[PATCH bpf-next 00/10] Add support arena atomics for RV64

[PATCH bpf-next 00/10] Add support arena atomics for RV64

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

patch 1-3 refactor redundant load and store operations.
patch 4-7 add Zacas instructions for cmpxchg.
patch 8 optimizes exception table handling.
patch 9-10 add support arena atomics for RV64.

Tests `test_progs -t atomic,arena` have passed as shown bellow,
as well as `test_verifier` and `test_bpf.ko` have passed.

$ ./test_progs -t arena,atomic
#3/1     arena_atomics/add:OK
#3/2     arena_atomics/sub:OK
#3/3     arena_atomics/and:OK
#3/4     arena_atomics/or:OK
#3/5     arena_atomics/xor:OK
#3/6     arena_atomics/cmpxchg:OK
#3/7     arena_atomics/xchg:OK
#3/8     arena_atomics/uaf:OK
#3/9     arena_atomics/load_acquire:OK
#3/10    arena_atomics/store_release:OK
#3       arena_atomics:OK
#4/1     arena_htab/arena_htab_llvm:OK
#4/2     arena_htab/arena_htab_asm:OK
#4       arena_htab:OK
#5/1     arena_list/arena_list_1:OK
#5/2     arena_list/arena_list_1000:OK
#5       arena_list:OK
#6/1     arena_spin_lock/arena_spin_lock_1:OK
#6/2     arena_spin_lock/arena_spin_lock_1000:OK
#6/3     arena_spin_lock/arena_spin_lock_50000:OK
#6       arena_spin_lock:OK
#10      atomic_bounds:OK
#11/1    atomics/add:OK
#11/2    atomics/sub:OK
#11/3    atomics/and:OK
#11/4    atomics/or:OK
#11/5    atomics/xor:OK
#11/6    atomics/cmpxchg:OK
#11/7    atomics/xchg:OK
#11      atomics:OK
#513/1   verifier_arena/basic_alloc1:OK
#513/2   verifier_arena/basic_alloc2:OK
#513/3   verifier_arena/basic_alloc3:OK
#513/4   verifier_arena/basic_reserve1:OK
#513/5   verifier_arena/basic_reserve2:OK
#513/6   verifier_arena/reserve_twice:OK
#513/7   verifier_arena/reserve_invalid_region:OK
#513/8   verifier_arena/iter_maps1:OK
#513/9   verifier_arena/iter_maps2:OK
#513/10  verifier_arena/iter_maps3:OK
#513     verifier_arena:OK
#514/1   verifier_arena_large/big_alloc1:OK
#514/2   verifier_arena_large/access_reserved:OK
#514/3   verifier_arena_large/request_partially_reserved:OK
#514/4   verifier_arena_large/free_reserved:OK
#514/5   verifier_arena_large/big_alloc2:OK
#514     verifier_arena_large:OK
Summary: 8/39 PASSED, 0 SKIPPED, 0 FAILED

Pu Lehui (10):
  riscv, bpf: Extract emit_stx() helper
  riscv, bpf: Extract emit_st() helper
  riscv, bpf: Extract emit_ldx() helper
  riscv: Separate toolchain support dependency from RISCV_ISA_ZACAS
  riscv, bpf: Add rv_ext_enabled macro for runtime detection extentsion
  riscv, bpf: Add Zacas instructions
  riscv, bpf: Optimize cmpxchg insn with Zacas support
  riscv, bpf: Add ex_insn_off and ex_jmp_off for exception table
    handling
  riscv, bpf: Add support arena atomics for RV64
  selftests/bpf: Enable arena atomics tests for RV64

 arch/riscv/Kconfig                            |   1 -
 arch/riscv/include/asm/cmpxchg.h              |   6 +-
 arch/riscv/kernel/setup.c                     |   1 +
 arch/riscv/net/bpf_jit.h                      |  70 ++-
 arch/riscv/net/bpf_jit_comp64.c               | 516 +++++-------------
 .../selftests/bpf/progs/arena_atomics.c       |   9 +-
 6 files changed, 214 insertions(+), 389 deletions(-)

-- 
2.34.1

[PATCH bpf-next 01/10] riscv, bpf: Extract emit_stx() helper

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

There's a lot of redundant code related to store from register
operations, let's extract emit_stx() to make code more compact.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 arch/riscv/net/bpf_jit_comp64.c | 172 ++++++++------------------------
 1 file changed, 41 insertions(+), 131 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 10e01ff06312..ba75ba179b26 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -559,52 +559,39 @@ static int emit_load_64(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_cont
 	return ctx->ninsns - insns_start;
 }
 
-static void emit_store_8(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+static void emit_stx_insn(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context *ctx)
 {
-	if (is_12b_int(off)) {
+	switch (size) {
+	case BPF_B:
 		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)) {
+		break;
+	case BPF_H:
 		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)) {
+		break;
+	case BPF_W:
 		emit_sw(rd, off, rs, ctx);
-		return;
+		break;
+	case BPF_DW:
+		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_sw(RV_REG_T1, 0, rs, ctx);
 }
 
-static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx)
+static int emit_stx(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context *ctx)
 {
+	int insns_start;
+
 	if (is_12b_int(off)) {
-		emit_sd(rd, off, rs, ctx);
-		return;
+		insns_start = ctx->ninsns;
+		emit_stx_insn(rd, off, rs, size, ctx);
+		return ctx->ninsns - insns_start;
 	}
 
 	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);
+	insns_start = ctx->ninsns;
+	emit_stx_insn(RV_REG_T1, 0, rs, size, ctx);
+	return ctx->ninsns - insns_start;
 }
 
 static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn,
@@ -642,20 +629,7 @@ static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn,
 	/* 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;
-		}
+		emit_stx(rd, off, rs, BPF_SIZE(code), ctx);
 		break;
 	default:
 		pr_err_once("bpf-jit: invalid atomic load/store opcode %02x\n", imm);
@@ -2023,106 +1997,42 @@ 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:
-		emit_store_8(rd, off, rs, ctx);
-		break;
 	case BPF_STX | BPF_MEM | BPF_H:
-		emit_store_16(rd, off, rs, ctx);
-		break;
 	case BPF_STX | BPF_MEM | BPF_W:
-		emit_store_32(rd, off, rs, ctx);
-		break;
 	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:
-		if (bpf_atomic_is_load_store(insn))
-			ret = emit_atomic_ld_st(rd, rs, insn, ctx);
-		else
-			ret = emit_atomic_rmw(rd, rs, insn, ctx);
-		if (ret)
-			return ret;
-		break;
-
+	/* STX | PROBE_MEM32: *(size *)(dst + RV_REG_ARENA + off) = src */
 	case BPF_STX | BPF_PROBE_MEM32 | BPF_B:
 	case BPF_STX | BPF_PROBE_MEM32 | BPF_H:
 	case BPF_STX | BPF_PROBE_MEM32 | BPF_W:
 	case BPF_STX | BPF_PROBE_MEM32 | BPF_DW:
 	{
-		int insn_len, insns_start;
-
-		emit_add(RV_REG_T2, rd, RV_REG_ARENA, ctx);
-		rd = RV_REG_T2;
-
-		switch (BPF_SIZE(code)) {
-		case BPF_B:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit(rv_sb(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, rd, ctx);
-			insns_start = ctx->ninsns;
-			emit(rv_sb(RV_REG_T1, 0, rs), ctx);
-			insn_len = ctx->ninsns - insns_start;
-			break;
-		case BPF_H:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit(rv_sh(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, rd, ctx);
-			insns_start = ctx->ninsns;
-			emit(rv_sh(RV_REG_T1, 0, rs), ctx);
-			insn_len = ctx->ninsns - insns_start;
-			break;
-		case BPF_W:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit_sw(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, rd, ctx);
-			insns_start = ctx->ninsns;
-			emit_sw(RV_REG_T1, 0, rs, ctx);
-			insn_len = ctx->ninsns - insns_start;
-			break;
-		case BPF_DW:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit_sd(rd, off, rs, ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
+		int insn_len;
 
