Skip to contentSkip to conversation

bpf: Report arena faults to BPF streams

PATCH Superseded Puranjay Mohan 2 participants 5 messages Aug 11, 2025 – Aug 15, 2025

Subsystems (8)
x86 Kselftest BPF arm64 +4 more subsystems

v2 of 7 Superseded Latest is v7 →

lore
Share & tools
lore

Puranjay Mohan

author maintainer
#0 lore raw

v2 cover bpf: Report arena faults to BPF streams

Changes in v1->v2:
v1: https://lore.kernel.org/all/[email protected]/
- Changed variable and mask names for consistency (Yonghong)
- Added Acked-by: Yonghong Song <[email protected]> on two patches

This set adds the support of reporting page faults inside arena to BPF stderr stream. The reported address is the one that a user would expect to see if they pass it to bpf_printk();

Here is an example output from a stream and bpf_printk()

ERROR: Arena WRITE access at unmapped address 0xdeaddead0000

CPU: 9 UID: 0 PID: 502 Comm: test_progs
Call trace:
bpf_stream_stage_dump_stack+0xc0/0x150
bpf_prog_report_arena_violation+0x98/0xf0
ex_handler_bpf+0x5c/0x78
fixup_exception+0xf8/0x160
__do_kernel_fault+0x40/0x188
do_bad_area+0x70/0x88
do_translation_fault+0x54/0x98
do_mem_abort+0x4c/0xa8
el1_abort+0x44/0x70
el1h_64_sync_handler+0x50/0x108
el1h_64_sync+0x6c/0x70
bpf_prog_a64a9778d31b8e88_stream_arena_write_fault+0x84/0xc8
  *(page) = 1; @ stream.c:100
bpf_prog_test_run_syscall+0x100/0x328
__sys_bpf+0x508/0xb98
__arm64_sys_bpf+0x2c/0x48
invoke_syscall+0x50/0x120
el0_svc_common.constprop.0+0x48/0xf8
do_el0_svc+0x28/0x40
el0_svc+0x48/0xf8
el0t_64_sync_handler+0xa0/0xe8
el0t_64_sync+0x198/0x1a0

Same address is seen by using bpf_printk():

1389.078831: bpf_trace_printk: Read Address: 0xdeaddead0000

To make this possible, some extra metadata has to be passed to the bpf exception handler, so the bpf exception handling mechanism for both x86-64 and arm64 have been improved in this set.

The streams selftest has been updated to also test this new feature.

Puranjay Mohan (3):
bpf: arm64: simplify exception table handling
bpf: Report arena faults to BPF stderr selftests/bpf: Add tests for arena fault reporting

 arch/arm64/net/bpf_jit_comp.c                 | 56 +++++++------
 arch/x86/net/bpf_jit_comp.c                   | 79 ++++++++++++++++++-
 include/linux/bpf.h                           |  1 +
 kernel/bpf/arena.c                            | 20 +++++
 .../testing/selftests/bpf/prog_tests/stream.c | 24 ++++++
 tools/testing/selftests/bpf/progs/stream.c    | 37 +++++++++
 6 files changed, 191 insertions(+), 26 deletions(-)
Signature · 1 line
2.47.3
author maintainer
#1 lore raw

PATCH v2 1/3 bpf: arm64: simplify exception table handling

BPF loads with BPF_PROBE_MEM(SX) can load from unsafe pointers and the JIT adds an exception table entry for the JITed instruction which allows the exeption handler to set the destination register of the load to zero and continue execution from the next instruction.

As all arm64 instructions are AARCH64_INSN_SIZE size, the exception handler can just increment the pc by AARCH64_INSN_SIZE without needing the exact address of the instruction following the the faulting instruction.

Simplify the exception table usage in arm64 JIT by only saving the destination register in ex->fixup and drop everything related to the fixup_offset. The fault handler is modified to add AARCH64_INSN_SIZE to the pc.

---
 arch/arm64/net/bpf_jit_comp.c | 25 +++----------------------
 1 file changed, 3 insertions(+), 22 deletions(-)
arch/arm64/net/bpf_jit_comp.c +3 -22
index 52ffe115a8c47..42643fd9168fc 100644
@@ -1066,19 +1066,18 @@ static void build_epilogue(struct jit_ctx *ctx, bool was_classic)
 	emit(A64_RET(A64_LR), ctx);
 }
 
-#define BPF_FIXUP_OFFSET_MASK	GENMASK(26, 0)
 #define BPF_FIXUP_REG_MASK	GENMASK(31, 27)
 #define DONT_CLEAR 5 /* Unused ARM64 register from BPF's POV */
 
 bool ex_handler_bpf(const struct exception_table_entry *ex,
 		    struct pt_regs *regs)
 {
-	off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup);
 	int dst_reg = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup);
 
 	if (dst_reg != DONT_CLEAR)
 		regs->regs[dst_reg] = 0;
-	regs->pc = (unsigned long)&ex->fixup - offset;
+	/* Skip the faulting instruction */
+	regs->pc += AARCH64_INSN_SIZE;
 	return true;
 }
 
