From a6e414a4cb5ab320747b913b0897d1159fa978eb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Sep 2023 10:28:50 -0300 Subject: perf tools: Update copy of libbpf's hashmap.c To pick the changes in: a3e7e6b17946f48b ("libbpf: Remove HASHMAP_INIT static initialization helper") That don't entail any changes in tools/perf. This addresses this perf build warning: Warning: Kernel ABI header differences: diff -u tools/perf/util/hashmap.h tools/lib/bpf/hashmap.h Not a kernel ABI, its just that this uses the mechanism in place for checking kernel ABI files drift. Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hashmap.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'tools') diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h index 0a5bf1937a7c..c12f8320e668 100644 --- a/tools/perf/util/hashmap.h +++ b/tools/perf/util/hashmap.h @@ -80,16 +80,6 @@ struct hashmap { size_t sz; }; -#define HASHMAP_INIT(hash_fn, equal_fn, ctx) { \ - .hash_fn = (hash_fn), \ - .equal_fn = (equal_fn), \ - .ctx = (ctx), \ - .buckets = NULL, \ - .cap = 0, \ - .cap_bits = 0, \ - .sz = 0, \ -} - void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn, hashmap_equal_fn equal_fn, void *ctx); struct hashmap *hashmap__new(hashmap_hash_fn hash_fn, -- cgit v1.2.3 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 ++++- tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl | 1 + tools/perf/arch/powerpc/entry/syscalls/syscall.tbl | 1 + tools/perf/arch/s390/entry/syscalls/syscall.tbl | 1 + tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 2 ++ 5 files changed, 9 insertions(+), 1 deletion(-) (limited to 'tools') 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 diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index cfda2511badf..cb5e757f6621 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -366,3 +366,4 @@ 449 n64 futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 n64 cachestat sys_cachestat +452 n64 fchmodat2 sys_fchmodat2 diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index 8c0b08b7a80e..20e50586e8a2 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -538,3 +538,4 @@ 449 common futex_waitv sys_futex_waitv 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index a6935af2235c..0122cc156952 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -454,3 +454,4 @@ 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 sys_fchmodat2 diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index 227538b0ce80..1d6eee30eceb 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -373,6 +373,8 @@ 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node 451 common cachestat sys_cachestat +452 common fchmodat2 sys_fchmodat2 +453 64 map_shadow_stack sys_map_shadow_stack # # Due to a historical design error, certain syscalls are numbered differently -- cgit v1.2.3 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 +++++++++++++++++++++++++++++++++++++ tools/perf/check-headers.sh | 1 + 2 files changed, 158 insertions(+) create mode 100644 tools/include/uapi/linux/seccomp.h (limited to 'tools') 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 */ diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 4314c9197850..e21caadda7c1 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -21,6 +21,7 @@ FILES=( "include/uapi/linux/perf_event.h" "include/uapi/linux/prctl.h" "include/uapi/linux/sched.h" + "include/uapi/linux/seccomp.h" "include/uapi/linux/stat.h" "include/uapi/linux/usbdevice_fs.h" "include/uapi/linux/vhost.h" -- cgit v1.2.3 From 678ddf730a1b0b347ad6e5deb7fdea52654e5bdf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 13 Sep 2023 08:38:56 -0300 Subject: perf bench sched-seccomp-notify: Use the tools copy of seccomp.h UAPI To keep perf building in systems where types and defines used in this new benchmark are not available, such as: 12 13.46 centos:stream : FAIL gcc version 8.5.0 