-			emit_imm(RV_REG_T1, off, ctx);
-			emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-			insns_start = ctx->ninsns;
-			emit_sd(RV_REG_T1, 0, rs, ctx);
-			insn_len = ctx->ninsns - insns_start;
-			break;
+		if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
+			emit_add(RV_REG_T2, rd, RV_REG_ARENA, ctx);
+			rd = RV_REG_T2;
 		}
 
-		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER,
-					    insn_len);
+		insn_len = emit_stx(rd, off, rs, BPF_SIZE(code), ctx);
+
+		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER, insn_len);
 		if (ret)
 			return ret;
-
 		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:
+		if (bpf_atomic_is_load_store(insn))
+			ret = emit_atomic_ld_st(rd, rs, insn, ctx);
+		else
+			ret = emit_atomic_rmw(rd, rs, insn, ctx);
+		if (ret)
+			return ret;
+		break;
+
 	default:
 		pr_err("bpf-jit: unknown opcode %02x\n", code);
 		return -EINVAL;
-- 
2.34.1

[PATCH bpf-next 02/10] riscv, bpf: Extract emit_st() helper

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

There's a lot of redundant code related to store from immediate
operations, let's extract emit_st() to make code more compact.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 arch/riscv/net/bpf_jit_comp64.c | 135 ++++++--------------------------
 1 file changed, 26 insertions(+), 109 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index ba75ba179b26..5e354f686ea3 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -577,6 +577,24 @@ static void emit_stx_insn(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context
 	}
 }
 
+static int emit_st(u8 rd, s16 off, s32 imm, u8 size, struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	emit_imm(RV_REG_T1, imm, ctx);
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		emit_stx_insn(rd, off, RV_REG_T1, size, ctx);
+		return ctx->ninsns - insns_start;
+	}
+
+	emit_imm(RV_REG_T2, off, ctx);
+	emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
+	insns_start = ctx->ninsns;
+	emit_stx_insn(RV_REG_T2, 0, RV_REG_T1, size, ctx);
+	return ctx->ninsns - insns_start;
+}
+
 static int emit_stx(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context *ctx)
 {
 	int insns_start;
@@ -1870,128 +1888,27 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
 	/* ST: *(size *)(dst + off) = imm */
 	case BPF_ST | BPF_MEM | BPF_B:
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (is_12b_int(off)) {
-			emit(rv_sb(rd, off, RV_REG_T1), ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T2, off, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
-		emit(rv_sb(RV_REG_T2, 0, RV_REG_T1), ctx);
-		break;
-
 	case BPF_ST | BPF_MEM | BPF_H:
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (is_12b_int(off)) {
-			emit(rv_sh(rd, off, RV_REG_T1), ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T2, off, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
-		emit(rv_sh(RV_REG_T2, 0, RV_REG_T1), ctx);
-		break;
 	case BPF_ST | BPF_MEM | BPF_W:
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (is_12b_int(off)) {
-			emit_sw(rd, off, RV_REG_T1, ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T2, off, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
-		emit_sw(RV_REG_T2, 0, RV_REG_T1, ctx);
-		break;
 	case BPF_ST | BPF_MEM | BPF_DW:
-		emit_imm(RV_REG_T1, imm, ctx);
-		if (is_12b_int(off)) {
-			emit_sd(rd, off, RV_REG_T1, ctx);
-			break;
-		}
-
-		emit_imm(RV_REG_T2, off, ctx);
-		emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
-		emit_sd(RV_REG_T2, 0, RV_REG_T1, ctx);
-		break;
-
+	/* ST | PROBE_MEM32: *(size *)(dst + RV_REG_ARENA + off) = imm */
 	case BPF_ST | BPF_PROBE_MEM32 | BPF_B:
 	case BPF_ST | BPF_PROBE_MEM32 | BPF_H:
 	case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
 	case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
 	{
-		int insn_len, insns_start;
-
-		emit_add(RV_REG_T3, rd, RV_REG_ARENA, ctx);
-		rd = RV_REG_T3;
-
-		/* Load imm to a register then store it */
-		emit_imm(RV_REG_T1, imm, ctx);
-
-		switch (BPF_SIZE(code)) {
-		case BPF_B:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit(rv_sb(rd, off, RV_REG_T1), ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T2, off, ctx);
-			emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
-			insns_start = ctx->ninsns;
-			emit(rv_sb(RV_REG_T2, 0, RV_REG_T1), ctx);
-			insn_len = ctx->ninsns - insns_start;
-			break;
-		case BPF_H:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit(rv_sh(rd, off, RV_REG_T1), ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T2, off, ctx);
-			emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
-			insns_start = ctx->ninsns;
-			emit(rv_sh(RV_REG_T2, 0, RV_REG_T1), ctx);
-			insn_len = ctx->ninsns - insns_start;
-			break;
-		case BPF_W:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit_sw(rd, off, RV_REG_T1, ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
-
-			emit_imm(RV_REG_T2, off, ctx);
-			emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
-			insns_start = ctx->ninsns;
-			emit_sw(RV_REG_T2, 0, RV_REG_T1, ctx);
-			insn_len = ctx->ninsns - insns_start;
-			break;
-		case BPF_DW:
-			if (is_12b_int(off)) {
-				insns_start = ctx->ninsns;
-				emit_sd(rd, off, RV_REG_T1, ctx);
-				insn_len = ctx->ninsns - insns_start;
-				break;
-			}
+		int insn_len;
 
-			emit_imm(RV_REG_T2, off, ctx);
-			emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
-			insns_start = ctx->ninsns;
-			emit_sd(RV_REG_T2, 0, RV_REG_T1, ctx);
-			insn_len = ctx->ninsns - insns_start;
-			break;
+		if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
+			emit_add(RV_REG_T3, rd, RV_REG_ARENA, ctx);
+			rd = RV_REG_T3;
 		}
 
-		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER,
-					    insn_len);
+		insn_len = emit_st(rd, off, imm, BPF_SIZE(code), ctx);
+
+		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER, insn_len);
 		if (ret)
 			return ret;
-
 		break;
 	}
 
-- 
2.34.1

[PATCH bpf-next 03/10] riscv, bpf: Extract emit_ldx() helper

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

There's a lot of redundant code related to load into register
operations, let's extract emit_ldx() to make code more compact.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 arch/riscv/net/bpf_jit_comp64.c | 143 ++++++++------------------------
 1 file changed, 35 insertions(+), 108 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 5e354f686ea3..a6a9fd9193e5 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -473,90 +473,24 @@ 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)
+static void emit_ldx_insn(u8 rd, s16 off, u8 rs, u8 size, bool sign_ext,
+			  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;
+	switch (size) {
+	case BPF_B:
+		emit(sign_ext ? rv_lb(rd, off, rs) : rv_lbu(rd, off, rs), ctx);
+		break;
+	case BPF_H:
+		emit(sign_ext ? rv_lh(rd, off, rs) : rv_lhu(rd, off, rs), ctx);
+		break;
+	case BPF_W:
+		emit(sign_ext ? rv_lw(rd, off, rs) : rv_lwu(rd, off, rs), ctx);
+		break;
+	case BPF_DW:
 		emit_ld(rd, off, rs, ctx);
-		return 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);
-	return ctx->ninsns - insns_start;
 }
 
 static void emit_stx_insn(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context *ctx)
@@ -577,6 +511,24 @@ static void emit_stx_insn(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context
 	}
 }
 
