From f7875966dc0c68cb7c02992ff9ac9e3f88fb5fca Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Sep 2023 10:34:00 -0300 Subject: tools headers UAPI: Sync files changed by new fchmodat2 and map_shadow_stack syscalls with the kernel sources To pick the changes in these csets: c35559f94ebc3e3b ("x86/shstk: Introduce map_shadow_stack syscall") 78252deb023cf087 ("arch: Register fchmodat2, usually as syscall 452") That add support for this new syscall in tools such as 'perf trace'. For instance, this is now possible: # perf trace -v -e fchmodat*,map_shadow_stack --max-events=4 Using CPUID AuthenticAMD-25-21-0 Reusing "openat" BPF sys_enter augmenter for "fchmodat" event qualifier tracepoint filter: (common_pid != 3499340 && common_pid != 11259) && (id == 268 || id == 452 || id == 453) ^C# And it'll work as with other syscalls, for instance openat: # perf trace -e openat* --max-events=4 0.000 ( 0.015 ms): systemd-oomd/1150 openat(dfd: CWD, filename: "/proc/meminfo", flags: RDONLY|CLOEXEC) = 11 0.068 ( 0.019 ms): systemd-oomd/1150 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1001.slice/user@1001.service/memory.pressure", flags: RDONLY|CLOEXEC) = 11 0.119 ( 0.008 ms): systemd-oomd/1150 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1001.slice/user@1001.service/memory.current", flags: RDONLY|CLOEXEC) = 11 0.138 ( 0.006 ms): systemd-oomd/1150 openat(dfd: CWD, filename: "/sys/fs/cgroup/user.slice/user-1001.slice/user@1001.service/memory.min", flags: RDONLY|CLOEXEC) = 11 # That is the filter expression attached to the raw_syscalls:sys_{enter,exit} tracepoints. $ find tools/perf/arch/ -name "syscall*tbl" | xargs grep -E fchmodat\|sys_map_shadow_stack tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl:258 n64 fchmodat sys_fchmodat tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl:452 n64 fchmodat2 sys_fchmodat2 tools/perf/arch/powerpc/entry/syscalls/syscall.tbl:297 common fchmodat sys_fchmodat tools/perf/arch/powerpc/entry/syscalls/syscall.tbl:452 common fchmodat2 sys_fchmodat2 tools/perf/arch/s390/entry/syscalls/syscall.tbl:299 common fchmodat sys_fchmodat sys_fchmodat tools/perf/arch/s390/entry/syscalls/syscall.tbl:452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl:268 common fchmodat sys_fchmodat tools/perf/arch/x86/entry/syscalls/syscall_64.tbl:452 common fchmodat2 sys_fchmodat2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl:453 64 map_shadow_stack sys_map_shadow_stack $ $ grep -Ew map_shadow_stack\|fchmodat2 /tmp/build/perf-tools/arch/x86/include/generated/asm/syscalls_64.c [452] = "fchmodat2", [453] = "map_shadow_stack", $ This addresses these perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl diff -u tools/perf/arch/powerpc/entry/syscalls/syscall.tbl arch/powerpc/kernel/syscalls/syscall.tbl diff -u tools/perf/arch/s390/entry/syscalls/syscall.tbl arch/s390/kernel/syscalls/syscall.tbl diff -u tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl arch/mips/kernel/syscalls/syscall_n64.tbl Cc: Adrian Hunter Cc: Christian Brauner Cc: Dave Hansen Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Palmer Dabbelt Cc: Rick Edgecombe Link: https://lore.kernel.org/lkml/ZP8bE7aXDBu%2Fdrak@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/asm-generic/unistd.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'tools/include') diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index fd6c1cb585db..abe087c53b4b 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -820,8 +820,11 @@ __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) #define __NR_cachestat 451 __SYSCALL(__NR_cachestat, sys_cachestat) +#define __NR_fchmodat2 452 +__SYSCALL(__NR_fchmodat2, sys_fchmodat2) + #undef __NR_syscalls -#define __NR_syscalls 452 +#define __NR_syscalls 453 /* * 32 bit systems traditionally used different -- cgit From 417ecb614fd870a9c898f5ce6fd3d338606aaf5d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 13 Sep 2023 08:35:09 -0300 Subject: tools headers UAPI: Copy seccomp.h to be able to build 'perf bench' in older systems The new 'perf bench' for sched-seccomp-notify uses defines and types not available in older systems where we want to have perf available, so grab a copy of this UAPI from the kernel sources to allow that. This will be checked in the future for drift from the original when we build the perf tool, that