@@ -519,7 +519,6 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key);
int bpf_trampoline_link_prog(struct bpf_prog *prog);
int bpf_trampoline_unlink_prog(struct bpf_prog *prog);
void bpf_trampoline_put(struct bpf_trampoline *tr);
-void *bpf_jit_alloc_exec_page(void);
#define BPF_DISPATCHER_INIT(name) { \
.mutex = __MUTEX_INITIALIZER(name.mutex), \
.func = &name##func, \
@@ -551,6 +550,13 @@ void *bpf_jit_alloc_exec_page(void);
#define BPF_DISPATCHER_PTR(name) (&name)
void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
struct bpf_prog *to);
+struct bpf_image {
+ struct latch_tree_node tnode;
+ unsigned char data[];
+};
+#define BPF_IMAGE_SIZE (PAGE_SIZE - sizeof(struct bpf_image))
+bool is_bpf_image_address(unsigned long address);
+void *bpf_image_alloc(void);
#else
static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
{
@@ -572,6 +578,10 @@ static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d,
struct bpf_prog *from,
struct bpf_prog *to) {}
+static inline bool is_bpf_image_address(unsigned long address)
+{
+ return false;
+}
#endif
struct bpf_func_info_aux {
@@ -113,7 +113,7 @@ static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs)
noff = 0;
} else {
old = d->image + d->image_off;
- noff = d->image_off ^ (PAGE_SIZE / 2);
+ noff = d->image_off ^ (BPF_IMAGE_SIZE / 2);
}
new = d->num_progs ? d->image + noff : NULL;
@@ -140,7 +140,7 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
mutex_lock(&d->mutex);
if (!d->image) {
- d->image = bpf_jit_alloc_exec_page();
+ d->image = bpf_image_alloc();
if (!d->image)
goto out;
}
@@ -4,6 +4,7 @@
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/ftrace.h>
+#include <linux/rbtree_latch.h>
/* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */
#define TRAMPOLINE_HASH_BITS 10
@@ -14,7 +15,12 @@ static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE];
/* serializes access to trampoline_table */
static DEFINE_MUTEX(trampoline_mutex);
-void *bpf_jit_alloc_exec_page(void)
+static struct latch_tree_root image_tree __cacheline_aligned;
+
+/* serializes access to image_tree */
+static DEFINE_MUTEX(image_mutex);
+
+static void *bpf_jit_alloc_exec_page(void)
{
void *image;
@@ -30,6 +36,68 @@ void *bpf_jit_alloc_exec_page(void)
return image;
}
+static __always_inline bool image_tree_less(struct latch_tree_node *a,
+ struct latch_tree_node *b)
+{
+ struct bpf_image *ia = container_of(a, struct bpf_image, tnode);
+ struct bpf_image *ib = container_of(b, struct bpf_image, tnode);
+
+ return ia < ib;
+}
+
+static __always_inline int image_tree_comp(void *addr, struct latch_tree_node *n)
+{
+ void *image = container_of(n, struct bpf_image, tnode);
+
+ if (addr < image)
+ return -1;
+ if (addr >= image + PAGE_SIZE)
+ return 1;
+
+ return 0;
+}
+
+static const struct latch_tree_ops image_tree_ops = {
+ .less = image_tree_less,
+ .comp = image_tree_comp,
+};
+
+void *bpf_image_alloc(void)
+{
+ struct bpf_image *image;
+
+ image = bpf_jit_alloc_exec_page();
+ if (!image)
+ return NULL;
+
+ mutex_lock(&image_mutex);
+ latch_tree_insert(&image->tnode, &image_tree, &image_tree_ops);
+ mutex_unlock(&image_mutex);
+ return image->data;
+}
+
+void bpf_image_delete(void *ptr)
+{
+ struct bpf_image *image = container_of(ptr, struct bpf_image, data);
+
+ mutex_lock(&image_mutex);
+ latch_tree_erase(&image->tnode, &image_tree, &image_tree_ops);
+ synchronize_rcu();
+ bpf_jit_free_exec(image);
+ mutex_unlock(&image_mutex);
+}
+
+bool is_bpf_image_address(unsigned long addr)
+{
+ bool ret;
+
+ rcu_read_lock();
+ ret = latch_tree_find((void *) addr, &image_tree, &image_tree_ops) != NULL;
+ rcu_read_unlock();
+
+ return ret;
+}
+
struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
{
struct bpf_trampoline *tr;
@@ -50,7 +118,7 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
goto out;
/* is_root was checked earlier. No need for bpf_jit_charge_modmem() */
- image = bpf_jit_alloc_exec_page();
+ image = bpf_image_alloc();
if (!image) {
kfree(tr);
tr = NULL;
@@ -125,14 +193,14 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
}
/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
- * bytes on x86. Pick a number to fit into PAGE_SIZE / 2
+ * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2
*/
#define BPF_MAX_TRAMP_PROGS 40
static int bpf_trampoline_update(struct bpf_trampoline *tr)
{
- void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2;
- void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2;
+ void *old_image = tr->image + ((tr->selector + 1) & 1) * BPF_IMAGE_SIZE/2;
+ void *new_image = tr->image + (tr->selector & 1) * BPF_IMAGE_SIZE/2;
struct bpf_prog *progs_to_run[BPF_MAX_TRAMP_PROGS];
int fentry_cnt = tr->progs_cnt[BPF_TRAMP_FENTRY];
int fexit_cnt = tr->progs_cnt[BPF_TRAMP_FEXIT];
@@ -160,7 +228,7 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
if (fexit_cnt)
flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
- err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
+ err = arch_prepare_bpf_trampoline(new_image, new_image + BPF_IMAGE_SIZE / 2,
&tr->func.model, flags,
fentry, fentry_cnt,
fexit, fexit_cnt,
@@ -251,7 +319,7 @@ void bpf_trampoline_put(struct bpf_trampoline *tr)
goto out;
if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
goto out;
- bpf_jit_free_exec(tr->image);
+ bpf_image_delete(tr->image);
hlist_del(&tr->hlist);
kfree(tr);
out:
@@ -131,8 +131,9 @@ int kernel_text_address(unsigned long addr)
* triggers a stack trace, or a WARN() that happens during
* coming back from idle, or cpu on or offlining.
*
- * is_module_text_address() as well as the kprobe slots
- * and is_bpf_text_address() require RCU to be watching.
+ * is_module_text_address() as well as the kprobe slots,
+ * is_bpf_text_address() and is_bpf_image_address require
+ * RCU to be watching.
*/
no_rcu = !rcu_is_watching();
@@ -148,6 +149,8 @@ int kernel_text_address(unsigned long addr)
goto out;
if (is_bpf_text_address(addr))
goto out;
+ if (is_bpf_image_address(addr))
+ goto out;
ret = 0;
out:
if (no_rcu)
When unwinding the stack we need to identify each address to successfully continue. Adding latch tree to keep trampolines for quick lookup during the unwind. The patch uses first 48 bytes for latch tree node, leaving 4048 bytes from the rest of the page for trampoline or dispatcher generated code. It's still enough not to affect trampoline and dispatcher progs maximum counts. Signed-off-by: Jiri Olsa <jolsa@kernel.org> --- include/linux/bpf.h | 12 +++++- kernel/bpf/dispatcher.c | 4 +- kernel/bpf/trampoline.c | 82 +++++++++++++++++++++++++++++++++++++---- kernel/extable.c | 7 +++- 4 files changed, 93 insertions(+), 12 deletions(-)