All of lore.kernel.org
 help / color / mirror / Atom feed
From: Vineet Gupta <vineet.gupta@linux.dev>
To: ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
	eddyz87@gmail.com, memxor@gmail.com
Cc: martin.lau@linux.dev, song@kernel.org, yonghong.song@linux.dev,
	jolsa@kernel.org, emil@etsalapatis.com, ihor.solodrai@linux.dev,
	john.fastabend@gmail.com, shuah@kernel.org, bpf@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org,
	Vineet Gupta <vineet.gupta@linux.dev>
Subject: [PATCH bpf-next v2 09/13] bpf: track low-32 scalar equality across narrowing stack fills
Date: Thu, 10 Sep 2026 22:16:31 +0530	[thread overview]
Message-ID: <20260910164635.459558-10-vineet.gupta@linux.dev> (raw)
In-Reply-To: <20260910164635.459558-1-vineet.gupta@linux.dev>

A 32-bit fill from a wider spilled scalar has the same shape as a 32-bit
mov from a wider source: the destination shares the slot's low 32 bits and
nothing else. The relation was dropped instead of recorded, so a later
narrowing of the spilled value never reached the filled register:

  r6 = ...                  /* full 64-bit unknown */
  *(u64 *)(r10 - 8) = r6;   /* slot linked to r6 */
  r2 = *(u32 *)(r10 - 8);   /* narrowing fill */
  if w6 != 0 goto ...       /* not taken: r6's low 32 bits are 0 */
  if r2 == 0 goto ...       /* not deduced today */

Record a low-32 link, as the mov arm does. Stack slots are already
first-class members of an ->id set, so sync_linked_regs() and the
reconstruction helpers apply unchanged. A fill narrower than 32 bits has
no expressible relation and still drops it.

Which kind to record depends on how the load fills the high half, so
check_stack_read() takes is_ldsx. Doing it there rather than correcting
afterwards in check_mem_access() keeps a single assignment.

check_mem_access() in turn no longer clears the id of a ->subreg register
on a sign-extending load: the link already records how the high half
follows, which is what that sign extension produced.

Signed-off-by: Vineet Gupta <vineet.gupta@linux.dev>
---
v2: new. Loads were asked for on the RFC cover letter; the fill is the
only load whose destination inherits an id.

 kernel/bpf/verifier.c | 43 +++++++++++++++++++++++++++++++------------
 1 file changed, 31 insertions(+), 12 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 308ff53232f0..89be1240c99a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3927,7 +3927,8 @@ static void bpf_diag_stack_read_uninit(struct bpf_verifier_env *env, int off, in
 static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 				      /* func where src register points to */
 				      struct bpf_func_state *reg_state,
-				      int off, int size, int dst_regno)
+				      int off, int size, int dst_regno,
+				      bool is_ldsx)
 {
 	struct bpf_verifier_state *vstate = env->cur_state;
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
@@ -3968,18 +3969,34 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 
 			if (size <= spill_size &&
 			    bpf_stack_narrow_access_ok(off, size, spill_size)) {
-				if (env->bpf_capable && size == 4 && spill_size == 4 &&
-				    get_reg_width(reg) <= 32)
+				bool narrowing = get_reg_width(reg) > size * BITS_PER_BYTE;
+				/*
+				 * A narrowing fill keeps only the slot's low 32 bits,
+				 * so record a low-32 link rather than dropping the
+				 * relation, as a 32-bit mov from a wide source does.
+				 * Which kind depends on how the load fills the high
+				 * half, hence is_ldsx.
+				 */
+				bool subreg_link = narrowing && size == 4;
+
+				if (env->bpf_capable && size == 4 &&
+				    (subreg_link || (spill_size == 4 && !narrowing)))
 					/* Ensure stack slot has an ID to build a relation
 					 * with the destination register on fill.
 					 */
 					assign_scalar_id_before_mov(env, reg);
 				state->regs[dst_regno] = *reg;
 
-				/* Break the relation on a narrowing fill.
-				 * coerce_reg_to_size will adjust the boundaries.
-				 */
-				if (get_reg_width(reg) > size * BITS_PER_BYTE)
+				if (subreg_link && reg->id)
+					state->regs[dst_regno].subreg =
+						is_ldsx ? SUBREG_SEXT : SUBREG_ZEXT;
+				else if (narrowing)
+					/*
+					 * Nothing to relate: either the slot has
+					 * no id to share, or the fill is narrower
+					 * than the 32 bits a link can describe.
+					 * coerce_reg_to_size adjusts the bounds.
+					 */
 					clear_scalar_id(&state->regs[dst_regno]);
 			} else {
 				int spill_cnt = 0, zero_cnt = 0;
@@ -4144,7 +4161,7 @@ static int check_stack_read_var_off(struct bpf_verifier_env *env, struct bpf_reg
  */
 static int check_stack_read(struct bpf_verifier_env *env,
 			    struct bpf_reg_state *reg, argno_t ptr_argno, int off, int size,
-			    int dst_regno)
+			    int dst_regno, bool is_ldsx)
 {
 	struct bpf_func_state *state = bpf_func(env, reg);
 	int err;
@@ -4183,7 +4200,7 @@ static int check_stack_read(struct bpf_verifier_env *env,
 	if (!var_off) {
 		off += reg->var_off.value;
 		err = check_stack_read_fixed_off(env, state, off, size,
-						 dst_regno);
+						 dst_regno, is_ldsx);
 	} else {
 		/* Variable offset stack reads need more conservative handling
 		 * than fixed offset ones. Note that dst_regno >= 0 on this
@@ -6639,7 +6656,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, struct b
 
