From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
To: bpf@vger.kernel.org
Cc: Tejun Heo <tj@kernel.org>, Alexei Starovoitov <ast@kernel.org>,
Andrii Nakryiko <andrii@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Eduard Zingerman <eddyz87@gmail.com>,
Emil Tsalapatis <emil@etsalapatis.com>,
kkd@meta.com, kernel-team@meta.com
Subject: [PATCH bpf-next v1 4/9] bpf, x86: Convert struct_ops arena arguments in the trampoline
Date: Thu, 16 Jul 2026 00:00:44 +0200 [thread overview]
Message-ID: <20260715220052.1590783-5-memxor@gmail.com> (raw)
In-Reply-To: <20260715220052.1590783-1-memxor@gmail.com>
From: Tejun Heo <tj@kernel.org>
Implement the struct_ops arena argument conversion on x86. save_args()
gains the conversion map from bpf_tramp_collect_arena_args() and, as it
copies each native argument into the BPF ctx, routes a marked slot
through RAX:
movl %esrc, %eax /* truncate and clear the upper 32 bits */
subl $base_lo, %eax
movq %rax, ctx_slot
A nullable slot tests the full 64-bit kernel pointer first:
movq %rsrc, %rax
testq %rax, %rax
jz 1f
subl $base_lo, %eax
1:
movq %rax, ctx_slot
The 32-bit subtraction is sufficient since (u32)(kaddr - base) ==
(u32)kaddr - (u32)base, and it clears the upper half as the JITs require
of arena pointer registers. Stack-passed arguments already reload
through RAX, so only the subtraction (and the NULL test) is inserted
there. The marked slots are tracked with a running slot counter shared
by the register and stack branches, matching the flattened ctx offsets
in ctx_arg_info. The size probe reruns the same emission with the same
tnodes, so the image size matches by construction.
With both the kfunc and struct_ops directions implemented, flip
bpf_jit_supports_arena_args() on for x86.
v3: New patch, moving the conversion from a BPF entry prologue into the
trampoline, per review from Kumar.
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
arch/x86/net/bpf_jit_comp.c | 64 +++++++++++++++++++++++++++++++++----
1 file changed, 57 insertions(+), 7 deletions(-)
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index dd9009fcdc39..2f25353f135b 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -3042,12 +3042,39 @@ static int get_nr_used_regs(const struct btf_func_model *m)
return nr_used_regs;
}
+/*
+ * Convert an arena kernel address into the arena pointer form on its way
+ * into the BPF ctx, rax = (u32)(src - kern_vm_start). A nullable arg
+ * preserves NULL, tested on the full 64-bit kernel pointer. The 32-bit
+ * subtraction both truncates and clears the upper half, so the stored
+ * value satisfies the JIT invariant for arena pointer registers.
+ */
+static void emit_arena_arg_conv(u8 **pprog, u32 src_reg, bool nullable, u32 base_lo)
+{
+ u8 *prog = *pprog;
+
+ if (nullable) {
+ if (src_reg != BPF_REG_0)
+ emit_mov_reg(&prog, true, BPF_REG_0, src_reg);
+ /* test rax, rax; jz over the 5-byte sub */
+ EMIT3(0x48, 0x85, 0xC0);
+ EMIT2(X86_JE, 5);
+ } else if (src_reg != BPF_REG_0) {
+ emit_mov_reg(&prog, false, BPF_REG_0, src_reg);
+ }
+ /* sub eax, base_lo */
+ EMIT1_off32(0x2D, base_lo);
+
+ *pprog = prog;
+}
+
static void save_args(const struct btf_func_model *m, u8 **prog,
- int stack_size, bool for_call_origin, u32 flags)
+ int stack_size, bool for_call_origin, u32 flags,
+ const struct bpf_tramp_arena_args *aargs)
{
int arg_regs, first_off = 0, nr_regs = 0, nr_stack_slots = 0;
bool use_jmp = bpf_trampoline_use_jmp(flags);
- int i, j;
+ int i, j, slot = 0;
/* Store function arguments to stack.
