// SPDX-License-Identifier: GPL-2.0-only/* Copyright (c) 2016 Facebook */#include <linux/bpf.h>#include <linux/jhash.h>#include <linux/filter.h>#include <linux/kernel.h>#include <linux/stacktrace.h>#include <linux/perf_event.h>#include <linux/btf_ids.h>#include <linux/buildid.h>#include "percpu_freelist.h"#include "mmap_unlock_work.h" #define STACK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY | \ BPF_F_STACK_BUILD_ID) struct stack_map_bucket { struct pcpu_freelist_node fnode; u32 hash; u32 nr; u64 data[];}; struct bpf_stack_map { struct bpf_map map; void *elems; struct pcpu_freelist freelist; u32 n_buckets; struct stack_map_bucket *buckets[] __counted_by(n_buckets);}; static inline bool stack_map_use_build_id(struct bpf_map *map){ return (map->map_flags & BPF_F_STACK_BUILD_ID);} static inline int stack_map_data_size(struct bpf_map *map){ return stack_map_use_build_id(map) ? sizeof(struct bpf_stack_build_id) : sizeof(u64);} /** * stack_map_calculate_max_depth - Calculate maximum allowed stack trace depth * @size: Size of the buffer/map value in bytes * @elem_size: Size of each stack trace element * @flags: BPF stack trace flags (BPF_F_USER_STACK, BPF_F_USER_BUILD_ID, ...) * * Return: Maximum number of stack trace entries that can be safely stored */static u32 stack_map_calculate_max_depth(u32 size, u32 elem_size, u64 flags){ u32 skip = flags & BPF_F_SKIP_FIELD_MASK; u32 max_depth; u32 curr_sysctl_max_stack = READ_ONCE(sysctl_perf_event_max_stack); max_depth = size / elem_size; max_depth += skip; if (max_depth > curr_sysctl_max_stack) return curr_sysctl_max_stack; return max_depth;} static int prealloc_elems_and_freelist(struct bpf_stack_map *smap){ u64 elem_size = sizeof(struct stack_map_bucket) + (u64)smap->map.value_size; int err; smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, smap->map.numa_node); if (!smap->elems) return -ENOMEM; err = pcpu_freelist_init(&smap->freelist); if (err) goto free_elems; pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size, smap->map.max_entries); return 0; free_elems: bpf_map_area_free(smap->elems); return err;} /* Called from syscall */static struct bpf_map *stack_map_alloc(union bpf_attr *attr){ u32 value_size = attr->value_size; struct bpf_stack_map *smap; u64 cost, n_buckets; int err; if (attr->map_flags & ~STACK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || value_size < 8 || value_size % 8) return ERR_PTR(-EINVAL); BUILD_BUG_ON(sizeof(struct bpf_stack_build_id) % sizeof(u64)); if (attr->map_flags & BPF_F_STACK_BUILD_ID) { if (value_size % sizeof(struct bpf_stack_build_id) || value_size / sizeof(struct bpf_stack_build_id) > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); } else if (value_size / 8 > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); /* hash table size must be power of 2; roundup_pow_of_two() can overflow * into UB on 32-bit arches, so check that first */ if (attr->max_entries > 1UL << 31) return ERR_PTR(-E2BIG); n_buckets = roundup_pow_of_two(attr->max_entries); cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); smap->n_buckets = n_buckets; err = get_callchain_buffers(sysctl_perf_event_max_stack); if (err) goto free_smap; err = prealloc_elems_and_freelist(smap); if (err) goto put_buffers; return &smap->map; put_buffers: put_callchain_buffers();free_smap: bpf_map_area_free(smap); return ERR_PTR(err);} static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, bool may_fault){ return may_fault ? build_id_parse(vma, build_id, NULL) : build_id_parse_nofault(vma, build_id, NULL);} /* * Expects all id_offs[i].ip values to be set to correct initial IPs. * They will be subsequently: * - either adjusted in place to a file offset, if build ID fetching * succeeds; in this case id_offs[i].build_id is set to correct build ID, * and id_offs[i].status is set to BPF_STACK_BUILD_ID_VALID; * - or IP will be kept intact, if build ID fetching failed; in this case * id_offs[i].build_id is zeroed out and id_offs[i].status is set to * BPF_STACK_BUILD_ID_IP. */static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, u32 