. Offset to skb->data", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + /* r6 = 0 */ + BPF_MOV32_IMM(BPF_REG_6, 0), + /* r7 = 20 */ + BPF_MOV32_IMM(BPF_REG_7, 20), + /* *(u32 *)(r10 -4) = r6 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4), + /* *(u32 *)(r10 -8) = r7 */ + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8), + /* r4 = *(u64 *)(r10 -8) */ + BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8), + /* r0 = r2 */ + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4), + /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1), + /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid access to packet", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ "Spill a u32 const scalar. Refill as u16 from fp-6. Offset to skb->data", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index 2debba4e8a3a..4d347bc53aa2 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -1078,6 +1078,29 @@ .errstr_unpriv = "R0 pointer -= pointer prohibited", }, { + "map access: trying to leak tained dst reg", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV32_IMM(BPF_REG_1, 0xFFFFFFFF), + BPF_MOV32_REG(BPF_REG_1, BPF_REG_1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 4 }, + .result = REJECT, + .errstr = "math between map_value pointer and 4294967295 is not allowed", +}, +{ "32bit pkt_ptr -= scalar", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1, diff --git a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c index bfb97383e6b5..b4ec228eb95d 100644 --- a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c +++ b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c @@ -35,7 +35,7 @@ .prog_type = BPF_PROG_TYPE_XDP, }, { - "XDP pkt read, pkt_data' > pkt_end, good access", + "XDP pkt read, pkt_data' > pkt_end, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -88,6 +88,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data' > pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' > pkt_end, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_end > pkt_data', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -106,16 +141,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end > pkt_data', bad access 1", + "XDP pkt read, pkt_end > pkt_data', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -143,6 +178,42 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_end > pkt_data', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end > pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data' < pkt_end, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -161,16 +232,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data' < pkt_end, bad access 1", + "XDP pkt read, pkt_data' < pkt_end, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -198,7 +269,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end < pkt_data', good access", + "XDP pkt read, pkt_data' < pkt_end, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' < pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end < pkt_data', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -251,6 +358,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_end < pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end < pkt_data', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data' >= pkt_end, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -268,15 +410,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data' >= pkt_end, bad access 1", + "XDP pkt read, pkt_data' >= pkt_end, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -304,7 +446,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end >= pkt_data', good access", + "XDP pkt read, pkt_data' >= pkt_end, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' >= pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end >= pkt_data', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -359,7 +535,44 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data' <= pkt_end, good access", + "XDP pkt read, pkt_end >= pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end >= pkt_data', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' <= pkt_end, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, @@ -414,6 +627,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data' <= pkt_end, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data' <= pkt_end, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_end <= pkt_data', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), @@ -431,15 +681,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_end <= pkt_data', bad access 1", + "XDP pkt read, pkt_end <= pkt_data', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data_end)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -467,7 +717,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' > pkt_data, good access", + "XDP pkt read, pkt_end <= pkt_data', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_end <= pkt_data', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, + offsetof(struct xdp_md, data_end)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' > pkt_data, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -520,6 +804,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_meta' > pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' > pkt_data, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data > pkt_meta', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -538,16 +857,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data > pkt_meta', bad access 1", + "XDP pkt read, pkt_data > pkt_meta', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -575,6 +894,42 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data > pkt_meta', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data > pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_meta' < pkt_data, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -593,16 +948,16 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' < pkt_data, bad access 1", + "XDP pkt read, pkt_meta' < pkt_data, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), BPF_JMP_IMM(BPF_JA, 0, 0, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -630,7 +985,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data < pkt_meta', good access", + "XDP pkt read, pkt_meta' < pkt_data, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' < pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data < pkt_meta', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -683,6 +1074,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_data < pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data < pkt_meta', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_meta' >= pkt_data, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -700,15 +1126,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' >= pkt_data, bad access 1", + "XDP pkt read, pkt_meta' >= pkt_data, corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -736,7 +1162,41 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data >= pkt_meta', good access", + "XDP pkt read, pkt_meta' >= pkt_data, corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' >= pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data >= pkt_meta', corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -791,7 +1251,44 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_meta' <= pkt_data, good access", + "XDP pkt read, pkt_data >= pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data >= pkt_meta', corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' <= pkt_data, corner case, good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), @@ -846,6 +1343,43 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { + "XDP pkt read, pkt_meta' <= pkt_data, corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_meta' <= pkt_data, corner case -1, bad access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1), + BPF_JMP_IMM(BPF_JA, 0, 0, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "R1 offset is outside of the packet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ "XDP pkt read, pkt_data <= pkt_meta', good access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -863,15 +1397,15 @@ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { - "XDP pkt read, pkt_data <= pkt_meta', bad access 1", + "XDP pkt read, pkt_data <= pkt_meta', corner case -1, bad access", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data_meta)), BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), - BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6), BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), - BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, @@ -898,3 +1432,37 @@ .prog_type = BPF_PROG_TYPE_XDP, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, +{ + "XDP pkt read, pkt_data <= pkt_meta', corner case, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "XDP pkt read, pkt_data <= pkt_meta', corner case +1, good access", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct xdp_md, data_meta)), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_2), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8), + BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_XDP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index 027198768fad..5e43c79ddc6e 100755 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -4,17 +4,34 @@ set -u set -e -# This script currently only works for x86_64, as -# it is based on the VM image used by the BPF CI which is -# x86_64. -QEMU_BINARY="${QEMU_BINARY:="qemu-system-x86_64"}" -X86_BZIMAGE="arch/x86/boot/bzImage" +# This script currently only works for x86_64 and s390x, as +# it is based on the VM image used by the BPF CI, which is +# available only for these architectures. +ARCH="$(uname -m)" +case "${ARCH}" in +s390x) + QEMU_BINARY=qemu-system-s390x + QEMU_CONSOLE="ttyS1" + QEMU_FLAGS=(-smp 2) + BZIMAGE="arch/s390/boot/compressed/vmlinux" + ;; +x86_64) + QEMU_BINARY=qemu-system-x86_64 + QEMU_CONSOLE="ttyS0,115200" + QEMU_FLAGS=(-cpu host -smp 8) + BZIMAGE="arch/x86/boot/bzImage" + ;; +*) + echo "Unsupported architecture" + exit 1 + ;; +esac DEFAULT_COMMAND="./test_progs" MOUNT_DIR="mnt" ROOTFS_IMAGE="root.img" OUTPUT_DIR="$HOME/.bpf_selftests" -KCONFIG_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/latest.config" -KCONFIG_API_URL="https://api.github.com/repos/libbpf/libbpf/contents/travis-ci/vmtest/configs/latest.config" +KCONFIG_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/config-latest.${ARCH}" +KCONFIG_API_URL="https://api.github.com/repos/libbpf/libbpf/contents/travis-ci/vmtest/configs/config-latest.${ARCH}" INDEX_URL="https://raw.githubusercontent.com/libbpf/libbpf/master/travis-ci/vmtest/configs/INDEX" NUM_COMPILE_JOBS="$(nproc)" LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")" @@ -85,7 +102,7 @@ newest_rootfs_version() { { for file in "${!URLS[@]}"; do - if [[ $file =~ ^libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then + if [[ $file =~ ^"${ARCH}"/libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then echo "${BASH_REMATCH[1]}" fi done @@ -102,7 +119,7 @@ download_rootfs() exit 1 fi - download "libbpf-vmtest-rootfs-$rootfsversion.tar.zst" | + download "${ARCH}/libbpf-vmtest-rootfs-$rootfsversion.tar.zst" | zstd -d | sudo tar -C "$dir" -x } @@ -224,13 +241,12 @@ EOF -nodefaults \ -display none \ -serial mon:stdio \ - -cpu host \ + "${qemu_flags[@]}" \ -enable-kvm \ - -smp 8 \ -m 4G \ -drive file="${rootfs_img}",format=raw,index=1,media=disk,if=virtio,cache=none \ -kernel "${kernel_bzimage}" \ - -append "root=/dev/vda rw console=ttyS0,115200" + -append "root=/dev/vda rw console=${QEMU_CONSOLE}" } copy_logs() @@ -282,7 +298,7 @@ main() local kernel_checkout=$(realpath "${script_dir}"/../../../../) # By default the script searches for the kernel in the checkout directory but # it also obeys environment variables O= and KBUILD_OUTPUT= - local kernel_bzimage="${kernel_checkout}/${X86_BZIMAGE}" + local kernel_bzimage="${kernel_checkout}/${BZIMAGE}" local command="${DEFAULT_COMMAND}" local update_image="no" local exit_command="poweroff -f" @@ -337,13 +353,13 @@ main() if is_rel_path "${O}"; then O="$(realpath "${PWD}/${O}")" fi - kernel_bzimage="${O}/${X86_BZIMAGE}" + kernel_bzimage="${O}/${BZIMAGE}" make_command="${make_command} O=${O}" elif [[ "${KBUILD_OUTPUT:=""}" != "" ]]; then if is_rel_path "${KBUILD_OUTPUT}"; then KBUILD_OUTPUT="$(realpath "${PWD}/${KBUILD_OUTPUT}")" fi - kernel_bzimage="${KBUILD_OUTPUT}/${X86_BZIMAGE}" + kernel_bzimage="${KBUILD_OUTPUT}/${BZIMAGE}" make_command="${make_command} KBUILD_OUTPUT=${KBUILD_OUTPUT}" fi diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c index f5ffba341c17..51c8224b4ccc 100644 --- a/tools/testing/selftests/bpf/xdp_redirect_multi.c +++ b/tools/testing/selftests/bpf/xdp_redirect_multi.c @@ -85,10 +85,7 @@ int main(int argc, char **argv) { int prog_fd, group_all, mac_map; struct bpf_program *ingress_prog, *egress_prog; - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_UNSPEC, - }; - int i, ret, opt, egress_prog_fd = 0; + int i, err, ret, opt, egress_prog_fd = 0; struct