[PATCH tip/core/rcu 0/6] kvfree_rcu() updates for v5.12-rc1

[PATCH tip/core/rcu 0/6] kvfree_rcu() updates for v5.12-rc1

[Paul E. McKenney]

Hello!

This series contains kvfree_rcu() updates, most notably surrounding GPF
flags for memory allocation.

1.	kvfree_rcu: Directly allocate page for single-argument case,
	courtesy of "Uladzislau Rezki (Sony)".

2.	kvfree_rcu: Use __GFP_NOMEMALLOC for single-argument kvfree_rcu().

3.	kvfree_rcu: Make krc_this_cpu_unlock() use
	raw_spin_unlock_irqrestore().

4.	kvfree_rcu: Replace __GFP_RETRY_MAYFAIL by __GFP_NORETRY,
	courtesy of "Uladzislau Rezki (Sony)".

5.	kvfree_rcu: Use same set of GFP flags as does single-argument,
	courtesy of "Uladzislau Rezki (Sony)".

6.	Add kfree_rcu() single-argument scale test, courtesy of
	"Uladzislau Rezki (Sony)".

						Thanx, Paul

------------------------------------------------------------------------

 Documentation/admin-guide/kernel-parameters.txt |   12 ++++
 kernel/rcu/rcuscale.c                           |   15 +++++
 kernel/rcu/tree.c                               |   63 ++++++++++++++++--------
 3 files changed, 68 insertions(+), 22 deletions(-)

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

[paulmck]

From: "Uladzislau Rezki (Sony)" <urezki@gmail.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@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.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

[PATCH tip/core/rcu 2/6] kvfree_rcu: Use __GFP_NOMEMALLOC for single-argument kvfree_rcu()

[paulmck]

From: "Paul E. McKenney" <paulmck@kernel.org>

This commit applies the __GFP_NOMEMALLOC gfp flag to memory allocations
carried out by the single-argument variant of kvfree_rcu(), thus avoiding
this can-sleep code path from dipping into the emergency reserves.

Acked-by: Michal Hocko <mhocko@suse.com>
Suggested-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1f8c980..08b5044 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3519,7 +3519,7 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **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);
+				__get_free_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOMEMALLOC | __GFP_NOWARN);
 			*krcp = krc_this_cpu_lock(flags);
 		}
 
-- 
2.9.5

[PATCH tip/core/rcu 3/6] kvfree_rcu: Make krc_this_cpu_unlock() use raw_spin_unlock_irqrestore()

[paulmck]

From: "Paul E. McKenney" <paulmck@kernel.org>

The krc_this_cpu_unlock() function does a raw_spin_unlock() immediately
followed by a local_irq_restore().  This commit saves a line of code by
merging them into a raw_spin_unlock_irqrestore().  This transformation
also reduces scheduling latency because raw_spin_unlock_irqrestore()
responds immediately to a reschedule request.  In contrast,
local_irq_restore() does a scheduling-oblivious enabling of interrupts.

Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tree.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 08b5044..7ee83f3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3229,8 +3229,7 @@ krc_this_cpu_lock(unsigned long *flags)
 static inline void
 krc_this_cpu_unlock(struct kfree_rcu_cpu *krcp, unsigned long flags)
 {
-	raw_spin_unlock(&krcp->lock);
-	local_irq_restore(flags);
+	raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
 static inline struct kvfree_rcu_bulk_data *
-- 
2.9.5

[PATCH tip/core/rcu 4/6] kvfree_rcu: Replace __GFP_RETRY_MAYFAIL by __GFP_NORETRY

[paulmck]

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

__GFP_RETRY_MAYFAIL can spend quite a bit of time reclaiming, and this
can be wasted effort given that there is a fallback code path in case
memory allocation fails.

__GFP_NORETRY does perform some light-weight reclaim, but it will fail
under OOM conditions, allowing the fallback to be taken as an alternative
to hard-OOMing the system.

