Skip to contentSkip to conversation

bpf, riscv64: Support load-acquire and store-release instructions

PATCH Superseded Peilin Ye 3 participants 24 messages Apr 30, 2025 – May 7, 2025

Subsystems (7)
Kselftest BPF RISC-V BPF selftests +3 more subsystems

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore

Peilin Ye

author
#0 lore raw

cover bpf, riscv64: Support load-acquire and store-release instructions

Hi all!

Patchset [1] introduced BPF load-acquire (BPF_LOAD_ACQ) and store-release (BPF_STORE_REL) instructions, and added x86-64 and arm64 JIT compiler support. As a follow-up, this patchset supports load-acquire and store-release instructions for the riscv64 JIT compiler, and introduces some related selftests/ changes.

Specifically:

* PATCH 1 makes insn_def_regno() handle load-acquires properly for bpf_jit_needs_zext() (true for riscv64) architectures
* PATCH 2, 3 from Andrea Parri add the actual support to the riscv64 JIT compiler
* PATCH 4 optimizes code emission by skipping redundant zext instructions inserted by the verifier
* PATCH 5, 6 and 7 are minor selftest/ improvements
* PATCH 8 enables (non-arena) load-acquire/store-release selftests for riscv64

Please refer to individual patches for details. Thanks!

[1] https://lore.kernel.org/all/[email protected]/

Andrea Parri (2):
bpf, riscv64: Introduce emit_load_*() and emit_store_*() bpf, riscv64: Support load-acquire and store-release instructions

Peilin Ye (6):
bpf/verifier: Handle BPF_LOAD_ACQ instructions in insn_def_regno() bpf, riscv64: Skip redundant zext instruction after load-acquire selftests/bpf: Use CAN_USE_LOAD_ACQ_STORE_REL when appropriate selftests/bpf: Avoid passing out-of-range values to __retval() selftests/bpf: Verify zero-extension behavior in load-acquire tests selftests/bpf: Enable non-arena load-acquire/store-release selftests
for riscv64

 arch/riscv/net/bpf_jit.h                      |  15 +
 arch/riscv/net/bpf_jit_comp64.c               | 334 ++++++++++++------
 arch/riscv/net/bpf_jit_core.c                 |   3 +-
 kernel/bpf/verifier.c                         |  11 +-
 tools/testing/selftests/bpf/progs/bpf_misc.h  |   5 +-
 .../bpf/progs/verifier_load_acquire.c         |  48 ++-
 .../selftests/bpf/progs/verifier_precision.c  |   5 +-
 .../bpf/progs/verifier_store_release.c        |  39 +-
 8 files changed, 314 insertions(+), 146 deletions(-)
Signature · 1 line
2.49.0.901.g37484f566f-goog
author
#1 lore raw

PATCH 1/8 bpf/verifier: Handle BPF_LOAD_ACQ instructions in insn_def_regno()

In preparation for supporting BPF load-acquire and store-release instructions for architectures where bpf_jit_needs_zext() returns true (e.g. riscv64), make insn_def_regno() handle load-acquires properly.

---
 kernel/bpf/verifier.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
kernel/bpf/verifier.c +7 -4
index 54c6953a8b84..6435ea23fee4 100644
@@ -3649,13 +3649,16 @@ static int insn_def_regno(const struct bpf_insn *insn)
 	case BPF_ST:
 		return -1;
 	case BPF_STX:
-		if ((BPF_MODE(insn->code) == BPF_ATOMIC ||
-		     BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) &&
-		    (insn->imm & BPF_FETCH)) {
+		if (BPF_MODE(insn->code) == BPF_ATOMIC ||
+		    BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) {
 			if (insn->imm == BPF_CMPXCHG)
 				return BPF_REG_0;
-			else
+			else if (insn->imm == BPF_LOAD_ACQ)
+				return insn->dst_reg;
+			else if (insn->imm & BPF_FETCH)
 				return insn->src_reg;
+			else
+				return -1;
 		} else {
 			return -1;
 		}
Signature · 1 line
2.49.0.901.g37484f566f-goog
author
#4 lore raw

PATCH 2/8 bpf, riscv64: Introduce emit_load_*() and emit_store_*()

In reply to Peilin Ye

From: Andrea Parri <[email protected]>

We're planning to add support for the load-acquire and store-release BPF instructions. Define emit_load_<size>() and emit_store_<size>() to enable/facilitate the (re)use of their code.

---
 arch/riscv/net/bpf_jit_comp64.c | 242 +++++++++++++++++++-------------
 1 file changed, 143 insertions(+), 99 deletions(-)
arch/riscv/net/bpf_jit_comp64.c +143 -99
index ca60db75199d..953b6a20c69f 100644
@@ -473,6 +473,140 @@ static inline void emit_kcfi(u32 hash, struct rv_jit_context *ctx)
 		emit(hash, ctx);
 }
 
+static int emit_load_8(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		if (sign_ext)
+			emit(rv_lb(rd, off, rs), ctx);
+		else
+			emit(rv_lbu(rd, off, rs), ctx);
+		return ctx->ninsns - insns_start;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+	insns_start = ctx->ninsns;
+	if (sign_ext)
+		emit(rv_lb(rd, 0, RV_REG_T1), ctx);
+	else
+		emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
+	return ctx->ninsns - insns_start;
+}
+
+static int emit_load_16(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		if (sign_ext)
+			emit(rv_lh(rd, off, rs), ctx);
+		else
+			emit(rv_lhu(rd, off, rs), ctx);
+		return ctx->ninsns - insns_start;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+	insns_start = ctx->ninsns;
+	if (sign_ext)
+		emit(rv_lh(rd, 0, RV_REG_T1), ctx);
+	else
+		emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
+	return ctx->ninsns - insns_start;
+}
+
+static int emit_load_32(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		if (sign_ext)
+			emit(rv_lw(rd, off, rs), ctx);
+		else
+			emit(rv_lwu(rd, off, rs), ctx);
+		return ctx->ninsns - insns_start;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+	insns_start = ctx->ninsns;
+	if (sign_ext)
+		emit(rv_lw(rd, 0, RV_REG_T1), ctx);
+	else
+		emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
+	return ctx->ninsns - insns_start;
+}
+
+static int emit_load_64(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		emit_ld(rd, off, rs, ctx);
+		return ctx->ninsns - insns_start;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+	insns_start = ctx->ninsns;
+	emit_ld(rd, 0, RV_REG_T1, ctx);
+	return ctx->ninsns - insns_start;
+}
+
+static void emit_store_8(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	if (is_12b_int(off)) {
+		emit(rv_sb(rd, off, rs), ctx);
+		return;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+	emit(rv_sb(RV_REG_T1, 0, rs), ctx);
+}
+
+static void emit_store_16(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	if (is_12b_int(off)) {
+		emit(rv_sh(rd, off, rs), ctx);
+		return;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+	emit(rv_sh(RV_REG_T1, 0, rs), ctx);
+}
+
+static void emit_store_32(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	if (is_12b_int(off)) {
+		emit_sw(rd, off, rs, ctx);
+		return;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+	emit_sw(RV_REG_T1, 0, rs, ctx);
+}
+
+static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	if (is_12b_int(off)) {
+		emit_sd(rd, off, rs, ctx);
+		return;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+	emit_sd(RV_REG_T1, 0, rs, ctx);
+}
+
 static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
 			struct rv_jit_context *ctx)
 {
@@ -1650,8 +1784,8 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_LDX | BPF_PROBE_MEM32 | BPF_W:
 	case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW:
 	{
-		int insn_len, insns_start;
 		bool sign_ext;
+		int insn_len;
 
 		sign_ext = BPF_MODE(insn->code) == BPF_MEMSX ||
 			   BPF_MODE(insn->code) == BPF_PROBE_MEMSX;
@@ -1663,78 +1797,16 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
 		switch (BPF_SIZE(code)) {
 		case BPF_B:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				if (sign_ext)
-					emit(rv_lb(rd, off, rs), ctx);
-				else
-					emit(rv_lbu(rd, off, rs), ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T1, off, ctx);
-			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-			insns_start = ctx->ninsns;
-			if (sign_ext)
-				emit(rv_lb(rd, 0, RV_REG_T1), ctx);
-			else
-				emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
-			insn_len = ctx->ninsns - insns_start;
+			insn_len = emit_load_8(sign_ext, rd, off, rs, ctx);
 			break;
 		case BPF_H:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				if (sign_ext)
-					emit(rv_lh(rd, off, rs), ctx);
-				else
-					emit(rv_lhu(rd, off, rs), ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T1, off, ctx);
-			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-			insns_start = ctx->ninsns;
-			if (sign_ext)
-				emit(rv_lh(rd, 0, RV_REG_T1), ctx);
-			else
-				emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
-			insn_len = ctx->ninsns - insns_start;
+			insn_len = emit_load_16(sign_ext, rd, off, rs, ctx);
 			break;
 		case BPF_W:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				if (sign_ext)
-					emit(rv_lw(rd, off, rs), ctx);
-				else
-					emit(rv_lwu(rd, off, rs), ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T1, off, ctx);
-			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-			insns_start = ctx->ninsns;
-			if (sign_ext)
-				emit(rv_lw(rd, 0, RV_REG_T1), ctx);
-			else
-				emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
-			insn_len = ctx->ninsns - insns_start;
+			insn_len = emit_load_32(sign_ext, rd, off, rs, ctx);
 			break;
 		case BPF_DW:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit_ld(rd, off, rs, ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T1, off, ctx);
-			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-			insns_start = ctx->ninsns;
-			emit_ld(rd, 0, RV_REG_T1, ctx);
-			insn_len = ctx->ninsns - insns_start;
+			insn_len = emit_load_64(sign_ext, rd, off, rs, ctx);
 			break;
 		}
 