* For a function that accepts two pointers the sequence will be:
@@ -3088,6 +3115,10 @@ static void save_args(const struct btf_func_model *m, u8 **prog,
for (j = 0; j < arg_regs; j++) {
emit_ldx(prog, BPF_DW, BPF_REG_0, BPF_REG_FP,
nr_stack_slots * 8 + 16 + (!use_jmp) * 8);
+ if (aargs && (aargs->slots & BIT(slot)))
+ emit_arena_arg_conv(prog, BPF_REG_0,
+ aargs->nullable_slots & BIT(slot),
+ (u32)aargs->kern_vm_start);
emit_stx(prog, BPF_DW, BPF_REG_FP, BPF_REG_0,
-stack_size);
@@ -3095,6 +3126,7 @@ static void save_args(const struct btf_func_model *m, u8 **prog,
first_off = stack_size;
stack_size -= 8;
nr_stack_slots++;
+ slot++;
}
} else {
/* Only copy the arguments on-stack to current
@@ -3103,16 +3135,24 @@ static void save_args(const struct btf_func_model *m, u8 **prog,
*/
if (for_call_origin) {
nr_regs += arg_regs;
+ slot += arg_regs;
continue;
}
/* copy the arguments from regs into stack */
for (j = 0; j < arg_regs; j++) {
- emit_stx(prog, BPF_DW, BPF_REG_FP,
- nr_regs == 5 ? X86_REG_R9 : BPF_REG_1 + nr_regs,
- -stack_size);
+ u32 src = nr_regs == 5 ? X86_REG_R9 : BPF_REG_1 + nr_regs;
+
+ if (aargs && (aargs->slots & BIT(slot))) {
+ emit_arena_arg_conv(prog, src,
+ aargs->nullable_slots & BIT(slot),
+ (u32)aargs->kern_vm_start);
+ src = BPF_REG_0;
+ }
+ emit_stx(prog, BPF_DW, BPF_REG_FP, src, -stack_size);
stack_size -= 8;
nr_regs++;
+ slot++;
}
}
}
@@ -3403,11 +3443,13 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
struct bpf_tramp_nodes *fentry = &tnodes[BPF_TRAMP_FENTRY];
struct bpf_tramp_nodes *fexit = &tnodes[BPF_TRAMP_FEXIT];
struct bpf_tramp_nodes *fmod_ret = &tnodes[BPF_TRAMP_MODIFY_RETURN];
+ struct bpf_tramp_arena_args aargs;
void *orig_call = func_addr;
int cookie_off, cookie_cnt;
u8 **branches = NULL;
u64 func_meta;
u8 *prog;
+ bool has_aargs;
bool save_ret;
/*
@@ -3418,6 +3460,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
WARN_ON_ONCE((flags & BPF_TRAMP_F_INDIRECT) &&
(flags & ~(BPF_TRAMP_F_INDIRECT | BPF_TRAMP_F_RET_FENTRY_RET)));
+ has_aargs = bpf_tramp_collect_arena_args(tnodes, flags, &aargs);
+
/* extra registers for struct arguments */
for (i = 0; i < m->nr_args; i++) {
if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
@@ -3555,7 +3599,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
emit_store_stack_imm64(&prog, BPF_REG_0, -ip_off, (long)func_addr);
}
- save_args(m, &prog, regs_off, false, flags);
+ save_args(m, &prog, regs_off, false, flags,
+ has_aargs ? &aargs : NULL);
if (flags & BPF_TRAMP_F_CALL_ORIG) {
/* arg1: mov rdi, im */
@@ -3597,7 +3642,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
if (flags & BPF_TRAMP_F_CALL_ORIG) {
restore_regs(m, &prog, regs_off);
- save_args(m, &prog, arg_stack_off, true, flags);
+ save_args(m, &prog, arg_stack_off, true, flags, NULL);
if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
/* Before calling the original function, load the
@@ -4099,6 +4144,11 @@ bool bpf_jit_supports_stack_args(void)
return true;
}
+bool bpf_jit_supports_arena_args(void)
+{
+ return true;
+}
+
void *bpf_arch_text_copy(void *dst, void *src, size_t len)
{
if (text_poke_copy(dst, src, len) == NULL)
--
2.53.0
next prev parent reply other threads:[~2026-07-15 22:00 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-15 22:00 [PATCH bpf-next v1 0/9] Add arena argument support to kfuncs and struct_ops Kumar Kartikeya Dwivedi
2026-07-15 22:00 ` [PATCH bpf-next v1 1/9] bpf: Support __arena and __arena_nullable kfunc argument suffixes Kumar Kartikeya Dwivedi
2026-07-15 23:05 ` bot+bpf-ci
2026-07-15 22:00 ` [PATCH bpf-next v1 2/9] bpf: Support __arena and __arena_nullable on struct_ops stub arguments Kumar Kartikeya Dwivedi
2026-07-15 22:22 ` sashiko-bot
2026-07-15 22:00 ` [PATCH bpf-next v1 3/9] bpf, x86: JIT __arena kfunc argument rebasing Kumar Kartikeya Dwivedi
2026-07-15 22:00 ` Kumar Kartikeya Dwivedi [this message]
2026-07-15 22:00 ` [PATCH bpf-next v1 5/9] selftests/bpf: Add kfunc __arena and __arena_nullable argument tests Kumar Kartikeya Dwivedi
2026-07-15 22:00 ` [PATCH bpf-next v1 6/9] selftests/bpf: Add JIT-sequence tests for __arena kfunc arguments Kumar Kartikeya Dwivedi
2026-07-15 22:00 ` [PATCH bpf-next v1 7/9] selftests/bpf: Add struct_ops __arena and __arena_nullable argument tests Kumar Kartikeya Dwivedi
2026-07-15 22:00 ` [PATCH bpf-next v1 8/9] bpf, x86: Fix stack-passed arguments for indirect trampolines Kumar Kartikeya Dwivedi
2026-07-15 22:14 ` sashiko-bot
2026-07-15 22:51 ` bot+bpf-ci
2026-07-15 22:00 ` [PATCH bpf-next v1 9/9] selftests/bpf: Test stack-passed struct_ops arena arguments Kumar Kartikeya Dwivedi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260715220052.1590783-5-memxor@gmail.com \
--to=memxor@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=eddyz87@gmail.com \
--cc=emil@etsalapatis.com \
--cc=kernel-team@meta.com \
--cc=kkd@meta.com \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.