 		if (t == BPF_READ)
 			err = check_stack_read(env, reg, argno, off, size,
-					       value_regno);
+					       value_regno, is_ldsx);
 		else
 			err = check_stack_write(env, reg, off, size,
 						value_regno, insn_idx);
@@ -6736,13 +6753,15 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, struct b
 			 * Sign-extension can change the register value relative
 			 * to a scalar it is linked with by id (e.g. a zero-
 			 * extending fill of the same spilled stack slot), thus
-			 * drop the shared id in that case.
+			 * drop the shared id in that case. A ->subreg link is
+			 * the exception: it already records that only the low
+			 * 32 bits are shared, and how the high half follows.
 			 */
 			bool no_sext = reg_umax(&regs[value_regno]) <
 					(1ULL << (size * BITS_PER_BYTE - 1));
 
 			coerce_reg_to_size_sx(&regs[value_regno], size);
-			if (!no_sext)
+			if (!no_sext && !regs[value_regno].subreg)
 				clear_scalar_id(&regs[value_regno]);
 		}
 	}
-- 
2.53.0-Meta


  parent reply	other threads:[~2026-09-10 16:47 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-10 16:46 [PATCH bpf-next v2 00/13] bpf: track scalar equality across the low 32 bits Vineet Gupta
2026-09-10 16:46 ` [PATCH bpf-next v2 01/13] bpf: move linked-scalar flags out of bpf_reg_state->id [NFC] Vineet Gupta
2026-09-10 17:00   ` sashiko-bot
2026-09-11  6:56     ` Vineet Gupta
2026-09-10 17:52   ` bot+bpf-ci
2026-09-12 18:50   ` Alexei Starovoitov
2026-09-10 16:46 ` [PATCH bpf-next v2 02/13] bpf: compare linked-scalar kinds in regs_exact() Vineet Gupta
2026-09-12 18:51   ` Alexei Starovoitov
2026-09-10 16:46 ` [PATCH bpf-next v2 03/13] bpf: track low-32 scalar equality across zero-extending movs Vineet Gupta
2026-09-10 17:52   ` bot+bpf-ci
2026-09-11  9:29     ` Vineet Gupta
2026-09-12 18:59   ` Alexei Starovoitov
2026-09-10 16:46 ` [PATCH bpf-next v2 04/13] selftests/bpf: cover the low-32 link for " Vineet Gupta
2026-09-10 16:46 ` [PATCH bpf-next v2 05/13] bpf: keep the range across a sign extension that cannot change it Vineet Gupta
2026-09-10 17:08   ` sashiko-bot
2026-09-10 17:52   ` bot+bpf-ci
2026-09-11 10:37     ` Vineet Gupta
2026-09-12 19:02   ` Alexei Starovoitov
2026-09-10 16:46 ` [PATCH bpf-next v2 06/13] selftests/bpf: cover sign extensions that cannot change the range Vineet Gupta
2026-09-10 16:46 ` [PATCH bpf-next v2 07/13] bpf: track low-32 scalar equality across sign-extending movs Vineet Gupta
2026-09-10 17:52   ` bot+bpf-ci
2026-09-11 10:00     ` Vineet Gupta
2026-09-12 19:09   ` Alexei Starovoitov
2026-09-10 16:46 ` [PATCH bpf-next v2 08/13] selftests/bpf: cover the low-32 link for " Vineet Gupta
2026-09-10 17:52   ` bot+bpf-ci
2026-09-11  8:00     ` Vineet Gupta
2026-09-10 16:46 ` Vineet Gupta [this message]
2026-09-10 17:04   ` [PATCH bpf-next v2 09/13] bpf: track low-32 scalar equality across narrowing stack fills sashiko-bot
2026-09-11  6:07     ` Vineet Gupta
2026-09-11  6:43       ` Vineet Gupta
2026-09-10 16:46 ` [PATCH bpf-next v2 10/13] selftests/bpf: cover the low-32 link for " Vineet Gupta
2026-09-10 17:00   ` sashiko-bot
2026-09-11  5:34     ` Vineet Gupta
2026-09-10 17:31   ` bot+bpf-ci
2026-09-11  5:07     ` Vineet Gupta
2026-09-10 16:46 ` [PATCH bpf-next v2 11/13] bpf: record what a narrowing spill actually stores Vineet Gupta
2026-09-10 16:46 ` [PATCH bpf-next v2 12/13] bpf: track low-32 scalar equality across narrowing stack spills Vineet Gupta
2026-09-10 17:05   ` sashiko-bot
2026-09-10 16:46 ` [PATCH bpf-next v2 13/13] selftests/bpf: cover the low-32 link for " Vineet Gupta

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=20260910164635.459558-10-vineet.gupta@linux.dev \
    --to=vineet.gupta@linux.dev \
    --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=ihor.solodrai@linux.dev \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=martin.lau@linux.dev \
    --cc=memxor@gmail.com \
    --cc=shuah@kernel.org \
    --cc=song@kernel.org \
    --cc=yonghong.song@linux.dev \
    /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.