linux-kernel - [PATCH 15/16] rcu/tree: Allocate a page when caller is preemptible

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: <20201029165019.14218-15-urezki@gmail.com>
Date:   Thu, 29 Oct 2020 17:50:18 +0100
From:   "Uladzislau Rezki (Sony)" <urezki@...il.com>
To:     LKML <linux-kernel@...r.kernel.org>, RCU <rcu@...r.kernel.org>,
        "Paul E . McKenney" <paulmck@...nel.org>
Cc:     Andrew Morton <akpm@...ux-foundation.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Michal Hocko <mhocko@...e.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        "Theodore Y . Ts'o" <tytso@....edu>,
        Joel Fernandes <joel@...lfernandes.org>,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
        Uladzislau Rezki <urezki@...il.com>,
        Oleksiy Avramchenko <oleksiy.avramchenko@...ymobile.com>
Subject: [PATCH 15/16] rcu/tree: Allocate a page when caller is preemptible

Given that CONFIG_PREEMPT_COUNT is unconditionally enabled by the
earlier commits in this series, the preemptible() macro now properly
detects preempt-disable code regions even in kernels built with
CONFIG_PREEMPT_NONE.

This commit therefore uses preemptible() to determine whether allocation
is possible at all for double-argument kvfree_rcu().  If !preemptible(),
then allocation is not possible, and kvfree_rcu() falls back to using
the less cache-friendly rcu_head approach.  Even when preemptible(),
the caller might be involved in reclaim, so the GFP_ flags used by
double-argument kvfree_rcu() must avoid invoking reclaim processing.

Note that single-argument kvfree_rcu() must be invoked in sleepable
contexts, and that its fallback is the relatively high latency
synchronize_rcu().  Single-argument kvfree_rcu() therefore uses
GFP_KERNEL|__GFP_RETRY_MAYFAIL to allow limited sleeping within the
memory 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 | 48 ++++++++++++++++++++++++++++++-----------------
 1 file changed, 31 insertions(+), 17 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f2da2a1cc716..3f9b016a44dc 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3406,37 +3406,55 @@ 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_sleep 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.
+// If !can_sleep, then if !preemptible() no allocation will be undertaken,
+// otherwise the allocation will use GFP_ATOMIC to avoid the remainder of
+// the aforementioned deadlock possibilities.  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_sleep)
 {
 	struct kvfree_rcu_bulk_data *bnode;
+	bool can_alloc_page = preemptible();
+	gfp_t gfp = (can_sleep ? GFP_KERNEL | __GFP_RETRY_MAYFAIL :
+		GFP_ATOMIC) | __GFP_NOWARN;
 	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_page) {
+			krc_this_cpu_unlock(*krcp, *flags);
+			bnode = (struct kvfree_rcu_bulk_data *)
+				__get_free_page(gfp);
+			*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;
 }
@@ -3474,20 +3492,16 @@ 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.
 		WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
 			  __func__, head);
 
-		// Mark as success and leave.
-		success = true;
-		goto unlock_return;
+		return;
 	}
 
-	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);
 
-- 
2.20.1