@@ -1879,44 +1951,16 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
 	/* STX: *(size *)(dst + off) = src */
 	case BPF_STX | BPF_MEM | BPF_B:
-		if (is_12b_int(off)) {
-			emit(rv_sb(rd, off, rs), ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-		emit(rv_sb(RV_REG_T1, 0, rs), ctx);
+		emit_store_8(rd, off, rs, ctx);
 		break;
 	case BPF_STX | BPF_MEM | BPF_H:
-		if (is_12b_int(off)) {
-			emit(rv_sh(rd, off, rs), ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-		emit(rv_sh(RV_REG_T1, 0, rs), ctx);
+		emit_store_16(rd, off, rs, ctx);
 		break;
 	case BPF_STX | BPF_MEM | BPF_W:
-		if (is_12b_int(off)) {
-			emit_sw(rd, off, rs, ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-		emit_sw(RV_REG_T1, 0, rs, ctx);
+		emit_store_32(rd, off, rs, ctx);
 		break;
 	case BPF_STX | BPF_MEM | BPF_DW:
-		if (is_12b_int(off)) {
-			emit_sd(rd, off, rs, ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-		emit_sd(RV_REG_T1, 0, rs, ctx);
+		emit_store_64(rd, off, rs, ctx);
 		break;
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
Signature · 1 line
2.49.0.901.g37484f566f-goog
author
#6 lore raw

PATCH 3/8 bpf, riscv64: Support load-acquire and store-release instructions

In reply to Peilin Ye

From: Andrea Parri <[email protected]>

Support BPF load-acquire (BPF_LOAD_ACQ) and store-release (BPF_STORE_REL) instructions in the riscv64 JIT compiler. For example, consider the following 64-bit load-acquire (assuming little-endian):

db 10 00 00 00 01 00 00 r1 = load_acquire((u64 *)(r1 + 0x0)) 95 00 00 00 00 00 00 00 exit

opcode (0xdb): BPF_ATOMIC | BPF_DW | BPF_STX
imm (0x00000100): BPF_LOAD_ACQ

The JIT compiler will emit an LD instruction followed by a FENCE R,RW instruction for the above, e.g.:

ld x7,0(x6)
fence r,rw

Similarly, consider the following 16-bit store-release:

cb 21 00 00 10 01 00 00 store_release((u16 *)(r1 + 0x0), w2) 95 00 00 00 00 00 00 00 exit

opcode (0xcb): BPF_ATOMIC | BPF_H | BPF_STX
imm (0x00000110): BPF_STORE_REL

A FENCE RW,W instruction followed by an SH instruction will be emitted, e.g.:

fence rw,w
sh x2,0(x4)

8-bit and 16-bit load-acquires are zero-extending (cf., LBU, LHU). The verifier always rejects misaligned load-acquires/store-releases (even if BPF_F_ANY_ALIGNMENT is set), so the emitted load and store instructions are guaranteed to be single-copy atomic.

Introduce primitives to emit the relevant (and the most common/used in the kernel) fences, i.e. fences with R -> RW, RW -> W and RW -> RW.

Rename emit_atomic() to emit_atomic_rmw() to make it clear that it only handles RMW atomics, and replace its is64 parameter to allow to perform the required checks on the opsize (BPF_SIZE(code)).

[[email protected]: whitespace changes; cosmetic changes to commit
title and message]

---
 arch/riscv/net/bpf_jit.h        | 15 +++++++
 arch/riscv/net/bpf_jit_comp64.c | 77 ++++++++++++++++++++++++++++++---
 2 files changed, 85 insertions(+), 7 deletions(-)
arch/riscv/net/bpf_jit.h +15 -0
index 1d1c78d4cff1..e7b032dfd17f 100644
@@ -608,6 +608,21 @@ static inline u32 rv_fence(u8 pred, u8 succ)
 	return rv_i_insn(imm11_0, 0, 0, 0, 0xf);
 }
 
+static inline void emit_fence_r_rw(struct rv_jit_context *ctx)
+{
+	emit(rv_fence(0x2, 0x3), ctx);
+}
+
+static inline void emit_fence_rw_w(struct rv_jit_context *ctx)
+{
+	emit(rv_fence(0x3, 0x1), ctx);
+}
+
+static inline void emit_fence_rw_rw(struct rv_jit_context *ctx)
+{
+	emit(rv_fence(0x3, 0x3), ctx);
+}
+
 static inline u32 rv_nop(void)
 {
 	return rv_i_insn(0, 0, 0, 0, 0x13);
arch/riscv/net/bpf_jit_comp64.c +70 -7

114 lines not on this page · raw message

Signature · 1 line
2.49.0.901.g37484f566f-goog
author
#10 lore raw

PATCH 4/8 bpf, riscv64: Skip redundant zext instruction after load-acquire

In reply to Peilin Ye

Currently, the verifier inserts a zext instruction right after every 8-, 16- or 32-bit load-acquire, which is already zero-extending. Skip such redundant zext instructions.

While we are here, update that already-obsolete comment about "skip the next instruction" in build_body(). Also change emit_atomic_rmw()'s parameters to keep it consistent with emit_atomic_ld_st().

Note that checking 'insn[1]' relies on 'insn' not being the last instruction, which should have been guaranteed by the verifier; we already use 'insn[1]' elsewhere in the file for similar purposes. Additionally, we don't check if 'insn[1]' is actually a zext for our load-acquire's dst_reg, or some other registers - in other words, here we are relying on the verifier to always insert a redundant zext right after a 8/16/32-bit load-acquire, for its dst_reg.

---
 arch/riscv/net/bpf_jit_comp64.c | 23 ++++++++++++++++++-----
 arch/riscv/net/bpf_jit_core.c   |  3 +--
 2 files changed, 19 insertions(+), 7 deletions(-)
arch/riscv/net/bpf_jit_comp64.c +18 -5
index b71a9c88fb4f..4cb50dbbe94b 100644
@@ -607,8 +607,13 @@ static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
 	emit_sd(RV_REG_T1, 0, rs, ctx);
 }
 
-static int emit_atomic_ld_st(u8 rd, u8 rs, s16 off, s32 imm, u8 code, struct rv_jit_context *ctx)
+static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn,
+			     struct rv_jit_context *ctx)
 {
+	u8 code = insn->code;
+	s32 imm = insn->imm;
+	s16 off = insn->off;
+
 	switch (imm) {
 	/* dst_reg = load_acquire(src_reg + off16) */
 	case BPF_LOAD_ACQ:
@@ -627,6 +632,12 @@ static int emit_atomic_ld_st(u8 rd, u8 rs, s16 off, s32 imm, u8 code, struct rv_
 			break;
 		}
 		emit_fence_r_rw(ctx);
+
+		/* If our next insn is a redundant zext, return 1 to tell
+		 * build_body() to skip it.
+		 */
+		if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	/* store_release(dst_reg + off16, src_reg) */
 	case BPF_STORE_REL:
@@ -654,10 +665,12 @@ static int emit_atomic_ld_st(u8 rd, u8 rs, s16 off, s32 imm, u8 code, struct rv_
 	return 0;
 }
 
-static int emit_atomic_rmw(u8 rd, u8 rs, s16 off, s32 imm, u8 code,
+static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn,
 			   struct rv_jit_context *ctx)
 {
-	u8 r0;
+	u8 r0, code = insn->code;
+	s16 off = insn->off;
+	s32 imm = insn->imm;
 	int jmp_offset;
 	bool is64;
 
@@ -2026,9 +2039,9 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_STX | BPF_ATOMIC | BPF_W:
 	case BPF_STX | BPF_ATOMIC | BPF_DW:
 		if (bpf_atomic_is_load_store(insn))
-			ret = emit_atomic_ld_st(rd, rs, off, imm, code, ctx);
+			ret = emit_atomic_ld_st(rd, rs, insn, ctx);
 		else
-			ret = emit_atomic_rmw(rd, rs, off, imm, code, ctx);
+			ret = emit_atomic_rmw(rd, rs, insn, ctx);
 		break;
 
 	case BPF_STX | BPF_PROBE_MEM32 | BPF_B:
arch/riscv/net/bpf_jit_core.c +1 -2
index f8cd2f70a7fb..f6ca5cfa6b2f 100644
@@ -26,9 +26,8 @@ static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset)
 		int ret;
 
 		ret = bpf_jit_emit_insn(insn, ctx, extra_pass);
-		/* BPF_LD | BPF_IMM | BPF_DW: skip the next instruction. */
 		if (ret > 0)
-			i++;
+			i++; /* skip the next instruction */
 		if (offset)
 			offset[i] = ctx->ninsns;
 		if (ret < 0)
Signature · 1 line
2.49.0.901.g37484f566f-goog
author
#12 lore raw

PATCH 5/8 selftests/bpf: Use CAN_USE_LOAD_ACQ_STORE_REL when appropriate

In reply to Peilin Ye

Instead of open-coding the conditions, use
'#ifdef CAN_USE_LOAD_ACQ_STORE_REL' to guard the following tests:

verifier_precision/bpf_load_acquire
verifier_precision/bpf_store_release
verifier_store_release/*

Note that, for the first two tests in verifier_precision.c, switching to '#ifdef CAN_USE_LOAD_ACQ_STORE_REL' means also checking if '__clang_major__ >= 18', which has already been guaranteed by the outer '#if' check.

---
 tools/testing/selftests/bpf/progs/verifier_precision.c     | 5 ++---
 tools/testing/selftests/bpf/progs/verifier_store_release.c | 7 +++----
 2 files changed, 5 insertions(+), 7 deletions(-)
tools/testing/selftests/bpf/progs/verifier_precision.c +2 -3
index 6662d4b39969..2dd0d15c2678 100644
@@ -91,8 +91,7 @@ __naked int bpf_end_bswap(void)
 		::: __clobber_all);
 }
 
-#if defined(ENABLE_ATOMICS_TESTS) && \
-	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
 
 SEC("?raw_tp")
 __success __log_level(2)
@@ -138,7 +137,7 @@ __naked int bpf_store_release(void)
 	: __clobber_all);
 }
 
-#endif /* load-acquire, store-release */
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
 #endif /* v4 instruction */
 
 SEC("?raw_tp")
tools/testing/selftests/bpf/progs/verifier_store_release.c +3 -4
index c0442d5bb049..7e456e2861b4 100644
@@ -6,8 +6,7 @@
 #include "../../../include/linux/filter.h"
 #include "bpf_misc.h"
 
-#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \
-	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
 
 SEC("socket")
 __description("store-release, 8-bit")
@@ -271,7 +270,7 @@ __naked void store_release_with_invalid_reg(void)
 	: __clobber_all);
 }
 
-#else
+#else /* CAN_USE_LOAD_ACQ_STORE_REL */
 
 SEC("socket")
 __description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support store-release, use a dummy test")
@@ -281,6 +280,6 @@ int dummy_test(void)
 	return 0;
 }
 
-#endif
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
 
 char _license[] SEC("license") = "GPL";
Signature · 1 line
2.49.0.901.g37484f566f-goog
author
#14 lore raw

PATCH 6/8 selftests/bpf: Avoid passing out-of-range values to __retval()

In reply to Peilin Ye

Currently, we pass 0x1234567890abcdef to __retval() for the following two tests:

verifier_load_acquire/load_acquire_64
verifier_store_release/store_release_64

However, the upper 32 bits of that value are being ignored, since __retval() expects an int. Actually, the tests would still pass even if I change '__retval(0x1234567890abcdef)' to e.g. '__retval(0x90abcdef)'.

