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
  ...

1 files changed, 39 insertions, 21 deletions

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