trace_nr, bool user, bool may_fault){ int i; struct mmap_unlock_irq_work *work = NULL; bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); struct vm_area_struct *vma, *prev_vma = NULL; const char *prev_build_id; /* If the irq_work is in use, fall back to report ips. Same * fallback is used for kernel stack (!user) on a stackmap with * build_id. */ if (!user || !current || !current->mm || irq_work_busy || !mmap_read_trylock(current->mm)) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { id_offs[i].status = BPF_STACK_BUILD_ID_IP; memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); } return; } for (i = 0; i < trace_nr; i++) { u64 ip = READ_ONCE(id_offs[i].ip); if (range_in_vma(prev_vma, ip, ip)) { vma = prev_vma; memcpy(id_offs[i].build_id, prev_build_id, BUILD_ID_SIZE_MAX); goto build_id_valid; } vma = find_vma(current->mm, ip); if (!vma || fetch_build_id(vma, id_offs[i].build_id, may_fault)) { /* per entry fall back to ips */ id_offs[i].status = BPF_STACK_BUILD_ID_IP; memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); continue; }build_id_valid: id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ip - vma->vm_start; id_offs[i].status = BPF_STACK_BUILD_ID_VALID; prev_vma = vma; prev_build_id = id_offs[i].build_id; } bpf_mmap_unlock_mm(work, current->mm);} static struct perf_callchain_entry *get_callchain_entry_for_task(struct task_struct *task, u32 max_depth){#ifdef CONFIG_STACKTRACE struct perf_callchain_entry *entry; int rctx; entry = get_callchain_entry(&rctx); if (!entry) return NULL; entry->nr = stack_trace_save_tsk(task, (unsigned long *)entry->ip, max_depth, 0); /* stack_trace_save_tsk() works on unsigned long array, while * perf_callchain_entry uses u64 array. For 32-bit systems, it is * necessary to fix this mismatch. */ if (__BITS_PER_LONG != 64) { unsigned long *from = (unsigned long *) entry->ip; u64 *to = entry->ip; int i; /* copy data from the end to avoid using extra buffer */ for (i = entry->nr - 1; i >= 0; i--) to[i] = (u64)(from[i]); } put_callchain_entry(rctx); return entry;#else /* CONFIG_STACKTRACE */ return NULL;#endif} static long __bpf_get_stackid(struct bpf_map *map, struct perf_callchain_entry *trace, u64 flags){ struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *bucket, *new_bucket, *old_bucket; u32 hash, id, trace_nr, trace_len, i, max_depth; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; u64 *ips; bool hash_matches; if (trace->nr <= skip) /* skipping more than usable stack trace */ return -EFAULT; max_depth = stack_map_calculate_max_depth(map->value_size, stack_map_data_size(map), flags); trace_nr = min_t(u32, trace->nr - skip, max_depth - skip); trace_len = trace_nr * sizeof(u64); ips = trace->ip + skip; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); id = hash & (smap->n_buckets - 1); bucket = READ_ONCE(smap->buckets[id]); hash_matches = bucket && bucket->hash == hash; /* fast cmp */ if (hash_matches && flags & BPF_F_FAST_STACK_CMP) return id; if (stack_map_use_build_id(map)) { struct bpf_stack_build_id *id_offs; /* for build_id+offset, pop a bucket before slow cmp */ new_bucket = (struct stack_map_bucket *) pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; new_bucket->nr = trace_nr; id_offs = (struct bpf_stack_build_id *)new_bucket->data; for (i = 0; i < trace_nr; i++) id_offs[i].ip = ips[i]; stack_map_get_build_id_offset(id_offs, trace_nr, user, false /* !may_fault */); trace_len = trace_nr * sizeof(struct bpf_stack_build_id); if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, new_bucket->data, trace_len) == 0) { pcpu_freelist_push(&smap->freelist, &new_bucket->fnode); return id; } if (bucket && !(flags & BPF_F_REUSE_STACKID)) { pcpu_freelist_push(&smap->freelist, &new_bucket->fnode); return -EEXIST; } } else { if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, ips, trace_len) == 0) return id; if (bucket && !