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

Daniel Borkmann says:

====================
pull-request: bpf 2024-06-24

We've added 12 non-merge commits during the last 10 day(s) which contain
a total of 10 files changed, 412 insertions(+), 16 deletions(-).

The main changes are:

1) Fix a BPF verifier issue validating may_goto with a negative offset,
   from Alexei Starovoitov.

2) Fix a BPF verifier validation bug with may_goto combined with jump to
   the first instruction, also from Alexei Starovoitov.

3) Fix a bug with overrunning reservations in BPF ring buffer,
   from Daniel Borkmann.

4) Fix a bug in BPF verifier due to missing proper var_off setting related
   to movsx instruction, from Yonghong Song.

5) Silence unnecessary syzkaller-triggered warning in __xdp_reg_mem_model(),
   from Daniil Dulov.

* tag 'for-netdev' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  xdp: Remove WARN() from __xdp_reg_mem_model()
  selftests/bpf: Add tests for may_goto with negative offset.
  bpf: Fix may_goto with negative offset.
  selftests/bpf: Add more ring buffer test coverage
  bpf: Fix overrunning reservations in ringbuf
  selftests/bpf: Tests with may_goto and jumps to the 1st insn
  bpf: Fix the corner case with may_goto and jump to the 1st insn.
  bpf: Update BPF LSM maintainer list
  bpf: Fix remap of arena.
  selftests/bpf: Add a few tests to cover
  bpf: Add missed var_off setting in coerce_subreg_to_size_sx()
  bpf: Add missed var_off setting in set_sext32_default_val()
====================

Link: https://patch.msgid.link/20240624124330.8401-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: kuba-moo

MAINTAINERS

@@ -4083,12 +4083,13 @@ F:	kernel/bpf/ringbuf.c
 
 BPF [SECURITY & LSM] (Security Audit and Enforcement using BPF)
 M:	KP Singh <kpsingh@kernel.org>
-R:	Matt Bobrowski <mattbobrowski@google.com>
+M:	Matt Bobrowski <mattbobrowski@google.com>
 L:	bpf@vger.kernel.org
 S:	Maintained
 F:	Documentation/bpf/prog_lsm.rst
 F:	include/linux/bpf_lsm.h
 F:	kernel/bpf/bpf_lsm.c
+F:	kernel/trace/bpf_trace.c
 F:	security/bpf/
 
 BPF [SELFTESTS] (Test Runners & Infrastructure)

kernel/bpf/arena.c

@@ -212,6 +212,7 @@ static u64 arena_map_mem_usage(const struct bpf_map *map)
 struct vma_list {
 	struct vm_area_struct *vma;
 	struct list_head head;
+	atomic_t mmap_count;
 };
 
 static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
@@ -221,20 +222,30 @@ static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
 	vml = kmalloc(sizeof(*vml), GFP_KERNEL);
 	if (!vml)
 		return -ENOMEM;
+	atomic_set(&vml->mmap_count, 1);
 	vma->vm_private_data = vml;
 	vml->vma = vma;
 	list_add(&vml->head, &arena->vma_list);
 	return 0;
 }
 
+static void arena_vm_open(struct vm_area_struct *vma)
+{
+	struct vma_list *vml = vma->vm_private_data;
+
+	atomic_inc(&vml->mmap_count);
+}
+
 static void arena_vm_close(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);
-	struct vma_list *vml;
+	struct vma_list *vml = vma->vm_private_data;
 
+	if (!atomic_dec_and_test(&vml->mmap_count))
+		return;
 	guard(mutex)(&arena->lock);
-	vml = vma->vm_private_data;
+	/* update link list under lock */
 	list_del(&vml->head);
 	vma->vm_private_data = NULL;
 	kfree(vml);
@@ -287,6 +298,7 @@ static vm_fault_t arena_vm_fault(struct vm_fault *vmf)
 }
 
 static const struct vm_operations_struct arena_vm_ops = {
+	.open		= arena_vm_open,
 	.close		= arena_vm_close,
 	.fault          = arena_vm_fault,
 };

kernel/bpf/ringbuf.c

@@ -51,7 +51,8 @@ struct bpf_ringbuf {
 	 * This prevents a user-space application from modifying the
 	 * position and ruining in-kernel tracking. The permissions of the
 	 * pages depend on who is producing samples: user-space or the
-	 * kernel.
+	 * kernel. Note that the pending counter is placed in the same
+	 * page as the producer, so that it shares the same cache line.
 	 *
 	 * Kernel-producer
 	 * ---------------
@@ -70,6 +71,7 @@ struct bpf_ringbuf {
 	 */
 	unsigned long consumer_pos __aligned(PAGE_SIZE);
 	unsigned long producer_pos __aligned(PAGE_SIZE);
+	unsigned long pending_pos;
 	char data[] __aligned(PAGE_SIZE);
 };
 
