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, 280 insertions, 0 deletions

diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
new file mode 100644
index 000000000..ebaf7cc42
--- /dev/null
+++ b/fs/ext4/ext4_extents.h
@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com
+ * Written by Alex Tomas <alex@clusterfs.com>
+ */
+
+#ifndef _EXT4_EXTENTS
+#define _EXT4_EXTENTS
+
+#include "ext4.h"
+
+/*
+ * With AGGRESSIVE_TEST defined, the capacity of index/leaf blocks
+ * becomes very small, so index split, in-depth growing and
+ * other hard changes happen much more often.
+ * This is for debug purposes only.
+ */
+#define AGGRESSIVE_TEST_
+
+/*
+ * With EXTENTS_STATS defined, the number of blocks and extents
+ * are collected in the truncate path. They'll be shown at
+ * umount time.
+ */
+#define EXTENTS_STATS__
+
+/*
+ * If CHECK_BINSEARCH is defined, then the results of the binary search
+ * will also be checked by linear search.
+ */
+#define CHECK_BINSEARCH__
+
+/*
+ * ext4_inode has i_block array (60 bytes total).
+ * The first 12 bytes store ext4_extent_header;
+ * the remainder stores an array of ext4_extent.
+ * For non-inode extent blocks, ext4_extent_tail
+ * follows the array.
+ */
+
+/*
+ * This is the extent tail on-disk structure.
+ * All other extent structures are 12 bytes long.  It turns out that
+ * block_size % 12 >= 4 for at least all powers of 2 greater than 512, which
+ * covers all valid ext4 block sizes.  Therefore, this tail structure can be
+ * crammed into the end of the block without having to rebalance the tree.
+ */
+struct ext4_extent_tail {
+	__le32	et_checksum;	/* crc32c(uuid+inum+extent_block) */
+};
+
+/*
+ * This is the extent on-disk structure.
+ * It's used at the bottom of the tree.
+ */
+struct ext4_extent {
+	__le32	ee_block;	/* first logical block extent covers */
+	__le16	ee_len;		/* number of blocks covered by extent */
+	__le16	ee_start_hi;	/* high 16 bits of physical block */
+	__le32	ee_start_lo;	/* low 32 bits of physical block */
+};
+
+/*
+ * This is index on-disk structure.
+ * It's used at all the levels except the bottom.
+ */
+struct ext4_extent_idx {
+	__le32	ei_block;	/* index covers logical blocks from 'block' */
+	__le32	ei_leaf_lo;	/* pointer to the physical block of the next *
+				 * level. leaf or next index could be there */
+	__le16	ei_leaf_hi;	/* high 16 bits of physical block */
+	__u16	ei_unused;
+};
+
+/*
+ * Each block (leaves and indexes), even inode-stored has header.
+ */
+struct ext4_extent_header {
+	__le16	eh_magic;	/* probably will support different formats */
+	__le16	eh_entries;	/* number of valid entries */
+	__le16	eh_max;		/* capacity of store in entries */
+	__le16	eh_depth;	/* has tree real underlying blocks? */
+	__le32	eh_generation;	/* generation of the tree */
+};
+
+#define EXT4_EXT_MAGIC		cpu_to_le16(0xf30a)
+#define EXT4_MAX_EXTENT_DEPTH 5
+
+#define EXT4_EXTENT_TAIL_OFFSET(hdr) \
+	(sizeof(struct ext4_extent_header) + \
+	 (sizeof(struct ext4_extent) * le16_to_cpu((hdr)->eh_max)))
+
+static inline struct ext4_extent_tail *
+find_ext4_extent_tail(struct ext4_extent_header *eh)
+{
+	return (struct ext4_extent_tail *)(((void *)eh) +
+					   EXT4_EXTENT_TAIL_OFFSET(eh));
+}
+
+/*
+ * Array of ext4_ext_path contains path to some extent.
+ * Creation/lookup routines use it for traversal/splitting/etc.
+ * Truncate uses it to simulate recursive walking.
+ */
+struct ext4_ext_path {
+	ext4_fsblk_t			p_block;
+	__u16				p_depth;
+	__u16				p_maxdepth;
+	struct ext4_extent		*p_ext;
+	struct ext4_extent_idx		*p_idx;
+	struct ext4_extent_header	*p_hdr;
+	struct buffer_head		*p_bh;
+};
+
+/*
+ * Used to record a portion of a cluster found at the beginning or end
+ * of an extent while traversing the extent tree during space removal.
+ * A partial cluster may be removed if it does not contain blocks shared
+ * with extents that aren't being deleted (tofree state).  Otherwise,
+ * it cannot be removed (nofree state).
+ */
+struct partial_cluster {
+	ext4_fsblk_t pclu;  /* physical cluster number */
+	ext4_lblk_t lblk;   /* logical block number within logical cluster */
+	enum {initial, tofree, nofree} state;
+};
+
+/*
+ * structure for external API
+ */
+
+/*
+ * EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
+ * initialized extent. This is 2^15 and not (2^16 - 1), since we use the
+ * MSB of ee_len field in the extent datastructure to signify if this
+ * particular extent is an initialized extent or an unwritten (i.e.
+ * preallocated).
+ * EXT_UNWRITTEN_MAX_LEN is the maximum number of blocks we can have in an
+ * unwritten extent.
+ * If ee_len is <= 0x8000, it is an initialized extent. Otherwise, it is an
+ * unwritten one. In other words, if MSB of ee_len is set, it is an
+ * unwritten extent with only one special scenario when ee_len = 0x8000.