Restructure the tests a bit to test the entire 64-bit values properly. Do the same to their 8-, 16- and 32-bit variants as well to keep the style consistent.

Fixes ff3afe5da998 ("selftests/bpf: Add selftests for load-acquire and store-release instructions")
---
 .../bpf/progs/verifier_load_acquire.c         | 40 +++++++++++++------
 .../bpf/progs/verifier_store_release.c        | 32 +++++++++++----
 2 files changed, 52 insertions(+), 20 deletions(-)
tools/testing/selftests/bpf/progs/verifier_load_acquire.c +28 -12
index 77698d5a19e4..a696ab84bfd6 100644
@@ -10,65 +10,81 @@
 
 SEC("socket")
 __description("load-acquire, 8-bit")
-__success __success_unpriv __retval(0x12)
+__success __success_unpriv __retval(0)
 __naked void load_acquire_8(void)
 {
 	asm volatile (
+	"r0 = 0;"
 	"w1 = 0x12;"
 	"*(u8 *)(r10 - 1) = w1;"
-	".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r10 - 1));
+	".8byte %[load_acquire_insn];" // w2 = load_acquire((u8 *)(r10 - 1));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
 	"exit;"
 	:
 	: __imm_insn(load_acquire_insn,
-		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -1))
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -1))
 	: __clobber_all);
 }
 
 SEC("socket")
 __description("load-acquire, 16-bit")
-__success __success_unpriv __retval(0x1234)
+__success __success_unpriv __retval(0)
 __naked void load_acquire_16(void)
 {
 	asm volatile (
+	"r0 = 0;"
 	"w1 = 0x1234;"
 	"*(u16 *)(r10 - 2) = w1;"
-	".8byte %[load_acquire_insn];" // w0 = load_acquire((u16 *)(r10 - 2));
+	".8byte %[load_acquire_insn];" // w2 = load_acquire((u16 *)(r10 - 2));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
 	"exit;"
 	:
 	: __imm_insn(load_acquire_insn,
-		     BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -2))
+		     BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -2))
 	: __clobber_all);
 }
 
 SEC("socket")
 __description("load-acquire, 32-bit")
-__success __success_unpriv __retval(0x12345678)
+__success __success_unpriv __retval(0)
 __naked void load_acquire_32(void)
 {
 	asm volatile (
+	"r0 = 0;"
 	"w1 = 0x12345678;"
 	"*(u32 *)(r10 - 4) = w1;"
-	".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 4));
+	".8byte %[load_acquire_insn];" // w2 = load_acquire((u32 *)(r10 - 4));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
 	"exit;"
 	:
 	: __imm_insn(load_acquire_insn,
-		     BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -4))
+		     BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -4))
 	: __clobber_all);
 }
 
 SEC("socket")
 __description("load-acquire, 64-bit")
-__success __success_unpriv __retval(0x1234567890abcdef)
+__success __success_unpriv __retval(0)
 __naked void load_acquire_64(void)
 {
 	asm volatile (
+	"r0 = 0;"
 	"r1 = 0x1234567890abcdef ll;"
 	"*(u64 *)(r10 - 8) = r1;"
-	".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r10 - 8));
+	".8byte %[load_acquire_insn];" // r2 = load_acquire((u64 *)(r10 - 8));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
 	"exit;"
 	:
 	: __imm_insn(load_acquire_insn,
-		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -8))
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -8))
 	: __clobber_all);
 }
 
tools/testing/selftests/bpf/progs/verifier_store_release.c +24 -8
index 7e456e2861b4..72f1eb006074 100644
@@ -10,13 +10,17 @@
 
 SEC("socket")
 __description("store-release, 8-bit")
-__success __success_unpriv __retval(0x12)
+__success __success_unpriv __retval(0)
 __naked void store_release_8(void)
 {
 	asm volatile (
+	"r0 = 0;"
 	"w1 = 0x12;"
 	".8byte %[store_release_insn];" // store_release((u8 *)(r10 - 1), w1);
-	"w0 = *(u8 *)(r10 - 1);"
+	"w2 = *(u8 *)(r10 - 1);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
 	"exit;"
 	:
 	: __imm_insn(store_release_insn,
@@ -26,13 +30,17 @@ __naked void store_release_8(void)
 
 SEC("socket")
 __description("store-release, 16-bit")
-__success __success_unpriv __retval(0x1234)
+__success __success_unpriv __retval(0)
 __naked void store_release_16(void)
 {
 	asm volatile (
+	"r0 = 0;"
 	"w1 = 0x1234;"
 	".8byte %[store_release_insn];" // store_release((u16 *)(r10 - 2), w1);
-	"w0 = *(u16 *)(r10 - 2);"
+	"w2 = *(u16 *)(r10 - 2);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
 	"exit;"
 	:
 	: __imm_insn(store_release_insn,
@@ -42,13 +50,17 @@ __naked void store_release_16(void)
 
 SEC("socket")
 __description("store-release, 32-bit")
-__success __success_unpriv __retval(0x12345678)
+__success __success_unpriv __retval(0)
 __naked void store_release_32(void)
 {
 	asm volatile (
+	"r0 = 0;"
 	"w1 = 0x12345678;"
 	".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 4), w1);
-	"w0 = *(u32 *)(r10 - 4);"
+	"w2 = *(u32 *)(r10 - 4);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
 	"exit;"
 	:
 	: __imm_insn(store_release_insn,
@@ -58,13 +70,17 @@ __naked void store_release_32(void)
 
 SEC("socket")
 __description("store-release, 64-bit")
-__success __success_unpriv __retval(0x1234567890abcdef)
+__success __success_unpriv __retval(0)
 __naked void store_release_64(void)
 {
 	asm volatile (
+	"r0 = 0;"
 	"r1 = 0x1234567890abcdef ll;"
 	".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1);
-	"r0 = *(u64 *)(r10 - 8);"
+	"r2 = *(u64 *)(r10 - 8);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
 	"exit;"
 	:
 	: __imm_insn(store_release_insn,
Signature · 1 line
2.49.0.901.g37484f566f-goog
author
#16 lore raw

PATCH 7/8 selftests/bpf: Verify zero-extension behavior in load-acquire tests

In reply to Peilin Ye

Verify that 8-, 16- and 32-bit load-acquires are zero-extending by using immediate values with their highest bit set. Do the same for the 64-bit variant to keep the style consistent.

---
 tools/testing/selftests/bpf/progs/verifier_load_acquire.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
tools/testing/selftests/bpf/progs/verifier_load_acquire.c +4 -4
index a696ab84bfd6..74f4f19c10b8 100644
@@ -15,7 +15,7 @@ __naked void load_acquire_8(void)
 {
 	asm volatile (
 	"r0 = 0;"
-	"w1 = 0x12;"
+	"w1 = 0xfe;"
 	"*(u8 *)(r10 - 1) = w1;"
 	".8byte %[load_acquire_insn];" // w2 = load_acquire((u8 *)(r10 - 1));
 	"if r2 == r1 goto 1f;"
@@ -35,7 +35,7 @@ __naked void load_acquire_16(void)
 {
 	asm volatile (
 	"r0 = 0;"
-	"w1 = 0x1234;"
+	"w1 = 0xfedc;"
 	"*(u16 *)(r10 - 2) = w1;"
 	".8byte %[load_acquire_insn];" // w2 = load_acquire((u16 *)(r10 - 2));
 	"if r2 == r1 goto 1f;"
@@ -55,7 +55,7 @@ __naked void load_acquire_32(void)
 {
 	asm volatile (
 	"r0 = 0;"
-	"w1 = 0x12345678;"
+	"w1 = 0xfedcba09;"
 	"*(u32 *)(r10 - 4) = w1;"
 	".8byte %[load_acquire_insn];" // w2 = load_acquire((u32 *)(r10 - 4));
 	"if r2 == r1 goto 1f;"
@@ -75,7 +75,7 @@ __naked void load_acquire_64(void)
 {
 	asm volatile (
 	"r0 = 0;"
-	"r1 = 0x1234567890abcdef ll;"
+	"r1 = 0xfedcba0987654321 ll;"
 	"*(u64 *)(r10 - 8) = r1;"
 	".8byte %[load_acquire_insn];" // r2 = load_acquire((u64 *)(r10 - 8));
 	"if r2 == r1 goto 1f;"
Signature · 1 line
2.49.0.901.g37484f566f-goog
author
#18 lore raw

PATCH 8/8 selftests/bpf: Enable non-arena load-acquire/store-release selftests for riscv64

In reply to Peilin Ye

For riscv64, enable all BPF_{LOAD_ACQ,STORE_REL} selftests except the arena_atomics/* ones (not guarded behind CAN_USE_LOAD_ACQ_STORE_REL), since arena access is not yet supported.

---
 tools/testing/selftests/bpf/progs/bpf_misc.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
tools/testing/selftests/bpf/progs/bpf_misc.h +3 -2
index 863df7c0fdd0..6e208e24ba3b 100644
@@ -225,8 +225,9 @@
 #define CAN_USE_BPF_ST
 #endif
 
-#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \
-	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) &&		\
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) ||	\
+	 (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
 #define CAN_USE_LOAD_ACQ_STORE_REL
 #endif
 
Signature · 1 line
2.49.0.901.g37484f566f-goog
maintainer Reviewed-by on v1 2/8
#5 lore raw

Re: [PATCH bpf-next 2/8] bpf, riscv64: Introduce emit_load_*() and emit_store_*()

In reply to Peilin Ye
Quoted 291 lines · Peilin Ye

From: Andrea Parri <[email protected]>

We're planning to add support for the load-acquire and store-release BPF instructions. Define emit_load_<size>() and emit_store_<size>() to enable/facilitate the (re)use of their code.