@@ -1088,7 +1087,6 @@ static int add_exception_handler(const struct bpf_insn *insn,
 				 int dst_reg)
 {
 	off_t ins_offset;
-	off_t fixup_offset;
 	unsigned long pc;
 	struct exception_table_entry *ex;
 
@@ -1119,22 +1117,6 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	if (WARN_ON_ONCE(ins_offset >= 0 || ins_offset < INT_MIN))
 		return -ERANGE;
 
-	/*
-	 * Since the extable follows the program, the fixup offset is always
-	 * negative and limited to BPF_JIT_REGION_SIZE. Store a positive value
-	 * to keep things simple, and put the destination register in the upper
-	 * bits. We don't need to worry about buildtime or runtime sort
-	 * modifying the upper bits because the table is already sorted, and
-	 * isn't part of the main exception table.
-	 *
-	 * The fixup_offset is set to the next instruction from the instruction
-	 * that may fault. The execution will jump to this after handling the
-	 * fault.
-	 */
-	fixup_offset = (long)&ex->fixup - (pc + AARCH64_INSN_SIZE);
-	if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, fixup_offset))
-		return -ERANGE;
-
 	/*
 	 * The offsets above have been calculated using the RO buffer but we
 	 * need to use the R/W buffer for writes.
@@ -1147,8 +1129,7 @@ static int add_exception_handler(const struct bpf_insn *insn,
 	if (BPF_CLASS(insn->code) != BPF_LDX)
 		dst_reg = DONT_CLEAR;
 
-	ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, fixup_offset) |
-		    FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
+	ex->fixup = FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg);
 
 	ex->type = EX_TYPE_BPF;
 
Signature · 1 line
2.47.3
author maintainer
#2 lore raw

PATCH v2 2/3 bpf: Report arena faults to BPF stderr

In reply to Puranjay Mohan

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();

---
 arch/arm64/net/bpf_jit_comp.c | 31 ++++++++++++++
 arch/x86/net/bpf_jit_comp.c   | 79 +++++++++++++++++++++++++++++++++--
 include/linux/bpf.h           |  1 +
 kernel/bpf/arena.c            | 20 +++++++++
 4 files changed, 127 insertions(+), 4 deletions(-)
arch/arm64/net/bpf_jit_comp.c +31 -0
index 42643fd9168fc..ce3b49fc0a1b1 100644
@@ -1066,6 +1066,9 @@ static void build_epilogue(struct jit_ctx *ctx, bool was_classic)
 	emit(A64_RET(A64_LR), ctx);
 }
 
+#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 +1076,22 @@ 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 +1101,9 @@ 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 +1117,9 @@ 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 +1151,17 @@ 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++;
arch/x86/net/bpf_jit_comp.c +75 -4

111 lines not on this page · raw message

include/linux/bpf.h +1 -0
index e7ee089e8a31a..9187765c6f704 100644
@@ -3654,6 +3654,7 @@ int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...);
 int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog,
 			    enum bpf_stream_id stream_id);
 int bpf_stream_stage_dump_stack(struct bpf_stream_stage *ss);
+void bpf_prog_report_arena_violation(bool write, unsigned long addr);
 
 #define bpf_stream_printk(ss, ...) bpf_stream_stage_printk(&ss, __VA_ARGS__)
 #define bpf_stream_dump_stack(ss) bpf_stream_stage_dump_stack(&ss)
kernel/bpf/arena.c +20 -0
index 5b37753799d20..a1653d1c04ca5 100644
@@ -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);
+	}));
+}
Signature · 1 line
2.47.3
#3 lore raw

Re: [PATCH bpf-next v2 2/3] bpf: Report arena faults to BPF stderr

kernel test robot noticed the following build errors:

Hi Puranjay,

kernel test robot noticed the following build errors:

[auto build test ERROR on bpf-next/master]

url:    https://github.com/intel-lab-lkp/linux/commits/Puranjay-Mohan/bpf-arm64-simplify-exception-table-handling/20250811-192218
base:   https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git master
patch link:    https://lore.kernel.org/r/20250811111828.13836-3-puranjay%40kernel.org
patch subject: [PATCH bpf-next v2 2/3] bpf: Report arena faults to BPF stderr
config: x86_64-randconfig-122-20250815 (https://download.01.org/0day-ci/archive/20250816/[email protected]/config)
compiler: gcc-11 (Debian 11.3.0-12) 11.3.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250816/[email protected]/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/

All errors (new ones prefixed by >>):

ld: vmlinux.o: in function `ex_handler_bpf':

