Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
bpf-next-for-netdev
The following pull-request contains BPF updates for your *net-next* tree.

We've added 22 non-merge commits during the last 3 day(s) which contain
a total of 23 files changed, 652 insertions(+), 431 deletions(-).

The main changes are:

1) Add verifier support for annotating user's global BPF subprogram arguments
   with few commonly requested annotations for a better developer experience,
   from Andrii Nakryiko.

   These tags are:
     - Ability to annotate a special PTR_TO_CTX argument
     - Ability to annotate a generic PTR_TO_MEM as non-NULL

2) Support BPF verifier tracking of BPF_JNE which helps cases when the compiler
   transforms (unsigned) "a > 0" into "if a == 0 goto xxx" and the like, from
   Menglong Dong.

3) Fix a warning in bpf_mem_cache's check_obj_size() as reported by LKP, from Hou Tao.

4) Re-support uid/gid options when mounting bpffs which had to be reverted with
   the prior token series revert to avoid conflicts, from Daniel Borkmann.

5) Fix a libbpf NULL pointer dereference in bpf_object__collect_prog_relos() found
   from fuzzing the library with malformed ELF files, from Mingyi Zhang.

6) Skip DWARF sections in libbpf's linker sanity check given compiler options to
   generate compressed debug sections can trigger a rejection due to misalignment,
   from Alyssa Ross.

7) Fix an unnecessary use of the comma operator in BPF verifier, from Simon Horman.

8) Fix format specifier for unsigned long values in cpustat sample, from Colin Ian King.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 11 insertions, 94 deletions

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 6a51cfe4c2d6..aa0fbf000a12 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -490,27 +490,6 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
 }
 
-static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
-{
-	struct llist_node *first;
-	unsigned int obj_size;
-
-	first = c->free_llist.first;
-	if (!first)
-		return 0;
-
-	if (c->percpu_size)
-		obj_size = pcpu_alloc_size(((void **)first)[1]);
-	else
-		obj_size = ksize(first);
-	if (obj_size != c->unit_size) {
-		WARN_ONCE(1, "bpf_mem_cache[%u]: percpu %d, unexpected object size %u, expect %u\n",
-			  idx, c->percpu_size, obj_size, c->unit_size);
-		return -EINVAL;
-	}
-	return 0;
-}
-
 /* When size != 0 bpf_mem_cache for each cpu.
  * This is typical bpf hash map use case when all elements have equal size.
  *
@@ -521,10 +500,10 @@ static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 {
 	static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
-	int cpu, i, err, unit_size, percpu_size = 0;
 	struct bpf_mem_caches *cc, __percpu *pcc;
 	struct bpf_mem_cache *c, __percpu *pc;
 	struct obj_cgroup *objcg = NULL;
+	int cpu, i, unit_size, percpu_size = 0;
 
 	/* room for llist_node and per-cpu pointer */
 	if (percpu)
@@ -560,7 +539,6 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 	pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
 	if (!pcc)
 		return -ENOMEM;
-	err = 0;
 #ifdef CONFIG_MEMCG_KMEM
 	objcg = get_obj_cgroup_from_current();
 #endif
@@ -574,28 +552,12 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->tgt = c;
 
 			init_refill_work(c);
-			/* Another bpf_mem_cache will be used when allocating
-			 * c->unit_size in bpf_mem_alloc(), so doesn't prefill
-			 * for the bpf_mem_cache because these free objects will
-			 * never be used.
-			 */
-			if (i != bpf_mem_cache_idx(c->unit_size))
-				continue;
 			prefill_mem_cache(c, cpu);
-			err = check_obj_size(c, i);
-			if (err)
-				goto out;
 		}
 	}
 
-out:
 	ma->caches = pcc;
-	/* refill_work is either zeroed or initialized, so it is safe to
-	 * call irq_work_sync().
-	 */
-	if (err)
-		bpf_mem_alloc_destroy(ma);
-	return err;
+	return 0;
 }
 
 static void drain_mem_cache(struct bpf_mem_cache *c)
@@ -869,7 +831,7 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
 	void *ret;
 
 	if (!size)
-		return ZERO_SIZE_PTR;
+		return NULL;
 
 	idx = bpf_mem_cache_idx(size + LLIST_NODE_SZ);
 	if (idx < 0)
@@ -879,26 +841,17 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size)
 	return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
 
-static notrace int bpf_mem_free_idx(void *ptr, bool percpu)
-{
-	size_t size;
-
-	if (percpu)
-		size = pcpu_alloc_size(*((void **)ptr));
-	else
-		size = ksize(ptr - LLIST_NODE_SZ);
-	return bpf_mem_cache_idx(size);
-}
-
 void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
 {
+	struct bpf_mem_cache *c;
 	int idx;
 
 	if (!ptr)
 		return;
 
-	idx = bpf_mem_free_idx(ptr, ma->percpu);
-	if (idx < 0)
+	c = *(void **)(ptr - LLIST_NODE_SZ);
+	idx = bpf_mem_cache_idx(c->unit_size);
+	if (WARN_ON_ONCE(idx < 0))
 		return;
 
 	unit_free(this_cpu_ptr(ma->caches)->cache + idx, ptr);
@@ -906,13 +859,15 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr)
 
 void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr)
 {
+	struct bpf_mem_cache *c;
 	int idx;
 
 	if (!ptr)
 		return;
 
-	idx = bpf_mem_free_idx(ptr, ma->percpu);
-	if (idx < 0)
+	c = *(void **)(ptr - LLIST_NODE_SZ);
+	idx = bpf_mem_cache_idx(c->unit_size);
+	if (WARN_ON_ONCE(idx < 0))
 		return;
 
 	unit_free_rcu(this_cpu_ptr(ma->caches)->cache + idx, ptr);
@@ -986,41 +941,3 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 
 	return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
-
-/* The alignment of dynamic per-cpu area is 8, so c->unit_size and the
- * actual size of dynamic per-cpu area will always be matched and there is
- * no need to adjust size_index for per-cpu allocation. However for the
- * simplicity of the implementation, use an unified size_index for both
- * kmalloc and per-cpu allocation.
- */
-static __init int bpf_mem_cache_adjust_size(void)
-{
-	unsigned int size;
-
-	/* Adjusting the indexes in size_index() according to the object_size
-	 * of underlying slab cache, so bpf_mem_alloc() will select a
-	 * bpf_mem_cache with unit_size equal to the object_size of
-	 * the underlying slab cache.
-	 *
-	 * The maximal value of KMALLOC_MIN_SIZE and __kmalloc_minalign() is
-	 * 256-bytes, so only do adjustment for [8-bytes, 192-bytes].
-	 */
-	for (size = 192; size >= 8; size -= 8) {
-		unsigned int kmalloc_size, index;
-
-		kmalloc_size = kmalloc_size_roundup(size);
-		if (kmalloc_size == size)
-			continue;
-
-		if (kmalloc_size <= 192)
-			index = size_index[(kmalloc_size - 1) / 8];
-		else
-			index = fls(kmalloc_size - 1) - 1;
-		/* Only overwrite if necessary */
-		if (size_index[(size - 1) / 8] != index)
-			size_index[(size - 1) / 8] = index;
-	}
-
-	return 0;
-}
-subsys_initcall(bpf_mem_cache_adjust_size);