@@ -179,6 +181,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
 	rb->mask = data_sz - 1;
 	rb->consumer_pos = 0;
 	rb->producer_pos = 0;
+	rb->pending_pos = 0;
 
 	return rb;
 }
@@ -404,9 +407,9 @@ bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr)
 
 static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 {
-	unsigned long cons_pos, prod_pos, new_prod_pos, flags;
-	u32 len, pg_off;
+	unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, flags;
 	struct bpf_ringbuf_hdr *hdr;
+	u32 len, pg_off, tmp_size, hdr_len;
 
 	if (unlikely(size > RINGBUF_MAX_RECORD_SZ))
 		return NULL;
@@ -424,13 +427,29 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 		spin_lock_irqsave(&rb->spinlock, flags);
 	}
 
+	pend_pos = rb->pending_pos;
 	prod_pos = rb->producer_pos;
 	new_prod_pos = prod_pos + len;
 
-	/* check for out of ringbuf space by ensuring producer position
-	 * doesn't advance more than (ringbuf_size - 1) ahead
+	while (pend_pos < prod_pos) {
+		hdr = (void *)rb->data + (pend_pos & rb->mask);
+		hdr_len = READ_ONCE(hdr->len);
+		if (hdr_len & BPF_RINGBUF_BUSY_BIT)
+			break;
+		tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT;
+		tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8);
+		pend_pos += tmp_size;
+	}
+	rb->pending_pos = pend_pos;
+
+	/* check for out of ringbuf space:
+	 * - by ensuring producer position doesn't advance more than
+	 *   (ringbuf_size - 1) ahead
+	 * - by ensuring oldest not yet committed record until newest
+	 *   record does not span more than (ringbuf_size - 1)
 	 */
-	if (new_prod_pos - cons_pos > rb->mask) {
+	if (new_prod_pos - cons_pos > rb->mask ||
+	    new_prod_pos - pend_pos > rb->mask) {
 		spin_unlock_irqrestore(&rb->spinlock, flags);
 		return NULL;
 	}

kernel/bpf/verifier.c

@@ -6236,6 +6236,7 @@ static void set_sext32_default_val(struct bpf_reg_state *reg, int size)
 	}
 	reg->u32_min_value = 0;
 	reg->u32_max_value = U32_MAX;
+	reg->var_off = tnum_subreg(tnum_unknown);
 }
 
 static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
@@ -6280,6 +6281,7 @@ static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
 		reg->s32_max_value = s32_max;
 		reg->u32_min_value = (u32)s32_min;
 		reg->u32_max_value = (u32)s32_max;
+		reg->var_off = tnum_subreg(tnum_range(s32_min, s32_max));
 		return;
 	}
 
@@ -12719,6 +12721,16 @@ static bool signed_add32_overflows(s32 a, s32 b)
 	return res < a;
 }
 
+static bool signed_add16_overflows(s16 a, s16 b)
+{
+	/* Do the add in u16, where overflow is well-defined */
+	s16 res = (s16)((u16)a + (u16)b);
+
+	if (b < 0)
+		return res > a;
+	return res < a;
+}
+
 static bool signed_sub_overflows(s64 a, s64 b)
 {
 	/* Do the sub in u64, where overflow is well-defined */
@@ -17448,11 +17460,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 				goto skip_inf_loop_check;
 			}
 			if (is_may_goto_insn_at(env, insn_idx)) {
-				if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) {
+				if (sl->state.may_goto_depth != cur->may_goto_depth &&
+				    states_equal(env, &sl->state, cur, RANGE_WITHIN)) {
 					update_loop_entry(cur, &sl->state);
 					goto hit;
 				}
-				goto skip_inf_loop_check;
 			}
 			if (calls_callback(env, insn_idx)) {
 				if (states_equal(env, &sl->state, cur, RANGE_WITHIN))
@@ -18730,6 +18742,39 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	return new_prog;
 }
 
+/*
+ * For all jmp insns in a given 'prog' that point to 'tgt_idx' insn adjust the
+ * jump offset by 'delta'.
+ */
+static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta)
+{
+	struct bpf_insn *insn = prog->insnsi;
+	u32 insn_cnt = prog->len, i;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		u8 code = insn->code;
+
+		if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) ||
+		    BPF_OP(code) == BPF_CALL || BPF_OP(code) == BPF_EXIT)
+			continue;
+
+		if (insn->code == (BPF_JMP32 | BPF_JA)) {
+			if (i + 1 + insn->imm != tgt_idx)
+				continue;
+			if (signed_add32_overflows(insn->imm, delta))
+				return -ERANGE;
+			insn->imm += delta;
+		} else {
+			if (i + 1 + insn->off != tgt_idx)
+				continue;
+			if (signed_add16_overflows(insn->imm, delta))
+				return -ERANGE;
+			insn->off += delta;
+		}
+	}
+	return 0;
+}
+
 static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env,
 					      u32 off, u32 cnt)
 {
@@ -20004,7 +20049,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 
 			stack_depth_extra = 8;
 			insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off);
-			insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2);
+			if (insn->off >= 0)
+				insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2);
+			else
+				insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1);
 			insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1);
 			insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off);
 			cnt = 4;
@@ -20546,6 +20594,13 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 		if (!new_prog)
 			return -ENOMEM;
 		env->prog = prog = new_prog;
+		/*
+		 * If may_goto is a first insn of a prog there could be a jmp
+		 * insn that points to it, hence adjust all such jmps to point
+		 * to insn after BPF_ST that inits may_goto count.
+		 * Adjustment will succeed because bpf_patch_insn_data() didn't fail.
+		 */
+		WARN_ON(adjust_jmp_off(env->prog, subprog_start, 1));
 	}
 