There is a four-way tradeoff that must be balanced:
    1) Minimize use of the fallback path;
    2) Avoid full-up OOM;
    3) Do a light-wait allocation request;
    4) Avoid dipping into the emergency reserves.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tree.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7ee83f3..0ecc1fb 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3517,8 +3517,20 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp,
 		bnode = get_cached_bnode(*krcp);
 		if (!bnode && can_alloc) {
 			krc_this_cpu_unlock(*krcp, *flags);
+
+			// __GFP_NORETRY - allows a light-weight direct reclaim
+			// what is OK from minimizing of fallback hitting point of
+			// view. Apart of that it forbids any OOM invoking what is
+			// also beneficial since we are about to release memory soon.
+			//
+			// __GFP_NOMEMALLOC - prevents from consuming of all the
+			// memory reserves. Please note we have a fallback path.
+			//
+			// __GFP_NOWARN - it is supposed that an allocation can
+			// be failed under low memory or high memory pressure
+			// scenarios.
 			bnode = (struct kvfree_rcu_bulk_data *)
-				__get_free_page(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOMEMALLOC | __GFP_NOWARN);
+				__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 			*krcp = krc_this_cpu_lock(flags);
 		}
 
-- 
2.9.5

[PATCH tip/core/rcu 5/6] kvfree_rcu: Use same set of GFP flags as does single-argument

[paulmck]

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

Running an rcuscale stress-suite can lead to "Out of memory" of a
system. This can happen under high memory pressure with a small amount
of physical memory.

For example, a KVM test configuration with 64 CPUs and 512 megabytes
can result in OOM when running rcuscale with below parameters:

../kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig CONFIG_NR_CPUS=64 \
--bootargs "rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 rcuscale.holdoff=20 \
  rcuscale.kfree_loops=10000 torture.disable_onoff_at_boot" --trust-make

<snip>
[   12.054448] kworker/1:1H invoked oom-killer: gfp_mask=0x2cc0(GFP_KERNEL|__GFP_NOWARN), order=0, oom_score_adj=0
[   12.055303] CPU: 1 PID: 377 Comm: kworker/1:1H Not tainted 5.11.0-rc3+ #510
[   12.055416] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014
[   12.056485] Workqueue: events_highpri fill_page_cache_func
[   12.056485] Call Trace:
[   12.056485]  dump_stack+0x57/0x6a
[   12.056485]  dump_header+0x4c/0x30a
[   12.056485]  ? del_timer_sync+0x20/0x30
[   12.056485]  out_of_memory.cold.47+0xa/0x7e
[   12.056485]  __alloc_pages_slowpath.constprop.123+0x82f/0xc00
[   12.056485]  __alloc_pages_nodemask+0x289/0x2c0
[   12.056485]  __get_free_pages+0x8/0x30
[   12.056485]  fill_page_cache_func+0x39/0xb0
[   12.056485]  process_one_work+0x1ed/0x3b0
[   12.056485]  ? process_one_work+0x3b0/0x3b0
[   12.060485]  worker_thread+0x28/0x3c0
[   12.060485]  ? process_one_work+0x3b0/0x3b0
[   12.060485]  kthread+0x138/0x160
[   12.060485]  ? kthread_park+0x80/0x80
[   12.060485]  ret_from_fork+0x22/0x30
[   12.062156] Mem-Info:
[   12.062350] active_anon:0 inactive_anon:0 isolated_anon:0
[   12.062350]  active_file:0 inactive_file:0 isolated_file:0
[   12.062350]  unevictable:0 dirty:0 writeback:0
[   12.062350]  slab_reclaimable:2797 slab_unreclaimable:80920
[   12.062350]  mapped:1 shmem:2 pagetables:8 bounce:0
[   12.062350]  free:10488 free_pcp:1227 free_cma:0
...
[   12.101610] Out of memory and no killable processes...
[   12.102042] Kernel panic - not syncing: System is deadlocked on memory
[   12.102583] CPU: 1 PID: 377 Comm: kworker/1:1H Not tainted 5.11.0-rc3+ #510
[   12.102600] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.12.0-1 04/01/2014
<snip>

Because kvfree_rcu() has a fallback path, memory allocation failure is
not the end of the world.  Furthermore, the added overhead of aggressive
GFP settings must be balanced against the overhead of the fallback path,
which is a cache miss for double-argument kvfree_rcu() and a call to
synchronize_rcu() for single-argument kvfree_rcu().  The current choice
of GFP_KERNEL|__GFP_NOWARN can result in longer latencies than a call
to synchronize_rcu(), so less-tenacious GFP flags would be helpful.

Here is the tradeoff that must be balanced:
    a) Minimize use of the fallback path,
    b) Avoid pushing the system into OOM,
    c) Bound allocation latency to that of synchronize_rcu(), and
    d) Leave the emergency reserves to use cases lacking fallbacks.

