From c9784e23c1020e63d6dba5e10ca8bf3d8b85c19c Mon Sep 17 00:00:00 2001 From: Dave Penkler Date: Tue, 15 Dec 2020 16:56:19 +0100 Subject: USB: usbtmc: Add USBTMC_IOCTL_GET_STB This new ioctl reads the status byte (STB) from the device and returns the STB unmodified to the application. The srq_asserted bit is not taken into account and not changed. This ioctl is useful to support non USBTMC-488 compliant devices. Tested-by: Jian-Wei Wu Reviewed-by: Guido Kiener Signed-off-by: Dave Penkler Link: https://lore.kernel.org/r/20201215155621.9592-3-dpenkler@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/tmc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/tmc.h b/include/uapi/linux/usb/tmc.h index fdd4d88a7b95..1e7878fe591f 100644 --- a/include/uapi/linux/usb/tmc.h +++ b/include/uapi/linux/usb/tmc.h @@ -102,6 +102,8 @@ struct usbtmc_message { #define USBTMC_IOCTL_MSG_IN_ATTR _IOR(USBTMC_IOC_NR, 24, __u8) #define USBTMC_IOCTL_AUTO_ABORT _IOW(USBTMC_IOC_NR, 25, __u8) +#define USBTMC_IOCTL_GET_STB _IOR(USBTMC_IOC_NR, 26, __u8) + /* Cancel and cleanup asynchronous calls */ #define USBTMC_IOCTL_CANCEL_IO _IO(USBTMC_IOC_NR, 35) #define USBTMC_IOCTL_CLEANUP_IO _IO(USBTMC_IOC_NR, 36) -- cgit v1.2.3 From d1d9defdc6d582119d29f5d88f810b72bb1837fa Mon Sep 17 00:00:00 2001 From: Dave Penkler Date: Tue, 15 Dec 2020 16:56:20 +0100 Subject: USB: usbtmc: Add separate USBTMC_IOCTL_GET_SRQ_STB This new ioctl only returns the status byte (STB) that was originally sent by the device due to a service request (SRQ) condition. This ioctl checks the srq_asserted bit of the associated file descriptor. If set, the srq_asserted bit is reset and the cached STB with original SRQ information is returned. Otherwise the ioctl returns the error code ENOMSG. This ioctl is useful to support non USBTMC-488 compliant devices. Time sensitive applications can read the cached STB without incurring the cost of an urb transaction over the bus. Tested-by: Jian-Wei Wu Reviewed-by: Guido Kiener Signed-off-by: Dave Penkler Link: https://lore.kernel.org/r/20201215155621.9592-4-dpenkler@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/tmc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/tmc.h b/include/uapi/linux/usb/tmc.h index 1e7878fe591f..d791cc58a7f0 100644 --- a/include/uapi/linux/usb/tmc.h +++ b/include/uapi/linux/usb/tmc.h @@ -103,6 +103,7 @@ struct usbtmc_message { #define USBTMC_IOCTL_AUTO_ABORT _IOW(USBTMC_IOC_NR, 25, __u8) #define USBTMC_IOCTL_GET_STB _IOR(USBTMC_IOC_NR, 26, __u8) +#define USBTMC_IOCTL_GET_SRQ_STB _IOR(USBTMC_IOC_NR, 27, __u8) /* Cancel and cleanup asynchronous calls */ #define USBTMC_IOCTL_CANCEL_IO _IO(USBTMC_IOC_NR, 35) -- cgit v1.2.3 From 99668f618062816ca7ba639b007eb145b9d3d41e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 17 Dec 2020 09:19:10 -0700 Subject: fs: expose LOOKUP_CACHED through openat2() RESOLVE_CACHED Now that we support non-blocking path resolution internally, expose it via openat2() in the struct open_how ->resolve flags. This allows applications using openat2() to limit path resolution to the extent that it is already cached. If the lookup cannot be satisfied in a non-blocking manner, openat2(2) will return -1/-EAGAIN. Cc: Al Viro Signed-off-by: Jens Axboe Signed-off-by: Al Viro --- include/uapi/linux/openat2.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h index 58b1eb711360..a5feb7604948 100644 --- a/include/uapi/linux/openat2.h +++ b/include/uapi/linux/openat2.h @@ -35,5 +35,9 @@ struct open_how { #define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." be scoped inside the dirfd (similar to chroot(2)). */ +#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be + completed through cached lookup. May + return -EAGAIN if that's not + possible. */ #endif /* _UAPI_LINUX_OPENAT2_H */ -- cgit v1.2.3 From c762a2b846b619c0f92f23e2e8e16f70d20df800 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 5 Jan 2021 13:02:39 +0100 Subject: tty: drop termiox user definitions As was concluded in a follow-up discussion of commit e0efb3168d34 (tty: Remove dead termiox code) [1], termiox ioctls never worked, so there is barely anyone using this interface. We can safely remove the user definitions for this never adopted interface. [1] https://lore.kernel.org/lkml/c1c9fc04-02eb-2260-195b-44c357f057c0@kernel.org/t/#u Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210105120239.28031-12-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/termios.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/termios.h b/include/uapi/linux/termios.h index 33961d4e4de0..e6da9d4433d1 100644 --- a/include/uapi/linux/termios.h +++ b/include/uapi/linux/termios.h @@ -5,19 +5,4 @@ #include #include -#define NFF 5 - -struct termiox -{ - __u16 x_hflag; - __u16 x_cflag; - __u16 x_rflag[NFF]; - __u16 x_sflag; -}; - -#define RTSXOFF 0x0001 /* RTS flow control on input */ -#define CTSXON 0x0002 /* CTS flow control on output */ -#define DTRXOFF 0x0004 /* DTR flow control on input */ -#define DSRXON 0x0008 /* DCD flow control on output */ - #endif -- cgit v1.2.3 From 0f9f696a502e1b01fbb137a08f56f157da9d95eb Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 8 Jan 2021 16:47:59 -0800 Subject: mptcp: add set_flags command in PM netlink This patch added a new command MPTCP_PM_CMD_SET_FLAGS in PM netlink: In mptcp_nl_cmd_set_flags, parse the input address, get the backup value according to whether the address's FLAG_BACKUP flag is set from the user-space. Then check whether this address had been added in the local address list. If it had been, then call mptcp_nl_addr_backup to deal with this address. In mptcp_nl_addr_backup, traverse all the existing msk sockets to find the relevant sockets, and call mptcp_pm_nl_mp_prio_send_ack to send out a MP_PRIO ACK packet. Finally in mptcp_nl_cmd_set_flags, set or clear the address's FLAG_BACKUP flag. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 9762660df741..3674a451a18c 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -82,6 +82,7 @@ enum { MPTCP_PM_CMD_FLUSH_ADDRS, MPTCP_PM_CMD_SET_LIMITS, MPTCP_PM_CMD_GET_LIMITS, + MPTCP_PM_CMD_SET_FLAGS, __MPTCP_PM_CMD_AFTER_LAST }; -- cgit v1.2.3 From ad0bfc233ae2e7ee3bcb9a6089e4aa54e2b44fa1 Mon Sep 17 00:00:00 2001 From: Danilo Carvalho Date: Fri, 8 Jan 2021 22:21:04 +0000 Subject: Fix whitespace in uapi/linux/tcp.h. List of things fixed: - Two of the socket options were idented with spaces instead of tabs. - Trailing whitespace in some lines. - Improper spacing around parenthesis caught by checkpatch.pl. - Mix of space and tabs in tcp_word_hdr union. Signed-off-by: Danilo Carvalho Link: https://lore.kernel.org/r/20210108222104.2079472-1-doak@google.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 13ceeb395eb8..768e93bd5b51 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -51,7 +51,7 @@ struct tcphdr { fin:1; #else #error "Adjust your defines" -#endif +#endif __be16 window; __sum16 check; __be16 urg_ptr; @@ -62,14 +62,14 @@ struct tcphdr { * (union is compatible to any of its members) * This means this part of the code is -fstrict-aliasing safe now. */ -union tcp_word_hdr { +union tcp_word_hdr { struct tcphdr hdr; - __be32 words[5]; -}; + __be32 words[5]; +}; -#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) +#define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3]) -enum { +enum { TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000), TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000), TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000), @@ -80,7 +80,7 @@ enum { TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000), TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000), TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000) -}; +}; /* * TCP general constants @@ -103,8 +103,8 @@ enum { #define TCP_QUICKACK 12 /* Block/reenable quick acks */ #define TCP_CONGESTION 13 /* Congestion control algorithm */ #define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ -#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ -#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ +#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ +#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ #define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */ #define TCP_REPAIR 19 /* TCP sock is under repair right now */ #define TCP_REPAIR_QUEUE 20 -- cgit v1.2.3 From c6458e72f6fd6ac7e390da0d9abe8446084886e5 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Tue, 12 Jan 2021 12:34:22 +0000 Subject: bpf: Clarify return value of probe str helpers When the buffer is too small to contain the input string, these helpers return the length of the buffer, not the length of the original string. This tries to make the docs totally clear about that, since "the length of the [copied ]string" could also refer to the length of the input. Signed-off-by: Brendan Jackman Signed-off-by: Daniel Borkmann Acked-by: KP Singh Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210112123422.2011234-1-jackmanb@google.com --- include/uapi/linux/bpf.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 77d7c1bb2923..a1ad32456f89 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2993,10 +2993,10 @@ union bpf_attr { * string length is larger than *size*, just *size*-1 bytes are * copied and the last byte is set to NUL. * - * On success, the length of the copied string is returned. This - * makes this helper useful in tracing programs for reading - * strings, and more importantly to get its length at runtime. See - * the following snippet: + * On success, returns the number of bytes that were written, + * including the terminal NUL. This makes this helper useful in + * tracing programs for reading strings, and more importantly to + * get its length at runtime. See the following snippet: * * :: * @@ -3024,7 +3024,7 @@ union bpf_attr { * **->mm->env_start**: using this helper and the return value, * one can quickly iterate at the right offset of the memory area. * Return - * On success, the strictly positive length of the string, + * On success, the strictly positive length of the output string, * including the trailing NUL character. On error, a negative * value. * -- cgit v1.2.3 From 91c960b0056672e74627776655c926388350fa30 Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:44 +0000 Subject: bpf: Rename BPF_XADD and prepare to encode other atomics in .imm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A subsequent patch will add additional atomic operations. These new operations will use the same opcode field as the existing XADD, with the immediate discriminating different operations. In preparation, rename the instruction mode BPF_ATOMIC and start calling the zero immediate BPF_ADD. This is possible (doesn't break existing valid BPF progs) because the immediate field is currently reserved MBZ and BPF_ADD is zero. All uses are removed from the tree but the BPF_XADD definition is kept around to avoid breaking builds for people including kernel headers. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Björn Töpel Link: https://lore.kernel.org/bpf/20210114181751.768687-5-jackmanb@google.com --- include/uapi/linux/bpf.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a1ad32456f89..6b3996343e63 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -19,7 +19,8 @@ /* ld/ldx fields */ #define BPF_DW 0x18 /* double word (64-bit) */ -#define BPF_XADD 0xc0 /* exclusive add */ +#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ +#define BPF_XADD 0xc0 /* exclusive add - legacy name */ /* alu/jmp fields */ #define BPF_MOV 0xb0 /* mov reg to reg */ @@ -2448,7 +2449,7 @@ union bpf_attr { * running simultaneously. * * A user should care about the synchronization by himself. - * For example, by using the **BPF_STX_XADD** instruction to alter + * For example, by using the **BPF_ATOMIC** instructions to alter * the shared data. * Return * A pointer to the local storage area. -- cgit v1.2.3 From 5ca419f2864a2c60940dcf4bbaeb69546200e36f Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:46 +0000 Subject: bpf: Add BPF_FETCH field / create atomic_fetch_add instruction The BPF_FETCH field can be set in bpf_insn.imm, for BPF_ATOMIC instructions, in order to have the previous value of the atomically-modified memory location loaded into the src register after an atomic op is carried out. Suggested-by: Yonghong Song Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20210114181751.768687-7-jackmanb@google.com --- include/uapi/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6b3996343e63..ea262b009049 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -44,6 +44,9 @@ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ +/* atomic op type fields (stored in immediate) */ +#define BPF_FETCH 0x01 /* fetch previous value into src reg */ + /* Register numbers */ enum { BPF_REG_0 = 0, -- cgit v1.2.3 From 5ffa25502b5ab3d639829a2d1e316cff7f59a41e Mon Sep 17 00:00:00 2001 From: Brendan Jackman Date: Thu, 14 Jan 2021 18:17:47 +0000 Subject: bpf: Add instructions for atomic_[cmp]xchg This adds two atomic opcodes, both of which include the BPF_FETCH flag. XCHG without the BPF_FETCH flag would naturally encode atomic_set. This is not supported because it would be of limited value to userspace (it doesn't imply any barriers). CMPXCHG without BPF_FETCH woulud be an atomic compare-and-write. We don't have such an operation in the kernel so it isn't provided to BPF either. There are two significant design decisions made for the CMPXCHG instruction: - To solve the issue that this operation fundamentally has 3 operands, but we only have two register fields. Therefore the operand we compare against (the kernel's API calls it 'old') is hard-coded to be R0. x86 has similar design (and A64 doesn't have this problem). A potential alternative might be to encode the other operand's register number in the immediate field. - The kernel's atomic_cmpxchg returns the old value, while the C11 userspace APIs return a boolean indicating the comparison result. Which should BPF do? A64 returns the old value. x86 returns the old value in the hard-coded register (and also sets a flag). That means return-old-value is easier to JIT, so that's what we use. Signed-off-by: Brendan Jackman Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210114181751.768687-8-jackmanb@google.com --- include/uapi/linux/bpf.