bpf_devmap_val devmap_val; bool attach_egress_prog = false; unsigned char mac_addr[6]; @@ -147,10 +144,14 @@ int main(int argc, char **argv) printf("\n"); snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - prog_load_attr.file = filename; - - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + obj = bpf_object__open_file(filename, NULL); + err = libbpf_get_error(obj); + if (err) + goto err_out; + err = bpf_object__load(obj); + if (err) goto err_out; + prog_fd = bpf_program__fd(bpf_object__next_program(obj, NULL)); if (attach_egress_prog) group_all = bpf_object__find_map_fd_by_name(obj, "map_egress"); diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index fe7f423b8c3f..0a5d23da486d 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -100,6 +100,12 @@ #include "xdpxceiver.h" #include "../kselftest.h" +/* AF_XDP APIs were moved into libxdp and marked as deprecated in libbpf. + * Until xdpxceiver is either moved or re-writed into libxdp, suppress + * deprecation warnings in this file + */ +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62"; static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61"; static const char *IP1 = "192.168.100.162"; @@ -1217,7 +1223,7 @@ static bool hugepages_present(struct ifobject *ifobject) void *bufs; bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, - MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE | MAP_HUGETLB, -1, 0); + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); if (bufs == MAP_FAILED) return false; @@ -1364,6 +1370,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_ testapp_invalid_desc(test); break; case TEST_TYPE_UNALIGNED_INV_DESC: + if (!hugepages_present(test->ifobj_tx)) { + ksft_test_result_skip("No 2M huge pages present.\n"); + return; + } test_spec_set_name(test, "UNALIGNED_INV_DESC"); test->ifobj_tx->umem->unaligned_mode = true; test->ifobj_rx->umem->unaligned_mode = true; diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore new file mode 100644 index 000000000000..c6c2965a6607 --- /dev/null +++ b/tools/testing/selftests/damon/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +huge_count_read_write diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 8a3f2cd9fec0..937d36ae9a69 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -1,7 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for damon selftests -TEST_FILES = _chk_dependency.sh -TEST_PROGS = debugfs_attrs.sh +TEST_GEN_FILES += huge_count_read_write + +TEST_FILES = _chk_dependency.sh _debugfs_common.sh +TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh +TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh include ../lib.mk diff --git a/tools/testing/selftests/damon/_debugfs_common.sh b/tools/testing/selftests/damon/_debugfs_common.sh new file mode 100644 index 000000000000..48989d4813ae --- /dev/null +++ b/tools/testing/selftests/damon/_debugfs_common.sh @@ -0,0 +1,52 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +test_write_result() { + file=$1 + content=$2 + orig_content=$3 + expect_reason=$4 + expected=$5 + + echo "$content" > "$file" + if [ $? -ne "$expected" ] + then + echo "writing $content to $file doesn't return $expected" + echo "expected because: $expect_reason" + echo "$orig_content" > "$file" + exit 1 + fi +} + +test_write_succ() { + test_write_result "$1" "$2" "$3" "$4" 0 +} + +test_write_fail() { + test_write_result "$1" "$2" "$3" "$4" 1 +} + +test_content() { + file=$1 + orig_content=$2 + expected=$3 + expect_reason=$4 + + content=$(cat "$file") + if [ "$content" != "$expected" ] + then + echo "reading $file expected $expected but $content" + echo "expected because: $expect_reason" + echo "$orig_content" > "$file" + exit 1 + fi +} + +source ./_chk_dependency.sh + +damon_onoff="$DBGFS/monitor_on" +if [ $(cat "$damon_onoff") = "on" ] +then + echo "monitoring is on" + exit $ksft_skip +fi diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh index 196b6640bf37..902e312bca89 100644 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ b/tools/testing/selftests/damon/debugfs_attrs.sh @@ -1,48 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -test_write_result() { - file=$1 - content=$2 - orig_content=$3 - expect_reason=$4 - expected=$5 - - echo "$content" > "$file" - if [ $? -ne "$expected" ] - then - echo "writing $content to $file doesn't return $expected" - echo "expected because: $expect_reason" - echo "$orig_content" > "$file" - exit 1 - fi -} - -test_write_succ() { - test_write_result "$1" "$2" "$3" "$4" 0 -} - -test_write_fail() { - test_write_result "$1" "$2" "$3" "$4" 1 -} - -test_content() { - file=$1 - orig_content=$2 - expected=$3 - expect_reason=$4 - - content=$(cat "$file") - if [ "$content" != "$expected" ] - then - echo "reading $file expected $expected but $content" - echo "expected because: $expect_reason" - echo "$orig_content" > "$file" - exit 1 - fi -} - -source ./_chk_dependency.sh +source _debugfs_common.sh # Test attrs file # =============== @@ -56,33 +15,3 @@ test_write_fail "$file" "1 2 3 5 4" "$orig_content" \ "min_nr_regions > max_nr_regions" test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written" echo "$orig_content" > "$file" - -# Test schemes file -# ================= - -file="$DBGFS/schemes" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \ - "$orig_content" "valid input" -test_write_fail "$file" "1 2 -3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines" -test_write_succ "$file" "" "$orig_content" "disabling" -echo "$orig_content" > "$file" - -# Test target_ids file -# ==================== - -file="$DBGFS/target_ids" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input" -test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input" -test_content "$file" "$orig_content" "1 2" "non-integer was there" -test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input" -test_content "$file" "$orig_content" "" "wrong input written" -test_write_succ "$file" "" "$orig_content" "empty input" -test_content "$file" "$orig_content" "" "empty input written" -echo "$orig_content" > "$file" - -echo "PASS" diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh new file mode 100644 index 000000000000..87aff8083822 --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_empty_targets.sh @@ -0,0 +1,13 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source _debugfs_common.sh + +# Test empty targets case +# ======================= + +orig_target_ids=$(cat "$DBGFS/target_ids") +echo "" > "$DBGFS/target_ids" +orig_monitor_on=$(cat "$DBGFS/monitor_on") +test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids" +echo "$orig_target_ids" > "$DBGFS/target_ids" diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh new file mode 100644 index 000000000000..922cadac2950 --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh @@ -0,0 +1,22 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source _debugfs_common.sh + +# Test huge count read write +# ========================== + +dmesg -C + +for file in "$DBGFS/"* +do + ./huge_count_read_write "$file" +done + +if dmesg | grep -q WARNING +then + dmesg + exit 1 +else + exit 0 +fi diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh new file mode 100644 index 000000000000..5b39ab44731c --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_schemes.sh @@ -0,0 +1,19 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source _debugfs_common.sh + +# Test schemes file +# ================= + +file="$DBGFS/schemes" +orig_content=$(cat "$file") + +test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \ + "$orig_content" "valid input" +test_write_fail "$file" "1 2 +3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines" +test_write_succ "$file" "" "$orig_content" "disabling" +test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \ + "$orig_content" "wrong condition ranges" +echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh new file mode 100644 index 000000000000..49aeabdb0aae --- /dev/null +++ b/tools/testing/selftests/damon/debugfs_target_ids.sh @@ -0,0 +1,19 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source _debugfs_common.sh + +# Test target_ids file +# ==================== + +file="$DBGFS/target_ids" +orig_content=$(cat "$file") + +test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input" +test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input" +test_content "$file" "$orig_content" "1 2" "non-integer was there" +test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input" +test_content "$file" "$orig_content" "" "wrong input written" +test_write_succ "$file" "" "$orig_content" "empty input" +test_content "$file" "$orig_content" "" "empty input written" +echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c new file mode 100644 index 000000000000..ad7a6b4cf338 --- /dev/null +++ b/tools/testing/selftests/damon/huge_count_read_write.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: SeongJae Park <sj@kernel.org> + */ + +#include <fcntl.h> +#include <stdlib.h> +#include <unistd.h> +#include <stdio.h> + +void write_read_with_huge_count(char *file) +{ + int filedesc = open(file, O_RDWR); + char buf[25]; + int ret; + + printf("%s %s\n", __func__, file); + if (filedesc < 0) { + fprintf(stderr, "failed opening %s\n", file); + exit(1); + } + + write(filedesc, "", 0xfffffffful); + perror("after write: "); + ret = read(filedesc, buf, 0xfffffffful); + perror("after read: "); + close(filedesc); +} + +int main(int argc, char *argv[]) +{ + if (argc != 2) { + fprintf(stderr, "Usage: %s <file>\n", argv[0]); + exit(1); + } + write_read_with_huge_count(argv[1]); + + return 0; +} diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh index b513f64d9092..026a126f584d 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh @@ -72,6 +72,35 @@ rif_mac_profile_replacement_test() ip link set $h1.10 address $h1_10_mac } +rif_mac_profile_consolidation_test() +{ + local count=$1; shift + local h1_20_mac + + RET=0 + + if [[ $count -eq 1 ]]; then + return + fi + + h1_20_mac=$(mac_get $h1.20) + + # Set the MAC of $h1.20 to that of $h1.10 and confirm that they are + # using the same MAC profile. + ip link set $h1.20 address 00:11:11:11:11:11 + check_err $? + + occ=$(devlink -j resource show $DEVLINK_DEV \ + | jq '.[][][] | select(.name=="rif_mac_profiles") |.["occ"]') + + [[ $occ -eq $((count - 1)) ]] + check_err $? "MAC profile occupancy did not decrease" + + log_test "RIF MAC profile consolidation" + + ip link set $h1.20 address $h1_20_mac +} + rif_mac_profile_shared_replacement_test() { local count=$1; shift @@ -104,6 +133,7 @@ rif_mac_profile_edit_test() create_max_rif_mac_profiles $count rif_mac_profile_replacement_test + rif_mac_profile_consolidation_test $count rif_mac_profile_shared_replacement_test $count } diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh index 729a86cc4ede..3639b89c81ba 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh @@ -145,23 +145,6 @@ sanitization_single_dev_no_local_ip_test() log_test "vxlan device with no local ip" } -sanitization_single_dev_local_ipv6_test() -{ - RET=0 - - ip link add dev br0 type bridge mcast_snooping 0 - - ip link add name vxlan0 up type vxlan id 10 nolearning noudpcsum \ - ttl 20 tos inherit local 2001:db8::1 dstport 4789 - - sanitization_single_dev_test_fail - - ip link del dev vxlan0 - ip link del dev br0 - - log_test "vxlan device with local ipv6 address" -} - sanitization_single_dev_learning_enabled_test() { RET=0 @@ -276,7 +259,6 @@ sanitization_single_dev_test() sanitization_single_dev_mcast_enabled_test sanitization_single_dev_mcast_group_test sanitization_single_dev_no_local_ip_test - sanitization_single_dev_local_ipv6_test sanitization_single_dev_learning_enabled_test sanitization_single_dev_local_interface_test sanitization_single_dev_port_range_test diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 3763105029fb..00814c0f87a6 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -30,6 +30,7 @@ /x86_64/svm_int_ctl_test /x86_64/sync_regs_test /x86_64/tsc_msrs_test +/x86_64/userspace_io_test /x86_64/userspace_msr_exit_test /x86_64/vmx_apic_access_test /x86_64/vmx_close_while_nested_test diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index c4e34717826a..f307c9f61981 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -59,6 +59,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test +TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 6a1a37f30494..da2b702da71a 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -71,6 +71,15 @@ enum vm_guest_mode { #endif +#if defined(__x86_64__) +unsigned long vm_compute_max_gfn(struct kvm_vm *vm); +#else +static inline unsigned long vm_compute_max_gfn(struct kvm_vm *vm) +{ + return ((1ULL << vm->pa_bits) >> vm->page_shift) - 1; +} +#endif + #define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT) #define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 8f2e0bb1ef96..daf6fdb217a7 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -302,7 +302,7 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) (1ULL << (vm->va_bits - 