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, 115 insertions, 0 deletions

diff --git a/arch/powerpc/boot/treeboot-currituck.c b/arch/powerpc/boot/treeboot-currituck.c
new file mode 100644
index 000000000..5b5363b74
--- /dev/null
+++ b/arch/powerpc/boot/treeboot-currituck.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright © 2011 Tony Breeds IBM Corporation
+ *
+ * Based on earlier code:
+ *   Copyright (C) Paul Mackerras 1997.
+ *
+ *   Matt Porter <mporter@kernel.crashing.org>
+ *   Copyright 2002-2005 MontaVista Software Inc.
+ *
+ *   Eugene Surovegin <eugene.surovegin@zultys.com> or <ebs@ebshome.net>
+ *   Copyright (c) 2003, 2004 Zultys Technologies
+ *
+ *    Copyright 2007 David Gibson, IBM Corporation.
+ *    Copyright 2010 Ben. Herrenschmidt, IBM Corporation.
+ *    Copyright © 2011 David Kleikamp IBM Corporation
+ */
+#include <stdarg.h>
+#include <stddef.h>
+#include "types.h"
+#include "elf.h"
+#include "string.h"
+#include "stdio.h"
+#include "page.h"
+#include "ops.h"
+#include "reg.h"
+#include "io.h"
+#include "dcr.h"
+#include "4xx.h"
+#include "44x.h"
+#include "libfdt.h"
+
+BSS_STACK(4096);
+
+#define MAX_RANKS	0x4
+#define DDR3_MR0CF	0x80010011U
+
+static unsigned long long ibm_currituck_memsize;
+static unsigned long long ibm_currituck_detect_memsize(void)
+{
+	u32 reg;
+	unsigned i;
+	unsigned long long memsize = 0;
+
+	for(i = 0; i < MAX_RANKS; i++){
+		reg = mfdcrx(DDR3_MR0CF + i);
+
+		if (!(reg & 1))
+			continue;
+
+		reg &= 0x0000f000;
+		reg >>= 12;
+		memsize += (0x800000ULL << reg);
+	}
+
+	return memsize;
+}
+
+static void ibm_currituck_fixups(void)
+{
+	void *devp = finddevice("/");
+	u32 dma_ranges[7];
+
+	dt_fixup_memory(0x0ULL,  ibm_currituck_memsize);
+
+	while ((devp = find_node_by_devtype(devp, "pci"))) {
+		if (getprop(devp, "dma-ranges", dma_ranges, sizeof(dma_ranges)) < 0) {
+			printf("%s: Failed to get dma-ranges\r\n", __func__);
+			continue;
+		}
+
+		dma_ranges[5] = ibm_currituck_memsize >> 32;
+		dma_ranges[6] = ibm_currituck_memsize & 0xffffffffUL;
+
+		setprop(devp, "dma-ranges", dma_ranges, sizeof(dma_ranges));
+	}
+}
+
+#define SPRN_PIR	0x11E	/* Processor Identification Register */
+void platform_init(void)
+{
+	unsigned long end_of_ram, avail_ram;
+	u32 pir_reg;
+	int node, size;
+	const u32 *timebase;
+
+	ibm_currituck_memsize = ibm_currituck_detect_memsize();
+	if (ibm_currituck_memsize >> 32)
+		end_of_ram = ~0UL;
+	else
+		end_of_ram = ibm_currituck_memsize;
+	avail_ram = end_of_ram - (unsigned long)_end;
+
+	simple_alloc_init(_end, avail_ram, 128, 64);
+	platform_ops.fixups = ibm_currituck_fixups;
+	platform_ops.exit = ibm44x_dbcr_reset;
+	pir_reg = mfspr(SPRN_PIR);
+
+	/* Make sure FDT blob is sane */
+	if (fdt_check_header(_dtb_start) != 0)
+		fatal("Invalid device tree blob\n");
+
+	node = fdt_node_offset_by_prop_value(_dtb_start, -1, "device_type",
+	                                     "cpu", sizeof("cpu"));
+	if (node < 0)
+		fatal("Cannot find cpu node\n");
+	timebase = fdt_getprop(_dtb_start, node, "timebase-frequency", &size);
+	if (timebase && (size == 4))
+		timebase_period_ns = 1000000000 / *timebase;
+
+	fdt_set_boot_cpuid_phys(_dtb_start, pir_reg);
+	fdt_init(_dtb_start);
+
+	serial_console_init();
+}