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ea262b009049..c001766adcbc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -45,7 +45,9 @@ #define BPF_EXIT 0x90 /* function return */ /* atomic op type fields (stored in immediate) */ -#define BPF_FETCH 0x01 /* fetch previous value into src reg */ +#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */ +#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ +#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ /* Register numbers */ enum { -- cgit v1.2.3 From 88a16a1309333e43d328621ece3e9fa37027e8eb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 14 Jan 2021 14:40:44 +0100 Subject: perf: Add build id data in mmap2 event Adding support to carry build id data in mmap2 event. The build id data replaces maj/min/ino/ino_generation fields, which are also used to identify map's binary, so it's ok to replace them with build id data: union { struct { u32 maj; u32 min; u64 ino; u64 ino_generation; }; struct { u8 build_id_size; u8 __reserved_1; u16 __reserved_2; u8 build_id[20]; }; }; Replaced maj/min/ino/ino_generation fields give us size of 24 bytes. We use 20 bytes for build id data, 1 byte for size and rest is unused. There's new misc bit for mmap2 to signal there's build id data in it: #define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14) Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/bpf/20210114134044.1418404-4-jolsa@kernel.org --- include/uapi/linux/perf_event.h | 42 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 37 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b15e3447cd9f..cb6f84103560 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -386,7 +386,8 @@ struct perf_event_attr { aux_output : 1, /* generate AUX records instead of events */ cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ - __reserved_1 : 30; + build_id : 1, /* use build id in mmap2 events */ + __reserved_1 : 29; union { __u32 wakeup_events; /* wakeup every n events */ @@ -659,6 +660,22 @@ struct perf_event_mmap_page { __u64 aux_size; }; +/* + * The current state of perf_event_header::misc bits usage: + * ('|' used bit, '-' unused bit) + * + * 012 CDEF + * |||---------|||| + * + * Where: + * 0-2 CPUMODE_MASK + * + * C PROC_MAP_PARSE_TIMEOUT + * D MMAP_DATA / COMM_EXEC / FORK_EXEC / SWITCH_OUT + * E MMAP_BUILD_ID / EXACT_IP / SCHED_OUT_PREEMPT + * F (reserved) + */ + #define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) #define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) #define PERF_RECORD_MISC_KERNEL (1 << 0) @@ -690,6 +707,7 @@ struct perf_event_mmap_page { * * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events + * PERF_RECORD_MISC_MMAP_BUILD_ID - PERF_RECORD_MMAP2 event * * * PERF_RECORD_MISC_EXACT_IP: @@ -699,9 +717,13 @@ struct perf_event_mmap_page { * * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT: * Indicates that thread was preempted in TASK_RUNNING state. + * + * PERF_RECORD_MISC_MMAP_BUILD_ID: + * Indicates that mmap2 event carries build id data. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) #define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) +#define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14) /* * Reserve the last bit to indicate some extended misc field */ @@ -915,10 +937,20 @@ enum perf_event_type { * u64 addr; * u64 len; * u64 pgoff; - * u32 maj; - * u32 min; - * u64 ino; - * u64 ino_generation; + * union { + * struct { + * u32 maj; + * u32 min; + * u64 ino; + * u64 ino_generation; + * }; + * struct { + * u8 build_id_size; + * u8 __reserved_1; + * u16 __reserved_2; + * u8 build_id[20]; + * }; + * }; * u32 prot, flags; * char filename[]; * struct sample_id sample_id; -- cgit v1.2.3 From 429b29aef7f841086949c7359f9c3ccb051e7ea3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Fri, 15 Jan 2021 16:51:29 +0100 Subject: tty: serial: Drop unused efm32 serial driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support for this machine was just removed, so drop the now unused UART driver, too. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20210115155130.185010-7-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/serial_core.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h index 62c22045fe65..c4042dcfdc0c 100644 --- a/include/uapi/linux/serial_core.h +++ b/include/uapi/linux/serial_core.h @@ -208,9 +208,6 @@ /* Atheros AR933X SoC */ #define PORT_AR933X 99 -/* Energy Micro efm32 SoC */ -#define PORT_EFMUART 100 - /* ARC (Synopsys) on-chip UART */ #define PORT_ARC 101 -- cgit v1.2.3 From 9ab7e76aefc97a9aa664accb59d6e8dc5e52514a Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Sat, 9 Jan 2021 23:00:21 -0800 Subject: GTP: add support for flow based tunneling API Following patch add support for flow based tunneling API to send and recv GTP tunnel packet over tunnel metadata API. This would allow this device integration with OVS or eBPF using flow based tunneling APIs. Signed-off-by: Pravin B Shelar Link: https://lore.kernel.org/r/20210110070021.26822-1-pbshelar@fb.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/gtp.h | 12 ++++++++++++ include/uapi/linux/if_link.h | 1 + include/uapi/linux/if_tunnel.h | 1 + 3 files changed, 14 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 79f9191bbb24..62aff78b7c56 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,6 +2,8 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ +#include + #define GTP_GENL_MCGRP_NAME "gtp" enum gtp_genl_cmds { @@ -34,4 +36,14 @@ enum gtp_attrs { }; #define GTPA_MAX (__GTPA_MAX + 1) +enum { + GTP_METADATA_V1 +}; + +struct gtpu_metadata { + __u8 ver; + __u8 flags; + __u8 type; +}; + #endif /* _UAPI_LINUX_GTP_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 82708c6db432..2bd0d8bbcdb2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -809,6 +809,7 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, + IFLA_GTP_COLLECT_METADATA, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 7d9105533c7b..802da679fab1 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -176,6 +176,7 @@ enum { #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) #define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) +#define TUNNEL_GTPU_OPT __cpu_to_be16(0x8000) #define TUNNEL_OPTIONS_PRESENT \ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) -- cgit v1.2.3 From f2fc9ff28d1c9bef7760516feadd38164044caae Mon Sep 17 00:00:00 2001 From: Thinh Nguyen Date: Wed, 13 Jan 2021 18:52:46 -0800 Subject: usb: ch9: Add USB 3.2 SSP attributes In preparation for USB 3.2 dual-lane support, add sublink speed attribute macros and enum usb_ssp_rate. A USB device that operates in SuperSpeed Plus may operate at different speed and lane count. These additional macros and enum values help specifying that. Signed-off-by: Thinh Nguyen Link: https://lore.kernel.org/r/ae9293ebd63a29f2a2035054753534d9eb123d74.1610592135.git.Thinh.Nguyen@synopsys.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/ch9.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 0f865ae4ba89..17ce56198c9a 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -968,9 +968,22 @@ struct usb_ssp_cap_descriptor { __le32 bmSublinkSpeedAttr[1]; /* list of sublink speed attrib entries */ #define USB_SSP_SUBLINK_SPEED_SSID (0xf) /* sublink speed ID */ #define USB_SSP_SUBLINK_SPEED_LSE (0x3 << 4) /* Lanespeed exponent */ +#define USB_SSP_SUBLINK_SPEED_LSE_BPS 0 +#define USB_SSP_SUBLINK_SPEED_LSE_KBPS 1 +#define USB_SSP_SUBLINK_SPEED_LSE_MBPS 2 +#define USB_SSP_SUBLINK_SPEED_LSE_GBPS 3 + #define USB_SSP_SUBLINK_SPEED_ST (0x3 << 6) /* Sublink type */ +#define USB_SSP_SUBLINK_SPEED_ST_SYM_RX 0 +#define USB_SSP_SUBLINK_SPEED_ST_ASYM_RX 1 +#define USB_SSP_SUBLINK_SPEED_ST_SYM_TX 2 +#define USB_SSP_SUBLINK_SPEED_ST_ASYM_TX 3 + #define USB_SSP_SUBLINK_SPEED_RSVD (0x3f << 8) /* Reserved */ #define USB_SSP_SUBLINK_SPEED_LP (0x3 << 14) /* Link protocol */ +#define USB_SSP_SUBLINK_SPEED_LP_SS 0 +#define USB_SSP_SUBLINK_SPEED_LP_SSP 1 + #define USB_SSP_SUBLINK_SPEED_LSM (0xff << 16) /* Lanespeed mantissa */ } __attribute__((packed)); -- cgit v1.2.3 From 7b8fc0103bb51d1d3e1fb5fd67958612e709f883 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Mon, 18 Jan 2021 20:09:27 -0500 Subject: bonding: add a vlan+srcmac tx hashing option This comes from an end-user request, where they're running multiple VMs on hosts with bonded interfaces connected to some interest switch topologies, where 802.3ad isn't an option. They're currently running a proprietary solution that effectively achieves load-balancing of VMs and bandwidth utilization improvements with a similar form of transmission algorithm. Basically, each VM has it's own vlan, so it always sends its traffic out the same interface, unless that interface fails. Traffic gets split between the interfaces, maintaining a consistent path, with failover still available if an interface goes down. Unlike bond_eth_hash(), this hash function is using the full source MAC address instead of just the last byte, as there are so few components to the hash, and in the no-vlan case, we would be returning just the last byte of the source MAC as the hash value. It's entirely possible to have two NICs in a bond with the same last byte of their MAC, but not the same MAC, so this adjustment should guarantee distinct hashes in all cases. This has been rudimetarily tested to provide similar results to the proprietary solution it is aiming to replace. A patch for iproute2 is also posted, to properly support the new mode there as well. Cc: Jay Vosburgh Cc: Veaceslav Falico Cc: Andy Gospodarek Cc: Thomas Davis Signed-off-by: Jarod Wilson Link: https://lore.kernel.org/r/20210119010927.1191922-1-jarod@redhat.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bonding.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h index 45f3750aa861..e8eb4ad03cf1 100644 --- a/include/uapi/linux/if_bonding.h +++ b/include/uapi/linux/if_bonding.h @@ -94,6 +94,7 @@ #define BOND_XMIT_POLICY_LAYER23 2 /* layer 2+3 (IP ^ MAC) */ #define BOND_XMIT_POLICY_ENCAP23 3 /* encapsulated layer 2+3 */ #define BOND_XMIT_POLICY_ENCAP34 4 /* encapsulated layer 3+4 */ +#define BOND_XMIT_POLICY_VLAN_SRCMAC 5 /* vlan + source MAC */ /* 802.3ad port state definitions (43.4.2.2 in the 802.3ad standard) */ #define LACP_STATE_LACP_ACTIVITY 0x1 -- cgit v1.2.3 From 7baf2429a1a965369b0ce44efb6315cdd515aa9c Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 19 Jan 2021 16:31:50 +0800 Subject: net/sched: cls_flower add CT_FLAGS_INVALID flag support This patch add the TCA_FLOWER_KEY_CT_FLAGS_INVALID flag to match the ct_state with invalid for conntrack. Signed-off-by: wenxu Acked-by: Marcelo Ricardo Leitner Link: https://lore.kernel.org/r/1611045110-682-1-git-send-email-wenxu@ucloud.cn Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ee95f42fb0ec..709668e264b0 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -591,6 +591,7 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ + TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */ }; enum { -- cgit v1.2.3 From b8288837ef6bdaac331752b401f5ca3b59b37430 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:13 -0800 Subject: devlink: Introduce PCI SF port flavour and port attribute A PCI sub-function (SF) represents a portion of the device similar to PCI VF. In an eswitch, PCI SF may have port which is normally represented using a representor netdevice. To have better visibility of eswitch port, its association with SF, and its representor netdevice, introduce a PCI SF port flavour. When devlink port flavour is PCI SF, fill up PCI SF attributes of the port. Extend port name creation using PCI PF and SF number scheme on best effort basis, so that vendor drivers can skip defining their own scheme. This is done as cApfNSfM, where A, N and M are controller, PCI PF and PCI SF number respectively. This is similar to existing naming for PCI PF and PCI VF ports. An example view of a PCI SF port: $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state active opstate attached $ devlink port show pci/0000:06:00.0/32768 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "splittable": false, "function": { "hw_addr": "00:00:00:00:88:88", "state": "active", "opstate": "attached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/uapi/linux/devlink.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cf89c318f2ac..1a241b09a7f8 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -200,6 +200,10 @@ enum devlink_port_flavour { DEVLINK_PORT_FLAVOUR_UNUSED, /* Port which exists in the switch, but * is not used in any way. */ + DEVLINK_PORT_FLAVOUR_PCI_SF, /* Represents eswitch port + * for the PCI SF. It is an internal + * port that faces the PCI SF. + */ }; enum devlink_param_cmode { @@ -529,6 +533,7 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_ACTION_INFO, /* nested */ DEVLINK_ATTR_RELOAD_ACTION_STATS, /* nested */ + DEVLINK_ATTR_PORT_PCI_SF_NUMBER, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, -- cgit v1.2.3 From a556dded9c23c51c82654f1ebe389cbc0bc22057 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 11 Dec 2020 22:12:15 -0800 Subject: devlink: Support get and set state of port function devlink port function can be in active or inactive state. Allow users to get and set port function's state. When the port function it activated, its operational state may change after a while when the device is created and driver binds to it. Similarly on deactivation flow. To clearly describe the state of the port function and its device's operational state in the host system, define state and opstate attributes. Example of a PCI SF port which supports a port function: $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev $ devlink port show pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 pci/0000:08:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:00:00 state inactive opstate detached $ devlink port show pci/0000:06:00.0/32768 pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false function: hw_addr 00:00:00:00:88:88 state inactive opstate detached $ devlink port function set pci/0000:06:00.0/32768 hw_addr 00:00:00:00:88:88 state active $ devlink port show pci/0000:06:00.0/32768 -jp { "port": { "pci/0000:06:00.0/32768": { "type": "eth", "netdev": "ens2f0npf0sf88", "flavour": "pcisf", "controller": 0, "pfnum": 0, "sfnum": 88, "external": false, "splittable": false, "function": { "hw_addr": "00:00:00:00:88:88", "state": "active", "opstate": "attached" } } } } Signed-off-by: Parav Pandit Reviewed-by: Jiri Pirko Reviewed-by: Vu Pham Signed-off-by: Saeed Mahameed --- include/uapi/linux/devlink.