From 2b986b9e917bc88f81aa1ed386af63b26c983f1d Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <hawk@kernel.org>
Date: Thu, 14 Aug 2025 20:24:37 +0200
Subject: [PATCH 01/15] bpf, cpumap: Disable page_pool direct xdp_return need
 larger scope

When running an XDP bpf_prog on the remote CPU in cpumap code
then we must disable the direct return optimization that
xdp_return can perform for mem_type page_pool.  This optimization
assumes code is still executing under RX-NAPI of the original
receiving CPU, which isn't true on this remote CPU.

The cpumap code already disabled this via helpers
xdp_set_return_frame_no_direct() and xdp_clear_return_frame_no_direct(),
but the scope didn't include xdp_do_flush().

When doing XDP_REDIRECT towards e.g devmap this causes the
function bq_xmit_all() to run with direct return optimization
enabled. This can lead to hard to find bugs.  The issue
only happens when bq_xmit_all() cannot ndo_xdp_xmit all
frames and them frees them via xdp_return_frame_rx_napi().

Fix by expanding scope to include xdp_do_flush(). This was found
by Dragos Tatulea.

Fixes: 11941f8a8536 ("bpf: cpumap: Implement generic cpumap")
Reported-by: Dragos Tatulea <dtatulea@nvidia.com>
Reported-by: Chris Arges <carges@cloudflare.com>
Signed-off-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Chris Arges <carges@cloudflare.com>
Link: https://patch.msgid.link/175519587755.3008742.1088294435150406835.stgit@firesoul
---
 kernel/bpf/cpumap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index b2b7b8ec2c2a..c46360b27871 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -186,7 +186,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 	struct xdp_buff xdp;
 	int i, nframes = 0;
 
-	xdp_set_return_frame_no_direct();
 	xdp.rxq = &rxq;
 
 	for (i = 0; i < n; i++) {
@@ -231,7 +230,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 		}
 	}
 
-	xdp_clear_return_frame_no_direct();
 	stats->pass += nframes;
 
 	return nframes;
@@ -255,6 +253,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 
 	rcu_read_lock();
 	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+	xdp_set_return_frame_no_direct();
 
 	ret->xdp_n = cpu_map_bpf_prog_run_xdp(rcpu, frames, ret->xdp_n, stats);
 	if (unlikely(ret->skb_n))
@@ -264,6 +263,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 	if (stats->redirect)
 		xdp_do_flush();
 
+	xdp_clear_return_frame_no_direct();
 	bpf_net_ctx_clear(bpf_net_ctx);
 	rcu_read_unlock();
 

From e4414b01c1cd9887bbde92f946c1ba94e40d6d64 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <olsajiri@gmail.com>
Date: Thu, 14 Aug 2025 22:06:55 +0200
Subject: [PATCH 02/15] bpf: Check the helper function is valid in
 get_helper_proto

kernel test robot reported verifier bug [1] where the helper func
pointer could be NULL due to disabled config option.

As Alexei suggested we could check on that in get_helper_proto
directly. Marking tail_call helper func with BPF_PTR_POISON,
because it is unused by design.

  [1] https://lore.kernel.org/oe-lkp/202507160818.68358831-lkp@intel.com

Reported-by: kernel test robot <oliver.sang@intel.com>
Reported-by: syzbot+a9ed3d9132939852d0df@syzkaller.appspotmail.com
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Paul Chaignon <paul.chaignon@gmail.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20250814200655.945632-1-jolsa@kernel.org
Closes: https://lore.kernel.org/oe-lkp/202507160818.68358831-lkp@intel.com
---
 kernel/bpf/core.c     | 5 ++++-
 kernel/bpf/verifier.c | 2 +-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 5d1650af899d..f8ac77d08ca7 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -3024,7 +3024,10 @@ EXPORT_SYMBOL_GPL(bpf_event_output);
 
 /* Always built-in helper functions. */
 const struct bpf_func_proto bpf_tail_call_proto = {
-	.func		= NULL,
+	/* func is unused for tail_call, we set it to pass the
+	 * get_helper_proto check
+	 */
+	.func		= BPF_PTR_POISON,
 	.gpl_only	= false,
 	.ret_type	= RET_VOID,
 	.arg1_type	= ARG_PTR_TO_CTX,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c4f69a9e9af6..c89e2b1bc644 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -11354,7 +11354,7 @@ static int get_helper_proto(struct bpf_verifier_env *env, int func_id,
 		return -EINVAL;
 
 	*ptr = env->ops->get_func_proto(func_id, env->prog);
-	return *ptr ? 0 : -EINVAL;
+	return *ptr && (*ptr)->func ? 0 : -EINVAL;
 }
 
 static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,

From f9bb6ffa7f5ad0f8ee0f53fc4a10655872ee4a14 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 29 Aug 2025 16:36:56 +0200
Subject: [PATCH 03/15] bpf: Fix out-of-bounds dynptr write in bpf_crypto_crypt

Stanislav reported that in bpf_crypto_crypt() the destination dynptr's
size is not validated to be at least as large as the source dynptr's
size before calling into the crypto backend with 'len = src_len'. This
can result in an OOB write when the destination is smaller than the
source.

Concretely, in mentioned function, psrc and pdst are both linear
buffers fetched from each dynptr:

  psrc = __bpf_dynptr_data(src, src_len);
  [...]
  pdst = __bpf_dynptr_data_rw(dst, dst_len);
  [...]
  err = decrypt ?
        ctx->type->decrypt(ctx->tfm, psrc, pdst, src_len, piv) :
        ctx->type->encrypt(ctx->tfm, psrc, pdst, src_len, piv);

The crypto backend expects pdst to be large enough with a src_len length
that can be written. Add an additional src_len > dst_len check and bail
out if it's the case. Note that these kfuncs are accessible under root
privileges only.