20210514 (Red Hat 8.5.0-20) (GCC) bench/sched-seccomp-notify.c: In function 'user_notif_syscall': bench/sched-seccomp-notify.c:55:27: error: 'SECCOMP_RET_USER_NOTIF' undeclared (first use in this function); did you mean 'SECCOMP_RET_ERRNO'? BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_USER_NOTIF), ^~~~~~~~~~~~~~~~~~~~~~ /git/perf-6.6.0-rc1/tools/include/uapi/linux/filter.h:49:59: note: in definition of macro 'BPF_STMT' #define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k } ^ bench/sched-seccomp-notify.c:55:27: note: each undeclared identifier is reported only once for each function it appears in BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_USER_NOTIF), ^~~~~~~~~~~~~~~~~~~~~~ /git/perf-6.6.0-rc1/tools/include/uapi/linux/filter.h:49:59: note: in definition of macro 'BPF_STMT' #define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k } ^ bench/sched-seccomp-notify.c:55:3: error: missing initializer for field 'k' of 'struct sock_filter' [-Werror=missing-field-initializers] BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_USER_NOTIF), ^~~~~~~~ In file included from bench/sched-seccomp-notify.c:5: /git/perf-6.6.0-rc1/tools/include/uapi/linux/filter.h:28:8: note: 'k' declared here __u32 k; /* Generic multiuse field */ ^ bench/sched-seccomp-notify.c: In function 'user_notification_sync_loop': bench/sched-seccomp-notify.c:70:28: error: storage size of 'resp' isn't known struct seccomp_notif_resp resp; ^~~~ bench/sched-seccomp-notify.c:71:23: error: storage size of 'req' isn't known struct seccomp_notif req; ^~~ bench/sched-seccomp-notify.c:76:23: error: 'SECCOMP_IOCTL_NOTIF_RECV' undeclared (first use in this function); did you mean 'SECCOMP_MODE_STRICT'? if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req)) ^~~~~~~~~~~~~~~~~~~~~~~~ SECCOMP_MODE_STRICT bench/sched-seccomp-notify.c:86:23: error: 'SECCOMP_IOCTL_NOTIF_SEND' undeclared (first use in this function); did you mean 'SECCOMP_RET_ACTION'? if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp)) ^~~~~~~~~~~~~~~~~~~~~~~~ SECCOMP_RET_ACTION bench/sched-seccomp-notify.c:71:23: error: unused variable 'req' [-Werror=unused-variable] struct seccomp_notif req; ^~~ bench/sched-seccomp-notify.c:70:28: error: unused variable 'resp' [-Werror=unused-variable] struct seccomp_notif_resp resp; ^~~~ 14 11.31 debian:10 : FAIL gcc version 8.3.0 (Debian 8.3.0-6) 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/ZQGhjaojgOGtSNk6@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/bench/sched-seccomp-notify.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/bench/sched-seccomp-notify.c b/tools/perf/bench/sched-seccomp-notify.c index b04ebcde4036..a01c40131493 100644 --- a/tools/perf/bench/sched-seccomp-notify.c +++ b/tools/perf/bench/sched-seccomp-notify.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include -- cgit v1.2.3 From 15ca35494ec58f50aa58f51437a22573431e8448 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 13 Sep 2023 08:50:10 -0300 Subject: tools arch x86: Sync the msr-index.h copy with the kernel sources To pick up the changes from these csets: 1b5277c0ea0b2473 ("x86/srso: Add SRSO_NO support") 8974eb588283b7d4 ("x86/speculation: Add Gather Data Sampling mitigation") That cause no changes to tooling: $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > before $ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h $ tools/perf/trace/beauty/tracepoints/x86_msr.sh > after $ diff -u before after $ Just silences this perf build warning: Warning: Kernel ABI header differences: diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Cc: Adrian Hunter Cc: Borislav Petkov (AMD) Cc: Daniel Sneddon Cc: Dave Hansen Cc: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Link: https://lore.kernel.org/lkml/ZQGismCqcDddjEIQ@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/msr-index.