+ * In this case we can not have an unwritten extent of zero length and
+ * thus we make it as a special case of initialized extent with 0x8000 length.
+ * This way we get better extent-to-group alignment for initialized extents.
+ * Hence, the maximum number of blocks we can have in an *initialized*
+ * extent is 2^15 (32768) and in an *unwritten* extent is 2^15-1 (32767).
+ */
+#define EXT_INIT_MAX_LEN	(1UL << 15)
+#define EXT_UNWRITTEN_MAX_LEN	(EXT_INIT_MAX_LEN - 1)
+
+
+#define EXT_FIRST_EXTENT(__hdr__) \
+	((struct ext4_extent *) (((char *) (__hdr__)) +		\
+				 sizeof(struct ext4_extent_header)))
+#define EXT_FIRST_INDEX(__hdr__) \
+	((struct ext4_extent_idx *) (((char *) (__hdr__)) +	\
+				     sizeof(struct ext4_extent_header)))
+#define EXT_HAS_FREE_INDEX(__path__) \
+	(le16_to_cpu((__path__)->p_hdr->eh_entries) \
+				     < le16_to_cpu((__path__)->p_hdr->eh_max))
+#define EXT_LAST_EXTENT(__hdr__) \
+	(EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_LAST_INDEX(__hdr__) \
+	(EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_entries) - 1)
+#define EXT_MAX_EXTENT(__hdr__)	\
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_EXTENT((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \
+					: NULL)
+#define EXT_MAX_INDEX(__hdr__) \
+	((le16_to_cpu((__hdr__)->eh_max)) ? \
+	((EXT_FIRST_INDEX((__hdr__)) + le16_to_cpu((__hdr__)->eh_max) - 1)) \
+					: NULL)
+
+static inline struct ext4_extent_header *ext_inode_hdr(struct inode *inode)
+{
+	return (struct ext4_extent_header *) EXT4_I(inode)->i_data;
+}
+
+static inline struct ext4_extent_header *ext_block_hdr(struct buffer_head *bh)
+{
+	return (struct ext4_extent_header *) bh->b_data;
+}
+
+static inline unsigned short ext_depth(struct inode *inode)
+{
+	return le16_to_cpu(ext_inode_hdr(inode)->eh_depth);
+}
+
+static inline void ext4_ext_mark_unwritten(struct ext4_extent *ext)
+{
+	/* We can not have an unwritten extent of zero length! */
+	BUG_ON((le16_to_cpu(ext->ee_len) & ~EXT_INIT_MAX_LEN) == 0);
+	ext->ee_len |= cpu_to_le16(EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_is_unwritten(struct ext4_extent *ext)
+{
+	/* Extent with ee_len of 0x8000 is treated as an initialized extent */
+	return (le16_to_cpu(ext->ee_len) > EXT_INIT_MAX_LEN);
+}
+
+static inline int ext4_ext_get_actual_len(struct ext4_extent *ext)
+{
+	return (le16_to_cpu(ext->ee_len) <= EXT_INIT_MAX_LEN ?
+		le16_to_cpu(ext->ee_len) :
+		(le16_to_cpu(ext->ee_len) - EXT_INIT_MAX_LEN));
+}
+
+static inline void ext4_ext_mark_initialized(struct ext4_extent *ext)
+{
+	ext->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ext));
+}
+
+/*
+ * ext4_ext_pblock:
+ * combine low and high parts of physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_ext_pblock(struct ext4_extent *ex)
+{
+	ext4_fsblk_t block;
+
+	block = le32_to_cpu(ex->ee_start_lo);
+	block |= ((ext4_fsblk_t) le16_to_cpu(ex->ee_start_hi) << 31) << 1;
+	return block;
+}
+
+/*
+ * ext4_idx_pblock:
+ * combine low and high parts of a leaf physical block number into ext4_fsblk_t
+ */
+static inline ext4_fsblk_t ext4_idx_pblock(struct ext4_extent_idx *ix)
+{
+	ext4_fsblk_t block;
+
+	block = le32_to_cpu(ix->ei_leaf_lo);
+	block |= ((ext4_fsblk_t) le16_to_cpu(ix->ei_leaf_hi) << 31) << 1;
+	return block;
+}
+
+/*
+ * ext4_ext_store_pblock:
+ * stores a large physical block number into an extent struct,
+ * breaking it into parts
+ */
+static inline void ext4_ext_store_pblock(struct ext4_extent *ex,
+					 ext4_fsblk_t pb)
+{
+	ex->ee_start_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+	ex->ee_start_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+				      0xffff);
+}
+
+/*
+ * ext4_idx_store_pblock:
+ * stores a large physical block number into an index struct,
+ * breaking it into parts
+ */
+static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix,
+					 ext4_fsblk_t pb)
+{
+	ix->ei_leaf_lo = cpu_to_le32((unsigned long) (pb & 0xffffffff));
+	ix->ei_leaf_hi = cpu_to_le16((unsigned long) ((pb >> 31) >> 1) &
+				     0xffff);
+}
+
+extern int __ext4_ext_dirty(const char *where, unsigned int line,
+			    handle_t *handle, struct inode *inode,
+			    struct ext4_ext_path *path);
+extern int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex);
+#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS)
+extern int ext4_ext_space_root_idx_test(struct inode *inode, int check);
+extern struct ext4_ext_path *ext4_split_convert_extents_test(
+				handle_t *handle, struct inode *inode,
+				struct ext4_map_blocks *map,
+				struct ext4_ext_path *path,
+				int flags, unsigned int *allocated);
+#endif
+#endif /* _EXT4_EXTENTS */
+