Fixes: 3e1c6f35409f ("bpf: make common crypto API for TC/XDP programs")
Reported-by: Stanislav Fort <disclosure@aisle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://lore.kernel.org/r/20250829143657.318524-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/crypto.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c
index 94854cd9c4cc..83c4d9943084 100644
--- a/kernel/bpf/crypto.c
+++ b/kernel/bpf/crypto.c
@@ -278,7 +278,7 @@ static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx,
 	siv_len = siv ? __bpf_dynptr_size(siv) : 0;
 	src_len = __bpf_dynptr_size(src);
 	dst_len = __bpf_dynptr_size(dst);
-	if (!src_len || !dst_len)
+	if (!src_len || !dst_len || src_len > dst_len)
 		return -EINVAL;
 
 	if (siv_len != ctx->siv_len)

From 3aa9b9a165d5e9afc7d8b5dbcd508810c05c8e89 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 29 Aug 2025 16:36:57 +0200
Subject: [PATCH 04/15] selftests/bpf: Extend crypto_sanity selftest with
 invalid dst buffer

Small cleanup and test extension to probe the bpf_crypto_{encrypt,decrypt}()
kfunc when a bad dst buffer is passed in to assert that an error is returned.

Also, encrypt_sanity() and skb_crypto_setup() were explicit to set the global
status variable to zero before any test, so do the same for decrypt_sanity().
Do not explicitly zero the on-stack err before bpf_crypto_ctx_create() given
the kfunc is expected to do it internally for the success case.

Before kernel fix:

  # ./vmtest.sh -- ./test_progs -t crypto
  [...]
  [    1.531200] bpf_testmod: loading out-of-tree module taints kernel.
  [    1.533388] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel
  #87/1    crypto_basic/crypto_release:OK
  #87/2    crypto_basic/crypto_acquire:OK
  #87      crypto_basic:OK
  test_crypto_sanity:PASS:skel open 0 nsec
  test_crypto_sanity:PASS:ip netns add crypto_sanity_ns 0 nsec
  test_crypto_sanity:PASS:ip -net crypto_sanity_ns -6 addr add face::1/128 dev lo nodad 0 nsec
  test_crypto_sanity:PASS:ip -net crypto_sanity_ns link set dev lo up 0 nsec
  test_crypto_sanity:PASS:open_netns 0 nsec
  test_crypto_sanity:PASS:AF_ALG init fail 0 nsec
  test_crypto_sanity:PASS:if_nametoindex lo 0 nsec
  test_crypto_sanity:PASS:skb_crypto_setup fd 0 nsec
  test_crypto_sanity:PASS:skb_crypto_setup 0 nsec
  test_crypto_sanity:PASS:skb_crypto_setup retval 0 nsec
  test_crypto_sanity:PASS:skb_crypto_setup status 0 nsec
  test_crypto_sanity:PASS:create qdisc hook 0 nsec
  test_crypto_sanity:PASS:make_sockaddr 0 nsec
  test_crypto_sanity:PASS:attach encrypt filter 0 nsec
  test_crypto_sanity:PASS:encrypt socket 0 nsec
  test_crypto_sanity:PASS:encrypt send 0 nsec
  test_crypto_sanity:FAIL:encrypt status unexpected error: -5 (errno 95)
  #88      crypto_sanity:FAIL
  Summary: 1/2 PASSED, 0 SKIPPED, 1 FAILED

After kernel fix:

  # ./vmtest.sh -- ./test_progs -t crypto
  [...]
  [    1.540963] bpf_testmod: loading out-of-tree module taints kernel.
  [    1.542404] bpf_testmod: module verification failed: signature and/or required key missing - tainting kernel
  #87/1    crypto_basic/crypto_release:OK
  #87/2    crypto_basic/crypto_acquire:OK
  #87      crypto_basic:OK
  #88      crypto_sanity:OK
  Summary: 2/2 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://lore.kernel.org/r/20250829143657.318524-2-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 .../selftests/bpf/progs/crypto_sanity.c       | 46 +++++++++++++------
 1 file changed, 32 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c
index 645be6cddf36..dfd8a258f14a 100644
--- a/tools/testing/selftests/bpf/progs/crypto_sanity.c
+++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c
@@ -14,7 +14,7 @@ unsigned char key[256] = {};
 u16 udp_test_port = 7777;
 u32 authsize, key_len;
 char algo[128] = {};
-char dst[16] = {};
+char dst[16] = {}, dst_bad[8] = {};
 int status;
 
 static int skb_dynptr_validate(struct __sk_buff *skb, struct bpf_dynptr *psrc)
@@ -59,10 +59,9 @@ int skb_crypto_setup(void *ctx)
 		.authsize = authsize,
 	};
 	struct bpf_crypto_ctx *cctx;
-	int err = 0;
+	int err;
 
 	status = 0;
-
 	if (key_len > 256) {
 		status = -EINVAL;
 		return 0;
@@ -70,8 +69,8 @@ int skb_crypto_setup(void *ctx)
 
 	__builtin_memcpy(&params.algo, algo, sizeof(algo));
 	__builtin_memcpy(&params.key, key, sizeof(key));
-	cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
 
+	cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
 	if (!cctx) {
 		status = err;
 		return 0;
@@ -80,7 +79,6 @@ int skb_crypto_setup(void *ctx)
 	err = crypto_ctx_insert(cctx);
 	if (err && err != -EEXIST)
 		status = err;
-
 	return 0;
 }
 
@@ -92,6 +90,7 @@ int decrypt_sanity(struct __sk_buff *skb)
 	struct bpf_dynptr psrc, pdst;
 	int err;
 
+	status = 0;
 	err = skb_dynptr_validate(skb, &psrc);
 	if (err < 0) {
 		status = err;
@@ -110,13 +109,23 @@ int decrypt_sanity(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 	}
 
-	/* dst is a global variable to make testing part easier to check. In real
-	 * production code, a percpu map should be used to store the result.
+	/* Check also bad case where the dst buffer is smaller than the
+	 * skb's linear section.
+	 */
+	bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
+	if (!status)
+		status = -EIO;
+	if (status != -EINVAL)
+		goto err;
+
+	/* dst is a global variable to make testing part easier to check.
+	 * In real production code, a percpu map should be used to store
+	 * the result.
 	 */
 	bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-
 	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
-
+err:
 	return TC_ACT_SHOT;
 }
 
@@ -129,7 +138,6 @@ int encrypt_sanity(struct __sk_buff *skb)
 	int err;
 
 	status = 0;
-
 	err = skb_dynptr_validate(skb, &psrc);
 	if (err < 0) {
 		status = err;
@@ -148,13 +156,23 @@ int encrypt_sanity(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 	}
 