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'tools') diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index a00a53e15ab7..1d111350197f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -57,6 +57,7 @@ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */ #define MSR_PPIN_CTL 0x0000004e #define MSR_PPIN 0x0000004f @@ -155,6 +156,15 @@ * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. */ +#define ARCH_CAP_GDS_CTRL BIT(25) /* + * CPU is vulnerable to Gather + * Data Sampling (GDS) and + * has controls for mitigation. + */ +#define ARCH_CAP_GDS_NO BIT(26) /* + * CPU is not vulnerable to Gather + * Data Sampling (GDS). + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -178,6 +188,8 @@ #define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ #define RTM_ALLOW BIT(1) /* TSX development mode */ #define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ +#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */ +#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */ #define MSR_IA32_SYSENTER_CS 0x00000174 #define MSR_IA32_SYSENTER_ESP 0x00000175 -- cgit v1.2.3 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') 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 v1.2.3 From 4a73fca226925d5cae8ee032d37e9de637b25ed6 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 13 Sep 2023 11:45:34 -0700 Subject: perf bpf-prologue: Remove unused file Commit 3d6dfae88917 ("perf parse-events: Remove BPF event support") removed building bpf-prologue.c but failed to remove the actual file. Fixes: 3d6dfae88917 ("perf parse-events: Remove BPF event support") Signed-off-by: Ian Rogers Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230913184534.227961-1-irogers@google.com Signed-off-by: Namhyung Kim --- tools/perf/util/bpf-prologue.c | 508 ----------------------------------------- 1 file changed, 508 deletions(-) delete mode 100644 tools/perf/util/bpf-prologue.c (limited to 'tools') diff --git a/tools/perf/util/bpf-prologue.c b/tools/perf/util/bpf-prologue.c deleted file mode 100644 index 9887ae09242d..000000000000 --- a/tools/perf/util/bpf-prologue.c +++ /dev/null @@ -1,508 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bpf-prologue.c - * - * Copyright (C) 2015 He Kuang - * Copyright (C) 2015 Wang Nan - * Copyright (C) 2015 Huawei Inc. - */ - -#include -#include "debug.h" -#include "bpf-loader.h" -#include "bpf-prologue.h" -#include "probe-finder.h" -#include -#include -#include -#include - -#define BPF_REG_SIZE 8 - -#define JMP_TO_ERROR_CODE -1 -#define JMP_TO_SUCCESS_CODE -2 -#define JMP_TO_USER_CODE -3 - -struct bpf_insn_pos { - struct bpf_insn *begin; - struct bpf_insn *end; - struct bpf_insn *pos; -}; - -static inline int -pos_get_cnt(struct bpf_insn_pos *pos) -{ - return pos->pos - pos->begin; -} - -static int -append_insn(struct bpf_insn new_insn, struct bpf_insn_pos *pos) -{ - if (!pos->pos) - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - - if (pos->pos + 1 >= pos->end) { - pr_err("bpf prologue: prologue too long\n"); - pos->pos = NULL; - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - } - - *(pos->pos)++ = new_insn; - return 0; -} - -static int -check_pos(struct bpf_insn_pos *pos) -{ - if (!pos->pos || pos->pos >= pos->end) - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - return 0; -} - -/* - * Convert type string (u8/u16/u32/u64/s8/s16/s32/s64 ..., see - * Documentation/trace/kprobetrace.rst) to size field of BPF_LDX_MEM - * instruction (BPF_{B,H,W,DW}). - */ -static int -argtype_to_ldx_size(const char *type) -{ - int arg_size = type ? atoi(&type[1]) : 64; - - switch (arg_size) { - case 8: - return BPF_B; - case 16: - return BPF_H; - case 32: - return BPF_W; - case 64: - default: - return BPF_DW; - } -} - -static const char * -insn_sz_to_str(int insn_sz) -{ - switch (insn_sz) { - case BPF_B: - return "BPF_B"; - case BPF_H: - return "BPF_H"; - case