Merge tag 'bcachefs-2024-03-13' of https://evilpiepirate.org/git/bcachefs

Pull bcachefs updates from Kent Overstreet:

 - Subvolume children btree; this is needed for providing a userspace
   interface for walking subvolumes, which will come later

 - Lots of improvements to directory structure checking

 - Improved journal pipelining, significantly improving performance on
   high iodepth write workloads

 - Discard path improvements: the discard path is more efficient, and no
   longer flushes the journal unnecessarily

 - Buffered write path can now avoid taking the inode lock

 - new mm helper: memalloc_flags_{save|restore}

 - mempool now does kvmalloc mempools

* tag 'bcachefs-2024-03-13' of https://evilpiepirate.org/git/bcachefs: (128 commits)
  bcachefs: time_stats: shrink time_stat_buffer for better alignment
  bcachefs: time_stats: split stats-with-quantiles into a separate structure
  bcachefs: mean_and_variance: put struct mean_and_variance_weighted on a diet
  bcachefs: time_stats: add larger units
  bcachefs: pull out time_stats.[ch]
  bcachefs: reconstruct_alloc cleanup
  bcachefs: fix bch_folio_sector padding
  bcachefs: Fix btree key cache coherency during replay
  bcachefs: Always flush write buffer in delete_dead_inodes()
  bcachefs: Fix order of gc_done passes
  bcachefs: fix deletion of indirect extents in btree_gc
  bcachefs: Prefer struct_size over open coded arithmetic
  bcachefs: Kill unused flags argument to btree_split()
  bcachefs: Check for writing superblocks with nonsense member seq fields
  bcachefs: fix bch2_journal_buf_to_text()
  lib/generic-radix-tree.c: Make nodes more reasonably sized
  bcachefs: copy_(to|from)_user_errcode()
  bcachefs: Split out bkey_types.h
  bcachefs: fix lost journal buf wakeup due to improved pipelining
  bcachefs: intercept mountoption value for bool type
  ...

5 files changed, 71 insertions, 36 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index d5d5a4ee24f0..00fc429b0af0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3074,6 +3074,7 @@ extern struct inode *new_inode_pseudo(struct super_block *sb);
 extern struct inode *new_inode(struct super_block *sb);
 extern void free_inode_nonrcu(struct inode *inode);
 extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *);
+extern int file_remove_privs_flags(struct file *file, unsigned int flags);
 extern int file_remove_privs(struct file *);
 int setattr_should_drop_sgid(struct mnt_idmap *idmap,
 			     const struct inode *inode);
diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h
index 847413164738..f3512fddf3d7 100644
--- a/include/linux/generic-radix-tree.h
+++ b/include/linux/generic-radix-tree.h
@@ -5,7 +5,7 @@
  * DOC: Generic radix trees/sparse arrays
  *
  * Very simple and minimalistic, supporting arbitrary size entries up to
- * PAGE_SIZE.
+ * GENRADIX_NODE_SIZE.
  *
  * A genradix is defined with the type it will store, like so:
  *
@@ -45,12 +45,15 @@
 
 struct genradix_root;
 
+#define GENRADIX_NODE_SHIFT	9
+#define GENRADIX_NODE_SIZE	(1U << GENRADIX_NODE_SHIFT)
+
 struct __genradix {
 	struct genradix_root		*root;
 };
 
 /*
- * NOTE: currently, sizeof(_type) must not be larger than PAGE_SIZE:
+ * NOTE: currently, sizeof(_type) must not be larger than GENRADIX_NODE_SIZE:
  */
 
 #define __GENRADIX_INITIALIZER					\
@@ -101,14 +104,14 @@ void __genradix_free(struct __genradix *);
 static inline size_t __idx_to_offset(size_t idx, size_t obj_size)
 {
 	if (__builtin_constant_p(obj_size))
-		BUILD_BUG_ON(obj_size > PAGE_SIZE);
+		BUILD_BUG_ON(obj_size > GENRADIX_NODE_SIZE);
 	else
-		BUG_ON(obj_size > PAGE_SIZE);
+		BUG_ON(obj_size > GENRADIX_NODE_SIZE);
 
 	if (!is_power_of_2(obj_size)) {
-		size_t objs_per_page = PAGE_SIZE / obj_size;
+		size_t objs_per_page = GENRADIX_NODE_SIZE / obj_size;
 
