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, 376 insertions, 0 deletions

diff --git a/tools/testing/shared/linux.c b/tools/testing/shared/linux.c
new file mode 100644
index 000000000..e0a0693df
--- /dev/null
+++ b/tools/testing/shared/linux.c
@@ -0,0 +1,376 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdlib.h>
+#include <string.h>
+#include <malloc.h>
+#include <pthread.h>
+#include <unistd.h>
+#include <assert.h>
+
+#include <linux/gfp.h>
+#include <linux/poison.h>
+#include <linux/slab.h>
+#include <linux/radix-tree.h>
+#include <urcu/uatomic.h>
+
+int nr_allocated;
+int preempt_count;
+int test_verbose;
+
+void kmem_cache_set_callback(struct kmem_cache *cachep, void (*callback)(void *))
+{
+	cachep->callback = callback;
+}
+
+void kmem_cache_set_private(struct kmem_cache *cachep, void *private)
+{
+	cachep->private = private;
+}
+
+void kmem_cache_set_non_kernel(struct kmem_cache *cachep, unsigned int val)
+{
+	cachep->non_kernel = val;
+}
+
+unsigned long kmem_cache_get_alloc(struct kmem_cache *cachep)
+{
+	return cachep->size * cachep->nr_allocated;
+}
+
+unsigned long kmem_cache_nr_allocated(struct kmem_cache *cachep)
+{
+	return cachep->nr_allocated;
+}
+
+unsigned long kmem_cache_nr_tallocated(struct kmem_cache *cachep)
+{
+	return cachep->nr_tallocated;
+}
+
+void kmem_cache_zero_nr_tallocated(struct kmem_cache *cachep)
+{
+	cachep->nr_tallocated = 0;
+}
+
+void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
+		int gfp)
+{
+	void *p;
+
+	if (cachep->exec_callback) {
+		if (cachep->callback)
+			cachep->callback(cachep->private);
+		cachep->exec_callback = false;
+	}
+
+	if (!(gfp & __GFP_DIRECT_RECLAIM)) {
+		if (!cachep->non_kernel) {
+			if (cachep->callback)
+				cachep->exec_callback = true;
+			return NULL;
+		}
+
+		cachep->non_kernel--;
+	}
+
+	pthread_mutex_lock(&cachep->lock);
+	if (cachep->nr_objs) {
+		struct radix_tree_node *node = cachep->objs;
+		cachep->nr_objs--;
+		cachep->objs = node->parent;
+		pthread_mutex_unlock(&cachep->lock);
+		node->parent = NULL;
+		p = node;
+	} else {
+		pthread_mutex_unlock(&cachep->lock);
+		if (cachep->align) {
+			if (posix_memalign(&p, cachep->align, cachep->size) < 0)
+				return NULL;
+		} else {
+			p = malloc(cachep->size);
+		}
+
+		if (cachep->ctor)
+			cachep->ctor(p);
+		else if (gfp & __GFP_ZERO)
+			memset(p, 0, cachep->size);
+	}
+
+	uatomic_inc(&cachep->nr_allocated);
+	uatomic_inc(&nr_allocated);
+	uatomic_inc(&cachep->nr_tallocated);
+	if (kmalloc_verbose)
+		printf("Allocating %p from slab\n", p);
+	return p;
+}
+
+void __kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
+{
+	assert(objp);
+	if (cachep->nr_objs > 10 || cachep->align) {
+		memset(objp, POISON_FREE, cachep->size);
+		free(objp);
+	} else {
+		struct radix_tree_node *node = objp;
+		cachep->nr_objs++;
+		node->parent = cachep->objs;
+		cachep->objs = node;
+	}
+}
+
+void kmem_cache_free_locked(struct kmem_cache *cachep, void *objp)
+{
+	uatomic_dec(&nr_allocated);