>> arch/x86/net/bpf_jit_comp.c:1450: undefined reference to `bpf_prog_report_arena_violation'

vim +1450 arch/x86/net/bpf_jit_comp.c

1430
1431 bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs)
1432 {
1433 u32 reg = FIELD_GET(FIXUP_REG_MASK, x->fixup);
1434 u32 insn_len = FIELD_GET(FIXUP_INSN_LEN_MASK, x->fixup);
1435 bool is_arena = !!(x->fixup & FIXUP_ARENA_ACCESS);
1436 bool is_write = (reg == DONT_CLEAR);
1437 unsigned long addr;
1438 s16 off;
1439 u32 arena_reg;
1440
1441 /* jump over faulting load and clear dest register */
1442 if (reg != DONT_CLEAR)
1443 *(unsigned long *)((void *)regs + reg) = 0;
1444 regs->ip += insn_len;
1445
1446 if (is_arena) {
1447 arena_reg = FIELD_GET(FIXUP_ARENA_REG_MASK, x->data);
1448 off = FIELD_GET(DATA_ARENA_OFFSET_MASK, x->data);
1449 addr = *(unsigned long *)((void *)regs + arena_reg) + off;

> 1450			bpf_prog_report_arena_violation(is_write, addr);

1451 }
1452
1453 return true;
1454 }
1455

Signature · 2 lines
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
author maintainer
#4 lore raw

PATCH v2 3/3 selftests/bpf: Add tests for arena fault reporting

In reply to Puranjay Mohan

Add selftests for testing the reporting of arena page faults through BPF streams. Two new bpf programs are added that read and write to an unmapped arena address and the fault reporting is verified in the userspace through streams.

---
 .../testing/selftests/bpf/prog_tests/stream.c | 24 ++++++++++++
 tools/testing/selftests/bpf/progs/stream.c    | 37 +++++++++++++++++++
 2 files changed, 61 insertions(+)
tools/testing/selftests/bpf/prog_tests/stream.c +24 -0
index d9f0185dca61b..4bdde56de35b1 100644
@@ -41,6 +41,22 @@ struct {
 		"([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
 		"|[ \t]+[^\n]+\n)*",
 	},
+	{
+		offsetof(struct stream, progs.stream_arena_read_fault),
+		"ERROR: Arena READ access at unmapped address 0x.*\n"
+		"CPU: [0-9]+ UID: 0 PID: [0-9]+ Comm: .*\n"
+		"Call trace:\n"
+		"([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+		"|[ \t]+[^\n]+\n)*",
+	},
+	{
+		offsetof(struct stream, progs.stream_arena_write_fault),
+		"ERROR: Arena WRITE access at unmapped address 0x.*\n"
+		"CPU: [0-9]+ UID: 0 PID: [0-9]+ Comm: .*\n"
+		"Call trace:\n"
+		"([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+		"|[ \t]+[^\n]+\n)*",
+	},
 };
 
 static int match_regex(const char *pattern, const char *string)
@@ -85,6 +101,14 @@ void test_stream_errors(void)
 			continue;
 		}
 #endif
+#if !defined(__x86_64__) && !defined(__aarch64__)
+		ASSERT_TRUE(1, "Arena fault reporting unsupported, skip.");
+		if (i == 2 || i == 3) {
+			ret = bpf_prog_stream_read(prog_fd, 2, buf, sizeof(buf), &ropts);
+			ASSERT_EQ(ret, 0, "stream read");
+			continue;
+		}
+#endif
 
 		ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDERR, buf, sizeof(buf), &ropts);
 		ASSERT_GT(ret, 0, "stream read");
tools/testing/selftests/bpf/progs/stream.c +37 -0
index 35790897dc879..58ebff60cd96a 100644
@@ -1,10 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#define BPF_NO_KFUNC_PROTOTYPES
 #include <vmlinux.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_misc.h"
 #include "bpf_experimental.h"
+#include "bpf_arena_common.h"
+
+extern int bpf_res_spin_lock(struct bpf_res_spin_lock *lock) __weak __ksym;
+extern void bpf_res_spin_unlock(struct bpf_res_spin_lock *lock) __weak __ksym;
 
 struct arr_elem {
 	struct bpf_res_spin_lock lock;
@@ -17,6 +22,12 @@ struct {
 	__type(value, struct arr_elem);
 } arrmap SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 1); /* number of pages */
+} arena SEC(".maps");
+
 #define ENOSPC 28
 #define _STR "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
 
@@ -76,4 +87,30 @@ int stream_syscall(void *ctx)
 	return 0;
 }
 
+SEC("syscall")
+__success __retval(0)
+int stream_arena_write_fault(void *ctx)
+{
+	unsigned char __arena *page;
+
+	page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	bpf_arena_free_pages(&arena, page, 1);
+
+	*(page + 0xbeef) = 1;
+
+	return 0;
+}
+
+SEC("syscall")
+__success __retval(0)
+int stream_arena_read_fault(void *ctx)
+{
+	unsigned char __arena *page;
+
+	page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	bpf_arena_free_pages(&arena, page, 1);
+
+	return *(page + 0xbeef);
+}
+
 char _license[] SEC("license") = "GPL";
Signature · 1 line
2.47.3