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, 236 insertions, 0 deletions

diff --git a/drivers/of/fdt_address.c b/drivers/of/fdt_address.c
new file mode 100644
index 000000000..f358d2c80
--- /dev/null
+++ b/drivers/of/fdt_address.c
@@ -0,0 +1,236 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * FDT Address translation based on u-boot fdt_support.c which in turn was
+ * based on the kernel unflattened DT address translation code.
+ *
+ * (C) Copyright 2007
+ * Gerald Van Baren, Custom IDEAS, vanbaren@cideas.com
+ *
+ * Copyright 2010-2011 Freescale Semiconductor, Inc.
+ */
+
+#define pr_fmt(fmt)	"OF: fdt: " fmt
+
+#include <linux/kernel.h>
+#include <linux/libfdt.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/sizes.h>
+
+/* Uncomment me to enable of_dump_addr() debugging output */
+// #define DEBUG
+
+#include "of_private.h"
+
+/* Callbacks for bus specific translators */
+struct of_bus {
+	void		(*count_cells)(const void *blob, int parentoffset,
+				int *addrc, int *sizec);
+	u64		(*map)(__be32 *addr, const __be32 *range,
+				int na, int ns, int pna);
+	int		(*translate)(__be32 *addr, u64 offset, int na);
+};
+
+/* Default translator (generic bus) */
+static void __init fdt_bus_default_count_cells(const void *blob, int parentoffset,
+					       int *addrc, int *sizec)
+{
+	const __be32 *prop;
+
+	if (addrc) {
+		prop = fdt_getprop(blob, parentoffset, "#address-cells", NULL);
+		if (prop)
+			*addrc = be32_to_cpup(prop);
+		else
+			*addrc = -1;
+	}
+
+	if (sizec) {
+		prop = fdt_getprop(blob, parentoffset, "#size-cells", NULL);
+		if (prop)
+			*sizec = be32_to_cpup(prop);
+		else
+			*sizec = -1;
+	}
+}
+
+static u64 __init fdt_bus_default_map(__be32 *addr, const __be32 *range,
+				      int na, int ns, int pna)
+{
+	u64 cp, s, da;
+
+	cp = of_read_number(range, na);
+	s  = of_read_number(range + na + pna, ns);
+	da = of_read_number(addr, na);
+
+	pr_debug("default map, cp=%llx, s=%llx, da=%llx\n",
+	    cp, s, da);
+
+	if (da < cp || da >= (cp + s))
+		return OF_BAD_ADDR;
+	return da - cp;
+}
+
+static int __init fdt_bus_default_translate(__be32 *addr, u64 offset, int na)
+{
+	u64 a = of_read_number(addr, na);
+	memset(addr, 0, na * 4);
+	a += offset;
+	if (na > 1)
+		addr[na - 2] = cpu_to_fdt32(a >> 32);
+	addr[na - 1] = cpu_to_fdt32(a & 0xffffffffu);
+
+	return 0;
+}
+
+/* Array of bus specific translators */
+static const struct of_bus of_busses[] __initconst = {
+	/* Default */
+	{
+		.count_cells = fdt_bus_default_count_cells,
+		.map = fdt_bus_default_map,
+		.translate = fdt_bus_default_translate,
+	},
+};
+
+static int __init fdt_translate_one(const void *blob, int parent,
+				    const struct of_bus *bus,
+				    const struct of_bus *pbus, __be32 *addr,
+				    int na, int ns, int pna, const char *rprop)
+{
+	const __be32 *ranges;
+	int rlen;
+	int rone;
+	u64 offset = OF_BAD_ADDR;
+
+	ranges = fdt_getprop(blob, parent, rprop, &rlen);
+	if (!ranges)
+		return 1;
+	if (rlen == 0) {
+		offset = of_read_number(addr, na);
+		memset(addr, 0, pna * 4);
+		pr_debug("empty ranges, 1:1 translation\n");
+		goto finish;
+	}
+
+	pr_debug("walking ranges...\n");
+
+	/* Now walk through the ranges */
+	rlen /= 4;
+	rone = na + pna + ns;
+	for (; rlen >= rone; rlen -= rone, ranges += rone) {
+		offset = bus->map(addr, ranges, na, ns, pna);
+		if (offset != OF_BAD_ADDR)
+			break;
+	}
+	if (offset == OF_BAD_ADDR) {
+		pr_debug("not found !\n");
+		return 1;
+	}
+	memcpy(addr, ranges + na, 4 * pna);
+
+ finish:
+	of_dump_addr("parent translation for:", addr, pna);
+	pr_debug("with offset: %llx\n", offset);
+
+	/* Translate it into parent bus space */
+	return pbus->translate(addr, offset, pna);
+}
+
+/*
+ * Translate an address from the device-tree into a CPU physical address,
+ * this walks up the tree and applies the various bus mappings on the
+ * way.
