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, 289 insertions, 0 deletions

diff --git a/fs/proc/page.c b/fs/proc/page.c
new file mode 100644
index 000000000..260772b20
--- /dev/null
+++ b/fs/proc/page.c
@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/memblock.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/ksm.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/huge_mm.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/hugetlb.h>
+#include <linux/memremap.h>
+#include <linux/memcontrol.h>
+#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
+#include <linux/kernel-page-flags.h>
+#include <linux/uaccess.h>
+#include "internal.h"
+
+#define KPMSIZE sizeof(u64)
+#define KPMMASK (KPMSIZE - 1)
+
+enum kpage_operation {
+	KPAGE_FLAGS,
+	KPAGE_COUNT,
+	KPAGE_CGROUP,
+};
+
+static inline unsigned long get_max_dump_pfn(void)
+{
+#ifdef CONFIG_SPARSEMEM
+	/*
+	 * The memmap of early sections is completely populated and marked
+	 * online even if max_pfn does not fall on a section boundary -
+	 * pfn_to_online_page() will succeed on all pages. Allow inspecting
+	 * these memmaps.
+	 */
+	return round_up(max_pfn, PAGES_PER_SECTION);
+#else
+	return max_pfn;
+#endif
+}
+
+static u64 get_kpage_count(const struct page *page)
+{
+	struct page_snapshot ps;
+	u64 ret;
+
+	snapshot_page(&ps, page);
+
+	if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+		ret = folio_precise_page_mapcount(&ps.folio_snapshot,
+						  &ps.page_snapshot);
+	else
+		ret = folio_average_page_mapcount(&ps.folio_snapshot);
+
+	return ret;
+}
+
+static ssize_t kpage_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos,
+		enum kpage_operation op)
+{
+	const unsigned long max_dump_pfn = get_max_dump_pfn();
+	u64 __user *out = (u64 __user *)buf;
+	struct page *page;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+	u64 info;
+
+	pfn = src / KPMSIZE;
+	if (src & KPMMASK || count & KPMMASK)
+		return -EINVAL;
+	if (src >= max_dump_pfn * KPMSIZE)
+		return 0;
+	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
+
+	while (count > 0) {
+		/*
+		 * TODO: ZONE_DEVICE support requires to identify
+		 * memmaps that were actually initialized.
+		 */
+		page = pfn_to_online_page(pfn);
+
+		if (page) {
+			switch (op) {
+			case KPAGE_FLAGS:
+				info = stable_page_flags(page);
+				break;
+			case KPAGE_COUNT:
+				info = get_kpage_count(page);
+				break;
+			case KPAGE_CGROUP:
+				info = page_cgroup_ino(page);
+				break;
+			default:
+				info = 0;
+				break;
+			}
+		} else
+			info = 0;
+
+		if (put_user(info, out)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		pfn++;
+		out++;
+		count -= KPMSIZE;
+
+		cond_resched();
+	}
+
+	*ppos += (char __user *)out - buf;
+	if (!ret)
+		ret = (char __user *)out - buf;
+	return ret;
+}
+
+/* /proc/kpagecount - an array exposing page mapcounts
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page mapcount.
+ */
+static ssize_t kpagecount_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_COUNT);
+}
+
+static const struct proc_ops kpagecount_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpagecount_read,
+};
+
+
+static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
+{
+	return ((kflags >> kbit) & 1) << ubit;
+}
+
+u64 stable_page_flags(const struct page *page)
+{
+	const struct folio *folio;
+	struct page_snapshot ps;
+	unsigned long k;
+	u64 u = 0;
+
+	/*
+	 * pseudo flag: KPF_NOPAGE
+	 * it differentiates a memory hole from a page with no flags
+	 */
+	if (!page)
+		return BIT_ULL(KPF_NOPAGE);
+
+	snapshot_page(&ps, page);
+	folio = &ps.folio_snapshot;
