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, 147 insertions, 0 deletions

diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig
new file mode 100644
index 000000000..402b7b175
--- /dev/null
+++ b/drivers/block/zram/Kconfig
@@ -0,0 +1,147 @@
+# SPDX-License-Identifier: GPL-2.0
+config ZRAM
+	tristate "Compressed RAM block device support"
+	depends on BLOCK && SYSFS && MMU
+	select ZSMALLOC
+	help
+	  Creates virtual block devices called /dev/zramX (X = 0, 1, ...).
+	  Pages written to these disks are compressed and stored in memory
+	  itself. These disks allow very fast I/O and compression provides
+	  good amounts of memory savings.
+
+	  It has several use cases, for example: /tmp storage, use as swap
+	  disks and maybe many more.
+
+	  See Documentation/admin-guide/blockdev/zram.rst for more information.
+
+config ZRAM_BACKEND_LZ4
+	bool "lz4 compression support"
+	depends on ZRAM
+	select LZ4_COMPRESS
+	select LZ4_DECOMPRESS
+
+config ZRAM_BACKEND_LZ4HC
+	bool "lz4hc compression support"
+	depends on ZRAM
+	select LZ4HC_COMPRESS
+	select LZ4_DECOMPRESS
+
+config ZRAM_BACKEND_ZSTD
+	bool "zstd compression support"
+	depends on ZRAM
+	select ZSTD_COMPRESS
+	select ZSTD_DECOMPRESS
+
+config ZRAM_BACKEND_DEFLATE
+	bool "deflate compression support"
+	depends on ZRAM
+	select ZLIB_DEFLATE
+	select ZLIB_INFLATE
+
+config ZRAM_BACKEND_842
+	bool "842 compression support"
+	depends on ZRAM
+	select 842_COMPRESS
+	select 842_DECOMPRESS
+
+config ZRAM_BACKEND_FORCE_LZO
+	depends on ZRAM
+	def_bool !ZRAM_BACKEND_LZ4 && !ZRAM_BACKEND_LZ4HC && \
+		!ZRAM_BACKEND_ZSTD && !ZRAM_BACKEND_DEFLATE && \
+		!ZRAM_BACKEND_842
+
+config ZRAM_BACKEND_LZO
+	bool "lzo and lzo-rle compression support" if !ZRAM_BACKEND_FORCE_LZO
+	depends on ZRAM
+	default ZRAM_BACKEND_FORCE_LZO
+	select LZO_COMPRESS
+	select LZO_DECOMPRESS
+
+choice
+	prompt "Default zram compressor"
+	default ZRAM_DEF_COMP_LZORLE
+	depends on ZRAM
+
+config ZRAM_DEF_COMP_LZORLE
+	bool "lzo-rle"
+	depends on ZRAM_BACKEND_LZO
+
+config ZRAM_DEF_COMP_LZO
+	bool "lzo"
+	depends on ZRAM_BACKEND_LZO
+
+config ZRAM_DEF_COMP_LZ4
+	bool "lz4"
+	depends on ZRAM_BACKEND_LZ4
+
+config ZRAM_DEF_COMP_LZ4HC
+	bool "lz4hc"
+	depends on ZRAM_BACKEND_LZ4HC
+
+config ZRAM_DEF_COMP_ZSTD
+	bool "zstd"
+	depends on ZRAM_BACKEND_ZSTD
+
+config ZRAM_DEF_COMP_DEFLATE
+	bool "deflate"
+	depends on ZRAM_BACKEND_DEFLATE
+
+config ZRAM_DEF_COMP_842
+	bool "842"
+	depends on ZRAM_BACKEND_842
+
+endchoice
+
+config ZRAM_DEF_COMP
+	string
+	depends on ZRAM
+	default "lzo-rle" if ZRAM_DEF_COMP_LZORLE
+	default "lzo" if ZRAM_DEF_COMP_LZO
+	default "lz4" if ZRAM_DEF_COMP_LZ4
+	default "lz4hc" if ZRAM_DEF_COMP_LZ4HC
+	default "zstd" if ZRAM_DEF_COMP_ZSTD
+	default "deflate" if ZRAM_DEF_COMP_DEFLATE
+	default "842" if ZRAM_DEF_COMP_842
+	default "unset-value"
+
+config ZRAM_WRITEBACK
+       bool "Write back incompressible or idle page to backing device"
+       depends on ZRAM
+       help
+	 This lets zram entries (incompressible or idle pages) be written
+	 back to a backing device, helping save memory.
+	 For this feature, admin should set up backing device via
+	 /sys/block/zramX/backing_dev.
+
+	 With /sys/block/zramX/{idle,writeback}, application could ask
+	 idle page's writeback to the backing device to save in memory.
+
+	 See Documentation/admin-guide/blockdev/zram.rst for more information.
+
+config ZRAM_TRACK_ENTRY_ACTIME
+	bool "Track access time of zram entries"
+	depends on ZRAM
+	help
+	  With this feature zram tracks access time of every stored
+	  entry (page), which can be used for a more fine grained IDLE
+	  pages writeback.
+
+config ZRAM_MEMORY_TRACKING
+	bool "Track zRam block status"
+	depends on ZRAM && DEBUG_FS
+	select ZRAM_TRACK_ENTRY_ACTIME
+	help
+	  With this feature, admin can track the state of allocated blocks
+	  of zRAM. Admin could see the information via
+	  /sys/kernel/debug/zram/zramX/block_state.
+
+	  See Documentation/admin-guide/blockdev/zram.rst for more information.
+
+config ZRAM_MULTI_COMP
+	bool "Enable multiple compression streams"
+	depends on ZRAM
+	help
+	  This will enable multi-compression streams, so that ZRAM can
+	  re-compress pages using a potentially slower but more effective
+	  compression algorithm. Note, that IDLE page recompression
+	  requires ZRAM_TRACK_ENTRY_ACTIME.