will warn when that happens like: make: Entering directory '/var/home/acme/git/perf-tools/tools/perf' BUILD: Doing 'make -j32' parallel build Warning: Kernel ABI header differences: Cc: Adrian Hunter Cc: Andrei Vagin Cc: Ian Rogers Cc: Jiri Olsa Cc: Kees Kook Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/lkml/ZQGhMXtwX7RvV3ya@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/seccomp.h | 157 +++++++++++++++++++++++++++++++++++++ 1 file changed, 157 insertions(+) create mode 100644 tools/include/uapi/linux/seccomp.h (limited to 'tools/include') diff --git a/tools/include/uapi/linux/seccomp.h b/tools/include/uapi/linux/seccomp.h new file mode 100644 index 000000000000..dbfc9b37fcae --- /dev/null +++ b/tools/include/uapi/linux/seccomp.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_SECCOMP_H +#define _UAPI_LINUX_SECCOMP_H + +#include +#include + + +/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, ) */ +#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */ +#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */ +#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */ + +/* Valid operations for seccomp syscall. */ +#define SECCOMP_SET_MODE_STRICT 0 +#define SECCOMP_SET_MODE_FILTER 1 +#define SECCOMP_GET_ACTION_AVAIL 2 +#define SECCOMP_GET_NOTIF_SIZES 3 + +/* Valid flags for SECCOMP_SET_MODE_FILTER */ +#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) +#define SECCOMP_FILTER_FLAG_LOG (1UL << 1) +#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) +#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) +#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4) +/* Received notifications wait in killable state (only respond to fatal signals) */ +#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5) + +/* + * All BPF programs must return a 32-bit value. + * The bottom 16-bits are for optional return data. + * The upper 16-bits are ordered from least permissive values to most, + * as a signed value (so 0x8000000 is negative). + * + * The ordering ensures that a min_t() over composed return values always + * selects the least permissive choice. + */ +#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */ +#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */ +#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD +#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ +#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ +#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */ +#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ +#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ + +/* Masks for the return value sections. */ +#define SECCOMP_RET_ACTION_FULL 0xffff0000U +#define SECCOMP_RET_ACTION 0x7fff0000U +#define SECCOMP_RET_DATA 0x0000ffffU + +/** + * struct seccomp_data - the format the BPF program executes over. + * @nr: the system call number + * @arch: indicates system call convention as an AUDIT_ARCH_* value + * as defined in . + * @instruction_pointer: at the time of the system call. + * @args: up to 6 system call arguments always stored as 64-bit values + * regardless of the architecture. + */ +struct seccomp_data { + int nr; + __u32 arch; + __u64 instruction_pointer; + __u64 args[6]; +}; + +struct seccomp_notif_sizes { + __u16 seccomp_notif; + __u16 seccomp_notif_resp; + __u16 seccomp_data; +}; + +struct seccomp_notif { + __u64 id; + __u32 pid; + __u32 flags; + struct seccomp_data data; +}; + +/* + * Valid flags for struct seccomp_notif_resp + * + * Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution! + * If set by the process supervising the syscalls of another process the + * syscall will continue. This is problematic because of an inherent TOCTOU. + * An attacker can exploit the time while the supervised process is waiting on + * a response from the supervising process to rewrite syscall arguments which + * are passed as pointers of the intercepted syscall. + * It should be absolutely clear that this means that the seccomp notifier + * _cannot_ be used to implement a security policy! It should only ever be used + * in scenarios where a more privileged process supervises the syscalls of a + * lesser privileged process to get around kernel-enforced security + * restrictions when the privileged process deems this safe. In other words, + * in order to continue a syscall the supervising