From 8b62645b09f870d70c7910e7550289d444239a46 Mon Sep 17 00:00:00 2001 From: Wander Lairson Costa Date: Fri, 20 Sep 2024 16:06:59 -0300 Subject: [PATCH 01/38] bpf: Use raw_spinlock_t in ringbuf The function __bpf_ringbuf_reserve is invoked from a tracepoint, which disables preemption. Using spinlock_t in this context can lead to a "sleep in atomic" warning in the RT variant. This issue is illustrated in the example below: BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 556208, name: test_progs preempt_count: 1, expected: 0 RCU nest depth: 1, expected: 1 INFO: lockdep is turned off. Preemption disabled at: [] migrate_enable+0xc0/0x39c CPU: 7 PID: 556208 Comm: test_progs Tainted: G Hardware name: Qualcomm SA8775P Ride (DT) Call trace: dump_backtrace+0xac/0x130 show_stack+0x1c/0x30 dump_stack_lvl+0xac/0xe8 dump_stack+0x18/0x30 __might_resched+0x3bc/0x4fc rt_spin_lock+0x8c/0x1a4 __bpf_ringbuf_reserve+0xc4/0x254 bpf_ringbuf_reserve_dynptr+0x5c/0xdc bpf_prog_ac3d15160d62622a_test_read_write+0x104/0x238 trace_call_bpf+0x238/0x774 perf_call_bpf_enter.isra.0+0x104/0x194 perf_syscall_enter+0x2f8/0x510 trace_sys_enter+0x39c/0x564 syscall_trace_enter+0x220/0x3c0 do_el0_svc+0x138/0x1dc el0_svc+0x54/0x130 el0t_64_sync_handler+0x134/0x150 el0t_64_sync+0x17c/0x180 Switch the spinlock to raw_spinlock_t to avoid this error. Fixes: 457f44363a88 ("bpf: Implement BPF ring buffer and verifier support for it") Reported-by: Brian Grech Signed-off-by: Wander Lairson Costa Signed-off-by: Wander Lairson Costa Signed-off-by: Daniel Borkmann Acked-by: Daniel Borkmann Link: https://lore.kernel.org/r/20240920190700.617253-1-wander@redhat.com --- kernel/bpf/ringbuf.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index e20b90c36131..de3b681d1d13 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -29,7 +29,7 @@ struct bpf_ringbuf { u64 mask; struct page **pages; int nr_pages; - spinlock_t spinlock ____cacheline_aligned_in_smp; + raw_spinlock_t spinlock ____cacheline_aligned_in_smp; /* For user-space producer ring buffers, an atomic_t busy bit is used * to synchronize access to the ring buffers in the kernel, rather than * the spinlock that is used for kernel-producer ring buffers. This is @@ -173,7 +173,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) if (!rb) return NULL; - spin_lock_init(&rb->spinlock); + raw_spin_lock_init(&rb->spinlock); atomic_set(&rb->busy, 0); init_waitqueue_head(&rb->waitq); init_irq_work(&rb->work, bpf_ringbuf_notify); @@ -421,10 +421,10 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) cons_pos = smp_load_acquire(&rb->consumer_pos); if (in_nmi()) { - if (!spin_trylock_irqsave(&rb->spinlock, flags)) + if (!raw_spin_trylock_irqsave(&rb->spinlock, flags)) return NULL; } else { - spin_lock_irqsave(&rb->spinlock, flags); + raw_spin_lock_irqsave(&rb->spinlock, flags); } pend_pos = rb->pending_pos; @@ -450,7 +450,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) */ if (new_prod_pos - cons_pos > rb->mask || new_prod_pos - pend_pos > rb->mask) { - spin_unlock_irqrestore(&rb->spinlock, flags); + raw_spin_unlock_irqrestore(&rb->spinlock, flags); return NULL; } @@ -462,7 +462,7 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size) /* pairs with consumer's smp_load_acquire() */ smp_store_release(&rb->producer_pos, new_prod_pos); - spin_unlock_irqrestore(&rb->spinlock, flags); + raw_spin_unlock_irqrestore(&rb->spinlock, flags); return (void *)hdr + BPF_RINGBUF_HDR_SZ; } From e9bd9c498cb0f5843996dbe5cbce7a1836a83c70 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Tue, 24 Sep 2024 14:08:43 -0700 Subject: [PATCH 02/38] bpf: sync_linked_regs() must preserve subreg_def Range propagation must not affect subreg_def marks, otherwise the following example is rewritten by verifier incorrectly when BPF_F_TEST_RND_HI32 flag is set: 0: call bpf_ktime_get_ns call bpf_ktime_get_ns 1: r0 &= 0x7fffffff after verifier r0 &= 0x7fffffff 2: w1 = w0 rewrites w1 = w0 3: if w0 < 10 goto +0 --------------> r11 = 0x2f5674a6 (r) 4: r1 >>= 32 r11 <<= 32 (r) 5: r0 = r1 r1 |= r11 (r) 6: exit; if w0 < 0xa goto pc+0 r1 >>= 32 r0 = r1 exit (or zero extension of w1 at (2) is missing for architectures that require zero extension for upper register half). The following happens w/o this patch: - r0 is marked as not a subreg at (0); - w1 is marked as subreg at (2); - w1 subreg_def is overridden at (3) by copy_register_state(); - w1 is read at (5) but mark_insn_zext() does not mark (2) for zero extension, because w1 subreg_def is not set; - because of BPF_F_TEST_RND_HI32 flag verifier inserts random value for hi32 bits of (2) (marked (r)); - this random value is read at (5). Fixes: 75748837b7e5 ("bpf: Propagate scalar ranges through register assignments.") Reported-by: Lonial Con Signed-off-by: Lonial Con Signed-off-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Daniel Borkmann Closes: https://lore.kernel.org/bpf/7e2aa30a62d740db182c170fdd8f81c596df280d.camel@gmail.com Link: https://lore.kernel.org/bpf/20240924210844.1758441-1-eddyz87@gmail.com --- kernel/bpf/verifier.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9a7ed527e47e..434de48cd24b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -15326,8 +15326,12 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s continue; if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) || reg->off == known_reg->off) { + s32 saved_subreg_def = reg->subreg_def; + copy_register_state(reg, known_reg); + reg->subreg_def = saved_subreg_def; } else { + s32 saved_subreg_def = reg->subreg_def; s32 saved_off = reg->off; fake_reg.type = SCALAR_VALUE; @@ -15340,6 +15344,7 @@ static void sync_linked_regs(struct bpf_verifier_state *vstate, struct bpf_reg_s * otherwise another sync_linked_regs() will be incorrect. */ reg->off = saved_off; + reg->subreg_def = saved_subreg_def; scalar32_min_max_add(reg, &fake_reg); scalar_min_max_add(reg, &fake_reg); From a41b3828ec056a631ad22413d4560017fed5c3bd Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Tue, 24 Sep 2024 14:08:44 -0700 Subject: [PATCH 03/38] selftests/bpf: Verify that sync_linked_regs preserves subreg_def This test was added because of a bug in verifier.c:sync_linked_regs(), upon range propagation it destroyed subreg_def marks for registers. The test is written in a way to return an upper half of a register that is affected by range propagation and must have it's subreg_def preserved. This gives a return value of 0 and leads to undefined return value if subreg_def mark is not preserved. Signed-off-by: Eduard Zingerman Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20240924210844.1758441-2-eddyz87@gmail.com --- .../selftests/bpf/progs/verifier_scalar_ids.c | 67 +++++++++++++++++++ 1 file changed, 67 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c index 2ecf77b623e0..7c5e5e6d10eb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c +++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c @@ -760,4 +760,71 @@ __naked void two_old_ids_one_cur_id(void) : __clobber_all); } +SEC("socket") +/* Note the flag, see verifier.c:opt_subreg_zext_lo32_rnd_hi32() */ +__flag(BPF_F_TEST_RND_HI32) +__success +/* This test was added because of a bug in verifier.c:sync_linked_regs(), + * upon range propagation it destroyed subreg_def marks for registers. + * The subreg_def mark is used to decide whether zero extension instructions + * are needed when register is read. When BPF_F_TEST_RND_HI32 is set it + * also causes generation of statements to randomize upper halves of + * read registers. + * + * The test is written in a way to return an upper half of a register + * that is affected by range propagation and must have it's subreg_def + * preserved. This gives a return value of 0 and leads to undefined + * return value if subreg_def mark is not preserved. + */ +__retval(0) +/* Check that verifier believes r1/r0 are zero at exit */ +__log_level(2) +__msg("4: (77) r1 >>= 32 ; R1_w=0") +__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("6: (95) exit") +__msg("from 3 to 4") +__msg("4: (77) r1 >>= 32 ; R1_w=0") +__msg("5: (bf) r0 = r1 ; R0_w=0 R1_w=0") +__msg("6: (95) exit") +/* Verify that statements to randomize upper half of r1 had not been + * generated. + */ +__xlated("call unknown") +__xlated("r0 &= 2147483647") +__xlated("w1 = w0") +/* This is how disasm.c prints BPF_ZEXT_REG at the moment, x86 and arm + * are the only CI archs that do not need zero extension for subregs. + */ +#if !defined(__TARGET_ARCH_x86) && !defined(__TARGET_ARCH_arm64) +__xlated("w1 = w1") +#endif +__xlated("if w0 < 0xa goto pc+0") +__xlated("r1 >>= 32") +__xlated("r0 = r1") +__xlated("exit") +__naked void linked_regs_and_subreg_def(void) +{ + asm volatile ( + "call %[bpf_ktime_get_ns];" + /* make sure r0 is in 32-bit range, otherwise w1 = w0 won't + * assign same IDs to registers. + */ + "r0 &= 0x7fffffff;" + /* link w1 and w0 via ID */ + "w1 = w0;" + /* 'if' statement propagates range info from w0 to w1, + * but should not affect w1->subreg_def property. + */ + "if w0 < 10 goto +0;" + /* r1 is read here, on archs that require subreg zero + * extension this would cause zext patch generation. + */ + "r1 >>= 32;" + "r0 = r1;" + "exit;" + : + : __imm(bpf_ktime_get_ns) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; From 09d88791c7cd888d5195c84733caf9183dcfbd16 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Fri, 20 Sep 2024 14:56:24 +0200 Subject: [PATCH 04/38] bpf: Make sure internal and UAPI bpf_redirect flags don't overlap MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bpf_redirect_info is shared between the SKB and XDP redirect paths, and the two paths use the same numeric flag values in the ri->flags field (specifically, BPF_F_BROADCAST == BPF_F_NEXTHOP). This means that if skb bpf_redirect_neigh() is used with a non-NULL params argument and, subsequently, an XDP redirect is performed using the same bpf_redirect_info struct, the XDP path will get confused and end up crashing, which syzbot managed to trigger. With the stack-allocated bpf_redirect_info, the structure is no longer shared between the SKB and XDP paths, so the crash doesn't happen anymore. However, different code paths using identically-numbered flag values in the same struct field still seems like a bit of a mess, so this patch cleans that up by moving the flag definitions together and redefining the three flags in BPF_F_REDIRECT_INTERNAL to not overlap with the flags used for XDP. It also adds a BUILD_BUG_ON() check to make sure the overlap is not re-introduced by mistake. Fixes: e624d4ed4aa8 ("xdp: Extend xdp_redirect_map with broadcast support") Reported-by: syzbot+cca39e6e84a367a7e6f6@syzkaller.appspotmail.com Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Acked-by: Daniel Borkmann Closes: https://syzkaller.appspot.com/bug?extid=cca39e6e84a367a7e6f6 Link: https://lore.kernel.org/bpf/20240920125625.59465-1-toke@redhat.com --- include/uapi/linux/bpf.h | 13 +++++-------- net/core/filter.c | 8 +++++--- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c6cd7c7aeeee..e8241b320c6d 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6047,11 +6047,6 @@ enum { BPF_F_MARK_ENFORCE = (1ULL << 6), }; -/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ -enum { - BPF_F_INGRESS = (1ULL << 0), -}; - /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ enum { BPF_F_TUNINFO_IPV6 = (1ULL << 0), @@ -6198,10 +6193,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; -/* Flags for bpf_redirect_map helper */ +/* Flags for bpf_redirect and bpf_redirect_map helpers */ enum { - BPF_F_BROADCAST = (1ULL << 3), - BPF_F_EXCLUDE_INGRESS = (1ULL << 4), + BPF_F_INGRESS = (1ULL << 0), /* used for skb path */ + BPF_F_BROADCAST = (1ULL << 3), /* used for XDP path */ + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), /* used for XDP path */ +#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) }; #define __bpf_md_ptr(type, name) \ diff --git a/net/core/filter.c b/net/core/filter.c index cd3524cb326b..4e3f42cc6611 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2438,9 +2438,9 @@ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev, /* Internal, non-exposed redirect flags. */ enum { - BPF_F_NEIGH = (1ULL << 1), - BPF_F_PEER = (1ULL << 2), - BPF_F_NEXTHOP = (1ULL << 3), + BPF_F_NEIGH = (1ULL << 16), + BPF_F_PEER = (1ULL << 17), + BPF_F_NEXTHOP = (1ULL << 18), #define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP) }; @@ -2450,6 +2450,8 @@ BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) struct sk_buff *clone; int ret; + BUILD_BUG_ON(BPF_F_REDIRECT_INTERNAL & BPF_F_REDIRECT_FLAGS); + if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; From 3ed6be68913b2d56a35d30c67f83ba3d2f1998fc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 1 Oct 2024 21:41:05 +0200 Subject: [PATCH 05/38] bpf: Sync uapi bpf.h header to tools directory There is a delta between kernel UAPI bpf.h and tools