+ *
+ * Note: We consider that crossing any level with #size-cells == 0 to mean
+ * that translation is impossible (that is we are not dealing with a value
+ * that can be mapped to a cpu physical address). This is not really specified
+ * that way, but this is traditionally the way IBM at least do things
+ */
+static u64 __init fdt_translate_address(const void *blob, int node_offset)
+{
+	int parent, len;
+	const struct of_bus *bus, *pbus;
+	const __be32 *reg;
+	__be32 addr[OF_MAX_ADDR_CELLS];
+	int na, ns, pna, pns;
+	u64 result = OF_BAD_ADDR;
+
+	pr_debug("** translation for device %s **\n",
+		 fdt_get_name(blob, node_offset, NULL));
+
+	reg = fdt_getprop(blob, node_offset, "reg", &len);
+	if (!reg) {
+		pr_err("warning: device tree node '%s' has no address.\n",
+			fdt_get_name(blob, node_offset, NULL));
+		goto bail;
+	}
+
+	/* Get parent & match bus type */
+	parent = fdt_parent_offset(blob, node_offset);
+	if (parent < 0)
+		goto bail;
+	bus = &of_busses[0];
+
+	/* Cound address cells & copy address locally */
+	bus->count_cells(blob, parent, &na, &ns);
+	if (!OF_CHECK_COUNTS(na, ns)) {
+		pr_err("Bad cell count for %s\n",
+		       fdt_get_name(blob, node_offset, NULL));
+		goto bail;
+	}
+	memcpy(addr, reg, na * 4);
+
+	pr_debug("bus (na=%d, ns=%d) on %s\n",
+		 na, ns, fdt_get_name(blob, parent, NULL));
+	of_dump_addr("translating address:", addr, na);
+
+	/* Translate */
+	for (;;) {
+		/* Switch to parent bus */
+		node_offset = parent;
+		parent = fdt_parent_offset(blob, node_offset);
+
+		/* If root, we have finished */
+		if (parent < 0) {
+			pr_debug("reached root node\n");
+			result = of_read_number(addr, na);
+			break;
+		}
+
+		/* Get new parent bus and counts */
+		pbus = &of_busses[0];
+		pbus->count_cells(blob, parent, &pna, &pns);
+		if (!OF_CHECK_COUNTS(pna, pns)) {
+			pr_err("Bad cell count for %s\n",
+				fdt_get_name(blob, node_offset, NULL));
+			break;
+		}
+
+		pr_debug("parent bus (na=%d, ns=%d) on %s\n",
+			 pna, pns, fdt_get_name(blob, parent, NULL));
+
+		/* Apply bus translation */
+		if (fdt_translate_one(blob, node_offset, bus, pbus,
+					addr, na, ns, pna, "ranges"))
+			break;
+
+		/* Complete the move up one level */
+		na = pna;
+		ns = pns;
+		bus = pbus;
+
+		of_dump_addr("one level translation:", addr, na);
+	}
+ bail:
+	return result;
+}
+
+/**
+ * of_flat_dt_translate_address - translate DT addr into CPU phys addr
+ * @node: node in the flat blob
+ */
+u64 __init of_flat_dt_translate_address(unsigned long node)
+{
+	return fdt_translate_address(initial_boot_params, node);
+}