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, 269 insertions, 0 deletions

diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c
new file mode 100644
index 000000000..abec43833
--- /dev/null
+++ b/fs/minix/bitmap.c
@@ -0,0 +1,269 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/minix/bitmap.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+/*
+ * Modified for 680x0 by Hamish Macdonald
+ * Fixed for 680x0 by Andreas Schwab
+ */
+
+/* bitmap.c contains the code that handles the inode and block bitmaps */
+
+#include "minix.h"
+#include <linux/buffer_head.h>
+#include <linux/bitops.h>
+#include <linux/sched.h>
+
+static DEFINE_SPINLOCK(bitmap_lock);
+
+/*
+ * bitmap consists of blocks filled with 16bit words
+ * bit set == busy, bit clear == free
+ * endianness is a mess, but for counting zero bits it really doesn't matter...
+ */
+static __u32 count_free(struct buffer_head *map[], unsigned blocksize, __u32 numbits)
+{
+	__u32 sum = 0;
+	unsigned blocks = DIV_ROUND_UP(numbits, blocksize * 8);
+
+	while (blocks--) {
+		unsigned words = blocksize / 2;
+		__u16 *p = (__u16 *)(*map++)->b_data;
+		while (words--)
+			sum += 16 - hweight16(*p++);
+	}
+
+	return sum;
+}
+
+void minix_free_block(struct inode *inode, unsigned long block)
+{
+	struct super_block *sb = inode->i_sb;
+	struct minix_sb_info *sbi = minix_sb(sb);
+	struct buffer_head *bh;
+	int k = sb->s_blocksize_bits + 3;
+	unsigned long bit, zone;
+
+	if (block < sbi->s_firstdatazone || block >= sbi->s_nzones) {
+		printk("Trying to free block not in datazone\n");
+		return;
+	}
+	zone = block - sbi->s_firstdatazone + 1;
+	bit = zone & ((1<<k) - 1);
+	zone >>= k;
+	if (zone >= sbi->s_zmap_blocks) {
+		printk("minix_free_block: nonexistent bitmap buffer\n");
+		return;
+	}
+	bh = sbi->s_zmap[zone];
+	spin_lock(&bitmap_lock);
+	if (!minix_test_and_clear_bit(bit, bh->b_data))
+		printk("minix_free_block (%s:%lu): bit already cleared\n",
+		       sb->s_id, block);
+	spin_unlock(&bitmap_lock);
+	mark_buffer_dirty(bh);
+	return;
+}
+
+int minix_new_block(struct inode * inode)
+{
+	struct minix_sb_info *sbi = minix_sb(inode->i_sb);
+	int bits_per_zone = 8 * inode->i_sb->s_blocksize;
+	int i;
+
+	for (i = 0; i < sbi->s_zmap_blocks; i++) {
+		struct buffer_head *bh = sbi->s_zmap[i];
+		int j;
+
+		spin_lock(&bitmap_lock);
+		j = minix_find_first_zero_bit(bh->b_data, bits_per_zone);
+		if (j < bits_per_zone) {
+			minix_set_bit(j, bh->b_data);
+			spin_unlock(&bitmap_lock);
+			mark_buffer_dirty(bh);
+			j += i * bits_per_zone + sbi->s_firstdatazone-1;
+			if (j < sbi->s_firstdatazone || j >= sbi->s_nzones)
+				break;
+			return j;
+		}
+		spin_unlock(&bitmap_lock);
+	}
+	return 0;
+}
+
+unsigned long minix_count_free_blocks(struct super_block *sb)
+{
+	struct minix_sb_info *sbi = minix_sb(sb);
+	u32 bits = sbi->s_nzones - sbi->s_firstdatazone + 1;
+
+	return (count_free(sbi->s_zmap, sb->s_blocksize, bits)
+		<< sbi->s_log_zone_size);
+}
+
+struct minix_inode *
+minix_V1_raw_inode(struct super_block *sb, ino_t ino, struct buffer_head **bh)
+{
+	int block;
+	struct minix_sb_info *sbi = minix_sb(sb);
+	struct minix_inode *p;
+
+	if (!ino || ino > sbi->s_ninodes) {
+		printk("Bad inode number on dev %s: %ld is out of range\n",
+		       sb->s_id, (long)ino);
+		return NULL;
+	}
+	ino--;
+	block = 2 + sbi->s_imap_blocks + sbi->s_zmap_blocks +
+		 ino / MINIX_INODES_PER_BLOCK;
+	*bh = sb_bread(sb, block);
+	if (!*bh) {
+		printk("Unable to read inode block\n");
+		return NULL;
+	}
+	p = (void *)(*bh)->b_data;
+	return p + ino % MINIX_INODES_PER_BLOCK;
+}
+
+struct minix2_inode *