UAPI bpf.h, thus sync them again. Signed-off-by: Daniel Borkmann --- tools/include/uapi/linux/bpf.h | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1fb3cb2636e6..e8241b320c6d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5519,11 +5519,12 @@ union bpf_attr { * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if * invalid arguments are passed. * - * void *bpf_kptr_xchg(void *map_value, void *ptr) + * void *bpf_kptr_xchg(void *dst, void *ptr) * Description - * Exchange kptr at pointer *map_value* with *ptr*, and return the - * old value. *ptr* can be NULL, otherwise it must be a referenced - * pointer which will be released when this helper is called. + * Exchange kptr at pointer *dst* with *ptr*, and return the old value. + * *dst* can be map value or local kptr. *ptr* can be NULL, otherwise + * it must be a referenced pointer which will be released when this helper + * is called. * Return * The old value of kptr (which can be NULL). The returned pointer * if not NULL, is a reference which must be released using its @@ -6046,11 +6047,6 @@ enum { BPF_F_MARK_ENFORCE = (1ULL << 6), }; -/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ -enum { - BPF_F_INGRESS = (1ULL << 0), -}; - /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ enum { BPF_F_TUNINFO_IPV6 = (1ULL << 0), @@ -6197,10 +6193,12 @@ enum { BPF_F_BPRM_SECUREEXEC = (1ULL << 0), }; -/* Flags for bpf_redirect_map helper */ +/* Flags for bpf_redirect and bpf_redirect_map helpers */ enum { - BPF_F_BROADCAST = (1ULL << 3), - BPF_F_EXCLUDE_INGRESS = (1ULL << 4), + BPF_F_INGRESS = (1ULL << 0), /* used for skb path */ + BPF_F_BROADCAST = (1ULL << 3), /* used for XDP path */ + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), /* used for XDP path */ +#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) }; #define __bpf_md_ptr(type, name) \ From ca9984c5f0ab3690d98b13937b2485a978c8dd73 Mon Sep 17 00:00:00 2001 From: Florian Kauer Date: Wed, 11 Sep 2024 10:41:18 +0200 Subject: [PATCH 06/38] bpf: devmap: provide rxq after redirect MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rxq contains a pointer to the device from where the redirect happened. Currently, the BPF program that was executed after a redirect via BPF_MAP_TYPE_DEVMAP* does not have it set. This is particularly bad since accessing ingress_ifindex, e.g. SEC("xdp") int prog(struct xdp_md *pkt) { return bpf_redirect_map(&dev_redirect_map, 0, 0); } SEC("xdp/devmap") int prog_after_redirect(struct xdp_md *pkt) { bpf_printk("ifindex %i", pkt->ingress_ifindex); return XDP_PASS; } depends on access to rxq, so a NULL pointer gets dereferenced: <1>[ 574.475170] BUG: kernel NULL pointer dereference, address: 0000000000000000 <1>[ 574.475188] #PF: supervisor read access in kernel mode <1>[ 574.475194] #PF: error_code(0x0000) - not-present page <6>[ 574.475199] PGD 0 P4D 0 <4>[ 574.475207] Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI <4>[ 574.475217] CPU: 4 UID: 0 PID: 217 Comm: kworker/4:1 Not tainted 6.11.0-rc5-reduced-00859-g780801200300 #23 <4>[ 574.475226] Hardware name: Intel(R) Client Systems NUC13ANHi7/NUC13ANBi7, BIOS ANRPL357.0026.2023.0314.1458 03/14/2023 <4>[ 574.475231] Workqueue: mld mld_ifc_work <4>[ 574.475247] RIP: 0010:bpf_prog_5e13354d9cf5018a_prog_after_redirect+0x17/0x3c <4>[ 574.475257] Code: cc cc cc cc cc cc cc 80 00 00 00 cc cc cc cc cc cc cc cc f3 0f 1e fa 0f 1f 44 00 00 66 90 55 48 89 e5 f3 0f 1e fa 48 8b 57 20 <48> 8b 52 00 8b 92 e0 00 00 00 48 bf f8 a6 d5 c4 5d a0 ff ff be 0b <4>[ 574.475263] RSP: 0018:ffffa62440280c98 EFLAGS: 00010206 <4>[ 574.475269] RAX: ffffa62440280cd8 RBX: 0000000000000001 RCX: 0000000000000000 <4>[ 574.475274] RDX: 0000000000000000 RSI: ffffa62440549048 RDI: ffffa62440280ce0 <4>[ 574.475278] RBP: ffffa62440280c98 R08: 0000000000000002 R09: 0000000000000001 <4>[ 574.475281] R10: ffffa05dc8b98000 R11: ffffa05f577fca40 R12: ffffa05dcab24000 <4>[ 574.475285] R13: ffffa62440280ce0 R14: ffffa62440549048 R15: ffffa62440549000 <4>[ 574.475289] FS: 0000000000000000(0000) GS:ffffa05f4f700000(0000) knlGS:0000000000000000 <4>[ 574.475294] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 574.475298] CR2: 0000000000000000 CR3: 000000025522e000 CR4: 0000000000f50ef0 <4>[ 574.475303] PKRU: 55555554 <4>[ 574.475306] Call Trace: <4>[ 574.475313] <4>[ 574.475318] ? __die+0x23/0x70 <4>[ 574.475329] ? page_fault_oops+0x180/0x4c0 <4>[ 574.475339] ? skb_pp_cow_data+0x34c/0x490 <4>[ 574.475346] ? kmem_cache_free+0x257/0x280 <4>[ 574.475357] ? exc_page_fault+0x67/0x150 <4>[ 574.475368] ? asm_exc_page_fault+0x26/0x30 <4>[ 574.475381] ? bpf_prog_5e13354d9cf5018a_prog_after_redirect+0x17/0x3c <4>[ 574.475386] bq_xmit_all+0x158/0x420 <4>[ 574.475397] __dev_flush+0x30/0x90 <4>[ 574.475407] veth_poll+0x216/0x250 [veth] <4>[ 574.475421] __napi_poll+0x28/0x1c0 <4>[ 574.475430] net_rx_action+0x32d/0x3a0 <4>[ 574.475441] handle_softirqs+0xcb/0x2c0 <4>[ 574.475451] do_softirq+0x40/0x60 <4>[ 574.475458] <4>[ 574.475461] <4>[ 574.475464] __local_bh_enable_ip+0x66/0x70 <4>[ 574.475471] __dev_queue_xmit+0x268/0xe40 <4>[ 574.475480] ? selinux_ip_postroute+0x213/0x420 <4>[ 574.475491] ? alloc_skb_with_frags+0x4a/0x1d0 <4>[ 574.475502] ip6_finish_output2+0x2be/0x640 <4>[ 574.475512] ? nf_hook_slow+0x42/0xf0 <4>[ 574.475521] ip6_finish_output+0x194/0x300 <4>[ 574.475529] ? __pfx_ip6_finish_output+0x10/0x10 <4>[ 574.475538] mld_sendpack+0x17c/0x240 <4>[ 574.475548] mld_ifc_work+0x192/0x410 <4>[ 574.475557] process_one_work+0x15d/0x380 <4>[ 574.475566] worker_thread+0x29d/0x3a0 <4>[ 574.475573] ? __pfx_worker_thread+0x10/0x10 <4>[ 574.475580] ? __pfx_worker_thread+0x10/0x10 <4>[ 574.475587] kthread+0xcd/0x100 <4>[ 574.475597] ? __pfx_kthread+0x10/0x10 <4>[ 574.475606] ret_from_fork+0x31/0x50 <4>[ 574.475615] ? __pfx_kthread+0x10/0x10 <4>[ 574.475623] ret_from_fork_asm+0x1a/0x30 <4>[ 574.475635] <4>[ 574.475637] Modules linked in: veth br_netfilter bridge stp llc iwlmvm x86_pkg_temp_thermal iwlwifi efivarfs nvme nvme_core <4>[ 574.475662] CR2: 0000000000000000 <4>[ 574.475668] ---[ end trace 0000000000000000 ]--- Therefore, provide it to the program by setting rxq properly. Fixes: cb261b594b41 ("bpf: Run devmap xdp_prog on flush instead of bulk enqueue") Reviewed-by: Toke Høiland-Jørgensen Signed-off-by: Florian Kauer Acked-by: Jakub Kicinski Link: https://lore.kernel.org/r/20240911-devel-koalo-fix-ingress-ifindex-v4-1-5c643ae10258@linutronix.de Signed-off-by: Martin KaFai Lau --- kernel/bpf/devmap.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 9e0e3b0a18e4..7878be18e9d2 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -333,9 +333,11 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, - struct net_device *dev) + struct net_device *tx_dev, + struct net_device *rx_dev) { - struct xdp_txq_info txq = { .dev = dev }; + struct xdp_txq_info txq = { .dev = tx_dev }; + struct xdp_rxq_info rxq = { .dev = rx_dev }; struct xdp_buff xdp; int i, nframes = 0; @@ -346,6 +348,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; + xdp.rxq = &rxq; act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { @@ -360,7 +363,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: - trace_xdp_exception(dev, xdp_prog, act); + trace_xdp_exception(tx_dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); @@ -388,7 +391,7 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) } if (bq->xdp_prog) { - to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev); + to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); if (!to_send) goto out; } From 49ebeb0c15e86548822a8fc8c5ac34c70709c1aa Mon Sep 17 00:00:00 2001 From: Florian Kauer Date: Wed, 11 Sep 2024 10:41:19 +0200 Subject: [PATCH 07/38] bpf: selftests: send packet to devmap redirect XDP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current xdp_devmap_attach test attaches a program that redirects to another program via devmap. It is, however, never executed, so do that to catch any bugs that might occur during execution. Also, execute the same for a veth pair so that we also cover the non-generic path. Warning: Running this without the bugfix in this series will likely crash your system. Signed-off-by: Florian Kauer Reviewed-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20240911-devel-koalo-fix-ingress-ifindex-v4-2-5c643ae10258@linutronix.de Signed-off-by: Martin KaFai Lau --- .../bpf/prog_tests/xdp_devmap_attach.c | 127 ++++++++++++++++-- .../bpf/progs/test_xdp_with_devmap_helpers.c | 2 +- 2 files changed, 119 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index ce6812558287..27ffed17d4be 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include +#include +#include #include #include "test_xdp_devmap_helpers.skel.h" @@ -8,30 +11,35 @@ #include "test_xdp_with_devmap_helpers.skel.h" #define IFINDEX_LO 1 +#define TEST_NS "devmap_attach_ns" static void test_xdp_with_devmap_helpers(void) { - struct test_xdp_with_devmap_helpers *skel; + struct test_xdp_with_devmap_helpers *skel = NULL; struct bpf_prog_info info = {}; struct bpf_devmap_val val = { .ifindex = IFINDEX_LO, }; __u32 len = sizeof(info); - int err, dm_fd, map_fd; + int err, dm_fd, dm_fd_redir, map_fd; + struct nstoken *nstoken = NULL; + char data[10] = {}; __u32 idx = 0; + SYS(out_close, "ip netns add %s", TEST_NS); + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto out_close; + SYS(out_close, "ip link set dev lo up"); skel = test_xdp_with_devmap_helpers__open_and_load(); if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) - return; - - dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); - if (!ASSERT_OK(err, "Generic attach of program with 8-byte devmap")) goto out_close; - err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); - ASSERT_OK(err, "XDP program detach"); + dm_fd_redir = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_xdp_attach(IFINDEX_LO, dm_fd_redir, XDP_FLAGS_SKB_MODE, NULL); + if (!ASSERT_OK(err, "Generic attach of program with 8-byte devmap")) + goto out_close; dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); map_fd = bpf_map__fd(skel->maps.dm_ports); @@ -47,6 +55,22 @@ static void test_xdp_with_devmap_helpers(void) ASSERT_OK(err, "Read devmap entry"); ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id"); + /* send a packet to trigger any potential bugs in there */ + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = 10, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(dm_fd_redir, &opts); + ASSERT_OK(err, "XDP test run"); + + /* wait for the packets to be flushed */ + kern_sync_rcu(); + + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + /* can not attach BPF_XDP_DEVMAP program to a device */ err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_DEVMAP program")) @@ -67,6 +91,8 @@ static void test_xdp_with_devmap_helpers(void) ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to devmap entry"); out_close: + close_netns(nstoken); + SYS_NOFAIL("ip netns del %s", TEST_NS); test_xdp_with_devmap_helpers__destroy(skel); } @@ -124,6 +150,86 @@ static void test_xdp_with_devmap_frags_helpers(void) test_xdp_with_devmap_frags_helpers__destroy(skel); } +static void test_xdp_with_devmap_helpers_veth(void) +{ + struct test_xdp_with_devmap_helpers *skel = NULL; + struct bpf_prog_info info = {}; + struct bpf_devmap_val val = {}; + struct nstoken *nstoken = NULL; + __u32 len = sizeof(info); + int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst; + char data[10] = {}; + __u32 idx = 0; + + SYS(out_close, "ip netns add %s", TEST_NS); + nstoken = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto out_close; + + SYS(out_close, "ip link add veth_src type veth peer name veth_dst"); + SYS(out_close, "ip link set dev veth_src up"); + SYS(out_close, "ip link set dev veth_dst up"); + + val.ifindex = if_nametoindex("veth_src"); + ifindex_dst = if_nametoindex("veth_dst"); + if (!ASSERT_NEQ(val.ifindex, 0, "val.ifindex") || + !