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 1a241b09a7f8..f6008b2fa60f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -583,9 +583,29 @@ enum devlink_resource_unit { enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, /* binary */ + DEVLINK_PORT_FN_ATTR_STATE, /* u8 */ + DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */ __DEVLINK_PORT_FUNCTION_ATTR_MAX, DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 }; +enum devlink_port_fn_state { + DEVLINK_PORT_FN_STATE_INACTIVE, + DEVLINK_PORT_FN_STATE_ACTIVE, +}; + +/** + * enum devlink_port_fn_opstate - indicates operational state of the function + * @DEVLINK_PORT_FN_OPSTATE_ATTACHED: Driver is attached to the function. + * For graceful tear down of the function, after inactivation of the + * function, user should wait for operational state to turn DETACHED. + * @DEVLINK_PORT_FN_OPSTATE_DETACHED: Driver is detached from the function. + * It is safe to delete the port. + */ +enum devlink_port_fn_opstate { + DEVLINK_PORT_FN_OPSTATE_DETACHED, + DEVLINK_PORT_FN_OPSTATE_ATTACHED, +}; + #endif /* _UAPI_LINUX_DEVLINK_H_ */ -- cgit v1.2.3 From e7ed11ee945438b737e2ae2370e35591e16ec371 Mon Sep 17 00:00:00 2001 From: Yousuk Seung Date: Wed, 20 Jan 2021 12:41:55 -0800 Subject: tcp: add TTL to SCM_TIMESTAMPING_OPT_STATS This patch adds TCP_NLA_TTL to SCM_TIMESTAMPING_OPT_STATS that exports the time-to-live or hop limit of the latest incoming packet with SCM_TSTAMP_ACK. The value exported may not be from the packet that acks the sequence when incoming packets are aggregated. Exporting the time-to-live or hop limit value of incoming packets helps to estimate the hop count of the path of the flow that may change over time. Signed-off-by: Yousuk Seung Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Link: https://lore.kernel.org/r/20210120204155.552275-1-ysseung@google.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 768e93bd5b51..16dfa40bdac3 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -314,6 +314,7 @@ enum { TCP_NLA_TIMEOUT_REHASH, /* Timeout-triggered rehash attempts */ TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */ TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */ + TCP_NLA_TTL, /* TTL or hop limit of a packet received */ }; /* for TCP_MD5SIG socket option */ -- cgit v1.2.3 From 7eeba1706eba6def15f6cb2fc7b3c3b9a2651edc Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Wed, 20 Jan 2021 16:41:48 -0800 Subject: tcp: Add receive timestamp support for receive zerocopy. tcp_recvmsg() uses the CMSG mechanism to receive control information like packet receive timestamps. This patch adds CMSG fields to struct tcp_zerocopy_receive, and provides receive timestamps if available to the user. Signed-off-by: Arjun Roy Signed-off-by: Jakub Kicinski --- include/uapi/linux/tcp.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 16dfa40bdac3..42fc5a640df4 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -354,5 +354,9 @@ struct tcp_zerocopy_receive { __u64 copybuf_address; /* in: copybuf address (small reads) */ __s32 copybuf_len; /* in/out: copybuf bytes avail/used or error */ __u32 flags; /* in: flags */ + __u64 msg_control; /* ancillary data */ + __u64 msg_controllen; + __u32 msg_flags; + /* __u32 hole; Next we must add >1 u32 otherwise length checks fail. */ }; #endif /* _UAPI_LINUX_TCP_H */ -- cgit v1.2.3 From d03b195b5aa015f6c11988b86a3625f8d5dbac52 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 19 Jan 2021 14:08:13 +0200 Subject: sch_htb: Hierarchical QoS hardware offload HTB doesn't scale well because of contention on a single lock, and it also consumes CPU. This patch adds support for offloading HTB to hardware that supports hierarchical rate limiting. In the offload mode, HTB passes control commands to the driver using ndo_setup_tc. The driver has to replicate the whole hierarchy of classes and their settings (rate, ceil) in the NIC. Every modification of the HTB tree caused by the admin results in ndo_setup_tc being called. After this setup, the HTB algorithm is done completely in the NIC. An SQ (send queue) is created for every leaf class and attached to the hierarchy, so that the NIC can calculate and obey aggregated rate limits, too. In the future, it can be changed, so that multiple SQs will back a single leaf class. ndo_select_queue is responsible for selecting the right queue that serves the traffic class of each packet. The data path works as follows: a packet is classified by clsact, the driver selects a hardware queue according to its class, and the packet is enqueued into this queue's qdisc. This solution addresses two main problems of scaling HTB: 1. Contention by flow classification. Currently the filters are attached to the HTB instance as follows: # tc filter add dev eth0 parent 1:0 protocol ip flower dst_port 80 classid 1:10 It's possible to move classification to clsact egress hook, which is thread-safe and lock-free: # tc filter add dev eth0 egress protocol ip flower dst_port 80 action skbedit priority 1:10 This way classification still happens in software, but the lock contention is eliminated, and it happens before selecting the TX queue, allowing the driver to translate the class to the corresponding hardware queue in ndo_select_queue. Note that this is already compatible with non-offloaded HTB and doesn't require changes to the kernel nor iproute2. 2. Contention by handling packets. HTB is not multi-queue, it attaches to a whole net device, and handling of all packets takes the same lock. When HTB is offloaded, it registers itself as a multi-queue qdisc, similarly to mq: HTB is attached to the netdev, and each queue has its own qdisc. Some features of HTB may be not supported by some particular hardware, for example, the maximum number of classes may be limited, the granularity of rate and ceil parameters may be different, etc. - so, the offload is not enabled by default, a new parameter is used to enable it: # tc qdisc replace dev eth0 root handle 1: htb offload Signed-off-by: Maxim Mikityanskiy Reviewed-by: Tariq Toukan Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 9e7c2c607845..79a699f106b1 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -434,6 +434,7 @@ enum { TCA_HTB_RATE64, TCA_HTB_CEIL64, TCA_HTB_PAD, + TCA_HTB_OFFLOAD, __TCA_HTB_MAX, }; -- cgit v1.2.3 From 9cde9360d18d8b352b737d10f90f2aecccf93dbe Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 20 Oct 2020 15:48:22 -0400 Subject: NFSD: Update the SETATTR3args decoder to use struct xdr_stream Signed-off-by: Chuck Lever --- include/uapi/linux/nfs3.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nfs3.h b/include/uapi/linux/nfs3.h index 37e4b34e6b43..c22ab77713bd 100644 --- a/include/uapi/linux/nfs3.h +++ b/include/uapi/linux/nfs3.h @@ -63,6 +63,12 @@ enum nfs3_ftype { NF3BAD = 8 }; +enum nfs3_time_how { + DONT_CHANGE = 0, + SET_TO_SERVER_TIME = 1, + SET_TO_CLIENT_TIME = 2, +}; + struct nfs3_fh { unsigned short size; unsigned char data[NFS3_FHSIZE]; -- cgit v1.2.3 From 6b2e04bc240fe9be9e690059f710e9f95346d34d Mon Sep 17 00:00:00 2001 From: Praveen Chaudhary Date: Mon, 25 Jan 2021 13:44:30 -0800 Subject: net: allow user to set metric on default route learned via Router Advertisement For IPv4, default route is learned via DHCPv4 and user is allowed to change metric using config etc/network/interfaces. But for IPv6, default route can be learned via RA, for which, currently a fixed metric value 1024 is used. Ideally, user should be able to configure metric on default route for IPv6 similar to IPv4. This patch adds sysctl for the same. Logs: For IPv4: Config in etc/network/interfaces: auto eth0 iface eth0 inet dhcp metric 4261413864 IPv4 Kernel Route Table: $ ip route list default via 172.21.47.1 dev eth0 metric 4261413864 FRR Table, if a static route is configured: [In real scenario, it is useful to prefer BGP learned default route over DHCPv4 default route.] Codes: K - kernel route, C - connected, S - static, R - RIP, O - OSPF, I - IS-IS, B - BGP, P - PIM, E - EIGRP, N - NHRP, T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP, > - selected route, * - FIB route S>* 0.0.0.0/0 [20/0] is directly connected, eth0, 00:00:03 K 0.0.0.0/0 [254/1000] via 172.21.47.1, eth0, 6d08h51m i.e. User can prefer Default Router learned via Routing Protocol in IPv4. Similar behavior is not possible for IPv6, without this fix. After fix [for IPv6]: sudo sysctl -w net.ipv6.conf.eth0.net.ipv6.conf.eth0.ra_defrtr_metric=1996489705 IP monitor: [When IPv6 RA is received] default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489705 pref high Kernel IPv6 routing table $ ip -6 route list default via fe80::be16:65ff:feb3:ce8e dev eth0 proto ra metric 1996489705 expires 21sec hoplimit 64 pref high FRR Table, if a static route is configured: [In real scenario, it is useful to prefer BGP learned default route over IPv6 RA default route.] Codes: K - kernel route, C - connected, S - static, R - RIPng, O - OSPFv3, I - IS-IS, B - BGP, N - NHRP, T - Table, v - VNC, V - VNC-Direct, A - Babel, D - SHARP, > - selected route, * - FIB route S>* ::/0 [20/0] is directly connected, eth0, 00:00:06 K ::/0 [119/1001] via fe80::xx16:xxxx:feb3:ce8e, eth0, 6d07h43m If the metric is changed later, the effect will be seen only when next IPv6 RA is received, because the default route must be fully controlled by RA msg. Below metric is changed from 1996489705 to 1996489704. $ sudo sysctl -w net.ipv6.conf.eth0.ra_defrtr_metric=1996489704 net.ipv6.conf.eth0.ra_defrtr_metric = 1996489704 IP monitor: [On next IPv6 RA msg, Kernel deletes prev route and installs new route with updated metric] Deleted default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489705 expires 3sec hoplimit 64 pref high default via fe80::xx16:xxxx:feb3:ce8e dev eth0 proto ra metric 1996489704 pref high Signed-off-by: Praveen Chaudhary Signed-off-by: Zhenggen Xu Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20210125214430.24079-1-pchaudhary@linkedin.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/ipv6.h | 1 + include/uapi/linux/sysctl.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 13e8751bf24a..70603775fe91 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -189,6 +189,7 @@ enum { DEVCONF_ACCEPT_RA_RT_INFO_MIN_PLEN, DEVCONF_NDISC_TCLASS, DEVCONF_RPL_SEG_ENABLED, + DEVCONF_RA_DEFRTR_METRIC, DEVCONF_MAX }; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 458179df9b27..1e05d3caa712 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -571,6 +571,7 @@ enum { NET_IPV6_ACCEPT_SOURCE_ROUTE=25, NET_IPV6_ACCEPT_RA_FROM_LOCAL=26, NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27, + NET_IPV6_RA_DEFRTR_METRIC=28, __NET_IPV6_MAX }; -- cgit v1.2.3 From 2dba407f994e5b0eb3b70a8cb280e014ec4a7ff3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 26 Jan 2021 11:35:33 +0200 Subject: net: bridge: multicast: make tracked EHT hosts limit configurable Add two new port attributes which make EHT hosts limit configurable and export the current number of tracked EHT hosts: - IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT: configure/retrieve current limit - IFLA_BRPORT_MCAST_EHT_HOSTS_CNT: current number of tracked hosts Setting IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT to 0 is currently not allowed. Note that we have to increase RTNL_SLAVE_MAX_TYPE to 38 minimum, I've increased it to 40 to have space for two more future entries. v2: move br_multicast_eht_set_hosts_limit() to br_multicast_eht.c, no functional change Signed-off-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_link.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 2bd0d8bbcdb2..eb8018c3a737 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -525,6 +525,8 @@ enum { IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) -- cgit v1.2.3 From 31f190e0ccac8b75d33fdc95a797c526cf9b149e Mon Sep 17 00:00:00 2001 From: Dafna Hirschfeld Date: Thu, 21 Jan 2021 15:44:02 +0100 Subject: media: rkisp1: uapi: change hist_bins array type from __u16 to __u32 Each entry in the array is a 20 bits value composed of 16 bits unsigned integer and 4 bits fractional part. So the type should change to __u32. In addition add a documentation of how the measurements are done. Signed-off-by: Dafna Hirschfeld Acked-by: Helen Koike Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/rkisp1-config.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 6e449e784260..24f05d6d258f 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -844,13 +844,18 @@ struct rkisp1_cif_isp_af_stat { /** * struct rkisp1_cif_isp_hist_stat - statistics histogram data * - * @hist_bins: measured bin counters + * @hist_bins: measured bin counters. Each bin is a 20 bits unsigned fixed point + * type. Bits 0-4 are the fractional part and bits 5-19 are the + * integer part. * - * Measurement window divided into 25 sub-windows, set - * with ISP_HIST_XXX + * The window of the measurements area is divided to 5x5 sub-windows. The + * histogram is then computed for each sub-window independently and the final + * result is a weighted average of the histogram measurements on all + * sub-windows. The window of the measurements area and the weight of each + * sub-window are configurable using struct @rkisp1_cif_isp_hst_config. */ struct rkisp1_cif_isp_hist_stat { - __u16 hist_bins[RKISP1_CIF_ISP_HIST_BIN_N_MAX]; + __u32 hist_bins[RKISP1_CIF_ISP_HIST_BIN_N_MAX]; }; /** -- cgit v1.2.3 From 66d81de7ea9d2b0775e5bfd5e770483a1c24b9ca Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Thu, 21 Jan 2021 15:44:05 +0100 Subject: media: rockchip: rkisp1: reduce number of histogram grid elements in uapi The uapi right now specifies an array size of 28 but the actual number of elements is only 25 with the last 3 being unused. Reduce the array size to the correct number of elements and change the params code to iterate the array 25 times. Signed-off-by: Heiko Stuebner Signed-off-by: Dafna Hirschfeld Acked-by: Helen Koike Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/rkisp1-config.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 24f05d6d258f..35aa82d5f6dd 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -102,8 +102,7 @@ /* * Histogram calculation */ -/* Last 3 values unused. */ -#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 28 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 25 /* * Defect Pixel Cluster Correction -- cgit v1.2.3 From fc672d806bd77eff26117479e90ccdcfd2a8ecb4 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Thu, 21 Jan 2021 15:44:06 +0100 Subject: media: rockchip: rkisp1: carry ip version information The IP block evolved from its rk3288/rk3399 base and the vendor designates them with a numerical version. rk3399 for example is designated V10 probably meaning V1.0. There doesn't seem to be an actual version register we could read that information from, so allow the match_data to carry that information for future differentiation. Also carry that information in the hw_revision field of the media- controller API, so that userspace also has access to that. The added versions are: - V10: at least rk3288 + rk3399 - V11: seemingly unused as of now, but probably appeared in some soc - V12: at least rk3326 + px30 - V13: at least rk1808 [fix checkpatch warning don't use multiple blank lines] Signed-off-by: Heiko Stuebner Signed-off-by: Dafna Hirschfeld Reviewed-by: Ezequiel Garcia Acked-by: Helen Koike Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/rkisp1-config.