1 files changed, 191 insertions, 285 deletions

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index bfafbf115bf3..3615c06b7dfa 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -7,11 +7,10 @@
 #include <linux/kernel.h>
 #include <linux/stacktrace.h>
 #include <linux/perf_event.h>
-#include <linux/elf.h>
-#include <linux/pagemap.h>
-#include <linux/irq_work.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 |	\
@@ -29,28 +28,9 @@ struct bpf_stack_map {
 	void *elems;
 	struct pcpu_freelist freelist;
 	u32 n_buckets;
-	struct stack_map_bucket *buckets[];
+	struct stack_map_bucket *buckets[] __counted_by(n_buckets);
 };
 
-/* irq_work to run up_read() for build_id lookup in nmi context */
-struct stack_map_irq_work {
-	struct irq_work irq_work;
-	struct mm_struct *mm;
-};
-
-static void do_up_read(struct irq_work *entry)
-{
-	struct stack_map_irq_work *work;
-
-	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT)))
-		return;
-
-	work = container_of(entry, struct stack_map_irq_work, irq_work);
-	mmap_read_unlock_non_owner(work->mm);
-}
-
-static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);
-
 static inline bool stack_map_use_build_id(struct bpf_map *map)
 {
 	return (map->map_flags & BPF_F_STACK_BUILD_ID);
@@ -64,7 +44,8 @@ static inline int stack_map_data_size(struct bpf_map *map)
 
 static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
 {
-	u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
+	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,
@@ -93,9 +74,6 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	u64 cost, n_buckets;
 	int err;
 
-	if (!bpf_capable())
-		return ERR_PTR(-EPERM);
-
 	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
@@ -113,19 +91,20 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	} else if (value_size / 8 > sysctl_perf_event_max_stack)
 		return ERR_PTR(-EINVAL);
 
-	/* hash table size must be power of 2 */
-	n_buckets = roundup_pow_of_two(attr->max_entries);
-	if (!n_buckets)
+	/* 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);
-	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
 	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->map.value_size = value_size;
 	smap->n_buckets = n_buckets;
 
 	err = get_callchain_buffers(sysctl_perf_event_max_stack);
@@ -145,209 +124,71 @@ free_smap:
 	return ERR_PTR(err);
 }
 