-	/* dst is a global variable to make testing part easier to check. In real
-	 * production code, a percpu map should be used to store the result.
+	/* Check also bad case where the dst buffer is smaller than the
+	 * skb's linear section.
+	 */
+	bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
+	if (!status)
+		status = -EIO;
+	if (status != -EINVAL)
+		goto err;
+
+	/* dst is a global variable to make testing part easier to check.
+	 * In real production code, a percpu map should be used to store
+	 * the result.
 	 */
 	bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
-
 	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
-
+err:
 	return TC_ACT_SHOT;
 }
 

From 7edfc024708258d75f65fadffd7e5f6ac46810b6 Mon Sep 17 00:00:00 2001
From: Rong Tao <rongtao@cestc.cn>
Date: Sat, 30 Aug 2025 00:31:58 +0800
Subject: [PATCH 05/15] bpf: Fix bpf_strnstr() to handle suffix match cases
 better

bpf_strnstr() should not treat the ending '\0' of s2 as a matching character
if the parameter 'len' equal to s2 string length, for example:

    1. bpf_strnstr("openat", "open", 4) = -ENOENT
    2. bpf_strnstr("openat", "open", 5) = 0

This patch makes (1) return 0, fix just the `len == strlen(s2)` case.

And fix a more general case when s2 is a suffix of the first len
characters of s1.

Fixes: e91370550f1f ("bpf: Add kfuncs for read-only string operations")
Signed-off-by: Rong Tao <rongtao@cestc.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/tencent_17DC57B9D16BC443837021BEACE84B7C1507@qq.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/helpers.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6b4877e85a68..b9b0c5fe33f6 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -3664,10 +3664,17 @@ __bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len
 
 	guard(pagefault)();
 	for (i = 0; i < XATTR_SIZE_MAX; i++) {
-		for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) {
+		for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) {
 			__get_kernel_nofault(&c2, s2__ign + j, char, err_out);
 			if (c2 == '\0')
 				return i;
+			/*
+			 * We allow reading an extra byte from s2 (note the
+			 * `i + j <= len` above) to cover the case when s2 is
+			 * a suffix of the first len chars of s1.
+			 */
+			if (i + j == len)
+				break;
 			__get_kernel_nofault(&c1, s1__ign + j, char, err_out);
 			if (c1 == '\0')
 				return -ENOENT;

From 5d40c038c879eeb910039adeaf6102e1c4dda807 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Fri, 29 Aug 2025 04:53:57 +0200
Subject: [PATCH 06/15] selftests/bpf: Fix "expression result unused" warnings
 with icecc

icecc is a compiler wrapper that distributes compile jobs over a build
farm [1]. It works by sending toolchain binaries and preprocessed
source code to remote machines.

Unfortunately using it with BPF selftests causes build failures due to
a clang bug [2]. The problem is that clang suppresses the
-Wunused-value warning if the unused expression comes from a macro
expansion. Since icecc compiles preprocessed source code, this
information is not available. This leads to -Wunused-value false
positives.

obj_new_no_struct() and obj_new_acq() use the bpf_obj_new() macro and
discard the result. arena_spin_lock_slowpath() uses two macros that
produce values and ignores the results. Add (void) casts to explicitly
indicate that this is intentional and suppress the warning.

An alternative solution is to change the macros to not produce values.
This would work today for the arena_spin_lock_slowpath() issue, but in
the future there may appear users who need them. Another potential
solution is to replace these macros with functions. Unfortunately this
would not work, because these macros work with unknown types and
control flow.

[1] https://github.com/icecc/icecream
[2] https://github.com/llvm/llvm-project/issues/142614

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20250829030017.102615-2-iii@linux.ibm.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h | 4 ++--
 tools/testing/selftests/bpf/progs/linked_list_fail.c    | 5 ++---
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
index d67466c1ff77..f90531cf3ee5 100644
--- a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
+++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
@@ -302,7 +302,7 @@ int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val
 	 * barriers.
 	 */
 	if (val & _Q_LOCKED_MASK)
-		smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
+		(void)smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
 
 	/*
 	 * take ownership and clear the pending bit.
@@ -380,7 +380,7 @@ queue:
 		/* Link @node into the waitqueue. */
 		WRITE_ONCE(prev->next, node);
 
-		arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
+		(void)arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
 
 		/*
 		 * While waiting for the MCS lock, the next pointer may have
diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c
index 6438982b928b..ddd26d1a083f 100644
--- a/tools/testing/selftests/bpf/progs/linked_list_fail.c
+++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c
@@ -226,8 +226,7 @@ int obj_new_no_composite(void *ctx)
 SEC("?tc")
 int obj_new_no_struct(void *ctx)
 {
-
-	bpf_obj_new(union { int data; unsigned udata; });
+	(void)bpf_obj_new(union { int data; unsigned udata; });
 	return 0;
 }
 
@@ -252,7 +251,7 @@ int new_null_ret(void *ctx)
 SEC("?tc")
 int obj_new_acq(void *ctx)
 {
-	bpf_obj_new(struct foo);
+	(void)bpf_obj_new(struct foo);
 	return 0;
 }
 

From 6624fb2f3382271953f951d46f2ea30415a0917e Mon Sep 17 00:00:00 2001
From: Rong Tao <rongtao@cestc.cn>
Date: Sat, 30 Aug 2025 00:32:13 +0800
Subject: [PATCH 07/15] selftests/bpf: Add tests for bpf_strnstr

Add tests for bpf_strnstr():

    bpf_strnstr("", "", 0) = 0
    bpf_strnstr("hello world", "hello", 5) = 0
    bpf_strnstr(str, "hello", 4) = -ENOENT
    bpf_strnstr("", "a", 0) = -ENOENT

Signed-off-by: Rong Tao <rongtao@cestc.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/tencent_2ED218F8082565C95D86A804BDDA8DBA200A@qq.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/progs/string_kfuncs_success.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
index 46697f381878..a47690174e0e 100644
--- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
@@ -30,8 +30,12 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); }
 __test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); }
 __test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); }
 __test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); }
-__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); }
-__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); }
+__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); }
+__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); }
+__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); }
+__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); }
 __test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); }
 
 char _license[] SEC("license") = "GPL";

From 6c6f5c19e67c89e974ef0dd8601804eaa4ae868d Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Tue, 9 Sep 2025 10:16:38 -0700
Subject: [PATCH 08/15] bpf: Update the list of BPF selftests maintainers

Unfortunately Mykola won't participate in BPF selftests maintenance
anymore. Remove the entry on his behalf.