This commit therefore changes GFP flags from GFP_KERNEL|__GFP_NOWARN to
GFP_KERNEL|__GFP_NORETRY|__GFP_NOMEMALLOC|__GFP_NOWARN.  This combination
leaves the emergency reserves alone and can initiate reclaim, but will
not invoke the OOM killer.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 0ecc1fb..4120d4b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3463,7 +3463,7 @@ static void fill_page_cache_func(struct work_struct *work)
 
 	for (i = 0; i < rcu_min_cached_objs; i++) {
 		bnode = (struct kvfree_rcu_bulk_data *)
-			__get_free_page(GFP_KERNEL | __GFP_NOWARN);
+			__get_free_page(GFP_KERNEL | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
 
 		if (bnode) {
 			raw_spin_lock_irqsave(&krcp->lock, flags);
-- 
2.9.5

[PATCH tip/core/rcu 6/6] rcuscale: Add kfree_rcu() single-argument scale test

[paulmck]

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

The single-argument variant of kfree_rcu() is currently not
tested by any member of the rcutoture test suite.  This
commit therefore adds rcuscale code to test it.  This
testing is controlled by two new boolean module parameters,
kfree_rcu_test_single and kfree_rcu_test_double.  If one
is set and the other not, only the corresponding variant
is tested, otherwise both are tested, with the variant to
be tested determined randomly on each invocation.

Both of these module parameters are initialized to false,
so setting either to true will test only that variant.

Suggested-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 Documentation/admin-guide/kernel-parameters.txt | 12 ++++++++++++
 kernel/rcu/rcuscale.c                           | 15 ++++++++++++++-
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 0454572..84fce41 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4259,6 +4259,18 @@
 	rcuscale.kfree_rcu_test= [KNL]
 			Set to measure performance of kfree_rcu() flooding.
 
+	rcuscale.kfree_rcu_test_double= [KNL]
+			Test the double-argument variant of kfree_rcu().
+			If this parameter has the same value as
+			rcuscale.kfree_rcu_test_single, both the single-
+			and double-argument variants are tested.
+
+	rcuscale.kfree_rcu_test_single= [KNL]
+			Test the single-argument variant of kfree_rcu().
+			If this parameter has the same value as
+			rcuscale.kfree_rcu_test_double, both the single-
+			and double-argument variants are tested.
+
 	rcuscale.kfree_nthreads= [KNL]
 			The number of threads running loops of kfree_rcu().
 
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 06491d5..dca51fe 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -625,6 +625,8 @@ rcu_scale_shutdown(void *arg)
 torture_param(int, kfree_nthreads, -1, "Number of threads running loops of kfree_rcu().");
 torture_param(int, kfree_alloc_num, 8000, "Number of allocations and frees done in an iteration.");
 torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num allocations and frees.");
+torture_param(bool, kfree_rcu_test_double, false, "Do we run a kfree_rcu() double-argument scale test?");
+torture_param(bool, kfree_rcu_test_single, false, "Do we run a kfree_rcu() single-argument scale test?");
 
 static struct task_struct **kfree_reader_tasks;
 static int kfree_nrealthreads;
@@ -644,10 +646,13 @@ kfree_scale_thread(void *arg)
 	struct kfree_obj *alloc_ptr;
 	u64 start_time, end_time;
 	long long mem_begin, mem_during = 0;
+	bool kfree_rcu_test_both;
+	DEFINE_TORTURE_RANDOM(tr);
 
 	VERBOSE_SCALEOUT_STRING("kfree_scale_thread task started");
 	set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
 	set_user_nice(current, MAX_NICE);
+	kfree_rcu_test_both = (kfree_rcu_test_single == kfree_rcu_test_double);
 
 	start_time = ktime_get_mono_fast_ns();
 
@@ -670,7 +675,15 @@ kfree_scale_thread(void *arg)
 			if (!alloc_ptr)
 				return -ENOMEM;
 
-			kfree_rcu(alloc_ptr, rh);
+			// By default kfree_rcu_test_single and kfree_rcu_test_double are
+			// initialized to false. If both have the same value (false or true)
+			// both are randomly tested, otherwise only the one with value true
+			// is tested.
+			if ((kfree_rcu_test_single && !kfree_rcu_test_double) ||
+					(kfree_rcu_test_both && torture_random(&tr) & 0x800))
+				kfree_rcu(alloc_ptr);
+			else
+				kfree_rcu(alloc_ptr, rh);
 		}
 
 		cond_resched();
-- 
2.9.5