+	uatomic_dec(&cachep->nr_allocated);
+	if (kmalloc_verbose)
+		printf("Freeing %p to slab\n", objp);
+	__kmem_cache_free_locked(cachep, objp);
+}
+
+void kmem_cache_free(struct kmem_cache *cachep, void *objp)
+{
+	pthread_mutex_lock(&cachep->lock);
+	kmem_cache_free_locked(cachep, objp);
+	pthread_mutex_unlock(&cachep->lock);
+}
+
+void kmem_cache_free_bulk(struct kmem_cache *cachep, size_t size, void **list)
+{
+	if (kmalloc_verbose)
+		pr_debug("Bulk free %p[0-%zu]\n", list, size - 1);
+
+	if (cachep->exec_callback) {
+		if (cachep->callback)
+			cachep->callback(cachep->private);
+		cachep->exec_callback = false;
+	}
+
+	pthread_mutex_lock(&cachep->lock);
+	for (int i = 0; i < size; i++)
+		kmem_cache_free_locked(cachep, list[i]);
+	pthread_mutex_unlock(&cachep->lock);
+}
+
+void kmem_cache_shrink(struct kmem_cache *cachep)
+{
+}
+
+bool kmem_cache_alloc_bulk(struct kmem_cache *cachep, gfp_t gfp, size_t size,
+			  void **p)
+{
+	size_t i;
+
+	if (kmalloc_verbose)
+		pr_debug("Bulk alloc %zu\n", size);
+
+	pthread_mutex_lock(&cachep->lock);
+	if (cachep->nr_objs >= size) {
+		struct radix_tree_node *node;
+
+		for (i = 0; i < size; i++) {
+			if (!(gfp & __GFP_DIRECT_RECLAIM)) {
+				if (!cachep->non_kernel)
+					break;
+				cachep->non_kernel--;
+			}
+
+			node = cachep->objs;
+			cachep->nr_objs--;
+			cachep->objs = node->parent;
+			p[i] = node;
+			node->parent = NULL;
+		}
+		pthread_mutex_unlock(&cachep->lock);
+	} else {
+		pthread_mutex_unlock(&cachep->lock);
+		for (i = 0; i < size; i++) {
+			if (!(gfp & __GFP_DIRECT_RECLAIM)) {
+				if (!cachep->non_kernel)
+					break;
+				cachep->non_kernel--;
+			}
+
+			if (cachep->align) {
+				if (posix_memalign(&p[i], cachep->align,
+					       cachep->size) < 0)
+					break;
+			} else {
+				p[i] = malloc(cachep->size);
+				if (!p[i])
+					break;
+			}
+			if (cachep->ctor)
+				cachep->ctor(p[i]);
+			else if (gfp & __GFP_ZERO)
+				memset(p[i], 0, cachep->size);
+		}
+	}
+
+	if (i < size) {
+		size = i;
+		pthread_mutex_lock(&cachep->lock);
+		for (i = 0; i < size; i++)
+			__kmem_cache_free_locked(cachep, p[i]);
+		pthread_mutex_unlock(&cachep->lock);
+		if (cachep->callback)
+			cachep->exec_callback = true;
+		return false;
+	}
+
+	for (i = 0; i < size; i++) {
+		uatomic_inc(&nr_allocated);
+		uatomic_inc(&cachep->nr_allocated);
+		uatomic_inc(&cachep->nr_tallocated);
+		if (kmalloc_verbose)
+			printf("Allocating %p from slab\n", p[i]);
+	}
+
+	return true;
+}
+
+struct kmem_cache *
+__kmem_cache_create_args(const char *name, unsigned int size,
+			  struct kmem_cache_args *args,
+			  unsigned int flags)
+{
+	struct kmem_cache *ret = malloc(sizeof(*ret));
+
+	pthread_mutex_init(&ret->lock, NULL);
+	ret->size = size;
+	ret->align = args->align;
+	ret->sheaf_capacity = args->sheaf_capacity;
+	ret->nr_objs = 0;
+	ret->nr_allocated = 0;
+	ret->nr_tallocated = 0;
+	ret->objs = NULL;
+	ret->ctor = args->ctor;
+	ret->non_kernel = 0;