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst")) + goto out_close; + + skel = test_xdp_with_devmap_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) + goto out_close; + + dm_fd_redir = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_xdp_attach(val.ifindex, dm_fd_redir, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "Attach of program with 8-byte devmap")) + goto out_close; + + dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); + map_fd = bpf_map__fd(skel->maps.dm_ports); + err = bpf_prog_get_info_by_fd(dm_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = dm_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add program to devmap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read devmap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id"); + + /* attach dummy to other side to enable reception */ + dm_fd = bpf_program__fd(skel->progs.xdp_dummy_prog); + err = bpf_xdp_attach(ifindex_dst, dm_fd, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "Attach of dummy XDP")) + goto out_close; + + /* send a packet to trigger any potential bugs in there */ + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = 10, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(dm_fd_redir, &opts); + ASSERT_OK(err, "XDP test run"); + + /* wait for the packets to be flushed */ + kern_sync_rcu(); + + err = bpf_xdp_detach(val.ifindex, XDP_FLAGS_DRV_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + + err = bpf_xdp_detach(ifindex_dst, XDP_FLAGS_DRV_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + +out_close: + close_netns(nstoken); + SYS_NOFAIL("ip netns del %s", TEST_NS); + test_xdp_with_devmap_helpers__destroy(skel); +} + void serial_test_xdp_devmap_attach(void) { if (test__start_subtest("DEVMAP with programs in entries")) @@ -134,4 +240,7 @@ void serial_test_xdp_devmap_attach(void) if (test__start_subtest("Verifier check of DEVMAP programs")) test_neg_xdp_devmap_helpers(); + + if (test__start_subtest("DEVMAP with programs in entries on veth")) + test_xdp_with_devmap_helpers_veth(); } diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c index 4139a14f9996..92b65a485d4a 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c @@ -12,7 +12,7 @@ struct { SEC("xdp") int xdp_redir_prog(struct xdp_md *ctx) { - return bpf_redirect_map(&dm_ports, 1, 0); + return bpf_redirect_map(&dm_ports, 0, 0); } /* invalid program on DEVMAP entry; From 45126b155e3b5201179cdc038504bf93a8ccd921 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 7 Oct 2024 18:09:58 +0200 Subject: [PATCH 08/38] bpf: Fix memory leak in bpf_core_apply We need to free specs properly. Fixes: 3d2786d65aaa ("bpf: correctly handle malformed BPF_CORE_TYPE_ID_LOCAL relos") Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20241007160958.607434-1-jolsa@kernel.org --- kernel/bpf/btf.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 75e4fe83c509..a05da5f43547 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -8961,6 +8961,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, if (!type) { bpf_log(ctx->log, "relo #%u: bad type id %u\n", relo_idx, relo->type_id); + kfree(specs); return -EINVAL; } From b24d7f0da6ef5a23456a301eaf51b170f961d4ae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= Date: Sat, 5 Oct 2024 02:06:28 +0200 Subject: [PATCH 09/38] bpf, lsm: Remove bpf_lsm_key_free hook MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The key_free LSM hook has been removed. Remove the corresponding BPF hook. Avoid warnings during the build: BTFIDS vmlinux WARN: resolve_btfids: unresolved symbol bpf_lsm_key_free Fixes: 5f8d28f6d7d5 ("lsm: infrastructure management of the key security blob") Signed-off-by: Thomas Weißschuh Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Acked-by: Jiri Olsa Link: https://lore.kernel.org/bpf/20241005-lsm-key_free-v1-1-42ea801dbd63@weissschuh.net --- kernel/bpf/bpf_lsm.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 6292ac5f9bd1..3bc61628ab25 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -339,10 +339,6 @@ BTF_ID(func, bpf_lsm_path_chmod) BTF_ID(func, bpf_lsm_path_chown) #endif /* CONFIG_SECURITY_PATH */ -#ifdef CONFIG_KEYS -BTF_ID(func, bpf_lsm_key_free) -#endif /* CONFIG_KEYS */ - BTF_ID(func, bpf_lsm_mmap_file) BTF_ID(func, bpf_lsm_netlink_send) BTF_ID(func, bpf_lsm_path_notify) From 797d73ee232dd1833dec4824bc53a22032e97c1c Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Tue, 8 Oct 2024 15:11:13 +0800 Subject: [PATCH 10/38] bpf: Check the remaining info_cnt before repeating btf fields When trying to repeat the btf fields for array of nested struct, it doesn't check the remaining info_cnt. The following splat will be reported when the value of ret * nelems is greater than BTF_FIELDS_MAX: ------------[ cut here ]------------ UBSAN: array-index-out-of-bounds in ../kernel/bpf/btf.c:3951:49 index 11 is out of range for type 'btf_field_info [11]' CPU: 6 UID: 0 PID: 411 Comm: test_progs ...... 6.11.0-rc4+ #1 Tainted: [O]=OOT_MODULE Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ... Call Trace: dump_stack_lvl+0x57/0x70 dump_stack+0x10/0x20 ubsan_epilogue+0x9/0x40 __ubsan_handle_out_of_bounds+0x6f/0x80 ? kallsyms_lookup_name+0x48/0xb0 btf_parse_fields+0x992/0xce0 map_create+0x591/0x770 __sys_bpf+0x229/0x2410 __x64_sys_bpf+0x1f/0x30 x64_sys_call+0x199/0x9f0 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 RIP: 0033:0x7fea56f2cc5d ...... ---[ end trace ]--- Fix it by checking the remaining info_cnt in btf_repeat_fields() before repeating the btf fields. Fixes: 64e8ee814819 ("bpf: look into the types of the fields of a struct type recursively.") Signed-off-by: Hou Tao Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20241008071114.3718177-2-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/btf.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index a05da5f43547..5cd1c7a23848 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3523,7 +3523,7 @@ static int btf_get_field_type(const struct btf *btf, const struct btf_type *var_ * (i + 1) * elem_size * where i is the repeat index and elem_size is the size of an element. */ -static int btf_repeat_fields(struct btf_field_info *info, +static int btf_repeat_fields(struct btf_field_info *info, int info_cnt, u32 field_cnt, u32 repeat_cnt, u32 elem_size) { u32 i, j; @@ -3543,6 +3543,12 @@ static int btf_repeat_fields(struct btf_field_info *info, } } + /* The type of struct size or variable size is u32, + * so the multiplication will not overflow. + */ + if (field_cnt * (repeat_cnt + 1) > info_cnt) + return -E2BIG; + cur = field_cnt; for (i = 0; i < repeat_cnt; i++) { memcpy(&info[cur], &info[0], field_cnt * sizeof(info[0])); @@ -3587,7 +3593,7 @@ static int btf_find_nested_struct(const struct btf *btf, const struct btf_type * info[i].off += off; if (nelems > 1) { - err = btf_repeat_fields(info, ret, nelems - 1, t->size); + err = btf_repeat_fields(info, info_cnt, ret, nelems - 1, t->size); if (err == 0) ret *= nelems; else @@ -3681,10 +3687,10 @@ static int btf_find_field_one(const struct btf *btf, if (ret == BTF_FIELD_IGNORE) return 0; - if (nelems > info_cnt) + if (!info_cnt) return -E2BIG; if (nelems > 1) { - ret = btf_repeat_fields(info, 1, nelems - 1, sz); + ret = btf_repeat_fields(info, info_cnt, 1, nelems - 1, sz); if (ret < 0) return ret; } From c456f08040589a5096481277c83168a4e7ae7ed7 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Tue, 8 Oct 2024 15:11:14 +0800 Subject: [PATCH 11/38] selftests/bpf: Add more test case for field flattening Add three success test cases to test the flattening of array of nested struct. For these three tests, the number of special fields in map is BTF_FIELDS_MAX, but the array is defined in structs with different nested level. Add one failure test case for the flattening as well. In the test case, the number of special fields in map is BTF_FIELDS_MAX + 1. It will make btf_parse_fields() in map_create() return -E2BIG, the creation of map will succeed, but the load of program will fail because the btf_record is invalid for the map. Signed-off-by: Hou Tao Acked-by: Eduard Zingerman Link: https://lore.kernel.org/r/20241008071114.3718177-3-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/prog_tests/cpumask.c | 1 + .../selftests/bpf/progs/cpumask_common.h | 5 ++ .../selftests/bpf/progs/cpumask_failure.c | 35 +++++++++ .../selftests/bpf/progs/cpumask_success.c | 78 ++++++++++++++++++- 4 files changed, 117 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c index 2570bd4b0cb2..e58a04654238 100644 --- a/tools/testing/selftests/bpf/prog_tests/cpumask.c +++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c @@ -23,6 +23,7 @@ static const char * const cpumask_success_testcases[] = { "test_global_mask_array_l2_rcu", "test_global_mask_nested_rcu", "test_global_mask_nested_deep_rcu", + "test_global_mask_nested_deep_array_rcu", "test_cpumask_weight", }; diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h index b979e91f55f0..4ece7873ba60 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_common.h +++ b/tools/testing/selftests/bpf/progs/cpumask_common.h @@ -7,6 +7,11 @@ #include "errno.h" #include +/* Should use BTF_FIELDS_MAX, but it is not always available in vmlinux.h, + * so use the hard-coded number as a workaround. + */ +#define CPUMASK_KPTR_FIELDS_MAX 11 + int err; #define private(name) SEC(".bss." #name) __attribute__((aligned(8))) diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c index a988d2823b52..b40b52548ffb 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_failure.c +++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c @@ -10,6 +10,21 @@ char _license[] SEC("license") = "GPL"; +struct kptr_nested_array_2 { + struct bpf_cpumask __kptr * mask; +}; + +struct kptr_nested_array_1 { + /* Make btf_parse_fields() in map_create() return -E2BIG */ + struct kptr_nested_array_2 d_2[CPUMASK_KPTR_FIELDS_MAX + 1]; +}; + +struct kptr_nested_array { + struct kptr_nested_array_1 d_1; +}; + +private(MASK_NESTED) static struct kptr_nested_array global_mask_nested_arr; + /* Prototype for all of the program trace events below: * * TRACE_EVENT(task_newtask, @@ -187,3 +202,23 @@ int BPF_PROG(test_global_mask_rcu_no_null_check, struct task_struct *task, u64 c return 0; } + +SEC("tp_btf/task_newtask") +__failure __msg("has no valid kptr") +int BPF_PROG(test_invalid_nested_array, struct task_struct *task, u64 clone_flags) +{ + struct bpf_cpumask *local, *prev; + + local = create_cpumask(); + if (!local) + return 0; + + prev = bpf_kptr_xchg(&global_mask_nested_arr.d_1.d_2[CPUMASK_KPTR_FIELDS_MAX].mask, local); + if (prev) { + bpf_cpumask_release(prev); + err = 3; + return 0; + } + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c index fd8106831c32..80ee469b0b60 100644 --- a/tools/testing/selftests/bpf/progs/cpumask_success.c +++ b/tools/testing/selftests/bpf/progs/cpumask_success.c @@ -31,11 +31,59 @@ struct kptr_nested_deep { struct kptr_nested_pair ptr_pairs[3]; }; +struct kptr_nested_deep_array_1_2 { + int dummy; + struct bpf_cpumask __kptr * mask[CPUMASK_KPTR_FIELDS_MAX]; +}; + +struct kptr_nested_deep_array_1_1 { + int dummy; + struct kptr_nested_deep_array_1_2 d_2; +}; + +struct kptr_nested_deep_array_1 { + long dummy; + struct kptr_nested_deep_array_1_1 d_1; +}; + +struct kptr_nested_deep_array_2_2 { + long dummy[2]; + struct bpf_cpumask __kptr * mask; +}; + +struct kptr_nested_deep_array_2_1 { + int dummy; + struct kptr_nested_deep_array_2_2 d_2[CPUMASK_KPTR_FIELDS_MAX]; +}; + +struct kptr_nested_deep_array_2 { + long dummy; + struct kptr_nested_deep_array_2_1 d_1; +}; + +struct kptr_nested_deep_array_3_2 { + long dummy[2]; + struct bpf_cpumask __kptr * mask; +}; + +struct kptr_nested_deep_array_3_1 { + int dummy; + struct kptr_nested_deep_array_3_2 d_2; +}; + +struct kptr_nested_deep_array_3 { + long dummy; + struct kptr_nested_deep_array_3_1 d_1[CPUMASK_KPTR_FIELDS_MAX]; +}; + private(MASK) static struct bpf_cpumask __kptr * global_mask_array[2]; private(MASK) static struct bpf_cpumask __kptr * global_mask_array_l2[2][1]; private(MASK) static struct bpf_cpumask __kptr * global_mask_array_one[1]; private(MASK) static struct kptr_nested global_mask_nested[2]; private(MASK_DEEP) static struct kptr_nested_deep global_mask_nested_deep; +private(MASK_1) static struct kptr_nested_deep_array_1 global_mask_nested_deep_array_1; +private(MASK_2) static struct kptr_nested_deep_array_2 global_mask_nested_deep_array_2; +private(MASK_3) static struct kptr_nested_deep_array_3 global_mask_nested_deep_array_3; static bool is_test_task(void) { @@ -543,12 +591,21 @@ static int _global_mask_array_rcu(struct bpf_cpumask **mask0, goto err_exit; } - /* [, NULL] */ - if (!*mask0 || *mask1) { + /* [, *] */ + if (!*mask0) { err = 2; goto err_exit; } + if (!mask1) + goto err_exit; + + /* [*, NULL] */ + if (*mask1) { + err = 3; + goto err_exit; + } + local = create_cpumask(); if (!local) { err = 9; @@ -631,6 +688,23 @@ int BPF_PROG(test_global_mask_nested_deep_rcu, struct task_struct *task, u64 clo return 0; } +SEC("tp_btf/task_newtask") +int BPF_PROG(test_global_mask_nested_deep_array_rcu, struct task_struct *task, u64 clone_flags) +{ + int i; + + for (i = 0; i < CPUMASK_KPTR_FIELDS_MAX; i++) + _global_mask_array_rcu(&global_mask_nested_deep_array_1.d_1.d_2.mask[i], NULL); + + for (i = 0; i < CPUMASK_KPTR_FIELDS_MAX; i++) + _global_mask_array_rcu(&global_mask_nested_deep_array_2.d_1.d_2[i].mask, NULL); + + for (i = 0; i < CPUMASK_KPTR_FIELDS_MAX; i++) + _global_mask_array_rcu(&global_mask_nested_deep_array_3.d_1[i].d_2.mask, NULL); + + return 0; +} + SEC("tp_btf/task_newtask") int BPF_PROG(test_cpumask_weight, struct task_struct *task, u64 clone_flags) { From 434247637c66e1be2bc71a9987d4c3f0d8672387 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Tue, 8 Oct 2024 17:07:35 -0400 Subject: [PATCH 12/38] bpf: use kvzmalloc to allocate BPF verifier environment The kzmalloc call in bpf_check can fail when memory is very fragmented, which in turn can lead to an OOM kill. Use kvzmalloc to fall back to vmalloc when memory is too fragmented to allocate an order 3 sized bpf verifier environment. Admittedly this is not a very common case, and only happens on systems where memory has already been squeezed close to the limit, but this does not seem like much of a hot path, and it's a simple enough fix. Signed-off-by: Rik van Riel Reviewed-by: Shakeel Butt Link: https://lore.kernel.org/r/20241008170735.16766766@imladris.surriel.