---
  arch/riscv/net/bpf_jit_comp64.c | 242 +++++++++++++++++++-------------
  1 file changed, 143 insertions(+), 99 deletions(-)
arch/riscv/net/bpf_jit_comp64.c +142 -93
index ca60db75199d..953b6a20c69f 100644
@@ -473,6 +473,140 @@ static inline void emit_kcfi(u32 hash, struct rv_jit_context *ctx)
  		emit(hash, ctx);
  }
 
+static int emit_load_8(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		if (sign_ext)
+			emit(rv_lb(rd, off, rs), ctx);
+		else
+			emit(rv_lbu(rd, off, rs), ctx);
+		return ctx->ninsns - insns_start;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+	insns_start = ctx->ninsns;
+	if (sign_ext)
+		emit(rv_lb(rd, 0, RV_REG_T1), ctx);
+	else
+		emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
+	return ctx->ninsns - insns_start;
+}
+
+static int emit_load_16(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		if (sign_ext)
+			emit(rv_lh(rd, off, rs), ctx);
+		else
+			emit(rv_lhu(rd, off, rs), ctx);
+		return ctx->ninsns - insns_start;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+	insns_start = ctx->ninsns;
+	if (sign_ext)
+		emit(rv_lh(rd, 0, RV_REG_T1), ctx);
+	else
+		emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
+	return ctx->ninsns - insns_start;
+}
+
+static int emit_load_32(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		if (sign_ext)
+			emit(rv_lw(rd, off, rs), ctx);
+		else
+			emit(rv_lwu(rd, off, rs), ctx);
+		return ctx->ninsns - insns_start;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+	insns_start = ctx->ninsns;
+	if (sign_ext)
+		emit(rv_lw(rd, 0, RV_REG_T1), ctx);
+	else
+		emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
+	return ctx->ninsns - insns_start;
+}
+
+static int emit_load_64(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		emit_ld(rd, off, rs, ctx);
+		return ctx->ninsns - insns_start;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
+	insns_start = ctx->ninsns;
+	emit_ld(rd, 0, RV_REG_T1, ctx);
+	return ctx->ninsns - insns_start;
+}
+
+static void emit_store_8(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	if (is_12b_int(off)) {
+		emit(rv_sb(rd, off, rs), ctx);
+		return;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+	emit(rv_sb(RV_REG_T1, 0, rs), ctx);
+}
+
+static void emit_store_16(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	if (is_12b_int(off)) {
+		emit(rv_sh(rd, off, rs), ctx);
+		return;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+	emit(rv_sh(RV_REG_T1, 0, rs), ctx);
+}
+
+static void emit_store_32(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	if (is_12b_int(off)) {
+		emit_sw(rd, off, rs, ctx);
+		return;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+	emit_sw(RV_REG_T1, 0, rs, ctx);
+}
+
+static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+{
+	if (is_12b_int(off)) {
+		emit_sd(rd, off, rs, ctx);
+		return;
+	}
+
+	emit_imm(RV_REG_T1, off, ctx);
+	emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
+	emit_sd(RV_REG_T1, 0, rs, ctx);
+}
+
  static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
  			struct rv_jit_context *ctx)
  {
@@ -1650,8 +1784,8 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  	case BPF_LDX | BPF_PROBE_MEM32 | BPF_W:
  	case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW:
  	{
-		int insn_len, insns_start;
  		bool sign_ext;
+		int insn_len;
 
  		sign_ext = BPF_MODE(insn->code) == BPF_MEMSX ||
  			   BPF_MODE(insn->code) == BPF_PROBE_MEMSX;
@@ -1663,78 +1797,16 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
  		switch (BPF_SIZE(code)) {
  		case BPF_B:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				if (sign_ext)
-					emit(rv_lb(rd, off, rs), ctx);
-				else
-					emit(rv_lbu(rd, off, rs), ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T1, off, ctx);
-			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-			insns_start = ctx->ninsns;
-			if (sign_ext)
-				emit(rv_lb(rd, 0, RV_REG_T1), ctx);
-			else
-				emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
-			insn_len = ctx->ninsns - insns_start;
+			insn_len = emit_load_8(sign_ext, rd, off, rs, ctx);
  			break;
  		case BPF_H:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				if (sign_ext)
-					emit(rv_lh(rd, off, rs), ctx);
-				else
-					emit(rv_lhu(rd, off, rs), ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T1, off, ctx);
-			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-			insns_start = ctx->ninsns;
-			if (sign_ext)
-				emit(rv_lh(rd, 0, RV_REG_T1), ctx);
-			else
-				emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
-			insn_len = ctx->ninsns - insns_start;
+			insn_len = emit_load_16(sign_ext, rd, off, rs, ctx);
  			break;
  		case BPF_W:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				if (sign_ext)
-					emit(rv_lw(rd, off, rs), ctx);
-				else
-					emit(rv_lwu(rd, off, rs), ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T1, off, ctx);
-			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-			insns_start = ctx->ninsns;
-			if (sign_ext)
-				emit(rv_lw(rd, 0, RV_REG_T1), ctx);
-			else
-				emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
-			insn_len = ctx->ninsns - insns_start;
+			insn_len = emit_load_32(sign_ext, rd, off, rs, ctx);
  			break;
  		case BPF_DW:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit_ld(rd, off, rs, ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T1, off, ctx);
-			emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-			insns_start = ctx->ninsns;
-			emit_ld(rd, 0, RV_REG_T1, ctx);
-			insn_len = ctx->ninsns - insns_start;
+			insn_len = emit_load_64(sign_ext, rd, off, rs, ctx);
  			break;
  		}
 
@@ -1879,44 +1951,16 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
  	/* STX: *(size *)(dst + off) = src */
  	case BPF_STX | BPF_MEM | BPF_B:
-		if (is_12b_int(off)) {
-			emit(rv_sb(rd, off, rs), ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-		emit(rv_sb(RV_REG_T1, 0, rs), ctx);
+		emit_store_8(rd, off, rs, ctx);
  		break;
  	case BPF_STX | BPF_MEM | BPF_H:
-		if (is_12b_int(off)) {
-			emit(rv_sh(rd, off, rs), ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-		emit(rv_sh(RV_REG_T1, 0, rs), ctx);
+		emit_store_16(rd, off, rs, ctx);
  		break;
  	case BPF_STX | BPF_MEM | BPF_W:
-		if (is_12b_int(off)) {
-			emit_sw(rd, off, rs, ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-		emit_sw(RV_REG_T1, 0, rs, ctx);
+		emit_store_32(rd, off, rs, ctx);
  		break;
  	case BPF_STX | BPF_MEM | BPF_DW:
-		if (is_12b_int(off)) {
-			emit_sd(rd, off, rs, ctx);

arch/riscv/net/bpf_jit_comp64.c int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, · line 1966

Quoted 10 lines
arch/riscv/net/bpf_jit_comp64.c +1 -6
-			break;
-		}
-
-		emit_imm(RV_REG_T1, off, ctx);
-		emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-		emit_sd(RV_REG_T1, 0, rs, ctx);
+		emit_store_64(rd, off, rs, ctx);
  		break;
  	case BPF_STX | BPF_ATOMIC | BPF_W:
  	case BPF_STX | BPF_ATOMIC | BPF_DW:
maintainer Reviewed-by on v1 3/8
#7 lore raw
In reply to Peilin Ye
Quoted 195 lines · Peilin Ye

From: Andrea Parri <[email protected]>

Support BPF load-acquire (BPF_LOAD_ACQ) and store-release (BPF_STORE_REL) instructions in the riscv64 JIT compiler. For example, consider the following 64-bit load-acquire (assuming little-endian):

   db 10 00 00 00 01 00 00  r1 = load_acquire((u64 *)(r1 + 0x0))
   95 00 00 00 00 00 00 00  exit

   opcode (0xdb): BPF_ATOMIC | BPF_DW | BPF_STX
   imm (0x00000100): BPF_LOAD_ACQ

The JIT compiler will emit an LD instruction followed by a FENCE R,RW instruction for the above, e.g.:

   ld x7,0(x6)
   fence r,rw

Similarly, consider the following 16-bit store-release:

   cb 21 00 00 10 01 00 00  store_release((u16 *)(r1 + 0x0), w2)
   95 00 00 00 00 00 00 00  exit

   opcode (0xcb): BPF_ATOMIC | BPF_H | BPF_STX
   imm (0x00000110): BPF_STORE_REL

A FENCE RW,W instruction followed by an SH instruction will be emitted, e.g.:

   fence rw,w
   sh x2,0(x4)

8-bit and 16-bit load-acquires are zero-extending (cf., LBU, LHU). The verifier always rejects misaligned load-acquires/store-releases (even if BPF_F_ANY_ALIGNMENT is set), so the emitted load and store instructions are guaranteed to be single-copy atomic.

Introduce primitives to emit the relevant (and the most common/used in the kernel) fences, i.e. fences with R -> RW, RW -> W and RW -> RW.

Rename emit_atomic() to emit_atomic_rmw() to make it clear that it only handles RMW atomics, and replace its is64 parameter to allow to perform the required checks on the opsize (BPF_SIZE(code)).