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index 35aa82d5f6dd..bee4413fe0d3 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -123,6 +123,21 @@ #define RKISP1_CIF_ISP_STAT_AFM (1U << 2) #define RKISP1_CIF_ISP_STAT_HIST (1U << 3) +/** + * enum rkisp1_cif_isp_version - ISP variants + * + * @RKISP1_V10: used at least in rk3288 and rk3399 + * @RKISP1_V11: declared in the original vendor code, but not used + * @RKISP1_V12: used at least in rk3326 and px30 + * @RKISP1_V13: used at least in rk1808 + */ +enum rkisp1_cif_isp_version { + RKISP1_V10 = 10, + RKISP1_V11, + RKISP1_V12, + RKISP1_V13, +}; + enum rkisp1_cif_isp_histogram_mode { RKISP1_CIF_ISP_HISTOGRAM_MODE_DISABLE, RKISP1_CIF_ISP_HISTOGRAM_MODE_RGB_COMBINED, -- cgit v1.2.3 From ef357e02b6c420dc2d668ebf3165838c77358acd Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Thu, 21 Jan 2021 15:44:07 +0100 Subject: media: rockchip: rkisp1: extend uapi array sizes Later variants of the rkisp1 block use more entries in some arrays: RKISP1_CIF_ISP_AE_MEAN_MAX 25 -> 81 RKISP1_CIF_ISP_HIST_BIN_N_MAX 16 -> 32 RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES 17 -> 34 RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 25 -> 81 and we can still extend the uapi during the 5.11-rc cycle, so do that now to be on the safe side. V10 and V11 only need the smaller sizes, while V12 and V13 needed the larger sizes. When adding the bigger sizes make sure, values filled from hardware values and transmitted to userspace don't leak kernel data by zeroing them beforehand. Signed-off-by: Heiko Stuebner Signed-off-by: Dafna Hirschfeld Reviewed-by: Ezequiel Garcia Acked-by: Helen Koike Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/rkisp1-config.h | 67 ++++++++++++++++++++++++++++++++------ 1 file changed, 57 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rkisp1-config.h b/include/uapi/linux/rkisp1-config.h index bee4413fe0d3..36e3efb81b01 100644 --- a/include/uapi/linux/rkisp1-config.h +++ b/include/uapi/linux/rkisp1-config.h @@ -49,8 +49,14 @@ #define RKISP1_CIF_ISP_CTK_COEFF_MAX 0x100 #define RKISP1_CIF_ISP_CTK_OFFSET_MAX 0x800 -#define RKISP1_CIF_ISP_AE_MEAN_MAX 25 -#define RKISP1_CIF_ISP_HIST_BIN_N_MAX 16 +#define RKISP1_CIF_ISP_AE_MEAN_MAX_V10 25 +#define RKISP1_CIF_ISP_AE_MEAN_MAX_V12 81 +#define RKISP1_CIF_ISP_AE_MEAN_MAX RKISP1_CIF_ISP_AE_MEAN_MAX_V12 + +#define RKISP1_CIF_ISP_HIST_BIN_N_MAX_V10 16 +#define RKISP1_CIF_ISP_HIST_BIN_N_MAX_V12 32 +#define RKISP1_CIF_ISP_HIST_BIN_N_MAX RKISP1_CIF_ISP_HIST_BIN_N_MAX_V12 + #define RKISP1_CIF_ISP_AFM_MAX_WINDOWS 3 #define RKISP1_CIF_ISP_DEGAMMA_CURVE_SIZE 17 @@ -86,7 +92,9 @@ * Gamma out */ /* Maximum number of color samples supported */ -#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES 17 +#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V10 17 +#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V12 34 +#define RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V12 /* * Lens shade correction @@ -102,7 +110,9 @@ /* * Histogram calculation */ -#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE 25 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V10 25 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V12 81 +#define RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V12 /* * Defect Pixel Cluster Correction @@ -524,6 +534,15 @@ enum rkisp1_cif_isp_goc_mode { * * @mode: goc mode (from enum rkisp1_cif_isp_goc_mode) * @gamma_y: gamma out curve y-axis for all color components + * + * The number of entries of @gamma_y depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V10 + * entries, versions >= V12 have RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES_V12 + * entries. RKISP1_CIF_ISP_GAMMA_OUT_MAX_SAMPLES is equal to the maximum + * of the two. */ struct rkisp1_cif_isp_goc_config { __u32 mode; @@ -538,6 +557,15 @@ struct rkisp1_cif_isp_goc_config { * skipped * @meas_window: coordinates of the measure window * @hist_weight: weighting factor for sub-windows + * + * The number of entries of @hist_weight depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V10 + * entries, versions >= V12 have RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE_V12 + * entries. RKISP1_CIF_ISP_HISTOGRAM_WEIGHT_GRIDS_SIZE is equal to the maximum + * of the two. */ struct rkisp1_cif_isp_hst_config { __u32 mode; @@ -825,7 +853,15 @@ struct rkisp1_cif_isp_bls_meas_val { * @exp_mean: Mean luminance value of block xx * @bls_val: BLS measured values * - * Image is divided into 5x5 blocks. + * The number of entries of @exp_mean depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_AE_MEAN_MAX_V10 entries, + * versions >= V12 have RKISP1_CIF_ISP_AE_MEAN_MAX_V12 entries. + * RKISP1_CIF_ISP_AE_MEAN_MAX is equal to the maximum of the two. + * + * Image is divided into 5x5 blocks on V10 and 9x9 blocks on V12. */ struct rkisp1_cif_isp_ae_stat { __u8 exp_mean[RKISP1_CIF_ISP_AE_MEAN_MAX]; @@ -862,11 +898,22 @@ struct rkisp1_cif_isp_af_stat { * type. Bits 0-4 are the fractional part and bits 5-19 are the * integer part. * - * The window of the measurements area is divided to 5x5 sub-windows. The - * histogram is then computed for each sub-window independently and the final - * result is a weighted average of the histogram measurements on all - * sub-windows. The window of the measurements area and the weight of each - * sub-window are configurable using struct @rkisp1_cif_isp_hst_config. + * The window of the measurements area is divided to 5x5 sub-windows for + * V10/V11 and to 9x9 sub-windows for V12. The histogram is then computed for + * each sub-window independently and the final result is a weighted average of + * the histogram measurements on all sub-windows. The window of the + * measurements area and the weight of each sub-window are configurable using + * struct @rkisp1_cif_isp_hst_config. + * + * The histogram contains 16 bins in V10/V11 and 32 bins in V12/V13. + * + * The number of entries of @hist_bins depends on the hardware revision + * as is reported by the hw_revision field of the struct media_device_info + * that is returned by ioctl MEDIA_IOC_DEVICE_INFO. + * + * Versions <= V11 have RKISP1_CIF_ISP_HIST_BIN_N_MAX_V10 entries, + * versions >= V12 have RKISP1_CIF_ISP_HIST_BIN_N_MAX_V12 entries. + * RKISP1_CIF_ISP_HIST_BIN_N_MAX is equal to the maximum of the two. */ struct rkisp1_cif_isp_hist_stat { __u32 hist_bins[RKISP1_CIF_ISP_HIST_BIN_N_MAX]; -- cgit v1.2.3 From 8c85d18ce647ac2517a1a1bb01b02648e23700e6 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Wed, 27 Jan 2021 16:32:45 +0200 Subject: net/sched: cls_flower: Add match on the ct_state reply flag Add match on the ct_state reply flag. Example: $ tc filter add dev ens1f0_0 ingress prio 1 chain 1 proto ip flower \ ct_state +trk+est+rpl \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress prio 1 chain 1 proto ip flower \ ct_state +trk+est-rpl \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/uapi/linux/pkt_cls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 709668e264b0..afe6836e44b1 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -592,6 +592,7 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ TCA_FLOWER_KEY_CT_FLAGS_INVALID = 1 << 4, /* Conntrack is invalid. */ + TCA_FLOWER_KEY_CT_FLAGS_REPLY = 1 << 5, /* Packet is in the reply direction. */ }; enum { -- cgit v1.2.3 From 2a6c6b7d7ad346f0679d0963cb19b3f0ea7ef32c Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 28 Jan 2021 14:40:07 -0800 Subject: perf/core: Add PERF_SAMPLE_WEIGHT_STRUCT Current PERF_SAMPLE_WEIGHT sample type is very useful to expresses the cost of an action represented by the sample. This allows the profiler to scale the samples to be more informative to the programmer. It could also help to locate a hotspot, e.g., when profiling by memory latencies, the expensive load appear higher up in the histograms. But current PERF_SAMPLE_WEIGHT sample type is solely determined by one factor. This could be a problem, if users want two or more factors to contribute to the weight. For example, Golden Cove core PMU can provide both the instruction latency and the cache Latency information as factors for the memory profiling. For current X86 platforms, although meminfo::latency is defined as a u64, only the lower 32 bits include the valid data in practice (No memory access could last than 4G cycles). The higher 32 bits can be used to store new factors. Add a new sample type, PERF_SAMPLE_WEIGHT_STRUCT, to indicate the new sample weight structure. It shares the same space as the PERF_SAMPLE_WEIGHT sample type. Users can apply either the PERF_SAMPLE_WEIGHT sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type to retrieve the sample weight, but they cannot apply both sample types simultaneously. Currently, only X86 and PowerPC use the PERF_SAMPLE_WEIGHT sample type. - For PowerPC, there is nothing changed for the PERF_SAMPLE_WEIGHT sample type. There is no effect for the new PERF_SAMPLE_WEIGHT_STRUCT sample type. PowerPC can re-struct the weight field similarly later. - For X86, the same value will be dumped for the PERF_SAMPLE_WEIGHT sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type for now. The following patches will apply the new factors for the PERF_SAMPLE_WEIGHT_STRUCT sample type. The field in the union perf_sample_weight should be shared among different architectures. A generic name is required, but it's hard to abstract a name that applies to all architectures. For example, on X86, the fields are to store all kinds of latency. While on PowerPC, it stores MMCRA[TECX/TECM], which should not be latency. So a general name prefix 'var$NUM' is used here. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1611873611-156687-2-git-send-email-kan.liang@linux.intel.com --- include/uapi/linux/perf_event.h | 42 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 40 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b15e3447cd9f..b2cc246ec119 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -145,12 +145,14 @@ enum perf_event_sample_format { PERF_SAMPLE_CGROUP = 1U << 21, PERF_SAMPLE_DATA_PAGE_SIZE = 1U << 22, PERF_SAMPLE_CODE_PAGE_SIZE = 1U << 23, + PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24, - PERF_SAMPLE_MAX = 1U << 24, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; +#define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) /* * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set * @@ -890,7 +892,24 @@ enum perf_event_type { * char data[size]; * u64 dyn_size; } && PERF_SAMPLE_STACK_USER * - * { u64 weight; } && PERF_SAMPLE_WEIGHT + * { union perf_sample_weight + * { + * u64 full; && PERF_SAMPLE_WEIGHT + * #if defined(__LITTLE_ENDIAN_BITFIELD) + * struct { + * u32 var1_dw; + * u16 var2_w; + * u16 var3_w; + * } && PERF_SAMPLE_WEIGHT_STRUCT + * #elif defined(__BIG_ENDIAN_BITFIELD) + * struct { + * u16 var3_w; + * u16 var2_w; + * u32 var1_dw; + * } && PERF_SAMPLE_WEIGHT_STRUCT + * #endif + * } + * } * { u64 data_src; } && PERF_SAMPLE_DATA_SRC * { u64 transaction; } && PERF_SAMPLE_TRANSACTION * { u64 abi; # enum perf_sample_regs_abi @@ -1248,4 +1267,23 @@ struct perf_branch_entry { reserved:40; }; +union perf_sample_weight { + __u64 full; +#if defined(__LITTLE_ENDIAN_BITFIELD) + struct { + __u32 var1_dw; + __u16 var2_w; + __u16 var3_w; + }; +#elif defined(__BIG_ENDIAN_BITFIELD) + struct { + __u16 var3_w; + __u16 var2_w; + __u32 var1_dw; + }; +#else +#error "Unknown endianness" +#endif +}; + #endif /* _UAPI_LINUX_PERF_EVENT_H */ -- cgit v1.2.3 From 61b985e3e775a3a75fda04ce7ef1b1aefc4758bc Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 28 Jan 2021 14:40:10 -0800 Subject: perf/x86/intel: Add perf core PMU support for Sapphire Rapids Add perf core PMU support for the Intel Sapphire Rapids server, which is the successor of the Intel Ice Lake server. The enabling code is based on Ice Lake, but there are several new features introduced. The event encoding is changed and simplified, e.g., the event codes which are below 0x90 are restricted to counters 0-3. The event codes which above 0x90 are likely to have no restrictions. The event constraints, extra_regs(), and hardware cache events table are changed accordingly. A new Precise Distribution (PDist) facility is introduced, which further minimizes the skid when a precise event is programmed on the GP counter 0. Enable the Precise Distribution (PDist) facility with :ppp event. For this facility to work, the period must be initialized with a value larger than 127. Add spr_limit_period() to apply the limit for :ppp event. Two new data source fields, data block & address block, are added in the PEBS Memory Info Record for the load latency event. To enable the feature, - An auxiliary event has to be enabled together with the load latency event on Sapphire Rapids. A new flag PMU_FL_MEM_LOADS_AUX is introduced to indicate the case. A new event, mem-loads-aux, is exposed to sysfs for the user tool. Add a check in hw_config(). If the auxiliary event is not detected, return an unique error -ENODATA. - The union perf_mem_data_src is extended to support the new fields. - Ice Lake and earlier models do not support block information, but the fields may be set by HW on some machines. Add pebs_no_block to explicitly indicate the previous platforms which don't support the new block fields. Accessing the new block fields are ignored on those platforms. A new store Latency facility is introduced, which leverages the PEBS facility where it can provide additional information about sampled stores. The additional information includes the data address, memory auxiliary info (e.g. Data Source, STLB miss) and the latency of the store access. To enable the facility, the new event (0x02cd) has to be programed on the GP counter 0. A new flag PERF_X86_EVENT_PEBS_STLAT is introduced to indicate the event. The store_latency_data() is introduced to parse the memory auxiliary info. The layout of access latency field of PEBS Memory Info Record has been changed. Two latency, instruction latency (bit 15:0) and cache access latency (bit 47:32) are recorded. - The cache access latency is similar to previous memory access latency. For loads, the latency starts by the actual cache access until the data is returned by the memory subsystem. For stores, the latency starts when the demand write accesses the L1 data cache and lasts until the cacheline write is completed in the memory subsystem. The cache access latency is stored in low 32bits of the sample type PERF_SAMPLE_WEIGHT_STRUCT. - The instruction latency starts by the dispatch of the load operation for execution and lasts until completion of the instruction it belongs to. Add a new flag PMU_FL_INSTR_LATENCY to indicate the instruction latency support. The instruction latency is stored in the bit 47:32 of the sample type PERF_SAMPLE_WEIGHT_STRUCT. Extends the PERF_METRICS MSR to feature TMA method level 2 metrics. The lower half of the register is the TMA level 1 metrics (legacy). The upper half is also divided into four 8-bit fields for the new level 2 metrics. Expose all eight Topdown metrics events to user space. The full description for the SPR features can be found at Intel Architecture Instruction Set Extensions and Future Features Programming Reference, 319433-041. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1611873611-156687-5-git-send-email-kan.liang@linux.intel.com --- include/uapi/linux/perf_event.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b2cc246ec119..7d292de51410 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1146,14 +1146,16 @@ union perf_mem_data_src { mem_lvl_num:4, /* memory hierarchy level number */ mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ - mem_rsvd:24; + mem_blk:3, /* access blocked */ + mem_rsvd:21; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:24, + __u64 mem_rsvd:21, + mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ mem_lvl_num:4, /* memory hierarchy level number */ @@ -1236,6 +1238,12 @@ union perf_mem_data_src { #define PERF_MEM_TLB_OS 0x40 /* OS fault handler */ #define PERF_MEM_TLB_SHIFT 26 +/* Access blocked */ +#define PERF_MEM_BLK_NA 0x01 /* not available */ +#define PERF_MEM_BLK_DATA 0x02 /* data could not be forwarded */ +#define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ +#define PERF_MEM_BLK_SHIFT 40 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) -- cgit v1.2.3 From 269bbe5fd4d2fdd3b0d3a82a3c3c1dd1209aa8b8 Mon Sep 17 00:00:00 2001 From: Bijan Mottahedeh Date: Fri, 15 Jan 2021 17:37:44 +0000 Subject: io_uring: rename file related variables to rsrc This is a prep rename patch for subsequent patches to generalize file registration. [io_uring_rsrc_update:: rename fds -> data] Reviewed-by: Pavel Begunkov Signed-off-by: Bijan Mottahedeh [leave io_uring_files_update as struct] Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index d31a2a1e8ef9..f9f106c54d90 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -285,12 +285,19 @@ enum { IORING_REGISTER_LAST }; +/* deprecated, see struct io_uring_rsrc_update */ struct io_uring_files_update { __u32 offset; __u32 resv; __aligned_u64 /* __s32 * */ fds; }; +struct io_uring_rsrc_update { + __u32 offset; + __u32 resv; + __aligned_u64 data; +}; + #define IO_URING_OP_SUPPORTED (1U << 0) struct io_uring_probe_op { -- cgit v1.2.3 From 4e0377a1c5c633852f443a562ec55f7dfea65350 Mon Sep 17 00:00:00 2001 From: noah Date: Tue, 26 Jan 2021 15:23:28 -0500 Subject: io_uring: Add skip option for __io_sqe_files_update This patch adds support for skipping a file descriptor when using IORING_REGISTER_FILES_UPDATE. __io_sqe_files_update will skip fds set to IORING_REGISTER_FILES_SKIP. IORING_REGISTER_FILES_SKIP is inturn added as a #define in io_uring.h Signed-off-by: noah Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index f9f106c54d90..ac4e1738a9af 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -298,6 +298,9 @@ struct io_uring_rsrc_update { __aligned_u64 data; }; +/* Skip updating fd indexes set to this value in the fd table */ +#define IORING_REGISTER_FILES_SKIP (-2) + #define IO_URING_OP_SUPPORTED (1U << 0) struct io_uring_probe_op { -- cgit v1.2.3 From c7020068bf2397b60bb62a1f71ca0fe626c1f7e7 Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Sun, 20 Sep 2020 04:58:57 +0300 Subject: tee: fix some comment typos in header files struct tee_param: revc -> recv. TEE_IOC_SUPPL_SEND: typo introduced by copy-pasting, replace invalid description with description from the according argument struct. Signed-off-by: Elvira Khabirova Signed-off-by: Jens Wiklander --- include/uapi/linux/tee.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index d67cadf221fc..25a6c534beb1 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -355,7 +355,7 @@ struct tee_iocl_supp_send_arg { }; /** - * TEE_IOC_SUPPL_SEND - Receive a request for a supplicant function + * TEE_IOC_SUPPL_SEND - Send a response to a received request * * Takes a struct tee_ioctl_buf_data which contains a struct * tee_iocl_supp_send_arg followed by any array of struct tee_param -- cgit v1.2.3 From 012ce4dd3102a0f4d80167de343e9d44b257c1b8 Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 2 Feb 2021 20:06:06 +0200 Subject: ethtool: Extend link modes settings uAPI with lanes Currently, when auto negotiation is on, the user can advertise all the linkmodes which correspond to a specific speed, but does not have a similar selector for the number of lanes. This is significant when a specific speed can be achieved using different number of lanes. For example, 2x50 or 4x25. Add 'ETHTOOL_A_LINKMODES_LANES' attribute and expand 'struct ethtool_link_settings' with lanes field in order to implement a new lanes-selector that will enable the user to advertise a specific number of lanes as well. When auto negotiation is off, lanes parameter can be forced only if the driver supports it. Add a capability bit in 'struct ethtool_ops' that allows ethtool know if the driver can handle the lanes parameter when auto negotiation is off, so if it does not, an error message will be returned when trying to set lanes. Example: $ ethtool -s swp1 lanes 4 $ ethtool swp1 Settings for swp1: Supported ports: [ FIBRE ] Supported link modes: 1000baseKX/Full 10000baseKR/Full 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 25000baseCR/Full 25000baseSR/Full 50000baseCR2/Full 100000baseSR4/Full 100000baseCR4/Full Supported pause frame use: Symmetric Receive-only Supports auto-negotiation: Yes Supported FEC modes: Not reported Advertised link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full Advertised pause frame use: No Advertised auto-negotiation: Yes Advertised FEC modes: Not reported Speed: Unknown! Duplex: Unknown! (255) Auto-negotiation: on Port: Direct Attach Copper PHYAD: 0 Transceiver: internal Link detected: no Signed-off-by: Danielle Ratson Signed-off-by: Jakub Kicinski --- include/uapi/linux/ethtool_netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index e2bf36e6964b..a286635ac9b8 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -227,6 +227,7 @@ enum { ETHTOOL_A_LINKMODES_DUPLEX, /* u8 */ ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG, /* u8 */ ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE, /* u8 */ + ETHTOOL_A_LINKMODES_LANES, /* u32 */ /* add new constants above here */ __ETHTOOL_A_LINKMODES_CNT, -- cgit v1.2.3 From 2c07ded06427dd3339278487a1413d5e478f05f9 Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Mon, 4 Jan 2021 09:17:49 -0600 Subject: KVM/SVM: add support for SEV attestation command The SEV FW version >= 0.23 added a new command that can be used to query the attestation report containing the SHA-256 digest of the guest memory encrypted through the KVM_SEV_LAUNCH_UPDATE_{DATA, VMSA} commands and sign the report with the Platform Endorsement Key (PEK). See the SEV FW API spec section 6.8 for more details. Note there already exist a command (KVM_SEV_LAUNCH_MEASURE) that can be used to get the SHA-256 digest. The main difference between the KVM_SEV_LAUNCH_MEASURE and KVM_SEV_ATTESTATION_REPORT is that the latter can be called while the guest is running and the measurement value is signed with PEK. Cc: James Bottomley Cc: Tom Lendacky Cc: David Rientjes Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Borislav Petkov Cc: John Allen Cc: Herbert Xu Cc: linux-crypto@vger.kernel.org Reviewed-by: Tom Lendacky Acked-by: David Rientjes Tested-by: James Bottomley Signed-off-by: Brijesh Singh Message-Id: <20210104151749.30248-1-brijesh.singh@amd.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 374c67875cdb..07c194e2c302 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1593,6 +1593,8 @@ enum sev_cmd_id { KVM_SEV_DBG_ENCRYPT, /* Guest certificates commands */ KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, KVM_SEV_NR_MAX, }; @@ -1645,6 +1647,12 @@ struct kvm_sev_dbg { __u32 len; }; +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; +}; + #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) #define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1) #define KVM_DEV_ASSIGN_MASK_INTX (1 << 2) -- cgit v1.2.3 From fe6b6bc802b40081e8a7a1abe8d32b88d10a03e1 Mon Sep 17 00:00:00 2001 From: Chenyi Qiang Date: Fri, 6 Nov 2020 17:03:14 +0800 Subject: KVM: VMX: Enable bus lock VM exit Virtual Machine can exploit bus locks to degrade the performance of system. Bus lock can be caused by split locked access to writeback(WB) memory or by using locks on uncacheable(UC) memory. The bus lock is typically >1000 cycles slower than an atomic operation within a cache line. It also disrupts performance on other cores (which must wait for the bus lock to be released before their memory operations can complete). To address the threat, bus lock VM exit is introduced to notify the VMM when a bus lock was acquired, allowing it to enforce throttling or other policy based mitigations. A VMM can enable VM exit due to bus locks by setting a new "Bus Lock Detection" VM-execution control(bit 30 of Secondary Processor-based VM execution controls). If delivery of this VM exit was preempted by a higher priority VM exit (e.g. EPT misconfiguration, EPT violation, APIC access VM exit, APIC write VM exit, exception bitmap exiting), bit 26 of exit reason in vmcs field is set to 1. In current implementation, the KVM exposes this capability through KVM_CAP_X86_BUS_LOCK_EXIT. The user can get the supported mode bitmap (i.e. off and exit) and enable it explicitly (disabled by default). If bus locks in guest are detected by KVM, exit to user space even when current exit reason is handled by KVM internally. Set a new field KVM_RUN_BUS_LOCK in vcpu->run->flags to inform the user space that there is a bus lock detected in guest. Document for Bus Lock VM exit is now available at the latest "Intel Architecture Instruction Set Extensions Programming Reference". Document Link: https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html Co-developed-by: Xiaoyao Li Signed-off-by: Xiaoyao Li Signed-off-by: Chenyi Qiang Message-Id: <20201106090315.18606-4-chenyi.qiang@intel.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 07c194e2c302..dfe3ba5cf262 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -252,6 +252,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_X86_WRMSR 30 #define KVM_EXIT_DIRTY_RING_FULL 31 #define KVM_EXIT_AP_RESET_HOLD 32 +#define KVM_EXIT_X86_BUS_LOCK 33 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -1058,6 +1059,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 #define KVM_CAP_SYS_HYPERV_CPUID 191 #define KVM_CAP_DIRTY_LOG_RING 192 +#define KVM_CAP_X86_BUS_LOCK_EXIT 193 #ifdef KVM_CAP_IRQ_ROUTING @@ -1774,4 +1776,7 @@ struct kvm_dirty_gfn { __u64 offset; }; +#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) +#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) + #endif /* __LINUX_KVM_H */ -- cgit v1.2.3 From 23200b7a30de315d0e9a40663c905869d29d833c Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Wed, 13 Jun 2018 09:55:44 -0400 Subject: KVM: x86/xen: intercept xen hypercalls if enabled Add a new exit reason for emulator to handle Xen hypercalls. Since this means KVM owns the ABI, dispense with the facility for the VMM to provide its own copy of the hypercall pages; just fill them in directly using VMCALL/VMMCALL as we do for the Hyper-V hypercall page. This behaviour is enabled by a new INTERCEPT_HCALL flag in the KVM_XEN_HVM_CONFIG ioctl structure, and advertised by the same flag being returned from the KVM_CAP_XEN_HVM check. Rename xen_hvm_config() to kvm_xen_write_hypercall_page() and move it to the nascent xen.c while we're at it, and add a test case. Signed-off-by: Joao Martins Signed-off-by: David Woodhouse --- include/uapi/linux/kvm.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index dfe3ba5cf262..c87defe5db4f 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -216,6 +216,20 @@ struct kvm_hyperv_exit { } u; }; +struct kvm_xen_exit { +#define KVM_EXIT_XEN_HCALL 1 + __u32 type; + union { + struct { + __u32 longmode; + __u32 cpl; + __u64 input; + __u64 result; + __u64 params[6]; + } hcall; + } u; +}; + #define KVM_S390_GET_SKEYS_NONE 1 #define KVM_S390_SKEYS_MAX 1048576 @@ -253,6 +267,7 @@ struct kvm_hyperv_exit { #define KVM_EXIT_DIRTY_RING_FULL 31 #define KVM_EXIT_AP_RESET_HOLD 32 #define KVM_EXIT_X86_BUS_LOCK 33 +#define KVM_EXIT_XEN 34 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -429,6 +444,8 @@ struct kvm_run { __u32 index; /* kernel -> user */ __u64 data; /* kernel <-> user */ } msr; + /* KVM_EXIT_XEN */ + struct kvm_xen_exit xen; /* Fix the size of the union. */ char padding[256]; }; @@ -1133,6 +1150,9 @@ struct kvm_x86_mce { #endif #ifdef KVM_CAP_XEN_HVM +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) + struct kvm_xen_hvm_config { __u32 flags; __u32 msr; -- cgit v1.2.3 From a76b9641ad1c0b045045727a6cbbeebf80b6b9bb Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Thu, 3 Dec 2020 15:52:25 +0000 Subject: KVM: x86/xen: add KVM_XEN_HVM_SET_ATTR/KVM_XEN_HVM_GET_ATTR This will be used to set up shared info pages etc. Signed-off-by: Joao Martins Signed-off-by: David Woodhouse --- include/uapi/linux/kvm.