x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 177 insertions, 0 deletions

diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S
new file mode 100644
index 000000000..5018ac03b
--- /dev/null
+++ b/arch/arm64/lib/mte.S
@@ -0,0 +1,177 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#include <linux/linkage.h>
+
+#include <asm/asm-uaccess.h>
+#include <asm/assembler.h>
+#include <asm/mte.h>
+#include <asm/page.h>
+#include <asm/sysreg.h>
+
+	.arch	armv8.5-a+memtag
+
+/*
+ * multitag_transfer_size - set \reg to the block size that is accessed by the
+ * LDGM/STGM instructions.
+ */
+	.macro	multitag_transfer_size, reg, tmp
+	mrs_s	\reg, SYS_GMID_EL1
+	ubfx	\reg, \reg, #GMID_EL1_BS_SHIFT, #GMID_EL1_BS_WIDTH
+	mov	\tmp, #4
+	lsl	\reg, \tmp, \reg
+	.endm
+
+/*
+ * Clear the tags in a page
+ *   x0 - address of the page to be cleared
+ */
+SYM_FUNC_START(mte_clear_page_tags)
+	multitag_transfer_size x1, x2
+1:	stgm	xzr, [x0]
+	add	x0, x0, x1
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+SYM_FUNC_END(mte_clear_page_tags)
+
+/*
+ * Zero the page and tags at the same time
+ *
+ * Parameters:
+ *	x0 - address to the beginning of the page
+ */
+SYM_FUNC_START(mte_zero_clear_page_tags)
+	and	x0, x0, #(1 << MTE_TAG_SHIFT) - 1	// clear the tag
+	mrs	x1, dczid_el0
+	tbnz	x1, #4, 2f	// Branch if DC GZVA is prohibited
+	and	w1, w1, #0xf
+	mov	x2, #4
+	lsl	x1, x2, x1
+
+1:	dc	gzva, x0
+	add	x0, x0, x1
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+
+2:	stz2g	x0, [x0], #(MTE_GRANULE_SIZE * 2)
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	2b
+	ret
+SYM_FUNC_END(mte_zero_clear_page_tags)
+
+/*
+ * Copy the tags from the source page to the destination one
+ *   x0 - address of the destination page
+ *   x1 - address of the source page
+ */
+SYM_FUNC_START(mte_copy_page_tags)
+	mov	x2, x0
+	mov	x3, x1
+	multitag_transfer_size x5, x6
+1:	ldgm	x4, [x3]
+	stgm	x4, [x2]
+	add	x2, x2, x5
+	add	x3, x3, x5
+	tst	x2, #(PAGE_SIZE - 1)
+	b.ne	1b
+	ret
+SYM_FUNC_END(mte_copy_page_tags)
+
+/*
+ * Read tags from a user buffer (one tag per byte) and set the corresponding
+ * tags at the given kernel address. Used by PTRACE_POKEMTETAGS.
+ *   x0 - kernel address (to)
+ *   x1 - user buffer (from)
+ *   x2 - number of tags/bytes (n)
+ * Returns:
+ *   x0 - number of tags read/set
+ */
+SYM_FUNC_START(mte_copy_tags_from_user)
+	mov	x3, x1
+	cbz	x2, 2f
+1:
+USER(2f, ldtrb	w4, [x1])
+	lsl	x4, x4, #MTE_TAG_SHIFT
+	stg	x4, [x0], #MTE_GRANULE_SIZE
+	add	x1, x1, #1
+	subs	x2, x2, #1
+	b.ne	1b
+
+	// exception handling and function return
+2:	sub	x0, x1, x3		// update the number of tags set
+	ret
+SYM_FUNC_END(mte_copy_tags_from_user)
+
+/*
+ * Get the tags from a kernel address range and write the tag values to the
+ * given user buffer (one tag per byte). Used by PTRACE_PEEKMTETAGS.
+ *   x0 - user buffer (to)
+ *   x1 - kernel address (from)
+ *   x2 - number of tags/bytes (n)
+ * Returns:
+ *   x0 - number of tags read/set
+ */
+SYM_FUNC_START(mte_copy_tags_to_user)
+	mov	x3, x0
+	cbz	x2, 2f
+1:
+	ldg	x4, [x1]
+	ubfx	x4, x4, #MTE_TAG_SHIFT, #MTE_TAG_SIZE
+USER(2f, sttrb	w4, [x0])
+	add	x0, x0, #1
+	add	x1, x1, #MTE_GRANULE_SIZE
+	subs	x2, x2, #1
+	b.ne	1b
+
+	// exception handling and function return
+2:	sub	x0, x0, x3		// update the number of tags copied
+	ret
+SYM_FUNC_END(mte_copy_tags_to_user)
+
+/*
+ * Save the tags in a page
+ *   x0 - page address
+ *   x1 - tag storage, MTE_PAGE_TAG_STORAGE bytes
+ */
+SYM_FUNC_START(mte_save_page_tags)
+	multitag_transfer_size x7, x5
+1:
+	mov	x2, #0
+2:
+	ldgm	x5, [x0]
+	orr	x2, x2, x5
+	add	x0, x0, x7
+	tst	x0, #0xFF		// 16 tag values fit in a register,
+	b.ne	2b			// which is 16*16=256 bytes
+
+	str	x2, [x1], #8
+
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+
+	ret
+SYM_FUNC_END(mte_save_page_tags)
+
+/*
+ * Restore the tags in a page
+ *   x0 - page address
+ *   x1 - tag storage, MTE_PAGE_TAG_STORAGE bytes
+ */
+SYM_FUNC_START(mte_restore_page_tags)
+	multitag_transfer_size x7, x5
+1:
+	ldr	x2, [x1], #8
+2:
+	stgm	x2, [x0]
+	add	x0, x0, x7
+	tst	x0, #0xFF
+	b.ne	2b
+
+	tst	x0, #(PAGE_SIZE - 1)
+	b.ne	1b
+
+	ret
+SYM_FUNC_END(mte_restore_page_tags)