-		return (idx / objs_per_page) * PAGE_SIZE +
+		return (idx / objs_per_page) * GENRADIX_NODE_SIZE +
 			(idx % objs_per_page) * obj_size;
 	} else {
 		return idx * obj_size;
@@ -118,9 +121,9 @@ static inline size_t __idx_to_offset(size_t idx, size_t obj_size)
 #define __genradix_cast(_radix)		(typeof((_radix)->type[0]) *)
 #define __genradix_obj_size(_radix)	sizeof((_radix)->type[0])
 #define __genradix_objs_per_page(_radix)			\
-	(PAGE_SIZE / sizeof((_radix)->type[0]))
+	(GENRADIX_NODE_SIZE / sizeof((_radix)->type[0]))
 #define __genradix_page_remainder(_radix)			\
-	(PAGE_SIZE % sizeof((_radix)->type[0]))
+	(GENRADIX_NODE_SIZE % sizeof((_radix)->type[0]))
 
 #define __genradix_idx_to_offset(_radix, _idx)			\
 	__idx_to_offset(_idx, __genradix_obj_size(_radix))
@@ -217,8 +220,8 @@ static inline void __genradix_iter_advance(struct genradix_iter *iter,
 	iter->offset += obj_size;
 
 	if (!is_power_of_2(obj_size) &&
-	    (iter->offset & (PAGE_SIZE - 1)) + obj_size > PAGE_SIZE)
-		iter->offset = round_up(iter->offset, PAGE_SIZE);
+	    (iter->offset & (GENRADIX_NODE_SIZE - 1)) + obj_size > GENRADIX_NODE_SIZE)
+		iter->offset = round_up(iter->offset, GENRADIX_NODE_SIZE);
 
 	iter->pos++;
 }
@@ -235,8 +238,8 @@ static inline void __genradix_iter_rewind(struct genradix_iter *iter,
 		return;
 	}
 
-	if ((iter->offset & (PAGE_SIZE - 1)) == 0)
-		iter->offset -= PAGE_SIZE % obj_size;
+	if ((iter->offset & (GENRADIX_NODE_SIZE - 1)) == 0)
+		iter->offset -= GENRADIX_NODE_SIZE % obj_size;
 
 	iter->offset -= obj_size;
 	iter->pos--;
@@ -263,7 +266,7 @@ static inline void __genradix_iter_rewind(struct genradix_iter *iter,
 	genradix_for_each_from(_radix, _iter, _p, 0)
 
 #define genradix_last_pos(_radix)				\
-	(SIZE_MAX / PAGE_SIZE * __genradix_objs_per_page(_radix) - 1)
+	(SIZE_MAX / GENRADIX_NODE_SIZE * __genradix_objs_per_page(_radix) - 1)
 
 /**
  * genradix_for_each_reverse - iterate over entry in a genradix, reverse order
diff --git a/include/linux/mempool.h b/include/linux/mempool.h
index 7be1e32e6d42..16c5cc807ff6 100644
--- a/include/linux/mempool.h
+++ b/include/linux/mempool.h
@@ -95,6 +95,19 @@ static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size)
 			      (void *) size);
 }
 
+void *mempool_kvmalloc(gfp_t gfp_mask, void *pool_data);
+void mempool_kvfree(void *element, void *pool_data);
+
+static inline int mempool_init_kvmalloc_pool(mempool_t *pool, int min_nr, size_t size)
+{
+	return mempool_init(pool, min_nr, mempool_kvmalloc, mempool_kvfree, (void *) size);
+}
+
+static inline mempool_t *mempool_create_kvmalloc_pool(int min_nr, size_t size)
+{
+	return mempool_create(min_nr, mempool_kvmalloc, mempool_kvfree, (void *) size);
+}
+
 /*
  * A mempool_alloc_t and mempool_free_t for a simple page allocator that
  * allocates pages of the order specified by pool_data
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 94f0e618865b..3c2abbc587b4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1639,8 +1639,8 @@ extern struct pid *cad_pid;
 						 * I am cleaning dirty pages from some other bdi. */
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
-#define PF__HOLE__00800000	0x00800000
-#define PF__HOLE__01000000	0x01000000
+#define PF_MEMALLOC_NORECLAIM	0x00800000	/* All allocation requests will clear __GFP_DIRECT_RECLAIM */
+#define PF_MEMALLOC_NOWARN	0x01000000	/* All allocation requests will inherit __GFP_NOWARN */
 #define PF__HOLE__02000000	0x02000000
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 7a4066d22883..b6543f9d78d6 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -236,16 +236,25 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 {
 	unsigned int pflags = READ_ONCE(current->flags);
 