[[email protected]: whitespace changes; cosmetic changes to commit
title and message]

---
  arch/riscv/net/bpf_jit.h        | 15 +++++++
  arch/riscv/net/bpf_jit_comp64.c | 77 ++++++++++++++++++++++++++++++---
  2 files changed, 85 insertions(+), 7 deletions(-)
arch/riscv/net/bpf_jit.h +15 -0
index 1d1c78d4cff1..e7b032dfd17f 100644
@@ -608,6 +608,21 @@ static inline u32 rv_fence(u8 pred, u8 succ)
  	return rv_i_insn(imm11_0, 0, 0, 0, 0xf);
  }
 
+static inline void emit_fence_r_rw(struct rv_jit_context *ctx)
+{
+	emit(rv_fence(0x2, 0x3), ctx);
+}
+
+static inline void emit_fence_rw_w(struct rv_jit_context *ctx)
+{
+	emit(rv_fence(0x3, 0x1), ctx);
+}
+
+static inline void emit_fence_rw_rw(struct rv_jit_context *ctx)
+{
+	emit(rv_fence(0x3, 0x3), ctx);
+}
+
  static inline u32 rv_nop(void)
  {
  	return rv_i_insn(0, 0, 0, 0, 0x13);
arch/riscv/net/bpf_jit_comp64.c +69 -6
index 953b6a20c69f..b71a9c88fb4f 100644
@@ -607,11 +607,65 @@ static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
  	emit_sd(RV_REG_T1, 0, rs, ctx);
  }
 
-static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
-			struct rv_jit_context *ctx)
+static int emit_atomic_ld_st(u8 rd, u8 rs, s16 off, s32 imm, u8 code, struct rv_jit_context *ctx)
+{
+	switch (imm) {
+	/* dst_reg = load_acquire(src_reg + off16) */
+	case BPF_LOAD_ACQ:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit_load_8(false, rd, off, rs, ctx);
+			break;
+		case BPF_H:
+			emit_load_16(false, rd, off, rs, ctx);
+			break;
+		case BPF_W:
+			emit_load_32(false, rd, off, rs, ctx);
+			break;
+		case BPF_DW:
+			emit_load_64(false, rd, off, rs, ctx);
+			break;
+		}
+		emit_fence_r_rw(ctx);
+		break;
+	/* store_release(dst_reg + off16, src_reg) */
+	case BPF_STORE_REL:
+		emit_fence_rw_w(ctx);
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit_store_8(rd, off, rs, ctx);
+			break;
+		case BPF_H:
+			emit_store_16(rd, off, rs, ctx);
+			break;
+		case BPF_W:
+			emit_store_32(rd, off, rs, ctx);
+			break;
+		case BPF_DW:
+			emit_store_64(rd, off, rs, ctx);
+			break;
+		}
+		break;
+	default:
+		pr_err_once("bpf-jit: invalid atomic load/store opcode %02x\n", imm);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int emit_atomic_rmw(u8 rd, u8 rs, s16 off, s32 imm, u8 code,
+			   struct rv_jit_context *ctx)
  {
  	u8 r0;
  	int jmp_offset;
+	bool is64;
+
+	if (BPF_SIZE(code) != BPF_W && BPF_SIZE(code) != BPF_DW) {
+		pr_err_once("bpf-jit: 1- and 2-byte RMW atomics are not supported\n");
+		return -EINVAL;
+	}
+	is64 = BPF_SIZE(code) == BPF_DW;
 
  	if (off) {
  		if (is_12b_int(off)) {
@@ -688,9 +742,14 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
  		     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);
+		emit_fence_rw_rw(ctx);
  		break;
+	default:
+		pr_err_once("bpf-jit: invalid atomic RMW opcode %02x\n", imm);
+		return -EINVAL;
  	}
+
+	return 0;
  }
 
  #define BPF_FIXUP_OFFSET_MASK   GENMASK(26, 0)
@@ -1259,7 +1318,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  {
  	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
  		    BPF_CLASS(insn->code) == BPF_JMP;
-	int s, e, rvoff, ret, i = insn - ctx->prog->insnsi;
+	int s, e, rvoff, ret = 0, i = insn - ctx->prog->insnsi;
  	struct bpf_prog_aux *aux = ctx->prog->aux;
  	u8 rd = -1, rs = -1, code = insn->code;
  	s16 off = insn->off;
@@ -1962,10 +2021,14 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  	case BPF_STX | BPF_MEM | BPF_DW:
  		emit_store_64(rd, off, rs, ctx);
  		break;
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
  	case BPF_STX | BPF_ATOMIC | BPF_W:
  	case BPF_STX | BPF_ATOMIC | BPF_DW:
-		emit_atomic(rd, rs, off, imm,
-			    BPF_SIZE(code) == BPF_DW, ctx);
+		if (bpf_atomic_is_load_store(insn))
+			ret = emit_atomic_ld_st(rd, rs, off, imm, code, ctx);
+		else
+			ret = emit_atomic_rmw(rd, rs, off, imm, code, ctx);
  		break;
 
  	case BPF_STX | BPF_PROBE_MEM32 | BPF_B:

arch/riscv/net/bpf_jit_comp64.c int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, · line 2119

Quoted 8 lines
arch/riscv/net/bpf_jit_comp64.c +1 -1
@@ -2050,7 +2113,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  		return -EINVAL;
  	}
 
-	return 0;
+	return ret;
  }
 
  void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
maintainer Reviewed-by on v1 4/8
#11 lore raw

Re: [PATCH bpf-next 4/8] bpf, riscv64: Skip redundant zext instruction after load-acquire

In reply to Peilin Ye
Quoted 86 lines · Peilin Ye

Currently, the verifier inserts a zext instruction right after every 8-, 16- or 32-bit load-acquire, which is already zero-extending. Skip such redundant zext instructions.

While we are here, update that already-obsolete comment about "skip the next instruction" in build_body(). Also change emit_atomic_rmw()'s parameters to keep it consistent with emit_atomic_ld_st().

Note that checking 'insn[1]' relies on 'insn' not being the last instruction, which should have been guaranteed by the verifier; we already use 'insn[1]' elsewhere in the file for similar purposes. Additionally, we don't check if 'insn[1]' is actually a zext for our load-acquire's dst_reg, or some other registers - in other words, here we are relying on the verifier to always insert a redundant zext right after a 8/16/32-bit load-acquire, for its dst_reg.

---
  arch/riscv/net/bpf_jit_comp64.c | 23 ++++++++++++++++++-----
  arch/riscv/net/bpf_jit_core.c   |  3 +--
  2 files changed, 19 insertions(+), 7 deletions(-)
arch/riscv/net/bpf_jit_comp64.c +18 -5
index b71a9c88fb4f..4cb50dbbe94b 100644
@@ -607,8 +607,13 @@ static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
  	emit_sd(RV_REG_T1, 0, rs, ctx);
  }
 
-static int emit_atomic_ld_st(u8 rd, u8 rs, s16 off, s32 imm, u8 code, struct rv_jit_context *ctx)
+static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn,
+			     struct rv_jit_context *ctx)
  {
+	u8 code = insn->code;
+	s32 imm = insn->imm;
+	s16 off = insn->off;
+
  	switch (imm) {
  	/* dst_reg = load_acquire(src_reg + off16) */
  	case BPF_LOAD_ACQ:
@@ -627,6 +632,12 @@ static int emit_atomic_ld_st(u8 rd, u8 rs, s16 off, s32 imm, u8 code, struct rv_
  			break;
  		}
  		emit_fence_r_rw(ctx);
+
+		/* If our next insn is a redundant zext, return 1 to tell
+		 * build_body() to skip it.
+		 */
+		if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1]))
+			return 1;
  		break;
  	/* store_release(dst_reg + off16, src_reg) */
  	case BPF_STORE_REL:
@@ -654,10 +665,12 @@ static int emit_atomic_ld_st(u8 rd, u8 rs, s16 off, s32 imm, u8 code, struct rv_
  	return 0;
  }
 
-static int emit_atomic_rmw(u8 rd, u8 rs, s16 off, s32 imm, u8 code,
+static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn,
  			   struct rv_jit_context *ctx)
  {
-	u8 r0;
+	u8 r0, code = insn->code;
+	s16 off = insn->off;
+	s32 imm = insn->imm;
  	int jmp_offset;
  	bool is64;
 
@@ -2026,9 +2039,9 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  	case BPF_STX | BPF_ATOMIC | BPF_W:
  	case BPF_STX | BPF_ATOMIC | BPF_DW:
  		if (bpf_atomic_is_load_store(insn))
-			ret = emit_atomic_ld_st(rd, rs, off, imm, code, ctx);
+			ret = emit_atomic_ld_st(rd, rs, insn, ctx);
  		else
-			ret = emit_atomic_rmw(rd, rs, off, imm, code, ctx);
+			ret = emit_atomic_rmw(rd, rs, insn, ctx);
  		break;
 
  	case BPF_STX | BPF_PROBE_MEM32 | BPF_B:
arch/riscv/net/bpf_jit_core.c +0 -0
index f8cd2f70a7fb..f6ca5cfa6b2f 100644

arch/riscv/net/bpf_jit_core.c static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) · line 33

Quoted 10 lines
arch/riscv/net/bpf_jit_core.c +1 -2
@@ -26,9 +26,8 @@ static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset)
  		int ret;
 
  		ret = bpf_jit_emit_insn(insn, ctx, extra_pass);
-		/* BPF_LD | BPF_IMM | BPF_DW: skip the next instruction. */
  		if (ret > 0)
-			i++;
+			i++; /* skip the next instruction */
  		if (offset)
  			offset[i] = ctx->ninsns;
  		if (ret < 0)
maintainer
#20 lore raw
In reply to Peilin Ye
Quoted 37 lines · Peilin Ye

Hi all!

Patchset [1] introduced BPF load-acquire (BPF_LOAD_ACQ) and store-release (BPF_STORE_REL) instructions, and added x86-64 and arm64 JIT compiler support. As a follow-up, this patchset supports load-acquire and store-release instructions for the riscv64 JIT compiler, and introduces some related selftests/ changes.

Specifically:

* PATCH 1 makes insn_def_regno() handle load-acquires properly for bpf_jit_needs_zext() (true for riscv64) architectures
* PATCH 2, 3 from Andrea Parri add the actual support to the riscv64 JIT compiler
* PATCH 4 optimizes code emission by skipping redundant zext instructions inserted by the verifier
* PATCH 5, 6 and 7 are minor selftest/ improvements
* PATCH 8 enables (non-arena) load-acquire/store-release selftests for

    riscv64

Please refer to individual patches for details. Thanks!