 	/* Since poke tab is now finalized, publish aux to tracker. */

net/core/xdp.c

@@ -295,10 +295,8 @@ static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem,
 		mutex_lock(&mem_id_lock);
 		ret = __mem_id_init_hash_table();
 		mutex_unlock(&mem_id_lock);
-		if (ret < 0) {
-			WARN_ON(1);
+		if (ret < 0)
 			return ERR_PTR(ret);
-		}
 	}
 
 	xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp);

tools/testing/selftests/bpf/Makefile

@@ -457,7 +457,7 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
 LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c 		\
 	trace_printk.c trace_vprintk.c map_ptr_kern.c 			\
 	core_kern.c core_kern_overflow.c test_ringbuf.c			\
-	test_ringbuf_n.c test_ringbuf_map_key.c
+	test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c
 
 # Generate both light skeleton and libbpf skeleton for these
 LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \

tools/testing/selftests/bpf/prog_tests/ringbuf.c

@@ -12,9 +12,11 @@
 #include <sys/sysinfo.h>
 #include <linux/perf_event.h>
 #include <linux/ring_buffer.h>
+
 #include "test_ringbuf.lskel.h"
 #include "test_ringbuf_n.lskel.h"
 #include "test_ringbuf_map_key.lskel.h"
+#include "test_ringbuf_write.lskel.h"
 
 #define EDONE 7777
 
@@ -84,6 +86,58 @@ static void *poll_thread(void *input)
 	return (void *)(long)ring_buffer__poll(ringbuf, timeout);
 }
 
+static void ringbuf_write_subtest(void)
+{
+	struct test_ringbuf_write_lskel *skel;
+	int page_size = getpagesize();
+	size_t *mmap_ptr;
+	int err, rb_fd;
+
+	skel = test_ringbuf_write_lskel__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->maps.ringbuf.max_entries = 0x4000;
+
+	err = test_ringbuf_write_lskel__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	rb_fd = skel->maps.ringbuf.map_fd;
+
+	mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0);
+	if (!ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"))
+		goto cleanup;
+	*mmap_ptr = 0x3000;
+	ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw");
+
+	skel->bss->pid = getpid();
+
+	ringbuf = ring_buffer__new(rb_fd, process_sample, NULL, NULL);
+	if (!ASSERT_OK_PTR(ringbuf, "ringbuf_new"))
+		goto cleanup;
+
+	err = test_ringbuf_write_lskel__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup_ringbuf;
+
+	skel->bss->discarded = 0;
+	skel->bss->passed = 0;
+
+	/* trigger exactly two samples */
+	syscall(__NR_getpgid);
+	syscall(__NR_getpgid);
+
+	ASSERT_EQ(skel->bss->discarded, 2, "discarded");
+	ASSERT_EQ(skel->bss->passed, 0, "passed");
+
+	test_ringbuf_write_lskel__detach(skel);
+cleanup_ringbuf:
+	ring_buffer__free(ringbuf);
+cleanup:
+	test_ringbuf_write_lskel__destroy(skel);
+}
+
 static void ringbuf_subtest(void)
 {
 	const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample);
@@ -451,4 +505,6 @@ void test_ringbuf(void)
 		ringbuf_n_subtest();
 	if (test__start_subtest("ringbuf_map_key"))
 		ringbuf_map_key_subtest();
+	if (test__start_subtest("ringbuf_write"))
+		ringbuf_write_subtest();
 }

tools/testing/selftests/bpf/progs/test_ringbuf_write.c

@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+} ringbuf SEC(".maps");
+
+/* inputs */
+int pid = 0;
+
+/* outputs */
+long passed = 0;
+long discarded = 0;
+
+SEC("fentry/" SYS_PREFIX "sys_getpgid")
+int test_ringbuf_write(void *ctx)
+{
+	int *foo, cur_pid = bpf_get_current_pid_tgid() >> 32;
+	void *sample1, *sample2;
+
+	if (cur_pid != pid)
+		return 0;
+
+	sample1 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0);
+	if (!sample1)
+		return 0;
+	/* first one can pass */
+	sample2 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0);
+	if (!sample2) {
+		bpf_ringbuf_discard(sample1, 0);
+		__sync_fetch_and_add(&discarded, 1);
+		return 0;
+	}
+	/* second one must not */
+	__sync_fetch_and_add(&passed, 1);
+	foo = sample2 + 4084;
+	*foo = 256;
+	bpf_ringbuf_discard(sample1, 0);
+	bpf_ringbuf_discard(sample2, 0);
+	return 0;
+}