Merge tag 'locking-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Introduce cmpxchg128() -- aka. the demise of cmpxchg_double()

   The cmpxchg128() family of functions is basically & functionally the
   same as cmpxchg_double(), but with a saner interface.

   Instead of a 6-parameter horror that forced u128 - u64/u64-halves
   layout details on the interface and exposed users to complexity,
   fragility & bugs, use a natural 3-parameter interface with u128
   types.

 - Restructure the generated atomic headers, and add kerneldoc comments
   for all of the generic atomic{,64,_long}_t operations.

   The generated definitions are much cleaner now, and come with
   documentation.

 - Implement lock_set_cmp_fn() on lockdep, for defining an ordering when
   taking multiple locks of the same type.

   This gets rid of one use of lockdep_set_novalidate_class() in the
   bcache code.

 - Fix raw_cpu_generic_try_cmpxchg() bug due to an unintended variable
   shadowing generating garbage code on Clang on certain ARM builds.

* tag 'locking-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (43 commits)
  locking/atomic: scripts: fix ${atomic}_dec_if_positive() kerneldoc
  percpu: Fix self-assignment of __old in raw_cpu_generic_try_cmpxchg()
  locking/atomic: treewide: delete arch_atomic_*() kerneldoc
  locking/atomic: docs: Add atomic operations to the driver basic API documentation
  locking/atomic: scripts: generate kerneldoc comments
  docs: scripts: kernel-doc: accept bitwise negation like ~@var
  locking/atomic: scripts: simplify raw_atomic*() definitions
  locking/atomic: scripts: simplify raw_atomic_long*() definitions
  locking/atomic: scripts: split pfx/name/sfx/order
  locking/atomic: scripts: restructure fallback ifdeffery
  locking/atomic: scripts: build raw_atomic_long*() directly
  locking/atomic: treewide: use raw_atomic*_<op>()
  locking/atomic: scripts: add trivial raw_atomic*_<op>()
  locking/atomic: scripts: factor out order template generation
  locking/atomic: scripts: remove leftover "${mult}"
  locking/atomic: scripts: remove bogus order parameter
  locking/atomic: xtensa: add preprocessor symbols
  locking/atomic: x86: add preprocessor symbols
  locking/atomic: sparc: add preprocessor symbols
  locking/atomic: sh: add preprocessor symbols
  ...

5 files changed, 37 insertions, 17 deletions

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 2ddbda3a4374..ab8aa8f77cc4 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -986,8 +986,13 @@ union irte_ga_hi {
 };
 
 struct irte_ga {
-	union irte_ga_lo lo;
-	union irte_ga_hi hi;
+	union {
+		struct {
+			union irte_ga_lo lo;
+			union irte_ga_hi hi;
+		};
+		u128 irte;
+	};
 };
 
 struct irq_2_irte {
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index e8a2e5984acb..9ea40960978b 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3023,10 +3023,10 @@ out:
 static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 			  struct irte_ga *irte, struct amd_ir_data *data)
 {
-	bool ret;
 	struct irq_remap_table *table;
-	unsigned long flags;
 	struct irte_ga *entry;
+	unsigned long flags;
+	u128 old;
 
 	table = get_irq_table(iommu, devid);
 	if (!table)
@@ -3037,16 +3037,14 @@ static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 	entry = (struct irte_ga *)table->table;
 	entry = &entry[index];
 
-	ret = cmpxchg_double(&entry->lo.val, &entry->hi.val,
-			     entry->lo.val, entry->hi.val,
-			     irte->lo.val, irte->hi.val);
 	/*
 	 * We use cmpxchg16 to atomically update the 128-bit IRTE,
 	 * and it cannot be updated by the hardware or other processors
 	 * behind us, so the return value of cmpxchg16 should be the
 	 * same as the old value.
 	 */
-	WARN_ON(!ret);
+	old = entry->irte;
+	WARN_ON(!try_cmpxchg128(&entry->irte, &old, irte->irte));
 
 	if (data)
 		data->ref = entry;
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index a1b987335b31..08f56326e2f8 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -175,18 +175,14 @@ static int modify_irte(struct irq_2_iommu *irq_iommu,
 	irte = &iommu->ir_table->base[index];
 
 	if ((irte->pst == 1) || (irte_modified->pst == 1)) {
-		bool ret;
-
-		ret = cmpxchg_double(&irte->low, &irte->high,
-				     irte->low, irte->high,
-				     irte_modified->low, irte_modified->high);
 		/*
 		 * We use cmpxchg16 to atomically update the 128-bit IRTE,
 		 * and it cannot be updated by the hardware or other processors
 		 * behind us, so the return value of cmpxchg16 should be the
 		 * same as the old value.
 		 */
-		WARN_ON(!ret);
+		u128 old = irte->irte;
+		WARN_ON(!try_cmpxchg128(&irte->irte, &old, irte_modified->irte));
 	} else {
 		WRITE_ONCE(irte->low, irte_modified->low);
 		WRITE_ONCE(irte->high, irte_modified->high);
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 68b9d7ca864e..fd121a61f17c 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -559,6 +559,27 @@ static void mca_data_alloc(struct btree *b, struct bkey *k, gfp_t gfp)
 	}
 }
 
+#define cmp_int(l, r)		((l > r) - (l < r))
+
+#ifdef CONFIG_PROVE_LOCKING
+static int btree_lock_cmp_fn(const struct lockdep_map *_a,
+			     const struct lockdep_map *_b)
+{
+	const struct btree *a = container_of(_a, struct btree, lock.dep_map);
+	const struct btree *b = container_of(_b, struct btree, lock.dep_map);
+
+	return -cmp_int(a->level, b->level) ?: bkey_cmp(&a->key, &b->key);
+}
+
+static void btree_lock_print_fn(const struct lockdep_map *map)
+{
+	const struct btree *b = container_of(map, struct btree, lock.dep_map);
+
+	printk(KERN_CONT " l=%u %llu:%llu", b->level,
+	       KEY_INODE(&b->key), KEY_OFFSET(&b->key));
+}
+#endif
+
 static struct btree *mca_bucket_alloc(struct cache_set *c,
 				      struct bkey *k, gfp_t gfp)
 {
@@ -572,7 +593,7 @@ static struct btree *mca_bucket_alloc(struct cache_set *c,
 		return NULL;
 
 	init_rwsem(&b->lock);
-	lockdep_set_novalidate_class(&b->lock);
+	lock_set_cmp_fn(&b->lock, btree_lock_cmp_fn, btree_lock_print_fn);
 	mutex_init(&b->write_lock);
 	lockdep_set_novalidate_class(&b->write_lock);
 	INIT_LIST_HEAD(&b->list);
diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index a2920bbfcad5..45d64b54115a 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -247,8 +247,8 @@ static inline void bch_btree_op_init(struct btree_op *op, int write_lock_level)
 
 static inline void rw_lock(bool w, struct btree *b, int level)
 {
-	w ? down_write_nested(&b->lock, level + 1)
-	  : down_read_nested(&b->lock, level + 1);
+	w ? down_write(&b->lock)
+	  : down_read(&b->lock);
 	if (w)
 		b->seq++;
 }