[PATCH bpf-next v4 0/2] bpf,riscv: Add support for BPF Arena

[PATCH bpf-next v4 0/2] bpf,riscv: Add support for BPF Arena

[Puranjay Mohan]

Changes in V4:
V3: https://lore.kernel.org/all/20240326224943.86912-1-puranjay12@gmail.com/
- Fix some style issues.
- Add Tested-by: and Reviewed-by: tags by Pu Lehui and Björn

Changes in V3
V2: https://lore.kernel.org/bpf/20240325155434.65589-1-puranjay12@gmail.com/
- Use REG_DONT_CLEAR_MARKER in place of DONT_CLEAR as the name.
- Use RV_REG_ZERO for the above as it is guaranteed to be never used in as
  dst/src register in BPF LDX/STX/ST instructions.
- Use #define RV_REG_ARENA for RV_REG_S7

Changes in V2
V1: https://lore.kernel.org/bpf/20240323154652.54572-1-puranjay12@gmail.com/
- Used S7 in place of S11 for storing the kernel_vm_start
- Used 17 in place of 16 for DONT_CLEAR marker
- Remove an unused variable
- Removed some misleading information from the commit message.

This series adds the support for PROBE_MEM32 and bpf_addr_space_cast
instructions to the RISCV BPF JIT. These two instructions allow the
enablement of BPF Arena.

All arena related selftests are passing:

  root@rv-tester:~/bpf# uname -p
  riscv64
  root@rv-tester:~/bpf# ./test_progs -a "*arena*"
  #3/1     arena_htab/arena_htab_llvm:OK
  #3/2     arena_htab/arena_htab_asm:OK
  #3       arena_htab:OK
  #4/1     arena_list/arena_list_1:OK
  #4/2     arena_list/arena_list_1000:OK
  #4       arena_list:OK
  #434/1   verifier_arena/basic_alloc1:OK
  #434/2   verifier_arena/basic_alloc2:OK
  #434/3   verifier_arena/basic_alloc3:OK
  #434/4   verifier_arena/iter_maps1:OK
  #434/5   verifier_arena/iter_maps2:OK
  #434/6   verifier_arena/iter_maps3:OK
  #434     verifier_arena:OK
  Summary: 3/10 PASSED, 0 SKIPPED, 0 FAILED

Puranjay Mohan (2):
  bpf,riscv: Implement PROBE_MEM32 pseudo instructions
  bpf,riscv: Implement bpf_addr_space_cast instruction

 arch/riscv/net/bpf_jit.h        |   2 +
 arch/riscv/net/bpf_jit_comp64.c | 203 +++++++++++++++++++++++++++++++-
 arch/riscv/net/bpf_jit_core.c   |   2 +
 3 files changed, 205 insertions(+), 2 deletions(-)

-- 
2.40.1

[PATCH bpf-next v4 1/2] bpf,riscv: Implement PROBE_MEM32 pseudo instructions

[Puranjay Mohan]

Add support for [LDX | STX | ST], PROBE_MEM32, [B | H | W | DW]
instructions.  They are similar to PROBE_MEM instructions with the
following differences:
- PROBE_MEM32 supports store.
- PROBE_MEM32 relies on the verifier to clear upper 32-bit of the
  src/dst register
- PROBE_MEM32 adds 64-bit kern_vm_start address (which is stored in S7
  in the prologue). Due to bpf_arena constructions such S7 + reg +
  off16 access is guaranteed to be within arena virtual range, so no
  address check at run-time.
- S11 is a free callee-saved register, so it is used to store kern_vm_start
- PROBE_MEM32 allows STX and ST. If they fault the store is a nop. When
  LDX faults the destination register is zeroed.

To support these on riscv, we do tmp = S7 + src/dst reg and then use
tmp2 as the new src/dst register. This allows us to reuse most of the
code for normal [LDX | STX | ST].

Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
---
 arch/riscv/net/bpf_jit.h        |   1 +
 arch/riscv/net/bpf_jit_comp64.c | 189 +++++++++++++++++++++++++++++++-
 arch/riscv/net/bpf_jit_core.c   |   1 +
 3 files changed, 189 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index f4b6b3b9edda..8a47da08dd9c 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -81,6 +81,7 @@ struct rv_jit_context {
 	int nexentries;
 	unsigned long flags;
 	int stack_size;
+	u64 arena_vm_start;
 };
 
 /* Convert from ninsns to bytes. */
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 1adf2f39ce59..a4c8e1e6c1e2 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -18,6 +18,7 @@
 
