enable bs &#62; ps in XFS

[1] https://lore.kernel.org/linux-fsdevel/[email protected]/

---
 include/linux/pagemap.h | 107 +++++++++++++++++++++++++++++++++++-----
 mm/filemap.c            |   6 +--
 mm/readahead.c          |   4 +-
 3 files changed, 98 insertions(+), 19 deletions(-)

include/linux/pagemap.h +94 ~~-13~~

index 8026a8a433d36..8d2b5c51461b0 100644
@@ -204,14 +204,21 @@ enum mapping_flags {
 	AS_EXITING	= 4, 	/* final truncate in progress */
 	/* writeback related tags are not used */
 	AS_NO_WRITEBACK_TAGS = 5,
-	AS_LARGE_FOLIO_SUPPORT = 6,
-	AS_RELEASE_ALWAYS,	/* Call ->release_folio(), even if no private data */
-	AS_STABLE_WRITES,	/* must wait for writeback before modifying
+	AS_RELEASE_ALWAYS = 6,	/* Call ->release_folio(), even if no private data */
+	AS_STABLE_WRITES = 7,	/* must wait for writeback before modifying
 				   folio contents */
-	AS_UNMOVABLE,		/* The mapping cannot be moved, ever */
-	AS_INACCESSIBLE,	/* Do not attempt direct R/W access to the mapping */
+	AS_UNMOVABLE = 8,	/* The mapping cannot be moved, ever */
+	AS_INACCESSIBLE = 9,	/* Do not attempt direct R/W access to the mapping */
+	/* Bits 16-25 are used for FOLIO_ORDER */
+	AS_FOLIO_ORDER_BITS = 5,
+	AS_FOLIO_ORDER_MIN = 16,
+	AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS,
 };
 
+#define AS_FOLIO_ORDER_MASK     ((1u << AS_FOLIO_ORDER_BITS) - 1)
+#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_MASK << AS_FOLIO_ORDER_MIN)
+#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_MASK << AS_FOLIO_ORDER_MAX)
+
 /**
  * mapping_set_error - record a writeback error in the address_space
  * @mapping: the mapping in which an error should be set

@@ -367,9 +374,70 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 #define MAX_XAS_ORDER		(XA_CHUNK_SHIFT * 2 - 1)
 #define MAX_PAGECACHE_ORDER	min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER)
 
+/*
+ * mapping_max_folio_size_supported() - Check the max folio size supported
+ *
+ * The filesystem should call this function at mount time if there is a
+ * requirement on the folio mapping size in the page cache.
+ */
+static inline size_t mapping_max_folio_size_supported(void)
+{
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER);
+	return PAGE_SIZE;
+}
+
+/*
+ * mapping_set_folio_order_range() - Set the orders supported by a file.
+ * @mapping: The address space of the file.
+ * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive).
+ * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive).
+ *
+ * The filesystem should call this function in its inode constructor to
+ * indicate which base size (min) and maximum size (max) of folio the VFS
+ * can use to cache the contents of the file.  This should only be used
+ * if the filesystem needs special handling of folio sizes (ie there is
+ * something the core cannot know).
+ * Do not tune it based on, eg, i_size.
+ *
+ * Context: This should not be called while the inode is active as it
+ * is non-atomic.
+ */
+static inline void mapping_set_folio_order_range(struct address_space *mapping,
+						 unsigned int min,
+						 unsigned int max)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return;
+
+	if (min > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"min order > MAX_PAGECACHE_ORDER. Setting min_order to MAX_PAGECACHE_ORDER");
+		min = MAX_PAGECACHE_ORDER;
+	}
+
+	if (max > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"max order > MAX_PAGECACHE_ORDER. Setting max_order to MAX_PAGECACHE_ORDER");
+		max = MAX_PAGECACHE_ORDER;
+	}
+
+	if (max < min)
+		max = min;
+
+	mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) |
+		(min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX);
+}
+
+static inline void mapping_set_folio_min_order(struct address_space *mapping,
+					       unsigned int min)
+{
+	mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER);
+}
+
 /**
  * mapping_set_large_folios() - Indicate the file supports large folios.
- * @mapping: The file.
+ * @mapping: The address space of the file.
  *
  * The filesystem should call this function in its inode constructor to
  * indicate that the VFS can use large folios to cache the contents of

@@ -380,7 +448,23 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
  */
 static inline void mapping_set_large_folios(struct address_space *mapping)
 {
-	__set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
+	mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER);
+}
+
+static inline unsigned int
+mapping_max_folio_order(const struct address_space *mapping)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 0;
+	return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX;
+}
+
+static inline unsigned int
+mapping_min_folio_order(const struct address_space *mapping)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 0;
+	return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN;
 }
 
 /*

@@ -393,16 +477,13 @@ static inline bool mapping_large_folio_support(struct address_space *mapping)
 	VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON,
 			"Anonymous mapping always supports large folio");
 
-	return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
-		test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
+	return mapping_max_folio_order(mapping) > 0;
 }
 
 /* Return the maximum folio size for this pagecache mapping, in bytes. */
-static inline size_t mapping_max_folio_size(struct address_space *mapping)
+static inline size_t mapping_max_folio_size(const struct address_space *mapping)
 {
-	if (mapping_large_folio_support(mapping))
-		return PAGE_SIZE << MAX_PAGECACHE_ORDER;
-	return PAGE_SIZE;
+	return PAGE_SIZE << mapping_max_folio_order(mapping);
 }
 
 static inline int filemap_nr_thps(struct address_space *mapping)

mm/filemap.c +2 -4

index d62150418b910..ad5e4a848070e 100644
@@ -1933,10 +1933,8 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
 			fgp_flags |= FGP_LOCK;
 
-		if (!mapping_large_folio_support(mapping))
-			order = 0;
-		if (order > MAX_PAGECACHE_ORDER)
-			order = MAX_PAGECACHE_ORDER;
+		if (order > mapping_max_folio_order(mapping))
+			order = mapping_max_folio_order(mapping);
 		/* If we're not aligned, allocate a smaller folio */
 		if (index & ((1UL << order) - 1))
 			order = __ffs(index);

mm/readahead.c +2 -2

index 517c0be7ce665..3e5239e9e1777 100644
@@ -449,10 +449,10 @@ void page_cache_ra_order(struct readahead_control *ractl,
 
 	limit = min(limit, index + ra->size - 1);
 
-	if (new_order < MAX_PAGECACHE_ORDER)
+	if (new_order < mapping_max_folio_order(mapping))
 		new_order += 2;
 
-	new_order = min_t(unsigned int, MAX_PAGECACHE_ORDER, new_order);
+	new_order = min(mapping_max_folio_order(mapping), new_order);
 	new_order = min_t(unsigned int, new_order, ilog2(ra->size));
 
 	/* See comment in page_cache_ra_unbounded() */

Signature · 1 line

2.44.1

Matthew Wilcox

maintainer

2024-07-16 15:26 UTC #2 lore raw

Re: [PATCH v10 01/10] fs: Allow fine-grained control of folio sizes

include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 388

Quoted 12 lines · Pankaj Raghav (Samsung)

include/linux/pagemap.h +12 -0

+/*
+ * mapping_max_folio_size_supported() - Check the max folio size supported
+ *
+ * The filesystem should call this function at mount time if there is a
+ * requirement on the folio mapping size in the page cache.
+ */
+static inline size_t mapping_max_folio_size_supported(void)
+{
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER);
+	return PAGE_SIZE;
+}

There's no need for this to be part of this patch. I've removed stuff from this patch before that's not needed, please stop adding unnecessary functions. This would logically be part of patch 10.

include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 417

Quoted 12 lines

include/linux/pagemap.h +12 -0

+static inline void mapping_set_folio_order_range(struct address_space *mapping,
+						 unsigned int min,
+						 unsigned int max)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return;
+
+	if (min > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"min order > MAX_PAGECACHE_ORDER. Setting min_order to MAX_PAGECACHE_ORDER");
+		min = MAX_PAGECACHE_ORDER;
+	}

This is really too much. It's something that will never happen. Just delete the message.

include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 422

Quoted 4 lines

include/linux/pagemap.h +4 -0

+	if (max > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"max order > MAX_PAGECACHE_ORDER. Setting max_order to MAX_PAGECACHE_ORDER");
+		max = MAX_PAGECACHE_ORDER;

Absolutely not. If the filesystem declares it can support a block size of 4TB, then good for it. We just silently clamp it.

