diff mbox series

[v2,4/6] uprobes: travers uprobe's consumer list locklessly under SRCU protection

Message ID 20240808002118.918105-5-andrii@kernel.org (mailing list archive)
State Superseded
Headers show
Series uprobes: RCU-protected hot path optimizations | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch
bpf/vmtest-bpf-PR fail merge-conflict
bpf/vmtest-bpf-VM_Test-16 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-VM_Test-17 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-VM_Test-7 pending Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-6 pending Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-18 success Logs for set-matrix
bpf/vmtest-bpf-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-VM_Test-15 pending Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-VM_Test-13 success Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc
bpf/vmtest-bpf-VM_Test-14 pending Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-VM_Test-19 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-VM_Test-8 pending Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-VM_Test-20 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-VM_Test-21 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-22 pending Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-VM_Test-23 pending Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-24 pending Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-25 pending Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-26 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-27 pending Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-28 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-29 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-31 pending Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-32 pending Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-34 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-VM_Test-35 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-36 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-38 pending Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-39 pending Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-40 pending Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-42 success Logs for x86_64-llvm-18 / veristat

Commit Message

Andrii Nakryiko Aug. 8, 2024, 12:21 a.m. UTC 
uprobe->register_rwsem is one of a few big bottlenecks to scalability of
uprobes, so we need to get rid of it to improve uprobe performance and
multi-CPU scalability.

First, we turn uprobe's consumer list to a typical doubly-linked list
and utilize existing RCU-aware helpers for traversing such lists, as
well as adding and removing elements from it.

For entry uprobes we already have SRCU protection active since before
uprobe lookup. For uretprobe we keep refcount, guaranteeing that uprobe
won't go away from under us, but we add SRCU protection around consumer
list traversal.

Lastly, to keep handler_chain()'s UPROBE_HANDLER_REMOVE handling simple,
we remember whether any removal was requested during handler calls, but
then we double-check the decision under a proper register_rwsem using
consumers' filter callbacks. Handler removal is very rare, so this extra
lock won't hurt performance, overall, but we also avoid the need for any
extra protection (e.g., seqcount locks).

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
---
 include/linux/uprobes.h |   2 +-
 kernel/events/uprobes.c | 110 +++++++++++++++++++++-------------------
 2 files changed, 60 insertions(+), 52 deletions(-)

Comments

Oleg Nesterov Aug. 8, 2024, 2:40 p.m. UTC | #1 
On 08/07, Andrii Nakryiko wrote:
>
> @@ -1127,18 +1105,30 @@ void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
>  	int err;
>  
>  	down_write(&uprobe->register_rwsem);
> -	if (WARN_ON(!consumer_del(uprobe, uc))) {
> -		err = -ENOENT;
> -	} else {
> -		err = register_for_each_vma(uprobe, NULL);
> -		/* TODO : cant unregister? schedule a worker thread */
> -		if (unlikely(err))
> -			uprobe_warn(current, "unregister, leaking uprobe");
> -	}
> +
> +	list_del_rcu(&uc->cons_node);
> +	err = register_for_each_vma(uprobe, NULL);
> +
>  	up_write(&uprobe->register_rwsem);
>  
> -	if (!err)
> -		put_uprobe(uprobe);
> +	/* TODO : cant unregister? schedule a worker thread */
> +	if (unlikely(err)) {
> +		uprobe_warn(current, "unregister, leaking uprobe");
> +		return;

Looks wrong... We can (should) skip put_uprobe(), but we can't avoid
synchronize_srcu().

The caller can free the consumer right after return. You even added
a fat comment below.

Yes, the problem will go away after you split it into nosync/sync, but
still.

Oleg.
Andrii Nakryiko Aug. 8, 2024, 5:50 p.m. UTC | #2 
On Thu, Aug 8, 2024 at 7:40 AM Oleg Nesterov <oleg@redhat.com> wrote:
>
> On 08/07, Andrii Nakryiko wrote:
> >
> > @@ -1127,18 +1105,30 @@ void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
> >       int err;
> >
> >       down_write(&uprobe->register_rwsem);
> > -     if (WARN_ON(!consumer_del(uprobe, uc))) {
> > -             err = -ENOENT;
> > -     } else {
> > -             err = register_for_each_vma(uprobe, NULL);
> > -             /* TODO : cant unregister? schedule a worker thread */
> > -             if (unlikely(err))
> > -                     uprobe_warn(current, "unregister, leaking uprobe");
> > -     }
> > +
> > +     list_del_rcu(&uc->cons_node);
> > +     err = register_for_each_vma(uprobe, NULL);
> > +
> >       up_write(&uprobe->register_rwsem);
> >
> > -     if (!err)
> > -             put_uprobe(uprobe);
> > +     /* TODO : cant unregister? schedule a worker thread */
> > +     if (unlikely(err)) {
> > +             uprobe_warn(current, "unregister, leaking uprobe");
> > +             return;
>
> Looks wrong... We can (should) skip put_uprobe(), but we can't avoid
> synchronize_srcu().
>
> The caller can free the consumer right after return. You even added
> a fat comment below.
>

