All of lore.kernel.org
 help / color / mirror / Atom feed
From: Puranjay Mohan <puranjay@kernel.org>
To: Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Andrii Nakryiko <andrii@kernel.org>,
	Martin KaFai Lau <martin.lau@linux.dev>,
	Eduard Zingerman <eddyz87@gmail.com>, Song Liu <song@kernel.org>,
	Yonghong Song <yonghong.song@linux.dev>,
	John Fastabend <john.fastabend@gmail.com>,
	KP Singh <kpsingh@kernel.org>,
	Stanislav Fomichev <sdf@fomichev.me>, Hao Luo <haoluo@google.com>,
	Jiri Olsa <jolsa@kernel.org>,
	Puranjay Mohan <puranjay@kernel.org>,
	Xu Kuohai <xukuohai@huaweicloud.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	Kumar Kartikeya Dwivedi <memxor@gmail.com>,
	bpf@vger.kernel.org
Subject: [PATCH bpf-next v4 2/3] bpf: Report arena faults to BPF stderr
Date: Wed, 27 Aug 2025 15:37:25 +0000	[thread overview]
Message-ID: <20250827153728.28115-3-puranjay@kernel.org> (raw)
In-Reply-To: <20250827153728.28115-1-puranjay@kernel.org>

Begin reporting arena page faults and the faulting address to BPF
program's stderr, this patch adds support in the arm64 and x86-64 JITs,
support for other archs can be added later.

The fault handlers receive the 32 bit address in the arena region so
the upper 32 bits of user_vm_start is added to it before printing the
address. This is what the user would expect to see as this is what is
printed by bpf_printk() is you pass it an address returned by
bpf_arena_alloc_pages();

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
---
 arch/arm64/net/bpf_jit_comp.c | 52 +++++++++++++++++++++++
 arch/x86/net/bpf_jit_comp.c   | 79 +++++++++++++++++++++++++++++++++--
 include/linux/bpf.h           |  5 +++
 kernel/bpf/arena.c            | 20 +++++++++
 4 files changed, 152 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 42643fd9168fc..5083886d6e66b 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1066,6 +1066,30 @@ static void build_epilogue(struct jit_ctx *ctx, bool was_classic)
 	emit(A64_RET(A64_LR), ctx);
 }
 
+/*
+ * Metadata encoding for exception handling in JITed code.
+ *
+ * Format of `fixup` field in `struct exception_table_entry`:
+ *
+ * Bit layout of `fixup` (32-bit):
+ *
+ * +-----------+--------+-----------+-----------+----------+
+ * |   31-27   | 26-22  |     21    |   20-16   |   15-0   |
+ * |           |        |           |           |          |
+ * | FIXUP_REG | Unused | ARENA_ACC | ARENA_REG |  OFFSET  |
+ * +-----------+--------+-----------+-----------+----------+
+ *
+ * - OFFSET (16 bits): Offset used to compute address for Load/Store instruction.
+ * - ARENA_REG (5 bits): Register that is used to calculate the address for load/store when
+ *                       accessing the arena region.
+ * - ARENA_ACCESS (1 bit): This bit is set when the faulting instruction accessed the arena region.
+ * - FIXUP_REG (5 bits): Destination register for the load instruction (cleared on fault) or set to
+ *                       DONT_CLEAR if it is a store instruction.
+ */
+
+#define BPF_FIXUP_OFFSET_MASK      GENMASK(15, 0)
+#define BPF_FIXUP_ARENA_REG_MASK   GENMASK(20, 16)
+#define BPF_ARENA_ACCESS           BIT(21)
 #define BPF_FIXUP_REG_MASK	GENMASK(31, 27)
 #define DONT_CLEAR 5 /* Unused ARM64 register from BPF's POV */
 