Pankaj Raghav (Samsung)

author

2024-07-17 09:46 UTC #3 lore raw

Re: [PATCH v10 01/10] fs: Allow fine-grained control of folio sizes

Quoted 17 lines · Matthew Wilcox

include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 388
Quoted 12 lines · Pankaj Raghav (Samsung)
include/linux/pagemap.h +12 -0
+/*
+ * mapping_max_folio_size_supported() - Check the max folio size supported
+ *
+ * The filesystem should call this function at mount time if there is a
+ * requirement on the folio mapping size in the page cache.
+ */
+static inline size_t mapping_max_folio_size_supported(void)
+{
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER);
+	return PAGE_SIZE;
+}
There's no need for this to be part of this patch. I've removed stuff from this patch before that's not needed, please stop adding unnecessary functions. This would logically be part of patch 10.

That makes sense. I will move it to the last patch.

Quoted 17 lines

include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 417
Quoted 13 lines
include/linux/pagemap.h +12 -0
+static inline void mapping_set_folio_order_range(struct address_space *mapping,
+						 unsigned int min,
+						 unsigned int max)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return;
+
+	if (min > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"min order > MAX_PAGECACHE_ORDER. Setting min_order to MAX_PAGECACHE_ORDER");
+		min = MAX_PAGECACHE_ORDER;
+	}
This is really too much. It's something that will never happen. Just delete the message.

Quoted 7 lines

include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 422
Quoted 4 lines
include/linux/pagemap.h +4 -0
+	if (max > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"max order > MAX_PAGECACHE_ORDER. Setting max_order to MAX_PAGECACHE_ORDER");
+		max = MAX_PAGECACHE_ORDER;
Absolutely not. If the filesystem declares it can support a block size of 4TB, then good for it. We just silently clamp it.

Hmm, but you raised the point about clamping in the previous patches[1] after Ryan pointed out that we should not silently clamp the order.

```
> It seems strange to silently clamp these? Presumably for the bs>ps usecase,
> whatever values are passed in are a hard requirement? So wouldn't want them to
> be silently reduced. (Especially given the recent change to reduce the size of
> MAX_PAGECACHE_ORDER to less then PMD size in some cases).

Hm, yes.  We should probably make this return an errno.  Including
returning an errno for !IS_ENABLED() and min > 0.
```

It was not clear from the conversation in the previous patches that we decided to just clamp the order (like it was done before).

So let's just stick with how it was done before where we clamp the values if min and max > MAX_PAGECACHE_ORDER?

Ryan Roberts

reviewer

2024-07-17 09:59 UTC #4 lore raw

Re: [PATCH v10 01/10] fs: Allow fine-grained control of folio sizes

Quoted 59 lines · Pankaj Raghav (Samsung)

Quoted 17 lines · Matthew Wilcox
include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 388
Quoted 12 lines · Pankaj Raghav (Samsung)
include/linux/pagemap.h +12 -0
+/*
+ * mapping_max_folio_size_supported() - Check the max folio size supported
+ *
+ * The filesystem should call this function at mount time if there is a
+ * requirement on the folio mapping size in the page cache.
+ */
+static inline size_t mapping_max_folio_size_supported(void)
+{
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER);
+	return PAGE_SIZE;
+}
There's no need for this to be part of this patch. I've removed stuff from this patch before that's not needed, please stop adding unnecessary functions. This would logically be part of patch 10.
That makes sense. I will move it to the last patch.
Quoted 17 lines
include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 417
Quoted 13 lines
include/linux/pagemap.h +12 -0
+static inline void mapping_set_folio_order_range(struct address_space *mapping,
+						 unsigned int min,
+						 unsigned int max)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return;
+
+	if (min > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"min order > MAX_PAGECACHE_ORDER. Setting min_order to MAX_PAGECACHE_ORDER");
+		min = MAX_PAGECACHE_ORDER;
+	}
This is really too much. It's something that will never happen. Just delete the message.
Quoted 7 lines
include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 422
Quoted 4 lines
include/linux/pagemap.h +4 -0
+	if (max > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"max order > MAX_PAGECACHE_ORDER. Setting max_order to MAX_PAGECACHE_ORDER");
+		max = MAX_PAGECACHE_ORDER;
Absolutely not. If the filesystem declares it can support a block size of 4TB, then good for it. We just silently clamp it.
Hmm, but you raised the point about clamping in the previous patches[1] after Ryan pointed out that we should not silently clamp the order.
```
> It seems strange to silently clamp these? Presumably for the bs>ps usecase,
> whatever values are passed in are a hard requirement? So wouldn't want them to
> be silently reduced. (Especially given the recent change to reduce the size of
> MAX_PAGECACHE_ORDER to less then PMD size in some cases).

Hm, yes.  We should probably make this return an errno.  Including
returning an errno for !IS_ENABLED() and min > 0.
```

Quoted 7 lines

It was not clear from the conversation in the previous patches that we decided to just clamp the order (like it was done before).
So let's just stick with how it was done before where we clamp the values if min and max > MAX_PAGECACHE_ORDER?
[1] https://lore.kernel.org/linux-fsdevel/[email protected]/

The way I see it, there are 2 approaches we could take:

1. Implement mapping_max_folio_size_supported(), write a headerdoc for mapping_set_folio_order_range() that says min must be lte max, max must be lte mapping_max_folio_size_supported(). Then emit VM_WARN() in mapping_set_folio_order_range() if the constraints are violated, and clamp to make it safe (from page cache's perspective). The VM_WARN()s can just be inline in the if statements to keep them clean. The FS is responsible for checking mapping_max_folio_size_supported() and ensuring min and max meet requirements.

2. Return an error from mapping_set_folio_order_range() (and the other functions that set min/max). No need for warning. No state changed if error is returned. FS can emit warning on error if it wants.

Personally I prefer option 2, but 1 is definitely less churn.

Thanks,
Ryan

Pankaj Raghav (Samsung)

author

2024-07-17 15:13 UTC #5 lore raw

Re: [PATCH v10 01/10] fs: Allow fine-grained control of folio sizes

Quoted 33 lines

Quoted 25 lines
Quoted 11 lines
This is really too much. It's something that will never happen. Just delete the message.
include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 422
Quoted 4 lines
include/linux/pagemap.h +4 -0
+	if (max > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"max order > MAX_PAGECACHE_ORDER. Setting max_order to MAX_PAGECACHE_ORDER");
+		max = MAX_PAGECACHE_ORDER;
Absolutely not. If the filesystem declares it can support a block size of 4TB, then good for it. We just silently clamp it.
Hmm, but you raised the point about clamping in the previous patches[1] after Ryan pointed out that we should not silently clamp the order.
```
> It seems strange to silently clamp these? Presumably for the bs>ps usecase,
> whatever values are passed in are a hard requirement? So wouldn't want them to
> be silently reduced. (Especially given the recent change to reduce the size of
> MAX_PAGECACHE_ORDER to less then PMD size in some cases).

Hm, yes.  We should probably make this return an errno.  Including
returning an errno for !IS_ENABLED() and min > 0.
```
Quoted 7 lines
It was not clear from the conversation in the previous patches that we decided to just clamp the order (like it was done before).
So let's just stick with how it was done before where we clamp the values if min and max > MAX_PAGECACHE_ORDER?
[1] https://lore.kernel.org/linux-fsdevel/[email protected]/

Quoted 7 lines

The way I see it, there are 2 approaches we could take:
1. Implement mapping_max_folio_size_supported(), write a headerdoc for mapping_set_folio_order_range() that says min must be lte max, max must be lte mapping_max_folio_size_supported(). Then emit VM_WARN() in mapping_set_folio_order_range() if the constraints are violated, and clamp to make it safe (from page cache's perspective). The VM_WARN()s can just be inline

Inlining with the if is not possible since:
91241681c62a ("include/linux/mmdebug.h: make VM_WARN* non-rvals")

Quoted 2 lines

in the if statements to keep them clean. The FS is responsible for checking mapping_max_folio_size_supported() and ensuring min and max meet requirements.