1)) >> vm->page_shift); /* Limit physical addresses to PA-bits. */ - vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1; + vm->max_gfn = vm_compute_max_gfn(vm); /* Allocate and setup memory for guest. */ vm->vpages_mapped = sparsebit_alloc(); diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index 82c39db91369..eef7b34756d5 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -1431,3 +1431,71 @@ struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpui return cpuid; } + +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163 +#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65 + +static inline unsigned x86_family(unsigned int eax) +{ + unsigned int x86; + + x86 = (eax >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (eax >> 20) & 0xff; + + return x86; +} + +unsigned long vm_compute_max_gfn(struct kvm_vm *vm) +{ + const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */ + unsigned long ht_gfn, max_gfn, max_pfn; + uint32_t eax, ebx, ecx, edx, max_ext_leaf; + + max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; + + /* Avoid reserved HyperTransport region on AMD processors. */ + eax = ecx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx || + ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx || + edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) + return max_gfn; + + /* On parts with <40 physical address bits, the area is fully hidden */ + if (vm->pa_bits < 40) + return max_gfn; + + /* Before family 17h, the HyperTransport area is just below 1T. */ + ht_gfn = (1 << 28) - num_ht_pages; + eax = 1; + cpuid(&eax, &ebx, &ecx, &edx); + if (x86_family(eax) < 0x17) + goto done; + + /* + * Otherwise it's at the top of the physical address space, possibly + * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX. Use + * the old conservative value if MAXPHYADDR is not enumerated. + */ + eax = 0x80000000; + cpuid(&eax, &ebx, &ecx, &edx); + max_ext_leaf = eax; + if (max_ext_leaf < 0x80000008) + goto done; + + eax = 0x80000008; + cpuid(&eax, &ebx, &ecx, &edx); + max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1; + if (max_ext_leaf >= 0x8000001f) { + eax = 0x8000001f; + cpuid(&eax, &ebx, &ecx, &edx); + max_pfn >>= (ebx >> 6) & 0x3f; + } + + ht_gfn = max_pfn - num_ht_pages; +done: + return min(max_gfn, ht_gfn - 1); +} diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c index df04f56ce859..30a81038df46 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c @@ -75,7 +75,7 @@ static void l1_guest_code(struct svm_test_data *svm) vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; /* No intercepts for real and virtual interrupts */ - vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR); + vmcb->control.intercept &= ~(BIT(INTERCEPT_INTR) | BIT(INTERCEPT_VINTR)); /* Make a virtual interrupt VINTR_IRQ_NUMBER pending */ vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT); diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c new file mode 100644 index 000000000000..e4bef2e05686 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <fcntl.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> + +#include "test_util.h" + +#include "kvm_util.h" +#include "processor.h" + +#define VCPU_ID 1 + +static void guest_ins_port80(uint8_t *buffer, unsigned int count) +{ + unsigned long end; + + if (count == 2) + end = (unsigned long)buffer + 1; + else + end = (unsigned long)buffer + 8192; + + asm volatile("cld; rep; insb" : "+D"(buffer), "+c"(count) : "d"(0x80) : "memory"); + GUEST_ASSERT_1(count == 0, count); + GUEST_ASSERT_2((unsigned long)buffer == end, buffer, end); +} + +static void guest_code(void) +{ + uint8_t buffer[8192]; + int i; + + /* + * Special case tests. main() will adjust RCX 2 => 1 and 3 => 8192 to + * test that KVM doesn't explode when userspace modifies the "count" on + * a userspace I/O exit. KVM isn't required to play nice with the I/O + * itself as KVM doesn't support manipulating the count, it just needs + * to not explode or overflow a buffer. + */ + guest_ins_port80(buffer, 2); + guest_ins_port80(buffer, 3); + + /* Verify KVM fills the buffer correctly when not stuffing RCX. */ + memset(buffer, 0, sizeof(buffer)); + guest_ins_port80(buffer, 8192); + for (i = 0; i < 8192; i++) + GUEST_ASSERT_2(buffer[i] == 0xaa, i, buffer[i]); + + GUEST_DONE(); +} + +int main(int argc, char *argv[]) +{ + struct kvm_regs regs; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + int rc; + + /* Tell stdout not to buffer its content */ + setbuf(stdout, NULL); + + /* Create VM */ + vm = vm_create_default(VCPU_ID, 0, guest_code); + run = vcpu_state(vm, VCPU_ID); + + memset(®s, 0, sizeof(regs)); + + while (1) { + rc = _vcpu_run(vm, VCPU_ID); + + TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s),\n", + run->exit_reason, + exit_reason_str(run->exit_reason)); + + if (get_ucall(vm, VCPU_ID, &uc)) + break; + + TEST_ASSERT(run->io.port == 0x80, + "Expected I/O at port 0x80, got port 0x%x\n", run->io.port); + + /* + * Modify the rep string count in RCX: 2 => 1 and 3 => 8192. + * Note, this abuses KVM's batching of rep string I/O to avoid + * getting stuck in an infinite loop. That behavior isn't in + * scope from a testing perspective as it's not ABI in any way, + * i.e. it really is abusing internal KVM knowledge. + */ + vcpu_regs_get(vm, VCPU_ID, ®s); + if (regs.rcx == 2) + regs.rcx = 1; + if (regs.rcx == 3) + regs.rcx = 8192; + memset((void *)run + run->io.data_offset, 0xaa, 4096); + vcpu_regs_set(vm, VCPU_ID, ®s); + } + + switch (uc.cmd) { + case UCALL_DONE: + break; + case UCALL_ABORT: + TEST_FAIL("%s at %s:%ld : argN+1 = 0x%lx, argN+2 = 0x%lx", + (const char *)uc.args[0], __FILE__, uc.args[1], + uc.args[2], uc.args[3]); + default: + TEST_FAIL("Unknown ucall %lu", uc.cmd); + } + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 32d5f7bc588e..412d85205546 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -462,6 +462,22 @@ cleanup() ip netns del ${NSC} >/dev/null 2>&1 } +cleanup_vrf_dup() +{ + ip link del ${NSA_DEV2} >/dev/null 2>&1 + ip netns pids ${NSC} | xargs kill 2>/dev/null + ip netns del ${NSC} >/dev/null 2>&1 +} + +setup_vrf_dup() +{ + # some VRF tests use ns-C which has the same config as + # ns-B but for a device NOT in the VRF + create_ns ${NSC} "-" "-" + connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \ + ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 +} + setup() { local with_vrf=${1} @@ -491,12 +507,6 @@ setup() ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV} ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV} - - # some VRF tests use ns-C which has the same config as - # ns-B but for a device NOT in the VRF - create_ns ${NSC} "-" "-" - connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \ - ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64 else ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV} ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV} @@ -1247,7 +1257,9 @@ ipv4_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests + setup_vrf_dup ipv4_tcp_md5 + cleanup_vrf_dup # # enable VRF global server @@ -1813,8 +1825,9 @@ ipv4_addr_bind_vrf() for a in ${NSA_IP} ${VRF_IP} do log_start + show_hint "Socket not bound to VRF, but address is in VRF" run_cmd nettest -s -R -P icmp -l ${a} -b - log_test_addr ${a} $? 