BPF_W: - return "BPF_W"; - case BPF_DW: - return "BPF_DW"; - default: - return "UNKNOWN"; - } -} - -/* Give it a shorter name */ -#define ins(i, p) append_insn((i), (p)) - -/* - * Give a register name (in 'reg'), generate instruction to - * load register into an eBPF register rd: - * 'ldd target_reg, offset(ctx_reg)', where: - * ctx_reg is pre initialized to pointer of 'struct pt_regs'. - */ -static int -gen_ldx_reg_from_ctx(struct bpf_insn_pos *pos, int ctx_reg, - const char *reg, int target_reg) -{ - int offset = regs_query_register_offset(reg); - - if (offset < 0) { - pr_err("bpf: prologue: failed to get register %s\n", - reg); - return offset; - } - ins(BPF_LDX_MEM(BPF_DW, target_reg, ctx_reg, offset), pos); - - return check_pos(pos); -} - -/* - * Generate a BPF_FUNC_probe_read function call. - * - * src_base_addr_reg is a register holding base address, - * dst_addr_reg is a register holding dest address (on stack), - * result is: - * - * *[dst_addr_reg] = *([src_base_addr_reg] + offset) - * - * Arguments of BPF_FUNC_probe_read: - * ARG1: ptr to stack (dest) - * ARG2: size (8) - * ARG3: unsafe ptr (src) - */ -static int -gen_read_mem(struct bpf_insn_pos *pos, - int src_base_addr_reg, - int dst_addr_reg, - long offset, - int probeid) -{ - /* mov arg3, src_base_addr_reg */ - if (src_base_addr_reg != BPF_REG_ARG3) - ins(BPF_MOV64_REG(BPF_REG_ARG3, src_base_addr_reg), pos); - /* add arg3, #offset */ - if (offset) - ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG3, offset), pos); - - /* mov arg2, #reg_size */ - ins(BPF_ALU64_IMM(BPF_MOV, BPF_REG_ARG2, BPF_REG_SIZE), pos); - - /* mov arg1, dst_addr_reg */ - if (dst_addr_reg != BPF_REG_ARG1) - ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos); - - /* Call probe_read */ - ins(BPF_EMIT_CALL(probeid), pos); - /* - * Error processing: if read fail, goto error code, - * will be relocated. Target should be the start of - * error processing code. - */ - ins(BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, JMP_TO_ERROR_CODE), - pos); - - return check_pos(pos); -} - -/* - * Each arg should be bare register. Fetch and save them into argument - * registers (r3 - r5). - * - * BPF_REG_1 should have been initialized with pointer to - * 'struct pt_regs'. - */ -static int -gen_prologue_fastpath(struct bpf_insn_pos *pos, - struct probe_trace_arg *args, int nargs) -{ - int i, err = 0; - - for (i = 0; i < nargs; i++) { - err = gen_ldx_reg_from_ctx(pos, BPF_REG_1, args[i].value, - BPF_PROLOGUE_START_ARG_REG + i); - if (err) - goto errout; - } - - return check_pos(pos); -errout: - return err; -} - -/* - * Slow path: - * At least one argument has the form of 'offset($rx)'. - * - * Following code first stores them into stack, then loads all of then - * to r2 - r5. - * Before final loading, the final result should be: - * - * low address - * BPF_REG_FP - 24 ARG3 - * BPF_REG_FP - 16 ARG2 - * BPF_REG_FP - 8 ARG1 - * BPF_REG_FP - * high address - * - * For each argument (described as: offn(...off2(off1(reg)))), - * generates following code: - * - * r7 <- fp - * r7 <- r7 - stack_offset // Ideal code should initialize r7 using - * // fp before generating args. However, - * // eBPF won't regard r7 as stack pointer - * // if it is generated by minus 8 from - * // another stack pointer except fp. - * // This is why we have to set r7 - * // to fp for each variable. - * r3 <- value of 'reg'-> generated using gen_ldx_reg_from_ctx() - * (r7) <- r3 // skip following instructions for bare reg - * r3 <- r3 + off1 . // skip if off1 == 0 - * r2 <- 8 \ - * r1 <- r7 |-> generated by gen_read_mem() - * call probe_read / - * jnei r0, 0, err ./ - * r3 <- (r7) - * r3 <- r3 + off2 . // skip if off2 == 0 - * r2 <- 8 \ // r2 may be broken by probe_read, so set again - * r1 <- r7 |-> generated by gen_read_mem() - * call probe_read / - * jnei r0, 0, err ./ - * ... - */ -static int -gen_prologue_slowpath(struct bpf_insn_pos *pos, - struct probe_trace_arg *args, int nargs) -{ - int err, i, probeid; - - for (i = 0; i < nargs; i++) { - struct probe_trace_arg *arg = &args[i]; - const char *reg = arg->value; - struct probe_trace_arg_ref *ref = NULL; - int stack_offset = (i + 1) * -8; - - pr_debug("prologue: fetch arg %d, base reg is %s\n", - i, reg); - - /* value of base register is stored into ARG3 */ - err = gen_ldx_reg_from_ctx(pos, BPF_REG_CTX, reg, - BPF_REG_ARG3); - if (err) { - pr_err("prologue: failed to get offset of register %s\n", - reg); - goto errout; - } - - /* Make r7 the stack pointer. */ - ins(BPF_MOV64_REG(BPF_REG_7, BPF_REG_FP), pos); - /* r7 += -8 */ - ins(BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, stack_offset), pos); - /* - * Store r3 (base register) onto stack - * Ensure fp[offset] is set. - * fp is the only valid base register when storing - * into stack. We are not allowed to use r7 as base - * register here. - */ - ins(BPF_STX_MEM(BPF_DW, BPF_REG_FP, BPF_REG_ARG3, - stack_offset), pos); - - ref = arg->ref; - probeid = BPF_FUNC_probe_read_kernel; - while (ref) { - pr_debug("prologue: arg %d: offset %ld\n", - i, ref->offset); - - if (ref->user_access) - probeid = BPF_FUNC_probe_read_user; - - err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7, - ref->offset, probeid); - if (err) { - pr_err("prologue: failed to generate probe_read function call\n"); - goto errout; - } - - ref = ref->next; - /* - * Load previous result into ARG3. Use - * BPF_REG_FP instead of r7 because verifier - * allows FP based addressing only. - */ - if (ref) - ins(BPF_LDX_MEM(BPF_DW, BPF_REG_ARG3, - BPF_REG_FP, stack_offset), pos); - } - } - - /* Final pass: read to registers */ - for (i = 0; i < nargs; i++) { - int insn_sz = (args[i].ref) ? argtype_to_ldx_size(args[i].type) : BPF_DW; - - pr_debug("prologue: load arg %d, insn_sz is %s\n", - i, insn_sz_to_str(insn_sz)); - ins(BPF_LDX_MEM(insn_sz, BPF_PROLOGUE_START_ARG_REG + i, - BPF_REG_FP, -BPF_REG_SIZE * (i + 1)), pos); - } - - ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_SUCCESS_CODE), pos); - - return check_pos(pos); -errout: - return err; -} - -static int -prologue_relocate(struct bpf_insn_pos *pos, struct bpf_insn *error_code, - struct bpf_insn *success_code, struct bpf_insn *user_code) -{ - struct bpf_insn *insn; - - if (check_pos(pos)) - return -BPF_LOADER_ERRNO__PROLOGUE2BIG; - - for (insn = pos->begin; insn < pos->pos; insn++) { - struct bpf_insn *target; - u8 class = BPF_CLASS(insn->code); - u8 opcode; - - if (class != BPF_JMP) - continue; - opcode = BPF_OP(insn->code); - if (opcode == BPF_CALL) - continue; - - switch (insn->off) { - case JMP_TO_ERROR_CODE: - target = error_code; - break; - case JMP_TO_SUCCESS_CODE: - target = success_code; - break; - case JMP_TO_USER_CODE: - target = user_code; - break; - default: - pr_err("bpf prologue: internal error: relocation failed\n"); - return -BPF_LOADER_ERRNO__PROLOGUE; - } - - insn->off = target - (insn + 1); - } - return 0; -} - -int bpf__gen_prologue(struct probe_trace_arg *args, int nargs, - struct bpf_insn *new_prog, size_t *new_cnt, - size_t cnt_space) -{ - struct bpf_insn *success_code = NULL; - struct bpf_insn *error_code = NULL; - struct bpf_insn *user_code = NULL; - struct bpf_insn_pos pos; - bool fastpath = true; - int err = 0, i; - - if (!new_prog || !new_cnt) - return -EINVAL; - - if (cnt_space > BPF_MAXINSNS) - cnt_space = BPF_MAXINSNS; - - pos.begin = new_prog; - pos.end = new_prog + cnt_space; - pos.pos = new_prog; - - if (!nargs) { - ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), - &pos); - - if (check_pos(&pos)) - goto errout; - - *new_cnt = pos_get_cnt(&pos); - return 0; - } - - if (nargs > BPF_PROLOGUE_MAX_ARGS) { - pr_warning("bpf: prologue: %d arguments are dropped\n", - nargs - BPF_PROLOGUE_MAX_ARGS); - nargs = BPF_PROLOGUE_MAX_ARGS; - } - - /* First pass: validation */ - for (i = 0; i < nargs; i++) { - struct probe_trace_arg_ref *ref = args[i].ref; - - if (args[i].value[0] == '@') { - /* TODO: fetch global variable */ - pr_err("bpf: prologue: global %s%+ld not support\n", - args[i].value, ref ? ref->offset : 0); - return -ENOTSUP; - } - - while (ref) { - /* fastpath is true if all args has ref == NULL */ - fastpath = false; - - /* - * Instruction encodes immediate value using - * s32, ref->offset is long. On systems which - * can't fill long in s32, refuse to process if - * ref->offset too large (or small). - */ -#ifdef __LP64__ -#define OFFSET_MAX ((1LL << 31) - 1) -#define OFFSET_MIN ((1LL << 31) * -1) - if (ref->offset > OFFSET_MAX || - ref->offset < OFFSET_MIN) { - pr_err("bpf: prologue: offset out of bound: %ld\n", - ref->offset); - return -BPF_LOADER_ERRNO__PROLOGUEOOB; - } -#endif - ref = ref->next; - } - } - pr_debug("prologue: pass validation\n"); - - if (fastpath) { - /* If all variables are registers... */ - pr_debug("prologue: fast path\n"); - err = gen_prologue_fastpath(&pos, args, nargs); - if (err) - goto errout; - } else { - pr_debug("prologue: slow path\n"); - - /* Initialization: move ctx to a callee saved register. */ - ins(BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1), &pos); - - err = gen_prologue_slowpath(&pos, args, nargs); - if (err) - goto errout; - /* - * start of ERROR_CODE (only slow pass needs error code) - * mov r2 <- 1 // r2 is error number - * mov r3 <- 0 // r3, r4... should be touched or - * // verifier would complain - * mov r4 <- 0 - * ... - * goto usercode - */ - error_code = pos.pos; - ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 1), - &pos); - - for (i = 0; i < nargs; i++) - ins(BPF_ALU64_IMM(BPF_MOV, - BPF_PROLOGUE_START_ARG_REG + i, - 0), - &pos); - ins(BPF_JMP_IMM(BPF_JA, BPF_REG_0, 0, JMP_TO_USER_CODE), - &pos); - } - - /* - * start of SUCCESS_CODE: - * mov r2 <- 0 - * goto usercode // skip - */ - success_code = pos.pos; - ins(BPF_ALU64_IMM(BPF_MOV, BPF_PROLOGUE_FETCH_RESULT_REG, 0), &pos); - - /* - * start of USER_CODE: - * Restore ctx to r1 - */ - user_code = pos.pos; - if (!fastpath) { - /* - * Only slow path needs restoring of ctx. In fast path, - * register are loaded directly from r1. - */ - ins(BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX), &pos); - err = prologue_relocate(&pos, error_code, success_code, - user_code); - if (err) - goto errout; - } - - err = check_pos(&pos); - if (err) - goto errout; - - *new_cnt = pos_get_cnt(&pos); - return 0; -errout: - return err; -} -- cgit v1.2.3 From 33b725ce7b9887569749fbbcdafc4ab089a09741 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 13 Sep 2023 11:49:57 -0700 Subject: perf trace: Avoid compile error wrt redefining bool Make part of an existing TODO conditional to avoid the following build error: ``` tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c:26:14: error: cannot combine with previous 'char' declaration specifier 26 | typedef char bool; | ^ include/stdbool.h:20:14: note: expanded from macro 'bool' 20 | #define bool _Bool | ^ tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c:26:1: error: typedef requires a name [-Werror,-Wmissing-declarations] 26 | typedef char bool; | ^~~~~~~~~~~~~~~~~ 2 errors generated. ``` Signed-off-by: Ian Rogers Cc: Leo Yan Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230913184957.230076-1-irogers@google.com Signed-off-by: Namhyung Kim --- tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools') diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 90ce22f9c1a9..939ec769bf4a 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -23,7 +23,9 @@ #define MAX_CPUS 4096 // FIXME: These should come from system headers +#ifndef bool typedef char bool; +#endif typedef int pid_t; typedef long long int __s64; typedef __s64 time64_t; -- cgit v1.2.3 From d1bac78e26e513ce2cf1b47fcc667b33f51c6a36 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 13 Sep 2023 19:22:04 -0700 Subject: perf jevents metric: Fix type of strcmp_cpuid_str The parser wraps all strings as Events, so the input is an Event. Using a string would be bad as functions like Simplify are called on the arguments, which wouldn't be present on a string. Fixes: 9d5da30e4ae9 ("perf jevents: Add a new expression builtin strcmp_cpuid_str()") Signed-off-by: Ian Rogers Cc: James Clark Cc: Kajol Jain Cc: John Garry Link: https://lore.kernel.org/r/20230914022204.1488383-1-irogers@google.com Signed-off-by: Namhyung Kim --- tools/perf/pmu-events/metric.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tools') diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py index 0e9ec65d92ae..3e673f25d5fd 100644 --- a/tools/perf/pmu-events/metric.py +++ b/tools/perf/pmu-events/metric.py @@ -413,10 +413,10 @@ def has_event(event: Event) -> Function: # pylint: disable=invalid-name return Function('has_event', event) -def strcmp_cpuid_str(event: str) -> Function: +def strcmp_cpuid_str(cpuid: Event) -> Function: # pylint: disable=redefined-builtin # pylint: disable=invalid-name - return Function('strcmp_cpuid_str', event) + return Function('strcmp_cpuid_str', cpuid) class Metric: """An individual metric that will specifiable on the perf command line.""" -- cgit v1.2.3 From eaaebb01a7a6d7d422f80e0dacf9a07fb90f22dc Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 13 Sep 2023 19:24:25 -0700 Subject: perf pmu: Ensure all alias variables are initialized Fix an error detected by memory sanitizer: ``` ==4033==WARNING: MemorySanitizer: use-of-uninitialized-value #0 0x55fb0fbedfc7 in read_alias_info tools/perf/util/pmu.c:457:6 #1 0x55fb0fbea339 in check_info_data tools/perf/util/pmu.c:1434:2 #2 0x55fb0fbea339 in perf_pmu__check_alias tools/perf/util/pmu.c:1504:9 #3 0x55fb0fbdca85 in parse_events_add_pmu tools/perf/util/parse-events.c:1429:32 #4 0x55fb0f965230 in parse_events_parse tools/perf/util/parse-events.y:299:6 #5 0x55fb0fbdf6b2 in parse_events__scanner tools/perf/util/parse-events.c:1822:8 #6 0x55fb0fbdf8c1 in __parse_events tools/perf/util/parse-events.c:2094:8 #7 0x55fb0fa8ffa9 in parse_events tools/perf/util/parse-events.h:41:9 #8 0x55fb0fa8ffa9 in test_event tools/perf/tests/parse-events.c:2393:8 #9 0x55fb0fa8f458 in test__pmu_events tools/perf/tests/parse-events.c:2551:15 #10 0x55fb0fa6d93f in run_test tools/perf/tests/builtin-test.c:242:9 #11 0x55fb0fa6d93f in test_and_print tools/perf/tests/builtin-test.c:271:8 #12 0x55fb0fa6d082 in __cmd_test tools/perf/tests/builtin-test.c:442:5 #13 0x55fb0fa6d082 in cmd_test tools/perf/tests/builtin-test.c:564:9 #14 0x55fb0f942720 in run_builtin tools/perf/perf.c:322:11 #15 0x55fb0f942486 in handle_internal_command tools/perf/perf.c:375:8 #16 0x55fb0f941dab in run_argv tools/perf/perf.c:419:2 #17 0x55fb0f941dab in main tools/perf/perf.c:535:3 ``` Fixes: 7b723dbb96e8 ("perf pmu: Be lazy about loading event info files from sysfs") Signed-off-by: Ian Rogers Cc: James Clark Cc: Kan Liang Link: https://lore.kernel.org/r/20230914022425.1489035-1-irogers@google.com Signed-off-by: Namhyung Kim --- tools/perf/util/pmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d85602aa4b9f..8de6f39abd1b 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -520,7 +520,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, pmu_name = pe->pmu; } - alias = malloc(sizeof(*alias)); + alias = zalloc(sizeof(*alias)); if (!alias) return -ENOMEM; -- cgit v1.2.3 From e47749f1796d1df39a7eaae95f2784aaa43df57d Mon Sep 17 00:00:00 2001 From: Thomas Richter Date: Wed, 13 Sep 2023 14:51:57 +0200 Subject: perf jevent: fix core dump on software events on s390 Running commands such as # ./perf stat -e cs -- true Segmentation fault (core