+minix_V2_raw_inode(struct super_block *sb, ino_t ino, struct buffer_head **bh)
+{
+	int block;
+	struct minix_sb_info *sbi = minix_sb(sb);
+	struct minix2_inode *p;
+	int minix2_inodes_per_block = sb->s_blocksize / sizeof(struct minix2_inode);
+
+	*bh = NULL;
+	if (!ino || ino > sbi->s_ninodes) {
+		printk("Bad inode number on dev %s: %ld is out of range\n",
+		       sb->s_id, (long)ino);
+		return NULL;
+	}
+	ino--;
+	block = 2 + sbi->s_imap_blocks + sbi->s_zmap_blocks +
+		 ino / minix2_inodes_per_block;
+	*bh = sb_bread(sb, block);
+	if (!*bh) {
+		printk("Unable to read inode block\n");
+		return NULL;
+	}
+	p = (void *)(*bh)->b_data;
+	return p + ino % minix2_inodes_per_block;
+}
+
+/* Clear the link count and mode of a deleted inode on disk. */
+
+static void minix_clear_inode(struct inode *inode)
+{
+	struct buffer_head *bh = NULL;
+
+	if (INODE_VERSION(inode) == MINIX_V1) {
+		struct minix_inode *raw_inode;
+		raw_inode = minix_V1_raw_inode(inode->i_sb, inode->i_ino, &bh);
+		if (raw_inode) {
+			raw_inode->i_nlinks = 0;
+			raw_inode->i_mode = 0;
+		}
+	} else {
+		struct minix2_inode *raw_inode;
+		raw_inode = minix_V2_raw_inode(inode->i_sb, inode->i_ino, &bh);
+		if (raw_inode) {
+			raw_inode->i_nlinks = 0;
+			raw_inode->i_mode = 0;
+		}
+	}
+	if (bh) {
+		mark_buffer_dirty(bh);
+		brelse (bh);
+	}
+}
+
+void minix_free_inode(struct inode * inode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct minix_sb_info *sbi = minix_sb(inode->i_sb);
+	struct buffer_head *bh;
+	int k = sb->s_blocksize_bits + 3;
+	unsigned long ino, bit;
+
+	ino = inode->i_ino;
+	if (ino < 1 || ino > sbi->s_ninodes) {
+		printk("minix_free_inode: inode 0 or nonexistent inode\n");
+		return;
+	}
+	bit = ino & ((1<<k) - 1);
+	ino >>= k;
+	if (ino >= sbi->s_imap_blocks) {
+		printk("minix_free_inode: nonexistent imap in superblock\n");
+		return;
+	}
+
+	minix_clear_inode(inode);	/* clear on-disk copy */
+
+	bh = sbi->s_imap[ino];
+	spin_lock(&bitmap_lock);
+	if (!minix_test_and_clear_bit(bit, bh->b_data))
+		printk("minix_free_inode: bit %lu already cleared\n", bit);
+	spin_unlock(&bitmap_lock);
+	mark_buffer_dirty(bh);
+}
+
+struct inode *minix_new_inode(const struct inode *dir, umode_t mode)
+{
+	struct super_block *sb = dir->i_sb;
+	struct minix_sb_info *sbi = minix_sb(sb);
+	struct inode *inode = new_inode(sb);
+	struct buffer_head * bh;
+	int bits_per_zone = 8 * sb->s_blocksize;
+	unsigned long j;
+	int i;
+
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	j = bits_per_zone;
+	bh = NULL;
+	spin_lock(&bitmap_lock);
+	for (i = 0; i < sbi->s_imap_blocks; i++) {
+		bh = sbi->s_imap[i];
+		j = minix_find_first_zero_bit(bh->b_data, bits_per_zone);
+		if (j < bits_per_zone)
+			break;
+	}
+	if (!bh || j >= bits_per_zone) {
+		spin_unlock(&bitmap_lock);
+		iput(inode);
+		return ERR_PTR(-ENOSPC);
+	}
+	if (minix_test_and_set_bit(j, bh->b_data)) {	/* shouldn't happen */
+		spin_unlock(&bitmap_lock);
+		printk("minix_new_inode: bit already set\n");
+		iput(inode);
+		return ERR_PTR(-ENOSPC);
+	}
+	spin_unlock(&bitmap_lock);
+	mark_buffer_dirty(bh);
+	j += i * bits_per_zone;
+	if (!j || j > sbi->s_ninodes) {
+		iput(inode);
+		return ERR_PTR(-EFSCORRUPTED);
+	}
+	inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
+	inode->i_ino = j;
+	simple_inode_init_ts(inode);
+	inode->i_blocks = 0;
+	memset(&minix_i(inode)->u, 0, sizeof(minix_i(inode)->u));
+	insert_inode_hash(inode);
+	mark_inode_dirty(inode);
+
+	return inode;
+}
+
+unsigned long minix_count_free_inodes(struct super_block *sb)
+{
+	struct minix_sb_info *sbi = minix_sb(sb);
+	u32 bits = sbi->s_ninodes + 1;
+
+	return count_free(sbi->s_imap, sb->s_blocksize, bits);
+}