Acked-by: Mykola Lysenko <nickolay.lysenko@gmail.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250909171638.2417272-1-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fe168477caa4..6056ad6f1afa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4682,7 +4682,6 @@ F:	security/bpf/
 BPF [SELFTESTS] (Test Runners & Infrastructure)
 M:	Andrii Nakryiko <andrii@kernel.org>
 M:	Eduard Zingerman <eddyz87@gmail.com>
-R:	Mykola Lysenko <mykolal@fb.com>
 L:	bpf@vger.kernel.org
 S:	Maintained
 F:	tools/testing/selftests/bpf/

From 30f241fcf52aaaef7ac16e66530faa11be78a865 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Thu, 4 Sep 2025 21:49:07 +0200
Subject: [PATCH 09/15] xsk: Fix immature cq descriptor production

Eryk reported an issue that I have put under Closes: tag, related to
umem addrs being prematurely produced onto pool's completion queue.
Let us make the skb's destructor responsible for producing all addrs
that given skb used.

Commit from fixes tag introduced the buggy behavior, it was not broken
from day 1, but rather when xsk multi-buffer got introduced.

In order to mitigate performance impact as much as possible, mimic the
linear and frag parts within skb by storing the first address from XSK
descriptor at sk_buff::destructor_arg. For fragments, store them at ::cb
via list. The nodes that will go onto list will be allocated via
kmem_cache. xsk_destruct_skb() will consume address stored at
::destructor_arg and optionally go through list from ::cb, if count of
descriptors associated with this particular skb is bigger than 1.

Previous approach where whole array for storing UMEM addresses from XSK
descriptors was pre-allocated during first fragment processing yielded
too big performance regression for 64b traffic. In current approach
impact is much reduced on my tests and for jumbo frames I observed
traffic being slower by at most 9%.

Magnus suggested to have this way of processing special cased for
XDP_SHARED_UMEM, so we would identify this during bind and set different
hooks for 'backpressure mechanism' on CQ and for skb destructor, but
given that results looked promising on my side I decided to have a
single data path for XSK generic Tx. I suppose other auxiliary stuff
would have to land as well in order to make it work.

Fixes: b7f72a30e9ac ("xsk: introduce wrappers and helpers for supporting multi-buffer in Tx path")
Reported-by: Eryk Kubanski <e.kubanski@partner.samsung.com>
Closes: https://lore.kernel.org/netdev/20250530103456.53564-1-e.kubanski@partner.samsung.com/
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20250904194907.2342177-1-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 net/xdp/xsk.c       | 113 ++++++++++++++++++++++++++++++++++++++------
 net/xdp/xsk_queue.h |  12 +++++
 2 files changed, 111 insertions(+), 14 deletions(-)

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9c3acecc14b1..72e34bd2d925 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -36,6 +36,20 @@
 #define TX_BATCH_SIZE 32
 #define MAX_PER_SOCKET_BUDGET 32
 
+struct xsk_addr_node {
+	u64 addr;
+	struct list_head addr_node;
+};
+
+struct xsk_addr_head {
+	u32 num_descs;
+	struct list_head addrs_list;
+};
+
+static struct kmem_cache *xsk_tx_generic_cache;
+
+#define XSKCB(skb) ((struct xsk_addr_head *)((skb)->cb))
+
 void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
 	if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
@@ -532,24 +546,43 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 	return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
 }
 
-static int xsk_cq_reserve_addr_locked(struct xsk_buff_pool *pool, u64 addr)
+static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool)
 {
 	unsigned long flags;
 	int ret;
 
 	spin_lock_irqsave(&pool->cq_lock, flags);
-	ret = xskq_prod_reserve_addr(pool->cq, addr);
+	ret = xskq_prod_reserve(pool->cq);
 	spin_unlock_irqrestore(&pool->cq_lock, flags);
 
 	return ret;
 }
 
-static void xsk_cq_submit_locked(struct xsk_buff_pool *pool, u32 n)
+static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool,
+				      struct sk_buff *skb)
 {
+	struct xsk_addr_node *pos, *tmp;
+	u32 descs_processed = 0;
 	unsigned long flags;
+	u32 idx;
 
 	spin_lock_irqsave(&pool->cq_lock, flags);
-	xskq_prod_submit_n(pool->cq, n);
+	idx = xskq_get_prod(pool->cq);
+
+	xskq_prod_write_addr(pool->cq, idx,
+			     (u64)(uintptr_t)skb_shinfo(skb)->destructor_arg);
+	descs_processed++;
+
+	if (unlikely(XSKCB(skb)->num_descs > 1)) {
+		list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) {
+			xskq_prod_write_addr(pool->cq, idx + descs_processed,
+					     pos->addr);
+			descs_processed++;
+			list_del(&pos->addr_node);
+			kmem_cache_free(xsk_tx_generic_cache, pos);
+		}
+	}
+	xskq_prod_submit_n(pool->cq, descs_processed);
 	spin_unlock_irqrestore(&pool->cq_lock, flags);
 }
 
@@ -562,9 +595,14 @@ static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n)
 	spin_unlock_irqrestore(&pool->cq_lock, flags);
 }
 
+static void xsk_inc_num_desc(struct sk_buff *skb)
+{
+	XSKCB(skb)->num_descs++;
+}
+
 static u32 xsk_get_num_desc(struct sk_buff *skb)
 {
-	return skb ? (long)skb_shinfo(skb)->destructor_arg : 0;
+	return XSKCB(skb)->num_descs;
 }
 
 static void xsk_destruct_skb(struct sk_buff *skb)
@@ -576,23 +614,33 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 		*compl->tx_timestamp = ktime_get_tai_fast_ns();
 	}
 