(flags & BPF_F_REUSE_STACKID)) return -EEXIST; new_bucket = (struct stack_map_bucket *) pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; memcpy(new_bucket->data, ips, trace_len); } new_bucket->hash = hash; new_bucket->nr = trace_nr; old_bucket = xchg(&smap->buckets[id], new_bucket); if (old_bucket) pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return id;} BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u64, flags){ u32 elem_size = stack_map_data_size(map); bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; u32 max_depth; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; max_depth = stack_map_calculate_max_depth(map->value_size, elem_size, flags); trace = get_perf_callchain(regs, kernel, user, max_depth, false, false, 0); if (unlikely(!trace)) /* couldn't fetch the stack trace */ return -EFAULT; return __bpf_get_stackid(map, trace, flags);} const struct bpf_func_proto bpf_get_stackid_proto = { .func = bpf_get_stackid, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING,}; static __u64 count_kernel_ip(struct perf_callchain_entry *trace){ __u64 nr_kernel = 0; while (nr_kernel < trace->nr) { if (trace->ip[nr_kernel] == PERF_CONTEXT_USER) break; nr_kernel++; } return nr_kernel;} BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, struct bpf_map *, map, u64, flags){ struct perf_event *event = ctx->event; struct perf_callchain_entry *trace; bool kernel, user; __u64 nr_kernel; int ret; /* perf_sample_data doesn't have callchain, use bpf_get_stackid */ if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) return bpf_get_stackid((unsigned long)(ctx->regs), (unsigned long) map, flags, 0, 0); if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; user = flags & BPF_F_USER_STACK; kernel = !user; trace = ctx->data->callchain; if (unlikely(!trace)) return -EFAULT; nr_kernel = count_kernel_ip(trace); __u64 nr = trace->nr; /* save original */ if (kernel) { trace->nr = nr_kernel; ret = __bpf_get_stackid(map, trace, flags); } else { /* user */ u64 skip = flags & BPF_F_SKIP_FIELD_MASK; skip += nr_kernel; if (skip > BPF_F_SKIP_FIELD_MASK) return -EFAULT; flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; ret = __bpf_get_stackid(map, trace, flags); } /* restore nr */ trace->nr = nr; return ret;} const struct bpf_func_proto bpf_get_stackid_proto_pe = { .func = bpf_get_stackid_pe, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING,}; static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, struct perf_callchain_entry *trace_in, void *buf, u32 size, u64 flags, bool may_fault){ u32 trace_nr, copy_len, elem_size, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; bool crosstask = task && task != current; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; int err = -EINVAL; u64 *ips; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_USER_BUILD_ID))) goto clear; if (kernel && user_build_id) goto clear; elem_size = user_build_id ? sizeof(struct bpf_stack_build_id) : sizeof(u64); if (unlikely(size % elem_size)) goto clear; /* cannot get valid user stack for task without user_mode regs */ if (task && user && !user_mode(regs)) goto err_fault; /* get_perf_callchain does not support crosstask user stack walking * but returns an empty stack instead of NULL. */ if (crosstask && user) { err = -EOPNOTSUPP; goto clear; } max_depth = stack_map_calculate_max_depth(size, elem_size, flags); if (may_fault) rcu_read_lock(); /* need RCU for perf's callchain below */ if (trace_in) { trace = trace_in; trace->nr = min_t(u32, trace->nr, max_depth); } else if (kernel && task) { trace = get_callchain_entry_for_task(task, max_depth); } else { trace = get_perf_callchain(regs, kernel, user, max_depth, crosstask, false, 0); } if (unlikely(!trace) || trace->nr < skip) { if (may_fault) rcu_read_unlock(); goto err_fault; } trace_nr = trace->nr - skip; copy_len = trace_nr * elem_size; ips = trace->ip + skip; if (user_build_id) { struct bpf_stack_build_id *id_offs = buf; u32 i; for (i = 0; i < trace_nr; i++) id_offs[i].ip = ips[i]; } else { memcpy(buf, ips, copy_len); } /* trace/ips should not be dereferenced after this point */ if (may_fault) rcu_read_unlock(); if (user_build_id)Lines 1–500 of 792. Load more
// SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2016 Facebook */ #include <linux/bpf.h> #include <linux/jhash.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/stacktrace.h> #include <linux/perf_event.h> #include <linux/btf_ids.h> #include <linux/buildid.h> #include "percpu_freelist.h" #include "mmap_unlock_work.h" #define STACK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY | \ BPF_F_STACK_BUILD_ID) struct stack_map_bucket { struct pcpu_freelist_node fnode; u32 hash; u32 nr; u64 data[]; }; struct bpf_stack_map { struct bpf_map map; void *elems; struct pcpu_freelist freelist; u32 n_buckets; struct stack_map_bucket *buckets[] __counted_by(n_buckets); }; static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); } static inline int stack_map_data_size(struct bpf_map *map) { return stack_map_use_build_id(map) ? sizeof(struct bpf_stack_build_id) : sizeof(u64); } /** * stack_map_calculate_max_depth - Calculate maximum allowed stack trace depth * @size: Size of the buffer/map value in bytes * @elem_size: Size of each stack trace element * @flags: BPF stack trace flags (BPF_F_USER_STACK, BPF_F_USER_BUILD_ID, ...) * * Return: Maximum number of stack trace entries that can be safely stored */ static u32 stack_map_calculate_max_depth(u32 size, u32 elem_size, u64 flags) { u32 skip = flags & BPF_F_SKIP_FIELD_MASK; u32 max_depth; u32 curr_sysctl_max_stack = READ_ONCE(sysctl_perf_event_max_stack); max_depth = size / elem_size; max_depth += skip; if (max_depth > curr_sysctl_max_stack) return curr_sysctl_max_stack; return max_depth; } static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) { u64 elem_size = sizeof(struct stack_map_bucket) + (u64)smap->map.value_size; int err; smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries, smap->map.numa_node); if (!smap->elems) return -ENOMEM; err = pcpu_freelist_init(&smap->freelist); if (err) goto free_elems; pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size, smap->map.max_entries); return 0; free_elems: bpf_map_area_free(smap->elems); return err; } /* Called from syscall */ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) { u32 value_size = attr->value_size; struct bpf_stack_map *smap; u64 cost, n_buckets; int err; if (attr->map_flags & ~STACK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || value_size < 8 || value_size % 8) return ERR_PTR(-EINVAL); BUILD_BUG_ON(sizeof(struct bpf_stack_build_id) % sizeof(u64)); if (attr->map_flags & BPF_F_STACK_BUILD_ID) { if (value_size % sizeof(struct bpf_stack_build_id) || value_size / sizeof(struct bpf_stack_build_id) > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); } else if (value_size / 8 > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); /* hash table size must be power of 2; roundup_pow_of_two() can overflow * into UB on 32-bit arches, so check that first */ if (attr->max_entries > 1UL << 31) return ERR_PTR(-E2BIG); n_buckets = roundup_pow_of_two(attr->max_entries); cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); smap->n_buckets = n_buckets; err = get_callchain_buffers(sysctl_perf_event_max_stack); if (err) goto free_smap; err = prealloc_elems_and_freelist(smap); if (err) goto put_buffers; return &smap->map; put_buffers: put_callchain_buffers(); free_smap: bpf_map_area_free(smap); return ERR_PTR(err); } static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, bool may_fault) { return may_fault ? build_id_parse(vma, build_id, NULL) : build_id_parse_nofault(vma, build_id, NULL); } /* * Expects all id_offs[i].ip values to be set to correct initial IPs. * They will be subsequently: * - either adjusted in place to a file offset, if build ID fetching * succeeds; in this case id_offs[i].build_id is set to correct build ID, * and id_offs[i].status is set to BPF_STACK_BUILD_ID_VALID; * - or IP will be kept intact, if build ID fetching failed; in this case * id_offs[i].build_id is zeroed out and id_offs[i].status is set to * BPF_STACK_BUILD_ID_IP. */ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, u32 trace_nr, bool user, bool