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 434de48cd24b..633fd6da40c2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -22315,7 +22315,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 /* 'struct bpf_verifier_env' can be global, but since it's not small, * allocate/free it every time bpf_check() is called */ - env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); + env = kvzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; @@ -22551,6 +22551,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 mutex_unlock(&bpf_verifier_lock); vfree(env->insn_aux_data); err_free_env: - kfree(env); + kvfree(env); return ret; } From 4deecdd29cf29844c7bd164d72dc38d2e672f64e Mon Sep 17 00:00:00 2001 From: Tyrone Wu Date: Tue, 8 Oct 2024 16:43:11 +0000 Subject: [PATCH 13/38] bpf: fix unpopulated name_len field in perf_event link info Previously when retrieving `bpf_link_info.perf_event` for kprobe/uprobe/tracepoint, the `name_len` field was not populated by the kernel, leaving it to reflect the value initially set by the user. This behavior was inconsistent with how other input/output string buffer fields function (e.g. `raw_tracepoint.tp_name_len`). This patch fills `name_len` with the actual size of the string name. Fixes: 1b715e1b0ec5 ("bpf: Support ->fill_link_info for perf_event") Signed-off-by: Tyrone Wu Acked-by: Jiri Olsa Acked-by: Yafang Shao Link: https://lore.kernel.org/r/20241008164312.46269-1-wudevelops@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/syscall.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a8f1808a1ca5..8cfa7183d2ef 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3565,15 +3565,16 @@ static void bpf_perf_link_dealloc(struct bpf_link *link) } static int bpf_perf_link_fill_common(const struct perf_event *event, - char __user *uname, u32 ulen, + char __user *uname, u32 *ulenp, u64 *probe_offset, u64 *probe_addr, u32 *fd_type, unsigned long *missed) { const char *buf; - u32 prog_id; + u32 prog_id, ulen; size_t len; int err; + ulen = *ulenp; if (!ulen ^ !uname) return -EINVAL; @@ -3581,10 +3582,17 @@ static int bpf_perf_link_fill_common(const struct perf_event *event, probe_offset, probe_addr, missed); if (err) return err; - if (!uname) - return 0; + if (buf) { len = strlen(buf); + *ulenp = len + 1; + } else { + *ulenp = 1; + } + if (!uname) + return 0; + + if (buf) { err = bpf_copy_to_user(uname, buf, ulen, len); if (err) return err; @@ -3609,7 +3617,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); ulen = info->perf_event.kprobe.name_len; - err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, + err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, &type, &missed); if (err) return err; @@ -3617,7 +3625,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, info->perf_event.type = BPF_PERF_EVENT_KRETPROBE; else info->perf_event.type = BPF_PERF_EVENT_KPROBE; - + info->perf_event.kprobe.name_len = ulen; info->perf_event.kprobe.offset = offset; info->perf_event.kprobe.missed = missed; if (!kallsyms_show_value(current_cred())) @@ -3639,7 +3647,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; - err = bpf_perf_link_fill_common(event, uname, ulen, &offset, &addr, + err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, &type, NULL); if (err) return err; @@ -3648,6 +3656,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, info->perf_event.type = BPF_PERF_EVENT_URETPROBE; else info->perf_event.type = BPF_PERF_EVENT_UPROBE; + info->perf_event.uprobe.name_len = ulen; info->perf_event.uprobe.offset = offset; info->perf_event.uprobe.cookie = event->bpf_cookie; return 0; @@ -3673,12 +3682,18 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, { char __user *uname; u32 ulen; + int err; uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; + err = bpf_perf_link_fill_common(event, uname, &ulen, NULL, NULL, NULL, NULL); + if (err) + return err; + info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; + info->perf_event.tracepoint.name_len = ulen; info->perf_event.tracepoint.cookie = event->bpf_cookie; - return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL); + return 0; } static int bpf_perf_link_fill_perf_event(const struct perf_event *event, From 4538a38f654a1c292fe489a9b66179262bfed088 Mon Sep 17 00:00:00 2001 From: Tyrone Wu Date: Tue, 8 Oct 2024 16:43:12 +0000 Subject: [PATCH 14/38] selftests/bpf: fix perf_event link info name_len assertion Fix `name_len` field assertions in `bpf_link_info.perf_event` for kprobe/uprobe/tracepoint to validate correct name size instead of 0. Fixes: 23cf7aa539dc ("selftests/bpf: Add selftest for fill_link_info") Signed-off-by: Tyrone Wu Acked-by: Jiri Olsa Acked-by: Yafang Shao Link: https://lore.kernel.org/r/20241008164312.46269-2-wudevelops@gmail.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/fill_link_info.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index f3932941bbaa..745c5ada4c4b 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -67,8 +67,9 @@ static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long add ASSERT_EQ(info.perf_event.kprobe.cookie, PERF_EVENT_COOKIE, "kprobe_cookie"); + ASSERT_EQ(info.perf_event.kprobe.name_len, strlen(KPROBE_FUNC) + 1, + "name_len"); if (!info.perf_event.kprobe.func_name) { - ASSERT_EQ(info.perf_event.kprobe.name_len, 0, "name_len"); info.perf_event.kprobe.func_name = ptr_to_u64(&buf); info.perf_event.kprobe.name_len = sizeof(buf); goto again; @@ -79,8 +80,9 @@ static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long add ASSERT_EQ(err, 0, "cmp_kprobe_func_name"); break; case BPF_PERF_EVENT_TRACEPOINT: + ASSERT_EQ(info.perf_event.tracepoint.name_len, strlen(TP_NAME) + 1, + "name_len"); if (!info.perf_event.tracepoint.tp_name) { - ASSERT_EQ(info.perf_event.tracepoint.name_len, 0, "name_len"); info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf); info.perf_event.tracepoint.name_len = sizeof(buf); goto again; @@ -96,8 +98,9 @@ static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long add case BPF_PERF_EVENT_URETPROBE: ASSERT_EQ(info.perf_event.uprobe.offset, offset, "uprobe_offset"); + ASSERT_EQ(info.perf_event.uprobe.name_len, strlen(UPROBE_FILE) + 1, + "name_len"); if (!info.perf_event.uprobe.file_name) { - ASSERT_EQ(info.perf_event.uprobe.name_len, 0, "name_len"); info.perf_event.uprobe.file_name = ptr_to_u64(&buf); info.perf_event.uprobe.name_len = sizeof(buf); goto again; From 30a59cc79754fd9ff3f41b7ee2eb21da85988548 Mon Sep 17 00:00:00 2001 From: Pu Lehui Date: Tue, 8 Oct 2024 12:45:44 +0000 Subject: [PATCH 15/38] riscv, bpf: Fix possible infinite tailcall when CONFIG_CFI_CLANG is enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When CONFIG_CFI_CLANG is enabled, the number of prologue instructions skipped by tailcall needs to include the kcfi instruction, otherwise the TCC will be initialized every tailcall is called, which may result in infinite tailcalls. Fixes: e63985ecd226 ("bpf, riscv64/cfi: Support kCFI + BPF on riscv64") Signed-off-by: Pu Lehui Acked-by: Björn Töpel Link: https://lore.kernel.org/r/20241008124544.171161-1-pulehui@huaweicloud.com Signed-off-by: Alexei Starovoitov --- arch/riscv/net/bpf_jit_comp64.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 99f34409fb60..91bd5082c4d8 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -18,6 +18,7 @@ #define RV_MAX_REG_ARGS 8 #define RV_FENTRY_NINSNS 2 #define RV_FENTRY_NBYTES (RV_FENTRY_NINSNS * 4) +#define RV_KCFI_NINSNS (IS_ENABLED(CONFIG_CFI_CLANG) ? 1 : 0) /* imm that allows emit_imm to emit max count insns */ #define RV_MAX_COUNT_IMM 0x7FFF7FF7FF7FF7FF @@ -271,7 +272,8 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) if (!is_tail_call) emit_addiw(RV_REG_A0, RV_REG_A5, 0, ctx); emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA, - is_tail_call ? (RV_FENTRY_NINSNS + 1) * 4 : 0, /* skip reserved nops and TCC init */ + /* kcfi, fentry and TCC init insns will be skipped on tailcall */ + is_tail_call ? (RV_KCFI_NINSNS + RV_FENTRY_NINSNS + 1) * 4 : 0, ctx); } From 60f802e2d6e10df609a80962b13558b7455ab32b Mon Sep 17 00:00:00 2001 From: Tony Ambardar Date: Tue, 8 Oct 2024 16:12:32 -0700 Subject: [PATCH 16/38] selftests/bpf: Fix error compiling cgroup_ancestor.c with musl libc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Existing code calls connect() with a 'struct sockaddr_in6 *' argument where a 'struct sockaddr *' argument is declared, yielding compile errors when building for mips64el/musl-libc: In file included from cgroup_ancestor.c:3: cgroup_ancestor.c: In function 'send_datagram': cgroup_ancestor.c:38:38: error: passing argument 2 of 'connect' from incompatible pointer type [-Werror=incompatible-pointer-types] 38 | if (!ASSERT_OK(connect(sock, &addr, sizeof(addr)), "connect")) { | ^~~~~ | | | struct sockaddr_in6 * ./test_progs.h:343:29: note: in definition of macro 'ASSERT_OK' 343 | long long ___res = (res); \ | ^~~ In file included from .../netinet/in.h:10, from .../arpa/inet.h:9, from ./test_progs.h:17: .../sys/socket.h:386:19: note: expected 'const struct sockaddr *' but argument is of type 'struct sockaddr_in6 *' 386 | int connect (int, const struct sockaddr *, socklen_t); | ^~~~~~~~~~~~~~~~~~~~~~~ cc1: all warnings being treated as errors This only compiles because of a glibc extension allowing declaration of the argument as a "transparent union" which includes both types above. Explicitly cast the argument to allow compiling for both musl and glibc. Cc: Alexis Lothoré (eBPF Foundation) Fixes: f957c230e173 ("selftests/bpf: convert test_skb_cgroup_id_user to test_progs") Signed-off-by: Tony Ambardar Reviewed-by: Alexis Lothoré Link: https://lore.kernel.org/r/20241008231232.634047-1-tony.ambardar@gmail.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c b/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c index 9250a1e9f9af..3f9ffdf71343 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c @@ -35,7 +35,7 @@ static int send_datagram(void) if (!ASSERT_OK_FD(sock, "create socket")) return sock; - if (!ASSERT_OK(connect(sock, &addr, sizeof(addr)), "connect")) { + if (!ASSERT_OK(connect(sock, (struct sockaddr *)&addr, sizeof(addr)), "connect")) { close(sock); return -1; } From 6cb86a0fdece87e126323ec1bb19deb16a52aedf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Thu, 10 Oct 2024 15:27:07 +0200 Subject: [PATCH 17/38] bpf: fix kfunc btf caching for modules MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The verifier contains a cache for looking up module BTF objects when calling kfuncs defined in modules. This cache uses a 'struct bpf_kfunc_btf_tab', which contains a sorted list of BTF objects that were already seen in the current verifier run, and the BTF objects are looked up by the offset stored in the relocated call instruction using bsearch(). The first time a given offset is seen, the module BTF is loaded from the file descriptor passed in by libbpf, and stored into the cache. However, there's a bug in the code storing the new entry: it stores a pointer to the new cache entry, then calls sort() to keep the cache sorted for the next lookup using bsearch(), and then returns the entry that was just stored through the stored pointer. However, because sort() modifies the list of entries in place *by value*, the stored pointer may no longer point to the right entry, in which case the wrong BTF object will be returned. The end result of this is an intermittent bug where, if a BPF program calls two functions with the same signature in two different modules, the function from the wrong module may sometimes end up being called. Whether this happens depends on the order of the calls in the BPF program (as that affects whether sort() reorders the array of BTF objects), making it especially hard to track down. Simon, credited as reporter below, spent significant effort analysing and creating a reproducer for this issue. The reproducer is added as a selftest in a subsequent patch. The fix is straight forward: simply don't use the stored pointer after calling sort(). Since we already have an on-stack pointer to the BTF object itself at the point where the function return, just use that, and populate it from the cache entry in the branch where the lookup succeeds. Fixes: 2357672c54c3 ("bpf: Introduce BPF support for kernel module function calls") Reported-by: Simon Sundberg Acked-by: Jiri Olsa Acked-by: Kumar Kartikeya Dwivedi Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20241010-fix-kfunc-btf-caching-for-modules-v2-1-745af6c1af98@redhat.