This is sort of what is done here but IIUC willy's reply to the patch, he prefers silent clamping over having WARNINGS. I think because we check the constraints during the mount time, so it should be safe to call this I guess?

Quoted 4 lines

2. Return an error from mapping_set_folio_order_range() (and the other functions that set min/max). No need for warning. No state changed if error is returned. FS can emit warning on error if it wants.

I think Chinner was not happy with this approach because this is done per inode and basically we would just shutdown the filesystem in the first inode allocation instead of refusing the mount as we know about the MAX_PAGECACHE_ORDER even during the mount phase anyway.

--
Pankaj

Darrick J. Wong

2024-07-17 15:25 UTC #6 lore raw

Re: [PATCH v10 01/10] fs: Allow fine-grained control of folio sizes

Quoted 44 lines · Pankaj Raghav (Samsung)

Quoted 33 lines
Quoted 25 lines
Quoted 11 lines
This is really too much. It's something that will never happen. Just delete the message.
include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 422
Quoted 4 lines
include/linux/pagemap.h +4 -0
+	if (max > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"max order > MAX_PAGECACHE_ORDER. Setting max_order to MAX_PAGECACHE_ORDER");
+		max = MAX_PAGECACHE_ORDER;
Absolutely not. If the filesystem declares it can support a block size of 4TB, then good for it. We just silently clamp it.
Hmm, but you raised the point about clamping in the previous patches[1] after Ryan pointed out that we should not silently clamp the order.
```
> It seems strange to silently clamp these? Presumably for the bs>ps usecase,
> whatever values are passed in are a hard requirement? So wouldn't want them to
> be silently reduced. (Especially given the recent change to reduce the size of
> MAX_PAGECACHE_ORDER to less then PMD size in some cases).

Hm, yes.  We should probably make this return an errno.  Including
returning an errno for !IS_ENABLED() and min > 0.
```
Quoted 7 lines
It was not clear from the conversation in the previous patches that we decided to just clamp the order (like it was done before).
So let's just stick with how it was done before where we clamp the values if min and max > MAX_PAGECACHE_ORDER?
[1] https://lore.kernel.org/linux-fsdevel/[email protected]/
Quoted 7 lines
The way I see it, there are 2 approaches we could take:
1. Implement mapping_max_folio_size_supported(), write a headerdoc for mapping_set_folio_order_range() that says min must be lte max, max must be lte mapping_max_folio_size_supported(). Then emit VM_WARN() in mapping_set_folio_order_range() if the constraints are violated, and clamp to make it safe (from page cache's perspective). The VM_WARN()s can just be inline
Inlining with the if is not possible since:
91241681c62a ("include/linux/mmdebug.h: make VM_WARN* non-rvals")

Quoted 7 lines

Quoted 2 lines
in the if statements to keep them clean. The FS is responsible for checking mapping_max_folio_size_supported() and ensuring min and max meet requirements.
This is sort of what is done here but IIUC willy's reply to the patch, he prefers silent clamping over having WARNINGS. I think because we check the constraints during the mount time, so it should be safe to call this I guess?

That's my read of the situation, but I'll ask about it at the next thp meeting if that helps.

Quoted 9 lines

Quoted 4 lines
2. Return an error from mapping_set_folio_order_range() (and the other functions that set min/max). No need for warning. No state changed if error is returned. FS can emit warning on error if it wants.
I think Chinner was not happy with this approach because this is done per inode and basically we would just shutdown the filesystem in the first inode allocation instead of refusing the mount as we know about the MAX_PAGECACHE_ORDER even during the mount phase anyway.

I agree. Filesystem-wide properties (e.g. fs blocksize) should cause the mount to fail if the pagecache cannot possibly handle any file blocks. Inode-specific properties (e.g. the forcealign+notears write work John Garry is working on) could error out of open() with -EIO, but that's a specialty file property.

--D

Quoted 3 lines

--
Pankaj

Ryan Roberts

reviewer

2024-07-17 15:26 UTC #7 lore raw

Re: [PATCH v10 01/10] fs: Allow fine-grained control of folio sizes

In reply to Matthew Wilcox

Quoted 35 lines · Pankaj Raghav (Samsung)

Quoted 35 lines
Quoted 25 lines
Quoted 11 lines
This is really too much. It's something that will never happen. Just delete the message.
include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 422
Quoted 4 lines
include/linux/pagemap.h +4 -0
+	if (max > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"max order > MAX_PAGECACHE_ORDER. Setting max_order to MAX_PAGECACHE_ORDER");
+		max = MAX_PAGECACHE_ORDER;
Absolutely not. If the filesystem declares it can support a block size of 4TB, then good for it. We just silently clamp it.
Hmm, but you raised the point about clamping in the previous patches[1] after Ryan pointed out that we should not silently clamp the order.
```
> It seems strange to silently clamp these? Presumably for the bs>ps usecase,
> whatever values are passed in are a hard requirement? So wouldn't want them to
> be silently reduced. (Especially given the recent change to reduce the size of
> MAX_PAGECACHE_ORDER to less then PMD size in some cases).

Hm, yes.  We should probably make this return an errno.  Including
returning an errno for !IS_ENABLED() and min > 0.
```
Quoted 7 lines
It was not clear from the conversation in the previous patches that we decided to just clamp the order (like it was done before).
So let's just stick with how it was done before where we clamp the values if min and max > MAX_PAGECACHE_ORDER?
[1] https://lore.kernel.org/linux-fsdevel/[email protected]/
The way I see it, there are 2 approaches we could take:

Quoted 8 lines

Quoted 5 lines
1. Implement mapping_max_folio_size_supported(), write a headerdoc for mapping_set_folio_order_range() that says min must be lte max, max must be lte mapping_max_folio_size_supported(). Then emit VM_WARN() in mapping_set_folio_order_range() if the constraints are violated, and clamp to make it safe (from page cache's perspective). The VM_WARN()s can just be inline
Inlining with the if is not possible since:
91241681c62a ("include/linux/mmdebug.h: make VM_WARN* non-rvals")

Ahh my bad. Could use WARN_ON()?

Quoted 8 lines

Quoted 3 lines
in the if statements to keep them clean. The FS is responsible for checking mapping_max_folio_size_supported() and ensuring min and max meet requirements.
This is sort of what is done here but IIUC willy's reply to the patch, he prefers silent clamping over having WARNINGS. I think because we check the constraints during the mount time, so it should be safe to call this I guess?

I don't want to put words in his mouth, but I thought he was complaining about the verbosity of the warnings, not their presence.

Quoted 10 lines

Quoted 5 lines
2. Return an error from mapping_set_folio_order_range() (and the other functions that set min/max). No need for warning. No state changed if error is returned. FS can emit warning on error if it wants.
I think Chinner was not happy with this approach because this is done per inode and basically we would just shutdown the filesystem in the first inode allocation instead of refusing the mount as we know about the MAX_PAGECACHE_ORDER even during the mount phase anyway.

