BPF Archive on lore.kernel.org
 help / color / Atom feed
From: Brendan Jackman <jackmanb@google.com>
To: bpf@vger.kernel.org
Cc: "Alexei Starovoitov" <ast@kernel.org>,
	"Daniel Borkmann" <daniel@iogearbox.net>,
	"Andrii Nakryiko" <andrii.nakryiko@gmail.com>,
	"KP Singh" <kpsingh@chromium.org>,
	"Florent Revest" <revest@chromium.org>,
	linux-kernel@vger.kernel.org,
	"Björn Töpel" <bjorn.topel@gmail.com>,
	"John Fastabend" <john.fastabend@gmail.com>,
	"Yonghong Song" <yhs@fb.com>,
	"Brendan Jackman" <jackmanb@google.com>
Subject: [PATCH bpf-next v7 07/11] bpf: Add instructions for atomic_[cmp]xchg
Date: Thu, 14 Jan 2021 18:17:47 +0000
Message-ID: <20210114181751.768687-8-jackmanb@google.com> (raw)
In-Reply-To: <20210114181751.768687-1-jackmanb@google.com>

This adds two atomic opcodes, both of which include the BPF_FETCH
flag. XCHG without the BPF_FETCH flag would naturally encode
atomic_set. This is not supported because it would be of limited
value to userspace (it doesn't imply any barriers). CMPXCHG without
BPF_FETCH woulud be an atomic compare-and-write. We don't have such
an operation in the kernel so it isn't provided to BPF either.

There are two significant design decisions made for the CMPXCHG
instruction:

 - To solve the issue that this operation fundamentally has 3
   operands, but we only have two register fields. Therefore the
   operand we compare against (the kernel's API calls it 'old') is
   hard-coded to be R0. x86 has similar design (and A64 doesn't
   have this problem).

   A potential alternative might be to encode the other operand's
   register number in the immediate field.

 - The kernel's atomic_cmpxchg returns the old value, while the C11
   userspace APIs return a boolean indicating the comparison
   result. Which should BPF do? A64 returns the old value. x86 returns
   the old value in the hard-coded register (and also sets a
   flag). That means return-old-value is easier to JIT, so that's
   what we use.

Signed-off-by: Brendan Jackman <jackmanb@google.com>
Acked-by: Yonghong Song <yhs@fb.com>
---
 arch/x86/net/bpf_jit_comp.c    |  8 ++++++++
 include/linux/filter.h         |  2 ++
 include/uapi/linux/bpf.h       |  4 +++-
 kernel/bpf/core.c              | 20 ++++++++++++++++++++
 kernel/bpf/disasm.c            | 15 +++++++++++++++
 kernel/bpf/verifier.c          | 19 +++++++++++++++++--
 tools/include/linux/filter.h   |  2 ++
 tools/include/uapi/linux/bpf.h |  4 +++-
 8 files changed, 70 insertions(+), 4 deletions(-)

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index eea7d8b0bb12..308241187582 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -815,6 +815,14 @@ static int emit_atomic(u8 **pprog, u8 atomic_op,
 		/* src_reg = atomic_fetch_add(dst_reg + off, src_reg); */
 		EMIT2(0x0F, 0xC1);
 		break;
+	case BPF_XCHG:
+		/* src_reg = atomic_xchg(dst_reg + off, src_reg); */
+		EMIT1(0x87);
+		break;
+	case BPF_CMPXCHG:
+		/* r0 = atomic_cmpxchg(dst_reg + off, r0, src_reg); */
+		EMIT2(0x0F, 0xB1);
+		break;
 	default:
 		pr_err("bpf_jit: unknown atomic opcode %02x\n", atomic_op);
 		return -EFAULT;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 23fca41b8540..d563820f197d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -265,6 +265,8 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
  *
  *   BPF_ADD                  *(uint *) (dst_reg + off16) += src_reg
  *   BPF_ADD | BPF_FETCH      src_reg = atomic_fetch_add(dst_reg + off16, src_reg);
+ *   BPF_XCHG                 src_reg = atomic_xchg(dst_reg + off16, src_reg)
+ *   BPF_CMPXCHG              r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg)
  */
 