+static int emit_ldx(u8 rd, s16 off, u8 rs, u8 size, bool sign_ext,
+		    struct rv_jit_context *ctx)
+{
+	int insns_start;
+
+	if (is_12b_int(off)) {
+		insns_start = ctx->ninsns;
+		emit_ldx_insn(rd, off, rs, size, sign_ext, 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_ldx_insn(rd, 0, RV_REG_T1, size, sign_ext, ctx);
+	return ctx->ninsns - insns_start;
+}
+
 static int emit_st(u8 rd, s16 off, s32 imm, u8 size, struct rv_jit_context *ctx)
 {
 	int insns_start;
@@ -622,20 +574,7 @@ static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn,
 	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_ldx(rd, off, rs, BPF_SIZE(code), false, ctx);
 		emit_fence_r_rw(ctx);
 
 		/* If our next insn is a redundant zext, return 1 to tell
@@ -1859,20 +1798,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			rs = RV_REG_T2;
 		}
 
-		switch (BPF_SIZE(code)) {
-		case BPF_B:
-			insn_len = emit_load_8(sign_ext, rd, off, rs, ctx);
-			break;
-		case BPF_H:
-			insn_len = emit_load_16(sign_ext, rd, off, rs, ctx);
-			break;
-		case BPF_W:
-			insn_len = emit_load_32(sign_ext, rd, off, rs, ctx);
-			break;
-		case BPF_DW:
-			insn_len = emit_load_64(sign_ext, rd, off, rs, ctx);
-			break;
-		}
+		insn_len = emit_ldx(rd, off, rs, BPF_SIZE(code), sign_ext, ctx);
 
 		ret = add_exception_handler(insn, ctx, rd, insn_len);
 		if (ret)
@@ -1882,6 +1808,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			return 1;
 		break;
 	}
+
 	/* speculation barrier */
 	case BPF_ST | BPF_NOSPEC:
 		break;
-- 
2.34.1

[PATCH bpf-next 04/10] riscv: Separate toolchain support dependency from RISCV_ISA_ZACAS

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

RV64 bpf is going to support ZACAS instructions. Let's separate
toolchain support dependency from RISCV_ISA_ZACAS.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 arch/riscv/Kconfig               | 1 -
 arch/riscv/include/asm/cmpxchg.h | 6 ++++--
 arch/riscv/kernel/setup.c        | 1 +
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d71ea0f4466f..191b5d372fdf 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -717,7 +717,6 @@ config TOOLCHAIN_HAS_ZACAS
 
 config RISCV_ISA_ZACAS
 	bool "Zacas extension support for atomic CAS"
-	depends on TOOLCHAIN_HAS_ZACAS
 	depends on RISCV_ALTERNATIVE
 	default y
 	help
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 0b749e710216..4f4f389282b8 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -133,6 +133,7 @@
 ({										\
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&				\
 	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&				\
+	    IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZACAS) &&				\
 	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA) &&		\
 	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) {		\
 		r = o;								\
@@ -180,6 +181,7 @@
 		       r, p, co, o, n)					\
 ({									\
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&			\
+	    IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZACAS) &&			\
 	    riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) {	\
 		r = o;							\
 									\
@@ -315,7 +317,7 @@
 	arch_cmpxchg_release((ptr), (o), (n));				\
 })
 
-#if defined(CONFIG_64BIT) && defined(CONFIG_RISCV_ISA_ZACAS)
+#if defined(CONFIG_64BIT) && defined(CONFIG_RISCV_ISA_ZACAS) && defined(CONFIG_TOOLCHAIN_HAS_ZACAS)
 
 #define system_has_cmpxchg128()        riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)
 
@@ -351,7 +353,7 @@ union __u128_halves {
 #define arch_cmpxchg128_local(ptr, o, n)					\
 	__arch_cmpxchg128((ptr), (o), (n), "")
 
-#endif /* CONFIG_64BIT && CONFIG_RISCV_ISA_ZACAS */
+#endif /* CONFIG_64BIT && CONFIG_RISCV_ISA_ZACAS && CONFIG_TOOLCHAIN_HAS_ZACAS */
 
 #ifdef CONFIG_RISCV_ISA_ZAWRS
 /*
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 14888e5ea19a..348b924bbbca 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -288,6 +288,7 @@ static void __init riscv_spinlock_init(void)
 
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) &&
 	    IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) &&
+	    IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZACAS) &&
 	    riscv_isa_extension_available(NULL, ZABHA) &&
 	    riscv_isa_extension_available(NULL, ZACAS)) {
 		using_ext = "using Zabha";
-- 
2.34.1

[PATCH bpf-next 05/10] riscv, bpf: Add rv_ext_enabled macro for runtime detection extentsion

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

Add rv_ext_enabled macro to check whether the runtime detection
extension is enabled.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 arch/riscv/net/bpf_jit.h | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index e7b032dfd17f..0964df48c25e 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -13,21 +13,15 @@
 #include <linux/filter.h>
 #include <asm/cacheflush.h>
 
+/* verify runtime detection extension status */
+#define rv_ext_enabled(ext) \
+	(IS_ENABLED(CONFIG_RISCV_ISA_##ext) && riscv_has_extension_likely(RISCV_ISA_EXT_##ext))
+
 static inline bool rvc_enabled(void)
 {
 	return IS_ENABLED(CONFIG_RISCV_ISA_C);
 }
 
-static inline bool rvzba_enabled(void)
-{
-	return IS_ENABLED(CONFIG_RISCV_ISA_ZBA) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBA);
-}
-
-static inline bool rvzbb_enabled(void)
-{
-	return IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && riscv_has_extension_likely(RISCV_ISA_EXT_ZBB);
-}
-
 enum {
 	RV_REG_ZERO =	0,	/* The constant value 0 */
 	RV_REG_RA =	1,	/* Return address */
@@ -1123,7 +1117,7 @@ static inline void emit_sw(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx)
 
 static inline void emit_sh2add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
 {
-	if (rvzba_enabled()) {
+	if (rv_ext_enabled(ZBA)) {
 		emit(rvzba_sh2add(rd, rs1, rs2), ctx);
 		return;
 	}
@@ -1134,7 +1128,7 @@ static inline void emit_sh2add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx
 
 static inline void emit_sh3add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
 {
-	if (rvzba_enabled()) {
+	if (rv_ext_enabled(ZBA)) {
 		emit(rvzba_sh3add(rd, rs1, rs2), ctx);
 		return;
 	}
@@ -1184,7 +1178,7 @@ static inline void emit_subw(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx)
 
 static inline void emit_sextb(u8 rd, u8 rs, struct rv_jit_context *ctx)
 {
-	if (rvzbb_enabled()) {
+	if (rv_ext_enabled(ZBB)) {
 		emit(rvzbb_sextb(rd, rs), ctx);
 		return;
 	}
@@ -1195,7 +1189,7 @@ static inline void emit_sextb(u8 rd, u8 rs, struct rv_jit_context *ctx)
 
 static inline void emit_sexth(u8 rd, u8 rs, struct rv_jit_context *ctx)
 {
-	if (rvzbb_enabled()) {
+	if (rv_ext_enabled(ZBB)) {
 		emit(rvzbb_sexth(rd, rs), ctx);
 		return;
 	}
@@ -1211,7 +1205,7 @@ static inline void emit_sextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
 
 static inline void emit_zexth(u8 rd, u8 rs, struct rv_jit_context *ctx)
 {
-	if (rvzbb_enabled()) {
+	if (rv_ext_enabled(ZBB)) {
 		emit(rvzbb_zexth(rd, rs), ctx);
 		return;
 	}
@@ -1222,7 +1216,7 @@ static inline void emit_zexth(u8 rd, u8 rs, struct rv_jit_context *ctx)
 
 static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
 {
-	if (rvzba_enabled()) {
+	if (rv_ext_enabled(ZBA)) {
 		emit(rvzba_zextw(rd, rs), ctx);
 		return;
 	}
@@ -1233,7 +1227,7 @@ static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx)
 
 static inline void emit_bswap(u8 rd, s32 imm, struct rv_jit_context *ctx)
 {
-	if (rvzbb_enabled()) {
+	if (rv_ext_enabled(ZBB)) {
 		int bits = 64 - imm;
 
 		emit(rvzbb_rev8(rd, rd), ctx);
-- 
2.34.1

[PATCH bpf-next 06/10] riscv, bpf: Add Zacas instructions

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

Add Zacas instructions introduced by [0] to reduce code size and
improve performance of RV64 JIT.