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 633fd6da40c2..bf9996ea34fe 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2750,10 +2750,16 @@ static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, b->module = mod; b->offset = offset; + /* sort() reorders entries by value, so b may no longer point + * to the right entry after this + */ sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), kfunc_btf_cmp_by_off, NULL); + } else { + btf = b->btf; } - return b->btf; + + return btf; } void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) From 4192bb294f80928bc2257c7a2ff6c86a27de6807 Mon Sep 17 00:00:00 2001 From: Simon Sundberg Date: Thu, 10 Oct 2024 15:27:08 +0200 Subject: [PATCH 18/38] selftests/bpf: Provide a generic [un]load_module helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Generalize the previous [un]load_bpf_testmod() helpers (in testing_helpers.c) to the more generic [un]load_module(), which can load an arbitrary kernel module by name. This allows future selftests to more easily load custom kernel modules other than bpf_testmod.ko. Refactor [un]load_bpf_testmod() to wrap this new helper. Signed-off-by: Simon Sundberg Acked-by: Jiri Olsa Acked-by: Kumar Kartikeya Dwivedi Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20241010-fix-kfunc-btf-caching-for-modules-v2-2-745af6c1af98@redhat.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/testing_helpers.c | 34 ++++++++++++------- tools/testing/selftests/bpf/testing_helpers.h | 2 ++ 2 files changed, 24 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index d3c3c3a24150..5e9f16683be5 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -367,7 +367,7 @@ int delete_module(const char *name, int flags) return syscall(__NR_delete_module, name, flags); } -int unload_bpf_testmod(bool verbose) +int unload_module(const char *name, bool verbose) { int ret, cnt = 0; @@ -375,11 +375,11 @@ int unload_bpf_testmod(bool verbose) fprintf(stdout, "Failed to trigger kernel-side RCU sync!\n"); for (;;) { - ret = delete_module("bpf_testmod", 0); + ret = delete_module(name, 0); if (!ret || errno != EAGAIN) break; if (++cnt > 10000) { - fprintf(stdout, "Unload of bpf_testmod timed out\n"); + fprintf(stdout, "Unload of %s timed out\n", name); break; } usleep(100); @@ -388,41 +388,51 @@ int unload_bpf_testmod(bool verbose) if (ret) { if (errno == ENOENT) { if (verbose) - fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); + fprintf(stdout, "%s.ko is already unloaded.\n", name); return -1; } - fprintf(stdout, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); + fprintf(stdout, "Failed to unload %s.ko from kernel: %d\n", name, -errno); return -1; } if (verbose) - fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); + fprintf(stdout, "Successfully unloaded %s.ko.\n", name); return 0; } -int load_bpf_testmod(bool verbose) +int load_module(const char *path, bool verbose) { int fd; if (verbose) - fprintf(stdout, "Loading bpf_testmod.ko...\n"); + fprintf(stdout, "Loading %s...\n", path); - fd = open("bpf_testmod.ko", O_RDONLY); + fd = open(path, O_RDONLY); if (fd < 0) { - fprintf(stdout, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); + fprintf(stdout, "Can't find %s kernel module: %d\n", path, -errno); return -ENOENT; } if (finit_module(fd, "", 0)) { - fprintf(stdout, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); + fprintf(stdout, "Failed to load %s into the kernel: %d\n", path, -errno); close(fd); return -EINVAL; } close(fd); if (verbose) - fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); + fprintf(stdout, "Successfully loaded %s.\n", path); return 0; } +int unload_bpf_testmod(bool verbose) +{ + return unload_module("bpf_testmod", verbose); +} + +int load_bpf_testmod(bool verbose) +{ + return load_module("bpf_testmod.ko", verbose); +} + /* * Trigger synchronize_rcu() in kernel. */ diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h index d55f6ab12433..46d7f7089f63 100644 --- a/tools/testing/selftests/bpf/testing_helpers.h +++ b/tools/testing/selftests/bpf/testing_helpers.h @@ -38,6 +38,8 @@ int unload_bpf_testmod(bool verbose); int kern_sync_rcu(void); int finit_module(int fd, const char *param_values, int flags); int delete_module(const char *name, int flags); +int load_module(const char *path, bool verbose); +int unload_module(const char *name, bool verbose); static inline __u64 get_time_ns(void) { From f91b256644ea6f7628580029c5a223573f55d98c Mon Sep 17 00:00:00 2001 From: Simon Sundberg Date: Thu, 10 Oct 2024 15:27:09 +0200 Subject: [PATCH 19/38] selftests/bpf: Add test for kfunc module order MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a test case for kfuncs from multiple external modules, checking that the correct kfuncs are called regardless of which order they're called in. Specifically, check that calling the kfuncs in an order different from the one the modules' BTF are loaded in works. Signed-off-by: Simon Sundberg Acked-by: Kumar Kartikeya Dwivedi Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20241010-fix-kfunc-btf-caching-for-modules-v2-3-745af6c1af98@redhat.com Signed-off-by: Alexei Starovoitov --- tools/testing/selftests/bpf/Makefile | 20 ++++++- .../bpf/bpf_test_modorder_x/Makefile | 19 +++++++ .../bpf_test_modorder_x/bpf_test_modorder_x.c | 39 +++++++++++++ .../bpf/bpf_test_modorder_y/Makefile | 19 +++++++ .../bpf_test_modorder_y/bpf_test_modorder_y.c | 39 +++++++++++++ .../bpf/prog_tests/kfunc_module_order.c | 55 +++++++++++++++++++ .../selftests/bpf/progs/kfunc_module_order.c | 30 ++++++++++ 7 files changed, 220 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile create mode 100644 tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c create mode 100644 tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile create mode 100644 tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c create mode 100644 tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c create mode 100644 tools/testing/selftests/bpf/progs/kfunc_module_order.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index f04af11df8eb..6f9838a5dcc9 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -157,7 +157,8 @@ TEST_GEN_PROGS_EXTENDED = \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ - xdp_features bpf_test_no_cfi.ko + xdp_features bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ + bpf_test_modorder_y.ko TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi @@ -303,6 +304,19 @@ $(OUTPUT)/bpf_test_no_cfi.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_te $(Q)$(MAKE) $(submake_extras) RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) -C bpf_test_no_cfi $(Q)cp bpf_test_no_cfi/bpf_test_no_cfi.ko $@ +$(OUTPUT)/bpf_test_modorder_x.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_modorder_x/Makefile bpf_test_modorder_x/*.[ch]) + $(call msg,MOD,,$@) + $(Q)$(RM) bpf_test_modorder_x/bpf_test_modorder_x.ko # force re-compilation + $(Q)$(MAKE) $(submake_extras) RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) -C bpf_test_modorder_x + $(Q)cp bpf_test_modorder_x/bpf_test_modorder_x.ko $@ + +$(OUTPUT)/bpf_test_modorder_y.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_modorder_y/Makefile bpf_test_modorder_y/*.[ch]) + $(call msg,MOD,,$@) + $(Q)$(RM) bpf_test_modorder_y/bpf_test_modorder_y.ko # force re-compilation + $(Q)$(MAKE) $(submake_extras) RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) -C bpf_test_modorder_y + $(Q)cp bpf_test_modorder_y/bpf_test_modorder_y.ko $@ + + DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool ifneq ($(CROSS_COMPILE),) CROSS_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool @@ -722,6 +736,8 @@ TRUNNER_EXTRA_SOURCES := test_progs.c \ ip_check_defrag_frags.h TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ $(OUTPUT)/bpf_test_no_cfi.ko \ + $(OUTPUT)/bpf_test_modorder_x.ko \ + $(OUTPUT)/bpf_test_modorder_y.ko \ $(OUTPUT)/liburandom_read.so \ $(OUTPUT)/xdp_synproxy \ $(OUTPUT)/sign-file \ @@ -856,6 +872,8 @@ EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ $(addprefix $(OUTPUT)/,*.o *.d *.skel.h *.lskel.h *.subskel.h \ no_alu32 cpuv4 bpf_gcc bpf_testmod.ko \ bpf_test_no_cfi.ko \ + bpf_test_modorder_x.ko \ + bpf_test_modorder_y.ko \ liburandom_read.so) \ $(OUTPUT)/FEATURE-DUMP.selftests diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile b/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile new file mode 100644 index 000000000000..40b25b98ad1b --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile @@ -0,0 +1,19 @@ +BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = bpf_test_modorder_x.ko + +obj-m += bpf_test_modorder_x.o + +all: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean + diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c b/tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c new file mode 100644 index 000000000000..0cc747fa912f --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_test_modorder_retx(void) +{ + return 'x'; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(bpf_test_modorder_kfunc_x_ids) +BTF_ID_FLAGS(func, bpf_test_modorder_retx); +BTF_KFUNCS_END(bpf_test_modorder_kfunc_x_ids) + +static const struct btf_kfunc_id_set bpf_test_modorder_x_set = { + .owner = THIS_MODULE, + .set = &bpf_test_modorder_kfunc_x_ids, +}; + +static int __init bpf_test_modorder_x_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, + &bpf_test_modorder_x_set); +} + +static void __exit bpf_test_modorder_x_exit(void) +{ +} + +module_init(bpf_test_modorder_x_init); +module_exit(bpf_test_modorder_x_exit); + +MODULE_DESCRIPTION("BPF selftest ordertest module X"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile b/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile new file mode 100644 index 000000000000..52c3ab9d84e2 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile @@ -0,0 +1,19 @@ +BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = bpf_test_modorder_y.ko + +obj-m += bpf_test_modorder_y.o + +all: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean + diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c b/tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c new file mode 100644 index 000000000000..c627ee085d13 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_test_modorder_rety(void) +{ + return 'y'; +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(bpf_test_modorder_kfunc_y_ids) +BTF_ID_FLAGS(func, bpf_test_modorder_rety); +BTF_KFUNCS_END(bpf_test_modorder_kfunc_y_ids) + +static const struct btf_kfunc_id_set bpf_test_modorder_y_set = { + .owner = THIS_MODULE, + .set = &bpf_test_modorder_kfunc_y_ids, +}; + +static int __init bpf_test_modorder_y_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, + &bpf_test_modorder_y_set); +} + +static void __exit bpf_test_modorder_y_exit(void) +{ +} + +module_init(bpf_test_modorder_y_init); +module_exit(bpf_test_modorder_y_exit); + +MODULE_DESCRIPTION("BPF selftest ordertest module Y"); +MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c b/tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c new file mode 100644 index 000000000000..48c0560d398e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include + +#include "kfunc_module_order.skel.h" + +static int test_run_prog(const struct bpf_program *prog, + struct bpf_test_run_opts *opts) +{ + int err; + + err = bpf_prog_test_run_opts(bpf_program__fd(prog), opts); + if (!ASSERT_OK(err, "bpf_prog_test_run_opts")) + return err; + + if (!ASSERT_EQ((int)opts->retval, 0, bpf_program__name(prog))) + return -EINVAL; + + return 0; +} + +void test_kfunc_module_order(void) +{ + struct kfunc_module_order *skel; + char pkt_data[64] = {}; + int err = 0; + + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, test_opts, .data_in = pkt_data, + .data_size_in = sizeof(pkt_data)); + + err = load_module("bpf_test_modorder_x.ko", + env_verbosity > VERBOSE_NONE); + if (!ASSERT_OK(err, "load bpf_test_modorder_x.ko")) + return; + + err = load_module("bpf_test_modorder_y.ko", + env_verbosity > VERBOSE_NONE); + if (!ASSERT_OK(err, "load bpf_test_modorder_y.ko")) + goto exit_modx; + + skel = kfunc_module_order__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kfunc_module_order__open_and_load()")) { + err = -EINVAL; + goto exit_mods; + } + + test_run_prog(skel->progs.call_kfunc_xy, &test_opts); + test_run_prog(skel->progs.call_kfunc_yx, &test_opts); + + kfunc_module_order__destroy(skel); +exit_mods: + unload_module("bpf_test_modorder_y", env_verbosity > VERBOSE_NONE); +exit_modx: + unload_module("bpf_test_modorder_x", env_verbosity > VERBOSE_NONE); +} diff --git a/tools/testing/selftests/bpf/progs/kfunc_module_order.c b/tools/testing/selftests/bpf/progs/kfunc_module_order.c new file mode 100644 index 000000000000..76003d04c95f --- /dev/null +++ b/tools/testing/selftests/bpf/progs/kfunc_module_order.