0 "Raw socket bind to local address" + log_test_addr ${a} $? 1 "Raw socket bind to local address" log_start run_cmd nettest -s -R -P icmp -l ${a} -I ${NSA_DEV} -b @@ -2215,7 +2228,7 @@ ipv6_ping_vrf() log_start show_hint "Fails since VRF device does not support linklocal or multicast" run_cmd ${ping6} -c1 -w1 ${a} - log_test_addr ${a} $? 2 "ping out, VRF bind" + log_test_addr ${a} $? 1 "ping out, VRF bind" done for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV} @@ -2743,7 +2756,9 @@ ipv6_tcp_vrf() log_test_addr ${a} $? 1 "Global server, local connection" # run MD5 tests + setup_vrf_dup ipv6_tcp_md5 + cleanup_vrf_dup # # enable VRF global server @@ -3446,11 +3461,14 @@ ipv6_addr_bind_novrf() run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind" + # Sadly, the kernel allows binding a socket to a device and then + # binding to an address not on the device. So this test passes + # when it really should not a=${NSA_LO_IP6} log_start - show_hint "Should fail with 'Cannot assign requested address'" + show_hint "Tecnically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b - log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address" + log_test_addr ${a} $? 0 "TCP socket bind to out of scope local address" } ipv6_addr_bind_vrf() @@ -3499,10 +3517,15 @@ ipv6_addr_bind_vrf() run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to local address with device bind" + # Sadly, the kernel allows binding a socket to a device and then + # binding to an address not on the device. The only restriction + # is that the address is valid in the L3 domain. So this test + # passes when it really should not a=${VRF_IP6} log_start + show_hint "Tecnically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b - log_test_addr ${a} $? 1 "TCP socket bind to VRF address with device bind" + log_test_addr ${a} $? 0 "TCP socket bind to VRF address with device bind" a=${NSA_LO_IP6} log_start @@ -4115,3 +4138,11 @@ cleanup 2>/dev/null printf "\nTests passed: %3d\n" ${nsuccess} printf "Tests failed: %3d\n" ${nfail} + +if [ $nfail -ne 0 ]; then + exit 1 # KSFT_FAIL +elif [ $nsuccess -eq 0 ]; then + exit $ksft_skip +fi + +exit 0 # KSFT_PASS diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 5abe92d55b69..996af1ae3d3d 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -444,24 +444,63 @@ fib_rp_filter_test() setup set -e + ip netns add ns2 + ip netns set ns2 auto + + ip -netns ns2 link set dev lo up + + $IP link add name veth1 type veth peer name veth2 + $IP link set dev veth2 netns ns2 + $IP address add 192.0.2.1/24 dev veth1 + ip -netns ns2 address add 192.0.2.1/24 dev veth2 + $IP link set dev veth1 up + ip -netns ns2 link set dev veth2 up + $IP link set dev lo address 52:54:00:6a:c7:5e - $IP link set dummy0 address 52:54:00:6a:c7:5e - $IP link add dummy1 type dummy - $IP link set dummy1 address 52:54:00:6a:c7:5e - $IP link set dev dummy1 up + $IP link set dev veth1 address 52:54:00:6a:c7:5e + ip -netns ns2 link set dev lo address 52:54:00:6a:c7:5e + ip -netns ns2 link set dev veth2 address 52:54:00:6a:c7:5e + + # 1. (ns2) redirect lo's egress to veth2's egress + ip netns exec ns2 tc qdisc add dev lo parent root handle 1: fq_codel + ip netns exec ns2 tc filter add dev lo parent 1: protocol arp basic \ + action mirred egress redirect dev veth2 + ip netns exec ns2 tc filter add dev lo parent 1: protocol ip basic \ + action mirred egress redirect dev veth2 + + # 2. (ns1) redirect veth1's ingress to lo's ingress + $NS_EXEC tc qdisc add dev veth1 ingress + $NS_EXEC tc filter add dev veth1 ingress protocol arp basic \ + action mirred ingress redirect dev lo + $NS_EXEC tc filter add dev veth1 ingress protocol ip basic \ + action mirred ingress redirect dev lo + + # 3. (ns1) redirect lo's egress to veth1's egress + $NS_EXEC tc qdisc add dev lo parent root handle 1: fq_codel + $NS_EXEC tc filter add dev lo parent 1: protocol arp basic \ + action mirred egress redirect dev veth1 + $NS_EXEC tc filter add dev lo parent 1: protocol ip basic \ + action mirred egress redirect dev veth1 + + # 4. (ns2) redirect veth2's ingress to lo's ingress + ip netns exec ns2 tc qdisc add dev veth2 ingress + ip netns exec ns2 tc filter add dev veth2 ingress protocol arp basic \ + action mirred ingress redirect dev lo + ip netns exec ns2 tc filter add dev veth2 ingress protocol ip basic \ + action mirred ingress redirect dev lo + $NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1 $NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1 $NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1 - - $NS_EXEC tc qd add dev dummy1 parent root handle 1: fq_codel - $NS_EXEC tc filter add dev dummy1 parent 1: protocol arp basic action mirred egress redirect dev lo - $NS_EXEC tc filter add dev dummy1 parent 1: protocol ip basic action mirred egress redirect dev lo + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=1 + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.accept_local=1 + ip netns exec ns2 sysctl -qw net.ipv4.conf.all.route_localnet=1 set +e - run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 198.51.100.1" + run_cmd "ip netns exec ns2 ping -w1 -c1 192.0.2.1" log_test $? 0 "rp_filter passes local packets" - run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 127.0.0.1" + run_cmd "ip netns exec ns2 ping -w1 -c1 127.0.0.1" log_test $? 