Link: https://github.com/riscvarchive/riscv-zacas/releases/download/v1.0/riscv-zacas.pdf [0]
Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 arch/riscv/net/bpf_jit.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 0964df48c25e..2351fba5d3e7 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -751,6 +751,17 @@ static inline u16 rvc_swsp(u32 imm8, u8 rs2)
 	return rv_css_insn(0x6, imm, rs2, 0x2);
 }
 
+/* RVZACAS instructions. */
+static inline u32 rvzacas_amocas_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x5, aq, rl, rs2, rs1, 2, rd, 0x2f);
+}
+
+static inline u32 rvzacas_amocas_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl)
+{
+	return rv_amo_insn(0x5, aq, rl, rs2, rs1, 3, rd, 0x2f);
+}
+
 /* RVZBA instructions. */
 static inline u32 rvzba_sh2add(u8 rd, u8 rs1, u8 rs2)
 {
-- 
2.34.1

[PATCH bpf-next 07/10] riscv, bpf: Optimize cmpxchg insn with Zacas support

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

Optimize cmpxchg instruction with amocas.w and amocas.d
Zacas instructions.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 arch/riscv/net/bpf_jit.h        | 27 +++++++++++++++++++++++++++
 arch/riscv/net/bpf_jit_comp64.c | 18 ++----------------
 2 files changed, 29 insertions(+), 16 deletions(-)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 2351fba5d3e7..0790f40b7e9d 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -1294,6 +1294,33 @@ static inline void emit_bswap(u8 rd, s32 imm, struct rv_jit_context *ctx)
 	emit_mv(rd, RV_REG_T2, ctx);
 }
 
+static inline void emit_cmpxchg(u8 rd, u8 rs, u8 r0, bool is64, struct rv_jit_context *ctx)
+{
+	int jmp_offset;
+
+	if (rv_ext_enabled(ZACAS)) {
+		emit(is64 ? rvzacas_amocas_d(r0, rs, rd, 1, 1) :
+		     rvzacas_amocas_w(r0, rs, rd, 1, 1), ctx);
+		if (!is64)
+			emit_zextw(r0, r0, ctx);
+		return;
+	}
+
+	if (is64)
+		emit_mv(RV_REG_T2, r0, ctx);
+	else
+		emit_addiw(RV_REG_T2, r0, 0, ctx);
+	emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) :
+	     rv_lr_w(r0, 0, rd, 0, 0), ctx);
+	jmp_offset = ninsns_rvoff(8);
+	emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx);
+	emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 1) :
+	     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_fence_rw_rw(ctx);
+}
+
 #endif /* __riscv_xlen == 64 */
 
 void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog);
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index a6a9fd9193e5..8e813809d305 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -599,10 +599,9 @@ static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn,
 static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn,
 			   struct rv_jit_context *ctx)
 {
-	u8 r0, code = insn->code;
+	u8 code = insn->code;
 	s16 off = insn->off;
 	s32 imm = insn->imm;
-	int jmp_offset;
 	bool is64;
 
 	if (BPF_SIZE(code) != BPF_W && BPF_SIZE(code) != BPF_DW) {
@@ -673,20 +672,7 @@ static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn,
 		break;
 	/* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */
 	case BPF_CMPXCHG:
-		r0 = bpf_to_rv_reg(BPF_REG_0, ctx);
-		if (is64)
-			emit_mv(RV_REG_T2, r0, ctx);
-		else
-			emit_addiw(RV_REG_T2, r0, 0, ctx);
-		emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) :
-		     rv_lr_w(r0, 0, rd, 0, 0), ctx);
-		jmp_offset = ninsns_rvoff(8);
-		emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx);
-		emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 1) :
-		     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_fence_rw_rw(ctx);
+		emit_cmpxchg(rd, rs, regmap[BPF_REG_0], is64, ctx);
 		break;
 	default:
 		pr_err_once("bpf-jit: invalid atomic RMW opcode %02x\n", imm);
-- 
2.34.1

[PATCH bpf-next 08/10] riscv, bpf: Add ex_insn_off and ex_jmp_off for exception table handling

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

Add ex_insn_off and ex_jmp_off fields to struct rv_jit_context so that
add_exception_handler() does not need to be immediately followed by the
instruction to add the exception table. ex_insn_off indicates the offset
of the instruction to add the exception table, and ex_jmp_off indicates
the offset to jump over the faulting instruction. This is to prepare for
adding the exception table to atomic instructions later, because some
atomic instructions need to perform zext or other operations.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 arch/riscv/net/bpf_jit.h        |  2 +
 arch/riscv/net/bpf_jit_comp64.c | 84 +++++++++++++++------------------
 2 files changed, 39 insertions(+), 47 deletions(-)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 0790f40b7e9d..be2915444ce5 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -78,6 +78,8 @@ struct rv_jit_context {
 	int epilogue_offset;
 	int *offset;		/* BPF to RV */
 	int nexentries;
+	int ex_insn_off;
+	int ex_jmp_off;
 	unsigned long flags;
 	int stack_size;
 	u64 arena_vm_start;
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 8e813809d305..56b592af53a6 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -511,57 +511,54 @@ static void emit_stx_insn(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context
 	}
 }
 
-static int emit_ldx(u8 rd, s16 off, u8 rs, u8 size, bool sign_ext,
+static void emit_ldx(u8 rd, s16 off, u8 rs, u8 size, bool sign_ext,
 		    struct rv_jit_context *ctx)
 {
-	int insns_start;
-
 	if (is_12b_int(off)) {
-		insns_start = ctx->ninsns;
+		ctx->ex_insn_off = ctx->ninsns;
 		emit_ldx_insn(rd, off, rs, size, sign_ext, ctx);
-		return ctx->ninsns - insns_start;
+		ctx->ex_jmp_off = ctx->ninsns;
+		return;
 	}
 
 	emit_imm(RV_REG_T1, off, ctx);
 	emit_add(RV_REG_T1, RV_REG_T1, rs, ctx);
-	insns_start = ctx->ninsns;
+	ctx->ex_insn_off = ctx->ninsns;
 	emit_ldx_insn(rd, 0, RV_REG_T1, size, sign_ext, ctx);
-	return ctx->ninsns - insns_start;
+	ctx->ex_jmp_off = ctx->ninsns;
 }
 
-static int emit_st(u8 rd, s16 off, s32 imm, u8 size, struct rv_jit_context *ctx)
+static void emit_st(u8 rd, s16 off, s32 imm, u8 size, struct rv_jit_context *ctx)
 {
-	int insns_start;
-
 	emit_imm(RV_REG_T1, imm, ctx);
 	if (is_12b_int(off)) {
-		insns_start = ctx->ninsns;
+		ctx->ex_insn_off = ctx->ninsns;
 		emit_stx_insn(rd, off, RV_REG_T1, size, ctx);
-		return ctx->ninsns - insns_start;
+		ctx->ex_jmp_off = ctx->ninsns;
+		return;
 	}
 
 	emit_imm(RV_REG_T2, off, ctx);
 	emit_add(RV_REG_T2, RV_REG_T2, rd, ctx);
-	insns_start = ctx->ninsns;
+	ctx->ex_insn_off = ctx->ninsns;
 	emit_stx_insn(RV_REG_T2, 0, RV_REG_T1, size, ctx);
-	return ctx->ninsns - insns_start;
+	ctx->ex_jmp_off = ctx->ninsns;
 }
 