 #define RV_REG_TCC RV_REG_A6
 #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */
+#define RV_REG_ARENA RV_REG_S7 /* For storing arena_vm_start */
 
 static const int regmap[] = {
 	[BPF_REG_0] =	RV_REG_A5,
@@ -255,6 +256,10 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
 		emit_ld(RV_REG_S6, store_offset, RV_REG_SP, ctx);
 		store_offset -= 8;
 	}
+	if (ctx->arena_vm_start) {
+		emit_ld(RV_REG_ARENA, store_offset, RV_REG_SP, ctx);
+		store_offset -= 8;
+	}
 
 	emit_addi(RV_REG_SP, RV_REG_SP, stack_adjust, ctx);
 	/* Set return value. */
@@ -548,6 +553,7 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
 
 #define BPF_FIXUP_OFFSET_MASK   GENMASK(26, 0)
 #define BPF_FIXUP_REG_MASK      GENMASK(31, 27)
+#define REG_DONT_CLEAR_MARKER	0	/* RV_REG_ZERO unused in pt_regmap */
 
 bool ex_handler_bpf(const struct exception_table_entry *ex,
 		    struct pt_regs *regs)
@@ -555,7 +561,8 @@ bool ex_handler_bpf(const struct exception_table_entry *ex,
 	off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
 	int regs_offset = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
 
-	*(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0;
+	if (regs_offset != REG_DONT_CLEAR_MARKER)
+		*(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0;
 	regs->epc = (unsigned long)&ex->fixup - offset;
 
 	return true;
@@ -572,7 +579,8 @@ 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_MEM && BPF_MODE(insn->code) != BPF_PROBE_MEMSX &&
+	     BPF_MODE(insn->code) != BPF_PROBE_MEM32))
 		return 0;
 
 	if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries))
@@ -1539,6 +1547,11 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
 	case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
 	case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
+	/* LDX | PROBE_MEM32: dst = *(unsigned size *)(src + RV_REG_ARENA + off) */
+	case BPF_LDX | BPF_PROBE_MEM32 | BPF_B:
+	case BPF_LDX | BPF_PROBE_MEM32 | BPF_H:
+	case BPF_LDX | BPF_PROBE_MEM32 | BPF_W:
+	case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW:
 	{
 		int insn_len, insns_start;
 		bool sign_ext;
@@ -1546,6 +1559,11 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		sign_ext = BPF_MODE(insn->code) == BPF_MEMSX ||
 			   BPF_MODE(insn->code) == BPF_PROBE_MEMSX;
 
+		if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) {
+			emit_add(RV_REG_T2, rs, RV_REG_ARENA, ctx);
+			rs = RV_REG_T2;
+		}
+
 		switch (BPF_SIZE(code)) {
 		case BPF_B:
 			if (is_12b_int(off)) {
@@ -1682,6 +1700,86 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_sd(RV_REG_T2, 0, RV_REG_T1, ctx);
 		break;
 
+	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;
+			}
+
+			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;
+		}
+
+		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER,
+					    insn_len);
+		if (ret)
+			return ret;
+
+		break;
+	}
+
 	/* STX: *(size *)(dst + off) = src */
 	case BPF_STX | BPF_MEM | BPF_B:
 		if (is_12b_int(off)) {
@@ -1728,6 +1826,84 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_atomic(rd, rs, off, imm,
 			    BPF_SIZE(code) == BPF_DW, ctx);
 		break;
+
+	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;
+			}
+
+			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;
+		}
+
+		ret = add_exception_handler(insn, ctx, REG_DONT_CLEAR_MARKER,
+					    insn_len);
+		if (ret)
+			return ret;
+
+		break;
+	}
+
 	default:
 		pr_err("bpf-jit: unknown opcode %02x\n", code);
 		return -EINVAL;
@@ -1759,6 +1935,8 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
 		stack_adjust += 8;
 	if (seen_reg(RV_REG_S6, ctx))
 		stack_adjust += 8;
+	if (ctx->arena_vm_start)
+		stack_adjust += 8;
 
 	stack_adjust = round_up(stack_adjust, 16);
 	stack_adjust += bpf_stack_adjust;
@@ -1810,6 +1988,10 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
 		emit_sd(RV_REG_SP, store_offset, RV_REG_S6, ctx);
 		store_offset -= 8;
 	}
+	if (ctx->arena_vm_start) {
+		emit_sd(RV_REG_SP, store_offset, RV_REG_ARENA, ctx);
+		store_offset -= 8;
+	}
 
 	emit_addi(RV_REG_FP, RV_REG_SP, stack_adjust, ctx);
 
@@ -1823,6 +2005,9 @@ void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog)
 		emit_mv(RV_REG_TCC_SAVED, RV_REG_TCC, ctx);
 
 	ctx->stack_size = stack_adjust;
+
+	if (ctx->arena_vm_start)
+		emit_imm(RV_REG_ARENA, ctx->arena_vm_start, ctx);
 }
 
 void bpf_jit_build_epilogue(struct rv_jit_context *ctx)
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index 6b3acac30c06..9ab739b9f9a2 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -80,6 +80,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		goto skip_init_ctx;
 	}
 