may_fault) { int i; struct mmap_unlock_irq_work *work = NULL; bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); struct vm_area_struct *vma, *prev_vma = NULL; const char *prev_build_id; /* If the irq_work is in use, fall back to report ips. Same * fallback is used for kernel stack (!user) on a stackmap with * build_id. */ if (!user || !current || !current->mm || irq_work_busy || !mmap_read_trylock(current->mm)) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { id_offs[i].status = BPF_STACK_BUILD_ID_IP; memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); } return; } for (i = 0; i < trace_nr; i++) { u64 ip = READ_ONCE(id_offs[i].ip); if (range_in_vma(prev_vma, ip, ip)) { vma = prev_vma; memcpy(id_offs[i].build_id, prev_build_id, BUILD_ID_SIZE_MAX); goto build_id_valid; } vma = find_vma(current->mm, ip); if (!vma || fetch_build_id(vma, id_offs[i].build_id, may_fault)) { /* per entry fall back to ips */ id_offs[i].status = BPF_STACK_BUILD_ID_IP; memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX); continue; } build_id_valid: id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ip - vma->vm_start; id_offs[i].status = BPF_STACK_BUILD_ID_VALID; prev_vma = vma; prev_build_id = id_offs[i].build_id; } bpf_mmap_unlock_mm(work, current->mm); } static struct perf_callchain_entry * get_callchain_entry_for_task(struct task_struct *task, u32 max_depth) { #ifdef CONFIG_STACKTRACE struct perf_callchain_entry *entry; int rctx; entry = get_callchain_entry(&rctx); if (!entry) return NULL; entry->nr = stack_trace_save_tsk(task, (unsigned long *)entry->ip, max_depth, 0); /* stack_trace_save_tsk() works on unsigned long array, while * perf_callchain_entry uses u64 array. For 32-bit systems, it is * necessary to fix this mismatch. */ if (__BITS_PER_LONG != 64) { unsigned long *from = (unsigned long *) entry->ip; u64 *to = entry->ip; int i; /* copy data from the end to avoid using extra buffer */ for (i = entry->nr - 1; i >= 0; i--) to[i] = (u64)(from[i]); } put_callchain_entry(rctx); return entry; #else /* CONFIG_STACKTRACE */ return NULL; #endif } static long __bpf_get_stackid(struct bpf_map *map, struct perf_callchain_entry *trace, u64 flags) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); struct stack_map_bucket *bucket, *new_bucket, *old_bucket; u32 hash, id, trace_nr, trace_len, i, max_depth; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; u64 *ips; bool hash_matches; if (trace->nr <= skip) /* skipping more than usable stack trace */ return -EFAULT; max_depth = stack_map_calculate_max_depth(map->value_size, stack_map_data_size(map), flags); trace_nr = min_t(u32, trace->nr - skip, max_depth - skip); trace_len = trace_nr * sizeof(u64); ips = trace->ip + skip; hash = jhash2((u32 *)ips, trace_len / sizeof(u32), 0); id = hash & (smap->n_buckets - 1); bucket = READ_ONCE(smap->buckets[id]); hash_matches = bucket && bucket->hash == hash; /* fast cmp */ if (hash_matches && flags & BPF_F_FAST_STACK_CMP) return id; if (stack_map_use_build_id(map)) { struct bpf_stack_build_id *id_offs; /* for build_id+offset, pop a bucket before slow cmp */ new_bucket = (struct stack_map_bucket *) pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; new_bucket->nr = trace_nr; id_offs = (struct bpf_stack_build_id *)new_bucket->data; for (i = 0; i < trace_nr; i++) id_offs[i].ip = ips[i]; stack_map_get_build_id_offset(id_offs, trace_nr, user, false /* !may_fault */); trace_len = trace_nr * sizeof(struct bpf_stack_build_id); if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, new_bucket->data, trace_len) == 0) { pcpu_freelist_push(&smap->freelist, &new_bucket->fnode); return id; } if (bucket && !(flags & BPF_F_REUSE_STACKID)) { pcpu_freelist_push(&smap->freelist, &new_bucket->fnode); return -EEXIST; } } else { if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, ips, trace_len) == 0) return id; if (bucket && !