@@ -1073,11 +1097,22 @@ bool ex_handler_bpf(const struct exception_table_entry *ex,
 		    struct pt_regs *regs)
 {
 	int dst_reg = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
+	s16 off = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
+	int arena_reg = FIELD_GET(BPF_FIXUP_ARENA_REG_MASK, ex->fixup);
+	bool is_arena = !!(ex->fixup & BPF_ARENA_ACCESS);
+	bool is_write = (dst_reg == DONT_CLEAR);
+	unsigned long addr;
 
 	if (dst_reg != DONT_CLEAR)
 		regs->regs[dst_reg] = 0;
 	/* Skip the faulting instruction */
 	regs->pc += AARCH64_INSN_SIZE;
+
+	if (is_arena) {
+		addr = regs->regs[arena_reg] + off;
+		bpf_prog_report_arena_violation(is_write, addr);
+	}
+
 	return true;
 }
 
@@ -1087,6 +1122,9 @@ static int add_exception_handler(const struct bpf_insn *insn,
 				 int dst_reg)
 {
 	off_t ins_offset;
+	s16 off = insn->off;
+	bool is_arena;
+	int arena_reg;
 	unsigned long pc;
 	struct exception_table_entry *ex;
 
@@ -1100,6 +1138,9 @@ static int add_exception_handler(const struct bpf_insn *insn,
 				BPF_MODE(insn->code) != BPF_PROBE_ATOMIC)
 		return 0;
 
+	is_arena = (BPF_MODE(insn->code) == BPF_PROBE_MEM32) ||
+		   (BPF_MODE(insn->code) == BPF_PROBE_ATOMIC);
+
 	if (!ctx->prog->aux->extable ||
 	    WARN_ON_ONCE(ctx->exentry_idx >= ctx->prog->aux->num_exentries))
 		return -EINVAL;
@@ -1131,6 +1172,17 @@ static int add_exception_handler(const struct bpf_insn *insn,
 
 	ex->fixup = FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
 
+	if (is_arena) {
+		ex->fixup |= BPF_ARENA_ACCESS;
+		if (BPF_CLASS(insn->code) == BPF_LDX)
+			arena_reg = bpf2a64[insn->src_reg];
+		else
+			arena_reg = bpf2a64[insn->dst_reg];
+
+		ex->fixup |=  FIELD_PREP(BPF_FIXUP_OFFSET_MASK, off) |
+			      FIELD_PREP(BPF_FIXUP_ARENA_REG_MASK, arena_reg);
+	}
+
 	ex->type = EX_TYPE_BPF;
 
 	ctx->exentry_idx++;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7e3fca1646203..b75dea55df5a2 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -8,6 +8,7 @@
 #include <linux/netdevice.h>
 #include <linux/filter.h>
 #include <linux/if_vlan.h>
+#include <linux/bitfield.h>
 #include <linux/bpf.h>
 #include <linux/memory.h>
 #include <linux/sort.h>
@@ -1388,16 +1389,67 @@ static int emit_atomic_ld_st_index(u8 **pprog, u32 atomic_op, u32 size,
 	return 0;
 }
 
+/*
+ * Metadata encoding for exception handling in JITed code.
+ *
+ * Format of `fixup` and `data` fields in `struct exception_table_entry`:
+ *
+ * Bit layout of `fixup` (32-bit):
+ *
+ * +-----------+--------+-----------+---------+----------+
+ * | 31        | 30-24  |   23-16   |   15-8  |    7-0   |
+ * |           |        |           |         |          |
+ * | ARENA_ACC | Unused | ARENA_REG | DST_REG | INSN_LEN |
+ * +-----------+--------+-----------+---------+----------+
+ *
+ * - INSN_LEN (8 bits): Length of faulting insn (max x86 insn = 15 bytes (fits in 8 bits)).
+ * - DST_REG  (8 bits): Offset of dst_reg from reg2pt_regs[] (max offset = 112 (fits in 8 bits)).
+ *                      This is set to DONT_CLEAR if the insn is a store.
+ * - ARENA_REG (8 bits): Offset of the register that is used to calculate the
+ *                       address for load/store when accessing the arena region.
+ * - ARENA_ACCESS (1 bit): This bit is set when the faulting instruction accessed the arena region.
+ *
+ * Bit layout of `data` (32-bit):
+ *
+ * +--------------+--------+--------------+
+ * |	31-16	  |  15-8  |     7-0      |
+ * |              |	   |              |
+ * | ARENA_OFFSET | Unused |  EX_TYPE_BPF |
+ * +--------------+--------+--------------+
+ *
+ * - ARENA_OFFSET (16 bits): Offset used to calculate the address for load/store when
+ *                           accessing the arena region.
+ */
+
 #define DONT_CLEAR 1
+#define FIXUP_INSN_LEN_MASK	GENMASK(7, 0)
+#define FIXUP_REG_MASK		GENMASK(15, 8)
+#define FIXUP_ARENA_REG_MASK	GENMASK(23, 16)
+#define FIXUP_ARENA_ACCESS	BIT(31)
+#define DATA_ARENA_OFFSET_MASK	GENMASK(31, 16)
 
 bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
 {
-	u32 reg = x->fixup >> 8;
+	u32 reg = FIELD_GET(FIXUP_REG_MASK, x->fixup);
+	u32 insn_len = FIELD_GET(FIXUP_INSN_LEN_MASK, x->fixup);
+	bool is_arena = !!(x->fixup & FIXUP_ARENA_ACCESS);
+	bool is_write = (reg == DONT_CLEAR);
+	unsigned long addr;
+	s16 off;
+	u32 arena_reg;
 
 	/* jump over faulting load and clear dest register */
 	if (reg != DONT_CLEAR)
 		*(unsigned long *)((void *)regs + reg) = 0;
-	regs->ip += x->fixup & 0xff;
+	regs->ip += insn_len;
+
+	if (is_arena) {
+		arena_reg = FIELD_GET(FIXUP_ARENA_REG_MASK, x->fixup);
+		off = FIELD_GET(DATA_ARENA_OFFSET_MASK, x->data);
+		addr = *(unsigned long *)((void *)regs + arena_reg) + off;
+		bpf_prog_report_arena_violation(is_write, addr);
+	}
+
 	return true;
 }
 
@@ -2070,6 +2122,8 @@ st:			if (is_imm8(insn->off))
 			{
 				struct exception_table_entry *ex;
 				u8 *_insn = image + proglen + (start_of_ldx - temp);
+				u32 arena_reg, fixup_reg;
+				bool is_arena;
 				s64 delta;
 
 				if (!bpf_prog->aux->extable)
@@ -2089,8 +2143,25 @@ st:			if (is_imm8(insn->off))
 
 				ex->data = EX_TYPE_BPF;
 
-				ex->fixup = (prog - start_of_ldx) |
-					((BPF_CLASS(insn->code) == BPF_LDX ? reg2pt_regs[dst_reg] : DONT_CLEAR) << 8);
+				is_arena = (BPF_MODE(insn->code) == BPF_PROBE_MEM32) ||
+					   (BPF_MODE(insn->code) == BPF_PROBE_ATOMIC);
+
+				fixup_reg = (BPF_CLASS(insn->code) == BPF_LDX) ?
+					    reg2pt_regs[dst_reg] : DONT_CLEAR;
+
+				ex->fixup = FIELD_PREP(FIXUP_INSN_LEN_MASK, prog - start_of_ldx) |
+					    FIELD_PREP(FIXUP_REG_MASK, fixup_reg);
+
+				if (is_arena) {
+					ex->fixup |= FIXUP_ARENA_ACCESS;
+					if (BPF_CLASS(insn->code) == BPF_LDX)
+						arena_reg = reg2pt_regs[src_reg];
+					else
+						arena_reg = reg2pt_regs[dst_reg];
+
+					ex->fixup |= FIELD_PREP(FIXUP_ARENA_REG_MASK, arena_reg);
+					ex->data |= FIELD_PREP(DATA_ARENA_OFFSET_MASK, insn->off);
+				}
 			}
 			break;
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8f6e87f0f3a89..9959e30f805b2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2013,6 +2013,7 @@ int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc,
 			     struct bpf_verifier_log *log);
 void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map);
 void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc);
+void bpf_prog_report_arena_violation(bool write, unsigned long addr);
 #else
 #define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; })
 static inline bool bpf_try_module_get(const void *data, struct module *owner)
@@ -2045,6 +2046,10 @@ static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_op
 {
 }
 