-#define BPF_BUILD_ID 3
-/*
- * Parse build id from the note segment. This logic can be shared between
- * 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are
- * identical.
- */
-static inline int stack_map_parse_build_id(void *page_addr,
-					   unsigned char *build_id,
-					   void *note_start,
-					   Elf32_Word note_size)
-{
-	Elf32_Word note_offs = 0, new_offs;
-
-	/* check for overflow */
-	if (note_start < page_addr || note_start + note_size < note_start)
-		return -EINVAL;
-
-	/* only supports note that fits in the first page */
-	if (note_start + note_size > page_addr + PAGE_SIZE)
-		return -EINVAL;
-
-	while (note_offs + sizeof(Elf32_Nhdr) < note_size) {
-		Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs);
-
-		if (nhdr->n_type == BPF_BUILD_ID &&
-		    nhdr->n_namesz == sizeof("GNU") &&
-		    nhdr->n_descsz > 0 &&
-		    nhdr->n_descsz <= BPF_BUILD_ID_SIZE) {
-			memcpy(build_id,
-			       note_start + note_offs +
-			       ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr),
-			       nhdr->n_descsz);
-			memset(build_id + nhdr->n_descsz, 0,
-			       BPF_BUILD_ID_SIZE - nhdr->n_descsz);
-			return 0;
-		}
-		new_offs = note_offs + sizeof(Elf32_Nhdr) +
-			ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4);
-		if (new_offs <= note_offs)  /* overflow */
-			break;
-		note_offs = new_offs;
-	}
-	return -EINVAL;
-}
-
-/* Parse build ID from 32-bit ELF */
-static int stack_map_get_build_id_32(void *page_addr,
-				     unsigned char *build_id)
-{
-	Elf32_Ehdr *ehdr = (Elf32_Ehdr *)page_addr;
-	Elf32_Phdr *phdr;
-	int i;
-
-	/* only supports phdr that fits in one page */
-	if (ehdr->e_phnum >
-	    (PAGE_SIZE - sizeof(Elf32_Ehdr)) / sizeof(Elf32_Phdr))
-		return -EINVAL;
-
-	phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr));
-
-	for (i = 0; i < ehdr->e_phnum; ++i) {
-		if (phdr[i].p_type == PT_NOTE &&
-		    !stack_map_parse_build_id(page_addr, build_id,
-					      page_addr + phdr[i].p_offset,
-					      phdr[i].p_filesz))
-			return 0;
-	}
-	return -EINVAL;
-}
-
-/* Parse build ID from 64-bit ELF */
-static int stack_map_get_build_id_64(void *page_addr,
-				     unsigned char *build_id)
+static int fetch_build_id(struct vm_area_struct *vma, unsigned char *build_id, bool may_fault)
 {
-	Elf64_Ehdr *ehdr = (Elf64_Ehdr *)page_addr;
-	Elf64_Phdr *phdr;
-	int i;
-
-	/* only supports phdr that fits in one page */
-	if (ehdr->e_phnum >
-	    (PAGE_SIZE - sizeof(Elf64_Ehdr)) / sizeof(Elf64_Phdr))
-		return -EINVAL;
-
-	phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr));
-
-	for (i = 0; i < ehdr->e_phnum; ++i) {
-		if (phdr[i].p_type == PT_NOTE &&
-		    !stack_map_parse_build_id(page_addr, build_id,
-					      page_addr + phdr[i].p_offset,
-					      phdr[i].p_filesz))
-			return 0;
-	}
-	return -EINVAL;
-}
-
-/* Parse build ID of ELF file mapped to vma */
-static int stack_map_get_build_id(struct vm_area_struct *vma,
-				  unsigned char *build_id)
-{
-	Elf32_Ehdr *ehdr;
-	struct page *page;
-	void *page_addr;
-	int ret;
-
-	/* only works for page backed storage  */
-	if (!vma->vm_file)
-		return -EINVAL;
-
-	page = find_get_page(vma->vm_file->f_mapping, 0);
-	if (!page)
-		return -EFAULT;	/* page not mapped */
-
-	ret = -EINVAL;
-	page_addr = kmap_atomic(page);
-	ehdr = (Elf32_Ehdr *)page_addr;
-
-	/* compare magic x7f "ELF" */
-	if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG) != 0)
-		goto out;
-
-	/* only support executable file and shared object file */
-	if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN)
-		goto out;
-
-	if (ehdr->e_ident[EI_CLASS] == ELFCLASS32)
-		ret = stack_map_get_build_id_32(page_addr, build_id);
-	else if (ehdr->e_ident[EI_CLASS] == ELFCLASS64)
-		ret = stack_map_get_build_id_64(page_addr, build_id);
-out:
-	kunmap_atomic(page_addr);
-	put_page(page);
-	return ret;
+	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,
-					  u64 *ips, u32 trace_nr, bool user)
+					  u32 trace_nr, bool user, bool may_fault)
 {
 	int i;
-	struct vm_area_struct *vma;
-	bool irq_work_busy = false;
-	struct stack_map_irq_work *work = NULL;
-
-	if (irqs_disabled()) {
-		if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
-			work = this_cpu_ptr(&up_read_work);
-			if (irq_work_is_busy(&work->irq_work)) {
-				/* cannot queue more up_read, fallback */
-				irq_work_busy = true;
-			}
-		} else {
-			/*
-			 * PREEMPT_RT does not allow to trylock mmap sem in
-			 * interrupt disabled context. Force the fallback code.
-			 */
-			irq_work_busy = true;
-		}
-	}
-
-	/*
-	 * We cannot do up_read() when the irq is disabled, because of
-	 * risk to deadlock with rq_lock. To do build_id lookup when the
-	 * irqs are disabled, we need to run up_read() in irq_work. We use
-	 * a percpu variable to do the irq_work. If the irq_work is
-	 * already used by another lookup, we fall back to report ips.
-	 *
-	 * Same fallback is used for kernel stack (!user) on a stackmap
-	 * with build_id.
+	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_non_owner(current->mm)) {
+	    !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;
-			id_offs[i].ip = ips[i];
-			memset(id_offs[i].build_id, 0, BPF_BUILD_ID_SIZE);
+			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
 		}
 		return;
 	}
 
