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, 87 insertions, 0 deletions

diff --git a/drivers/mtd/sm_ftl.h b/drivers/mtd/sm_ftl.h
new file mode 100644
index 000000000..1a1a54ce8
--- /dev/null
+++ b/drivers/mtd/sm_ftl.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright © 2009 - Maxim Levitsky
+ * SmartMedia/xD translation layer
+ *
+ * Based loosly on ssfdc.c which is
+ *  © 2005 Eptar srl
+ *  Author: Claudio Lanconelli <lanconelli.claudio@eptar.com>
+ */
+
+#include <linux/mtd/blktrans.h>
+#include <linux/kfifo.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/mtd/mtd.h>
+
+
+
+struct ftl_zone {
+	bool initialized;
+	int16_t *lba_to_phys_table;		/* LBA to physical table */
+	struct kfifo free_sectors;	/* queue of free sectors */
+};
+
+struct sm_ftl {
+	struct mtd_blktrans_dev *trans;
+
+	struct mutex mutex;		/* protects the structure */
+	struct ftl_zone *zones;		/* FTL tables for each zone */
+
+	/* Media information */
+	int block_size;			/* block size in bytes */
+	int zone_size;			/* zone size in blocks */
+	int zone_count;			/* number of zones */
+	int max_lba;			/* maximum lba in a zone */
+	int smallpagenand;		/* 256 bytes/page nand */
+	bool readonly;			/* is FS readonly */
+	bool unstable;
+	int cis_block;			/* CIS block location */
+	int cis_boffset;		/* CIS offset in the block */
+	int cis_page_offset;		/* CIS offset in the page */
+
+	/* Cache */
+	int cache_block;		/* block number of cached block */
+	int cache_zone;			/* zone of cached block */
+	unsigned char *cache_data;	/* cached block data */
+	long unsigned int cache_data_invalid_bitmap;
+	bool cache_clean;
+	struct work_struct flush_work;
+	struct timer_list timer;
+
+	/* Geometry stuff */
+	int heads;
+	int sectors;
+	int cylinders;
+
+	struct attribute_group *disk_attributes;
+	u8 cis_buffer[];		/* tmp buffer for cis reads */
+};
+
+struct chs_entry {
+	unsigned long size;
+	unsigned short cyl;
+	unsigned char head;
+	unsigned char sec;
+};
+
+
+#define SM_FTL_PARTN_BITS	3
+
+#define sm_printk(format, ...) \
+	printk(KERN_WARNING "sm_ftl" ": " format "\n", ## __VA_ARGS__)
+
+#define dbg(format, ...) \
+	if (debug) \
+		printk(KERN_DEBUG "sm_ftl" ": " format "\n", ## __VA_ARGS__)
+
+#define dbg_verbose(format, ...) \
+	if (debug > 1) \
+		printk(KERN_DEBUG "sm_ftl" ": " format "\n", ## __VA_ARGS__)
+
+
+static int sm_erase_block(struct sm_ftl *ftl, int zone_num, uint16_t block,
+								int put_free);
+static void sm_mark_block_bad(struct sm_ftl *ftl, int zone_num, int block);
+
+static int sm_recheck_media(struct sm_ftl *ftl);