[1] https://lore.kernel.org/all/[email protected]/

Andrea Parri (2):
bpf, riscv64: Introduce emit_load_*() and emit_store_*() bpf, riscv64: Support load-acquire and store-release instructions

Peilin Ye (6):
bpf/verifier: Handle BPF_LOAD_ACQ instructions in insn_def_regno() bpf, riscv64: Skip redundant zext instruction after load-acquire selftests/bpf: Use CAN_USE_LOAD_ACQ_STORE_REL when appropriate selftests/bpf: Avoid passing out-of-range values to __retval() selftests/bpf: Verify zero-extension behavior in load-acquire tests selftests/bpf: Enable non-arena load-acquire/store-release selftests
for riscv64

Quoted 10 lines
  arch/riscv/net/bpf_jit.h                      |  15 +
  arch/riscv/net/bpf_jit_comp64.c               | 334 ++++++++++++------
  arch/riscv/net/bpf_jit_core.c                 |   3 +-
  kernel/bpf/verifier.c                         |  11 +-
  tools/testing/selftests/bpf/progs/bpf_misc.h  |   5 +-
  .../bpf/progs/verifier_load_acquire.c         |  48 ++-
  .../selftests/bpf/progs/verifier_precision.c  |   5 +-
  .../bpf/progs/verifier_store_release.c        |  39 +-
  8 files changed, 314 insertions(+), 146 deletions(-)

Hi Peilin, good to see the implementation of load-acquire and store-release instructions on RV64! But I'm about to start my vacation, so I'll test it once I'm back.

author
#21 lore raw

Hi Lehui,

Quoted 24 lines · Pu Lehui
Quoted 13 lines · Peilin Ye

Andrea Parri (2):
bpf, riscv64: Introduce emit_load_*() and emit_store_*() bpf, riscv64: Support load-acquire and store-release instructions

Peilin Ye (6):
bpf/verifier: Handle BPF_LOAD_ACQ instructions in insn_def_regno() bpf, riscv64: Skip redundant zext instruction after load-acquire selftests/bpf: Use CAN_USE_LOAD_ACQ_STORE_REL when appropriate selftests/bpf: Avoid passing out-of-range values to __retval() selftests/bpf: Verify zero-extension behavior in load-acquire tests selftests/bpf: Enable non-arena load-acquire/store-release selftests
for riscv64

Quoted 9 lines
  arch/riscv/net/bpf_jit.h                      |  15 +
  arch/riscv/net/bpf_jit_comp64.c               | 334 ++++++++++++------
  arch/riscv/net/bpf_jit_core.c                 |   3 +-
  kernel/bpf/verifier.c                         |  11 +-
  tools/testing/selftests/bpf/progs/bpf_misc.h  |   5 +-
  .../bpf/progs/verifier_load_acquire.c         |  48 ++-
  .../selftests/bpf/progs/verifier_precision.c  |   5 +-
  .../bpf/progs/verifier_store_release.c        |  39 +-
  8 files changed, 314 insertions(+), 146 deletions(-)
Quoted 3 lines

Hi Peilin, good to see the implementation of load-acquire and store-release instructions on RV64! But I'm about to start my vacation, so I'll test it once I'm back.

Thanks for the reviews, and have a great vacation!

Peilin Ye

maintainer Acked-by Tested-by on the v1 series
#22 lore raw
In reply to Peilin Ye

Andrea/Peilin!

Quoted 7 lines · Peilin Ye

Hi all!

Patchset [1] introduced BPF load-acquire (BPF_LOAD_ACQ) and store-release (BPF_STORE_REL) instructions, and added x86-64 and arm64 JIT compiler support. As a follow-up, this patchset supports load-acquire and store-release instructions for the riscv64 JIT compiler, and introduces some related selftests/ changes.

Thanks a bunch for working on this!

For the series:

author
#23 lore raw

Hi Björn,

Quoted 7 lines · Björn Töpel
Quoted 5 lines · Peilin Ye

Patchset [1] introduced BPF load-acquire (BPF_LOAD_ACQ) and store-release (BPF_STORE_REL) instructions, and added x86-64 and arm64 JIT compiler support. As a follow-up, this patchset supports load-acquire and store-release instructions for the riscv64 JIT compiler, and introduces some related selftests/ changes.

Quoted 5 lines

Thanks a bunch for working on this!

For the series:

Thanks for testing this!

Peilin Ye

maintainer
#2 lore raw

Re: [PATCH bpf-next 1/8] bpf/verifier: Handle BPF_LOAD_ACQ instructions in insn_def_regno()

In reply to Peilin Ye
Quoted 24 lines · Peilin Ye

In preparation for supporting BPF load-acquire and store-release instructions for architectures where bpf_jit_needs_zext() returns true (e.g. riscv64), make insn_def_regno() handle load-acquires properly.

---
  kernel/bpf/verifier.c | 11 +++++++----
  1 file changed, 7 insertions(+), 4 deletions(-)
kernel/bpf/verifier.c +2 -3
index 54c6953a8b84..6435ea23fee4 100644
@@ -3649,13 +3649,16 @@ static int insn_def_regno(const struct bpf_insn *insn)
  	case BPF_ST:
  		return -1;
  	case BPF_STX:
-		if ((BPF_MODE(insn->code) == BPF_ATOMIC ||
-		     BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) &&
-		    (insn->imm & BPF_FETCH)) {
+		if (BPF_MODE(insn->code) == BPF_ATOMIC ||
+		    BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) {
  			if (insn->imm == BPF_CMPXCHG)
  				return BPF_REG_0;

kernel/bpf/verifier.c static int insn_def_regno(const struct bpf_insn *insn) · line 3664

Quoted 10 lines
kernel/bpf/verifier.c +5 -1
-			else
+			else if (insn->imm == BPF_LOAD_ACQ)
+				return insn->dst_reg;
+			else if (insn->imm & BPF_FETCH)
  				return insn->src_reg;
+			else
+				return -1;
  		} else {
  			return -1;
  		}

How about simplify like this:

```
static int insn_def_regno(const struct bpf_insn *insn)
{
        switch (BPF_CLASS(insn->code)) {
        case BPF_JMP:
        case BPF_JMP32:
        case BPF_ST:
                return -1;
        case BPF_STX:
                if (BPF_MODE(insn->code) == BPF_ATOMIC ||
                    BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) {
                        if (insn->imm == BPF_CMPXCHG)
                                return BPF_REG_0;
                        else if (insn->imm == BPF_LOAD_ACQ)
                                return insn->dst_reg;
                        else if (insn->imm & BPF_FETCH)
                                return insn->src_reg;
                }
                return -1;
        default:
                return insn->dst_reg;
        }
}
```
maintainer
#8 lore raw
In reply to Peilin Ye
Quoted 195 lines · Peilin Ye

From: Andrea Parri <[email protected]>

Support BPF load-acquire (BPF_LOAD_ACQ) and store-release (BPF_STORE_REL) instructions in the riscv64 JIT compiler. For example, consider the following 64-bit load-acquire (assuming little-endian):

   db 10 00 00 00 01 00 00  r1 = load_acquire((u64 *)(r1 + 0x0))
   95 00 00 00 00 00 00 00  exit

   opcode (0xdb): BPF_ATOMIC | BPF_DW | BPF_STX
   imm (0x00000100): BPF_LOAD_ACQ

The JIT compiler will emit an LD instruction followed by a FENCE R,RW instruction for the above, e.g.:

   ld x7,0(x6)
   fence r,rw

Similarly, consider the following 16-bit store-release:

   cb 21 00 00 10 01 00 00  store_release((u16 *)(r1 + 0x0), w2)
   95 00 00 00 00 00 00 00  exit

   opcode (0xcb): BPF_ATOMIC | BPF_H | BPF_STX
   imm (0x00000110): BPF_STORE_REL

A FENCE RW,W instruction followed by an SH instruction will be emitted, e.g.:

   fence rw,w
   sh x2,0(x4)

8-bit and 16-bit load-acquires are zero-extending (cf., LBU, LHU). The verifier always rejects misaligned load-acquires/store-releases (even if BPF_F_ANY_ALIGNMENT is set), so the emitted load and store instructions are guaranteed to be single-copy atomic.

Introduce primitives to emit the relevant (and the most common/used in the kernel) fences, i.e. fences with R -> RW, RW -> W and RW -> RW.

Rename emit_atomic() to emit_atomic_rmw() to make it clear that it only handles RMW atomics, and replace its is64 parameter to allow to perform the required checks on the opsize (BPF_SIZE(code)).

[[email protected]: whitespace changes; cosmetic changes to commit
title and message]

---
  arch/riscv/net/bpf_jit.h        | 15 +++++++
  arch/riscv/net/bpf_jit_comp64.c | 77 ++++++++++++++++++++++++++++++---
  2 files changed, 85 insertions(+), 7 deletions(-)
arch/riscv/net/bpf_jit.h +15 -0
index 1d1c78d4cff1..e7b032dfd17f 100644
@@ -608,6 +608,21 @@ static inline u32 rv_fence(u8 pred, u8 succ)
  	return rv_i_insn(imm11_0, 0, 0, 0, 0xf);
  }
 
+static inline void emit_fence_r_rw(struct rv_jit_context *ctx)
+{
+	emit(rv_fence(0x2, 0x3), ctx);
+}
+
+static inline void emit_fence_rw_w(struct rv_jit_context *ctx)
+{
+	emit(rv_fence(0x3, 0x1), ctx);
+}
+
+static inline void emit_fence_rw_rw(struct rv_jit_context *ctx)
+{
+	emit(rv_fence(0x3, 0x3), ctx);
+}
+
  static inline u32 rv_nop(void)
  {
  	return rv_i_insn(0, 0, 0, 0, 0x13);
arch/riscv/net/bpf_jit_comp64.c +69 -6
index 953b6a20c69f..b71a9c88fb4f 100644
@@ -607,11 +607,65 @@ static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
  	emit_sd(RV_REG_T1, 0, rs, ctx);
  }
 