Yep, totally my bad, you are right. I'll add a goto synchronize (and
yep, we'll later remove it, but we should be thorough here).

> Yes, the problem will go away after you split it into nosync/sync, but
> still.
>
> Oleg.
>
diff mbox series

Patch

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 63ae2ade3487..f67f8d98c3c6 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -35,7 +35,7 @@  struct uprobe_consumer {
 				struct pt_regs *regs);
 	bool (*filter)(struct uprobe_consumer *self, struct mm_struct *mm);
 
-	struct uprobe_consumer *next;
+	struct list_head cons_node;
 };
 
 #ifdef CONFIG_UPROBES
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 9b31235bc177..5bddd20b7053 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -62,7 +62,7 @@  struct uprobe {
 	struct rw_semaphore	register_rwsem;
 	struct rw_semaphore	consumer_rwsem;
 	struct list_head	pending_list;
-	struct uprobe_consumer	*consumers;
+	struct list_head	consumers;
 	struct inode		*inode;		/* Also hold a ref to inode */
 	loff_t			offset;
 	loff_t			ref_ctr_offset;
@@ -785,6 +785,7 @@  static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset,
 	uprobe->inode = inode;
 	uprobe->offset = offset;
 	uprobe->ref_ctr_offset = ref_ctr_offset;
+	INIT_LIST_HEAD(&uprobe->consumers);
 	init_rwsem(&uprobe->register_rwsem);
 	init_rwsem(&uprobe->consumer_rwsem);
 	RB_CLEAR_NODE(&uprobe->rb_node);
@@ -810,34 +811,10 @@  static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset,
 static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc)
 {
 	down_write(&uprobe->consumer_rwsem);
-	uc->next = uprobe->consumers;
-	uprobe->consumers = uc;
+	list_add_rcu(&uc->cons_node, &uprobe->consumers);
 	up_write(&uprobe->consumer_rwsem);
 }
 
-/*
- * For uprobe @uprobe, delete the consumer @uc.
- * Return true if the @uc is deleted successfully
- * or return false.
- */
-static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc)
-{
-	struct uprobe_consumer **con;
-	bool ret = false;
-
-	down_write(&uprobe->consumer_rwsem);
-	for (con = &uprobe->consumers; *con; con = &(*con)->next) {
-		if (*con == uc) {
-			*con = uc->next;
-			ret = true;
-			break;
-		}
-	}
-	up_write(&uprobe->consumer_rwsem);
-
-	return ret;
-}
-
 static int __copy_insn(struct address_space *mapping, struct file *filp,
 			void *insn, int nbytes, loff_t offset)
 {
@@ -931,7 +908,8 @@  static bool filter_chain(struct uprobe *uprobe, struct mm_struct *mm)
 	bool ret = false;
 
 	down_read(&uprobe->consumer_rwsem);
-	for (uc = uprobe->consumers; uc; uc = uc->next) {
+	list_for_each_entry_srcu(uc, &uprobe->consumers, cons_node,
+				 srcu_read_lock_held(&uprobes_srcu)) {
 		ret = consumer_filter(uc, mm);
 		if (ret)
 			break;
@@ -1127,18 +1105,30 @@  void uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc)
 	int err;
 
 	down_write(&uprobe->register_rwsem);
-	if (WARN_ON(!consumer_del(uprobe, uc))) {
-		err = -ENOENT;
-	} else {
-		err = register_for_each_vma(uprobe, NULL);
-		/* TODO : cant unregister? schedule a worker thread */
-		if (unlikely(err))
-			uprobe_warn(current, "unregister, leaking uprobe");
-	}
+
+	list_del_rcu(&uc->cons_node);
+	err = register_for_each_vma(uprobe, NULL);
+
 	up_write(&uprobe->register_rwsem);
 
