From a625df3995c31a5d8cf46f2337b207e93bef9bdd Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: tools/include: Sync uapi/linux/kvm.h with the kernel sources And other arch-specific UAPI headers to pick up changes from: 4b23e0c199b2 KVM: Ensure new code that references immediate_exit gets extra scrutiny 85542adb65ec KVM: x86: Add KVM_RUN_X86_GUEST_MODE kvm_run flag 6fef518594bc KVM: x86: Add a capability to configure bus frequency for APIC timer 34ff65901735 x86/sev: Use kernel provided SVSM Calling Areas 5dcc1e76144f Merge tag 'kvm-x86-misc-6.11' of https://github.com/kvm-x86/linux into HEAD 9a0d2f4995dd KVM: PPC: Book3S HV: Add one-reg interface for HASHPKEYR register e9eb790b2557 KVM: PPC: Book3S HV: Add one-reg interface for HASHKEYR register 1a1e6865f516 KVM: PPC: Book3S HV: Add one-reg interface for DEXCR register This should be used to beautify KVM syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h diff -u tools/arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm.h diff -u tools/arch/x86/include/uapi/asm/svm.h arch/x86/include/uapi/asm/svm.h diff -u tools/arch/powerpc/include/uapi/asm/kvm.h arch/powerpc/include/uapi/asm/kvm.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Paolo Bonzini Cc: kvm@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/include/uapi/linux/kvm.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index e5af8c692dc0..637efc055145 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -192,11 +192,24 @@ struct kvm_xen_exit { /* Flags that describe what fields in emulation_failure hold valid data. */ #define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) +/* + * struct kvm_run can be modified by userspace at any time, so KVM must be + * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM() + * renames fields in struct kvm_run from to __unsafe when + * compiled into the kernel, ensuring that any use within KVM is obvious and + * gets extra scrutiny. + */ +#ifdef __KERNEL__ +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe +#else +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol +#endif + /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run { /* in */ __u8 request_interrupt_window; - __u8 immediate_exit; + __u8 HINT_UNSAFE_IN_KVM(immediate_exit); __u8 padding1[6]; /* out */ @@ -918,6 +931,8 @@ struct kvm_enable_cap { #define KVM_CAP_GUEST_MEMFD 234 #define KVM_CAP_VM_TYPES 235 #define KVM_CAP_PRE_FAULT_MEMORY 236 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 +#define KVM_CAP_X86_GUEST_MODE 238 struct kvm_irq_routing_irqchip { __u32 irqchip; -- cgit v1.2.3 From 8ec9497d3ef34fab216e277eca5035811f06b421 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: tools/include: Sync uapi/linux/perf.h with the kernel sources To pick up changes from: 608f6976c309 perf/x86/intel: Support new data source for Lunar Lake This should be used to beautify perf syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/perf_event.h include/uapi/linux/perf_event.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Ian Rogers Cc: Adrian Hunter Cc: "Liang, Kan" Cc: linux-perf-users@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/include/uapi/linux/perf_event.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 3a64499b0f5d..4842c36fdf80 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1349,12 +1349,14 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -/* 5-0x7 available */ +#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */ +/* 0x7 available */ #define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ #define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ +#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */ #define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ #define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ #define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ -- cgit v1.2.3 From ed86525f1f4b738bae75c73e89f25430bd0af1b0 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: tools/include: Sync network socket headers with the kernel sources To pick up changes from: d25a92ccae6b net/smc: Introduce IPPROTO_SMC 060f4ba6e403 io_uring/net: move charging socket out of zc io_uring bb6aaf736680 net: Split a __sys_listen helper for io_uring dc2e77979412 net: Split a __sys_bind helper for io_uring This should be used to beautify socket syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h diff -u tools/perf/trace/beauty/include/linux/socket.h include/linux/socket.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: netdev@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/include/uapi/linux/in.