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include + +extern int bpf_test_modorder_retx(void) __ksym; +extern int bpf_test_modorder_rety(void) __ksym; + +SEC("classifier") +int call_kfunc_xy(struct __sk_buff *skb) +{ + int ret1, ret2; + + ret1 = bpf_test_modorder_retx(); + ret2 = bpf_test_modorder_rety(); + + return ret1 == 'x' && ret2 == 'y' ? 0 : -1; +} + +SEC("classifier") +int call_kfunc_yx(struct __sk_buff *skb) +{ + int ret1, ret2; + + ret1 = bpf_test_modorder_rety(); + ret2 = bpf_test_modorder_retx(); + + return ret1 == 'y' && ret2 == 'x' ? 0 : -1; +} + +char _license[] SEC("license") = "GPL"; From fd526e121c4d6f71aed82d21a8b8277b03e60b43 Mon Sep 17 00:00:00 2001 From: Tony Ambardar Date: Tue, 8 Oct 2024 21:07:20 -0700 Subject: [PATCH 20/38] selftests/bpf: Fix cross-compiling urandom_read Linking of urandom_read and liburandom_read.so prefers LLVM's 'ld.lld' but falls back to using 'ld' if unsupported. However, this fallback discards any existing makefile macro for LD and can break cross-compilation. Fix by changing the fallback to use the target linker $(LD), passed via '-fuse-ld=' using an absolute path rather than a linker "flavour". Fixes: 08c79c9cd67f ("selftests/bpf: Don't force lld on non-x86 architectures") Signed-off-by: Tony Ambardar Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241009040720.635260-1-tony.ambardar@gmail.com --- tools/testing/selftests/bpf/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 6f9838a5dcc9..75016962f795 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -264,7 +264,7 @@ $(OUTPUT)/%:%.c ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 riscv)) LLD := lld else -LLD := ld +LLD := $(shell command -v $(LD)) endif # Filter out -static for liburandom_read.so and its dependent targets so that static builds From ad6b5b6ea9b764018249285a4fe0a2226bef4caa Mon Sep 17 00:00:00 2001 From: Tyrone Wu Date: Fri, 11 Oct 2024 00:08:02 +0000 Subject: [PATCH 21/38] bpf: Fix unpopulated path_size when uprobe_multi fields unset Previously when retrieving `bpf_link_info.uprobe_multi` with `path` and `path_size` fields unset, the `path_size` field is not populated (remains 0). This behavior was inconsistent with how other input/output string buffer fields work, as the field should be populated in cases when: - both buffer and length are set (currently works as expected) - both buffer and length are unset (not working as expected) This patch now fills the `path_size` field when `path` and `path_size` are unset. Fixes: e56fdbfb06e2 ("bpf: Add link_info support for uprobe multi link") Signed-off-by: Tyrone Wu Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241011000803.681190-1-wudevelops@gmail.com --- kernel/trace/bpf_trace.c | 36 +++++++++++++++++------------------- 1 file changed, 17 insertions(+), 19 deletions(-) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a582cd25ca87..3bd402fa62a4 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3133,7 +3133,8 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link, struct bpf_uprobe_multi_link *umulti_link; u32 ucount = info->uprobe_multi.count; int err = 0, i; - long left; + char *p, *buf; + long left = 0; if (!upath ^ !upath_size) return -EINVAL; @@ -3147,26 +3148,23 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link, info->uprobe_multi.pid = umulti_link->task ? task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0; - if (upath) { - char *p, *buf; - - upath_size = min_t(u32, upath_size, PATH_MAX); - - buf = kmalloc(upath_size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - p = d_path(&umulti_link->path, buf, upath_size); - if (IS_ERR(p)) { - kfree(buf); - return PTR_ERR(p); - } - upath_size = buf + upath_size - p; - left = copy_to_user(upath, p, upath_size); + upath_size = upath_size ? min_t(u32, upath_size, PATH_MAX) : PATH_MAX; + buf = kmalloc(upath_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + p = d_path(&umulti_link->path, buf, upath_size); + if (IS_ERR(p)) { kfree(buf); - if (left) - return -EFAULT; - info->uprobe_multi.path_size = upath_size; + return PTR_ERR(p); } + upath_size = buf + upath_size - p; + + if (upath) + left = copy_to_user(upath, p, upath_size); + kfree(buf); + if (left) + return -EFAULT; + info->uprobe_multi.path_size = upath_size; if (!uoffsets && !ucookies && !uref_ctr_offsets) return 0; From b836cbdf3b81a4a22b3452186efa2e5105a77e10 Mon Sep 17 00:00:00 2001 From: Tyrone Wu Date: Fri, 11 Oct 2024 00:08:03 +0000 Subject: [PATCH 22/38] selftests/bpf: Assert link info uprobe_multi count & path_size if unset Add assertions in `bpf_link_info.uprobe_multi` test to verify that `count` and `path_size` fields are correctly populated when the fields are unset. This tests a previous bug where the `path_size` field was not populated when `path` and `path_size` were unset. Signed-off-by: Tyrone Wu Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241011000803.681190-2-wudevelops@gmail.com --- tools/testing/selftests/bpf/prog_tests/fill_link_info.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index 745c5ada4c4b..d50cbd8040d4 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -420,6 +420,15 @@ verify_umulti_link_info(int fd, bool retprobe, __u64 *offsets, if (!ASSERT_NEQ(err, -1, "readlink")) return -1; + memset(&info, 0, sizeof(info)); + err = bpf_link_get_info_by_fd(fd, &info, &len); + if (!ASSERT_OK(err, "bpf_link_get_info_by_fd")) + return -1; + + ASSERT_EQ(info.uprobe_multi.count, 3, "info.uprobe_multi.count"); + ASSERT_EQ(info.uprobe_multi.path_size, strlen(path) + 1, + "info.uprobe_multi.path_size"); + for (bit = 0; bit < 8; bit++) { memset(&info, 0, sizeof(info)); info.uprobe_multi.path = ptr_to_u64(path_buf); From ae67b9fb8c4e981e929a665dcaa070f4b05ebdb4 Mon Sep 17 00:00:00 2001 From: Dimitar Kanaliev Date: Mon, 14 Oct 2024 15:11:53 +0300 Subject: [PATCH 23/38] bpf: Fix truncation bug in coerce_reg_to_size_sx() coerce_reg_to_size_sx() updates the register state after a sign-extension operation. However, there's a bug in the assignment order of the unsigned min/max values, leading to incorrect truncation: 0: (85) call bpf_get_prandom_u32#7 ; R0_w=scalar() 1: (57) r0 &= 1 ; R0_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=1,var_off=(0x0; 0x1)) 2: (07) r0 += 254 ; R0_w=scalar(smin=umin=smin32=umin32=254,smax=umax=smax32=umax32=255,var_off=(0xfe; 0x1)) 3: (bf) r0 = (s8)r0 ; R0_w=scalar(smin=smin32=-2,smax=smax32=-1,umin=umin32=0xfffffffe,umax=0xffffffff,var_off=(0xfffffffffffffffe; 0x1)) In the current implementation, the unsigned 32-bit min/max values (u32_min_value and u32_max_value) are assigned directly from the 64-bit signed min/max values (s64_min and s64_max): reg->umin_value = reg->u32_min_value = s64_min; reg->umax_value = reg->u32_max_value = s64_max; Due to the chain assigmnent, this is equivalent to: reg->u32_min_value = s64_min; // Unintended truncation reg->umin_value = reg->u32_min_value; reg->u32_max_value = s64_max; // Unintended truncation reg->umax_value = reg->u32_max_value; Fixes: 1f9a1ea821ff ("bpf: Support new sign-extension load insns") Reported-by: Shung-Hsi Yu Reported-by: Zac Ecob Signed-off-by: Dimitar Kanaliev Acked-by: Yonghong Song Reviewed-by: Shung-Hsi Yu Link: https://lore.kernel.org/r/20241014121155.92887-2-dimitar.kanaliev@siteground.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bf9996ea34fe..a8a0b6e4110e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6339,10 +6339,10 @@ static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size) /* both of s64_max/s64_min positive or negative */ if ((s64_max >= 0) == (s64_min >= 0)) { - reg->smin_value = reg->s32_min_value = s64_min; - reg->smax_value = reg->s32_max_value = s64_max; - reg->umin_value = reg->u32_min_value = s64_min; - reg->umax_value = reg->u32_max_value = s64_max; + reg->s32_min_value = reg->smin_value = s64_min; + reg->s32_max_value = reg->smax_value = s64_max; + reg->u32_min_value = reg->umin_value = s64_min; + reg->u32_max_value = reg->umax_value = s64_max; reg->var_off = tnum_range(s64_min, s64_max); return; } From 61f506eacc77a9dad510fce92477af72be82c89d Mon Sep 17 00:00:00 2001 From: Dimitar Kanaliev Date: Mon, 14 Oct 2024 15:11:54 +0300 Subject: [PATCH 24/38] selftests/bpf: Add test for truncation after sign extension in coerce_reg_to_size_sx() Add test that checks whether unsigned ranges deduced by the verifier for sign extension instruction is correct. Without previous patch that fixes truncation in coerce_reg_to_size_sx() this test fails. Acked-by: Shung-Hsi Yu Signed-off-by: Dimitar Kanaliev Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20241014121155.92887-3-dimitar.kanaliev@siteground.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/verifier_movsx.c | 20 +++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c index 028ec855587b..0cb879c609c5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_movsx.c +++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c @@ -287,6 +287,26 @@ l0_%=: \ : __clobber_all); } +SEC("socket") +__description("MOV64SX, S8, unsigned range_check") +__success __retval(0) +__naked void mov64sx_s8_range_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + r0 &= 0x1; \ + r0 += 0xfe; \ + r0 = (s8)r0; \ + if r0 < 0xfffffffffffffffe goto label_%=; \ + r0 = 0; \ + exit; \ +label_%=: \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + #else SEC("socket") From 35ccd576a23ce495b4064f4a3445626de790cd23 Mon Sep 17 00:00:00 2001 From: Dimitar Kanaliev Date: Mon, 14 Oct 2024 15:11:55 +0300 Subject: [PATCH 25/38] selftests/bpf: Add test for sign extension in coerce_subreg_to_size_sx() Add a test for unsigned ranges after signed extension instruction. This case isn't currently covered by existing tests in verifier_movsx.c. Acked-by: Shung-Hsi Yu Signed-off-by: Dimitar Kanaliev Acked-by: Yonghong Song Link: https://lore.kernel.org/r/20241014121155.92887-4-dimitar.kanaliev@siteground.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/progs/verifier_movsx.c | 20 +++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c index 0cb879c609c5..994bbc346d25 100644 --- a/tools/testing/selftests/bpf/progs/verifier_movsx.c +++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c @@ -307,6 +307,26 @@ label_%=: \ : __clobber_all); } +SEC("socket") +__description("MOV32SX, S8, unsigned range_check") +__success __retval(0) +__naked void mov32sx_s8_range_check(void) +{ + asm volatile (" \ + call %[bpf_get_prandom_u32]; \ + w0 &= 0x1; \ + w0 += 0xfe; \ + w0 = (s8)w0; \ + if w0 < 0xfffffffe goto label_%=; \ + r0 = 0; \ + exit; \ +label_%=: \ + exit; \ + " : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + #else SEC("socket") From 92f3715e1eba1d41e55be06159dc3d856b18326d Mon Sep 17 00:00:00 2001 From: Tyrone Wu Date: Fri, 11 Oct 2024 19:32:51 +0000 Subject: [PATCH 26/38] bpf: Fix link info netfilter flags to populate defrag flag This fix correctly populates the `bpf_link_info.netfilter.flags` field when user passes the `BPF_F_NETFILTER_IP_DEFRAG` flag. Fixes: 91721c2d02d3 ("netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG in netfilter link") Signed-off-by: Tyrone Wu Signed-off-by: Daniel Borkmann Acked-by: Florian Westphal Cc: Daniel Xu Link: https://lore.kernel.org/bpf/20241011193252.178997-1-wudevelops@gmail.com --- net/netfilter/nf_bpf_link.