-	if (!err)
-		put_uprobe(uprobe);
+	/* TODO : cant unregister? schedule a worker thread */
+	if (unlikely(err)) {
+		uprobe_warn(current, "unregister, leaking uprobe");
+		return;
+	}
+
+	put_uprobe(uprobe);
+
+	/*
+	 * Now that handler_chain() and handle_uretprobe_chain() iterate over
+	 * uprobe->consumers list under RCU protection without holding
+	 * uprobe->register_rwsem, we need to wait for RCU grace period to
+	 * make sure that we can't call into just unregistered
+	 * uprobe_consumer's callbacks anymore. If we don't do that, fast and
+	 * unlucky enough caller can free consumer's memory and cause
+	 * handler_chain() or handle_uretprobe_chain() to do an use-after-free.
+	 */
+	synchronize_srcu(&uprobes_srcu);
 }
 EXPORT_SYMBOL_GPL(uprobe_unregister);
 
@@ -1216,13 +1206,20 @@  EXPORT_SYMBOL_GPL(uprobe_register);
 int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool add)
 {
 	struct uprobe_consumer *con;
-	int ret = -ENOENT;
+	int ret = -ENOENT, srcu_idx;
 
 	down_write(&uprobe->register_rwsem);
-	for (con = uprobe->consumers; con && con != uc ; con = con->next)
-		;
-	if (con)
-		ret = register_for_each_vma(uprobe, add ? uc : NULL);
+
+	srcu_idx = srcu_read_lock(&uprobes_srcu);
+	list_for_each_entry_srcu(con, &uprobe->consumers, cons_node,
+				 srcu_read_lock_held(&uprobes_srcu)) {
+		if (con == uc) {
+			ret = register_for_each_vma(uprobe, add ? uc : NULL);
+			break;
+		}
+	}
+	srcu_read_unlock(&uprobes_srcu, srcu_idx);
+
 	up_write(&uprobe->register_rwsem);
 
 	return ret;
@@ -2088,10 +2085,12 @@  static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 	struct uprobe_consumer *uc;
 	int remove = UPROBE_HANDLER_REMOVE;
 	bool need_prep = false; /* prepare return uprobe, when needed */
+	bool has_consumers = false;
 
-	down_read(&uprobe->register_rwsem);
 	current->utask->auprobe = &uprobe->arch;
-	for (uc = uprobe->consumers; uc; uc = uc->next) {
+
+	list_for_each_entry_srcu(uc, &uprobe->consumers, cons_node,
+				 srcu_read_lock_held(&uprobes_srcu)) {
 		int rc = 0;
 
 		if (uc->handler) {
@@ -2104,17 +2103,24 @@  static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs)
 			need_prep = true;
 
 		remove &= rc;
+		has_consumers = true;
 	}
 	current->utask->auprobe = NULL;
 
 	if (need_prep && !remove)
 		prepare_uretprobe(uprobe, regs); /* put bp at return */
 
-	if (remove && uprobe->consumers) {
-		WARN_ON(!uprobe_is_active(uprobe));
-		unapply_uprobe(uprobe, current->mm);
+	if (remove && has_consumers) {
+		down_read(&uprobe->register_rwsem);
+
+		/* re-check that removal is still required, this time under lock */
+		if (!filter_chain(uprobe, current->mm)) {
+			WARN_ON(!uprobe_is_active(uprobe));
+			unapply_uprobe(uprobe, current->mm);
+		}
+
+		up_read(&uprobe->register_rwsem);
 	}
-	up_read(&uprobe->register_rwsem);
 }
 
 static void
@@ -2122,13 +2128,15 @@  handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs)
 {
 	struct uprobe *uprobe = ri->uprobe;
 	struct uprobe_consumer *uc;
+	int srcu_idx;
 
-	down_read(&uprobe->register_rwsem);
-	for (uc = uprobe->consumers; uc; uc = uc->next) {
+	srcu_idx = srcu_read_lock(&uprobes_srcu);
+	list_for_each_entry_srcu(uc, &uprobe->consumers, cons_node,
+				 srcu_read_lock_held(&uprobes_srcu)) {
 		if (uc->ret_handler)
 			uc->ret_handler(uc, ri->func, regs);
 	}
-	up_read(&uprobe->register_rwsem);
+	srcu_read_unlock(&uprobes_srcu, srcu_idx);
 }
 
 static struct return_instance *find_next_ret_chain(struct return_instance *ri)