dumped) # ./perf stat -e cpu-clock-- true Segmentation fault (core dumped) # dump core. This should not happen as these events are defined even when no hardware PMU is available. Debugging this reveals this call chain: perf_pmus__find_by_type(type=1) +--> pmu_read_sysfs(core_only=false) +--> perf_pmu__find2(dirfd=3, name=0x152a113 "software") +--> perf_pmu__lookup(pmus=0x14f0568 , dirfd=3, lookup_name=0x152a113 "software") +--> perf_pmu__find_events_table (pmu=0x1532130) Now the pmu is "software" and it tries to find a proper table generated by the pmu-event generation process for s390: # cd pmu-events/ # ./jevents.py s390 all /root/linux/tools/perf/pmu-events/arch |\ grep -E '^const struct pmu_table_entry' const struct pmu_table_entry pmu_events__cf_z10[] = { const struct pmu_table_entry pmu_events__cf_z13[] = { const struct pmu_table_entry pmu_metrics__cf_z13[] = { const struct pmu_table_entry pmu_events__cf_z14[] = { const struct pmu_table_entry pmu_metrics__cf_z14[] = { const struct pmu_table_entry pmu_events__cf_z15[] = { const struct pmu_table_entry pmu_metrics__cf_z15[] = { const struct pmu_table_entry pmu_events__cf_z16[] = { const struct pmu_table_entry pmu_metrics__cf_z16[] = { const struct pmu_table_entry pmu_events__cf_z196[] = { const struct pmu_table_entry pmu_events__cf_zec12[] = { const struct pmu_table_entry pmu_metrics__cf_zec12[] = { const struct pmu_table_entry pmu_events__test_soc_cpu[] = { const struct pmu_table_entry pmu_metrics__test_soc_cpu[] = { const struct pmu_table_entry pmu_events__test_soc_sys[] = { # However event "software" is not listed, as can be seen in the generated const struct pmu_events_map pmu_events_map[]. So in function perf_pmu__find_events_table(), the variable table is initialized to NULL, but never set to a proper value. The function scans all generated &pmu_events_map[] tables, but no table matches, because the tables are s390 CPU Measurement unit specific: i = 0; for (;;) { const struct pmu_events_map *map = &pmu_events_map[i++]; if (!map->arch) break; --> the maps are there because the build generated them if (!strcmp_cpuid_str(map->cpuid, cpuid)) { table = &map->event_table; break; } --> Since no matching CPU string the table var remains 0x0 } free(cpuid); if (!pmu) return table; --> The pmu is "software" so it exists and no return --> and here perf dies because table is 0x0 for (i = 0; i < table->num_pmus; i++) { ... } return NULL; Fix this and do not access the table variable. Instead return 0x0 which is the same return code when the for-loop was not successful. Output after: # ./perf stat -e cs -- true Performance counter stats for 'true': 0 cs 0.000853105 seconds time elapsed 0.000061000 seconds user 0.000827000 seconds sys # ./perf stat -e cpu-clock -- true Performance counter stats for 'true': 0.25 msec cpu-clock # 0.341 CPUs utilized 0.000728383 seconds time elapsed 0.000055000 seconds user 0.000706000 seconds sys # ./perf stat -e cycles -- true Performance counter stats for 'true': cycles 0.000767298 seconds time elapsed 0.000055000 seconds user 0.000739000 seconds sys # Fixes: 7c52f10c0d4d8 ("perf pmu: Cache JSON events table") Signed-off-by: Thomas Richter Reviewed-by: Ian Rogers Cc: dengler@linux.ibm.com Cc: gor@linux.ibm.com Cc: hca@linux.ibm.com Cc: sumanthk@linux.ibm.com Cc: svens@linux.ibm.com Link: https://lore.kernel.org/r/20230913125157.2790375-1-tmricht@linux.ibm.com Signed-off-by: Namhyung Kim --- tools/perf/pmu-events/jevents.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools') diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index a7e88332276d..72ba4a9239c6 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -991,7 +991,7 @@ const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) } } free(cpuid); - if (!pmu) + if (!pmu || !table) return table; for (i = 0; i < table->num_pmus; i++) { -- cgit v1.2.3