-	xsk_cq_submit_locked(xdp_sk(skb->sk)->pool, xsk_get_num_desc(skb));
+	xsk_cq_submit_addr_locked(xdp_sk(skb->sk)->pool, skb);
 	sock_wfree(skb);
 }
 
-static void xsk_set_destructor_arg(struct sk_buff *skb)
+static void xsk_set_destructor_arg(struct sk_buff *skb, u64 addr)
 {
-	long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1;
-
-	skb_shinfo(skb)->destructor_arg = (void *)num;
+	BUILD_BUG_ON(sizeof(struct xsk_addr_head) > sizeof(skb->cb));
+	INIT_LIST_HEAD(&XSKCB(skb)->addrs_list);
+	XSKCB(skb)->num_descs = 0;
+	skb_shinfo(skb)->destructor_arg = (void *)(uintptr_t)addr;
 }
 
 static void xsk_consume_skb(struct sk_buff *skb)
 {
 	struct xdp_sock *xs = xdp_sk(skb->sk);
+	u32 num_descs = xsk_get_num_desc(skb);
+	struct xsk_addr_node *pos, *tmp;
+
+	if (unlikely(num_descs > 1)) {
+		list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) {
+			list_del(&pos->addr_node);
+			kmem_cache_free(xsk_tx_generic_cache, pos);
+		}
+	}
 
 	skb->destructor = sock_wfree;
-	xsk_cq_cancel_locked(xs->pool, xsk_get_num_desc(skb));
+	xsk_cq_cancel_locked(xs->pool, num_descs);
 	/* Free skb without triggering the perf drop trace */
 	consume_skb(skb);
 	xs->skb = NULL;
@@ -609,6 +657,7 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 {
 	struct xsk_buff_pool *pool = xs->pool;
 	u32 hr, len, ts, offset, copy, copied;
+	struct xsk_addr_node *xsk_addr;
 	struct sk_buff *skb = xs->skb;
 	struct page *page;
 	void *buffer;
@@ -623,6 +672,19 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
 			return ERR_PTR(err);
 
 		skb_reserve(skb, hr);
+
+		xsk_set_destructor_arg(skb, desc->addr);
+	} else {
+		xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
+		if (!xsk_addr)
+			return ERR_PTR(-ENOMEM);
+
+		/* in case of -EOVERFLOW that could happen below,
+		 * xsk_consume_skb() will release this node as whole skb
+		 * would be dropped, which implies freeing all list elements
+		 */
+		xsk_addr->addr = desc->addr;
+		list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list);
 	}
 
 	addr = desc->addr;
@@ -694,8 +756,11 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 			err = skb_store_bits(skb, 0, buffer, len);
 			if (unlikely(err))
 				goto free_err;
+
+			xsk_set_destructor_arg(skb, desc->addr);
 		} else {
 			int nr_frags = skb_shinfo(skb)->nr_frags;
+			struct xsk_addr_node *xsk_addr;
 			struct page *page;
 			u8 *vaddr;
 
@@ -710,12 +775,22 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 				goto free_err;
 			}
 
+			xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
+			if (!xsk_addr) {
+				__free_page(page);
+				err = -ENOMEM;
+				goto free_err;
+			}
+
 			vaddr = kmap_local_page(page);
 			memcpy(vaddr, buffer, len);
 			kunmap_local(vaddr);
 
 			skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE);
 			refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc);
+
+			xsk_addr->addr = desc->addr;
+			list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list);
 		}
 
 		if (first_frag && desc->options & XDP_TX_METADATA) {
@@ -759,7 +834,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 	skb->mark = READ_ONCE(xs->sk.sk_mark);
 	skb->destructor = xsk_destruct_skb;
 	xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
-	xsk_set_destructor_arg(skb);
+	xsk_inc_num_desc(skb);
 
 	return skb;
 
@@ -769,7 +844,7 @@ free_err:
 
 	if (err == -EOVERFLOW) {
 		/* Drop the packet */
-		xsk_set_destructor_arg(xs->skb);
+		xsk_inc_num_desc(xs->skb);
 		xsk_drop_skb(xs->skb);
 		xskq_cons_release(xs->tx);
 	} else {
@@ -812,7 +887,7 @@ static int __xsk_generic_xmit(struct sock *sk)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
-		err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr);
+		err = xsk_cq_reserve_locked(xs->pool);
 		if (err) {
 			err = -EAGAIN;
 			goto out;
@@ -1815,8 +1890,18 @@ static int __init xsk_init(void)
 	if (err)
 		goto out_pernet;
 
+	xsk_tx_generic_cache = kmem_cache_create("xsk_generic_xmit_cache",
+						 sizeof(struct xsk_addr_node),
+						 0, SLAB_HWCACHE_ALIGN, NULL);
+	if (!xsk_tx_generic_cache) {
+		err = -ENOMEM;
+		goto out_unreg_notif;
+	}
+
 	return 0;
 
+out_unreg_notif:
+	unregister_netdevice_notifier(&xsk_netdev_notifier);
 out_pernet:
 	unregister_pernet_subsys(&xsk_net_ops);
 out_sk:
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 46d87e961ad6..f16f390370dc 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -344,6 +344,11 @@ static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
 
 /* Functions for producers */
 
+static inline u32 xskq_get_prod(struct xsk_queue *q)
+{
+	return READ_ONCE(q->ring->producer);
+}
+
 static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max)
 {
 	u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons);
@@ -390,6 +395,13 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr)
 	return 0;
 }
 
+static inline void xskq_prod_write_addr(struct xsk_queue *q, u32 idx, u64 addr)
+{
+	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+
+	ring->desc[idx & q->ring_mask] = addr;
+}
+
 static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
 					      u32 nb_entries)
 {

From 0d80e7f951be1bdd08d328fd87694be0d6e8aaa8 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Tue, 9 Sep 2025 18:49:59 +0000
Subject: [PATCH 10/15] rqspinlock: Choose trylock fallback for NMI waiters

Currently, out of all 3 types of waiters in the rqspinlock slow path
(i.e., pending bit waiter, wait queue head waiter, and wait queue
non-head waiter), only the pending bit waiter and wait queue head
waiters apply deadlock checks and a timeout on their waiting loop. The
assumption here was that the wait queue head's forward progress would be
sufficient to identify cases where the lock owner or pending bit waiter
is stuck, and non-head waiters relying on the head waiter would prove to
be sufficient for their own forward progress.

