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, 281 insertions, 0 deletions

diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
new file mode 100644
index 000000000..bfd8b03b0
--- /dev/null
+++ b/drivers/clk/at91/clk-programmable.c
@@ -0,0 +1,281 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Copyright (C) 2013 Boris BREZILLON <b.brezillon@overkiz.com>
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/clkdev.h>
+#include <linux/clk/at91_pmc.h>
+#include <linux/of.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+
+#include "pmc.h"
+
+#define PROG_ID_MAX		7
+
+#define PROG_STATUS_MASK(id)	(1 << ((id) + 8))
+#define PROG_PRES(layout, pckr)	((pckr >> layout->pres_shift) & layout->pres_mask)
+#define PROG_MAX_RM9200_CSS	3
+
+struct clk_programmable {
+	struct clk_hw hw;
+	struct regmap *regmap;
+	u32 *mux_table;
+	u8 id;
+	const struct clk_programmable_layout *layout;
+	struct at91_clk_pms pms;
+};
+
+#define to_clk_programmable(hw) container_of(hw, struct clk_programmable, hw)
+
+static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw,
+						  unsigned long parent_rate)
+{
+	struct clk_programmable *prog = to_clk_programmable(hw);
+	const struct clk_programmable_layout *layout = prog->layout;
+	unsigned int pckr;
+	unsigned long rate;
+
+	regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
+
+	if (layout->is_pres_direct)
+		rate = parent_rate / (PROG_PRES(layout, pckr) + 1);
+	else
+		rate = parent_rate >> PROG_PRES(layout, pckr);
+
+	return rate;
+}
+
+static int clk_programmable_determine_rate(struct clk_hw *hw,
+					   struct clk_rate_request *req)
+{
+	struct clk_programmable *prog = to_clk_programmable(hw);
+	const struct clk_programmable_layout *layout = prog->layout;
+	struct clk_hw *parent;
+	long best_rate = -EINVAL;
+	unsigned long parent_rate;
+	unsigned long tmp_rate = 0;
+	int shift;
+	int i;
+
+	for (i = 0; i < clk_hw_get_num_parents(hw); i++) {
+		parent = clk_hw_get_parent_by_index(hw, i);
+		if (!parent)
+			continue;
+
+		parent_rate = clk_hw_get_rate(parent);
+		if (layout->is_pres_direct) {
+			for (shift = 0; shift <= layout->pres_mask; shift++) {
+				tmp_rate = parent_rate / (shift + 1);
+				if (tmp_rate <= req->rate)
+					break;
+			}
+		} else {
+			for (shift = 0; shift < layout->pres_mask; shift++) {
+				tmp_rate = parent_rate >> shift;
+				if (tmp_rate <= req->rate)
+					break;
+			}
+		}
+
+		if (tmp_rate > req->rate)
+			continue;
+
+		if (best_rate < 0 ||
+		    (req->rate - tmp_rate) < (req->rate - best_rate)) {
+			best_rate = tmp_rate;
+			req->best_parent_rate = parent_rate;
+			req->best_parent_hw = parent;
+		}
+
+		if (!best_rate)
+			break;
+	}
+
+	if (best_rate < 0)
+		return best_rate;
+
+	req->rate = best_rate;
+	return 0;
+}
+
+static int clk_programmable_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_programmable *prog = to_clk_programmable(hw);
+	const struct clk_programmable_layout *layout = prog->layout;
+	unsigned int mask = layout->css_mask;
+	unsigned int pckr = index;
+
+	if (layout->have_slck_mck)
+		mask |= AT91_PMC_CSSMCK_MCK;
+
+	if (prog->mux_table)
+		pckr = clk_mux_index_to_val(prog->mux_table, 0, index);
+
+	if (index > layout->css_mask) {
+		if (index > PROG_MAX_RM9200_CSS && !layout->have_slck_mck)
+			return -EINVAL;
+
+		pckr |= AT91_PMC_CSSMCK_MCK;
+	}
+
+	regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id), mask, pckr);
+
+	return 0;
+}
+
+static u8 clk_programmable_get_parent(struct clk_hw *hw)
+{
+	struct clk_programmable *prog = to_clk_programmable(hw);
+	const struct clk_programmable_layout *layout = prog->layout;
+	unsigned int pckr;
+	u8 ret;
+
+	regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