Ahh that makes sense. Understood.

Quoted 3 lines

--
Pankaj

Pankaj Raghav (Samsung)

author

2024-07-22 14:20 UTC #8 lore raw

Re: [PATCH v10 01/10] fs: Allow fine-grained control of folio sizes

@willy:

I want to clarify before sending the next round of patches as I didn't get any reply in the previous email.

IIUC your comments properly:

- I will go back to silent clamping in mapping_set_folio_order_range as before and remove VM_WARN_ONCE().

- I will move the mapping_max_folio_size_supported() to patch 10, and FSs can use them to check for the max block size that can be supported and take the respective action.

--
Pankaj

Quoted 42 lines · Matthew Wilcox

include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 388
Quoted 12 lines · Pankaj Raghav (Samsung)
include/linux/pagemap.h +12 -0
+/*
+ * mapping_max_folio_size_supported() - Check the max folio size supported
+ *
+ * The filesystem should call this function at mount time if there is a
+ * requirement on the folio mapping size in the page cache.
+ */
+static inline size_t mapping_max_folio_size_supported(void)
+{
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER);
+	return PAGE_SIZE;
+}
There's no need for this to be part of this patch. I've removed stuff from this patch before that's not needed, please stop adding unnecessary functions. This would logically be part of patch 10.
include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 417
Quoted 12 lines
include/linux/pagemap.h +12 -0
+static inline void mapping_set_folio_order_range(struct address_space *mapping,
+						 unsigned int min,
+						 unsigned int max)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return;
+
+	if (min > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"min order > MAX_PAGECACHE_ORDER. Setting min_order to MAX_PAGECACHE_ORDER");
+		min = MAX_PAGECACHE_ORDER;
+	}
This is really too much. It's something that will never happen. Just delete the message.
include/linux/pagemap.h static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) · line 422
Quoted 4 lines
include/linux/pagemap.h +4 -0
+	if (max > MAX_PAGECACHE_ORDER) {
+		VM_WARN_ONCE(1,
+	"max order > MAX_PAGECACHE_ORDER. Setting max_order to MAX_PAGECACHE_ORDER");
+		max = MAX_PAGECACHE_ORDER;
Absolutely not. If the filesystem declares it can support a block size of 4TB, then good for it. We just silently clamp it.

Pankaj Raghav (Samsung)

author

2024-07-15 09:45 UTC #9 lore raw

PATCH v10 2/10 filemap: allocate mapping_min_order folios in the page cache

From: Pankaj Raghav <[email protected]>

filemap_create_folio() and do_read_cache_folio() were always allocating folio of order 0. __filemap_get_folio was trying to allocate higher order folios when fgp_flags had higher order hint set but it will default to order 0 folio if higher order memory allocation fails.

Supporting mapping_min_order implies that we guarantee each folio in the page cache has at least an order of mapping_min_order. When adding new folios to the page cache we must also ensure the index used is aligned to the mapping_min_order as the page cache requires the index to be aligned to the order of the folio.

Co-developed-by Luis Chamberlain <[email protected]>

Reviewed-by Matthew Wilcox (Oracle) <[email protected]>

---
 include/linux/pagemap.h | 20 ++++++++++++++++++++
 mm/filemap.c            | 24 ++++++++++++++++--------
 2 files changed, 36 insertions(+), 8 deletions(-)

include/linux/pagemap.h +20 -0

index 8d2b5c51461b0..68edbea9ae25a 100644
@@ -467,6 +467,26 @@ mapping_min_folio_order(const struct address_space *mapping)
 	return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN;
 }
 
+static inline unsigned long
+mapping_min_folio_nrpages(struct address_space *mapping)
+{
+	return 1UL << mapping_min_folio_order(mapping);
+}
+
+/**
+ * mapping_align_index() - Align index for this mapping.
+ * @mapping: The address_space.
+ *
+ * The index of a folio must be naturally aligned.  If you are adding a
+ * new folio to the page cache and need to know what index to give it,
+ * call this function.
+ */
+static inline pgoff_t mapping_align_index(struct address_space *mapping,
+					  pgoff_t index)
+{
+	return round_down(index, mapping_min_folio_nrpages(mapping));
+}
+
 /*
  * Large folio support currently depends on THP.  These dependencies are
  * being worked on but are not yet fixed.

mm/filemap.c +16 -8

index ad5e4a848070e..d27e9ac54309d 100644
@@ -859,6 +859,8 @@ noinline int __filemap_add_folio(struct address_space *mapping,
 
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
+	VM_BUG_ON_FOLIO(folio_order(folio) < mapping_min_folio_order(mapping),
+			folio);
 	mapping_set_update(&xas, mapping);
 
 	VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);

@@ -1919,8 +1921,10 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 		folio_wait_stable(folio);
 no_page:
 	if (!folio && (fgp_flags & FGP_CREAT)) {
-		unsigned order = FGF_GET_ORDER(fgp_flags);
+		unsigned int min_order = mapping_min_folio_order(mapping);
+		unsigned int order = max(min_order, FGF_GET_ORDER(fgp_flags));
 		int err;
+		index = mapping_align_index(mapping, index);
 
 		if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
 			gfp |= __GFP_WRITE;

@@ -1943,7 +1947,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 			gfp_t alloc_gfp = gfp;
 
 			err = -ENOMEM;
-			if (order > 0)
+			if (order > min_order)
 				alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN;
 			folio = filemap_alloc_folio(alloc_gfp, order);
 			if (!folio)

@@ -1958,7 +1962,7 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 				break;
 			folio_put(folio);
 			folio = NULL;
-		} while (order-- > 0);
+		} while (order-- > min_order);
 
 		if (err == -EEXIST)
 			goto repeat;

@@ -2447,13 +2451,15 @@ static int filemap_update_page(struct kiocb *iocb,
 }
 
 static int filemap_create_folio(struct file *file,
-		struct address_space *mapping, pgoff_t index,
+		struct address_space *mapping, loff_t pos,
 		struct folio_batch *fbatch)
 {
 	struct folio *folio;
 	int error;
+	unsigned int min_order = mapping_min_folio_order(mapping);
+	pgoff_t index;
 
-	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0);
+	folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order);
 	if (!folio)
 		return -ENOMEM;

@@ -2471,6 +2477,7 @@ static int filemap_create_folio(struct file *file,
 	 * well to keep locking rules simple.
 	 */
 	filemap_invalidate_lock_shared(mapping);
+	index = (pos >> (PAGE_SHIFT + min_order)) << min_order;
 	error = filemap_add_folio(mapping, folio, index,
 			mapping_gfp_constraint(mapping, GFP_KERNEL));
 	if (error == -EEXIST)

@@ -2531,8 +2538,7 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count,
 	if (!folio_batch_count(fbatch)) {
 		if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ))
 			return -EAGAIN;
-		err = filemap_create_folio(filp, mapping,
-				iocb->ki_pos >> PAGE_SHIFT, fbatch);
+		err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch);
 		if (err == AOP_TRUNCATED_PAGE)
 			goto retry;
 		return err;

@@ -3748,9 +3754,11 @@ static struct folio *do_read_cache_folio(struct address_space *mapping,
 repeat:
 	folio = filemap_get_folio(mapping, index);
 	if (IS_ERR(folio)) {
-		folio = filemap_alloc_folio(gfp, 0);
+		folio = filemap_alloc_folio(gfp,
+					    mapping_min_folio_order(mapping));
 		if (!folio)
 			return ERR_PTR(-ENOMEM);
+		index = mapping_align_index(mapping, index);
 		err = filemap_add_folio(mapping, folio, index, gfp);
 		if (unlikely(err)) {
 			folio_put(folio);

Signature · 1 line

2.44.1

Pankaj Raghav (Samsung)

author

2024-07-15 09:45 UTC #10 lore raw

PATCH v10 3/10 readahead: allocate folios with mapping_min_order in readahead

From: Pankaj Raghav <[email protected]>

page_cache_ra_unbounded() was allocating single pages (0 order folios) if there was no folio found in an index. Allocate mapping_min_order folios as we need to guarantee the minimum order if it is set.

page_cache_ra_order() tries to allocate folio to the page cache with a higher order if the index aligns with that order. Modify it so that the order does not go below the mapping_min_order requirement of the page cache. This function will do the right thing even if the new_order passed is less than the mapping_min_order.
When adding new folios to the page cache we must also ensure the index used is aligned to the mapping_min_order as the page cache requires the index to be aligned to the order of the folio.

readahead_expand() is called from readahead aops to extend the range of the readahead so this function can assume ractl->_index to be aligned with min_order.

