linux-kernel - [PATCH tip/core/rcu 1/6] kvfree_rcu: Directly allocate page for single-argument case

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210304001134.22977-1-paulmck@kernel.org>
Date:   Wed,  3 Mar 2021 16:11:29 -0800
From:   paulmck@...nel.org
To:     rcu@...r.kernel.org
Cc:     linux-kernel@...r.kernel.org, kernel-team@...com, mingo@...nel.org,
        jiangshanlai@...il.com, akpm@...ux-foundation.org,
        mathieu.desnoyers@...icios.com, josh@...htriplett.org,
        tglx@...utronix.de, peterz@...radead.org, rostedt@...dmis.org,
        dhowells@...hat.com, edumazet@...gle.com, fweisbec@...il.com,
        oleg@...hat.com, joel@...lfernandes.org,
        "Uladzislau Rezki (Sony)" <urezki@...il.com>,
        "Paul E . McKenney" <paulmck@...nel.org>
Subject: [PATCH tip/core/rcu 1/6] kvfree_rcu: Directly allocate page for single-argument case

From: "Uladzislau Rezki (Sony)" <urezki@...il.com>

Single-argument kvfree_rcu() must be invoked from sleepable contexts,
so we can directly allocate pages.  Furthermmore, the fallback in case
of page-allocation failure is the high-latency synchronize_rcu(), so it
makes sense to do these page allocations from the fastpath, and even to
permit limited sleeping within the allocator.

This commit therefore allocates if needed on the fastpath using
GFP_KERNEL|__GFP_RETRY_MAYFAIL.  This also has the beneficial effect
of leaving kvfree_rcu()'s per-CPU caches to the double-argument variant
of kvfree_rcu(), given that the double-argument variant cannot directly
invoke the allocator.

[ paulmck: Add add_ptr_to_bulk_krc_lock header comment per Michal Hocko. ]
Signed-off-by: Uladzislau Rezki (Sony) <urezki@...il.com>
Signed-off-by: Paul E. McKenney <paulmck@...nel.org>
---
 kernel/rcu/tree.c | 42 ++++++++++++++++++++++++++----------------
 1 file changed, 26 insertions(+), 16 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index da6f521..1f8c980 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3493,37 +3493,50 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp)
 	}
 }
 
+// Record ptr in a page managed by krcp, with the pre-krc_this_cpu_lock()
+// state specified by flags.  If can_alloc is true, the caller must
+// be schedulable and not be holding any locks or mutexes that might be
+// acquired by the memory allocator or anything that it might invoke.
+// Returns true if ptr was successfully recorded, else the caller must
+// use a fallback.
 static inline bool
-kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
+add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
+	unsigned long *flags, void *ptr, bool can_alloc)
 {
 	struct kvfree_rcu_bulk_data *bnode;
 	int idx;
 
-	if (unlikely(!krcp->initialized))
+	*krcp = krc_this_cpu_lock(flags);
+	if (unlikely(!(*krcp)->initialized))
 		return false;
 
-	lockdep_assert_held(&krcp->lock);
 	idx = !!is_vmalloc_addr(ptr);
 
 	/* Check if a new block is required. */
-	if (!krcp->bkvhead[idx] ||
-			krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
-		bnode = get_cached_bnode(krcp);
-		/* Switch to emergency path. */
+	if (!(*krcp)->bkvhead[idx] ||
+			(*krcp)->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
+		bnode = get_cached_bnode(*krcp);
+		if (!bnode && can_alloc) {
+			krc_this_cpu_unlock(*krcp, *flags);
+			bnode = (struct kvfree_rcu_bulk_data *)
+				__get_free_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+			*krcp = krc_this_cpu_lock(flags);
+		}
+
 		if (!bnode)
 			return false;
 
 		/* Initialize the new block. */
 		bnode->nr_records = 0;
-		bnode->next = krcp->bkvhead[idx];
+		bnode->next = (*krcp)->bkvhead[idx];
 
 		/* Attach it to the head. */
-		krcp->bkvhead[idx] = bnode;
+		(*krcp)->bkvhead[idx] = bnode;
 	}
 
 	/* Finally insert. */
-	krcp->bkvhead[idx]->records
-		[krcp->bkvhead[idx]->nr_records++] = ptr;
+	(*krcp)->bkvhead[idx]->records
+		[(*krcp)->bkvhead[idx]->nr_records++] = ptr;
 
 	return true;
 }
@@ -3561,8 +3574,6 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		ptr = (unsigned long *) func;
 	}
 
-	krcp = krc_this_cpu_lock(&flags);
-
 	// Queue the object but don't yet schedule the batch.
 	if (debug_rcu_head_queue(ptr)) {
 		// Probable double kfree_rcu(), just leak.
@@ -3570,12 +3581,11 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 			  __func__, head);
 
 		// Mark as success and leave.
-		success = true;
-		goto unlock_return;
+		return;
 	}
 
 	kasan_record_aux_stack(ptr);
-	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
+	success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
 	if (!success) {
 		run_page_cache_worker(krcp);
 
-- 
2.9.5