6.17-stable review patch. If anyone has any objections, please let me know.
------------------
From: Arnaud Lecomte contact@arnaud-lcm.com
[ Upstream commit e17d62fedd10ae56e2426858bd0757da544dbc73 ]
Extract the duplicated maximum allowed depth computation for stack traces stored in BPF stacks from bpf_get_stackid() and __bpf_get_stack() into a dedicated stack_map_calculate_max_depth() helper function.
This unifies the logic for: - The max depth computation - Enforcing the sysctl_perf_event_max_stack limit
No functional changes for existing code paths.
Signed-off-by: Arnaud Lecomte contact@arnaud-lcm.com Signed-off-by: Andrii Nakryiko andrii@kernel.org Acked-by: Yonghong Song yonghong.song@linux.dev Acked-by: Song Liu song@kernel.org Link: https://lore.kernel.org/bpf/20251025192858.31424-1-contact@arnaud-lcm.com Stable-dep-of: 23f852daa4ba ("bpf: Fix stackmap overflow check in __bpf_get_stackid()") Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/bpf/stackmap.c | 47 +++++++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 15 deletions(-)
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index ec3a57a5fba1f..d6027bac61c35 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -42,6 +42,28 @@ static inline int stack_map_data_size(struct bpf_map *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) + @@ -300,20 +322,17 @@ static long __bpf_get_stackid(struct bpf_map *map, BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, u64, flags) { - u32 max_depth = map->value_size / stack_map_data_size(map); - u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + 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 += skip; - if (max_depth > sysctl_perf_event_max_stack) - max_depth = sysctl_perf_event_max_stack; - + max_depth = stack_map_calculate_max_depth(map->value_size, elem_size, flags); trace = get_perf_callchain(regs, kernel, user, max_depth, false, false);
@@ -406,7 +425,7 @@ 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, num_elem, max_depth; + 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; @@ -438,21 +457,20 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, goto clear; }
- num_elem = size / elem_size; - max_depth = num_elem + skip; - if (sysctl_perf_event_max_stack < max_depth) - max_depth = sysctl_perf_event_max_stack; + 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) + if (trace_in) { trace = trace_in; - else if (kernel && task) + trace->nr = min_t(u32, trace->nr, max_depth); + } else if (kernel && task) { trace = get_callchain_entry_for_task(task, max_depth); - else + } else { trace = get_perf_callchain(regs, kernel, user, max_depth, crosstask, false); + }
if (unlikely(!trace) || trace->nr < skip) { if (may_fault) @@ -461,7 +479,6 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task, }
trace_nr = trace->nr - skip; - trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; copy_len = trace_nr * elem_size;
ips = trace->ip + skip;