+	ctx->arena_vm_start = bpf_arena_get_kern_vm_start(prog->aux->arena);
 	ctx->prog = prog;
 	ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
 	if (!ctx->offset) {
-- 
2.40.1

[PATCH bpf-next v4 2/2] bpf,riscv: Implement bpf_addr_space_cast instruction

[Puranjay Mohan]

LLVM generates bpf_addr_space_cast instruction while translating
pointers between native (zero) address space and
__attribute__((address_space(N))). The addr_space=0 is reserved as
bpf_arena address space.

rY = addr_space_cast(rX, 0, 1) is processed by the verifier and
converted to normal 32-bit move: wX = wY

rY = addr_space_cast(rX, 1, 0) has to be converted by JIT.

Tested-by: Björn Töpel <bjorn@rivosinc.com>
Tested-by: Pu Lehui <pulehui@huawei.com>
Acked-by: Björn Töpel <bjorn@kernel.org>
Reviewed-by: Pu Lehui <pulehui@huawei.com>
Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
---
 arch/riscv/net/bpf_jit.h        |  1 +
 arch/riscv/net/bpf_jit_comp64.c | 14 ++++++++++++++
 arch/riscv/net/bpf_jit_core.c   |  1 +
 3 files changed, 16 insertions(+)

diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h
index 8a47da08dd9c..5fc374ed98ea 100644
--- a/arch/riscv/net/bpf_jit.h
+++ b/arch/riscv/net/bpf_jit.h
@@ -82,6 +82,7 @@ struct rv_jit_context {
 	unsigned long flags;
 	int stack_size;
 	u64 arena_vm_start;
+	u64 user_vm_start;
 };
 
 /* Convert from ninsns to bytes. */
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index a4c8e1e6c1e2..15e482f2c657 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1081,6 +1081,15 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
 	case BPF_ALU64 | BPF_MOV | BPF_X:
+		if (insn_is_cast_user(insn)) {
+			emit_mv(RV_REG_T1, rs, ctx);
+			emit_zextw(RV_REG_T1, RV_REG_T1, ctx);
+			emit_imm(rd, (ctx->user_vm_start >> 32) << 32, ctx);
+			emit(rv_beq(RV_REG_T1, RV_REG_ZERO, 4), ctx);
+			emit_or(RV_REG_T1, rd, RV_REG_T1, ctx);
+			emit_mv(rd, RV_REG_T1, ctx);
+			break;
+		}
 		if (imm == 1) {
 			/* Special mov32 for zext */
 			emit_zextw(rd, rd, ctx);
@@ -2024,3 +2033,8 @@ bool bpf_jit_supports_ptr_xchg(void)
 {
 	return true;
 }
+
+bool bpf_jit_supports_arena(void)
+{
+	return true;
+}
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index 9ab739b9f9a2..8a69d6d81e32 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -81,6 +81,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	}
 
 	ctx->arena_vm_start = bpf_arena_get_kern_vm_start(prog->aux->arena);
+	ctx->user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena);
 	ctx->prog = prog;
 	ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL);
 	if (!ctx->offset) {
-- 
2.40.1

Re: [PATCH bpf-next v4 0/2] bpf,riscv: Add support for BPF Arena

[patchwork-bot+netdevbpf]

Hello:

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

On Thu,  4 Apr 2024 11:42:01 +0000 you wrote:
> Changes in V4:
> V3: https://lore.kernel.org/all/20240326224943.86912-1-puranjay12@gmail.com/
> - Fix some style issues.
> - Add Tested-by: and Reviewed-by: tags by Pu Lehui and Björn
> 
> Changes in V3
> V2: https://lore.kernel.org/bpf/20240325155434.65589-1-puranjay12@gmail.com/
> - Use REG_DONT_CLEAR_MARKER in place of DONT_CLEAR as the name.
> - Use RV_REG_ZERO for the above as it is guaranteed to be never used in as
>   dst/src register in BPF LDX/STX/ST instructions.
> - Use #define RV_REG_ARENA for RV_REG_S7
> 
> [...]

Here is the summary with links:
  - [bpf-next,v4,1/2] bpf,riscv: Implement PROBE_MEM32 pseudo instructions
    https://git.kernel.org/bpf/bpf-next/c/633a6e01d1a2
  - [bpf-next,v4,2/2] bpf,riscv: Implement bpf_addr_space_cast instruction
    https://git.kernel.org/bpf/bpf-next/c/21ab0b6d0cfc

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