 	for (i = 0; i < trace_nr; i++) {
-		vma = find_vma(current->mm, ips[i]);
-		if (!vma || stack_map_get_build_id(vma, id_offs[i].build_id)) {
+		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;
-			id_offs[i].ip = ips[i];
-			memset(id_offs[i].build_id, 0, BPF_BUILD_ID_SIZE);
+			memset(id_offs[i].build_id, 0, BUILD_ID_SIZE_MAX);
 			continue;
 		}
-		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
-			- vma->vm_start;
+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;
 	}
-
-	if (!work) {
-		mmap_read_unlock_non_owner(current->mm);
-	} else {
-		work->mm = current->mm;
-		irq_work_queue(&work->irq_work);
-	}
+	bpf_mmap_unlock_mm(work, current->mm);
 }
 
 static struct perf_callchain_entry *
-get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
+get_callchain_entry_for_task(struct task_struct *task, u32 max_depth)
 {
 #ifdef CONFIG_STACKTRACE
 	struct perf_callchain_entry *entry;
@@ -358,9 +199,8 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
 	if (!entry)
 		return NULL;
 
-	entry->nr = init_nr +
-		stack_trace_save_tsk(task, (unsigned long *)(entry->ip + init_nr),
-				     sysctl_perf_event_max_stack - init_nr, 0);
+	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
@@ -372,7 +212,7 @@ get_callchain_entry_for_task(struct task_struct *task, u32 init_nr)
 		int i;
 
 		/* copy data from the end to avoid using extra buffer */
-		for (i = entry->nr - 1; i >= (int)init_nr; i--)
+		for (i = entry->nr - 1; i >= 0; i--)
 			to[i] = (u64)(from[i]);
 	}
 
@@ -389,27 +229,19 @@ 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 max_depth = map->value_size / stack_map_data_size(map);
-	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
-	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
 	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
-	u32 hash, id, trace_nr, trace_len;
+	u32 hash, id, trace_nr, trace_len, i;
 	bool user = flags & BPF_F_USER_STACK;
 	u64 *ips;
 	bool hash_matches;
 
-	/* get_perf_callchain() guarantees that trace->nr >= init_nr
-	 * and trace-nr <= sysctl_perf_event_max_stack, so trace_nr <= max_depth
-	 */
-	trace_nr = trace->nr - init_nr;
-
-	if (trace_nr <= skip)
+	if (trace->nr <= skip)
 		/* skipping more than usable stack trace */
 		return -EFAULT;
 
-	trace_nr -= skip;
+	trace_nr = trace->nr - skip;
 	trace_len = trace_nr * sizeof(u64);
-	ips = trace->ip + skip + init_nr;
+	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]);
@@ -420,15 +252,18 @@ static long __bpf_get_stackid(struct bpf_map *map,
 		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;
-		stack_map_get_build_id_offset(
-			(struct bpf_stack_build_id *)new_bucket->data,
-			ips, trace_nr, user);
+		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) {
@@ -466,8 +301,7 @@ 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);
-	/* stack_map_alloc() checks that max_depth <= sysctl_perf_event_max_stack */
-	u32 init_nr = sysctl_perf_event_max_stack - max_depth;
+	u32 skip = flags & BPF_F_SKIP_FIELD_MASK;
 	bool user = flags & BPF_F_USER_STACK;
 	struct perf_callchain_entry *trace;
 	bool kernel = !user;
@@ -476,8 +310,12 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map,
 			       BPF_F_FAST_STACK_CMP | BPF_F_REUSE_STACKID)))
 		return -EINVAL;
 
-	trace = get_perf_callchain(regs, init_nr, kernel, user,
-				   sysctl_perf_event_max_stack, false, false);
+	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);
 
 	if (unlikely(!trace))
 		/* couldn't fetch the stack trace */
@@ -517,7 +355,7 @@ BPF_CALL_3(bpf_get_stackid_pe, struct bpf_perf_event_data_kern *, ctx,
 	int ret;
 