Co-developed-by Hannes Reinecke <[email protected]>

Signed-off-by Hannes Reinecke <[email protected]>

Acked-by Darrick J. Wong <[email protected]>

---
 mm/readahead.c | 79 ++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 61 insertions(+), 18 deletions(-)

mm/readahead.c +61 ~~-18~~

index 3e5239e9e1777..2078c42777a62 100644
@@ -206,9 +206,10 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 		unsigned long nr_to_read, unsigned long lookahead_size)
 {
 	struct address_space *mapping = ractl->mapping;
-	unsigned long index = readahead_index(ractl);
+	unsigned long ra_folio_index, index = readahead_index(ractl);
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
-	unsigned long i;
+	unsigned long mark, i = 0;
+	unsigned int min_nrpages = mapping_min_folio_nrpages(mapping);
 
 	/*
 	 * Partway through the readahead operation, we will have added

@@ -223,10 +224,24 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	unsigned int nofs = memalloc_nofs_save();
 
 	filemap_invalidate_lock_shared(mapping);
+	index = mapping_align_index(mapping, index);
+
+	/*
+	 * As iterator `i` is aligned to min_nrpages, round_up the
+	 * difference between nr_to_read and lookahead_size to mark the
+	 * index that only has lookahead or "async_region" to set the
+	 * readahead flag.
+	 */
+	ra_folio_index = round_up(readahead_index(ractl) + nr_to_read - lookahead_size,
+				  min_nrpages);
+	mark = ra_folio_index - index;
+	nr_to_read += readahead_index(ractl) - index;
+	ractl->_index = index;
+
 	/*
 	 * Preallocate as many pages as we will need.
 	 */
-	for (i = 0; i < nr_to_read; i++) {
+	while (i < nr_to_read) {
 		struct folio *folio = xa_load(&mapping->i_pages, index + i);
 		int ret;

@@ -240,12 +255,13 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			 * not worth getting one just for that.
 			 */
 			read_pages(ractl);
-			ractl->_index++;
-			i = ractl->_index + ractl->_nr_pages - index - 1;
+			ractl->_index += min_nrpages;
+			i = ractl->_index + ractl->_nr_pages - index;
 			continue;
 		}
 
-		folio = filemap_alloc_folio(gfp_mask, 0);
+		folio = filemap_alloc_folio(gfp_mask,
+					    mapping_min_folio_order(mapping));
 		if (!folio)
 			break;

@@ -255,14 +271,15 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 			if (ret == -ENOMEM)
 				break;
 			read_pages(ractl);
-			ractl->_index++;
-			i = ractl->_index + ractl->_nr_pages - index - 1;
+			ractl->_index += min_nrpages;
+			i = ractl->_index + ractl->_nr_pages - index;
 			continue;
 		}
-		if (i == nr_to_read - lookahead_size)
+		if (i == mark)
 			folio_set_readahead(folio);
 		ractl->_workingset |= folio_test_workingset(folio);
-		ractl->_nr_pages++;
+		ractl->_nr_pages += min_nrpages;
+		i += min_nrpages;
 	}
 
 	/*

@@ -438,13 +455,19 @@ void page_cache_ra_order(struct readahead_control *ractl,
 	struct address_space *mapping = ractl->mapping;
 	pgoff_t start = readahead_index(ractl);
 	pgoff_t index = start;
+	unsigned int min_order = mapping_min_folio_order(mapping);
 	pgoff_t limit = (i_size_read(mapping->host) - 1) >> PAGE_SHIFT;
 	pgoff_t mark = index + ra->size - ra->async_size;
 	unsigned int nofs;
 	int err = 0;
 	gfp_t gfp = readahead_gfp_mask(mapping);
+	unsigned int min_ra_size = max(4, mapping_min_folio_nrpages(mapping));
 
-	if (!mapping_large_folio_support(mapping) || ra->size < 4)
+	/*
+	 * Fallback when size < min_nrpages as each folio should be
+	 * at least min_nrpages anyway.
+	 */
+	if (!mapping_large_folio_support(mapping) || ra->size < min_ra_size)
 		goto fallback;
 
 	limit = min(limit, index + ra->size - 1);

@@ -454,10 +477,19 @@ void page_cache_ra_order(struct readahead_control *ractl,
 
 	new_order = min(mapping_max_folio_order(mapping), new_order);
 	new_order = min_t(unsigned int, new_order, ilog2(ra->size));
+	new_order = max(new_order, min_order);
 
 	/* See comment in page_cache_ra_unbounded() */
 	nofs = memalloc_nofs_save();
 	filemap_invalidate_lock_shared(mapping);
+	/*
+	 * If the new_order is greater than min_order and index is
+	 * already aligned to new_order, then this will be noop as index
+	 * aligned to new_order should also be aligned to min_order.
+	 */
+	ractl->_index = mapping_align_index(mapping, index);
+	index = readahead_index(ractl);
+
 	while (index <= limit) {
 		unsigned int order = new_order;

@@ -465,7 +497,7 @@ void page_cache_ra_order(struct readahead_control *ractl,
 		if (index & ((1UL << order) - 1))
 			order = __ffs(index);
 		/* Don't allocate pages past EOF */
-		while (index + (1UL << order) - 1 > limit)
+		while (order > min_order && index + (1UL << order) - 1 > limit)
 			order--;
 		err = ra_alloc_folio(ractl, index, mark, order, gfp);
 		if (err)

@@ -703,8 +735,15 @@ void readahead_expand(struct readahead_control *ractl,
 	struct file_ra_state *ra = ractl->ra;
 	pgoff_t new_index, new_nr_pages;
 	gfp_t gfp_mask = readahead_gfp_mask(mapping);
+	unsigned long min_nrpages = mapping_min_folio_nrpages(mapping);
+	unsigned int min_order = mapping_min_folio_order(mapping);
 
 	new_index = new_start / PAGE_SIZE;
+	/*
+	 * Readahead code should have aligned the ractl->_index to
+	 * min_nrpages before calling readahead aops.
+	 */
+	VM_BUG_ON(!IS_ALIGNED(ractl->_index, min_nrpages));
 
 	/* Expand the leading edge downwards */
 	while (ractl->_index > new_index) {

@@ -714,9 +753,11 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, 0);
+		folio = filemap_alloc_folio(gfp_mask, min_order);
 		if (!folio)
 			return;
+
+		index = mapping_align_index(mapping, index);
 		if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) {
 			folio_put(folio);
 			return;

@@ -726,7 +767,7 @@ void readahead_expand(struct readahead_control *ractl,
 			ractl->_workingset = true;
 			psi_memstall_enter(&ractl->_pflags);
 		}
-		ractl->_nr_pages++;
+		ractl->_nr_pages += min_nrpages;
 		ractl->_index = folio->index;
 	}

@@ -741,9 +782,11 @@ void readahead_expand(struct readahead_control *ractl,
 		if (folio && !xa_is_value(folio))
 			return; /* Folio apparently present */
 