-static int emit_stx(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context *ctx)
+static void emit_stx(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context *ctx)
 {
-	int insns_start;
-
 	if (is_12b_int(off)) {
-		insns_start = ctx->ninsns;
+		ctx->ex_insn_off = ctx->ninsns;
 		emit_stx_insn(rd, off, rs, size, ctx);
-		return ctx->ninsns - insns_start;
+		ctx->ex_jmp_off = ctx->ninsns;
+		return;
 	}
 
 	emit_imm(RV_REG_T1, off, ctx);
 	emit_add(RV_REG_T1, RV_REG_T1, rd, ctx);
-	insns_start = ctx->ninsns;
+	ctx->ex_insn_off = ctx->ninsns;
 	emit_stx_insn(RV_REG_T1, 0, rs, size, ctx);
-	return ctx->ninsns - insns_start;
+	ctx->ex_jmp_off = ctx->ninsns;
 }
 
 static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn,
@@ -700,9 +697,8 @@ bool ex_handler_bpf(const struct exception_table_entry *ex,
 }
 
 /* For accesses to BTF pointers, add an entry to the exception table */
-static int add_exception_handler(const struct bpf_insn *insn,
-				 struct rv_jit_context *ctx,
-				 int dst_reg, int insn_len)
+static int add_exception_handler(const struct bpf_insn *insn, int dst_reg,
+				 struct rv_jit_context *ctx)
 {
 	struct exception_table_entry *ex;
 	unsigned long pc;
@@ -710,21 +706,22 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	off_t fixup_offset;
 
 	if (!ctx->insns || !ctx->ro_insns || !ctx->prog->aux->extable ||
-	    (BPF_MODE(insn->code) != BPF_PROBE_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX &&
-	     BPF_MODE(insn->code) != BPF_PROBE_MEM32))
+	    ctx->ex_insn_off <= 0 || ctx->ex_jmp_off <= 0)
 		return 0;
 
-	if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries))
-		return -EINVAL;
+	if (BPF_MODE(insn->code) != BPF_PROBE_MEM &&
+	    BPF_MODE(insn->code) != BPF_PROBE_MEMSX &&
+	    BPF_MODE(insn->code) != BPF_PROBE_MEM32)
+		return 0;
 
-	if (WARN_ON_ONCE(insn_len > ctx->ninsns))
+	if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries))
 		return -EINVAL;
 
-	if (WARN_ON_ONCE(!rvc_enabled() && insn_len == 1))
+	if (WARN_ON_ONCE(ctx->ex_insn_off > ctx->ninsns || ctx->ex_jmp_off > ctx->ninsns))
 		return -EINVAL;
 
 	ex = &ctx->prog->aux->extable[ctx->nexentries];
-	pc = (unsigned long)&ctx->ro_insns[ctx->ninsns - insn_len];
+	pc = (unsigned long)&ctx->ro_insns[ctx->ex_insn_off];
 
 	/*
 	 * This is the relative offset of the instruction that may fault from
@@ -748,7 +745,7 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	 * that may fault. The execution will jump to this after handling the
 	 * fault.
 	 */
-	fixup_offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16));
+	fixup_offset = (long)&ex->fixup - (long)&ctx->ro_insns[ctx->ex_jmp_off];
 	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, fixup_offset))
 		return -ERANGE;
 
@@ -765,6 +762,8 @@ static int add_exception_handler(const struct bpf_insn *insn,
 		FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
 	ex->type = EX_TYPE_BPF;
 
+	ctx->ex_insn_off = 0;
+	ctx->ex_jmp_off = 0;
 	ctx->nexentries++;
 	return 0;
 }
@@ -1774,7 +1773,6 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW:
 	{
 		bool sign_ext;
-		int insn_len;
 
 		sign_ext = BPF_MODE(insn->code) == BPF_MEMSX ||
 			   BPF_MODE(insn->code) == BPF_PROBE_MEMSX;
@@ -1784,9 +1782,9 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			rs = RV_REG_T2;
 		}
 
-		insn_len = emit_ldx(rd, off, rs, BPF_SIZE(code), sign_ext, ctx);
+		emit_ldx(rd, off, rs, BPF_SIZE(code), sign_ext, ctx);
 
-		ret = add_exception_handler(insn, ctx, rd, insn_len);
+		ret = add_exception_handler(insn, rd, ctx);
 		if (ret)
 			return ret;
 
@@ -1809,21 +1807,17 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ST | BPF_PROBE_MEM32 | BPF_H:
 	case BPF_ST | BPF_PROBE_MEM32 | BPF_W:
 	case BPF_ST | BPF_PROBE_MEM32 | BPF_DW:
-	{
-		int insn_len;
-
 		if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
 			emit_add(RV_REG_T3, rd, RV_REG_ARENA, ctx);
 			rd = RV_REG_T3;
 		}
 
-		insn_len = emit_st(rd, off, imm, BPF_SIZE(code), ctx);
+		emit_st(rd, off, imm, BPF_SIZE(code), ctx);
 
-		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER, insn_len);
+		ret = add_exception_handler(insn, REG_DONT_CLEAR_MARKER, ctx);
 		if (ret)
 			return ret;
 		break;
-	}
 
 	/* STX: *(size *)(dst + off) = src */
 	case BPF_STX | BPF_MEM | BPF_B:
@@ -1835,21 +1829,17 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_STX | BPF_PROBE_MEM32 | BPF_H:
 	case BPF_STX | BPF_PROBE_MEM32 | BPF_W:
 	case BPF_STX | BPF_PROBE_MEM32 | BPF_DW:
-	{
-		int insn_len;
-
 		if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
 			emit_add(RV_REG_T2, rd, RV_REG_ARENA, ctx);
 			rd = RV_REG_T2;
 		}
 
-		insn_len = emit_stx(rd, off, rs, BPF_SIZE(code), ctx);
+		emit_stx(rd, off, rs, BPF_SIZE(code), ctx);
 
-		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER, insn_len);
+		ret = add_exception_handler(insn, REG_DONT_CLEAR_MARKER, ctx);
 		if (ret)
 			return ret;
 		break;
-	}
 
 	case BPF_STX | BPF_ATOMIC | BPF_B:
 	case BPF_STX | BPF_ATOMIC | BPF_H:
-- 
2.34.1

[PATCH bpf-next 09/10] riscv, bpf: Add support arena atomics for RV64

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

Add arena atomics support for RMW atomics and load-acquire and
store-release instructions. Non-Zacas cmpxchg is implemented via loop,
which is not currently supported because it requires more complex
extable and loop logic.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 arch/riscv/net/bpf_jit.h        |  2 ++
 arch/riscv/net/bpf_jit_comp64.c | 60 +++++++++++++++++++++++++++++++--
 2 files changed, 59 insertions(+), 3 deletions(-)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index be2915444ce5..632ced07bca4 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -1301,8 +1301,10 @@ static inline void emit_cmpxchg(u8 rd, u8 rs, u8 r0, bool is64, struct rv_jit_co
 	int jmp_offset;
 
 	if (rv_ext_enabled(ZACAS)) {
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rvzacas_amocas_d(r0, rs, rd, 1, 1) :
 		     rvzacas_amocas_w(r0, rs, rd, 1, 1), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		if (!is64)
 			emit_zextw(r0, r0, ctx);
 		return;
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 56b592af53a6..549c3063c7f1 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -571,6 +571,11 @@ static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn,
 	switch (imm) {
 	/* dst_reg = load_acquire(src_reg + off16) */
 	case BPF_LOAD_ACQ:
+		if (BPF_MODE(code) == BPF_PROBE_ATOMIC) {
+			emit_add(RV_REG_T2, rs, RV_REG_ARENA, ctx);
+			rs = RV_REG_T2;
+		}
+
 		emit_ldx(rd, off, rs, BPF_SIZE(code), false, ctx);
 		emit_fence_r_rw(ctx);
 