0 "rp_filter passes loopback packets" cleanup diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index bf17e485684f..b0980a2efa31 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -13,6 +13,8 @@ NETIFS[p5]=veth4 NETIFS[p6]=veth5 NETIFS[p7]=veth6 NETIFS[p8]=veth7 +NETIFS[p9]=veth8 +NETIFS[p10]=veth9 # Port that does not have a cable connected. NETIF_NO_CABLE=eth8 diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c index cf37ce86b0fd..ee0b03f3dd06 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/net/gro.c @@ -64,10 +64,6 @@ #define NUM_PACKETS 4 #define START_SEQ 100 #define START_ACK 100 -#define SIP6 "fdaa::2" -#define DIP6 "fdaa::1" -#define SIP4 "192.168.1.200" -#define DIP4 "192.168.1.100" #define ETH_P_NONE 0 #define TOTAL_HDR_LEN (ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct tcphdr)) #define MSS (4096 - sizeof(struct tcphdr) - sizeof(struct ipv6hdr)) @@ -75,6 +71,10 @@ #define NUM_LARGE_PKT (MAX_PAYLOAD / MSS) #define MAX_HDR_LEN (ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct tcphdr)) +static const char *addr6_src = "fdaa::2"; +static const char *addr6_dst = "fdaa::1"; +static const char *addr4_src = "192.168.1.200"; +static const char *addr4_dst = "192.168.1.100"; static int proto = -1; static uint8_t src_mac[ETH_ALEN], dst_mac[ETH_ALEN]; static char *testname = "data"; @@ -178,18 +178,18 @@ static uint16_t tcp_checksum(void *buf, int payload_len) uint32_t sum = 0; if (proto == PF_INET6) { - if (inet_pton(AF_INET6, SIP6, &ph6.saddr) != 1) + if (inet_pton(AF_INET6, addr6_src, &ph6.saddr) != 1) error(1, errno, "inet_pton6 source ip pseudo"); - if (inet_pton(AF_INET6, DIP6, &ph6.daddr) != 1) + if (inet_pton(AF_INET6, addr6_dst, &ph6.daddr) != 1) error(1, errno, "inet_pton6 dest ip pseudo"); ph6.protocol = htons(IPPROTO_TCP); ph6.payload_len = htons(sizeof(struct tcphdr) + payload_len); sum = checksum_nofold(&ph6, sizeof(ph6), 0); } else if (proto == PF_INET) { - if (inet_pton(AF_INET, SIP4, &ph4.saddr) != 1) + if (inet_pton(AF_INET, addr4_src, &ph4.saddr) != 1) error(1, errno, "inet_pton source ip pseudo"); - if (inet_pton(AF_INET, DIP4, &ph4.daddr) != 1) + if (inet_pton(AF_INET, addr4_dst, &ph4.daddr) != 1) error(1, errno, "inet_pton dest ip pseudo"); ph4.protocol = htons(IPPROTO_TCP); ph4.payload_len = htons(sizeof(struct tcphdr) + payload_len); @@ -229,9 +229,9 @@ static void fill_networklayer(void *buf, int payload_len) ip6h->payload_len = htons(sizeof(struct tcphdr) + payload_len); ip6h->nexthdr = IPPROTO_TCP; ip6h->hop_limit = 8; - if (inet_pton(AF_INET6, SIP6, &ip6h->saddr) != 1) + if (inet_pton(AF_INET6, addr6_src, &ip6h->saddr) != 1) error(1, errno, "inet_pton source ip6"); - if (inet_pton(AF_INET6, DIP6, &ip6h->daddr) != 1) + if (inet_pton(AF_INET6, addr6_dst, &ip6h->daddr) != 1) error(1, errno, "inet_pton dest ip6"); } else if (proto == PF_INET) { memset(iph, 0, sizeof(*iph)); @@ -243,9 +243,9 @@ static void fill_networklayer(void *buf, int payload_len) iph->tot_len = htons(sizeof(struct tcphdr) + payload_len + sizeof(struct iphdr)); iph->frag_off = htons(0x4000); /* DF = 1, MF = 0 */ - if (inet_pton(AF_INET, SIP4, &iph->saddr) != 1) + if (inet_pton(AF_INET, addr4_src, &iph->saddr) != 1) error(1, errno, "inet_pton source ip"); - if (inet_pton(AF_INET, DIP4, &iph->daddr) != 1) + if (inet_pton(AF_INET, addr4_dst, &iph->daddr) != 1) error(1, errno, "inet_pton dest ip"); iph->check = checksum_fold(buf, sizeof(struct iphdr), 0); } @@ -731,7 +731,7 @@ static void set_timeout(int fd) { struct timeval timeout; - timeout.tv_sec = 120; + timeout.tv_sec = 3; timeout.tv_usec = 0; if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, (char *)&timeout, sizeof(timeout)) < 0) @@ -1023,11 +1023,13 @@ static void gro_receiver(void) static void parse_args(int argc, char **argv) { static const struct option opts[] = { + { "daddr", required_argument, NULL, 'd' }, { "dmac", required_argument, NULL, 'D' }, { "iface", required_argument, NULL, 'i' }, { "ipv4", no_argument, NULL, '4' }, { "ipv6", no_argument, NULL, '6' }, { "rx", no_argument, NULL, 'r' }, + { "saddr", required_argument, NULL, 's' }, { "smac", required_argument, NULL, 'S' }, { "test", required_argument, NULL, 't' }, { "verbose", no_argument, NULL, 'v' }, @@ -1035,7 +1037,7 @@ static void parse_args(int argc, char **argv) }; int c; - while ((c = getopt_long(argc, argv, "46D:i:rS:t:v", opts, NULL)) != -1) { + while ((c = getopt_long(argc, argv, "46d:D:i:rs:S:t:v", opts, NULL)) != -1) { switch (c) { case '4': proto = PF_INET; @@ -1045,6 +1047,9 @@ static void parse_args(int argc, char **argv) proto = PF_INET6; ethhdr_proto = htons(ETH_P_IPV6); break; + case 'd': + addr4_dst = addr6_dst = optarg; + break; case 'D': dmac = optarg; break; @@ -1054,6 +1059,9 @@ static void parse_args(int argc, char **argv) case 'r': tx_socket = false; break; + case 's': + addr4_src = addr6_src = optarg; + break; case 'S': smac = optarg; break; @@ -1091,5 +1099,7 @@ int main(int argc, char **argv) gro_sender(); else gro_receiver(); + + fprintf(stderr, "Gro::%s test passed.\n", testname); return 0; } diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index ecbf57f264ed..7b9d6e31b8e7 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -311,7 +311,7 @@ check_exception() ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \ grep -E -v 'mtu|redirected' | grep -q "cache" fi - log_test $? 0 "IPv4: ${desc}" + log_test $? 0 "IPv4: ${desc}" 0 # No PMTU info for test "redirect" and "mtu exception plus redirect" if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c index b8debd4fb5ed..29f75e2a1116 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_inq.c +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -18,7 +18,6 @@ #include <time.h> #include <sys/ioctl.h> -#include <sys/ioctl.h> #include <sys/socket.h> #include <sys/types.h> #include <sys/wait.h> diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 8a22db0cca49..6e468e0f42f7 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -31,6 +31,8 @@ struct tls_crypto_info_keys { struct tls12_crypto_info_chacha20_poly1305 chacha20; struct tls12_crypto_info_sm4_gcm sm4gcm; struct tls12_crypto_info_sm4_ccm sm4ccm; + struct tls12_crypto_info_aes_ccm_128 aesccm128; + struct tls12_crypto_info_aes_gcm_256 aesgcm256; }; size_t len; }; @@ -61,6 +63,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type, tls12->sm4ccm.info.version = tls_version; tls12->sm4ccm.info.cipher_type = cipher_type; break; + case TLS_CIPHER_AES_CCM_128: + tls12->len = sizeof(struct tls12_crypto_info_aes_ccm_128); + tls12->aesccm128.info.version = tls_version; + tls12->aesccm128.info.cipher_type = cipher_type; + break; + case TLS_CIPHER_AES_GCM_256: + tls12->len = sizeof(struct tls12_crypto_info_aes_gcm_256); + tls12->aesgcm256.info.version = tls_version; + tls12->aesgcm256.info.cipher_type = cipher_type; + break; default: break; } @@ -261,6 +273,30 @@ FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) .cipher_type = TLS_CIPHER_SM4_CCM, }; +FIXTURE_VARIANT_ADD(tls, 12_aes_ccm) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_AES_CCM_128, +}; + +FIXTURE_VARIANT_ADD(tls, 13_aes_ccm) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_AES_CCM_128, +}; + +FIXTURE_VARIANT_ADD(tls, 12_aes_gcm_256) +{ + .tls_version = TLS_1_2_VERSION, + .cipher_type = TLS_CIPHER_AES_GCM_256, +}; + +FIXTURE_VARIANT_ADD(tls, 13_aes_gcm_256) +{ + .tls_version = TLS_1_3_VERSION, + .cipher_type = TLS_CIPHER_AES_GCM_256, +}; + FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c index 710ac956bdb3..c5489341cfb8 100644 --- a/tools/testing/selftests/net/toeplitz.c +++ b/tools/testing/selftests/net/toeplitz.c @@ -498,7 +498,7 @@ static void parse_opts(int argc, char **argv) bool have_toeplitz = false; int index, c; - while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:u:v", long_options, &index)) != -1) { + while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:uv", long_options, &index)) != -1) { switch (c) { case '4': cfg_family = AF_INET; diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh index 91f3ef0f1192..8b5ea9234588 100755 --- a/tools/testing/selftests/netfilter/conntrack_vrf.sh +++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh @@ -150,11 +150,27 @@ EOF # oifname is the vrf device. test_masquerade_vrf() { + local qdisc=$1 + + if [ "$qdisc" != "default" ]; then + tc -net $ns0 qdisc add dev tvrf root $qdisc + fi + ip netns exec $ns0 conntrack -F 2>/dev/null ip netns exec $ns0 nft -f - <<EOF flush ruleset table ip nat { + chain rawout { + type filter hook output priority raw; + + oif tvrf ct state untracked counter + } + chain postrouting2 { + type filter hook postrouting priority mangle; + + oif tvrf ct state untracked counter + } chain postrouting { type nat hook postrouting priority 0; # NB: masquerade should always be combined with 'oif(name) bla', @@ -171,13 +187,18 @@ EOF fi # must also check that nat table was evaluated on second (lower device) iteration. - ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' && + ip netns exec $ns0 nft list table ip nat |grep -q 'untracked counter packets [1-9]' if [ $? -eq 0 ]; then - echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device" + echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device ($qdisc qdisc)" else - echo "FAIL: vrf masq rule has unexpected counter value" + echo "FAIL: vrf rules have unexpected counter value" ret=1 fi + + if [ "$qdisc" != "default" ]; then + tc -net $ns0 qdisc del dev tvrf root + fi } # add masq rule that gets evaluated w. outif set to veth device. @@ -213,7 +234,8 @@ EOF } test_ct_zone_in -test_masquerade_vrf +test_masquerade_vrf "default" +test_masquerade_vrf "pfifo" test_masquerade_veth exit $ret diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index 5a4938d6dcf2..ed61f6cab60f 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -23,8 +23,8 @@ TESTS="reported_issues correctness concurrency timeout" # Set types, defined by TYPE_ variables below TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto - net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port - net_port_mac_proto_net" + net_port_net net_mac mac_net net_mac_icmp net6_mac_icmp + net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below BUGS="flush_remove_add" @@ -277,6 +277,23 @@ perf_entries 1000 perf_proto ipv4 " +TYPE_mac_net=" +display mac,net +type_spec ether_addr . ipv4_addr +chain_spec ether saddr . ip saddr +dst +src mac addr4 +start 1 +count 5 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + TYPE_net_mac_icmp=" display net,mac - ICMP type_spec ipv4_addr . ether_addr @@ -984,7 +1001,8 @@ format() { fi done for f in ${src}; do - __expr="${__expr} . " + [ "${__expr}" != "{ " ] && __expr="${__expr} . " + __start="$(eval format_"${f}" "${srcstart}")" __end="$(eval format_"${f}" "${srcend}")" diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh index ac646376eb01..04633119b29a 100755 --- a/tools/testing/selftests/netfilter/nft_zones_many.sh +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -18,11 +18,17 @@ cleanup() ip netns del $ns } -ip netns add $ns -if [ $? -ne 0 ];then - echo "SKIP: Could not create net namespace $gw" - exit $ksft_skip -fi +checktool (){ + if ! $1 > /dev/null 2>&1; then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} + +checktool "nft --version" "run test without nft tool" +checktool "ip -Version" "run test without ip tool" +checktool "socat -V" "run test without socat tool" +checktool "ip netns add $ns" "create net namespace" trap cleanup EXIT @@ -71,7 +77,8 @@ EOF local start=$(date +%s%3N) i=$((i + 10000)) j=$((j + 1)) - dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null + # nft rule in output places each packet in a different zone. + dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 if [ $? -ne 0 ] ;then ret=1 break diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index b71828df5a6d..a3239d5e40c7 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -60,6 +60,8 @@ CONFIG_NET_IFE_SKBTCINDEX=m CONFIG_NET_SCH_FIFO=y CONFIG_NET_SCH_ETS=m CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_FQ_PIE=m +CONFIG_NETDEVSIM=m # ## Network testing diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py index a3e43189d940..ee22e3447ec7 100755 --- a/tools/testing/selftests/tc-testing/tdc.py +++ b/tools/testing/selftests/tc-testing/tdc.py @@ -716,6 +716,7 @@ def set_operation_mode(pm, parser, args, remaining): list_test_cases(alltests) exit(0) + exit_code = 0 # KSFT_PASS if len(alltests): req_plugins = pm.get_required_plugins(alltests) try: @@ -724,6 +725,8 @@ def set_operation_mode(pm, parser, args, remaining): print('The following plugins were not found:') print('{}'.format(pde.missing_pg)) catresults = test_runner(pm, args, alltests) + if catresults.count_failures() != 0: + exit_code = 1 # KSFT_FAIL if args.format == 'none': print('Test results output suppression requested\n') else: @@ -748,6 +751,8 @@ def set_operation_mode(pm, parser, args, remaining): gid=int(os.getenv('SUDO_GID'))) else: print('No tests found\n') + exit_code = 4 # KSFT_SKIP + exit(exit_code) def main(): """ @@ -767,8 +772,5 @@ def main(): set_operation_mode(pm, parser, args, remaining) - exit(0) - - if __name__ == "__main__": main() diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index 7fe38c76db44..afb0cd86fa3d 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -1,5 +1,6 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 +modprobe netdevsim ./tdc.py -c actions --nobuildebpf ./tdc.py -c qdisc |