 #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF)			\
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index ea262b009049..c001766adcbc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -45,7 +45,9 @@
 #define BPF_EXIT	0x90	/* function return */
 
 /* atomic op type fields (stored in immediate) */
-#define BPF_FETCH	0x01	/* fetch previous value into src reg */
+#define BPF_FETCH	0x01	/* not an opcode on its own, used to build others */
+#define BPF_XCHG	(0xe0 | BPF_FETCH)	/* atomic exchange */
+#define BPF_CMPXCHG	(0xf0 | BPF_FETCH)	/* atomic compare-and-write */
 
 /* Register numbers */
 enum {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 28d6000463e4..4df6daba43ef 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1630,6 +1630,16 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 				(u32) SRC,
 				(atomic_t *)(unsigned long) (DST + insn->off));
 			break;
+		case BPF_XCHG:
+			SRC = (u32) atomic_xchg(
+				(atomic_t *)(unsigned long) (DST + insn->off),
+				(u32) SRC);
+			break;
+		case BPF_CMPXCHG:
+			BPF_R0 = (u32) atomic_cmpxchg(
+				(atomic_t *)(unsigned long) (DST + insn->off),
+				(u32) BPF_R0, (u32) SRC);
+			break;
 		default:
 			goto default_label;
 		}
@@ -1647,6 +1657,16 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 				(u64) SRC,
 				(atomic64_t *)(unsigned long) (DST + insn->off));
 			break;
+		case BPF_XCHG:
+			SRC = (u64) atomic64_xchg(
+				(atomic64_t *)(unsigned long) (DST + insn->off),
+				(u64) SRC);
+			break;
+		case BPF_CMPXCHG:
+			BPF_R0 = (u64) atomic64_cmpxchg(
+				(atomic64_t *)(unsigned long) (DST + insn->off),
+				(u64) BPF_R0, (u64) SRC);
+			break;
 		default:
 			goto default_label;
 		}
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index d2e20f6d0516..ee8d1132767b 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -167,6 +167,21 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 				BPF_SIZE(insn->code) == BPF_DW ? "64" : "",
 				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
 				insn->dst_reg, insn->off, insn->src_reg);
+		} else if (BPF_MODE(insn->code) == BPF_ATOMIC &&
+			   insn->imm == BPF_CMPXCHG) {
+			verbose(cbs->private_data, "(%02x) r0 = atomic%s_cmpxchg((%s *)(r%d %+d), r0, r%d)\n",
+				insn->code,
+				BPF_SIZE(insn->code) == BPF_DW ? "64" : "",
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg, insn->off,
+				insn->src_reg);
+		} else if (BPF_MODE(insn->code) == BPF_ATOMIC &&
+			   insn->imm == BPF_XCHG) {
+			verbose(cbs->private_data, "(%02x) r%d = atomic%s_xchg((%s *)(r%d %+d), r%d)\n",
+				insn->code, insn->src_reg,
+				BPF_SIZE(insn->code) == BPF_DW ? "64" : "",
+				bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+				insn->dst_reg, insn->off, insn->src_reg);
 		} else {
 			verbose(cbs->private_data, "BUG_%02x\n", insn->code);
 		}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6aa1fc919761..89a4d154ab37 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3606,11 +3606,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 
 static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
 {
+	int load_reg;
 	int err;
 
 	switch (insn->imm) {
 	case BPF_ADD:
 	case BPF_ADD | BPF_FETCH:
+	case BPF_XCHG:
+	case BPF_CMPXCHG:
 		break;
 	default:
 		verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n", insn->imm);
@@ -3632,6 +3635,13 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 	if (err)
 		return err;
 
+	if (insn->imm == BPF_CMPXCHG) {
+		/* Check comparison of R0 with memory location */
+		err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+		if (err)
+			return err;
+	}
+
 	if (is_pointer_value(env, insn->src_reg)) {
 		verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
 		return -EACCES;
@@ -3662,8 +3672,13 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 	if (!(insn->imm & BPF_FETCH))
 		return 0;
 
