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, 109 insertions, 0 deletions

diff --git a/drivers/ata/pata_netcell.c b/drivers/ata/pata_netcell.c
new file mode 100644
index 000000000..c0b2897fc
--- /dev/null
+++ b/drivers/ata/pata_netcell.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *    pata_netcell.c - Netcell PATA driver
+ *
+ *	(c) 2006 Red Hat
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <scsi/scsi_host.h>
+#include <linux/libata.h>
+#include <linux/ata.h>
+
+#define DRV_NAME	"pata_netcell"
+#define DRV_VERSION	"0.1.7"
+
+/* No PIO or DMA methods needed for this device */
+
+static unsigned int netcell_read_id(struct ata_device *adev,
+				    struct ata_taskfile *tf, __le16 *id)
+{
+	unsigned int err_mask = ata_do_dev_read_id(adev, tf, id);
+
+	/* Firmware forgets to mark words 85-87 valid */
+	if (err_mask == 0)
+		id[ATA_ID_CSF_DEFAULT] |= cpu_to_le16(0x4000);
+	return err_mask;
+}
+
+static const struct scsi_host_template netcell_sht = {
+	ATA_BMDMA_SHT(DRV_NAME),
+};
+
+static struct ata_port_operations netcell_ops = {
+	.inherits	= &ata_bmdma_port_ops,
+	.cable_detect	= ata_cable_80wire,
+	.read_id	= netcell_read_id,
+};
+
+
+/**
+ *	netcell_init_one - Register Netcell ATA PCI device with kernel services
+ *	@pdev: PCI device to register
+ *	@ent: Entry in netcell_pci_tbl matching with @pdev
+ *
+ *	Called from kernel PCI layer.
+ *
+ *	LOCKING:
+ *	Inherited from PCI layer (may sleep).
+ *
+ *	RETURNS:
+ *	Zero on success, or -ERRNO value.
+ */
+
+static int netcell_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	static const struct ata_port_info info = {
+		.flags		= ATA_FLAG_SLAVE_POSS,
+		/* Actually we don't really care about these as the
+		   firmware deals with it */
+		.pio_mask	= ATA_PIO4,
+		.mwdma_mask	= ATA_MWDMA2,
+		.udma_mask 	= ATA_UDMA5, /* UDMA 133 */
+		.port_ops	= &netcell_ops,
+	};
+	const struct ata_port_info *port_info[] = { &info, NULL };
+	int rc;
+
+	ata_print_version_once(&pdev->dev, DRV_VERSION);
+
+	rc = pcim_enable_device(pdev);
+	if (rc)
+		return rc;
+
+	/* Any chip specific setup/optimisation/messages here */
+	ata_pci_bmdma_clear_simplex(pdev);
+
+	/* And let the library code do the work */
+	return ata_pci_bmdma_init_one(pdev, port_info, &netcell_sht, NULL, 0);
+}
+
+static const struct pci_device_id netcell_pci_tbl[] = {
+	{ PCI_VDEVICE(NETCELL, PCI_DEVICE_ID_REVOLUTION), },
+
+	{ }	/* terminate list */
+};
+
+static struct pci_driver netcell_pci_driver = {
+	.name			= DRV_NAME,
+	.id_table		= netcell_pci_tbl,
+	.probe			= netcell_init_one,
+	.remove			= ata_pci_remove_one,
+#ifdef CONFIG_PM_SLEEP
+	.suspend		= ata_pci_device_suspend,
+	.resume			= ata_pci_device_resume,
+#endif
+};
+
+module_pci_driver(netcell_pci_driver);
+
+MODULE_AUTHOR("Alan Cox");
+MODULE_DESCRIPTION("SCSI low-level driver for Netcell PATA RAID");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(pci, netcell_pci_tbl);
+MODULE_VERSION(DRV_VERSION);