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, 128 insertions, 0 deletions

diff --git a/drivers/mtd/nand/bbt.c b/drivers/mtd/nand/bbt.c
new file mode 100644
index 000000000..db4f93a90
--- /dev/null
+++ b/drivers/mtd/nand/bbt.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017 Free Electrons
+ *
+ * Authors:
+ *	Boris Brezillon <boris.brezillon@free-electrons.com>
+ *	Peter Pan <peterpandong@micron.com>
+ */
+
+#define pr_fmt(fmt)	"nand-bbt: " fmt
+
+#include <linux/mtd/nand.h>
+#include <linux/slab.h>
+
+/**
+ * nanddev_bbt_init() - Initialize the BBT (Bad Block Table)
+ * @nand: NAND device
+ *
+ * Initialize the in-memory BBT.
+ *
+ * Return: 0 in case of success, a negative error code otherwise.
+ */
+int nanddev_bbt_init(struct nand_device *nand)
+{
+	unsigned int bits_per_block = fls(NAND_BBT_BLOCK_NUM_STATUS);
+	unsigned int nblocks = nanddev_neraseblocks(nand);
+
+	nand->bbt.cache = bitmap_zalloc(nblocks * bits_per_block, GFP_KERNEL);
+	if (!nand->bbt.cache)
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nanddev_bbt_init);
+
+/**
+ * nanddev_bbt_cleanup() - Cleanup the BBT (Bad Block Table)
+ * @nand: NAND device
+ *
+ * Undoes what has been done in nanddev_bbt_init()
+ */
+void nanddev_bbt_cleanup(struct nand_device *nand)
+{
+	bitmap_free(nand->bbt.cache);
+}
+EXPORT_SYMBOL_GPL(nanddev_bbt_cleanup);
+
+/**
+ * nanddev_bbt_update() - Update a BBT
+ * @nand: nand device
+ *
+ * Update the BBT. Currently a NOP function since on-flash bbt is not yet
+ * supported.
+ *
+ * Return: 0 in case of success, a negative error code otherwise.
+ */
+int nanddev_bbt_update(struct nand_device *nand)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nanddev_bbt_update);
+
+/**
+ * nanddev_bbt_get_block_status() - Return the status of an eraseblock
+ * @nand: nand device
+ * @entry: the BBT entry
+ *
+ * Return: a positive number nand_bbt_block_status status or -%ERANGE if @entry
+ *	   is bigger than the BBT size.
+ */
+int nanddev_bbt_get_block_status(const struct nand_device *nand,
+				 unsigned int entry)
+{
+	unsigned int bits_per_block = fls(NAND_BBT_BLOCK_NUM_STATUS);
+	unsigned long *pos = nand->bbt.cache +
+			     ((entry * bits_per_block) / BITS_PER_LONG);
+	unsigned int offs = (entry * bits_per_block) % BITS_PER_LONG;
+	unsigned long status;
+
+	if (entry >= nanddev_neraseblocks(nand))
+		return -ERANGE;
+
+	status = pos[0] >> offs;
+	if (bits_per_block + offs > BITS_PER_LONG)
+		status |= pos[1] << (BITS_PER_LONG - offs);
+
+	return status & GENMASK(bits_per_block - 1, 0);
+}
+EXPORT_SYMBOL_GPL(nanddev_bbt_get_block_status);
+
+/**
+ * nanddev_bbt_set_block_status() - Update the status of an eraseblock in the
+ *				    in-memory BBT
+ * @nand: nand device
+ * @entry: the BBT entry to update
+ * @status: the new status
+ *
+ * Update an entry of the in-memory BBT. If you want to push the updated BBT
+ * the NAND you should call nanddev_bbt_update().
+ *
+ * Return: 0 in case of success or -%ERANGE if @entry is bigger than the BBT
+ *	   size.
+ */
+int nanddev_bbt_set_block_status(struct nand_device *nand, unsigned int entry,
+				 enum nand_bbt_block_status status)
+{
+	unsigned int bits_per_block = fls(NAND_BBT_BLOCK_NUM_STATUS);
+	unsigned long *pos = nand->bbt.cache +
+			     ((entry * bits_per_block) / BITS_PER_LONG);
+	unsigned int offs = (entry * bits_per_block) % BITS_PER_LONG;
+	unsigned long val = status & GENMASK(bits_per_block - 1, 0);
+
+	if (entry >= nanddev_neraseblocks(nand))
+		return -ERANGE;
+
+	pos[0] &= ~GENMASK(offs + bits_per_block - 1, offs);
+	pos[0] |= val << offs;
+
+	if (bits_per_block + offs > BITS_PER_LONG) {
+		unsigned int rbits = bits_per_block + offs - BITS_PER_LONG;
+
+		pos[1] &= ~GENMASK(rbits - 1, 0);
+		pos[1] |= val >> (bits_per_block - rbits);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nanddev_bbt_set_block_status);