@@ -582,6 +587,11 @@ static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn,
 		break;
 	/* store_release(dst_reg + off16, src_reg) */
 	case BPF_STORE_REL:
+		if (BPF_MODE(code) == BPF_PROBE_ATOMIC) {
+			emit_add(RV_REG_T2, rd, RV_REG_ARENA, ctx);
+			rd = RV_REG_T2;
+		}
+
 		emit_fence_rw_w(ctx);
 		emit_stx(rd, off, rs, BPF_SIZE(code), ctx);
 		break;
@@ -599,13 +609,12 @@ static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn,
 	u8 code = insn->code;
 	s16 off = insn->off;
 	s32 imm = insn->imm;
-	bool is64;
+	bool is64 = BPF_SIZE(code) == BPF_DW;
 
 	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)) {
@@ -617,53 +626,76 @@ static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn,
 		rd = RV_REG_T1;
 	}
 
+	if (BPF_MODE(code) == BPF_PROBE_ATOMIC) {
+		emit_add(RV_REG_T1, rd, RV_REG_ARENA, ctx);
+		rd = RV_REG_T1;
+	}
+
 	switch (imm) {
 	/* lock *(u32/u64 *)(dst_reg + off16) <op>= src_reg */
 	case BPF_ADD:
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rv_amoadd_d(RV_REG_ZERO, rs, rd, 0, 0) :
 		     rv_amoadd_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		break;
 	case BPF_AND:
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rv_amoand_d(RV_REG_ZERO, rs, rd, 0, 0) :
 		     rv_amoand_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		break;
 	case BPF_OR:
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rv_amoor_d(RV_REG_ZERO, rs, rd, 0, 0) :
 		     rv_amoor_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		break;
 	case BPF_XOR:
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rv_amoxor_d(RV_REG_ZERO, rs, rd, 0, 0) :
 		     rv_amoxor_w(RV_REG_ZERO, rs, rd, 0, 0), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		break;
 	/* src_reg = atomic_fetch_<op>(dst_reg + off16, src_reg) */
 	case BPF_ADD | BPF_FETCH:
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rv_amoadd_d(rs, rs, rd, 1, 1) :
 		     rv_amoadd_w(rs, rs, rd, 1, 1), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
 	case BPF_AND | BPF_FETCH:
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rv_amoand_d(rs, rs, rd, 1, 1) :
 		     rv_amoand_w(rs, rs, rd, 1, 1), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
 	case BPF_OR | BPF_FETCH:
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rv_amoor_d(rs, rs, rd, 1, 1) :
 		     rv_amoor_w(rs, rs, rd, 1, 1), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
 	case BPF_XOR | BPF_FETCH:
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rv_amoxor_d(rs, rs, rd, 1, 1) :
 		     rv_amoxor_w(rs, rs, rd, 1, 1), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
 	/* src_reg = atomic_xchg(dst_reg + off16, src_reg); */
 	case BPF_XCHG:
+		ctx->ex_insn_off = ctx->ninsns;
 		emit(is64 ? rv_amoswap_d(rs, rs, rd, 1, 1) :
 		     rv_amoswap_w(rs, rs, rd, 1, 1), ctx);
+		ctx->ex_jmp_off = ctx->ninsns;
 		if (!is64)
 			emit_zextw(rs, rs, ctx);
 		break;
@@ -711,7 +743,8 @@ static int add_exception_handler(const struct bpf_insn *insn, int dst_reg,
 
 	if (BPF_MODE(insn->code) != BPF_PROBE_MEM &&
 	    BPF_MODE(insn->code) != BPF_PROBE_MEMSX &&
-	    BPF_MODE(insn->code) != BPF_PROBE_MEM32)
+	    BPF_MODE(insn->code) != BPF_PROBE_MEM32 &&
+	    BPF_MODE(insn->code) != BPF_PROBE_ATOMIC)
 		return 0;
 
 	if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries))
@@ -1841,14 +1874,21 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			return ret;
 		break;
 
+	/* Atomics */
 	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:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_B:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_H:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_W:
+	case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW:
 		if (bpf_atomic_is_load_store(insn))
 			ret = emit_atomic_ld_st(rd, rs, insn, ctx);
 		else
 			ret = emit_atomic_rmw(rd, rs, insn, ctx);
+
+		ret = ret ?: add_exception_handler(insn, REG_DONT_CLEAR_MARKER, ctx);
 		if (ret)
 			return ret;
 		break;
@@ -1979,6 +2019,20 @@ bool bpf_jit_supports_arena(void)
 	return true;
 }
 
+bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
+{
+	if (in_arena) {
+		switch (insn->code) {
+		case BPF_STX | BPF_ATOMIC | BPF_W:
+		case BPF_STX | BPF_ATOMIC | BPF_DW:
+			if (insn->imm == BPF_CMPXCHG)
+				return rv_ext_enabled(ZACAS);
+		}
+	}
+
+	return true;
+}
+
 bool bpf_jit_supports_percpu_insn(void)
 {
 	return true;
-- 
2.34.1

[PATCH bpf-next 10/10] selftests/bpf: Enable arena atomics tests for RV64

[Pu Lehui]

From: Pu Lehui <pulehui@huawei.com>

Enable arena atomics tests for RV64.

Signed-off-by: Pu Lehui <pulehui@huawei.com>
---
 tools/testing/selftests/bpf/progs/arena_atomics.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/arena_atomics.c b/tools/testing/selftests/bpf/progs/arena_atomics.c
index a52feff98112..d1841aac94a2 100644
--- a/tools/testing/selftests/bpf/progs/arena_atomics.c
+++ b/tools/testing/selftests/bpf/progs/arena_atomics.c
@@ -28,7 +28,8 @@ bool skip_all_tests = true;
 
 #if defined(ENABLE_ATOMICS_TESTS) &&		  \
 	defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
-	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	 (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
 bool skip_lacq_srel_tests __attribute((__section__(".data"))) = false;
 #else
 bool skip_lacq_srel_tests = true;
@@ -314,7 +315,8 @@ int load_acquire(const void *ctx)
 {
 #if defined(ENABLE_ATOMICS_TESTS) &&		  \
 	defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
-	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	 (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
 
 #define LOAD_ACQUIRE_ARENA(SIZEOP, SIZE, SRC, DST)	\
 	{ asm volatile (				\
@@ -365,7 +367,8 @@ int store_release(const void *ctx)
 {
 #if defined(ENABLE_ATOMICS_TESTS) &&		  \
 	defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
-	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86))
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	 (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
 
 #define STORE_RELEASE_ARENA(SIZEOP, DST, VAL)	\
 	{ asm volatile (			\
-- 
2.34.1

Re: [PATCH bpf-next 00/10] Add support arena atomics for RV64

[Björn Töpel]

Lehui!

On Sat, 19 Jul 2025 at 11:14, Pu Lehui <pulehui@huaweicloud.com> wrote:
>
> From: Pu Lehui <pulehui@huawei.com>
>
> patch 1-3 refactor redundant load and store operations.
> patch 4-7 add Zacas instructions for cmpxchg.
> patch 8 optimizes exception table handling.
> patch 9-10 add support arena atomics for RV64.
>
> Tests `test_progs -t atomic,arena` have passed as shown bellow,
> as well as `test_verifier` and `test_bpf.ko` have passed.