+	ret->exec_callback = false;
+	ret->callback = NULL;
+	ret->private = NULL;
+
+	return ret;
+}
+
+struct slab_sheaf *
+kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size)
+{
+	struct slab_sheaf *sheaf;
+	unsigned int capacity;
+
+	if (s->exec_callback) {
+		if (s->callback)
+			s->callback(s->private);
+		s->exec_callback = false;
+	}
+
+	capacity = max(size, s->sheaf_capacity);
+
+	sheaf = calloc(1, sizeof(*sheaf) + sizeof(void *) * capacity);
+	if (!sheaf)
+		return NULL;
+
+	sheaf->cache = s;
+	sheaf->capacity = capacity;
+	sheaf->size = size;
+	if (!kmem_cache_alloc_bulk(s, gfp, size, sheaf->objects)) {
+		free(sheaf);
+		return NULL;
+	}
+
+	return sheaf;
+}
+
+int kmem_cache_refill_sheaf(struct kmem_cache *s, gfp_t gfp,
+		 struct slab_sheaf **sheafp, unsigned int size)
+{
+	struct slab_sheaf *sheaf = *sheafp;
+
+	if (sheaf->size >= size)
+		return 0;
+
+	if (size > sheaf->capacity) {
+		sheaf = kmem_cache_prefill_sheaf(s, gfp, size);
+		if (!sheaf)
+			return -ENOMEM;
+
+		kmem_cache_return_sheaf(s, gfp, *sheafp);
+		*sheafp = sheaf;
+		return 0;
+	}
+
+	if (!kmem_cache_alloc_bulk(s, gfp, size - sheaf->size,
+			&sheaf->objects[sheaf->size]))
+		return -ENOMEM;
+	sheaf->size = size;
+	return 0;
+}
+
+void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp,
+		 struct slab_sheaf *sheaf)
+{
+	if (sheaf->size)
+		kmem_cache_free_bulk(s, sheaf->size, &sheaf->objects[0]);
+
+	free(sheaf);
+}
+
+void *
+kmem_cache_alloc_from_sheaf(struct kmem_cache *s, gfp_t gfp,
+		struct slab_sheaf *sheaf)
+{
+	void *obj;
+
+	if (sheaf->size == 0) {
+		printf("Nothing left in sheaf!\n");
+		return NULL;
+	}
+
+	obj = sheaf->objects[--sheaf->size];
+	sheaf->objects[sheaf->size] = NULL;
+
+	return obj;
+}
+
+/*
+ * Test the test infrastructure for kem_cache_alloc/free and bulk counterparts.
+ */
+void test_kmem_cache_bulk(void)
+{
+	int i;
+	void *list[12];
+	static struct kmem_cache *test_cache, *test_cache2;
+
+	/*
+	 * Testing the bulk allocators without aligned kmem_cache to force the
+	 * bulk alloc/free to reuse
+	 */
+	test_cache = kmem_cache_create("test_cache", 256, 0, SLAB_PANIC, NULL);
+
+	for (i = 0; i < 5; i++)
+		list[i] = kmem_cache_alloc(test_cache, __GFP_DIRECT_RECLAIM);
+
+	for (i = 0; i < 5; i++)
+		kmem_cache_free(test_cache, list[i]);
+	assert(test_cache->nr_objs == 5);
+
+	kmem_cache_alloc_bulk(test_cache, __GFP_DIRECT_RECLAIM, 5, list);
+	kmem_cache_free_bulk(test_cache, 5, list);
+
+	for (i = 0; i < 12 ; i++)
+		list[i] = kmem_cache_alloc(test_cache, __GFP_DIRECT_RECLAIM);
+
+	for (i = 0; i < 12; i++)
+		kmem_cache_free(test_cache, list[i]);
+
+	/* The last free will not be kept around */
+	assert(test_cache->nr_objs == 11);
+
+	/* Aligned caches will immediately free */
+	test_cache2 = kmem_cache_create("test_cache2", 128, 128, SLAB_PANIC, NULL);
+
+	kmem_cache_alloc_bulk(test_cache2, __GFP_DIRECT_RECLAIM, 10, list);
+	kmem_cache_free_bulk(test_cache2, 10, list);
+	assert(!test_cache2->nr_objs);
+
+
+}