However, the head waiter itself can be preempted by a non-head waiter
for the same lock (AA) or a different lock (ABBA) in a manner that
impedes its forward progress. In such a case, non-head waiters not
performing deadlock and timeout checks becomes insufficient, and the
system can enter a state of lockup.

This is typically not a concern with non-NMI lock acquisitions, as lock
holders which in run in different contexts (IRQ, non-IRQ) use "irqsave"
variants of the lock APIs, which naturally excludes such lock holders
from preempting one another on the same CPU.

It might seem likely that a similar case may occur for rqspinlock when
programs are attached to contention tracepoints (begin, end), however,
these tracepoints either precede the enqueue into the wait queue, or
succeed it, therefore cannot be used to preempt a head waiter's waiting
loop.

We must still be careful against nested kprobe and fentry programs that
may attach to the middle of the head's waiting loop to stall forward
progress and invoke another rqspinlock acquisition that proceeds as a
non-head waiter. To this end, drop CC_FLAGS_FTRACE from the rqspinlock.o
object file.

For now, this issue is resolved by falling back to a repeated trylock on
the lock word from NMI context, while performing the deadlock checks to
break out early in case forward progress is impossible, and use the
timeout as a final fallback.

A more involved fix to terminate the queue when such a condition occurs
will be made as a follow up. A selftest to stress this aspect of nested
NMI/non-NMI locking attempts will be added in a subsequent patch to the
bpf-next tree when this fix lands and trees are synchronized.

Reported-by: Josef Bacik <josef@toxicpanda.com>
Fixes: 164c246571e9 ("rqspinlock: Protect waiters in queue from stalls")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250909184959.3509085-1-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/Makefile     | 1 +
 kernel/bpf/rqspinlock.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 269c04a24664..f6cf8c2af5f7 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -62,3 +62,4 @@ CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_queue_stack_maps.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_lpm_trie.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_ringbuf.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_rqspinlock.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c
index 5ab354d55d82..a00561b1d3e5 100644
--- a/kernel/bpf/rqspinlock.c
+++ b/kernel/bpf/rqspinlock.c
@@ -471,7 +471,7 @@ queue:
 	 * any MCS node. This is not the most elegant solution, but is
 	 * simple enough.
 	 */
-	if (unlikely(idx >= _Q_MAX_NODES)) {
+	if (unlikely(idx >= _Q_MAX_NODES || in_nmi())) {
 		lockevent_inc(lock_no_node);
 		RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT);
 		while (!queued_spin_trylock(lock)) {

From df0cb5cb50bd54d3cd4d0d83417ceec6a66404aa Mon Sep 17 00:00:00 2001
From: KaFai Wan <kafai.wan@linux.dev>
Date: Tue, 9 Sep 2025 22:46:14 +0800
Subject: [PATCH 11/15] bpf: Allow fall back to interpreter for programs with
 stack size <= 512

OpenWRT users reported regression on ARMv6 devices after updating to latest
HEAD, where tcpdump filter:

tcpdump "not ether host 3c37121a2b3c and not ether host 184ecbca2a3a \
and not ether host 14130b4d3f47 and not ether host f0f61cf440b7 \
and not ether host a84b4dedf471 and not ether host d022be17e1d7 \
and not ether host 5c497967208b and not ether host 706655784d5b"

fails with warning: "Kernel filter failed: No error information"
when using config:
 # CONFIG_BPF_JIT_ALWAYS_ON is not set
 CONFIG_BPF_JIT_DEFAULT_ON=y

The issue arises because commits:
1. "bpf: Fix array bounds error with may_goto" changed default runtime to
   __bpf_prog_ret0_warn when jit_requested = 1
2. "bpf: Avoid __bpf_prog_ret0_warn when jit fails" returns error when
   jit_requested = 1 but jit fails

This change restores interpreter fallback capability for BPF programs with
stack size <= 512 bytes when jit fails.

Reported-by: Felix Fietkau <nbd@nbd.name>
Closes: https://lore.kernel.org/bpf/2e267b4b-0540-45d8-9310-e127bf95fc63@nbd.name/
Fixes: 6ebc5030e0c5 ("bpf: Fix array bounds error with may_goto")
Signed-off-by: KaFai Wan <kafai.wan@linux.dev>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250909144614.2991253-1-kafai.wan@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/core.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f8ac77d08ca7..e4568d44e827 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2366,8 +2366,7 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
 					 const struct bpf_insn *insn)
 {
 	/* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON
-	 * is not working properly, or interpreter is being used when
-	 * prog->jit_requested is not 0, so warn about it!
+	 * is not working properly, so warn about it!
 	 */
 	WARN_ON_ONCE(1);
 	return 0;
@@ -2468,8 +2467,9 @@ out:
 	return ret;
 }
 
-static void bpf_prog_select_func(struct bpf_prog *fp)
+static bool bpf_prog_select_interpreter(struct bpf_prog *fp)
 {
+	bool select_interpreter = false;
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
 	u32 idx = (round_up(stack_depth, 32) / 32) - 1;
@@ -2478,15 +2478,16 @@ static void bpf_prog_select_func(struct bpf_prog *fp)
 	 * But for non-JITed programs, we don't need bpf_func, so no bounds
 	 * check needed.
 	 */
-	if (!fp->jit_requested &&
-	    !WARN_ON_ONCE(idx >= ARRAY_SIZE(interpreters))) {
+	if (idx < ARRAY_SIZE(interpreters)) {
 		fp->bpf_func = interpreters[idx];
+		select_interpreter = true;
 	} else {
 		fp->bpf_func = __bpf_prog_ret0_warn;
 	}
 #else
 	fp->bpf_func = __bpf_prog_ret0_warn;
 #endif
+	return select_interpreter;
 }
 
 /**
@@ -2505,7 +2506,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	/* In case of BPF to BPF calls, verifier did all the prep
 	 * work with regards to JITing, etc.
 	 */
-	bool jit_needed = fp->jit_requested;
+	bool jit_needed = false;
 
 	if (fp->bpf_func)
 		goto finalize;
@@ -2514,7 +2515,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	    bpf_prog_has_kfunc_call(fp))
 		jit_needed = true;
 