process should be sure that + * another security mechanism or the kernel itself will sufficiently block + * syscalls if arguments are rewritten to something unsafe. + * + * Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF + * or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the + * same syscall, the most recently added filter takes precedence. This means + * that the new SECCOMP_RET_USER_NOTIF filter can override any + * SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all + * such filtered syscalls to be executed by sending the response + * SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally + * be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE. + */ +#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0) + +struct seccomp_notif_resp { + __u64 id; + __s64 val; + __s32 error; + __u32 flags; +}; + +#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0) + +/* valid flags for seccomp_notif_addfd */ +#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ +#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */ + +/** + * struct seccomp_notif_addfd + * @id: The ID of the seccomp notification + * @flags: SECCOMP_ADDFD_FLAG_* + * @srcfd: The local fd number + * @newfd: Optional remote FD number if SETFD option is set, otherwise 0. + * @newfd_flags: The O_* flags the remote FD should have applied + */ +struct seccomp_notif_addfd { + __u64 id; + __u32 flags; + __u32 srcfd; + __u32 newfd; + __u32 newfd_flags; +}; + +#define SECCOMP_IOC_MAGIC '!' +#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr) +#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type) + +/* Flags for seccomp notification fd ioctl. */ +#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) +#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ + struct seccomp_notif_resp) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) +/* On success, the return value is the remote process's added fd number */ +#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \ + struct seccomp_notif_addfd) + +#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64) + +#endif /* _UAPI_LINUX_SECCOMP_H */ -- cgit From c2122b687c212a28d237fb672cc979247bd94449 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 13 Sep 2023 08:55:20 -0300 Subject: tools headers UAPI: Update tools's copy of drm.h headers Picking the changes from: ad9ee11fdf113f96 ("drm/doc: document that PRIME import/export is always supported") 2ff4f6d410afa762 ("drm/doc: document drm_event and its types") 9a2eabf48ade4fba ("drm/doc: use proper cross-references for sections") c7a4722971691562 ("drm/syncobj: add IOCTL to register an eventfd") Addressing these perf build warnings: Warning: Kernel ABI header differences: diff -u tools/include/uapi/drm/drm.h include/uapi/drm/drm.h Now 'perf trace' and other code that might use the tools/perf/trace/beauty autogenerated tables will be able to translate this new ioctl code into a string: $ tools/perf/trace/beauty/drm_ioctl.sh > before $ cp include/uapi/drm/drm.h tools/include/uapi/drm/drm.h $ tools/perf/trace/beauty/drm_ioctl.sh > after $ diff -u before after --- before 2023-09-13 08:54:45.170134002 -0300 +++ after 2023-09-13 08:55:06.612712776 -0300 @@ -108,6 +108,7 @@ [0xCC] = "SYNCOBJ_TRANSFER", [0xCD] = "SYNCOBJ_TIMELINE_SIGNAL", [0xCE] = "MODE_GETFB2", + [0xCF] = "SYNCOBJ_EVENTFD", [DRM_COMMAND_BASE + 0x00] = "I915_INIT", [DRM_COMMAND_BASE + 0x01] = "I915_FLUSH", [DRM_COMMAND_BASE + 0x02] = "I915_FLIP", $ Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Simon Ser Link: https://lore.kernel.org/lkml/ZQGkh9qlhpKA%2FSMY@kernel.org/ Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/drm/drm.h | 84 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 69 insertions(+), 15 deletions(-) (limited to 'tools/include') diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index a87bbbbca2d4..794c1d857677 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -673,8 +673,11 @@ struct drm_gem_open { * Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT * and &DRM_PRIME_CAP_EXPORT. * - * PRIME buffers are exposed as dma-buf file descriptors. See - * Documentation/gpu/drm-mm.rst, section "PRIME Buffer Sharing". + * Starting from kernel version 6.6, both &DRM_PRIME_CAP_IMPORT and + * &DRM_PRIME_CAP_EXPORT are always advertised. + * + * PRIME buffers are exposed