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index c87defe5db4f..334796799dbc 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1587,6 +1587,17 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_DIRTY_LOG_RING */ #define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7) +#define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) +#define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 pad[8]; + } u; +}; + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From a3833b81b05d0ae92ae085959dd8da136ec91868 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Thu, 3 Dec 2020 16:20:32 +0000 Subject: KVM: x86/xen: latch long_mode when hypercall page is set up Signed-off-by: David Woodhouse --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 334796799dbc..11644954a2e2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1594,10 +1594,13 @@ struct kvm_xen_hvm_attr { __u16 type; __u16 pad[3]; union { + __u8 long_mode; __u64 pad[8]; } u; }; +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From 13ffb97a3b11998450d51457b6b3617781953f7c Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Fri, 15 Jun 2018 21:17:14 -0400 Subject: KVM: x86/xen: register shared_info page Add KVM_XEN_ATTR_TYPE_SHARED_INFO to allow hypervisor to know where the guest's shared info page is. Signed-off-by: Joao Martins Signed-off-by: David Woodhouse --- include/uapi/linux/kvm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 11644954a2e2..f57f6e741a28 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1595,11 +1595,15 @@ struct kvm_xen_hvm_attr { __u16 pad[3]; union { __u8 long_mode; + struct { + __u64 gfn; + } shared_info; __u64 pad[8]; } u; }; #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 3e3246158808d46b81edb8246214c0ab5a852594 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Tue, 2 Feb 2021 16:53:25 +0000 Subject: KVM: x86/xen: Add KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR This will be used for per-vCPU setup such as runstate and vcpu_info. Signed-off-by: David Woodhouse --- include/uapi/linux/kvm.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index f57f6e741a28..e2b0cbde1908 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1587,6 +1587,7 @@ struct kvm_pv_cmd { /* Available with KVM_CAP_DIRTY_LOG_RING */ #define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7) +/* Per-VM Xen attributes */ #define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) #define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) @@ -1605,6 +1606,18 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +/* Per-vCPU Xen attributes */ +#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) +#define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 pad[8]; + } u; +}; + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From 73e69a86347afe8156aa50c436fc192b280b0cd7 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Fri, 29 Jun 2018 10:52:52 -0400 Subject: KVM: x86/xen: register vcpu info The vcpu info supersedes the per vcpu area of the shared info page and the guest vcpus will use this instead. Signed-off-by: Joao Martins Signed-off-by: Ankur Arora Signed-off-by: David Woodhouse --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e2b0cbde1908..2db0657b3337 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1614,10 +1614,13 @@ struct kvm_xen_vcpu_attr { __u16 type; __u16 pad[3]; union { + __u64 gpa; __u64 pad[8]; } u; }; +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 + /* Secure Encrypted Virtualization command */ enum sev_cmd_id { /* Guest initialization commands */ -- cgit v1.2.3 From f2340cd9e41dc463cb1189274f3db560c1dfa1f4 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Mon, 23 Jul 2018 11:20:57 -0400 Subject: KVM: x86/xen: register vcpu time info region Allow the Xen emulated guest the ability to register secondary vcpu time information. On Xen guests this is used in order to be mapped to userspace and hence allow vdso gettimeofday to work. Signed-off-by: Joao Martins Signed-off-by: David Woodhouse --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2db0657b3337..0f045ffd9cb6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1620,6 +1620,7 @@ struct kvm_xen_vcpu_attr { }; #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { -- cgit v1.2.3 From 40da8ccd724f7ca2f08550a46268bc3a91cc8869 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 9 Dec 2020 20:08:30 +0000 Subject: KVM: x86/xen: Add event channel interrupt vector upcall It turns out that we can't handle event channels *entirely* in userspace by delivering them as ExtINT, because KVM is a bit picky about when it accepts ExtINT interrupts from a legacy PIC. The in-kernel local APIC has to have LVT0 configured in APIC_MODE_EXTINT and unmasked, which isn't necessarily the case for Xen guests especially on secondary CPUs. To cope with this, add kvm_xen_get_interrupt() which checks the evtchn_pending_upcall field in the Xen vcpu_info, and delivers the Xen upcall vector (configured by KVM_XEN_ATTR_TYPE_UPCALL_VECTOR) if it's set regardless of LAPIC LVT0 configuration. This gives us the minimum support we need for completely userspace-based implementation of event channels. This does mean that vcpu_enter_guest() needs to check for the evtchn_pending_upcall flag being set, because it can't rely on someone having set KVM_REQ_EVENT unless we were to add some way for userspace to do so manually. Signed-off-by: David Woodhouse --- include/uapi/linux/kvm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0f045ffd9cb6..4d4cd001c908 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1596,6 +1596,7 @@ struct kvm_xen_hvm_attr { __u16 pad[3]; union { __u8 long_mode; + __u8 vector; struct { __u64 gfn; } shared_info; @@ -1605,6 +1606,7 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) -- cgit v1.2.3 From 8d4e7e80838f45d3466d36d4fcb890424825faa9 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 4 Dec 2020 01:02:04 +0000 Subject: KVM: x86: declare Xen HVM shared info capability and add test case Instead of adding a plethora of new KVM_CAP_XEN_FOO capabilities, just add bits to the return value of KVM_CAP_XEN_HVM. Signed-off-by: David Woodhouse --- include/uapi/linux/kvm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 4d4cd001c908..63f8f6e95648 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1152,6 +1152,7 @@ struct kvm_x86_mce { #ifdef KVM_CAP_XEN_HVM #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) struct kvm_xen_hvm_config { __u32 flags; @@ -1604,6 +1605,7 @@ struct kvm_xen_hvm_attr { } u; }; +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 @@ -1621,6 +1623,7 @@ struct kvm_xen_vcpu_attr { } u; }; +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 -- cgit v1.2.3 From 49ecc587dca2754571791bebd36e9e36e2a0d973 Mon Sep 17 00:00:00 2001 From: Jonas Bonn Date: Wed, 3 Feb 2021 08:07:59 +0100 Subject: Revert "GTP: add support for flow based tunneling API" This reverts commit 9ab7e76aefc97a9aa664accb59d6e8dc5e52514a. This patch was committed without maintainer approval and despite a number of unaddressed concerns from review. There are several issues that impede the acceptance of this patch and that make a reversion of this particular instance of these changes the best way forward: i) the patch contains several logically separate changes that would be better served as smaller patches (for review purposes) ii) functionality like the handling of end markers has been introduced without further explanation iii) symmetry between the handling of GTPv0 and GTPv1 has been unnecessarily broken iv) the patchset produces 'broken' packets when extension headers are included v) there are no available userspace tools to allow for testing this functionality vi) there is an unaddressed Coverity report against the patch concering memory leakage vii) most importantly, the patch contains a large amount of superfluous churn that impedes other ongoing work with this driver This patch will be reworked into a series that aligns with other ongoing work and facilitates review. Signed-off-by: Jonas Bonn Acked-by: Harald Welte Acked-by: Pravin B Shelar Signed-off-by: Jakub Kicinski --- include/uapi/linux/gtp.h | 12 ------------ include/uapi/linux/if_link.h | 1 - include/uapi/linux/if_tunnel.h | 1 - 3 files changed, 14 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 62aff78b7c56..79f9191bbb24 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -2,8 +2,6 @@ #ifndef _UAPI_LINUX_GTP_H_ #define _UAPI_LINUX_GTP_H_ -#include - #define GTP_GENL_MCGRP_NAME "gtp" enum gtp_genl_cmds { @@ -36,14 +34,4 @@ enum gtp_attrs { }; #define GTPA_MAX (__GTPA_MAX + 1) -enum { - GTP_METADATA_V1 -}; - -struct gtpu_metadata { - __u8 ver; - __u8 flags; - __u8 type; -}; - #endif /* _UAPI_LINUX_GTP_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index eb8018c3a737..91c8dda6d95d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -811,7 +811,6 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, - IFLA_GTP_COLLECT_METADATA, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) diff --git a/include/uapi/linux/if_tunnel.h b/include/uapi/linux/if_tunnel.h index 802da679fab1..7d9105533c7b 100644 --- a/include/uapi/linux/if_tunnel.h +++ b/include/uapi/linux/if_tunnel.h @@ -176,7 +176,6 @@ enum { #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) #define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_ERSPAN_OPT __cpu_to_be16(0x4000) -#define TUNNEL_GTPU_OPT __cpu_to_be16(0x8000) #define TUNNEL_OPTIONS_PRESENT \ (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT | TUNNEL_ERSPAN_OPT) -- cgit v1.2.3 From 36a6c843fd0d8e02506681577e96dabd203dd8e8 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 5 Feb 2021 13:43:21 -0500 Subject: entry: Use different define for selector variable in SUD Michael Kerrisk suggested that, from an API perspective, it is a bad idea to share the PR_SYS_DISPATCH_ defines between the prctl operation and the selector variable. Therefore, define two new constants to be used by SUD's selector variable and update the corresponding documentation and test cases. While this changes the API syscall user dispatch has never been part of a Linux release, it will show up for the first time in 5.11. Suggested-by: Michael Kerrisk (man-pages) Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210205184321.2062251-1-krisman@collabora.com --- include/uapi/linux/prctl.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 90deb41c8a34..667f1aed091c 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -251,5 +251,8 @@ struct prctl_mm_map { #define PR_SET_SYSCALL_USER_DISPATCH 59 # define PR_SYS_DISPATCH_OFF 0 # define PR_SYS_DISPATCH_ON 1 +/* The control values for the user space selector when dispatch is enabled */ +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 #endif /* _LINUX_PRCTL_H */ -- cgit v1.2.3 From cfa55c6d47b1e75ccc4b950616e881f3fd07712e Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Fri, 1 Jan 2021 00:00:01 +0100 Subject: batman-adv: Drop publication years from copyright info The batman-adv source code was using the year of publication (to net-next) as "last" year for the copyright statement. The whole source code mentioned in the MAINTAINERS "BATMAN ADVANCED" section was handled as a single entity regarding the publishing year. This avoided having outdated (in sense of year information - not copyright holder) publishing information inside several files. But since the simple "update copyright year" commit (without other changes) in the file was not well received in the upstream kernel, the option to not have a copyright year (for initial and last publication) in the files are chosen instead. More detailed information about the years can still be retrieved from the SCM system. Signed-off-by: Sven Eckelmann Acked-by: Marek Lindner Signed-off-by: Simon Wunderlich --- include/uapi/linux/batadv_packet.h | 2 +- include/uapi/linux/batman_adv.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 9c8604c5b5f6..ea4692c339ce 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */ -/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index bdb317faa1dc..35dc016c9bb4 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: MIT */ -/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: +/* Copyright (C) B.A.T.M.A.N. contributors: * * Matthias Schiffer */ -- cgit v1.2.3 From e17fe6579de023725ec22a16965e9099e4a05ac9 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 Jan 2021 10:18:16 -0800 Subject: fs-verity: add FS_IOC_READ_VERITY_METADATA ioctl Add an ioctl FS_IOC_READ_VERITY_METADATA which will allow reading verity metadata from a file that has fs-verity enabled, including: - The Merkle tree - The fsverity_descriptor (not including the signature if present) - The built-in signature, if present This ioctl has similar semantics to pread(). It is passed the type of metadata to read (one of the above three), and a buffer, offset, and size. It returns the number of bytes read or an error. Separate patches will add support for each of the above metadata types. This patch just adds the ioctl itself. This ioctl doesn't make any assumption about where the metadata is stored on-disk. It does assume the metadata is in a stable format, but that's basically already the case: - The Merkle tree and fsverity_descriptor are defined by how fs-verity file digests are computed; see the "File digest computation" section of Documentation/filesystems/fsverity.rst. Technically, the way in which the levels of the tree are ordered relative to each other wasn't previously specified, but it's logical to put the root level first. - The built-in signature is the value passed to FS_IOC_ENABLE_VERITY. This ioctl is useful because it allows writing a server program that takes a verity file and serves it to a client program, such that the client can do its own fs-verity compatible verification of the file. This only makes sense if the client doesn't trust the server and if the server needs to provide the storage for the client. More concretely, there is interest in using this ability in Android to export APK files (which are protected by fs-verity) to "protected VMs". This would use Protected KVM (https://lwn.net/Articles/836693), which provides an isolated execution environment without having to trust the traditional "host". A "guest" VM can boot from a signed image and perform specific tasks in a minimum trusted environment using files that have fs-verity enabled on the host, without trusting the host or requiring that the guest has its own trusted storage. Technically, it would be possible to duplicate the metadata and store it in separate files for serving. However, that would be less efficient and would require extra care in userspace to maintain file consistency. In addition to the above, the ability to read the built-in signatures is useful because it allows a system that is using the in-kernel signature verification to migrate to userspace signature verification. Link: https://lore.kernel.org/r/20210115181819.34732-4-ebiggers@kernel.org Reviewed-by: Victor Hsieh Acked-by: Jaegeuk Kim Reviewed-by: Chao Yu Signed-off-by: Eric Biggers --- include/uapi/linux/fsverity.