-	bpf_prog_select_func(fp);
+	if (!bpf_prog_select_interpreter(fp))
+		jit_needed = true;
 
 	/* eBPF JITs can rewrite the program in case constant
 	 * blinding is active. However, in case of error during

From 6d78b4473cdb08b74662355a9e8510bde09c511e Mon Sep 17 00:00:00 2001
From: Peilin Ye <yepeilin@google.com>
Date: Tue, 9 Sep 2025 09:52:20 +0000
Subject: [PATCH 12/15] bpf: Tell memcg to use allow_spinning=false path in
 bpf_timer_init()

Currently, calling bpf_map_kmalloc_node() from __bpf_async_init() can
cause various locking issues; see the following stack trace (edited for
style) as one example:

...
 [10.011566]  do_raw_spin_lock.cold
 [10.011570]  try_to_wake_up             (5) double-acquiring the same
 [10.011575]  kick_pool                      rq_lock, causing a hardlockup
 [10.011579]  __queue_work
 [10.011582]  queue_work_on
 [10.011585]  kernfs_notify
 [10.011589]  cgroup_file_notify
 [10.011593]  try_charge_memcg           (4) memcg accounting raises an
 [10.011597]  obj_cgroup_charge_pages        MEMCG_MAX event
 [10.011599]  obj_cgroup_charge_account
 [10.011600]  __memcg_slab_post_alloc_hook
 [10.011603]  __kmalloc_node_noprof
...
 [10.011611]  bpf_map_kmalloc_node
 [10.011612]  __bpf_async_init
 [10.011615]  bpf_timer_init             (3) BPF calls bpf_timer_init()
 [10.011617]  bpf_prog_xxxxxxxxxxxxxxxx_fcg_runnable
 [10.011619]  bpf__sched_ext_ops_runnable
 [10.011620]  enqueue_task_scx           (2) BPF runs with rq_lock held
 [10.011622]  enqueue_task
 [10.011626]  ttwu_do_activate
 [10.011629]  sched_ttwu_pending         (1) grabs rq_lock
...

The above was reproduced on bpf-next (b338cf849ec8) by modifying
./tools/sched_ext/scx_flatcg.bpf.c to call bpf_timer_init() during
ops.runnable(), and hacking the memcg accounting code a bit to make
a bpf_timer_init() call more likely to raise an MEMCG_MAX event.

We have also run into other similar variants (both internally and on
bpf-next), including double-acquiring cgroup_file_kn_lock, the same
worker_pool::lock, etc.

As suggested by Shakeel, fix this by using __GFP_HIGH instead of
GFP_ATOMIC in __bpf_async_init(), so that e.g. if try_charge_memcg()
raises an MEMCG_MAX event, we call __memcg_memory_event() with
@allow_spinning=false and avoid calling cgroup_file_notify() there.

Depends on mm patch
"memcg: skip cgroup_file_notify if spinning is not allowed":
https://lore.kernel.org/bpf/20250905201606.66198-1-shakeel.butt@linux.dev/

v0 approach s/bpf_map_kmalloc_node/bpf_mem_alloc/
https://lore.kernel.org/bpf/20250905061919.439648-1-yepeilin@google.com/
v1 approach:
https://lore.kernel.org/bpf/20250905234547.862249-1-yepeilin@google.com/

Fixes: b00628b1c7d5 ("bpf: Introduce bpf timers.")
Suggested-by: Shakeel Butt <shakeel.butt@linux.dev>
Signed-off-by: Peilin Ye <yepeilin@google.com>
Link: https://lore.kernel.org/r/20250909095222.2121438-1-yepeilin@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/helpers.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index b9b0c5fe33f6..8af62cb243d9 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1274,8 +1274,11 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u
 		goto out;
 	}
 
-	/* allocate hrtimer via map_kmalloc to use memcg accounting */
-	cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, map->numa_node);
+	/* Allocate via bpf_map_kmalloc_node() for memcg accounting. Until
+	 * kmalloc_nolock() is available, avoid locking issues by using
+	 * __GFP_HIGH (GFP_ATOMIC & ~__GFP_RECLAIM).
+	 */
+	cb = bpf_map_kmalloc_node(map, size, __GFP_HIGH, map->numa_node);
 	if (!cb) {
 		ret = -ENOMEM;
 		goto out;

From a3967baad4d533dc254c31e0d221e51c8d223d58 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Tue, 9 Sep 2025 23:26:12 +0000
Subject: [PATCH 13/15] tcp_bpf: Call sk_msg_free() when tcp_bpf_send_verdict()
 fails to allocate psock->cork.

syzbot reported the splat below. [0]

The repro does the following:

  1. Load a sk_msg prog that calls bpf_msg_cork_bytes(msg, cork_bytes)
  2. Attach the prog to a SOCKMAP
  3. Add a socket to the SOCKMAP
  4. Activate fault injection
  5. Send data less than cork_bytes

At 5., the data is carried over to the next sendmsg() as it is
smaller than the cork_bytes specified by bpf_msg_cork_bytes().

Then, tcp_bpf_send_verdict() tries to allocate psock->cork to hold
the data, but this fails silently due to fault injection + __GFP_NOWARN.

If the allocation fails, we need to revert the sk->sk_forward_alloc
change done by sk_msg_alloc().

Let's call sk_msg_free() when tcp_bpf_send_verdict fails to allocate
psock->cork.

The "*copied" also needs to be updated such that a proper error can
be returned to the caller, sendmsg. It fails to allocate psock->cork.
Nothing has been corked so far, so this patch simply sets "*copied"
to 0.