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index e682ab628dfa..d358add1611c 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -81,6 +81,8 @@ enum { #define IPPROTO_ETHERNET IPPROTO_ETHERNET IPPROTO_RAW = 255, /* Raw IP packets */ #define IPPROTO_RAW IPPROTO_RAW + IPPROTO_SMC = 256, /* Shared Memory Communications */ +#define IPPROTO_SMC IPPROTO_SMC IPPROTO_MPTCP = 262, /* Multipath TCP connection */ #define IPPROTO_MPTCP IPPROTO_MPTCP IPPROTO_MAX -- cgit v1.2.3 From 845295f4004c7e1591bab4bad01b51f37d32272f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 6 Aug 2024 12:07:50 -0700 Subject: tools/include: Sync filesystem headers with the kernel sources To pick up changes from: 0f9ca80fa4f9 fs: Add initial atomic write support info to statx f9af549d1fd3 fs: export mount options via statmount() 0a3deb11858a fs: Allow listmount() in foreign mount namespace 09b31295f833 fs: export the mount ns id via statmount d04bccd8c19d listmount: allow listing in reverse order bfc69fd05ef9 fs/procfs: add build ID fetching to PROCMAP_QUERY API ed5d583a88a9 fs/procfs: implement efficient VMA querying API for /proc//maps This should be used to beautify FS syscall arguments and it addresses these tools/perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/linux/stat.h include/uapi/linux/stat.h diff -u tools/perf/trace/beauty/include/uapi/linux/fs.h include/uapi/linux/fs.h diff -u tools/perf/trace/beauty/include/uapi/linux/mount.h include/uapi/linux/mount.h diff -u tools/perf/trace/beauty/include/uapi/linux/stat.h include/uapi/linux/stat.h Please see tools/include/uapi/README for details (it's in the first patch of this series). Cc: Alexander Viro Cc: Christian Brauner Cc: Jan Kara Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Namhyung Kim --- tools/include/uapi/linux/stat.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h index 67626d535316..887a25286441 100644 --- a/tools/include/uapi/linux/stat.h +++ b/tools/include/uapi/linux/stat.h @@ -126,9 +126,15 @@ struct statx { __u64 stx_mnt_id; __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */ - __u64 stx_subvol; /* Subvolume identifier */ /* 0xa0 */ - __u64 __spare3[11]; /* Spare space for future expansion */ + __u64 stx_subvol; /* Subvolume identifier */ + __u32 stx_atomic_write_unit_min; /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; /* Max atomic write unit in bytes */ + /* 0xb0 */ + __u32 stx_atomic_write_segments_max; /* Max atomic write segment count */ + __u32 __spare1[1]; + /* 0xb8 */ + __u64 __spare3[9]; /* Spare space for future expansion */ /* 0x100 */ }; @@ -157,6 +163,7 @@ struct statx { #define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ #define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ #define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ #define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ @@ -192,6 +199,7 @@ struct statx { #define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ #define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ #define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ #endif /* _UAPI_LINUX_STAT_H */ -- cgit v1.2.3 From 3882dccf48f9fbe787b5df3187d708ef348ac860 Mon Sep 17 00:00:00 2001 From: Alan Maguire Date: Thu, 8 Aug 2024 16:05:57 +0100 Subject: bpf/bpf_get,set_sockopt: add option to set TCP-BPF sock ops flags Currently the only opportunity to set sock ops flags dictating which callbacks fire for a socket is from within a TCP-BPF sockops program. This is problematic if the connection is already set up as there is no further chance to specify callbacks for that socket. Add TCP_BPF_SOCK_OPS_CB_FLAGS to bpf_setsockopt() and bpf_getsockopt() to allow users to specify callbacks later, either via an iterator over sockets or via a socket-specific program triggered by a setsockopt() on the socket. Previous discussion on this here [1]. [1] https://lore.kernel.org/bpf/f42f157b-6e52-dd4d-3d97-9b86c84c0b00@oracle.com/ Signed-off-by: Alan Maguire Link: https://lore.kernel.org/r/20240808150558.1035626-2-alan.maguire@oracle.com Signed-off-by: Martin KaFai Lau --- tools/include/uapi/linux/bpf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 35bcf52dbc65..e05b39e39c3f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2851,7 +2851,7 @@ union bpf_attr { * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, - * **TCP_BPF_RTO_MIN**. + * **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports the following *optname*\ s: * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. @@ -7080,6 +7080,7 @@ enum { TCP_BPF_SYN = 1005, /* Copy