locking/local_lock, mm: replace localtry_ helpers with local_trylock_t type

Partially revert commit 0aaddfb06882 ("locking/local_lock: Introduce
localtry_lock_t").  Remove localtry_*() helpers, since localtry_lock()
name might be misinterpreted as "try lock".

Introduce local_trylock[_irqsave]() helpers that only work with newly
introduced local_trylock_t type.  Note that attempt to use
local_trylock[_irqsave]() with local_lock_t will cause compilation
failure.

Usage and behavior in !PREEMPT_RT:

local_lock_t lock;                     // sizeof(lock) == 0
local_lock(&lock);                     // preempt disable
local_lock_irqsave(&lock, ...);        // irq save
if (local_trylock_irqsave(&lock, ...)) // compilation error

local_trylock_t lock;                  // sizeof(lock) == 4
local_lock(&lock);                     // preempt disable, acquired = 1
local_lock_irqsave(&lock, ...);        // irq save, acquired = 1
if (local_trylock(&lock))              // if (!acquired) preempt disable, acquired = 1
if (local_trylock_irqsave(&lock, ...)) // if (!acquired) irq save, acquired = 1

The existing local_lock_*() macros can be used either with local_lock_t or
local_trylock_t.  With local_trylock_t they set acquired = 1 while
local_unlock_*() clears it.

In !PREEMPT_RT local_lock_irqsave(local_lock_t *) disables interrupts to
protect critical section, but it doesn't prevent NMI, so the fully
reentrant code cannot use local_lock_irqsave(local_lock_t *) for exclusive
access.

The local_lock_irqsave(local_trylock_t *) helper disables interrupts and
sets acquired=1, so local_trylock_irqsave(local_trylock_t *) from NMI
attempting to acquire the same lock will return false.

In PREEMPT_RT local_lock_irqsave() maps to preemptible spin_lock().  Map
local_trylock_irqsave() to preemptible spin_trylock().  When in hard IRQ
or NMI return false right away, since spin_trylock() is not safe due to
explicit locking in the underneath rt_spin_trylock() implementation. 
Removing this explicit locking and attempting only "trylock" is undesired
due to PI implications.

The local_trylock() without _irqsave can be used to avoid the cost of
disabling/enabling interrupts by only disabling preemption, so
local_trylock() in an interrupt attempting to acquire the same lock will
return false.

Note there is no need to use local_inc for acquired variable, since it's a
percpu variable with strict nesting scopes.

Note that guard(local_lock)(&lock) works only for "local_lock_t lock".

The patch also makes sure that local_lock_release(l) is called before
WRITE_ONCE(l->acquired, 0).  Though IRQs are disabled at this point the
local_trylock() from NMI will succeed and local_lock_acquire(l) will warn.

Link: https://lkml.kernel.org/r/20250403025514.41186-1-alexei.starovoitov@gmail.com
Fixes: 0aaddfb06882 ("locking/local_lock: Introduce localtry_lock_t")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Daniel Borkman <daniel@iogearbox.net>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Martin KaFai Lau <martin.lau@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 19 insertions, 20 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 421740f1bcdc..c96c1f2b9cf5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1759,7 +1759,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
 }
 
 struct memcg_stock_pcp {
-	localtry_lock_t stock_lock;
+	local_trylock_t stock_lock;
 	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
 
@@ -1774,7 +1774,7 @@ struct memcg_stock_pcp {
 #define FLUSHING_CACHED_CHARGE	0
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock) = {
-	.stock_lock = INIT_LOCALTRY_LOCK(stock_lock),
+	.stock_lock = INIT_LOCAL_TRYLOCK(stock_lock),
 };
 static DEFINE_MUTEX(percpu_charge_mutex);
 
@@ -1805,11 +1805,10 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages,
 	if (nr_pages > MEMCG_CHARGE_BATCH)
 		return ret;
 
-	if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
-		if (!gfpflags_allow_spinning(gfp_mask))
-			return ret;
-		localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
-	}
+	if (gfpflags_allow_spinning(gfp_mask))
+		local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	else if (!local_trylock_irqsave(&memcg_stock.stock_lock, flags))
+		return ret;
 
 	stock = this_cpu_ptr(&memcg_stock);
 	stock_pages = READ_ONCE(stock->nr_pages);
@@ -1818,7 +1817,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages,
 		ret = true;
 	}
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
@@ -1857,14 +1856,14 @@ static void drain_local_stock(struct work_struct *dummy)
 	 * drain_stock races is that we always operate on local CPU stock
 	 * here with IRQ disabled
 	 */
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	old = drain_obj_stock(stock);
 	drain_stock(stock);
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 }
 
@@ -1894,7 +1893,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	unsigned long flags;
 
-	if (!localtry_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
+	if (!local_trylock_irqsave(&memcg_stock.stock_lock, flags)) {
 		/*
 		 * In case of unlikely failure to lock percpu stock_lock
 		 * uncharge memcg directly.
@@ -1907,7 +1906,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 		return;
 	}
 	__refill_stock(memcg, nr_pages);
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 }
 
 /*
@@ -1964,9 +1963,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu)
 	stock = &per_cpu(memcg_stock, cpu);
 
 	/* drain_obj_stock requires stock_lock */
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 	old = drain_obj_stock(stock);
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	drain_stock(stock);
 	obj_cgroup_put(old);
@@ -2787,7 +2786,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	unsigned long flags;
 	int *bytes;
 
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 	stock = this_cpu_ptr(&memcg_stock);
 
 	/*
@@ -2836,7 +2835,7 @@ static void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	if (nr)
 		__mod_objcg_mlstate(objcg, pgdat, idx, nr);
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 }
 
@@ -2846,7 +2845,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 	unsigned long flags;
 	bool ret = false;
 
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (objcg == READ_ONCE(stock->cached_objcg) && stock->nr_bytes >= nr_bytes) {
@@ -2854,7 +2853,7 @@ static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 		ret = true;
 	}
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 
 	return ret;
 }
@@ -2946,7 +2945,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 	unsigned long flags;
 	unsigned int nr_pages = 0;
 
-	localtry_lock_irqsave(&memcg_stock.stock_lock, flags);
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
 	if (READ_ONCE(stock->cached_objcg) != objcg) { /* reset if necessary */
@@ -2960,7 +2959,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
 		stock->nr_bytes &= (PAGE_SIZE - 1);
 	}
 
-	localtry_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
 	obj_cgroup_put(old);
 
 	if (nr_pages)