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index 5257d5e7eb09..797fe8a9971e 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -150,11 +150,12 @@ static int bpf_nf_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_nf_link *nf_link = container_of(link, struct bpf_nf_link, link); + const struct nf_defrag_hook *hook = nf_link->defrag_hook; info->netfilter.pf = nf_link->hook_ops.pf; info->netfilter.hooknum = nf_link->hook_ops.hooknum; info->netfilter.priority = nf_link->hook_ops.priority; - info->netfilter.flags = 0; + info->netfilter.flags = hook ? BPF_F_NETFILTER_IP_DEFRAG : 0; return 0; } From 2aa587fd6659baef8722ccfb1d1d13d18e105059 Mon Sep 17 00:00:00 2001 From: Tyrone Wu Date: Fri, 11 Oct 2024 19:32:52 +0000 Subject: [PATCH 27/38] selftests/bpf: Add asserts for netfilter link info Add assertions/tests to verify `bpf_link_info` fields for netfilter link are correctly populated. Signed-off-by: Tyrone Wu Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20241011193252.178997-2-wudevelops@gmail.com --- .../bpf/prog_tests/netfilter_link_attach.c | 42 ++++++++++++++++++- 1 file changed, 40 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c index 4297a2a4cb11..2f52fa2641ba 100644 --- a/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c @@ -26,10 +26,43 @@ static const struct nf_link_test nf_hook_link_tests[] = { { .pf = NFPROTO_INET, .priority = 1, .name = "invalid-inet-not-supported", }, - { .pf = NFPROTO_IPV4, .priority = -10000, .expect_success = true, .name = "attach ipv4", }, - { .pf = NFPROTO_IPV6, .priority = 10001, .expect_success = true, .name = "attach ipv6", }, + { + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = -10000, + .flags = 0, + .expect_success = true, + .name = "attach ipv4", + }, + { + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_FORWARD, + .priority = 10001, + .flags = BPF_F_NETFILTER_IP_DEFRAG, + .expect_success = true, + .name = "attach ipv6", + }, }; +static void verify_netfilter_link_info(struct bpf_link *link, const struct nf_link_test nf_expected) +{ + struct bpf_link_info info; + __u32 len = sizeof(info); + int err, fd; + + memset(&info, 0, len); + + fd = bpf_link__fd(link); + err = bpf_link_get_info_by_fd(fd, &info, &len); + ASSERT_OK(err, "get_link_info"); + + ASSERT_EQ(info.type, BPF_LINK_TYPE_NETFILTER, "info link type"); + ASSERT_EQ(info.netfilter.pf, nf_expected.pf, "info nf protocol family"); + ASSERT_EQ(info.netfilter.hooknum, nf_expected.hooknum, "info nf hooknum"); + ASSERT_EQ(info.netfilter.priority, nf_expected.priority, "info nf priority"); + ASSERT_EQ(info.netfilter.flags, nf_expected.flags, "info nf flags"); +} + void test_netfilter_link_attach(void) { struct test_netfilter_link_attach *skel; @@ -64,6 +97,8 @@ void test_netfilter_link_attach(void) if (!ASSERT_OK_PTR(link, "program attach successful")) continue; + verify_netfilter_link_info(link, nf_hook_link_tests[i]); + link2 = bpf_program__attach_netfilter(prog, &opts); ASSERT_ERR_PTR(link2, "attach program with same pf/hook/priority"); @@ -73,6 +108,9 @@ void test_netfilter_link_attach(void) link2 = bpf_program__attach_netfilter(prog, &opts); if (!ASSERT_OK_PTR(link2, "program reattach successful")) continue; + + verify_netfilter_link_info(link2, nf_hook_link_tests[i]); + if (!ASSERT_OK(bpf_link__destroy(link2), "link destroy")) break; } else { From 9c5bd93edf7b8834aecaa7c340b852d5990d7c78 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Sun, 13 Oct 2024 18:26:39 +0200 Subject: [PATCH 28/38] bpf, sockmap: SK_DROP on attempted redirects of unsupported af_vsock Don't mislead the callers of bpf_{sk,msg}_redirect_{map,hash}(): make sure to immediately and visibly fail the forwarding of unsupported af_vsock packets. Fixes: 634f1a7110b4 ("vsock: support sockmap") Signed-off-by: Michal Luczaj Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20241013-vsock-fixes-for-redir-v2-1-d6577bbfe742@rbox.co --- include/net/sock.h | 5 +++++ net/core/sock_map.c | 8 ++++++++ 2 files changed, 13 insertions(+) diff --git a/include/net/sock.h b/include/net/sock.h index c58ca8dd561b..c87295f3476d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2715,6 +2715,11 @@ static inline bool sk_is_stream_unix(const struct sock *sk) return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; } +static inline bool sk_is_vsock(const struct sock *sk) +{ + return sk->sk_family == AF_VSOCK; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 242c91a6e3d3..07d6aa4e39ef 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -647,6 +647,8 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb, sk = __sock_map_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk)) + return SK_DROP; skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; @@ -675,6 +677,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, return SK_DROP; if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) return SK_DROP; + if (sk_is_vsock(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; @@ -1249,6 +1253,8 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb, sk = __sock_hash_lookup_elem(map, key); if (unlikely(!sk || !sock_map_redirect_allowed(sk))) return SK_DROP; + if ((flags & BPF_F_INGRESS) && sk_is_vsock(sk)) + return SK_DROP; skb_bpf_set_redir(skb, sk, flags & BPF_F_INGRESS); return SK_PASS; @@ -1277,6 +1283,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, return SK_DROP; if (!(flags & BPF_F_INGRESS) && !sk_is_tcp(sk)) return SK_DROP; + if (sk_is_vsock(sk)) + return SK_DROP; msg->flags = flags; msg->sk_redir = sk; From 3543152f2d330141d9394d28855cb90b860091d2 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Sun, 13 Oct 2024 18:26:40 +0200 Subject: [PATCH 29/38] vsock: Update rx_bytes on read_skb() Make sure virtio_transport_inc_rx_pkt() and virtio_transport_dec_rx_pkt() calls are balanced (i.e. virtio_vsock_sock::rx_bytes doesn't lie) after vsock_transport::read_skb(). While here, also inform the peer that we've freed up space and it has more credit. Failing to update rx_bytes after packet is dequeued leads to a warning on SOCK_STREAM recv(): [ 233.396654] rx_queue is empty, but rx_bytes is non-zero [ 233.396702] WARNING: CPU: 11 PID: 40601 at net/vmw_vsock/virtio_transport_common.c:589 Fixes: 634f1a7110b4 ("vsock: support sockmap") Suggested-by: Stefano Garzarella Signed-off-by: Michal Luczaj Signed-off-by: Daniel Borkmann Reviewed-by: Stefano Garzarella Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20241013-vsock-fixes-for-redir-v2-2-d6577bbfe742@rbox.co --- net/vmw_vsock/virtio_transport_common.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 884ee128851e..2e5ad96825cc 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1707,6 +1707,7 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto { struct virtio_vsock_sock *vvs = vsk->trans; struct sock *sk = sk_vsock(vsk); + struct virtio_vsock_hdr *hdr; struct sk_buff *skb; int off = 0; int err; @@ -1716,10 +1717,16 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto * works for types other than dgrams. */ skb = __skb_recv_datagram(sk, &vvs->rx_queue, MSG_DONTWAIT, &off, &err); + if (!skb) { + spin_unlock_bh(&vvs->rx_lock); + return err; + } + + hdr = virtio_vsock_hdr(skb); + virtio_transport_dec_rx_pkt(vvs, le32_to_cpu(hdr->len)); spin_unlock_bh(&vvs->rx_lock); - if (!skb) - return err; + virtio_transport_send_credit_update(vsk); return recv_actor(sk, skb); } From 6dafde852df8de3617d4b9f835b629aaeaccd01d Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Sun, 13 Oct 2024 18:26:41 +0200 Subject: [PATCH 30/38] vsock: Update msg_count on read_skb() Dequeuing via vsock_transport::read_skb() left msg_count outdated, which then confused SOCK_SEQPACKET recv(). Decrease the counter. Fixes: 634f1a7110b4 ("vsock: support sockmap") Signed-off-by: Michal Luczaj Signed-off-by: Daniel Borkmann Reviewed-by: Stefano Garzarella Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20241013-vsock-fixes-for-redir-v2-3-d6577bbfe742@rbox.co --- net/vmw_vsock/virtio_transport_common.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 2e5ad96825cc..ccbd2bc0d210 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -1723,6 +1723,9 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto } hdr = virtio_vsock_hdr(skb); + if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) + vvs->msg_count--; + virtio_transport_dec_rx_pkt(vvs, le32_to_cpu(hdr->len)); spin_unlock_bh(&vvs->rx_lock); From 19039f279797efbe044cae41ee216c5fe481fc33 Mon Sep 17 00:00:00 2001 From: Michal Luczaj Date: Sun, 13 Oct 2024 18:26:42 +0200 Subject: [PATCH 31/38] bpf, vsock: Drop static vsock_bpf_prot initialization vsock_bpf_prot is set up at runtime. Remove the superfluous init. No functional change intended. Fixes: 634f1a7110b4 ("vsock: support sockmap") Signed-off-by: Michal Luczaj Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20241013-vsock-fixes-for-redir-v2-4-d6577bbfe742@rbox.co --- net/vmw_vsock/vsock_bpf.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index c42c5cc18f32..4aa6e74ec295 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -114,14 +114,6 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, return copied; } -/* Copy of original proto with updated sock_map methods */ -static struct proto vsock_bpf_prot = { - .close = sock_map_close, - .recvmsg = vsock_bpf_recvmsg, - .sock_is_readable = sk_msg_is_readable, - .unhash = sock_map_unhash, -}; - static void vsock_bpf_rebuild_protos(struct proto *prot, const struct proto *base) { *prot = *base; From e59db0623f6955986d1be0880b351a1f56e7fd6d Mon Sep 17 00:00:00 2001 From: Andrea Parri Date: Thu, 17 Oct 2024 17:36:28 +0300 Subject: [PATCH 32/38] riscv, bpf: Make BPF_CMPXCHG fully ordered MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to the prototype formal BPF memory consistency model discussed e.g. in [1] and following the ordering properties of the C/in-kernel macro atomic_cmpxchg(), a BPF atomic operation with the BPF_CMPXCHG modifier is fully ordered. However, the current RISC-V JIT lowerings fail to meet such memory ordering property. This is illustrated by the following litmus test: BPF BPF__MP+success_cmpxchg+fence { 0:r1=x; 0:r3=y; 0:r5=1; 1:r2=y; 1:r4=f; 1:r7=x; } P0 | P1 ; *(u64 *)(r1 + 0) = 1 | r1 = *(u64 *)(r2 + 0) ; r2 = cmpxchg_64 (r3 + 0, r4, r5) | r3 = atomic_fetch_add((u64 *)(r4 + 0), r5) ; | r6 = *(u64 *)(r7 + 0) ; exists (1:r1=1 /\ 1:r6=0) whose "exists" clause is not satisfiable according to the BPF memory model. Using the current RISC-V JIT lowerings, the test can be mapped to the following RISC-V litmus test: RISCV RISCV__MP+success_cmpxchg+fence { 0:x1=x; 0:x3=y; 0:x5=1; 1:x2=y; 1:x4=f; 1:x7=x; } P0 | P1 ; sd x5, 0(x1) | ld x1, 0(x2) ; L00: | amoadd.d.aqrl x3, x5, 0(x4) ; lr.d x2, 0(x3) | ld x6, 0(x7) ; bne x2, x4, L01 | ; sc.d x6, x5, 0(x3) | ; bne x6, x4, L00 | ; fence rw, rw | ; L01: | ; exists (1:x1=1 /\ 1:x6=0) where the two stores in P0 can be reordered. Update the RISC-V JIT lowerings/implementation of BPF_CMPXCHG to emit an SC with RELEASE ("rl") annotation in order to meet the expected memory ordering guarantees. The resulting RISC-V JIT lowerings of BPF_CMPXCHG match the RISC-V lowerings of the C atomic_cmpxchg(). Other lowerings were fixed via 20a759df3bba ("riscv, bpf: make some atomic operations fully ordered"). Fixes: dd642ccb45ec ("riscv, bpf: Implement more atomic operations for RV64") Signed-off-by: Andrea Parri Signed-off-by: Daniel Borkmann Reviewed-by: Puranjay Mohan Acked-by: Björn Töpel Link: https://lpc.events/event/18/contributions/1949/attachments/1665/3441/bpfmemmodel.2024.09.19p.pdf [1] Link: https://lore.kernel.org/bpf/20241017143628.2673894-1-parri.andrea@gmail.com --- arch/riscv/net/bpf_jit_comp64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 91bd5082c4d8..4cc631fa7039 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -550,8 +550,8 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, rv_lr_w(r0, 0, rd, 0, 0), ctx); jmp_offset = ninsns_rvoff(8); emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx); - emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 0) : - rv_sc_w(RV_REG_T3, rs, rd, 0, 0), ctx); + emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 1) : + rv_sc_w(RV_REG_T3, rs, rd, 0, 1), ctx); jmp_offset = ninsns_rvoff(-6); emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx); emit(rv_fence(0x3, 0x3), ctx); From 9495a5b731fcaf580448a3438d63601c88367661 Mon Sep 17 00:00:00 2001 From: Jordan Rome Date: Wed, 16 Oct 2024 14:00:47 -0700 Subject: [PATCH 33/38] bpf: Fix iter/task tid filtering In userspace, you can add a tid filter by setting the "task.tid" field for "bpf_iter_link_info". However, `get_pid_task` when called for the `BPF_TASK_ITER_TID` type should have been using `PIDTYPE_PID` (tid) instead of `PIDTYPE_TGID` (pid). Fixes: f0d74c4da1f0 ("bpf: Parameterize task iterators.") Signed-off-by: Jordan Rome Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241016210048.1213935-1-linux@jordanrome.com --- kernel/bpf/task_iter.