-static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
-			struct rv_jit_context *ctx)
+static int emit_atomic_ld_st(u8 rd, u8 rs, s16 off, s32 imm, u8 code, struct rv_jit_context *ctx)
+{
+	switch (imm) {
+	/* dst_reg = load_acquire(src_reg + off16) */
+	case BPF_LOAD_ACQ:
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit_load_8(false, rd, off, rs, ctx);
+			break;
+		case BPF_H:
+			emit_load_16(false, rd, off, rs, ctx);
+			break;
+		case BPF_W:
+			emit_load_32(false, rd, off, rs, ctx);
+			break;
+		case BPF_DW:
+			emit_load_64(false, rd, off, rs, ctx);
+			break;
+		}
+		emit_fence_r_rw(ctx);
+		break;
+	/* store_release(dst_reg + off16, src_reg) */
+	case BPF_STORE_REL:
+		emit_fence_rw_w(ctx);
+		switch (BPF_SIZE(code)) {
+		case BPF_B:
+			emit_store_8(rd, off, rs, ctx);
+			break;
+		case BPF_H:
+			emit_store_16(rd, off, rs, ctx);
+			break;
+		case BPF_W:
+			emit_store_32(rd, off, rs, ctx);
+			break;
+		case BPF_DW:
+			emit_store_64(rd, off, rs, ctx);
+			break;
+		}
+		break;
+	default:
+		pr_err_once("bpf-jit: invalid atomic load/store opcode %02x\n", imm);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int emit_atomic_rmw(u8 rd, u8 rs, s16 off, s32 imm, u8 code,
+			   struct rv_jit_context *ctx)
  {
  	u8 r0;
  	int jmp_offset;
+	bool is64;
+
+	if (BPF_SIZE(code) != BPF_W && BPF_SIZE(code) != BPF_DW) {
+		pr_err_once("bpf-jit: 1- and 2-byte RMW atomics are not supported\n");
+		return -EINVAL;
+	}
+	is64 = BPF_SIZE(code) == BPF_DW;
 
  	if (off) {
  		if (is_12b_int(off)) {
@@ -688,9 +742,14 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
  		     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);
+		emit_fence_rw_rw(ctx);
  		break;
+	default:
+		pr_err_once("bpf-jit: invalid atomic RMW opcode %02x\n", imm);
+		return -EINVAL;
  	}
+
+	return 0;
  }
 
  #define BPF_FIXUP_OFFSET_MASK   GENMASK(26, 0)
@@ -1259,7 +1318,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  {
  	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
  		    BPF_CLASS(insn->code) == BPF_JMP;
-	int s, e, rvoff, ret, i = insn - ctx->prog->insnsi;
+	int s, e, rvoff, ret = 0, i = insn - ctx->prog->insnsi;
  	struct bpf_prog_aux *aux = ctx->prog->aux;
  	u8 rd = -1, rs = -1, code = insn->code;
  	s16 off = insn->off;
@@ -1962,10 +2021,14 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  	case BPF_STX | BPF_MEM | BPF_DW:
  		emit_store_64(rd, off, rs, ctx);
  		break;
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
  	case BPF_STX | BPF_ATOMIC | BPF_W:
  	case BPF_STX | BPF_ATOMIC | BPF_DW:
-		emit_atomic(rd, rs, off, imm,
-			    BPF_SIZE(code) == BPF_DW, ctx);
+		if (bpf_atomic_is_load_store(insn))
+			ret = emit_atomic_ld_st(rd, rs, off, imm, code, ctx);
+		else
+			ret = emit_atomic_rmw(rd, rs, off, imm, code, ctx);
  		break;
 
  	case BPF_STX | BPF_PROBE_MEM32 | BPF_B:

arch/riscv/net/bpf_jit_comp64.c int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, · line 2116

Quoted 5 lines
arch/riscv/net/bpf_jit_comp64.c +1 -1
@@ -2050,7 +2113,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  		return -EINVAL;
  	}
 
-	return 0;
+	return ret;

ret may be a value greater than zero, which will potentially cause build_body to skip the next instruction. Let's return 0 here, and return ret if the above fails.

Quoted 3 lines
arch/riscv/net/bpf_jit_comp64.c +0 -0
  }
 
  void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
maintainer Reviewed-by on v1 5/8
#13 lore raw

Re: [PATCH bpf-next 5/8] selftests/bpf: Use CAN_USE_LOAD_ACQ_STORE_REL when appropriate

In reply to Peilin Ye
Quoted 65 lines · Peilin Ye

Instead of open-coding the conditions, use
'#ifdef CAN_USE_LOAD_ACQ_STORE_REL' to guard the following tests:

verifier_precision/bpf_load_acquire
verifier_precision/bpf_store_release
verifier_store_release/*

Note that, for the first two tests in verifier_precision.c, switching to '#ifdef CAN_USE_LOAD_ACQ_STORE_REL' means also checking if '__clang_major__ >= 18', which has already been guaranteed by the outer '#if' check.

---
  tools/testing/selftests/bpf/progs/verifier_precision.c     | 5 ++---
  tools/testing/selftests/bpf/progs/verifier_store_release.c | 7 +++----
  2 files changed, 5 insertions(+), 7 deletions(-)
tools/testing/selftests/bpf/progs/verifier_precision.c +2 -3
index 6662d4b39969..2dd0d15c2678 100644
@@ -91,8 +91,7 @@ __naked int bpf_end_bswap(void)
  		::: __clobber_all);
  }
 
-#if defined(ENABLE_ATOMICS_TESTS) && \
-	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
 
  SEC("?raw_tp")
  __success __log_level(2)
@@ -138,7 +137,7 @@ __naked int bpf_store_release(void)
  	: __clobber_all);
  }
 
-#endif /* load-acquire, store-release */
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
  #endif /* v4 instruction */
 
  SEC("?raw_tp")
tools/testing/selftests/bpf/progs/verifier_store_release.c +2 -3
index c0442d5bb049..7e456e2861b4 100644
@@ -6,8 +6,7 @@
  #include "../../../include/linux/filter.h"
  #include "bpf_misc.h"
 
-#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \
-	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
 
  SEC("socket")
  __description("store-release, 8-bit")
@@ -271,7 +270,7 @@ __naked void store_release_with_invalid_reg(void)
  	: __clobber_all);
  }
 
-#else
+#else /* CAN_USE_LOAD_ACQ_STORE_REL */
 
  SEC("socket")
  __description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support store-release, use a dummy test")

tools/testing/selftests/bpf/progs/verifier_store_release.c int dummy_test(void) · line 285

Quoted 7 lines
tools/testing/selftests/bpf/progs/verifier_store_release.c +1 -1
@@ -281,6 +280,6 @@ int dummy_test(void)
  	return 0;
  }
 
-#endif
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
 
  char _license[] SEC("license") = "GPL";
maintainer Reviewed-by on v1 6/8
#15 lore raw

Re: [PATCH bpf-next 6/8] selftests/bpf: Avoid passing out-of-range values to __retval()

In reply to Peilin Ye
Quoted 193 lines · Peilin Ye

Currently, we pass 0x1234567890abcdef to __retval() for the following two tests:

verifier_load_acquire/load_acquire_64
verifier_store_release/store_release_64

However, the upper 32 bits of that value are being ignored, since __retval() expects an int. Actually, the tests would still pass even if I change '__retval(0x1234567890abcdef)' to e.g. '__retval(0x90abcdef)'.

Restructure the tests a bit to test the entire 64-bit values properly. Do the same to their 8-, 16- and 32-bit variants as well to keep the style consistent.

Fixes ff3afe5da998 ("selftests/bpf: Add selftests for load-acquire and store-release instructions")
---
  .../bpf/progs/verifier_load_acquire.c         | 40 +++++++++++++------
  .../bpf/progs/verifier_store_release.c        | 32 +++++++++++----
  2 files changed, 52 insertions(+), 20 deletions(-)
tools/testing/selftests/bpf/progs/verifier_load_acquire.c +28 -12
index 77698d5a19e4..a696ab84bfd6 100644
@@ -10,65 +10,81 @@
 
  SEC("socket")
  __description("load-acquire, 8-bit")
-__success __success_unpriv __retval(0x12)
+__success __success_unpriv __retval(0)
  __naked void load_acquire_8(void)
  {
  	asm volatile (
+	"r0 = 0;"
  	"w1 = 0x12;"
  	"*(u8 *)(r10 - 1) = w1;"
-	".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r10 - 1));
+	".8byte %[load_acquire_insn];" // w2 = load_acquire((u8 *)(r10 - 1));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
  	"exit;"
  	:
  	: __imm_insn(load_acquire_insn,
-		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -1))
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -1))
  	: __clobber_all);
  }
 
  SEC("socket")
  __description("load-acquire, 16-bit")
-__success __success_unpriv __retval(0x1234)
+__success __success_unpriv __retval(0)
  __naked void load_acquire_16(void)
  {
  	asm volatile (
+	"r0 = 0;"
  	"w1 = 0x1234;"
  	"*(u16 *)(r10 - 2) = w1;"
-	".8byte %[load_acquire_insn];" // w0 = load_acquire((u16 *)(r10 - 2));
+	".8byte %[load_acquire_insn];" // w2 = load_acquire((u16 *)(r10 - 2));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
  	"exit;"
  	:
  	: __imm_insn(load_acquire_insn,
-		     BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -2))
+		     BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -2))
  	: __clobber_all);
  }
 
  SEC("socket")
  __description("load-acquire, 32-bit")
-__success __success_unpriv __retval(0x12345678)
+__success __success_unpriv __retval(0)
  __naked void load_acquire_32(void)
  {
  	asm volatile (
+	"r0 = 0;"
  	"w1 = 0x12345678;"
  	"*(u32 *)(r10 - 4) = w1;"
-	".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 4));
+	".8byte %[load_acquire_insn];" // w2 = load_acquire((u32 *)(r10 - 4));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
  	"exit;"
  	:
  	: __imm_insn(load_acquire_insn,
-		     BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -4))
+		     BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -4))
  	: __clobber_all);
  }
 
  SEC("socket")
  __description("load-acquire, 64-bit")
-__success __success_unpriv __retval(0x1234567890abcdef)
+__success __success_unpriv __retval(0)
  __naked void load_acquire_64(void)
  {
  	asm volatile (
+	"r0 = 0;"
  	"r1 = 0x1234567890abcdef ll;"
  	"*(u64 *)(r10 - 8) = r1;"
-	".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r10 - 8));
+	".8byte %[load_acquire_insn];" // r2 = load_acquire((u64 *)(r10 - 8));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
  	"exit;"
  	:
  	: __imm_insn(load_acquire_insn,
-		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -8))
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -8))
  	: __clobber_all);
  }
 
tools/testing/selftests/bpf/progs/verifier_store_release.c +20 -7
index 7e456e2861b4..72f1eb006074 100644
@@ -10,13 +10,17 @@
 
  SEC("socket")
  __description("store-release, 8-bit")
-__success __success_unpriv __retval(0x12)
+__success __success_unpriv __retval(0)
  __naked void store_release_8(void)
  {
  	asm volatile (
+	"r0 = 0;"
  	"w1 = 0x12;"
  	".8byte %[store_release_insn];" // store_release((u8 *)(r10 - 1), w1);
-	"w0 = *(u8 *)(r10 - 1);"
+	"w2 = *(u8 *)(r10 - 1);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
  	"exit;"
  	:
  	: __imm_insn(store_release_insn,
@@ -26,13 +30,17 @@ __naked void store_release_8(void)
 