[0]:
WARNING: net/ipv4/af_inet.c:156 at inet_sock_destruct+0x623/0x730 net/ipv4/af_inet.c:156, CPU#1: syz-executor/5983
Modules linked in:
CPU: 1 UID: 0 PID: 5983 Comm: syz-executor Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
RIP: 0010:inet_sock_destruct+0x623/0x730 net/ipv4/af_inet.c:156
Code: 0f 0b 90 e9 62 fe ff ff e8 7a db b5 f7 90 0f 0b 90 e9 95 fe ff ff e8 6c db b5 f7 90 0f 0b 90 e9 bb fe ff ff e8 5e db b5 f7 90 <0f> 0b 90 e9 e1 fe ff ff 89 f9 80 e1 07 80 c1 03 38 c1 0f 8c 9f fc
RSP: 0018:ffffc90000a08b48 EFLAGS: 00010246
RAX: ffffffff8a09d0b2 RBX: dffffc0000000000 RCX: ffff888024a23c80
RDX: 0000000000000100 RSI: 0000000000000fff RDI: 0000000000000000
RBP: 0000000000000fff R08: ffff88807e07c627 R09: 1ffff1100fc0f8c4
R10: dffffc0000000000 R11: ffffed100fc0f8c5 R12: ffff88807e07c380
R13: dffffc0000000000 R14: ffff88807e07c60c R15: 1ffff1100fc0f872
FS:  00005555604c4500(0000) GS:ffff888125af1000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005555604df5c8 CR3: 0000000032b06000 CR4: 00000000003526f0
Call Trace:
 <IRQ>
 __sk_destruct+0x86/0x660 net/core/sock.c:2339
 rcu_do_batch kernel/rcu/tree.c:2605 [inline]
 rcu_core+0xca8/0x1770 kernel/rcu/tree.c:2861
 handle_softirqs+0x286/0x870 kernel/softirq.c:579
 __do_softirq kernel/softirq.c:613 [inline]
 invoke_softirq kernel/softirq.c:453 [inline]
 __irq_exit_rcu+0xca/0x1f0 kernel/softirq.c:680
 irq_exit_rcu+0x9/0x30 kernel/softirq.c:696
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1052 [inline]
 sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1052
 </IRQ>

Fixes: 4f738adba30a ("bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data")
Reported-by: syzbot+4cabd1d2fa917a456db8@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/68c0b6b5.050a0220.3c6139.0013.GAE@google.com/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250909232623.4151337-1-kuniyu@google.com
---
 net/ipv4/tcp_bpf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index ba581785adb4..a268e1595b22 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -408,8 +408,11 @@ more_data:
 		if (!psock->cork) {
 			psock->cork = kzalloc(sizeof(*psock->cork),
 					      GFP_ATOMIC | __GFP_NOWARN);
-			if (!psock->cork)
+			if (!psock->cork) {
+				sk_msg_free(sk, msg);
+				*copied = 0;
 				return -ENOMEM;
+			}
 		}
 		memcpy(psock->cork, msg, sizeof(*msg));
 		return 0;

From e25ddfb388c8b7e5f20e3bf38d627fb485003781 Mon Sep 17 00:00:00 2001
From: Leon Hwang <leon.hwang@linux.dev>
Date: Wed, 10 Sep 2025 20:57:39 +0800
Subject: [PATCH 14/15] bpf: Reject bpf_timer for PREEMPT_RT

When enable CONFIG_PREEMPT_RT, the kernel will warn when run timer
selftests by './test_progs -t timer':

BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48

In order to avoid such warning, reject bpf_timer in verifier when
PREEMPT_RT is enabled.

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
Link: https://lore.kernel.org/r/20250910125740.52172-2-leon.hwang@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c89e2b1bc644..9fb1f957a093 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -8547,6 +8547,10 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno,
 		verifier_bug(env, "Two map pointers in a timer helper");
 		return -EFAULT;
 	}
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		verbose(env, "bpf_timer cannot be used for PREEMPT_RT.\n");
+		return -EOPNOTSUPP;
+	}
 	meta->map_uid = reg->map_uid;
 	meta->map_ptr = map;
 	return 0;

From fbdd61c94bcb09b0c0eb0655917bf4193d07aac1 Mon Sep 17 00:00:00 2001
From: Leon Hwang <leon.hwang@linux.dev>
Date: Wed, 10 Sep 2025 20:57:40 +0800
Subject: [PATCH 15/15] selftests/bpf: Skip timer cases when bpf_timer is not
 supported

When enable CONFIG_PREEMPT_RT, verifier will reject bpf_timer with
returning -EOPNOTSUPP.

Therefore, skip test cases when errno is EOPNOTSUPP.

cd tools/testing/selftests/bpf
./test_progs -t timer
125     free_timer:SKIP
456     timer:SKIP
457/1   timer_crash/array:SKIP
457/2   timer_crash/hash:SKIP
457     timer_crash:SKIP
458     timer_lockup:SKIP
459     timer_mim:SKIP
Summary: 5/0 PASSED, 6 SKIPPED, 0 FAILED

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
Link: https://lore.kernel.org/r/20250910125740.52172-3-leon.hwang@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/prog_tests/free_timer.c   | 4 ++++
 tools/testing/selftests/bpf/prog_tests/timer.c        | 4 ++++
 tools/testing/selftests/bpf/prog_tests/timer_crash.c  | 4 ++++
 tools/testing/selftests/bpf/prog_tests/timer_lockup.c | 4 ++++
 tools/testing/selftests/bpf/prog_tests/timer_mim.c    | 4 ++++
 5 files changed, 20 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c
index b7b77a6b2979..0de8facca4c5 100644
--- a/tools/testing/selftests/bpf/prog_tests/free_timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c
@@ -124,6 +124,10 @@ void test_free_timer(void)
 	int err;
 
 	skel = free_timer__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(skel, "open_load"))
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index d66687f1ee6a..56f660ca567b 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -86,6 +86,10 @@ void serial_test_timer(void)
 	int err;
 
 	timer_skel = timer__open_and_load();
+	if (!timer_skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
index f74b82305da8..b841597c8a3a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
@@ -12,6 +12,10 @@ static void test_timer_crash_mode(int mode)
 	struct timer_crash *skel;
 
 	skel = timer_crash__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
 		return;
 	skel->bss->pid = getpid();
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
index 1a2f99596916..eb303fa1e09a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
@@ -59,6 +59,10 @@ void test_timer_lockup(void)
 	}
 
 	skel = timer_lockup__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load"))
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index 9ff7843909e7..c930c7d7105b 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -65,6 +65,10 @@ void serial_test_timer_mim(void)
 		goto cleanup;
 
 	timer_skel = timer_mim__open_and_load();
+	if (!timer_skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
 		goto cleanup;