From 7c7e3d31e7856a8260a254f8c71db416f7f9f5a1 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 5 Nov 2021 16:23:29 -0700 Subject: bpf: Introduce helper bpf_find_vma In some profiler use cases, it is necessary to map an address to the backing file, e.g., a shared library. bpf_find_vma helper provides a flexible way to achieve this. bpf_find_vma maps an address of a task to the vma (vm_area_struct) for this address, and feed the vma to an callback BPF function. The callback function is necessary here, as we need to ensure mmap_sem is unlocked. It is necessary to lock mmap_sem for find_vma. To lock and unlock mmap_sem safely when irqs are disable, we use the same mechanism as stackmap with build_id. Specifically, when irqs are disabled, the unlocked is postponed in an irq_work. Refactor stackmap.c so that the irq_work is shared among bpf_find_vma and stackmap helpers. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Tested-by: Hengqi Chen Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211105232330.1936330-2-songliubraving@fb.com --- kernel/trace/bpf_trace.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7396488793ff..390176a3031a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1208,6 +1208,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_func_ip_proto_tracing; case BPF_FUNC_get_branch_snapshot: return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_find_vma: + return &bpf_find_vma_proto; case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: -- cgit v1.2.3 From d19ddb476a539fd78ad1028ae13bb38506286931 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 12 Nov 2021 07:02:43 -0800 Subject: bpf: Introduce btf_tracing_ids Similar to btf_sock_ids, btf_tracing_ids provides btf ID for task_struct, file, and vm_area_struct via easy to understand format like btf_tracing_ids[BTF_TRACING_TYPE_[TASK|file|VMA]]. Suggested-by: Alexei Starovoitov Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211112150243.1270987-3-songliubraving@fb.com --- kernel/trace/bpf_trace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 390176a3031a..25ea521fb8f1 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -764,7 +764,7 @@ const struct bpf_func_proto bpf_get_current_task_btf_proto = { .func = bpf_get_current_task_btf, .gpl_only = true, .ret_type = RET_PTR_TO_BTF_ID, - .ret_btf_id = &btf_task_struct_ids[0], + .ret_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; BPF_CALL_1(bpf_task_pt_regs, struct task_struct *, task) @@ -779,7 +779,7 @@ const struct bpf_func_proto bpf_task_pt_regs_proto = { .func = bpf_task_pt_regs, .gpl_only = true, .arg1_type = ARG_PTR_TO_BTF_ID, - .arg1_btf_id = &btf_task_struct_ids[0], + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .ret_type = RET_PTR_TO_BTF_ID, .ret_btf_id = &bpf_task_pt_regs_ids[0], }; -- cgit v1.2.3 From db52f57211b4e45f0ebb274e2c877b211dc18591 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Mon, 6 Dec 2021 13:03:15 +0530 Subject: bpf: Remove config check to enable bpf support for branch records Branch data available to BPF programs can be very useful to get stack traces out of userspace application. Commit fff7b64355ea ("bpf: Add bpf_read_branch_records() helper") added BPF support to capture branch records in x86. Enable this feature also for other architectures as well by removing checks specific to x86. If an architecture doesn't support branch records, bpf_read_branch_records() still has appropriate checks and it will return an -EINVAL in that scenario. Based on UAPI helper doc in include/uapi/linux/bpf.h, unsupported architectures should return -ENOENT in such case. Hence, update the appropriate check to return -ENOENT instead. Selftest 'perf_branches' result on power9 machine which has the branch stacks support: - Before this patch: [command]# ./test_progs -t perf_branches #88/1 perf_branches/perf_branches_hw:FAIL #88/2 perf_branches/perf_branches_no_hw:OK #88 perf_branches:FAIL Summary: 0/1 PASSED, 0 SKIPPED, 1 FAILED - After this patch: [command]# ./test_progs -t perf_branches #88/1 perf_branches/perf_branches_hw:OK #88/2 perf_branches/perf_branches_no_hw:OK #88 perf_branches:OK Summary: 1/2 PASSED, 0 SKIPPED, 0 FAILED Selftest 'perf_branches' result on power9 machine which doesn't have branch stack report: - After this patch: [command]# ./test_progs -t perf_branches #88/1 perf_branches/perf_branches_hw:SKIP #88/2 perf_branches/perf_branches_no_hw:OK #88 perf_branches:OK Summary: 1/1 PASSED, 1 SKIPPED, 0 FAILED Fixes: fff7b64355eac ("bpf: Add bpf_read_branch_records() helper") Suggested-by: Peter Zijlstra Signed-off-by: Kajol Jain Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211206073315.77432-1-kjain@linux.ibm.com --- kernel/trace/bpf_trace.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 25ea521fb8f1..77f13de6f9f9 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1404,9 +1404,6 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, void *, buf, u32, size, u64, flags) { -#ifndef CONFIG_X86 - return -ENOENT; -#else static const u32 br_entry_size = sizeof(struct perf_branch_entry); struct perf_branch_stack *br_stack = ctx->data->br_stack; u32 to_copy; @@ -1415,7 +1412,7 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, return -EINVAL; if (unlikely(!br_stack)) - return -EINVAL; + return -ENOENT; if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE) return br_stack->nr * br_entry_size; @@ -1427,7 +1424,6 @@ BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, memcpy(buf, br_stack->entries, to_copy); return to_copy; -#endif } static const struct bpf_func_proto bpf_read_branch_records_proto = { -- cgit v1.2.3 From f92c1e183604c20ce00eb889315fdaa8f2d9e509 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 8 Dec 2021 20:32:44 +0100 Subject: bpf: Add get_func_[arg|ret|arg_cnt] helpers Adding following helpers for tracing programs: Get n-th argument of the traced function: long bpf_get_func_arg(void *ctx, u32 n, u64 *value) Get return value of the traced function: long bpf_get_func_ret(void *ctx, u64 *value) Get arguments count of the traced function: long bpf_get_func_arg_cnt(void *ctx) The trampoline now stores number of arguments on ctx-8 address, so it's easy to verify argument index and find return value argument's position. Moving function ip address on the trampoline stack behind the number of functions arguments, so it's now stored on ctx-16 address if it's needed. All helpers above are inlined by verifier. Also bit unrelated small change - using newly added function bpf_prog_has_trampoline in check_get_func_ip. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211208193245.172141-5-jolsa@kernel.org --- kernel/trace/bpf_trace.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 623dd0684429..cea2ca6df949 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1012,7 +1012,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx) { /* This helper call is inlined by verifier. */ - return ((u64 *)ctx)[-1]; + return ((u64 *)ctx)[-2]; } static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = { @@ -1091,6 +1091,53 @@ static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { .arg2_type = ARG_CONST_SIZE_OR_ZERO, }; +BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value) +{ + /* This helper call is inlined by verifier. */ + u64 nr_args = ((u64 *)ctx)[-1]; + + if ((u64) n >= nr_args) + return -EINVAL; + *value = ((u64 *)ctx)[n]; + return 0; +} + +static const struct bpf_func_proto bpf_get_func_arg_proto = { + .func = get_func_arg, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value) +{ + /* This helper call is inlined by verifier. */ + u64 nr_args = ((u64 *)ctx)[-1]; + + *value = ((u64 *)ctx)[nr_args]; + return 0; +} + +static const struct bpf_func_proto bpf_get_func_ret_proto = { + .func = get_func_ret, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_1(get_func_arg_cnt, void *, ctx) +{ + /* This helper call is inlined by verifier. */ + return ((u64 *)ctx)[-1]; +} + +static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = { + .func = get_func_arg_cnt, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1629,6 +1676,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) NULL; case BPF_FUNC_d_path: return &bpf_d_path_proto; + case BPF_FUNC_get_func_arg: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL; + case BPF_FUNC_get_func_ret: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL; + case BPF_FUNC_get_func_arg_cnt: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); if (!fn && prog->expected_attach_type == BPF_TRACE_ITER) -- cgit v1.2.3 From aef2feda97b840ec38e9fa53d0065188453304e8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 15 Dec 2021 18:55:37 -0800 Subject: add missing bpf-cgroup.h includes We're about to break the cgroup-defs.h -> bpf-cgroup.h dependency, make sure those who actually need more than the definition of struct cgroup_bpf include bpf-cgroup.h explicitly. Signed-off-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov Acked-by: Tejun Heo Link: https://lore.kernel.org/bpf/20211216025538.1649516-3-kuba@kernel.org --- kernel/trace/trace_kprobe.c | 1 + kernel/trace/trace_uprobe.c | 1 + 2 files changed, 2 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 33272a7b6912..4e1257f50aa3 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "trace_kprobe: " fmt +#include #include #include #include diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index f5f0039d31e5..4f35514a48f3 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "trace_uprobe: " fmt +#include #include #include #include -- cgit v1.2.3 From 216e3cd2f28dbbf1fe86848e0e29e6693b9f0a20 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Thu, 16 Dec 2021 16:31:51 -0800 Subject: bpf: Add MEM_RDONLY for helper args that are pointers to rdonly mem. Some helper functions may modify its arguments, for example, bpf_d_path, bpf_get_stack etc. Previously, their argument types were marked as ARG_PTR_TO_MEM, which is compatible with read-only mem types, such as PTR_TO_RDONLY_BUF. Therefore it's legitimate, but technically incorrect, to modify a read-only memory by passing it into one of such helper functions. This patch tags the bpf_args compatible with immutable memory with MEM_RDONLY flag. The arguments that don't have this flag will be only compatible with mutable memory types, preventing the helper from modifying a read-only memory. The bpf_args that have MEM_RDONLY are compatible with both mutable memory and immutable memory. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211217003152.48334-9-haoluo@google.com --- kernel/trace/bpf_trace.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cea2ca6df949..21aa30644219 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -345,7 +345,7 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; @@ -394,7 +394,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = { .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, }; @@ -450,9 +450,9 @@ static const struct bpf_func_proto bpf_trace_vprintk_proto = { .func = bpf_trace_vprintk, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, - .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -492,9 +492,9 @@ static const struct bpf_func_proto bpf_seq_printf_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, - .arg4_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -509,7 +509,7 @@ static const struct bpf_func_proto bpf_seq_write_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -533,7 +533,7 @@ static const struct bpf_func_proto bpf_seq_printf_btf_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -694,7 +694,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1004,7 +1004,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; @@ -1334,7 +1334,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1556,7 +1556,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1610,7 +1610,7 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; -- cgit v1.2.3