  SEC("socket")
  __description("store-release, 16-bit")
-__success __success_unpriv __retval(0x1234)
+__success __success_unpriv __retval(0)
  __naked void store_release_16(void)
  {
  	asm volatile (
+	"r0 = 0;"
  	"w1 = 0x1234;"
  	".8byte %[store_release_insn];" // store_release((u16 *)(r10 - 2), w1);
-	"w0 = *(u16 *)(r10 - 2);"
+	"w2 = *(u16 *)(r10 - 2);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
  	"exit;"
  	:
  	: __imm_insn(store_release_insn,
@@ -42,13 +50,17 @@ __naked void store_release_16(void)
 
  SEC("socket")
  __description("store-release, 32-bit")
-__success __success_unpriv __retval(0x12345678)
+__success __success_unpriv __retval(0)
  __naked void store_release_32(void)
  {
  	asm volatile (
+	"r0 = 0;"
  	"w1 = 0x12345678;"
  	".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 4), w1);
-	"w0 = *(u32 *)(r10 - 4);"
+	"w2 = *(u32 *)(r10 - 4);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
  	"exit;"
  	:
  	: __imm_insn(store_release_insn,
@@ -58,13 +70,17 @@ __naked void store_release_32(void)
 
  SEC("socket")
  __description("store-release, 64-bit")
-__success __success_unpriv __retval(0x1234567890abcdef)
+__success __success_unpriv __retval(0)
  __naked void store_release_64(void)
  {
  	asm volatile (
+	"r0 = 0;"

tools/testing/selftests/bpf/progs/verifier_store_release.c __naked void store_release_32(void) · line 86

Quoted 10 lines
tools/testing/selftests/bpf/progs/verifier_store_release.c +4 -1
  	"r1 = 0x1234567890abcdef ll;"
  	".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1);
-	"r0 = *(u64 *)(r10 - 8);"
+	"r2 = *(u64 *)(r10 - 8);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
  	"exit;"
  	:
  	: __imm_insn(store_release_insn,
maintainer Reviewed-by on v1 7/8
#17 lore raw

Re: [PATCH bpf-next 7/8] selftests/bpf: Verify zero-extension behavior in load-acquire tests

In reply to Peilin Ye
Quoted 41 lines · Peilin Ye

Verify that 8-, 16- and 32-bit load-acquires are zero-extending by using immediate values with their highest bit set. Do the same for the 64-bit variant to keep the style consistent.

---
  tools/testing/selftests/bpf/progs/verifier_load_acquire.c | 8 ++++----
  1 file changed, 4 insertions(+), 4 deletions(-)
tools/testing/selftests/bpf/progs/verifier_load_acquire.c +3 -3
index a696ab84bfd6..74f4f19c10b8 100644
@@ -15,7 +15,7 @@ __naked void load_acquire_8(void)
  {
  	asm volatile (
  	"r0 = 0;"
-	"w1 = 0x12;"
+	"w1 = 0xfe;"
  	"*(u8 *)(r10 - 1) = w1;"
  	".8byte %[load_acquire_insn];" // w2 = load_acquire((u8 *)(r10 - 1));
  	"if r2 == r1 goto 1f;"
@@ -35,7 +35,7 @@ __naked void load_acquire_16(void)
  {
  	asm volatile (
  	"r0 = 0;"
-	"w1 = 0x1234;"
+	"w1 = 0xfedc;"
  	"*(u16 *)(r10 - 2) = w1;"
  	".8byte %[load_acquire_insn];" // w2 = load_acquire((u16 *)(r10 - 2));
  	"if r2 == r1 goto 1f;"
@@ -55,7 +55,7 @@ __naked void load_acquire_32(void)
  {
  	asm volatile (
  	"r0 = 0;"
-	"w1 = 0x12345678;"
+	"w1 = 0xfedcba09;"
  	"*(u32 *)(r10 - 4) = w1;"
  	".8byte %[load_acquire_insn];" // w2 = load_acquire((u32 *)(r10 - 4));
  	"if r2 == r1 goto 1f;"

tools/testing/selftests/bpf/progs/verifier_load_acquire.c __naked void load_acquire_64(void) · line 81

Quoted 8 lines
tools/testing/selftests/bpf/progs/verifier_load_acquire.c +1 -1
@@ -75,7 +75,7 @@ __naked void load_acquire_64(void)
  {
  	asm volatile (
  	"r0 = 0;"
-	"r1 = 0x1234567890abcdef ll;"
+	"r1 = 0xfedcba0987654321 ll;"
  	"*(u64 *)(r10 - 8) = r1;"
  	".8byte %[load_acquire_insn];" // r2 = load_acquire((u64 *)(r10 - 8));
  	"if r2 == r1 goto 1f;"
maintainer Reviewed-by on v1 8/8
#19 lore raw

Re: [PATCH bpf-next 8/8] selftests/bpf: Enable non-arena load-acquire/store-release selftests for riscv64

In reply to Peilin Ye
Quoted 15 lines · Peilin Ye

For riscv64, enable all BPF_{LOAD_ACQ,STORE_REL} selftests except the arena_atomics/* ones (not guarded behind CAN_USE_LOAD_ACQ_STORE_REL), since arena access is not yet supported.

---
  tools/testing/selftests/bpf/progs/bpf_misc.h | 5 +++--
  1 file changed, 3 insertions(+), 2 deletions(-)
tools/testing/selftests/bpf/progs/bpf_misc.h +0 -0
index 863df7c0fdd0..6e208e24ba3b 100644
@@ -225,8 +225,9 @@
  #define CAN_USE_BPF_ST

tools/testing/selftests/bpf/progs/bpf_misc.h line 233

Quoted 10 lines
tools/testing/selftests/bpf/progs/bpf_misc.h +3 -2
  #endif
 
-#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) && \
-	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) &&		\
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) ||	\
+	 (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
  #define CAN_USE_LOAD_ACQ_STORE_REL
  #endif
 
author
#3 lore raw

Re: [PATCH bpf-next 1/8] bpf/verifier: Handle BPF_LOAD_ACQ instructions in insn_def_regno()

In reply to Pu Lehui

Hi Lehui,

Quoted 42 lines · Pu Lehui
Quoted 13 lines · Peilin Ye
kernel/bpf/verifier.c +2 -3
@@ -3649,13 +3649,16 @@ static int insn_def_regno(const struct bpf_insn *insn)
  	case BPF_ST:
  		return -1;
  	case BPF_STX:
-		if ((BPF_MODE(insn->code) == BPF_ATOMIC ||
-		     BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) &&
-		    (insn->imm & BPF_FETCH)) {
+		if (BPF_MODE(insn->code) == BPF_ATOMIC ||
+		    BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) {
  			if (insn->imm == BPF_CMPXCHG)
  				return BPF_REG_0;

kernel/bpf/verifier.c static int insn_def_regno(const struct bpf_insn *insn) · line 3664

Quoted 10 lines
kernel/bpf/verifier.c +5 -1
-			else
+			else if (insn->imm == BPF_LOAD_ACQ)
+				return insn->dst_reg;
+			else if (insn->imm & BPF_FETCH)
  				return insn->src_reg;
+			else
+				return -1;
  		} else {
  			return -1;
  		}

How about simplify like this:

```
static int insn_def_regno(const struct bpf_insn *insn)
{
        switch (BPF_CLASS(insn->code)) {
        case BPF_JMP:
        case BPF_JMP32:
        case BPF_ST:
                return -1;
        case BPF_STX:
                if (BPF_MODE(insn->code) == BPF_ATOMIC ||
                    BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) {
                        if (insn->imm == BPF_CMPXCHG)
                                return BPF_REG_0;
                        else if (insn->imm == BPF_LOAD_ACQ)
                                return insn->dst_reg;
                        else if (insn->imm & BPF_FETCH)
Quoted 8 lines
                                return insn->src_reg;
                }
                return -1;
        default:
                return insn->dst_reg;
        }
}
```

I see, I'll change it in v2. Thanks for the suggestion!

Peilin Ye

author
#9 lore raw
In reply to Pu Lehui
Quoted 27 lines · Pu Lehui
Quoted 26 lines · Peilin Ye
arch/riscv/net/bpf_jit_comp64.c +7 -3
@@ -1259,7 +1318,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  {
  	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
  		    BPF_CLASS(insn->code) == BPF_JMP;
-	int s, e, rvoff, ret, i = insn - ctx->prog->insnsi;
+	int s, e, rvoff, ret = 0, i = insn - ctx->prog->insnsi;
  	struct bpf_prog_aux *aux = ctx->prog->aux;
  	u8 rd = -1, rs = -1, code = insn->code;
  	s16 off = insn->off;
@@ -1962,10 +2021,14 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
  	case BPF_STX | BPF_MEM | BPF_DW:
  		emit_store_64(rd, off, rs, ctx);
  		break;
+	case BPF_STX | BPF_ATOMIC | BPF_B:
+	case BPF_STX | BPF_ATOMIC | BPF_H:
  	case BPF_STX | BPF_ATOMIC | BPF_W:
  	case BPF_STX | BPF_ATOMIC | BPF_DW:
-		emit_atomic(rd, rs, off, imm,
-			    BPF_SIZE(code) == BPF_DW, ctx);
+		if (bpf_atomic_is_load_store(insn))
+			ret = emit_atomic_ld_st(rd, rs, off, imm, code, ctx);
+		else
+			ret = emit_atomic_rmw(rd, rs, off, imm, code, ctx);
  		break;
  	case BPF_STX | BPF_PROBE_MEM32 | BPF_B:
@@ -2050,7 +2113,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
Quoted 8 lines

arch/riscv/net/bpf_jit_comp64.c int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, · line 2116

Quoted 4 lines
arch/riscv/net/bpf_jit_comp64.c +1 -1
  		return -EINVAL;
  	}
-	return 0;
+	return ret;

ret may be a value greater than zero, which will potentially cause build_body to skip the next instruction. Let's return 0 here, and return ret if the above fails.

Sure, I'll change this in v2.

Thanks,
Peilin Ye