Awesome, thank you for working on this!

I'm on vacation until 4th Aug, but I'll try to do a review before that
-- but expect some slowness!


Thanks,
Björn

Re: [PATCH bpf-next 01/10] riscv, bpf: Extract emit_stx() helper

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> There's a lot of redundant code related to store from register
> operations, let's extract emit_stx() to make code more compact.
>
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 02/10] riscv, bpf: Extract emit_st() helper

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> There's a lot of redundant code related to store from immediate
> operations, let's extract emit_st() to make code more compact.
>
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 03/10] riscv, bpf: Extract emit_ldx() helper

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> There's a lot of redundant code related to load into register
> operations, let's extract emit_ldx() to make code more compact.
>
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 04/10] riscv: Separate toolchain support dependency from RISCV_ISA_ZACAS

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> RV64 bpf is going to support ZACAS instructions. Let's separate
> toolchain support dependency from RISCV_ISA_ZACAS.
>
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 05/10] riscv, bpf: Add rv_ext_enabled macro for runtime detection extentsion

[Björn Töpel]

Nit: Subject: s/extentsion/extension/

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> Add rv_ext_enabled macro to check whether the runtime detection
> extension is enabled.
>
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 06/10] riscv, bpf: Add Zacas instructions

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> Add Zacas instructions introduced by [0] to reduce code size and
> improve performance of RV64 JIT.
>
> Link: https://github.com/riscvarchive/riscv-zacas/releases/download/v1.0/riscv-zacas.pdf [0]
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 10/10] selftests/bpf: Enable arena atomics tests for RV64

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> Enable arena atomics tests for RV64.
>
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 07/10] riscv, bpf: Optimize cmpxchg insn with Zacas support

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> Optimize cmpxchg instruction with amocas.w and amocas.d
> Zacas instructions.
>
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 08/10] riscv, bpf: Add ex_insn_off and ex_jmp_off for exception table handling

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> Add ex_insn_off and ex_jmp_off fields to struct rv_jit_context so that
> add_exception_handler() does not need to be immediately followed by the
> instruction to add the exception table. ex_insn_off indicates the offset
> of the instruction to add the exception table, and ex_jmp_off indicates
> the offset to jump over the faulting instruction. This is to prepare for
> adding the exception table to atomic instructions later, because some
> atomic instructions need to perform zext or other operations.
>
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

[...]

> @@ -748,7 +745,7 @@ static int add_exception_handler(const struct bpf_insn *insn,
>  	 * that may fault. The execution will jump to this after handling the
>  	 * fault.
>  	 */

Nit: After the upcoming change, the comment ^^^ is not entierly true.
Don't respin for this, but a follow up would be nice!

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 09/10] riscv, bpf: Add support arena atomics for RV64

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> Add arena atomics support for RMW atomics and load-acquire and
> store-release instructions. Non-Zacas cmpxchg is implemented via loop,
> which is not currently supported because it requires more complex
> extable and loop logic.
>
> Signed-off-by: Pu Lehui <pulehui@huawei.com>

Reviewed-by: Björn Töpel <bjorn@rivosinc.com>

Re: [PATCH bpf-next 00/10] Add support arena atomics for RV64

[Björn Töpel]

Pu Lehui <pulehui@huaweicloud.com> writes:

> From: Pu Lehui <pulehui@huawei.com>
>
> patch 1-3 refactor redundant load and store operations.
> patch 4-7 add Zacas instructions for cmpxchg.
> patch 8 optimizes exception table handling.
> patch 9-10 add support arena atomics for RV64.
>
> Tests `test_progs -t atomic,arena` have passed as shown bellow,
> as well as `test_verifier` and `test_bpf.ko` have passed.

[...]

> Pu Lehui (10):
>   riscv, bpf: Extract emit_stx() helper
>   riscv, bpf: Extract emit_st() helper
>   riscv, bpf: Extract emit_ldx() helper
>   riscv: Separate toolchain support dependency from RISCV_ISA_ZACAS
>   riscv, bpf: Add rv_ext_enabled macro for runtime detection extentsion
>   riscv, bpf: Add Zacas instructions
>   riscv, bpf: Optimize cmpxchg insn with Zacas support
>   riscv, bpf: Add ex_insn_off and ex_jmp_off for exception table
>     handling
>   riscv, bpf: Add support arena atomics for RV64
>   selftests/bpf: Enable arena atomics tests for RV64
>
>  arch/riscv/Kconfig                            |   1 -
>  arch/riscv/include/asm/cmpxchg.h              |   6 +-
>  arch/riscv/kernel/setup.c                     |   1 +
>  arch/riscv/net/bpf_jit.h                      |  70 ++-
>  arch/riscv/net/bpf_jit_comp64.c               | 516 +++++-------------
>  .../selftests/bpf/progs/arena_atomics.c       |   9 +-
>  6 files changed, 214 insertions(+), 389 deletions(-)

What a nice series! The best kind of changeset -- new feature, less
code! Thank you, Lehui! Again, apologies for the horrible SLA. The
weather in Sweden was simply Too Good this summer!

Tested-by: Björn Töpel <bjorn@rivosinc.com> # QEMU only
Acked-by: Björn Töpel <bjorn@kernel.org>

Re: [PATCH bpf-next 00/10] Add support arena atomics for RV64

[Pu Lehui]

On 2025/8/5 14:38, Björn Töpel wrote:
> Pu Lehui <pulehui@huaweicloud.com> writes:
> 
>> From: Pu Lehui <pulehui@huawei.com>
>>
>> patch 1-3 refactor redundant load and store operations.
>> patch 4-7 add Zacas instructions for cmpxchg.
>> patch 8 optimizes exception table handling.
>> patch 9-10 add support arena atomics for RV64.
>>
>> Tests `test_progs -t atomic,arena` have passed as shown bellow,
>> as well as `test_verifier` and `test_bpf.ko` have passed.
> 
> [...]
> 
>> Pu Lehui (10):
>>    riscv, bpf: Extract emit_stx() helper
>>    riscv, bpf: Extract emit_st() helper
>>    riscv, bpf: Extract emit_ldx() helper
>>    riscv: Separate toolchain support dependency from RISCV_ISA_ZACAS
>>    riscv, bpf: Add rv_ext_enabled macro for runtime detection extentsion
>>    riscv, bpf: Add Zacas instructions
>>    riscv, bpf: Optimize cmpxchg insn with Zacas support
>>    riscv, bpf: Add ex_insn_off and ex_jmp_off for exception table
>>      handling
>>    riscv, bpf: Add support arena atomics for RV64
>>    selftests/bpf: Enable arena atomics tests for RV64
>>
>>   arch/riscv/Kconfig                            |   1 -
>>   arch/riscv/include/asm/cmpxchg.h              |   6 +-
>>   arch/riscv/kernel/setup.c                     |   1 +
>>   arch/riscv/net/bpf_jit.h                      |  70 ++-
>>   arch/riscv/net/bpf_jit_comp64.c               | 516 +++++-------------
>>   .../selftests/bpf/progs/arena_atomics.c       |   9 +-
>>   6 files changed, 214 insertions(+), 389 deletions(-)
> 
> What a nice series! The best kind of changeset -- new feature, less
> code! Thank you, Lehui! Again, apologies for the horrible SLA. The
> weather in Sweden was simply Too Good this summer!

Sounds like a great vacation!

> 
> Tested-by: Björn Töpel <bjorn@rivosinc.com> # QEMU only
> Acked-by: Björn Töpel <bjorn@kernel.org>

Re: [PATCH bpf-next 00/10] Add support arena atomics for RV64

[patchwork-bot+netdevbpf]

Hello:

This series was applied to bpf/bpf-next.git (master)
by Daniel Borkmann <daniel@iogearbox.net>:

On Sat, 19 Jul 2025 09:17:20 +0000 you wrote:
> From: Pu Lehui <pulehui@huawei.com>
> 
> patch 1-3 refactor redundant load and store operations.
> patch 4-7 add Zacas instructions for cmpxchg.
> patch 8 optimizes exception table handling.
> patch 9-10 add support arena atomics for RV64.
> 
> [...]

