1 files changed, 256 insertions, 45 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 3615c06b7dfa..77ba03216c09 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -9,6 +9,7 @@
 #include <linux/perf_event.h>
 #include <linux/btf_ids.h>
 #include <linux/buildid.h>
+#include <linux/mmap_lock.h>
 #include "percpu_freelist.h"
 #include "mmap_unlock_work.h"
 
@@ -42,6 +43,28 @@ 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) +
@@ -130,6 +153,180 @@ static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, b
 			 : build_id_parse_nofault(vma, build_id, NULL);
 }
 
+static inline void stack_map_build_id_set_ip(struct bpf_stack_build_id *id)
+{
+	id->status = BPF_STACK_BUILD_ID_IP;
+	memset(id->build_id, 0, BUILD_ID_SIZE_MAX);
+}
+
+static inline u64 stack_map_build_id_offset(unsigned long vm_pgoff,
+					    unsigned long vm_start, u64 ip)
+{
+	return (vm_pgoff << PAGE_SHIFT) + ip - vm_start;
+}
+
+static inline void stack_map_build_id_set_valid(struct bpf_stack_build_id *id,
+						u64 offset,
+						const unsigned char *build_id)
+{
+	id->status = BPF_STACK_BUILD_ID_VALID;
+	id->offset = offset;
+	if (id->build_id != build_id)
+		memcpy(id->build_id, build_id, BUILD_ID_SIZE_MAX);
+}
+
+struct stack_map_vma_lock {
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+};
+
+/*
+ * Acquire a stable read-side reference on the VMA covering @ip.
+ *
+ * With CONFIG_PER_VMA_LOCK=y this returns a VMA with its per-VMA read
+ * lock held and mmap_lock dropped, so the caller may sleep.
+ *
+ * With CONFIG_PER_VMA_LOCK=n it returns a VMA with mmap_lock still
+ * held; the caller must snapshot any fields it needs and pin vm_file
+ * with get_file() before stack_map_unlock_vma() drops mmap_lock, as
+ * the VMA may be split, merged, or freed after that.
+ *
+ * Returns NULL on failure, in which case no lock is held.
+ */
+static struct vm_area_struct *
+stack_map_lock_vma(struct stack_map_vma_lock *lock, unsigned long ip)
+{
+	struct mm_struct *mm = lock->mm;
+	struct vm_area_struct *vma;
+
+	/* noop under !CONFIG_PER_VMA_LOCK */
+	vma = lock_vma_under_rcu(mm, ip);
+	if (vma) {
+		lock->vma = vma;
+		return vma;
+	}
+
+	/*
+	 * Taking mmap_read_lock() is unsafe here, because the caller BPF
+	 * program might already hold it, causing a deadlock.
+	 */
+	if (!mmap_read_trylock(mm))
+		return NULL;
+
+	vma = vma_lookup(mm, ip);
+	if (!vma) {
+		mmap_read_unlock(mm);
+		return NULL;
+	}
+
+#ifdef CONFIG_PER_VMA_LOCK
+	if (!vma_start_read_locked(vma)) {
+		mmap_read_unlock(mm);
+		return NULL;
+	}
+	mmap_read_unlock(mm);
+#endif
+
+	lock->vma = vma;
+	return vma;
+}
+
+static void stack_map_unlock_vma(struct stack_map_vma_lock *lock)
+{
+#ifdef CONFIG_PER_VMA_LOCK
+	vma_end_read(lock->vma);
+#else
+	mmap_read_unlock(lock->mm);
+#endif
+	lock->vma = NULL;
+}
+
+static void stack_map_get_build_id_offset_sleepable(struct bpf_stack_build_id *id_offs,