+
+	ret = pckr & layout->css_mask;
+
+	if (layout->have_slck_mck && (pckr & AT91_PMC_CSSMCK_MCK) && !ret)
+		ret = PROG_MAX_RM9200_CSS + 1;
+
+	if (prog->mux_table)
+		ret = clk_mux_val_to_index(&prog->hw, prog->mux_table, 0, ret);
+
+	return ret;
+}
+
+static int clk_programmable_set_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long parent_rate)
+{
+	struct clk_programmable *prog = to_clk_programmable(hw);
+	const struct clk_programmable_layout *layout = prog->layout;
+	unsigned long div = parent_rate / rate;
+	int shift = 0;
+
+	if (!div)
+		return -EINVAL;
+
+	if (layout->is_pres_direct) {
+		shift = div - 1;
+
+		if (shift > layout->pres_mask)
+			return -EINVAL;
+	} else {
+		shift = fls(div) - 1;
+
+		if (div != (1 << shift))
+			return -EINVAL;
+
+		if (shift >= layout->pres_mask)
+			return -EINVAL;
+	}
+
+	regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id),
+			   layout->pres_mask << layout->pres_shift,
+			   shift << layout->pres_shift);
+
+	return 0;
+}
+
+static int clk_programmable_save_context(struct clk_hw *hw)
+{
+	struct clk_programmable *prog = to_clk_programmable(hw);
+	struct clk_hw *parent_hw = clk_hw_get_parent(hw);
+
+	prog->pms.parent = clk_programmable_get_parent(hw);
+	prog->pms.parent_rate = clk_hw_get_rate(parent_hw);
+	prog->pms.rate = clk_programmable_recalc_rate(hw, prog->pms.parent_rate);
+
+	return 0;
+}
+
+static void clk_programmable_restore_context(struct clk_hw *hw)
+{
+	struct clk_programmable *prog = to_clk_programmable(hw);
+	int ret;
+
+	ret = clk_programmable_set_parent(hw, prog->pms.parent);
+	if (ret)
+		return;
+
+	clk_programmable_set_rate(hw, prog->pms.rate, prog->pms.parent_rate);
+}
+
+static const struct clk_ops programmable_ops = {
+	.recalc_rate = clk_programmable_recalc_rate,
+	.determine_rate = clk_programmable_determine_rate,
+	.get_parent = clk_programmable_get_parent,
+	.set_parent = clk_programmable_set_parent,
+	.set_rate = clk_programmable_set_rate,
+	.save_context = clk_programmable_save_context,
+	.restore_context = clk_programmable_restore_context,
+};
+
+struct clk_hw * __init
+at91_clk_register_programmable(struct regmap *regmap,
+			       const char *name, const char **parent_names,
+			       struct clk_hw **parent_hws, u8 num_parents, u8 id,
+			       const struct clk_programmable_layout *layout,
+			       u32 *mux_table)
+{
+	struct clk_programmable *prog;
+	struct clk_hw *hw;
+	struct clk_init_data init = {};
+	int ret;
+
+	if (id > PROG_ID_MAX || !(parent_names || parent_hws))
+		return ERR_PTR(-EINVAL);
+
+	prog = kzalloc_obj(*prog);
+	if (!prog)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &programmable_ops;
+	if (parent_hws)
+		init.parent_hws = (const struct clk_hw **)parent_hws;
+	else
+		init.parent_names = parent_names;
+	init.num_parents = num_parents;
+	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE;
+
+	prog->id = id;
+	prog->layout = layout;
+	prog->hw.init = &init;
+	prog->regmap = regmap;
+	prog->mux_table = mux_table;
+
+	hw = &prog->hw;
+	ret = clk_hw_register(NULL, &prog->hw);
+	if (ret) {
+		kfree(prog);
+		hw = ERR_PTR(ret);
+	}
+
+	return hw;
+}
+
+const struct clk_programmable_layout at91rm9200_programmable_layout = {
+	.pres_mask = 0x7,
+	.pres_shift = 2,
+	.css_mask = 0x3,
+	.have_slck_mck = 0,
+	.is_pres_direct = 0,
+};
+
+const struct clk_programmable_layout at91sam9g45_programmable_layout = {
+	.pres_mask = 0x7,
+	.pres_shift = 2,
+	.css_mask = 0x3,
+	.have_slck_mck = 1,
+	.is_pres_direct = 0,
+};
+
+const struct clk_programmable_layout at91sam9x5_programmable_layout = {
+	.pres_mask = 0x7,
+	.pres_shift = 4,
+	.css_mask = 0x7,
+	.have_slck_mck = 0,
+	.is_pres_direct = 0,
+};