 	/* perf_sample_data doesn't have callchain, use bpf_get_stackid */
-	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+	if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN))
 		return bpf_get_stackid((unsigned long)(ctx->regs),
 				       (unsigned long) map, flags, 0, 0);
 
@@ -566,10 +404,11 @@ const struct bpf_func_proto bpf_get_stackid_proto_pe = {
 
 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)
+			    void *buf, u32 size, u64 flags, bool may_fault)
 {
-	u32 init_nr, trace_nr, copy_len, elem_size, num_elem;
+	u32 trace_nr, copy_len, elem_size, num_elem, 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;
@@ -583,8 +422,7 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	if (kernel && user_build_id)
 		goto clear;
 
-	elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id)
-					    : sizeof(u64);
+	elem_size = user_build_id ? sizeof(struct bpf_stack_build_id) : sizeof(u64);
 	if (unlikely(size % elem_size))
 		goto clear;
 
@@ -592,35 +430,57 @@ static long __bpf_get_stack(struct pt_regs *regs, struct task_struct *task,
 	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;
+	}
+
 	num_elem = size / elem_size;
-	if (sysctl_perf_event_max_stack < num_elem)
-		init_nr = 0;
-	else
-		init_nr = sysctl_perf_event_max_stack - num_elem;
+	max_depth = num_elem + skip;
+	if (sysctl_perf_event_max_stack < max_depth)
+		max_depth = sysctl_perf_event_max_stack;
+
+	if (may_fault)
+		rcu_read_lock(); /* need RCU for perf's callchain below */
 
 	if (trace_in)
 		trace = trace_in;
 	else if (kernel && task)
-		trace = get_callchain_entry_for_task(task, init_nr);
+		trace = get_callchain_entry_for_task(task, max_depth);
 	else
-		trace = get_perf_callchain(regs, init_nr, kernel, user,
-					   sysctl_perf_event_max_stack,
-					   false, false);
-	if (unlikely(!trace))
-		goto err_fault;
+		trace = get_perf_callchain(regs, 0, kernel, user, max_depth,
+					   crosstask, false);
 
-	trace_nr = trace->nr - init_nr;
-	if (trace_nr < skip)
+	if (unlikely(!trace) || trace->nr < skip) {
+		if (may_fault)
+			rcu_read_unlock();
 		goto err_fault;
+	}
 
-	trace_nr -= skip;
+	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 + init_nr;
-	if (user && user_build_id)
-		stack_map_get_build_id_offset(buf, ips, trace_nr, user);
-	else
+
+	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)
+		stack_map_get_build_id_offset(buf, trace_nr, user, may_fault);
 
 	if (size > copy_len)
 		memset(buf + copy_len, 0, size - copy_len);
@@ -636,7 +496,7 @@ clear:
 BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size,
 	   u64, flags)
 {
-	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
+	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */);
 }
 
 const struct bpf_func_proto bpf_get_stack_proto = {
@@ -649,22 +509,68 @@ const struct bpf_func_proto bpf_get_stack_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
-	   u32, size, u64, flags)
+BPF_CALL_4(bpf_get_stack_sleepable, struct pt_regs *, regs, void *, buf, u32, size,
+	   u64, flags)
+{
+	return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, true /* may_fault */);
+}
+
+const struct bpf_func_proto bpf_get_stack_sleepable_proto = {
+	.func		= bpf_get_stack_sleepable,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+static long __bpf_get_task_stack(struct task_struct *task, void *buf, u32 size,
+				 u64 flags, bool may_fault)
 {
-	struct pt_regs *regs = task_pt_regs(task);
+	struct pt_regs *regs;
+	long res = -EINVAL;
 
-	return __bpf_get_stack(regs, task, NULL, buf, size, flags);
+	if (!try_get_task_stack(task))
+		return -EFAULT;
+
+	regs = task_pt_regs(task);
+	if (regs)
+		res = __bpf_get_stack(regs, task, NULL, buf, size, flags, may_fault);
+	put_task_stack(task);
+
+	return res;
 }
 
-BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct)
+BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	return __bpf_get_task_stack(task, buf, size, flags, false /* !may_fault */);
+}
 
 const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.func		= bpf_get_task_stack,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id	= &bpf_get_task_stack_btf_ids[0],
+	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
+	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_get_task_stack_sleepable, struct task_struct *, task, void *, buf,
+	   u32, size, u64, flags)
+{
+	return __bpf_get_task_stack(task, buf, size, flags, true /* !may_fault */);
+}
+
+const struct bpf_func_proto bpf_get_task_stack_sleepable_proto = {
+	.func		= bpf_get_task_stack_sleepable,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
@@ -680,8 +586,8 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 	int err = -EINVAL;
 	__u64 nr_kernel;
 
-	if (!(event->attr.sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
-		return __bpf_get_stack(regs, NULL, NULL, buf, size, flags);
+	if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN))
+		return __bpf_get_stack(regs, NULL, NULL, buf, size, flags, false /* !may_fault */);
 
 	if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK |
 			       BPF_F_USER_BUILD_ID)))
@@ -701,7 +607,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 		__u64 nr = trace->nr;
 
 		trace->nr = nr_kernel;
-		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);
+		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */);
 
 		/* restore nr */
 		trace->nr = nr;
@@ -713,7 +619,7 @@ BPF_CALL_4(bpf_get_stack_pe, struct bpf_perf_event_data_kern *, ctx,
 			goto clear;
 
 		flags = (flags & ~BPF_F_SKIP_FIELD_MASK) | skip;
-		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags);
+		err = __bpf_get_stack(regs, NULL, trace, buf, size, flags, false /* !may_fault */);
 	}
 	return err;
 
@@ -792,14 +698,14 @@ static int stack_map_get_next_key(struct bpf_map *map, void *key,
 	return 0;
 }
 
-static int stack_map_update_elem(struct bpf_map *map, void *key, void *value,
-				 u64 map_flags)
+static long stack_map_update_elem(struct bpf_map *map, void *key, void *value,
+				  u64 map_flags)
 {
 	return -EINVAL;
 }
 
 /* Called from syscall or from eBPF program */
-static int stack_map_delete_elem(struct bpf_map *map, void *key)
+static long stack_map_delete_elem(struct bpf_map *map, void *key)
 {
 	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
 	struct stack_map_bucket *old_bucket;
@@ -828,7 +734,20 @@ static void stack_map_free(struct bpf_map *map)
 	put_callchain_buffers();
 }
 
-static int stack_trace_map_btf_id;
+static u64 stack_map_mem_usage(const struct bpf_map *map)
+{
+	struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map);
+	u64 value_size = map->value_size;
+	u64 n_buckets = smap->n_buckets;
+	u64 enties = map->max_entries;
+	u64 usage = sizeof(*smap);
+
+	usage += n_buckets * sizeof(struct stack_map_bucket *);
+	usage += enties * (sizeof(struct stack_map_bucket) + value_size);
+	return usage;
+}
+
+BTF_ID_LIST_SINGLE(stack_trace_map_btf_ids, struct, bpf_stack_map)
 const struct bpf_map_ops stack_trace_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
 	.map_alloc = stack_map_alloc,
@@ -838,19 +757,6 @@ const struct bpf_map_ops stack_trace_map_ops = {
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
 	.map_check_btf = map_check_no_btf,
-	.map_btf_name = "bpf_stack_map",
-	.map_btf_id = &stack_trace_map_btf_id,
+	.map_mem_usage = stack_map_mem_usage,
+	.map_btf_id = &stack_trace_map_btf_ids[0],
 };
-
-static int __init stack_map_init(void)
-{
-	int cpu;
-	struct stack_map_irq_work *work;
-
-	for_each_possible_cpu(cpu) {
-		work = per_cpu_ptr(&up_read_work, cpu);
-		init_irq_work(&work->irq_work, do_up_read);
-	}
-	return 0;
-}
-subsys_initcall(stack_map_init);