+						    u32 trace_nr)
+{
+	struct mm_struct *mm = current->mm;
+	struct stack_map_vma_lock lock = { .mm = mm };
+	struct {
+		struct file *file;
+		const unsigned char *build_id;
+		unsigned long vm_start;
+		unsigned long vm_end;
+		unsigned long vm_pgoff;
+	} cache = {};
+	unsigned long vm_pgoff, vm_start, vm_end;
+	struct vm_area_struct *vma;
+	struct file *file;
+	u64 offset;
+	u64 ip;
+
+	for (u32 i = 0; i < trace_nr; i++) {
+		ip = READ_ONCE(id_offs[i].ip);
+
+		/*
+		 * Range cache fast path: if ip falls within the previously
+		 * resolved VMA range, reuse the cache build_id without
+		 * re-acquiring the VMA lock.
+		 */
+		if (cache.build_id && ip >= cache.vm_start && ip < cache.vm_end) {
+			offset = stack_map_build_id_offset(cache.vm_pgoff, cache.vm_start, ip);
+			stack_map_build_id_set_valid(&id_offs[i], offset, cache.build_id);
+			continue;
+		}
+
+		vma = stack_map_lock_vma(&lock, ip);
+		if (!vma) {
+			stack_map_build_id_set_ip(&id_offs[i]);
+			continue;
+		}
+		if (vma_is_anonymous(vma) || !vma->vm_file) {
+			stack_map_build_id_set_ip(&id_offs[i]);
+			stack_map_unlock_vma(&lock);
+			continue;
+		}
+
+		file = vma->vm_file;
+		vm_pgoff = vma->vm_pgoff;
+		vm_start = vma->vm_start;
+		vm_end = vma->vm_end;
+		offset = stack_map_build_id_offset(vm_pgoff, vm_start, ip);
+
+		/*
+		 * Same backing file as previous (e.g. different VMAs
+		 * of the same ELF binary). Reuse the cache build_id.
+		 */
+		if (file == cache.file) {
+			stack_map_unlock_vma(&lock);
+			stack_map_build_id_set_valid(&id_offs[i], offset, cache.build_id);
+			cache.vm_start = vm_start;
+			cache.vm_end = vm_end;
+			cache.vm_pgoff = vm_pgoff;
+			continue;
+		}
+
+		file = get_file(file);
+		stack_map_unlock_vma(&lock);
+
+		/* build_id_parse_file() may block on filesystem reads */
+		if (build_id_parse_file(file, id_offs[i].build_id, NULL)) {
+			stack_map_build_id_set_ip(&id_offs[i]);
+			fput(file);
+			continue;
+		}
+
+		stack_map_build_id_set_valid(&id_offs[i], offset, id_offs[i].build_id);
+		if (cache.file)
+			fput(cache.file);
+		cache.file = file;
+		cache.build_id = id_offs[i].build_id;
+		cache.vm_start = vm_start;
+		cache.vm_end = vm_end;
+		cache.vm_pgoff = vm_pgoff;
+	}
+
+	if (cache.file)
+		fput(cache.file);
+}
+
 /*
  * Expects all id_offs[i].ip values to be set to correct initial IPs.
  * They will be subsequently:
@@ -143,44 +340,50 @@ static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, b
 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);
+	bool has_user_ctx = user && current && current->mm;
 	struct vm_area_struct *vma, *prev_vma = NULL;
-	const char *prev_build_id;
+	const unsigned char *prev_build_id = NULL;
+	int i;
+
+	if (may_fault && has_user_ctx) {
+		stack_map_get_build_id_offset_sleepable(id_offs, trace_nr);
+		return;
+	}
 