-		folio = filemap_alloc_folio(gfp_mask, 0);
+		folio = filemap_alloc_folio(gfp_mask, min_order);
 		if (!folio)
 			return;
+
+		index = mapping_align_index(mapping, index);
 		if (filemap_add_folio(mapping, folio, index, gfp_mask) < 0) {
 			folio_put(folio);
 			return;

@@ -753,10 +796,10 @@ void readahead_expand(struct readahead_control *ractl,
 			ractl->_workingset = true;
 			psi_memstall_enter(&ractl->_pflags);
 		}
-		ractl->_nr_pages++;
+		ractl->_nr_pages += min_nrpages;
 		if (ra) {
-			ra->size++;
-			ra->async_size++;
+			ra->size += min_nrpages;
+			ra->async_size += min_nrpages;
 		}
 	}
 }

Signature · 1 line

2.44.1

Pankaj Raghav (Samsung)

author

2024-07-15 09:45 UTC #11 lore raw

PATCH v10 4/10 mm: split a folio in minimum folio order chunks

From: Luis Chamberlain <[email protected]>

split_folio() and split_folio_to_list() assume order 0, to support minorder for non-anonymous folios, we must expand these to check the folio mapping order and use that.

Set new_order to be at least minimum folio order if it is set in split_huge_page_to_list() so that we can maintain minimum folio order requirement in the page cache.

Update the debugfs write files used for testing to ensure the order is respected as well. We simply enforce the min order when a file mapping is used.

Reviewed-by Zi Yan <[email protected]>

---
 include/linux/huge_mm.h | 14 +++++++---
 mm/huge_memory.c        | 59 ++++++++++++++++++++++++++++++++++++++---
 2 files changed, 65 insertions(+), 8 deletions(-)

include/linux/huge_mm.h +10 -4

index cee3c5da8f0ed..b6024bf39a9fe 100644
@@ -90,6 +90,8 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr;
 #define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \
 	(!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order)))
 
+#define split_folio(f) split_folio_to_list(f, NULL)
+
 #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES
 #define HPAGE_PMD_SHIFT PMD_SHIFT
 #define HPAGE_PUD_SHIFT PUD_SHIFT

@@ -323,9 +325,10 @@ unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long add
 bool can_split_folio(struct folio *folio, int *pextra_pins);
 int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
 		unsigned int new_order);
+int split_folio_to_list(struct folio *folio, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {
-	return split_huge_page_to_list_to_order(page, NULL, 0);
+	return split_folio(page_folio(page));
 }
 void deferred_split_folio(struct folio *folio);

@@ -490,6 +493,12 @@ static inline int split_huge_page(struct page *page)
 {
 	return 0;
 }
+
+static inline int split_folio_to_list(struct folio *folio, struct list_head *list)
+{
+	return 0;
+}
+
 static inline void deferred_split_folio(struct folio *folio) {}
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)

@@ -604,7 +613,4 @@ static inline int split_folio_to_order(struct folio *folio, int new_order)
 	return split_folio_to_list_to_order(folio, NULL, new_order);
 }
 
-#define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0)
-#define split_folio(f) split_folio_to_order(f, 0)
-
 #endif /* _LINUX_HUGE_MM_H */

mm/huge_memory.c +55 -4

134 lines not on this page · raw message

Signature · 1 line

2.44.1

Pankaj Raghav (Samsung)

author

2024-07-15 09:45 UTC #12 lore raw

PATCH v10 5/10 filemap: cap PTE range to be created to allowed zero fill in folio_map_range()

From: Pankaj Raghav <[email protected]>

Usually the page cache does not extend beyond the size of the inode, therefore, no PTEs are created for folios that extend beyond the size.

But with LBS support, we might extend page cache beyond the size of the inode as we need to guarantee folios of minimum order. While doing a read, do_fault_around() can create PTEs for pages that lie beyond the EOF leading to incorrect error return when accessing a page beyond the mapped file.

Cap the PTE range to be created for the page cache up to the end of file(EOF) in filemap_map_pages() so that return error codes are consistent with POSIX[1] for LBS configurations.

generic/749(currently in xfstest-dev patches-in-queue branch [0]) has been created to trigger this edge case. This also fixes generic/749 for tmpfs with huge=always on systems with 4k base page size.

[0] https://lore.kernel.org/all/[email protected]/
[1](from mmap(2)) SIGBUS
Attempted access to a page of the buffer that lies beyond the end of the mapped file. For an explanation of the treatment of the bytes in the page that corresponds to the end of a mapped file that is not a multiple of the page size, see NOTES.

Reviewed-by Matthew Wilcox (Oracle) <[email protected]>

---
 mm/filemap.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

mm/filemap.c +5 -1

index d27e9ac54309d..d322109274532 100644
@@ -3608,7 +3608,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	struct vm_area_struct *vma = vmf->vma;
 	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
-	pgoff_t last_pgoff = start_pgoff;
+	pgoff_t file_end, last_pgoff = start_pgoff;
 	unsigned long addr;
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct folio *folio;

@@ -3634,6 +3634,10 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		goto out;
 	}
 
+	file_end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE) - 1;
+	if (end_pgoff > file_end)
+		end_pgoff = file_end;
+
 	folio_type = mm_counter_file(folio);
 	do {
 		unsigned long end;

Signature · 1 line

2.44.1

Pankaj Raghav (Samsung)

author

2024-07-15 09:45 UTC #13 lore raw

PATCH v10 6/10 iomap: fix iomap_dio_zero() for fs bs > system page size

From: Pankaj Raghav <[email protected]>

iomap_dio_zero() will pad a fs block with zeroes if the direct IO size < fs block size. iomap_dio_zero() has an implicit assumption that fs block size < page_size. This is true for most filesystems at the moment.

If the block size > page size, this will send the contents of the page next to zero page(as len > PAGE_SIZE) to the underlying block device, causing FS corruption.

iomap is a generic infrastructure and it should not make any assumptions about the fs block size and the page size of the system.

Reviewed-by Dave Chinner <[email protected]>

---
 fs/iomap/buffered-io.c |  4 ++--
 fs/iomap/direct-io.c   | 45 ++++++++++++++++++++++++++++++++++++------
 2 files changed, 41 insertions(+), 8 deletions(-)

fs/iomap/buffered-io.c +2 -2

index f420c53d86acc..d745f718bcde8 100644
@@ -2007,10 +2007,10 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);
 
-static int __init iomap_init(void)
+static int __init iomap_buffered_init(void)
 {
 	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
 			   offsetof(struct iomap_ioend, io_bio),
 			   BIOSET_NEED_BVECS);
 }
-fs_initcall(iomap_init);
+fs_initcall(iomap_buffered_init);

fs/iomap/direct-io.c +39 -6

90 lines not on this page · raw message

Signature · 1 line

2.44.1

Pankaj Raghav (Samsung)

author

2024-07-15 09:45 UTC #14 lore raw

PATCH v10 7/10 xfs: use kvmalloc for xattr buffers

From: Dave Chinner <[email protected]>

Pankaj Raghav reported that when filesystem block size is larger than page size, the xattr code can use kmalloc() for high order allocations. This triggers a useless warning in the allocator as it is a __GFP_NOFAIL allocation here:

static inline
struct page *rmqueue(struct zone *preferred_zone,
struct zone *zone, unsigned int order, gfp_t gfp_flags, unsigned int alloc_flags, int migratetype)

{
        struct page *page;

        /*
         * We most definitely don't want callers attempting to
         * allocate greater than order-1 page units with __GFP_NOFAIL.
         */

Quoted 1 line

Quoted 1 line
Quoted 1 line
Quoted 1 line
   WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));

...

Fix this by changing all these call sites to use kvmalloc(), which will strip the NOFAIL from the kmalloc attempt and if that fails will do a __GFP_NOFAIL vmalloc().

