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, 164 insertions, 0 deletions

diff --git a/drivers/iommu/iommu-debug-pagealloc.c b/drivers/iommu/iommu-debug-pagealloc.c
new file mode 100644
index 000000000..80164df5b
--- /dev/null
+++ b/drivers/iommu/iommu-debug-pagealloc.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 - Google Inc
+ * Author: Mostafa Saleh <smostafa@google.com>
+ * IOMMU API debug page alloc sanitizer
+ */
+#include <linux/atomic.h>
+#include <linux/iommu.h>
+#include <linux/iommu-debug-pagealloc.h>
+#include <linux/kernel.h>
+#include <linux/page_ext.h>
+#include <linux/page_owner.h>
+
+#include "iommu-priv.h"
+
+static bool needed;
+DEFINE_STATIC_KEY_FALSE(iommu_debug_initialized);
+
+struct iommu_debug_metadata {
+	atomic_t ref;
+};
+
+static __init bool need_iommu_debug(void)
+{
+	return needed;
+}
+
+struct page_ext_operations page_iommu_debug_ops = {
+	.size = sizeof(struct iommu_debug_metadata),
+	.need = need_iommu_debug,
+};
+
+static struct iommu_debug_metadata *get_iommu_data(struct page_ext *page_ext)
+{
+	return page_ext_data(page_ext, &page_iommu_debug_ops);
+}
+
+static void iommu_debug_inc_page(phys_addr_t phys)
+{
+	struct page_ext *page_ext = page_ext_from_phys(phys);
+	struct iommu_debug_metadata *d;
+
+	if (!page_ext)
+		return;
+
+	d = get_iommu_data(page_ext);
+	WARN_ON(atomic_inc_return_relaxed(&d->ref) <= 0);
+	page_ext_put(page_ext);
+}
+
+static void iommu_debug_dec_page(phys_addr_t phys)
+{
+	struct page_ext *page_ext = page_ext_from_phys(phys);
+	struct iommu_debug_metadata *d;
+
+	if (!page_ext)
+		return;
+
+	d = get_iommu_data(page_ext);
+	WARN_ON(atomic_dec_return_relaxed(&d->ref) < 0);
+	page_ext_put(page_ext);
+}
+
+/*
+ * IOMMU page size doesn't have to match the CPU page size. So, we use
+ * the smallest IOMMU page size to refcount the pages in the vmemmap.
+ * That is important as both map and unmap has to use the same page size
+ * to update the refcount to avoid double counting the same page.
+ * And as we can't know from iommu_unmap() what was the original page size
+ * used for map, we just use the minimum supported one for both.
+ */
+static size_t iommu_debug_page_size(struct iommu_domain *domain)
+{
+	return 1UL << __ffs(domain->pgsize_bitmap);
+}
+
+static bool iommu_debug_page_count(const struct page *page)
+{
+	unsigned int ref;
+	struct page_ext *page_ext = page_ext_get(page);
+	struct iommu_debug_metadata *d = get_iommu_data(page_ext);
+
+	ref = atomic_read(&d->ref);
+	page_ext_put(page_ext);
+	return ref != 0;
+}
+
+void __iommu_debug_check_unmapped(const struct page *page, int numpages)
+{
+	while (numpages--) {
+		if (WARN_ON(iommu_debug_page_count(page))) {
+			pr_warn("iommu: Detected page leak!\n");
+			dump_page_owner(page);
+		}
+		page++;
+	}
+}
+
+void __iommu_debug_map(struct iommu_domain *domain, phys_addr_t phys, size_t size)
+{
+	size_t off, end;
+	size_t page_size = iommu_debug_page_size(domain);
+
+	if (WARN_ON(!phys || check_add_overflow(phys, size, &end)))
+		return;
+
+	for (off = 0 ; off < size ; off += page_size)
+		iommu_debug_inc_page(phys + off);
+}
+
+static void __iommu_debug_update_iova(struct iommu_domain *domain,
+				      unsigned long iova, size_t size, bool inc)
+{
+	size_t off, end;
+	size_t page_size = iommu_debug_page_size(domain);
+
+	if (WARN_ON(check_add_overflow(iova, size, &end)))
+		return;
+
+	for (off = 0 ; off < size ; off += page_size) {
+		phys_addr_t phys = iommu_iova_to_phys(domain, iova + off);
+
+		if (!phys)
+			continue;
+
+		if (inc)
+			iommu_debug_inc_page(phys);
+		else
+			iommu_debug_dec_page(phys);
+	}
+}
+
+void __iommu_debug_unmap_begin(struct iommu_domain *domain,
+			       unsigned long iova, size_t size)
+{
+	__iommu_debug_update_iova(domain, iova, size, false);
+}
+
+void __iommu_debug_unmap_end(struct iommu_domain *domain,
+			     unsigned long iova, size_t size,
+			     size_t unmapped)
+{
+	if ((unmapped == size) || WARN_ON_ONCE(unmapped > size))
+		return;
+
+	/* If unmap failed, re-increment the refcount. */
+	__iommu_debug_update_iova(domain, iova + unmapped,
+				  size - unmapped, true);
+}
+
+void iommu_debug_init(void)
+{
+	if (!needed)
+		return;
+
+	pr_info("iommu: Debugging page allocations, expect overhead or disable iommu.debug_pagealloc");
+	static_branch_enable(&iommu_debug_initialized);
+}
+
+static int __init iommu_debug_pagealloc(char *str)
+{
+	return kstrtobool(str, &needed);
+}
+early_param("iommu.debug_pagealloc", iommu_debug_pagealloc);