+static inline void bpf_prog_report_arena_violation(bool write, unsigned long addr)
+{
+}
+
 #endif
 
 int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog,
diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 5b37753799d20..a1653d1c04ca5 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -633,3 +633,23 @@ static int __init kfunc_init(void)
 	return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set);
 }
 late_initcall(kfunc_init);
+
+void bpf_prog_report_arena_violation(bool write, unsigned long addr)
+{
+	struct bpf_stream_stage ss;
+	struct bpf_prog *prog;
+	u64 user_vm_start;
+
+	prog = bpf_prog_find_from_stack();
+	if (!prog)
+		return;
+
+	user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena);
+	addr += (user_vm_start >> 32) << 32;
+
+	bpf_stream_stage(ss, prog, BPF_STDERR, ({
+		bpf_stream_printk(ss, "ERROR: Arena %s access at unmapped address 0x%lx\n",
+				  write ? "WRITE" : "READ", addr);
+		bpf_stream_dump_stack(ss);
+	}));
+}
-- 
2.47.3


  parent reply	other threads:[~2025-08-27 15:37 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-27 15:37 [PATCH bpf-next v4 0/3] bpf: Report arena faults to BPF streams Puranjay Mohan
2025-08-27 15:37 ` [PATCH bpf-next v4 1/3] bpf: arm64: simplify exception table handling Puranjay Mohan
2025-08-28  0:19   ` Kumar Kartikeya Dwivedi
2025-08-29 10:06   ` Xu Kuohai
2025-08-27 15:37 ` Puranjay Mohan [this message]
2025-08-28  0:22   ` [PATCH bpf-next v4 2/3] bpf: Report arena faults to BPF stderr Kumar Kartikeya Dwivedi
2025-08-28  0:27     ` Kumar Kartikeya Dwivedi
2025-08-28 12:14     ` Puranjay Mohan
2025-08-29 10:30   ` Xu Kuohai
2025-08-29 20:28     ` Alexei Starovoitov
2025-09-01 13:34       ` Puranjay Mohan
2025-09-01 16:39         ` Alexei Starovoitov
2025-09-01 19:22           ` Puranjay Mohan
2025-09-01 22:44             ` Kumar Kartikeya Dwivedi
2025-09-02  2:18               ` Alexei Starovoitov
2025-08-27 15:37 ` [PATCH bpf-next v4 3/3] selftests/bpf: Add tests for arena fault reporting Puranjay Mohan
2025-08-27 19:54   ` Yonghong Song
2025-08-27 23:49     ` Kumar Kartikeya Dwivedi
2025-08-28 12:25     ` Puranjay Mohan
2025-08-28 15:44       ` Yonghong Song
2025-08-28  0:23 ` [PATCH bpf-next v4 0/3] bpf: Report arena faults to BPF streams Kumar Kartikeya Dwivedi
2025-08-28 12:13   ` Puranjay Mohan

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=20250827153728.28115-3-puranjay@kernel.org \
    --to=puranjay@kernel.org \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=daniel@iogearbox.net \
    --cc=eddyz87@gmail.com \
    --cc=haoluo@google.com \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kpsingh@kernel.org \
    --cc=martin.lau@linux.dev \
    --cc=memxor@gmail.com \
    --cc=sdf@fomichev.me \
    --cc=song@kernel.org \
    --cc=will@kernel.org \
    --cc=xukuohai@huaweicloud.com \
    --cc=yonghong.song@linux.dev \
    /path/to/YOUR_REPLY

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

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.