This is not an issue that productions systems will see as filesystems with block size > page size cannot be mounted by the kernel; Pankaj is developing this functionality right now.

Reported-by Pankaj Raghav <[email protected]>

Fixes f078d4ea8276 ("xfs: convert kmem_alloc() to kmalloc()")

Signed-off-by Dave Chinner <[email protected]>

Reviewed-by Pankaj Raghav <[email protected]>

---
 fs/xfs/libxfs/xfs_attr_leaf.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

fs/xfs/libxfs/xfs_attr_leaf.c +6 -9

index b9e98950eb3d8..09f4cb061a6e0 100644
@@ -1138,10 +1138,7 @@ xfs_attr3_leaf_to_shortform(
 
 	trace_xfs_attr_leaf_to_sf(args);
 
-	tmpbuffer = kmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
-	if (!tmpbuffer)
-		return -ENOMEM;
-
+	tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
 	memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
 
 	leaf = (xfs_attr_leafblock_t *)tmpbuffer;

@@ -1205,7 +1202,7 @@ xfs_attr3_leaf_to_shortform(
 	error = 0;
 
 out:
-	kfree(tmpbuffer);
+	kvfree(tmpbuffer);
 	return error;
 }

@@ -1613,7 +1610,7 @@ xfs_attr3_leaf_compact(
 
 	trace_xfs_attr_leaf_compact(args);
 
-	tmpbuffer = kmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
+	tmpbuffer = kvmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
 	memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
 	memset(bp->b_addr, 0, args->geo->blksize);
 	leaf_src = (xfs_attr_leafblock_t *)tmpbuffer;

@@ -1651,7 +1648,7 @@ xfs_attr3_leaf_compact(
 	 */
 	xfs_trans_log_buf(trans, bp, 0, args->geo->blksize - 1);
 
-	kfree(tmpbuffer);
+	kvfree(tmpbuffer);
 }
 
 /*

@@ -2330,7 +2327,7 @@ xfs_attr3_leaf_unbalance(
 		struct xfs_attr_leafblock *tmp_leaf;
 		struct xfs_attr3_icleaf_hdr tmphdr;
 
-		tmp_leaf = kzalloc(state->args->geo->blksize,
+		tmp_leaf = kvzalloc(state->args->geo->blksize,
 				GFP_KERNEL | __GFP_NOFAIL);
 
 		/*

@@ -2371,7 +2368,7 @@ xfs_attr3_leaf_unbalance(
 		}
 		memcpy(save_leaf, tmp_leaf, state->args->geo->blksize);
 		savehdr = tmphdr; /* struct copy */
-		kfree(tmp_leaf);
+		kvfree(tmp_leaf);
 	}
 
 	xfs_attr3_leaf_hdr_to_disk(state->args->geo, save_leaf, &savehdr);

Signature · 1 line

2.44.1

Pankaj Raghav (Samsung)

author

2024-07-15 09:45 UTC #15 lore raw

PATCH v10 8/10 xfs: expose block size in stat

[1] https://lwn.net/ml/linux-fsdevel/[email protected]/

From: Pankaj Raghav <[email protected]>

For block size larger than page size, the unit of efficient IO is the block size, not the page size. Leaving stat() to report PAGE_SIZE as the block size causes test programs like fsx to issue illegal ranges for operations that require block size alignment (e.g. fallocate() insert range). Hence update the preferred IO size to reflect the block size in this case.

This change is based on a patch originally from Dave Chinner.[1]

Reviewed-by Dave Chinner <[email protected]>

---
 fs/xfs/xfs_iops.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

fs/xfs/xfs_iops.c +1 -1

index a00dcbc77e12b..da5c13150315e 100644
@@ -562,7 +562,7 @@ xfs_stat_blksize(
 			return 1U << mp->m_allocsize_log;
 	}
 
-	return PAGE_SIZE;
+	return max_t(uint32_t, PAGE_SIZE, mp->m_sb.sb_blocksize);
 }
 
 STATIC int

Signature · 1 line

2.44.1

Pankaj Raghav (Samsung)

author

2024-07-15 09:45 UTC #16 lore raw

PATCH v10 9/10 xfs: make the calculation generic in xfs_sb_validate_fsb_count()

From: Pankaj Raghav <[email protected]>

Instead of assuming that PAGE_SHIFT is always higher than the blocklog, make the calculation generic so that page cache count can be calculated correctly for LBS.

Reviewed-by Dave Chinner <[email protected]>

---
 fs/xfs/xfs_mount.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

fs/xfs/xfs_mount.c +6 -1

index 09eef1721ef4f..3949f720b5354 100644
@@ -132,11 +132,16 @@ xfs_sb_validate_fsb_count(
 	xfs_sb_t	*sbp,
 	uint64_t	nblocks)
 {
+	uint64_t		max_bytes;
+
 	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
 
+	if (check_shl_overflow(nblocks, sbp->sb_blocklog, &max_bytes))
+		return -EFBIG;
+
 	/* Limited by ULONG_MAX of page cache index */
-	if (nblocks >> (PAGE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
+	if (max_bytes >> PAGE_SHIFT > ULONG_MAX)
 		return -EFBIG;
 	return 0;
 }

Signature · 1 line

2.44.1

Pankaj Raghav (Samsung)

author

2024-07-15 09:45 UTC #17 lore raw

PATCH v10 10/10 xfs: enable block size larger than page size support

From: Pankaj Raghav <[email protected]>

Page cache now has the ability to have a minimum order when allocating a folio which is a prerequisite to add support for block size > page size.

---
 fs/xfs/libxfs/xfs_ialloc.c |  5 +++++
 fs/xfs/libxfs/xfs_shared.h |  3 +++
 fs/xfs/xfs_icache.c        |  6 ++++--
 fs/xfs/xfs_mount.c         |  1 -
 fs/xfs/xfs_super.c         | 30 ++++++++++++++++++++++--------
 5 files changed, 34 insertions(+), 11 deletions(-)

fs/xfs/libxfs/xfs_ialloc.c +5 -0

index 14c81f227c5bb..1e76431d75a4b 100644
@@ -3019,6 +3019,11 @@ xfs_ialloc_setup_geometry(
 		igeo->ialloc_align = mp->m_dalign;
 	else
 		igeo->ialloc_align = 0;
+
+	if (mp->m_sb.sb_blocksize > PAGE_SIZE)
+		igeo->min_folio_order = mp->m_sb.sb_blocklog - PAGE_SHIFT;
+	else
+		igeo->min_folio_order = 0;
 }
 
 /* Compute the location of the root directory inode that is laid out by mkfs. */

fs/xfs/libxfs/xfs_shared.h +3 -0

index 34f104ed372c0..e67a1c7cc0b02 100644
@@ -231,6 +231,9 @@ struct xfs_ino_geometry {
 	/* precomputed value for di_flags2 */
 	uint64_t	new_diflags2;
 
+	/* minimum folio order of a page cache allocation */
+	unsigned int	min_folio_order;
+
 };
 
 #endif /* __XFS_SHARED_H__ */

fs/xfs/xfs_icache.c +4 -2

index cf629302d48e7..0fcf235e50235 100644
@@ -88,7 +88,8 @@ xfs_inode_alloc(
 
 	/* VFS doesn't initialise i_mode! */
 	VFS_I(ip)->i_mode = 0;
-	mapping_set_large_folios(VFS_I(ip)->i_mapping);
+	mapping_set_folio_min_order(VFS_I(ip)->i_mapping,
+				    M_IGEO(mp)->min_folio_order);
 
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);