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 02aa9db8d796..5af9e130e500 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -99,7 +99,7 @@ static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *co rcu_read_lock(); pid = find_pid_ns(common->pid, common->ns); if (pid) { - task = get_pid_task(pid, PIDTYPE_TGID); + task = get_pid_task(pid, PIDTYPE_PID); *tid = common->pid; } rcu_read_unlock(); From ee8c7c6c3f8c7105b1f2e0ba321c193e9f0158d9 Mon Sep 17 00:00:00 2001 From: Jordan Rome Date: Wed, 16 Oct 2024 14:00:48 -0700 Subject: [PATCH 34/38] bpf: Properly test iter/task tid filtering Previously test_task_tid was setting `linfo.task.tid` to `getpid()` which is the same as `gettid()` for the parent process. Instead create a new child thread and set `linfo.task.tid` to `gettid()` to make sure the tid filtering logic is working as expected. Signed-off-by: Jordan Rome Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241016210048.1213935-2-linux@jordanrome.com --- .../selftests/bpf/prog_tests/bpf_iter.c | 27 +++++++++++++++---- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 52e6f7570475..f0a3a9c18e9e 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -226,7 +226,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, ASSERT_OK(pthread_create(&thread_id, NULL, &do_nothing_wait, NULL), "pthread_create"); - skel->bss->tid = getpid(); + skel->bss->tid = gettid(); do_dummy_read_opts(skel->progs.dump_task, opts); @@ -249,25 +249,42 @@ static void test_task_common(struct bpf_iter_attach_opts *opts, int num_unknown, ASSERT_EQ(num_known_tid, num_known, "check_num_known_tid"); } -static void test_task_tid(void) +static void *run_test_task_tid(void *arg) { LIBBPF_OPTS(bpf_iter_attach_opts, opts); union bpf_iter_link_info linfo; int num_unknown_tid, num_known_tid; + ASSERT_NEQ(getpid(), gettid(), "check_new_thread_id"); + memset(&linfo, 0, sizeof(linfo)); - linfo.task.tid = getpid(); + linfo.task.tid = gettid(); opts.link_info = &linfo; opts.link_info_len = sizeof(linfo); test_task_common(&opts, 0, 1); linfo.task.tid = 0; linfo.task.pid = getpid(); - test_task_common(&opts, 1, 1); + /* This includes the parent thread, this thread, + * and the do_nothing_wait thread + */ + test_task_common(&opts, 2, 1); test_task_common_nocheck(NULL, &num_unknown_tid, &num_known_tid); - ASSERT_GT(num_unknown_tid, 1, "check_num_unknown_tid"); + ASSERT_GT(num_unknown_tid, 2, "check_num_unknown_tid"); ASSERT_EQ(num_known_tid, 1, "check_num_known_tid"); + + return NULL; +} + +static void test_task_tid(void) +{ + pthread_t thread_id; + + /* Create a new thread so pid and tid aren't the same */ + ASSERT_OK(pthread_create(&thread_id, NULL, &run_test_task_tid, NULL), + "pthread_create"); + ASSERT_FALSE(pthread_join(thread_id, NULL), "pthread_join"); } static void test_task_pid(void) From 3878ae04e9fc24dacb77a1d32bd87e7d8108599e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 16 Oct 2024 15:49:11 +0200 Subject: [PATCH 35/38] bpf: Fix incorrect delta propagation between linked registers Nathaniel reported a bug in the linked scalar delta tracking, which can lead to accepting a program with OOB access. The specific code is related to the sync_linked_regs() function and the BPF_ADD_CONST flag, which signifies a constant offset between two scalar registers tracked by the same register id. The verifier attempts to track "similar" scalars in order to propagate bounds information learned about one scalar to others. For instance, if r1 and r2 are known to contain the same value, then upon encountering 'if (r1 != 0x1234) goto xyz', not only does it know that r1 is equal to 0x1234 on the path where that conditional jump is not taken, it also knows that r2 is. Additionally, with env->bpf_capable set, the verifier will track scalars which should be a constant delta apart (if r1 is known to be one greater than r2, then if r1 is known to be equal to 0x1234, r2 must be equal to 0x1233.) The code path for the latter in adjust_reg_min_max_vals() is reached when processing both 32 and 64-bit addition operations. While adjust_reg_min_max_vals() knows whether dst_reg was produced by a 32 or a 64-bit addition (based on the alu32 bool), the only information saved in dst_reg is the id of the source register (reg->id, or'ed by BPF_ADD_CONST) and the value of the constant offset (reg->off). Later, the function sync_linked_regs() will attempt to use this information to propagate bounds information from one register (known_reg) to others, meaning, for all R in linked_regs, it copies known_reg range (and possibly adjusting delta) into R for the case of R->id == known_reg->id. For the delta adjustment, meaning, matching reg->id with BPF_ADD_CONST, the verifier adjusts the register as reg = known_reg; reg += delta where delta is computed as (s32)reg->off - (s32)known_reg->off and placed as a scalar into a fake_reg to then simulate the addition of reg += fake_reg. This is only correct, however, if the value in reg was created by a 64-bit addition. When reg contains the result of a 32-bit addition operation, its upper 32 bits will always be zero. sync_linked_regs() on the other hand, may cause the verifier to believe that the addition between fake_reg and reg overflows into those upper bits. For example, if reg was generated by adding the constant 1 to known_reg using a 32-bit alu operation, then reg->off is 1 and known_reg->off is 0. If known_reg is known to be the constant 0xFFFFFFFF, sync_linked_regs() will tell the verifier that reg is equal to the constant 0x100000000. This is incorrect as the actual value of reg will be 0, as the 32-bit addition will wrap around. Example: 0: (b7) r0 = 0; R0_w=0 1: (18) r1 = 0x80000001; R1_w=0x80000001 3: (37) r1 /= 1; R1_w=scalar() 4: (bf) r2 = r1; R1_w=scalar(id=1) R2_w=scalar(id=1) 5: (bf) r4 = r1; R1_w=scalar(id=1) R4_w=scalar(id=1) 6: (04) w2 += 2147483647; R2_w=scalar(id=1+2147483647,smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff)) 7: (04) w4 += 0 ; R4_w=scalar(id=1+0,smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff)) 8: (15) if r2 == 0x0 goto pc+1 10: R0=0 R1=0xffffffff80000001 R2=0x7fffffff R4=0xffffffff80000001 R10=fp0 What can be seen here is that r1 is copied to r2 and r4, such that {r1,r2,r4}.id are all the same which later lets sync_linked_regs() to be invoked. Then, in a next step constants are added with alu32 to r2 and r4, setting their ->off, as well as id |= BPF_ADD_CONST. Next, the conditional will bind r2 and propagate ranges to its linked registers. The verifier now believes the upper 32 bits of r4 are r4=0xffffffff80000001, while actually r4=r1=0x80000001. One approach for a simple fix suitable also for stable is to limit the constant delta tracking to only 64-bit alu addition. If necessary at some later point, BPF_ADD_CONST could be split into BPF_ADD_CONST64 and BPF_ADD_CONST32 to avoid mixing the two under the tradeoff to further complicate sync_linked_regs(). However, none of the added tests from dedf56d775c0 ("selftests/bpf: Add tests for add_const") make this necessary at this point, meaning, BPF CI also passes with just limiting tracking to 64-bit alu addition. Fixes: 98d7ca374ba4 ("bpf: Track delta between "linked" registers.") Reported-by: Nathaniel Theis Signed-off-by: Daniel Borkmann Signed-off-by: Andrii Nakryiko Reviewed-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20241016134913.32249-1-daniel@iogearbox.net --- kernel/bpf/verifier.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a8a0b6e4110e..411ab1b57af4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14270,12 +14270,13 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * r1 += 0x1 * if r2 < 1000 goto ... * use r1 in memory access - * So remember constant delta between r2 and r1 and update r1 after - * 'if' condition. + * So for 64-bit alu remember constant delta between r2 and r1 and + * update r1 after 'if' condition. */ - if (env->bpf_capable && BPF_OP(insn->code) == BPF_ADD && - dst_reg->id && is_reg_const(src_reg, alu32)) { - u64 val = reg_const_value(src_reg, alu32); + if (env->bpf_capable && + BPF_OP(insn->code) == BPF_ADD && !alu32 && + dst_reg->id && is_reg_const(src_reg, false)) { + u64 val = reg_const_value(src_reg, false); if ((dst_reg->id & BPF_ADD_CONST) || /* prevent overflow in sync_linked_regs() later */ From 3e9e708757ca3b7eb65a820031d62fea1a265709 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 16 Oct 2024 15:49:12 +0200 Subject: [PATCH 36/38] bpf: Fix print_reg_state's constant scalar dump print_reg_state() should not consider adding reg->off to reg->var_off.value when dumping scalars. Scalars can be produced with reg->off != 0 through BPF_ADD_CONST, and thus as-is this can skew the register log dump. Fixes: 98d7ca374ba4 ("bpf: Track delta between "linked" registers.") Reported-by: Nathaniel Theis Signed-off-by: Daniel Borkmann Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20241016134913.32249-2-daniel@iogearbox.net --- kernel/bpf/log.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 5aebfc3051e3..4a858fdb6476 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -688,8 +688,7 @@ static void print_reg_state(struct bpf_verifier_env *env, if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) { - /* reg->off should be 0 for SCALAR_VALUE */ - verbose_snum(env, reg->var_off.value + reg->off); + verbose_snum(env, reg->var_off.value); return; } From db123e42304d5bba9a1e04341db0cafaa7a52f35 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 16 Oct 2024 15:49:13 +0200 Subject: [PATCH 37/38] selftests/bpf: Add test case for delta propagation Add a small BPF verifier test case to ensure that alu32 additions to registers are not subject to linked scalar delta tracking. # ./vmtest.sh -- ./test_progs -t verifier_linked_scalars [...] ./test_progs -t verifier_linked_scalars [ 1.413138] tsc: Refined TSC clocksource calibration: 3407.993 MHz [ 1.413524] clocksource: tsc: mask: 0xffffffffffffffff max_cycles: 0x311fcd52370, max_idle_ns: 440795242006 ns [ 1.414223] clocksource: Switched to clocksource tsc [ 1.419640] bpf_testmod: loading out-of-tree module taints kernel. [ 1.420025] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel #500/1 verifier_linked_scalars/scalars: find linked scalars:OK #500 verifier_linked_scalars:OK Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED [ 1.590858] ACPI: PM: Preparing to enter system sleep state S5 [ 1.591402] reboot: Power down [...] Signed-off-by: Daniel Borkmann Signed-off-by: Andrii Nakryiko Acked-by: Eduard Zingerman Link: https://lore.kernel.org/bpf/20241016134913.32249-3-daniel@iogearbox.net --- .../selftests/bpf/prog_tests/verifier.c | 2 ++ .../bpf/progs/verifier_linked_scalars.c | 34 +++++++++++++++++++ 2 files changed, 36 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/verifier_linked_scalars.c diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index e26b5150fc43..5356f26bbb3f 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -44,6 +44,7 @@ #include "verifier_ld_ind.skel.h" #include "verifier_ldsx.skel.h" #include "verifier_leak_ptr.skel.h" +#include "verifier_linked_scalars.skel.h" #include "verifier_loops1.skel.h" #include "verifier_lwt.skel.h" #include "verifier_map_in_map.skel.h" @@ -170,6 +171,7 @@ void test_verifier_jit_convergence(void) { RUN(verifier_jit_convergence); } void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); } void test_verifier_ldsx(void) { RUN(verifier_ldsx); } void test_verifier_leak_ptr(void) { RUN(verifier_leak_ptr); } +void test_verifier_linked_scalars(void) { RUN(verifier_linked_scalars); } void test_verifier_loops1(void) { RUN(verifier_loops1); } void test_verifier_lwt(void) { RUN(verifier_lwt); } void test_verifier_map_in_map(void) { RUN(verifier_map_in_map); } diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c new file mode 100644 index 000000000000..8f755d2464cf --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include "bpf_misc.h" + +SEC("socket") +__description("scalars: find linked scalars") +__failure +__msg("math between fp pointer and 2147483647 is not allowed") +__naked void scalars(void) +{ + asm volatile (" \ + r0 = 0; \ + r1 = 0x80000001 ll; \ + r1 /= 1; \ + r2 = r1; \ + r4 = r1; \ + w2 += 0x7FFFFFFF; \ + w4 += 0; \ + if r2 == 0 goto l1; \ + exit; \ +l1: \ + r4 >>= 63; \ + r3 = 1; \ + r3 -= r4; \ + r3 *= 0x7FFFFFFF; \ + r3 += r10; \ + *(u8*)(r3 - 1) = r0; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; From 5ac9b4e935dfc6af41eee2ddc21deb5c36507a9f Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Thu, 17 Oct 2024 10:47:13 -0700 Subject: [PATCH 38/38] lib/buildid: Handle memfd_secret() files in build_id_parse() >From memfd_secret(2) manpage: The memory areas backing the file created with memfd_secret(2) are visible only to the processes that have access to the file descriptor. The memory region is removed from the kernel page tables and only the page tables of the processes holding the file descriptor map the corresponding physical memory. (Thus, the pages in the region can't be accessed by the kernel itself, so that, for example, pointers to the region can't be passed to system calls.) We need to handle this special case gracefully in build ID fetching code. Return -EFAULT whenever secretmem file is passed to build_id_parse() family of APIs. Original report and repro can be found in [0]. [0] https://lore.kernel.org/bpf/ZwyG8Uro%2FSyTXAni@ly-workstation/ Fixes: de3ec364c3c3 ("lib/buildid: add single folio-based file reader abstraction") Reported-by: Yi Lai Suggested-by: Shakeel Butt Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Acked-by: Shakeel Butt Link: https://lore.kernel.org/bpf/20241017175431.6183-A-hca@linux.ibm.com Link: https://lore.kernel.org/bpf/20241017174713.2157873-1-andrii@kernel.org --- lib/buildid.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/lib/buildid.c b/lib/buildid.c index 290641d92ac1..c4b0f376fb34 100644 --- a/lib/buildid.c +++ b/lib/buildid.c @@ -5,6 +5,7 @@ #include #include #include +#include #define BUILD_ID 3 @@ -64,6 +65,10 @@ static int freader_get_folio(struct freader *r, loff_t file_off) freader_put_folio(r); + /* reject secretmem folios created with memfd_secret() */ + if (secretmem_mapping(r->file->f_mapping)) + return -EFAULT; + r->folio = filemap_get_folio(r->file->f_mapping, file_off >> PAGE_SHIFT); /* if sleeping is allowed, wait for the page, if necessary */