-	/* check and record load of old value into src reg  */
-	err = check_reg_arg(env, insn->src_reg, DST_OP);
+	if (insn->imm == BPF_CMPXCHG)
+		load_reg = BPF_REG_0;
+	else
+		load_reg = insn->src_reg;
+
+	/* check and record load of old value */
+	err = check_reg_arg(env, load_reg, DST_OP);
 	if (err)
 		return err;
 
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
index 7211ce9fba53..d75998b0d5ac 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -174,6 +174,8 @@
  *
  *   BPF_ADD                  *(uint *) (dst_reg + off16) += src_reg
  *   BPF_ADD | BPF_FETCH      src_reg = atomic_fetch_add(dst_reg + off16, src_reg);
+ *   BPF_XCHG                 src_reg = atomic_xchg(dst_reg + off16, src_reg)
+ *   BPF_CMPXCHG              r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg)
  */
 
 #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF)			\
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index ea262b009049..c001766adcbc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -45,7 +45,9 @@
 #define BPF_EXIT	0x90	/* function return */
 
 /* atomic op type fields (stored in immediate) */
-#define BPF_FETCH	0x01	/* fetch previous value into src reg */
+#define BPF_FETCH	0x01	/* not an opcode on its own, used to build others */
+#define BPF_XCHG	(0xe0 | BPF_FETCH)	/* atomic exchange */
+#define BPF_CMPXCHG	(0xf0 | BPF_FETCH)	/* atomic compare-and-write */
 
 /* Register numbers */
 enum {
-- 
2.30.0.284.gd98b1dd5eaa7-goog


  parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-14 18:17 [PATCH bpf-next v7 00/11] Atomics for eBPF Brendan Jackman
2021-01-14 18:17 ` [PATCH bpf-next v7 01/11] bpf: x86: Factor out emission of ModR/M for *(reg + off) Brendan Jackman
2021-01-14 18:17 ` [PATCH bpf-next v7 02/11] bpf: x86: Factor out emission of REX byte Brendan Jackman
2021-01-14 18:17 ` [PATCH bpf-next v7 03/11] bpf: x86: Factor out a lookup table for some ALU opcodes Brendan Jackman
2021-01-14 18:17 ` [PATCH bpf-next v7 04/11] bpf: Rename BPF_XADD and prepare to encode other atomics in .imm Brendan Jackman
2021-01-14 18:17 ` [PATCH bpf-next v7 05/11] bpf: Move BPF_STX reserved field check into BPF_STX verifier code Brendan Jackman
2021-01-14 18:17 ` [PATCH bpf-next v7 06/11] bpf: Add BPF_FETCH field / create atomic_fetch_add instruction Brendan Jackman
2021-01-14 18:17 ` Brendan Jackman [this message]
2021-01-14 18:17 ` [PATCH bpf-next v7 08/11] bpf: Pull out a macro for interpreting atomic ALU operations Brendan Jackman
2021-01-14 18:17 ` [PATCH bpf-next v7 09/11] bpf: Add bitwise atomic instructions Brendan Jackman
2021-01-14 18:17 ` [PATCH bpf-next v7 10/11] bpf: Add tests for new BPF atomic operations Brendan Jackman
2021-01-14 18:17 ` [PATCH bpf-next v7 11/11] bpf: Document new atomic instructions Brendan Jackman
2021-01-15  3:20 ` [PATCH bpf-next v7 00/11] Atomics for eBPF patchwork-bot+netdevbpf
2021-01-15  3:23 ` Alexei Starovoitov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210114181751.768687-8-jackmanb@google.com \
    --to=jackmanb@google.com \
    --cc=andrii.nakryiko@gmail.com \
    --cc=ast@kernel.org \
    --cc=bjorn.topel@gmail.com \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=john.fastabend@gmail.com \
    --cc=kpsingh@chromium.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=revest@chromium.org \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

BPF Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/bpf/0 bpf/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 bpf bpf/ https://lore.kernel.org/bpf \
		bpf@vger.kernel.org
	public-inbox-index bpf

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.bpf


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git