(flags & BPF_F_REUSE_STACKID)) return -EEXIST; new_bucket = (struct stack_map_bucket *) pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; memcpy(new_bucket->data, ips, trace_len); } new_bucket->hash = hash; new_bucket->nr = trace_nr; old_bucket = xchg(&smap->buckets[id], new_bucket); if (old_bucket) pcpu_freelist_push(&smap->freelist, &old_bucket->fnode); return id; } BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u64, flags) { u32 elem_size = stack_map_data_size(map); bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; u32 max_depth; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; max_depth = stack_map_calculate_max_depth(map->value_size, elem_size, flags); trace = get_perf_callchain(regs, kernel, user, max_depth, false, false, 0); if (unlikely(!trace)) /* couldn't fetch the stack trace */ return -EFAULT; return __bpf_get_stackid(map, trace, flags); } const struct bpf_func_proto bpf_get_stackid_proto = { .func = bpf_get_stackid, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; static __u64 count_kernel_ip(struct perf_callchain_entry *trace) { __u64 nr_kernel = 0; while (nr_kernel < trace->nr) { if (trace->ip[nr_kernel] == PERF_CONTEXT_USER) break; nr_kernel++; } return nr_kernel; } BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx, struct bpf_map *, map, u64, flags) { struct perf_event *event = ctx->event; struct perf_callchain_entry *trace; bool kernel, user; __u64 nr_kernel; int ret; /* perf_sample_data doesn't have callchain, use bpf_get_stackid */ if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) return bpf_get_stackid((unsigned long)(ctx->regs), (unsigned long) map, flags, 0, 0); if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID))) return -EINVAL; user = flags & BPF_F_USER_STACK; kernel = !user; trace = ctx->data->callchain; if (unlikely(!trace)) return -EFAULT; nr_kernel = count_kernel_ip(trace); __u64 nr = trace->nr; /* save original */ if (kernel) { trace->nr = nr_kernel; ret = __bpf_get_stackid(map, trace, flags); } else { /* user */ u64 skip = flags & BPF_F_SKIP_FIELD_MASK; skip += nr_kernel; if (skip > BPF_F_SKIP_FIELD_MASK) return -EFAULT; flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip; ret = __bpf_get_stackid(map, trace, flags); } /* restore nr */ trace->nr = nr; return ret; } const struct bpf_func_proto bpf_get_stackid_proto_pe = { .func = bpf_get_stackid_pe, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, struct perf_callchain_entry *trace_in, void *buf, u32 size, u64 flags, bool may_fault) { u32 trace_nr, copy_len, elem_size, max_depth; bool user_build_id = flags & BPF_F_USER_BUILD_ID; bool crosstask = task && task != current; u32 skip = flags & BPF_F_SKIP_FIELD_MASK; bool user = flags & BPF_F_USER_STACK; struct perf_callchain_entry *trace; bool kernel = !user; int err = -EINVAL; u64 *ips; if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | BPF_F_USER_BUILD_ID))) goto clear; if (kernel && user_build_id) goto clear; elem_size = user_build_id ? sizeof(struct bpf_stack_build_id) : sizeof(u64); if (unlikely(size % elem_size)) goto clear; /* cannot get valid user stack for task without user_mode regs */ if (task && user && !user_mode(regs)) goto err_fault; /* get_perf_callchain does not support crosstask user stack walking * but returns an empty stack instead of NULL. */ if (crosstask && user) { err = -EOPNOTSUPP; goto clear; } max_depth = stack_map_calculate_max_depth(size, elem_size, flags); if (may_fault) rcu_read_lock(); /* need RCU for perf's callchain below */ if (trace_in) { trace = trace_in; trace->nr = min_t(u32, trace->nr, max_depth); } else if (kernel && task) { trace = get_callchain_entry_for_task(task, max_depth); } else { trace = get_perf_callchain(regs, kernel, user, max_depth, crosstask, false, 0); } if (unlikely(!trace) || trace->nr < skip) { if (may_fault) rcu_read_unlock(); goto err_fault; } trace_nr = trace->nr - skip; copy_len = trace_nr * elem_size; ips = trace->ip + skip; if (user_build_id) { struct bpf_stack_build_id *id_offs = buf; u32 i; for (i = 0; i < trace_nr; i++) id_offs[i].ip = ips[i]; } else { memcpy(buf, ips, copy_len); } /* trace/ips should not be dereferenced after this point */ if (may_fault) rcu_read_unlock(); if (user_build_id)