From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from 66-220-144-179.mail-mxout.facebook.com (66-220-144-179.mail-mxout.facebook.com [66.220.144.179]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 30DC43B5DE9 for ; Fri, 9 Oct 2026 04:16:08 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=66.220.144.179 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791519379; cv=none; b=QW5aCp31DM5EsdOLMmXQ0nSbb08X15SIm02URVkzOjDlv/7qmoMMBsfslSr0KCVVN9RX7miD3K+V1cXSnIU3KjjH+8Df2cg+QsmzLzDZr/Jk8G3JQihXqH9C7xoKt5LT7CSFecPZoq3vUdb9nmoLZTdwvN4tTgGSyh41fFLLfWQ= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791519379; c=relaxed/simple; bh=h3pFRc1iqvIVcLcVo9u4FOcSxWDpMWs+yAHqSuTK6z8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=jdWGgMpznsUz3yBsEzMe45crDkXTPrybOGeh9gLBOx+0+novASVYaAwXOTBCmBKTpLUmUehosWIF6NZMYneMMfIrZ0IpjIYO5lur8nkx85ZidAgvG/Avi28+AeGU8+l3ioRl7pD5JYCa74/c0u71N34tU5G+Eo/KfBL6K/WSB4I= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.dev; spf=fail smtp.mailfrom=linux.dev; arc=none smtp.client-ip=66.220.144.179 Authentication-Results: smtp.subspace.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=linux.dev Received: by devvm16039.vll0.facebook.com (Postfix, from userid 128203) id 1F0BA3008CBA07; Thu, 8 Oct 2026 21:16:05 -0700 (PDT) From: Yonghong Song To: bpf@vger.kernel.org Cc: Alexei Starovoitov , Andrii Nakryiko , Daniel Borkmann , Eduard Zingerman , kernel-team@fb.com Subject: [PATCH bpf-next v10 15/24] bpf, arm64: Dispatch exception cleanup pads at run time Date: Thu, 8 Oct 2026 21:16:05 -0700 Message-ID: <20261009041605.33513-1-yonghong.song@linux.dev> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20261009041447.17092-1-yonghong.song@linux.dev> References: <20261009041447.17092-1-yonghong.song@linux.dev> Precedence: bulk X-Mailing-List: bpf@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Add what bpf_unwind() relies on to send each frame of a program to its landing pad or its epilogue on arm64, as the previous patch does for x86-64: - arch_bpf_stack_walk_ra(): walks the frame records with the kernel unwinder, handing each return address to the consumer and storing a new one back into the record it was read from. The first frame, whose return into bpf_unwind() comes from the walk's own record, is skipped. - With CONFIG_ARM64_PTR_AUTH_KERNEL and a CPU that supports address authentication, the new address is signed as the BPF prologue signs the link register, with PACIASP and the record + 16 as modifier. - Once the image is final, the JIT fills in the native cleanup table and records each function's epilogue address in aux->epilogue_ip, where an unwind sends a frame with no pad. - bpf_jit_supports_cleanup_pads() says yes, also with a shadow call stack: only JITed frames' records are written, and JITed code keeps no x18 copy of its return address. A pad needs no BTI: it is only reached as a return address. Signed-off-by: Yonghong Song --- arch/arm64/kernel/stacktrace.c | 74 ++++++++++++++++++++++++++++++++++ arch/arm64/net/bpf_jit_comp.c | 16 ++++++++ 2 files changed, 90 insertions(+) diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrac= e.c index 3ebcf8c53fb0..56d1310eca32 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -445,6 +445,80 @@ noinline noinstr void arch_bpf_stack_walk(bool (*con= sume_entry)(void *cookie, u6 kunwind_stack_walk(arch_bpf_unwind_consume_entry, &data, current, NULL)= ; } =20 +struct bpf_unwind_ra_consume_entry_data { + bool (*consume_entry)(void *cookie, u64 ip, u64 sp, u64 fp, u64 *ra); + void *cookie; + unsigned long record; + bool seen_first; +}; + +static u64 bpf_unwind_sign_ra(u64 ra, u64 modifier) +{ + asm volatile(ARM64_ASM_PREAMBLE + ".arch_extension pauth\n" + " pacia %0, %1" + : "+r" (ra) : "r" (modifier)); + return ra; +} + +/* PACIASP's modifier is the entry sp, record + 16 for a BPF prologue. *= / +static void bpf_unwind_store_ra(unsigned long record, u64 ra) +{ + struct frame_record *rec =3D (struct frame_record *)record; + + /* + * Whether the slot holds a signed address is a property of the build, + * not one to be read off the value: a PAC can come out equal to the + * bits stripping puts back, and a signed address would then be taken + * for an unsigned one. What signs is CONFIG_ARM64_PTR_AUTH_KERNEL -- + * the prologue here, and -mbranch-protection for everything the + * compiler emits. + */ + if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) && + system_supports_address_auth()) + ra =3D bpf_unwind_sign_ra(ra, record + sizeof(struct frame_record)); + WRITE_ONCE(rec->lr, ra); +} + +static bool +arch_bpf_unwind_ra_consume_entry(const struct kunwind_state *state, void= *cookie) +{ + struct bpf_unwind_ra_consume_entry_data *data =3D cookie; + unsigned long record =3D data->record; + bool seen_first =3D data->seen_first; + u64 ra =3D state->common.pc; + bool cont; + + /* The record this frame's return address will have come out of. */ + data->record =3D state->common.fp; + data->seen_first =3D true; + + /* + * The first pc returns into bpf_unwind(), from this walk's own frame + * record: not a BPF frame, and not one to redirect. + */ + if (!seen_first) + return true; + /* A consumer that stops still gets to redirect the frame it stopped on= . */ + cont =3D data->consume_entry(data->cookie, state->common.pc, 0, + state->common.fp, &ra); + if (ra !=3D state->common.pc) + bpf_unwind_store_ra(record, ra); + return cont; +} + +noinline noinstr void arch_bpf_stack_walk_ra(bool (*consume_entry)(void = *cookie, u64 ip, u64 sp, + u64 fp, u64 *ra), + void *cookie) +{ + struct bpf_unwind_ra_consume_entry_data data =3D { + .consume_entry =3D consume_entry, + .cookie =3D cookie, + }; + + kunwind_stack_walk(arch_bpf_unwind_ra_consume_entry, &data, current, NU= LL); +} + static const char *state_source_string(const struct kunwind_state *state= ) { switch (state->source) { diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.= c index 08725cde0c5a..11e94e3bf859 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -2423,6 +2423,17 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_ve= rifier_env *env, struct bpf_pr * reasons, expects to point to the next instruction) */ bpf_prog_update_insn_ptrs(prog, ctx.offset, ctx.ro_image); + + /* + * Same byte offsets, consumed by the bpf_unwind() walk: + * turn the cleanup records into native address ranges now that + * the image is final. + */ + bpf_exc_fill_native_ranges(prog, ctx.offset, ctx.ro_image); + + /* Where an unwind sends a frame with no pad. */ + prog->aux->epilogue_ip =3D (u64)ctx.ro_image + + ctx.epilogue_offset * AARCH64_INSN_SIZE; out_off: if (!ro_header && priv_stack_ptr) { free_percpu(priv_stack_ptr); @@ -3415,6 +3426,11 @@ bool bpf_jit_supports_exceptions(void) return true; } =20 +bool bpf_jit_supports_cleanup_pads(void) +{ + return true; +} + bool bpf_jit_supports_arena(void) { return true; --=20 2.53.0-Meta