 	/* 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)) {
+	if (!has_user_ctx || 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);
-		}
+		for (i = 0; i < trace_nr; i++)
+			stack_map_build_id_set_ip(&id_offs[i]);
 		return;
 	}
 
 	for (i = 0; i < trace_nr; i++) {
 		u64 ip = READ_ONCE(id_offs[i].ip);
+		u64 offset;
 
-		if (range_in_vma(prev_vma, ip, ip)) {
+		if (prev_build_id && 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;
+			offset = stack_map_build_id_offset(vma->vm_pgoff, vma->vm_start, ip);
+			stack_map_build_id_set_valid(&id_offs[i], offset, prev_build_id);
+			continue;
 		}
 		vma = find_vma(current->mm, ip);
-		if (!vma || fetch_build_id(vma, id_offs[i].build_id, may_fault)) {
+		if (!vma || vma_is_anonymous(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);
+			stack_map_build_id_set_ip(&id_offs[i]);
+			prev_vma = vma;
+			prev_build_id = NULL;
 			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;
+		offset = stack_map_build_id_offset(vma->vm_pgoff, vma->vm_start, ip);
+		stack_map_build_id_set_valid(&id_offs[i], offset, id_offs[i].build_id);
 		prev_vma = vma;
 		prev_build_id = id_offs[i].build_id;
 	}
@@ -229,8 +432,8 @@ static long __bpf_get_stackid(struct bpf_map *map,
 {
 	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;
-	u32 hash, id, trace_nr, trace_len, i;
 	bool user = flags & BPF_F_USER_STACK;
 	u64 *ips;
 	bool hash_matches;
@@ -239,7 +442,8 @@ static long __bpf_get_stackid(struct bpf_map *map,
 		/* skipping more than usable stack trace */
 		return -EFAULT;
 
-	trace_nr = trace->nr - skip;
+	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);
@@ -300,22 +504,19 @@ 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;
-
-	trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
-				   false, false);
+	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 */
@@ -371,15 +572,11 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
 		return -EFAULT;
 
 	nr_kernel = count_kernel_ip(trace);
+	__u64 nr = trace->nr; /* save original */
 
 	if (kernel) {
-		__u64 nr = trace->nr;
-
 		trace->nr = nr_kernel;
 		ret = __bpf_get_stackid(map, trace, flags);
-
-		/* restore nr */
-		trace->nr = nr;
 	} else { /* user */
 		u64 skip = flags & BPF_F_SKIP_FIELD_MASK;
 
@@ -390,6 +587,10 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
 		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
 		ret = __bpf_get_stackid(map, trace, flags);
 	}
+
+	/* restore nr */
+	trace->nr = nr;
+
 	return ret;
 }
 
@@ -406,7 +607,7 @@ 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 +639,20 @@ 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
-		trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
-					   crosstask, false);
+	} else {
+		trace = get_perf_callchain(regs, kernel, user, max_depth,
+					   crosstask, false, 0);
+	}
 
 	if (unlikely(!trace) || trace->nr < skip) {
 		if (may_fault)
@@ -461,7 +661,6 @@ 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;
@@ -646,7 +845,15 @@ static void *stack_map_lookup_elem(struct bpf_map *map, void *key)
 }
 
 /* Called from syscall */
-int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
+static int stack_map_lookup_and_delete_elem(struct bpf_map *map, void *key,
+					    void *value, u64 flags)
+{
+	return bpf_stackmap_extract(map, key, value, true);
+}
+
+/* Called from syscall */
+int bpf_stackmap_extract(struct bpf_map *map, void *key, void *value,
+			 bool delete)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
 	struct stack_map_bucket *bucket, *old_bucket;
@@ -663,7 +870,10 @@ int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
 	memcpy(value, bucket->data, trace_len);
 	memset(value + trace_len, 0, map->value_size - trace_len);
 
-	old_bucket = xchg(&smap->buckets[id], bucket);
+	if (delete)
+		old_bucket = bucket;
+	else
+		old_bucket = xchg(&smap->buckets[id], bucket);
 	if (old_bucket)
 		pcpu_freelist_push(&smap->freelist, &old_bucket->fnode);
 	return 0;
@@ -754,6 +964,7 @@ const struct bpf_map_ops stack_trace_map_ops = {
 	.map_free = stack_map_free,
 	.map_get_next_key = stack_map_get_next_key,
 	.map_lookup_elem = stack_map_lookup_elem,
+	.map_lookup_and_delete_elem = stack_map_lookup_and_delete_elem,
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
 	.map_check_btf = map_check_no_btf,