the TCP header */ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ + TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ }; enum { -- cgit v1.2.3 From 65ab5ac4df012388481d0414fcac1d5ac1721fb3 Mon Sep 17 00:00:00 2001 From: Jordan Rome Date: Fri, 23 Aug 2024 12:51:00 -0700 Subject: bpf: Add bpf_copy_from_user_str kfunc This adds a kfunc wrapper around strncpy_from_user, which can be called from sleepable BPF programs. This matches the non-sleepable 'bpf_probe_read_user_str' helper except it includes an additional 'flags' param, which allows consumers to clear the entire destination buffer on success or failure. Signed-off-by: Jordan Rome Link: https://lore.kernel.org/r/20240823195101.3621028-1-linux@jordanrome.com Signed-off-by: Alexei Starovoitov --- tools/include/uapi/linux/bpf.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 35bcf52dbc65..f329ee44627a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7512,4 +7512,13 @@ struct bpf_iter_num { __u64 __opaque[1]; } __attribute__((aligned(8))); +/* + * Flags to control BPF kfunc behaviour. + * - BPF_F_PAD_ZEROS: Pad destination buffer with zeros. (See the respective + * helper documentation for details.) + */ +enum bpf_kfunc_flags { + BPF_F_PAD_ZEROS = (1ULL << 0), +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From 3efd7ab46d0aebc3e567a9846e79a98dbad3291c Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Tue, 10 Sep 2024 17:14:46 +0000 Subject: net: netdev netlink api to bind dma-buf to a net device API takes the dma-buf fd as input, and binds it to the netdevice. The user can specify the rx queues to bind the dma-buf to. Suggested-by: Stanislav Fomichev Signed-off-by: Mina Almasry Reviewed-by: Donald Hunter Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240910171458.219195-3-almasrymina@google.com Signed-off-by: Jakub Kicinski --- tools/include/uapi/linux/netdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 43742ac5b00d..91bf3ecc5f1d 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -173,6 +173,16 @@ enum { NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) }; +enum { + NETDEV_A_DMABUF_IFINDEX = 1, + NETDEV_A_DMABUF_QUEUES, + NETDEV_A_DMABUF_FD, + NETDEV_A_DMABUF_ID, + + __NETDEV_A_DMABUF_MAX, + NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -186,6 +196,7 @@ enum { NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, NETDEV_CMD_QSTATS_GET, + NETDEV_CMD_BIND_RX, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) -- cgit v1.2.3 From d0caf9876a1c9f844307effb598ad1312d9e0025 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Tue, 10 Sep 2024 17:14:57 +0000 Subject: netdev: add dmabuf introspection Add dmabuf information to page_pool stats: $ ./cli.py --spec ../netlink/specs/netdev.yaml --dump page-pool-get ... {'dmabuf': 10, 'id': 456, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 455, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 454, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 453, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 452, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 451, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 450, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 449, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, And queue stats: $ ./cli.py --spec ../netlink/specs/netdev.yaml --dump queue-get ... {'dmabuf': 10, 'id': 8, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 9, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 10, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 11, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 12, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 13, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 14, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 15, 'ifindex': 3, 'type': 'rx'}, Suggested-by: Jakub Kicinski Signed-off-by: Mina Almasry Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240910171458.219195-14-almasrymina@google.com Signed-off-by: Jakub Kicinski --- tools/include/uapi/linux/netdev.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 91bf3ecc5f1d..7c308f04e7a0 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -93,6 +93,7 @@ enum { NETDEV_A_PAGE_POOL_INFLIGHT, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, NETDEV_A_PAGE_POOL_DETACH_TIME, + NETDEV_A_PAGE_POOL_DMABUF, __NETDEV_A_PAGE_POOL_MAX, NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) @@ -131,6 +132,7 @@ enum { NETDEV_A_QUEUE_IFINDEX, NETDEV_A_QUEUE_TYPE, NETDEV_A_QUEUE_NAPI_ID, + NETDEV_A_QUEUE_DMABUF, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) -- cgit v1.2.3