as dma-buf file descriptors. + * See :ref:`prime_buffer_sharing`. */ #define DRM_CAP_PRIME 0x5 /** @@ -682,6 +685,8 @@ struct drm_gem_open { * * If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME * buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl. + * + * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME. */ #define DRM_PRIME_CAP_IMPORT 0x1 /** @@ -689,6 +694,8 @@ struct drm_gem_open { * * If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME * buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl. + * + * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME. */ #define DRM_PRIME_CAP_EXPORT 0x2 /** @@ -756,15 +763,14 @@ struct drm_gem_open { /** * DRM_CAP_SYNCOBJ * - * If set to 1, the driver supports sync objects. See - * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + * If set to 1, the driver supports sync objects. See :ref:`drm_sync_objects`. */ #define DRM_CAP_SYNCOBJ 0x13 /** * DRM_CAP_SYNCOBJ_TIMELINE * * If set to 1, the driver supports timeline operations on sync objects. See - * Documentation/gpu/drm-mm.rst, section "DRM Sync Objects". + * :ref:`drm_sync_objects`. */ #define DRM_CAP_SYNCOBJ_TIMELINE 0x14 @@ -909,6 +915,27 @@ struct drm_syncobj_timeline_wait { __u32 pad; }; +/** + * struct drm_syncobj_eventfd + * @handle: syncobj handle. + * @flags: Zero to wait for the point to be signalled, or + * &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE to wait for a fence to be + * available for the point. + * @point: syncobj timeline point (set to zero for binary syncobjs). + * @fd: Existing eventfd to sent events to. + * @pad: Must be zero. + * + * Register an eventfd to be signalled by a syncobj. The eventfd counter will + * be incremented by one. + */ +struct drm_syncobj_eventfd { + __u32 handle; + __u32 flags; + __u64 point; + __s32 fd; + __u32 pad; +}; + struct drm_syncobj_array { __u64 handles; @@ -1169,6 +1196,8 @@ extern "C" { */ #define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2) +#define DRM_IOCTL_SYNCOBJ_EVENTFD DRM_IOWR(0xCF, struct drm_syncobj_eventfd) + /* * Device specific ioctls should only be in their respective headers * The device specific ioctl range is from 0x40 to 0x9f. @@ -1180,25 +1209,50 @@ extern "C" { #define DRM_COMMAND_BASE 0x40 #define DRM_COMMAND_END 0xA0 -/* - * Header for events written back to userspace on the drm fd. The - * type defines the type of event, the length specifies the total - * length of the event (including the header), and user_data is - * typically a 64 bit value passed with the ioctl that triggered the - * event. A read on the drm fd will always only return complete - * events, that is, if for example the read buffer is 100 bytes, and - * there are two 64 byte events pending, only one will be returned. +/** + * struct drm_event - Header for DRM events + * @type: event type. + * @length: total number of payload bytes (including header). * - * Event types 0 - 0x7fffffff are generic drm events, 0x80000000 and - * up are chipset specific. + * This struct is a header for events written back to user-space on the DRM FD. + * A read on the DRM FD will always only return complete events: e.g. if the + * read buffer is 100 bytes large and there are two 64 byte events pending, + * only one will be returned. + * + * Event types 0 - 0x7fffffff are generic DRM events, 0x80000000 and + * up are chipset specific. Generic DRM events include &DRM_EVENT_VBLANK, + * &DRM_EVENT_FLIP_COMPLETE and &DRM_EVENT_CRTC_SEQUENCE. */ struct drm_event { __u32 type; __u32 length; }; +/** + * DRM_EVENT_VBLANK - vertical blanking event + * + * This event is sent in response to &DRM_IOCTL_WAIT_VBLANK with the + * &_DRM_VBLANK_EVENT flag set. + * + * The event payload is a struct drm_event_vblank. + */ #define DRM_EVENT_VBLANK 0x01 +/** + * DRM_EVENT_FLIP_COMPLETE - page-flip completion event + * + * This event is sent in response to an atomic commit or legacy page-flip with + * the &DRM_MODE_PAGE_FLIP_EVENT flag set. + * + * The event payload is a struct drm_event_vblank. + */ #define DRM_EVENT_FLIP_COMPLETE 0x02 +/** + * DRM_EVENT_CRTC_SEQUENCE - CRTC sequence event + * + * This event is sent in response to &DRM_IOCTL_CRTC_QUEUE_SEQUENCE. + * + * The event payload is a struct drm_event_crtc_sequence. + */ #define DRM_EVENT_CRTC_SEQUENCE 0x03 struct drm_event_vblank { -- cgit