+	k = folio->flags.f;
+
+	/*
+	 * pseudo flags for the well known (anonymous) memory mapped pages
+	 */
+	if (folio_mapped(folio))
+		u |= BIT_ULL(KPF_MMAP);
+	if (folio_test_anon(folio)) {
+		u |= BIT_ULL(KPF_ANON);
+		if (folio_test_ksm(folio))
+			u |= BIT_ULL(KPF_KSM);
+	}
+
+	/*
+	 * compound pages: export both head/tail info
+	 * they together define a compound page's start/end pos and order
+	 */
+	if (ps.idx == 0)
+		u |= kpf_copy_bit(k, KPF_COMPOUND_HEAD, PG_head);
+	else
+		u |= BIT_ULL(KPF_COMPOUND_TAIL);
+	if (folio_test_hugetlb(folio))
+		u |= BIT_ULL(KPF_HUGE);
+	else if (folio_test_large(folio) &&
+	         folio_test_large_rmappable(folio)) {
+		/* Note: we indicate any THPs here, not just PMD-sized ones */
+		u |= BIT_ULL(KPF_THP);
+	} else if (is_huge_zero_pfn(ps.pfn)) {
+		u |= BIT_ULL(KPF_ZERO_PAGE);
+		u |= BIT_ULL(KPF_THP);
+	} else if (is_zero_pfn(ps.pfn)) {
+		u |= BIT_ULL(KPF_ZERO_PAGE);
+	}
+
+	if (ps.flags & PAGE_SNAPSHOT_PG_BUDDY)
+		u |= BIT_ULL(KPF_BUDDY);
+
+	if (ps.flags & PAGE_SNAPSHOT_PG_IDLE)
+		u |= BIT_ULL(KPF_IDLE);
+
+	if (folio_test_offline(folio))
+		u |= BIT_ULL(KPF_OFFLINE);
+	if (folio_test_pgtable(folio))
+		u |= BIT_ULL(KPF_PGTABLE);
+	if (folio_test_slab(folio))
+		u |= BIT_ULL(KPF_SLAB);
+
+	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
+	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);
+	u |= kpf_copy_bit(k, KPF_UPTODATE,	PG_uptodate);
+	u |= kpf_copy_bit(k, KPF_WRITEBACK,	PG_writeback);
+
+	u |= kpf_copy_bit(k, KPF_LRU,		PG_lru);
+	u |= kpf_copy_bit(k, KPF_REFERENCED,	PG_referenced);
+	u |= kpf_copy_bit(k, KPF_ACTIVE,	PG_active);
+	u |= kpf_copy_bit(k, KPF_RECLAIM,	PG_reclaim);
+
+	if (folio_test_swapcache(folio))
+		u |= BIT_ULL(KPF_SWAPCACHE);
+
+	u |= kpf_copy_bit(k, KPF_SWAPBACKED,	PG_swapbacked);
+	u |= kpf_copy_bit(k, KPF_UNEVICTABLE,	PG_unevictable);
+	u |= kpf_copy_bit(k, KPF_MLOCKED,	PG_mlocked);
+
+#ifdef CONFIG_MEMORY_FAILURE
+	if (u & BIT_ULL(KPF_HUGE))
+		u |= kpf_copy_bit(k, KPF_HWPOISON,	PG_hwpoison);
+	else
+		u |= kpf_copy_bit(ps.page_snapshot.flags.f, KPF_HWPOISON, PG_hwpoison);
+#endif
+
+	u |= kpf_copy_bit(k, KPF_RESERVED,	PG_reserved);
+	u |= kpf_copy_bit(k, KPF_OWNER_2,	PG_owner_2);
+	u |= kpf_copy_bit(k, KPF_PRIVATE,	PG_private);
+	u |= kpf_copy_bit(k, KPF_PRIVATE_2,	PG_private_2);
+	u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE,	PG_owner_priv_1);
+	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
+#ifdef CONFIG_ARCH_USES_PG_ARCH_2
+	u |= kpf_copy_bit(k, KPF_ARCH_2,	PG_arch_2);
+#endif
+#ifdef CONFIG_ARCH_USES_PG_ARCH_3
+	u |= kpf_copy_bit(k, KPF_ARCH_3,	PG_arch_3);
+#endif
+
+	return u;
+}
+EXPORT_SYMBOL_GPL(stable_page_flags);
+
+/* /proc/kpageflags - an array exposing page flags
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page flags.
+ */
+static ssize_t kpageflags_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_FLAGS);
+}
+
+static const struct proc_ops kpageflags_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpageflags_read,
+};
+
+#ifdef CONFIG_MEMCG
+static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_CGROUP);
+}
+static const struct proc_ops kpagecgroup_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpagecgroup_read,
+};
+#endif /* CONFIG_MEMCG */
+
+static int __init proc_page_init(void)
+{
+	proc_create("kpagecount", S_IRUSR, NULL, &kpagecount_proc_ops);
+	proc_create("kpageflags", S_IRUSR, NULL, &kpageflags_proc_ops);
+#ifdef CONFIG_MEMCG
+	proc_create("kpagecgroup", S_IRUSR, NULL, &kpagecgroup_proc_ops);
+#endif
+	return 0;
+}
+fs_initcall(proc_page_init);