Here is the summary with links:
  - [bpf-next,01/10] riscv, bpf: Extract emit_stx() helper
    https://git.kernel.org/bpf/bpf-next/c/02fc01adec1c
  - [bpf-next,02/10] riscv, bpf: Extract emit_st() helper
    https://git.kernel.org/bpf/bpf-next/c/d92c11a6b55b
  - [bpf-next,03/10] riscv, bpf: Extract emit_ldx() helper
    https://git.kernel.org/bpf/bpf-next/c/01422a4f2c78
  - [bpf-next,04/10] riscv: Separate toolchain support dependency from RISCV_ISA_ZACAS
    https://git.kernel.org/bpf/bpf-next/c/ec74ae56626b
  - [bpf-next,05/10] riscv, bpf: Add rv_ext_enabled macro for runtime detection extentsion
    https://git.kernel.org/bpf/bpf-next/c/5090b339eeb3
  - [bpf-next,06/10] riscv, bpf: Add Zacas instructions
    https://git.kernel.org/bpf/bpf-next/c/de39d2c4cdb6
  - [bpf-next,07/10] riscv, bpf: Optimize cmpxchg insn with Zacas support
    https://git.kernel.org/bpf/bpf-next/c/1c0196b878a6
  - [bpf-next,08/10] riscv, bpf: Add ex_insn_off and ex_jmp_off for exception table handling
    https://git.kernel.org/bpf/bpf-next/c/b18f4aae6a5d
  - [bpf-next,09/10] riscv, bpf: Add support arena atomics for RV64
    https://git.kernel.org/bpf/bpf-next/c/fb7cefabae81
  - [bpf-next,10/10] selftests/bpf: Enable arena atomics tests for RV64
    https://git.kernel.org/bpf/bpf-next/c/dc0fe956144d

You are awesome, thank you!
-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html

Re: [PATCH bpf-next 00/10] Add support arena atomics for RV64

[Daniel Borkmann]

On 8/5/25 8:52 AM, Pu Lehui wrote:
> On 2025/8/5 14:38, Björn Töpel wrote:
>> Pu Lehui <pulehui@huaweicloud.com> writes:
>>
>>> From: Pu Lehui <pulehui@huawei.com>
>>>
>>> patch 1-3 refactor redundant load and store operations.
>>> patch 4-7 add Zacas instructions for cmpxchg.
>>> patch 8 optimizes exception table handling.
>>> patch 9-10 add support arena atomics for RV64.
>>>
>>> Tests `test_progs -t atomic,arena` have passed as shown bellow,
>>> as well as `test_verifier` and `test_bpf.ko` have passed.
>>
>> [...]
>>
>>> Pu Lehui (10):
>>>    riscv, bpf: Extract emit_stx() helper
>>>    riscv, bpf: Extract emit_st() helper
>>>    riscv, bpf: Extract emit_ldx() helper
>>>    riscv: Separate toolchain support dependency from RISCV_ISA_ZACAS
>>>    riscv, bpf: Add rv_ext_enabled macro for runtime detection extentsion
>>>    riscv, bpf: Add Zacas instructions
>>>    riscv, bpf: Optimize cmpxchg insn with Zacas support
>>>    riscv, bpf: Add ex_insn_off and ex_jmp_off for exception table
>>>      handling
>>>    riscv, bpf: Add support arena atomics for RV64
>>>    selftests/bpf: Enable arena atomics tests for RV64
>>>
>>>   arch/riscv/Kconfig                            |   1 -
>>>   arch/riscv/include/asm/cmpxchg.h              |   6 +-
>>>   arch/riscv/kernel/setup.c                     |   1 +
>>>   arch/riscv/net/bpf_jit.h                      |  70 ++-
>>>   arch/riscv/net/bpf_jit_comp64.c               | 516 +++++-------------
>>>   .../selftests/bpf/progs/arena_atomics.c       |   9 +-
>>>   6 files changed, 214 insertions(+), 389 deletions(-)
>>
>> What a nice series! The best kind of changeset -- new feature, less
>> code! Thank you, Lehui! Again, apologies for the horrible SLA. The
>> weather in Sweden was simply Too Good this summer!
> 
> Sounds like a great vacation!

Thanks for working on this! I just took this into bpf-next, please also
make sure to address the small follow-up request from Bjorn.

>> Tested-by: Björn Töpel <bjorn@rivosinc.com> # QEMU only
>> Acked-by: Björn Töpel <bjorn@kernel.org>

Thanks,
Daniel

Re: [PATCH bpf-next 00/10] Add support arena atomics for RV64

[Pu Lehui]

On 2025/8/15 16:55, Daniel Borkmann wrote:
> On 8/5/25 8:52 AM, Pu Lehui wrote:
>> On 2025/8/5 14:38, Björn Töpel wrote:
>>> Pu Lehui <pulehui@huaweicloud.com> writes:
>>>
>>>> From: Pu Lehui <pulehui@huawei.com>
>>>>
>>>> patch 1-3 refactor redundant load and store operations.
>>>> patch 4-7 add Zacas instructions for cmpxchg.
>>>> patch 8 optimizes exception table handling.
>>>> patch 9-10 add support arena atomics for RV64.
>>>>
>>>> Tests `test_progs -t atomic,arena` have passed as shown bellow,
>>>> as well as `test_verifier` and `test_bpf.ko` have passed.
>>>
>>> [...]
>>>
>>>> Pu Lehui (10):
>>>>    riscv, bpf: Extract emit_stx() helper
>>>>    riscv, bpf: Extract emit_st() helper
>>>>    riscv, bpf: Extract emit_ldx() helper
>>>>    riscv: Separate toolchain support dependency from RISCV_ISA_ZACAS
>>>>    riscv, bpf: Add rv_ext_enabled macro for runtime detection 
>>>> extentsion
>>>>    riscv, bpf: Add Zacas instructions
>>>>    riscv, bpf: Optimize cmpxchg insn with Zacas support
>>>>    riscv, bpf: Add ex_insn_off and ex_jmp_off for exception table
>>>>      handling
>>>>    riscv, bpf: Add support arena atomics for RV64
>>>>    selftests/bpf: Enable arena atomics tests for RV64
>>>>
>>>>   arch/riscv/Kconfig                            |   1 -
>>>>   arch/riscv/include/asm/cmpxchg.h              |   6 +-
>>>>   arch/riscv/kernel/setup.c                     |   1 +
>>>>   arch/riscv/net/bpf_jit.h                      |  70 ++-
>>>>   arch/riscv/net/bpf_jit_comp64.c               | 516 
>>>> +++++-------------
>>>>   .../selftests/bpf/progs/arena_atomics.c       |   9 +-
>>>>   6 files changed, 214 insertions(+), 389 deletions(-)
>>>
>>> What a nice series! The best kind of changeset -- new feature, less
>>> code! Thank you, Lehui! Again, apologies for the horrible SLA. The
>>> weather in Sweden was simply Too Good this summer!
>>
>> Sounds like a great vacation!
> 
> Thanks for working on this! I just took this into bpf-next, please also
> make sure to address the small follow-up request from Bjorn.

Hi Daniel,

Already explained and aligned with Bjorn, no further processing is 
required. Thanks.

> 
>>> Tested-by: Björn Töpel <bjorn@rivosinc.com> # QEMU only
>>> Acked-by: Björn Töpel <bjorn@kernel.org>
> 
> Thanks,
> Daniel