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fsverity.h b/include/uapi/linux/fsverity.h index 33f44156f8ea..e062751294d0 100644 --- a/include/uapi/linux/fsverity.h +++ b/include/uapi/linux/fsverity.h @@ -83,7 +83,17 @@ struct fsverity_formatted_digest { __u8 digest[]; }; +struct fsverity_read_metadata_arg { + __u64 metadata_type; + __u64 offset; + __u64 length; + __u64 buf_ptr; + __u64 __reserved; +}; + #define FS_IOC_ENABLE_VERITY _IOW('f', 133, struct fsverity_enable_arg) #define FS_IOC_MEASURE_VERITY _IOWR('f', 134, struct fsverity_digest) +#define FS_IOC_READ_VERITY_METADATA \ + _IOWR('f', 135, struct fsverity_read_metadata_arg) #endif /* _UAPI_LINUX_FSVERITY_H */ -- cgit v1.2.3 From 622699cfe6ec5578f52727002d5717ff3f092e23 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 Jan 2021 10:18:17 -0800 Subject: fs-verity: support reading Merkle tree with ioctl Add support for FS_VERITY_METADATA_TYPE_MERKLE_TREE to FS_IOC_READ_VERITY_METADATA. This allows a userspace server program to retrieve the Merkle tree of a verity file for serving to a client which implements fs-verity compatible verification. See the patch which introduced FS_IOC_READ_VERITY_METADATA for more details. This has been tested using a new xfstest which calls this ioctl via a new subcommand for the 'fsverity' program from fsverity-utils. Link: https://lore.kernel.org/r/20210115181819.34732-5-ebiggers@kernel.org Reviewed-by: Victor Hsieh Reviewed-by: Jaegeuk Kim Reviewed-by: Chao Yu Signed-off-by: Eric Biggers --- include/uapi/linux/fsverity.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fsverity.h b/include/uapi/linux/fsverity.h index e062751294d0..94003b153cb3 100644 --- a/include/uapi/linux/fsverity.h +++ b/include/uapi/linux/fsverity.h @@ -83,6 +83,8 @@ struct fsverity_formatted_digest { __u8 digest[]; }; +#define FS_VERITY_METADATA_TYPE_MERKLE_TREE 1 + struct fsverity_read_metadata_arg { __u64 metadata_type; __u64 offset; -- cgit v1.2.3 From 947191ac8caba85e25e0e036b0f097fee9e817f3 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 Jan 2021 10:18:18 -0800 Subject: fs-verity: support reading descriptor with ioctl Add support for FS_VERITY_METADATA_TYPE_DESCRIPTOR to FS_IOC_READ_VERITY_METADATA. This allows a userspace server program to retrieve the fs-verity descriptor of a file for serving to a client which implements fs-verity compatible verification. See the patch which introduced FS_IOC_READ_VERITY_METADATA for more details. "fs-verity descriptor" here means only the part that userspace cares about because it is hashed to produce the file digest. It doesn't include the signature which ext4 and f2fs append to the fsverity_descriptor struct when storing it on-disk, since that way of storing the signature is an implementation detail. The next patch adds a separate metadata_type value for retrieving the signature separately. This has been tested using a new xfstest which calls this ioctl via a new subcommand for the 'fsverity' program from fsverity-utils. Link: https://lore.kernel.org/r/20210115181819.34732-6-ebiggers@kernel.org Reviewed-by: Victor Hsieh Reviewed-by: Jaegeuk Kim Reviewed-by: Chao Yu Signed-off-by: Eric Biggers --- include/uapi/linux/fsverity.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fsverity.h b/include/uapi/linux/fsverity.h index 94003b153cb3..41abc283dbcc 100644 --- a/include/uapi/linux/fsverity.h +++ b/include/uapi/linux/fsverity.h @@ -84,6 +84,7 @@ struct fsverity_formatted_digest { }; #define FS_VERITY_METADATA_TYPE_MERKLE_TREE 1 +#define FS_VERITY_METADATA_TYPE_DESCRIPTOR 2 struct fsverity_read_metadata_arg { __u64 metadata_type; -- cgit v1.2.3 From 07c99001312cbf90a357d4877a358f796eede65b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Fri, 15 Jan 2021 10:18:19 -0800 Subject: fs-verity: support reading signature with ioctl Add support for FS_VERITY_METADATA_TYPE_SIGNATURE to FS_IOC_READ_VERITY_METADATA. This allows a userspace server program to retrieve the built-in signature (if present) of a verity file for serving to a client which implements fs-verity compatible verification. See the patch which introduced FS_IOC_READ_VERITY_METADATA for more details. The ability for userspace to read the built-in signatures is also useful because it allows a system that is using the in-kernel signature verification to migrate to userspace signature verification. This has been tested using a new xfstest which calls this ioctl via a new subcommand for the 'fsverity' program from fsverity-utils. Link: https://lore.kernel.org/r/20210115181819.34732-7-ebiggers@kernel.org Reviewed-by: Victor Hsieh Reviewed-by: Jaegeuk Kim Reviewed-by: Chao Yu Signed-off-by: Eric Biggers --- include/uapi/linux/fsverity.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fsverity.h b/include/uapi/linux/fsverity.h index 41abc283dbcc..15384e22e331 100644 --- a/include/uapi/linux/fsverity.h +++ b/include/uapi/linux/fsverity.h @@ -85,6 +85,7 @@ struct fsverity_formatted_digest { #define FS_VERITY_METADATA_TYPE_MERKLE_TREE 1 #define FS_VERITY_METADATA_TYPE_DESCRIPTOR 2 +#define FS_VERITY_METADATA_TYPE_SIGNATURE 3 struct fsverity_read_metadata_arg { __u64 metadata_type; -- cgit v1.2.3 From 49fc251360a10e6bff0d886c9e3c62008a1c4caf Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Sun, 7 Feb 2021 10:22:49 +0200 Subject: rtnetlink: Add RTM_F_OFFLOAD_FAILED flag The flag indicates to user space that route offload failed. Previous patch set added the ability to emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags are changed, but if the offload fails there is no indication to user-space. The flag will be used in subsequent patches by netdevsim and mlxsw to indicate to user space that route offload failed, so that users will have better visibility into the offload process. Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index b841caa4657e..91e4ca064d61 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -319,6 +319,11 @@ enum rt_scope_t { #define RTM_F_FIB_MATCH 0x2000 /* return full fib lookup match */ #define RTM_F_OFFLOAD 0x4000 /* route is offloaded */ #define RTM_F_TRAP 0x8000 /* route is trapping packets */ +#define RTM_F_OFFLOAD_FAILED 0x20000000 /* route offload failed, this value + * is chosen to avoid conflicts with + * other flags defined in + * include/uapi/linux/ipv6_route.h + */ /* Reserved table identifiers */ -- cgit v1.2.3 From d9a47edabc4f948102753fa9d41f2dc1dbeb28be Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Wed, 16 Dec 2020 16:12:19 +0530 Subject: KVM: PPC: Book3S HV: Introduce new capability for 2nd DAWR Introduce KVM_CAP_PPC_DAWR1 which can be used by QEMU to query whether KVM supports 2nd DAWR or not. The capability is by default disabled even when the underlying CPU supports 2nd DAWR. QEMU needs to check and enable it manually to use the feature. Signed-off-by: Ravi Bangoria Signed-off-by: Paul Mackerras --- include/uapi/linux/kvm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 63f8f6e95648..8b281f722e5b 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1077,6 +1077,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_SYS_HYPERV_CPUID 191 #define KVM_CAP_DIRTY_LOG_RING 192 #define KVM_CAP_X86_BUS_LOCK_EXIT 193 +#define KVM_CAP_PPC_DAWR1 194 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 1bcc51ac0731aab1b109b2cd5c3d495f1884e5ca Mon Sep 17 00:00:00 2001 From: wenxu Date: Tue, 9 Feb 2021 14:37:49 +0800 Subject: net/sched: cls_flower: Reject invalid ct_state flags rules Reject the unsupported and invalid ct_state flags of cls flower rules. Fixes: e0ace68af2ac ("net/sched: cls_flower: Add matching on conntrack info") Signed-off-by: wenxu Reviewed-by: Marcelo Ricardo Leitner Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/pkt_cls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index ee95f42fb0ec..88f4bf0047e7 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -591,6 +591,8 @@ enum { TCA_FLOWER_KEY_CT_FLAGS_ESTABLISHED = 1 << 1, /* Part of an existing connection. */ TCA_FLOWER_KEY_CT_FLAGS_RELATED = 1 << 2, /* Related to an established connection. */ TCA_FLOWER_KEY_CT_FLAGS_TRACKED = 1 << 3, /* Conntrack has occurred. */ + + __TCA_FLOWER_KEY_CT_FLAGS_MAX, }; enum { -- cgit v1.2.3 From 9ed9e9ba2337205311398a312796c213737bac35 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 9 Feb 2021 19:36:31 -0800 Subject: bpf: Count the number of times recursion was prevented Add per-program counter for number of times recursion prevention mechanism was triggered and expose it via show_fdinfo and bpf_prog_info. Teach bpftool to print it. Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210033634.62081-7-alexei.starovoitov@gmail.com --- include/uapi/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c001766adcbc..c547ad1ffe43 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4501,6 +4501,7 @@ struct bpf_prog_info { __aligned_u64 prog_tags; __u64 run_time_ns; __u64 run_cnt; + __u64 recursion_misses; } __attribute__((aligned(8))); struct bpf_map_info { -- cgit v1.2.3 From 07881ccbf40cc7893869f3f170301889ddca54ac Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Wed, 10 Feb 2021 12:14:02 +0100 Subject: bpf: Be less specific about socket cookies guarantees Since "92acdc58ab11 bpf, net: Rework cookie generator as per-cpu one" socket cookies are not guaranteed to be non-decreasing. The bpf_get_socket_cookie helper descriptions are currently specifying that cookies are non-decreasing but we don't want users to rely on that. Reported-by: Daniel Borkmann Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: KP Singh Link: https://lore.kernel.org/bpf/20210210111406.785541-1-revest@chromium.org --- include/uapi/linux/bpf.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c547ad1ffe43..dbf10bf08582 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1656,22 +1656,22 @@ union bpf_attr { * networking traffic statistics as it provides a global socket * identifier that can be assumed unique. * Return - * A 8-byte long non-decreasing number on success, or 0 if the - * socket field is missing inside *skb*. + * A 8-byte long unique number on success, or 0 if the socket + * field is missing inside *skb*. * * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) * Description * Equivalent to bpf_get_socket_cookie() helper that accepts * *skb*, but gets socket from **struct bpf_sock_addr** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique number. * * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) * Description * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts * *skb*, but gets socket from **struct bpf_sock_ops** context. * Return - * A 8-byte long non-decreasing number. + * A 8-byte long unique number. * * u32 bpf_get_socket_uid(struct sk_buff *skb) * Return -- cgit v1.2.3 From c5dbb89fc2ac013afe67b9e4fcb3743c02b567cd Mon Sep 17 00:00:00 2001 From: Florent Revest Date: Wed, 10 Feb 2021 12:14:03 +0100 Subject: bpf: Expose bpf_get_socket_cookie to tracing programs This needs a new helper that: - can work in a sleepable context (using sock_gen_cookie) - takes a struct sock pointer and checks that it's not NULL Signed-off-by: Florent Revest Signed-off-by: Alexei Starovoitov Acked-by: KP Singh Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210210111406.785541-2-revest@chromium.org --- include/uapi/linux/bpf.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index dbf10bf08582..07cc2e404291 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1673,6 +1673,14 @@ union bpf_attr { * Return * A 8-byte long unique number. * + * u64 bpf_get_socket_cookie(struct sock *sk) + * Description + * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts + * *sk*, but gets socket from a BTF **struct sock**. This helper + * also works for sleepable programs. + * Return + * A 8-byte long unique number or 0 if *sk* is NULL. + * * u32 bpf_get_socket_uid(struct sk_buff *skb) * Return * The owner UID of the socket associated to *skb*. If the socket -- cgit v1.2.3 From 3c5a2fd042d0bfac71a2dfb99515723d318df47b Mon Sep 17 00:00:00 2001 From: Arjun Roy Date: Thu, 11 Feb 2021 13:21:07 -0800 Subject: tcp: Sanitize CMSG flags and reserved args in tcp_zerocopy_receive. Explicitly define reserved field and require it and any subsequent fields to be zero-valued for now. Additionally, limit the valid CMSG flags that tcp_zerocopy_receive accepts. Fixes: 7eeba1706eba ("tcp: Add receive timestamp support for receive zerocopy.") Signed-off-by: Arjun Roy Signed-off-by: Eric Dumazet Signed-off-by: Soheil Hassas Yeganeh Suggested-by: David Ahern Suggested-by: Leon Romanovsky Suggested-by: Jakub Kicinski Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 42fc5a640df4..8fc09e8638b3 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -357,6 +357,6 @@ struct tcp_zerocopy_receive { __u64 msg_control; /* ancillary data */ __u64 msg_controllen; __u32 msg_flags; - /* __u32 hole; Next we must add >1 u32 otherwise length checks fail. */ + __u32 reserved; /* set to 0 for now */ }; #endif /* _UAPI_LINUX_TCP_H */ -- cgit v1.2.3 From b6db0f899a16a23f5a9ea6c8b0fafc7bbd38e03d Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Thu, 4 Feb 2021 06:46:10 -0800 Subject: cfg80211/mac80211: Support disabling HE mode Allow user to disable HE mode, similar to how VHT and HT can be disabled. Useful for testing. Signed-off-by: Ben Greear Link: https://lore.kernel.org/r/20210204144610.25971-1-greearb@candelatech.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 40832d13c2f1..5188fe581efc 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3045,6 +3045,8 @@ enum nl80211_attrs { NL80211_ATTR_SAR_SPEC, + NL80211_ATTR_DISABLE_HE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 735a48481cca453525d9199772f9c3733a47cff4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 12 Feb 2021 10:50:23 +0100 Subject: nl80211: add documentation for HT/VHT/HE disable attributes These were missed earlier, add the necessary documentation and, while at it, clarify it. Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20210212105023.895c3389f063.I46dea3bfc64385bc6f600c50d294007510994f8f@changeid Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5188fe581efc..ac78da99fccd 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1963,8 +1963,15 @@ enum nl80211_commands { * @NL80211_ATTR_PROBE_RESP: Probe Response template data. Contains the entire * probe-response frame. The DA field in the 802.11 header is zero-ed out, * to be filled by the FW. - * @NL80211_ATTR_DISABLE_HT: Force HT capable interfaces to disable - * this feature. Currently, only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_HT: Force HT capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_VHT: Force VHT capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. + * @NL80211_ATTR_DISABLE_HE: Force HE capable interfaces to disable + * this feature during association. This is a flag attribute. + * Currently only supported in mac80211 drivers. * @NL80211_ATTR_HT_CAPABILITY_MASK: Specify which bits of the * ATTR_HT_CAPABILITY to which attention should be paid. * Currently, only mac80211 NICs support this feature. -- cgit v1.2.3 From e1850ea9bd9eca3656820b4875967d6f9c11c237 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Feb 2021 14:38:19 +0100 Subject: bpf: bpf_fib_lookup return MTU value as output when looked up The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup) can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED. The BPF-prog don't know the MTU value that caused this rejection. If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it need to know this MTU value for the ICMP packet. Patch change lookup and result struct bpf_fib_lookup, to contain this MTU value as output via a union with 'tot_len' as this is the value used for the MTU lookup. V5: - Fixed uninit value spotted by Dan Carpenter. - Name struct output member mtu_result Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/161287789952.790810.13134700381067698781.stgit@firesoul --- include/uapi/linux/bpf.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 07cc2e404291..6b1f6058cccf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2239,6 +2239,9 @@ union bpf_attr { * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the * packet is not forwarded or needs assist from full stack * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) * Description * Add an entry to, or update a sockhash *map* referencing sockets. @@ -4990,9 +4993,13 @@ struct bpf_fib_lookup { __be16 sport; __be16 dport; - /* total length of packet from network header - used for MTU check */ - __u16 tot_len; + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + /* output: MTU value */ + __u16 mtu_result; + }; /* input: L3 device index for lookup * output: device index from FIB lookup */ -- cgit v1.2.3 From 34b2021cc61642d61c3cf943d9e71925b827941b Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 9 Feb 2021 14:38:24 +0100 Subject: bpf: Add BPF-helper for MTU checking This BPF-helper bpf_check_mtu() works for both XDP and TC-BPF programs. The SKB object is complex and the skb->len value (accessible from BPF-prog) also include the length of any extra GRO/GSO segments, but without taking into account that these GRO/GSO segments get added transport (L4) and network (L3) headers before being transmitted. Thus, this BPF-helper is created such that the BPF-programmer don't need to handle these details in the BPF-prog. The API is designed to help the BPF-programmer, that want to do packet context size changes, which involves other helpers. These other helpers usually does a delta size adjustment. This helper also support a delta size (len_diff), which allow BPF-programmer to reuse arguments needed by these other helpers, and perform the MTU check prior to doing any actual size adjustment of the packet context. It is on purpose, that we allow the len adjustment to become a negative result, that will pass the MTU check. This might seem weird, but it's not this helpers responsibility to "catch" wrong len_diff adjustments. Other helpers will take care of these checks, if BPF-programmer chooses to do actual size adjustment. V14: - Improve man-page desc of len_diff. V13: - Enforce flag BPF_MTU_CHK_SEGS cannot use len_diff. V12: - Simplify segment check that calls skb_gso_validate_network_len. - Helpers should return long V9: - Use dev->hard_header_len (instead of ETH_HLEN) - Annotate with unlikely req from Daniel - Fix logic error using skb_gso_validate_network_len from Daniel V6: - Took John's advice and dropped BPF_MTU_CHK_RELAX - Returned MTU is kept at L3-level (like fib_lookup) V4: Lot of changes - ifindex 0 now use current netdev for MTU lookup - rename helper from bpf_mtu_check to bpf_check_mtu - fix bug for GSO pkt length (as skb->len is total len) - remove __bpf_len_adj_positive, simply allow negative len adj Signed-off-by: Jesper Dangaard Brouer Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/161287790461.790810.3429728639563297353.stgit@firesoul --- include/uapi/linux/bpf.h | 75 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6b1f6058cccf..4c24daa43bac 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3847,6 +3847,69 @@ union bpf_attr { * Return * A pointer to a struct socket on success or NULL if the file is * not a socket. + * + * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags) + * Description + + * Check ctx packet size against exceeding MTU of net device (based + * on *ifindex*). This helper will likely be used in combination + * with helpers that adjust/change the packet size. + * + * The argument *len_diff* can be used for querying with a planned + * size change. This allows to check MTU prior to changing packet + * ctx. Providing an *len_diff* adjustment that is larger than the + * actual packet size (resulting in negative packet size) will in + * principle not exceed the MTU, why it is not considered a + * failure. Other BPF-helpers are needed for performing the + * planned size change, why the responsability for catch a negative + * packet size belong in those helpers. + * + * Specifying *ifindex* zero means the MTU check is performed + * against the current net device. This is practical if this isn't + * used prior to redirect. + * + * The Linux kernel route table can configure MTUs on a more + * specific per route level, which is not provided by this helper. + * For route level MTU checks use the **bpf_fib_lookup**\ () + * helper. + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** for tc cls_act programs. + * + * The *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_MTU_CHK_SEGS** + * This flag will only works for *ctx* **struct sk_buff**. + * If packet context contains extra packet segment buffers + * (often knows as GSO skb), then MTU check is harder to + * check at this point, because in transmit path it is + * possible for the skb packet to get re-segmented + * (depending on net device features). This could still be + * a MTU violation, so this flag enables performing MTU + * check against segments, with a different violation + * return code to tell it apart. Check cannot use len_diff. + * + * On return *mtu_len* pointer contains the MTU value of the net + * device. Remember the net device configured MTU is the L3 size, + * which is returned here and XDP and TX length operate at L2. + * Helper take this into account for you, but remember when using + * MTU value in your BPF-code. On input *mtu_len* must be a valid + * pointer and be initialized (to zero), else verifier will reject + * BPF program. + * + * Return + * * 0 on success, and populate MTU value in *mtu_len* pointer. + * + * * < 0 if any input argument is invalid (*mtu_len* not updated) + * + * MTU violations return positive values, but also populate MTU + * value in *mtu_len* pointer, as this can be needed for + * implementing PMTU handing: + * + * * **BPF_MTU_CHK_RET_FRAG_NEEDED** + * * **BPF_MTU_CHK_RET_SEGS_TOOBIG** + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -4012,6 +4075,7 @@ union bpf_attr { FN(ktime_get_coarse_ns), \ FN(ima_inode_hash), \ FN(sock_from_file), \ + FN(check_mtu), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5045,6 +5109,17 @@ struct bpf_redir_neigh { }; }; +/* bpf_check_mtu flags*/ +enum bpf_check_mtu_flags { + BPF_MTU_CHK_SEGS = (1U << 0), +}; + +enum bpf_check_mtu_ret { + BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */ + BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */ +}; + enum bpf_task_fd_type { BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ BPF_FD_TYPE_TRACEPOINT, /* tp name */ -- cgit v1.2.3 From b911c97c7dc771633c68ea9b8f15070f8af3d323 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 12 Feb 2021 16:00:01 -0800 Subject: mptcp: add netlink event support Allow userspace (mptcpd) to subscribe to mptcp genl multicast events. This implementation reuses the same event API as the mptcp kernel fork to ease integration of existing tools, e.g. mptcpd. Supported events include: 1. start and close of an mptcp connection 2. start and close of subflows (joins) 3. announce and withdrawals of addresses 4. subflow priority (backup/non-backup) change. Reviewed-by: Matthieu Baerts Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 74 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 3674a451a18c..c91578aaab32 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -36,6 +36,7 @@ enum { /* netlink interface */ #define MPTCP_PM_NAME "mptcp_pm" #define MPTCP_PM_CMD_GRP_NAME "mptcp_pm_cmds" +#define MPTCP_PM_EV_GRP_NAME "mptcp_pm_events" #define MPTCP_PM_VER 0x1 /* @@ -104,4 +105,77 @@ struct mptcp_info { __u64 mptcpi_rcv_nxt; }; +/* + * MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport + * A new MPTCP connection has been created. It is the good time to allocate + * memory and send ADD_ADDR if needed. Depending on the traffic-patterns + * it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. + * + * MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport + * A MPTCP connection is established (can start new subflows). + * + * MPTCP_EVENT_CLOSED: token + * A MPTCP connection has stopped. + * + * MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] + * A new address has been announced by the peer. + * + * 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] + * 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] + * 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. + */ +enum mptcp_event_type { + MPTCP_EVENT_UNSPEC = 0, + MPTCP_EVENT_CREATED = 1, + MPTCP_EVENT_ESTABLISHED = 2, + MPTCP_EVENT_CLOSED = 3, + + MPTCP_EVENT_ANNOUNCED = 6, + MPTCP_EVENT_REMOVED = 7, + + MPTCP_EVENT_SUB_ESTABLISHED = 10, + MPTCP_EVENT_SUB_CLOSED = 11, + + MPTCP_EVENT_SUB_PRIORITY = 13, +}; + +enum mptcp_event_attr { + MPTCP_ATTR_UNSPEC = 0, + + MPTCP_ATTR_TOKEN, /* u32 */ + MPTCP_ATTR_FAMILY, /* u16 */ + MPTCP_ATTR_LOC_ID, /* u8 */ + MPTCP_ATTR_REM_ID, /* u8 */ + MPTCP_ATTR_SADDR4, /* be32 */ + MPTCP_ATTR_SADDR6, /* struct in6_addr */ + MPTCP_ATTR_DADDR4, /* be32 */ + MPTCP_ATTR_DADDR6, /* struct in6_addr */ + MPTCP_ATTR_SPORT, /* be16 */ + MPTCP_ATTR_DPORT, /* be16 */ + MPTCP_ATTR_BACKUP, /* u8 */ + MPTCP_ATTR_ERROR, /* u8 */ + MPTCP_ATTR_FLAGS, /* u16 */ + MPTCP_ATTR_TIMEOUT, /* u32 */ + MPTCP_ATTR_IF_IDX, /* s32 */ + + __MPTCP_ATTR_AFTER_LAST +}; + +#define MPTCP_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1) + #endif /* _UAPI_MPTCP_H */ -- cgit v1.2.3 From 6001a930ce0378b62210d4f83583fc88a903d89d Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 15 Feb 2021 12:28:07 +0100 Subject: netfilter: nftables: introduce table ownership A userspace daemon like firewalld might need to monitor for netlink updates to detect its ruleset removal by the (global) flush ruleset command to ensure ruleset persistency. This adds extra complexity from userspace and, for some little time, the firewall policy is not in place. This patch adds the NFT_TABLE_F_OWNER flag which allows a userspace program to own the table that creates in exclusivity. Tables that are owned... - can only be updated and removed by the owner, non-owners hit EPERM if they try to update it or remove it. - are destroyed when the owner closes the netlink socket or the process is gone (implicit netlink socket closure). - are skipped by the global flush ruleset command. - are listed in the global ruleset. The userspace process that sets on the NFT_TABLE_F_OWNER flag need to leave open the netlink socket. A new NFTA_TABLE_OWNER netlink attribute specifies the netlink port ID to identify the owner from userspace. This patch also updates error reporting when an unknown table flag is specified to change it from EINVAL to EOPNOTSUPP given that EINVAL is usually reserved to report for malformed netlink messages to userspace. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index b1633e7ba529..79bab7a36b30 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -164,7 +164,10 @@ enum nft_hook_attributes { */ enum nft_table_flags { NFT_TABLE_F_DORMANT = 0x1, + NFT_TABLE_F_OWNER = 0x2, }; +#define NFT_TABLE_F_MASK (NFT_TABLE_F_DORMANT | \ + NFT_TABLE_F_OWNER) /** * enum nft_table_attributes - nf_tables table netlink attributes @@ -173,6 +176,7 @@ enum nft_table_flags { * @NFTA_TABLE_FLAGS: bitmask of enum nft_table_flags (NLA_U32) * @NFTA_TABLE_USE: number of chains in this table (NLA_U32) * @NFTA_TABLE_USERDATA: user data (NLA_BINARY) + * @NFTA_TABLE_OWNER: owner of this table through netlink portID (NLA_U32) */ enum nft_table_attributes { NFTA_TABLE_UNSPEC, @@ -182,6 +186,7 @@ enum nft_table_attributes { NFTA_TABLE_HANDLE, NFTA_TABLE_PAD, NFTA_TABLE_USERDATA, + NFTA_TABLE_OWNER, __NFTA_TABLE_MAX }; #define NFTA_TABLE_MAX (__NFTA_TABLE_MAX - 1) -- cgit v1.2.3 From 2347961b11d4079deace3c81dceed460c08a8fc1 Mon Sep 17 00:00:00 2001 From: Laurent Vivier Date: Tue, 28 Jan 2020 14:25:39 +0100 Subject: binfmt_misc: pass binfmt_misc flags to the interpreter It can be useful to the interpreter to know which flags are in use. For instance, knowing if the preserve-argv[0] is in use would allow to skip the pathname argument. This patch uses an unused auxiliary vector, AT_FLAGS, to add a flag to inform interpreter if the preserve-argv[0] is enabled. Note by Helge Deller: The real-world user of this patch is qemu-user, which needs to know if it has to preserve the argv[0]. See Debian bug #970460. Signed-off-by: Laurent Vivier Reviewed-by: YunQiang Su URL: http://bugs.debian.org/970460 Signed-off-by: Helge Deller --- include/uapi/linux/binfmts.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/binfmts.h b/include/uapi/linux/binfmts.h index 689025d9c185..c6f9450efc12 100644 --- a/include/uapi/linux/binfmts.h +++ b/include/uapi/linux/binfmts.h @@ -18,4 +18,8 @@ struct pt_regs; /* sizeof(linux_binprm->buf) */ #define BINPRM_BUF_SIZE 256 +/* preserve argv0 for the interpreter */ +#define AT_FLAGS_PRESERVE_ARGV0_BIT 0 +#define AT_FLAGS_PRESERVE_ARGV0 (1 << AT_FLAGS_PRESERVE_ARGV0_BIT) + #endif /* _UAPI_LINUX_BINFMTS_H */ -- cgit v1.2.3 From 0caf3ada24e4623d4b2c938a5b6d2d09e4ccee18 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 12 Feb 2021 16:52:02 -0800 Subject: mptcp: add local addr info in mptcp_info Add mptcpi_local_addr_used and mptcpi_local_addr_max in struct mptcp_info. Signed-off-by: Geliang Tang Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index c91578aaab32..e1172c1ffdfd 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -103,6 +103,8 @@ struct mptcp_info { __u64 mptcpi_write_seq; __u64 mptcpi_snd_una; __u64 mptcpi_rcv_nxt; + __u8 mptcpi_local_addr_used; + __u8 mptcpi_local_addr_max; }; /* -- cgit v1.2.3