-	if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) {
+	if (unlikely(pflags & (PF_MEMALLOC_NOIO |
+			       PF_MEMALLOC_NOFS |
+			       PF_MEMALLOC_NORECLAIM |
+			       PF_MEMALLOC_NOWARN |
+			       PF_MEMALLOC_PIN))) {
 		/*
-		 * NOIO implies both NOIO and NOFS and it is a weaker context
-		 * so always make sure it makes precedence
+		 * Stronger flags before weaker flags:
+		 * NORECLAIM implies NOIO, which in turn implies NOFS
 		 */
-		if (pflags & PF_MEMALLOC_NOIO)
+		if (pflags & PF_MEMALLOC_NORECLAIM)
+			flags &= ~__GFP_DIRECT_RECLAIM;
+		else if (pflags & PF_MEMALLOC_NOIO)
 			flags &= ~(__GFP_IO | __GFP_FS);
 		else if (pflags & PF_MEMALLOC_NOFS)
 			flags &= ~__GFP_FS;
 
+		if (pflags & PF_MEMALLOC_NOWARN)
+			flags |= __GFP_NOWARN;
+
 		if (pflags & PF_MEMALLOC_PIN)
 			flags &= ~__GFP_MOVABLE;
 	}
@@ -307,6 +316,24 @@ static inline void might_alloc(gfp_t gfp_mask)
 }
 
 /**
+ * memalloc_flags_save - Add a PF_* flag to current->flags, save old value
+ *
+ * This allows PF_* flags to be conveniently added, irrespective of current
+ * value, and then the old version restored with memalloc_flags_restore().
+ */
+static inline unsigned memalloc_flags_save(unsigned flags)
+{
+	unsigned oldflags = ~current->flags & flags;
+	current->flags |= flags;
+	return oldflags;
+}
+
+static inline void memalloc_flags_restore(unsigned flags)
+{
+	current->flags &= ~flags;
+}
+
+/**
  * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope.
  *
  * This functions marks the beginning of the GFP_NOIO allocation scope.
@@ -320,9 +347,7 @@ static inline void might_alloc(gfp_t gfp_mask)
  */
 static inline unsigned int memalloc_noio_save(void)
 {
-	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
-	current->flags |= PF_MEMALLOC_NOIO;
-	return flags;
+	return memalloc_flags_save(PF_MEMALLOC_NOIO);
 }
 
 /**
@@ -335,7 +360,7 @@ static inline unsigned int memalloc_noio_save(void)
  */
 static inline void memalloc_noio_restore(unsigned int flags)
 {
-	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
+	memalloc_flags_restore(flags);
 }
 
 /**
@@ -352,9 +377,7 @@ static inline void memalloc_noio_restore(unsigned int flags)
  */
 static inline unsigned int memalloc_nofs_save(void)
 {
-	unsigned int flags = current->flags & PF_MEMALLOC_NOFS;
-	current->flags |= PF_MEMALLOC_NOFS;
-	return flags;
+	return memalloc_flags_save(PF_MEMALLOC_NOFS);
 }
 
 /**
@@ -367,7 +390,7 @@ static inline unsigned int memalloc_nofs_save(void)
  */
 static inline void memalloc_nofs_restore(unsigned int flags)
 {
-	current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags;
+	memalloc_flags_restore(flags);
 }
 
 /**
@@ -395,9 +418,7 @@ static inline void memalloc_nofs_restore(unsigned int flags)
  */
 static inline unsigned int memalloc_noreclaim_save(void)
 {
-	unsigned int flags = current->flags & PF_MEMALLOC;
-	current->flags |= PF_MEMALLOC;
-	return flags;
+	return memalloc_flags_save(PF_MEMALLOC);
 }
 
 /**
@@ -410,7 +431,7 @@ static inline unsigned int memalloc_noreclaim_save(void)
  */
 static inline void memalloc_noreclaim_restore(unsigned int flags)
 {
-	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
+	memalloc_flags_restore(flags);
 }
 
 /**
@@ -425,10 +446,7 @@ static inline void memalloc_noreclaim_restore(unsigned int flags)
  */
 static inline unsigned int memalloc_pin_save(void)
 {
-	unsigned int flags = current->flags & PF_MEMALLOC_PIN;
-
-	current->flags |= PF_MEMALLOC_PIN;
-	return flags;
+	return memalloc_flags_save(PF_MEMALLOC_PIN);
 }
 
 /**
@@ -441,7 +459,7 @@ static inline unsigned int memalloc_pin_save(void)
  */
 static inline void memalloc_pin_restore(unsigned int flags)
 {
-	current->flags = (current->flags & ~PF_MEMALLOC_PIN) | flags;
+	memalloc_flags_restore(flags);
 }
 
 #ifdef CONFIG_MEMCG