@@ -325,7 +326,8 @@ xfs_reinit_inode(
 	inode->i_uid = uid;
 	inode->i_gid = gid;
 	inode->i_state = state;
-	mapping_set_large_folios(inode->i_mapping);
+	mapping_set_folio_min_order(inode->i_mapping,
+				    M_IGEO(mp)->min_folio_order);
 	return error;
 }

fs/xfs/xfs_mount.c +0 -1

index 3949f720b5354..c6933440f8066 100644
@@ -134,7 +134,6 @@ xfs_sb_validate_fsb_count(
 {
 	uint64_t		max_bytes;
 
-	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
 
 	if (check_shl_overflow(nblocks, sbp->sb_blocklog, &max_bytes))

fs/xfs/xfs_super.c +22 -8

index 27e9f749c4c7f..3c455ef588d48 100644
@@ -1638,16 +1638,30 @@ xfs_fs_fill_super(
 		goto out_free_sb;
 	}
 
-	/*
-	 * Until this is fixed only page-sized or smaller data blocks work.
-	 */
 	if (mp->m_sb.sb_blocksize > PAGE_SIZE) {
-		xfs_warn(mp,
-		"File system with blocksize %d bytes. "
-		"Only pagesize (%ld) or less will currently work.",
+		size_t max_folio_size = mapping_max_folio_size_supported();
+
+		if (!xfs_has_crc(mp)) {
+			xfs_warn(mp,
+"V4 Filesystem with blocksize %d bytes. Only pagesize (%ld) or less is supported.",
 				mp->m_sb.sb_blocksize, PAGE_SIZE);
-		error = -ENOSYS;
-		goto out_free_sb;
+			error = -ENOSYS;
+			goto out_free_sb;
+		}
+
+		if (mp->m_sb.sb_blocksize > max_folio_size) {
+			xfs_warn(mp,
+"block size (%u bytes) not supported; maximum folio size supported in "\
+"the page cache is (%ld bytes). Check MAX_PAGECACHE_ORDER (%d)",
+			mp->m_sb.sb_blocksize, max_folio_size,
+			MAX_PAGECACHE_ORDER);
+			error = -ENOSYS;
+			goto out_free_sb;
+		}
+
+		xfs_warn(mp,
+"EXPERIMENTAL: V5 Filesystem with Large Block Size (%d bytes) enabled.",
+			mp->m_sb.sb_blocksize);
 	}
 
 	/* Ensure this filesystem fits in the page cache limits */

Signature · 1 line

2.44.1

Darrick J. Wong

Reviewed-by on v10 10/10

2024-07-15 16:46 UTC #18 lore raw

Re: [PATCH v10 10/10] xfs: enable block size larger than page size support

Quoted 107 lines · Pankaj Raghav (Samsung)

From: Pankaj Raghav <[email protected]>

Page cache now has the ability to have a minimum order when allocating a folio which is a prerequisite to add support for block size > page size.

---
 fs/xfs/libxfs/xfs_ialloc.c |  5 +++++
 fs/xfs/libxfs/xfs_shared.h |  3 +++
 fs/xfs/xfs_icache.c        |  6 ++++--
 fs/xfs/xfs_mount.c         |  1 -
 fs/xfs/xfs_super.c         | 30 ++++++++++++++++++++++--------
 5 files changed, 34 insertions(+), 11 deletions(-)

fs/xfs/libxfs/xfs_ialloc.c +5 -0

index 14c81f227c5bb..1e76431d75a4b 100644
@@ -3019,6 +3019,11 @@ xfs_ialloc_setup_geometry(
 		igeo->ialloc_align = mp->m_dalign;
 	else
 		igeo->ialloc_align = 0;
+
+	if (mp->m_sb.sb_blocksize > PAGE_SIZE)
+		igeo->min_folio_order = mp->m_sb.sb_blocklog - PAGE_SHIFT;
+	else
+		igeo->min_folio_order = 0;
 }
 
 /* Compute the location of the root directory inode that is laid out by mkfs. */

fs/xfs/libxfs/xfs_shared.h +3 -0

index 34f104ed372c0..e67a1c7cc0b02 100644
@@ -231,6 +231,9 @@ struct xfs_ino_geometry {
 	/* precomputed value for di_flags2 */
 	uint64_t	new_diflags2;
 
+	/* minimum folio order of a page cache allocation */
+	unsigned int	min_folio_order;
+
 };
 
 #endif /* __XFS_SHARED_H__ */

fs/xfs/xfs_icache.c +4 -2

index cf629302d48e7..0fcf235e50235 100644
@@ -88,7 +88,8 @@ xfs_inode_alloc(
 
 	/* VFS doesn't initialise i_mode! */
 	VFS_I(ip)->i_mode = 0;
-	mapping_set_large_folios(VFS_I(ip)->i_mapping);
+	mapping_set_folio_min_order(VFS_I(ip)->i_mapping,
+				    M_IGEO(mp)->min_folio_order);
 
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);

@@ -325,7 +326,8 @@ xfs_reinit_inode(
 	inode->i_uid = uid;
 	inode->i_gid = gid;
 	inode->i_state = state;
-	mapping_set_large_folios(inode->i_mapping);
+	mapping_set_folio_min_order(inode->i_mapping,
+				    M_IGEO(mp)->min_folio_order);
 	return error;
 }

fs/xfs/xfs_mount.c +0 -1

index 3949f720b5354..c6933440f8066 100644
@@ -134,7 +134,6 @@ xfs_sb_validate_fsb_count(
 {
 	uint64_t		max_bytes;
 
-	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
 
 	if (check_shl_overflow(nblocks, sbp->sb_blocklog, &max_bytes))

fs/xfs/xfs_super.c +7 -8

index 27e9f749c4c7f..3c455ef588d48 100644
@@ -1638,16 +1638,30 @@ xfs_fs_fill_super(
 		goto out_free_sb;
 	}
 
-	/*
-	 * Until this is fixed only page-sized or smaller data blocks work.
-	 */
 	if (mp->m_sb.sb_blocksize > PAGE_SIZE) {
-		xfs_warn(mp,
-		"File system with blocksize %d bytes. "
-		"Only pagesize (%ld) or less will currently work.",
+		size_t max_folio_size = mapping_max_folio_size_supported();
+
+		if (!xfs_has_crc(mp)) {
+			xfs_warn(mp,
+"V4 Filesystem with blocksize %d bytes. Only pagesize (%ld) or less is supported.",
 				mp->m_sb.sb_blocksize, PAGE_SIZE);
-		error = -ENOSYS;
-		goto out_free_sb;
+			error = -ENOSYS;
+			goto out_free_sb;

fs/xfs/xfs_super.c xfs_fs_fill_super( · line 1659

Quoted 10 lines

fs/xfs/xfs_super.c +10 -0

+		}
+
+		if (mp->m_sb.sb_blocksize > max_folio_size) {
+			xfs_warn(mp,
+"block size (%u bytes) not supported; maximum folio size supported in "\
+"the page cache is (%ld bytes). Check MAX_PAGECACHE_ORDER (%d)",
+			mp->m_sb.sb_blocksize, max_folio_size,
+			MAX_PAGECACHE_ORDER);
+			error = -ENOSYS;
+			goto out_free_sb;

Nit: Continuation lines should be indented, not lined up with the next statement:

xfs_warn(mp,
"block size (%u bytes) not supported; maximum folio size supported in "\
"the page cache is (%ld bytes). Check MAX_PAGECACHE_ORDER (%d)",

					mp->m_sb.sb_blocksize,
					max_folio_size,
					MAX_PAGECACHE_ORDER);
			error = -ENOSYS;
			goto out_free_sb;

With that fixed,

--D

Quoted 12 lines

fs/xfs/xfs_super.c +5 -0

+		}
+
+		xfs_warn(mp,
+"EXPERIMENTAL: V5 Filesystem with Large Block Size (%d bytes) enabled.",
+			mp->m_sb.sb_blocksize);
 	}
 
 	/* Ensure this filesystem fits in the page cache limits */

Signature · 1 line

2.44.1

Pankaj Raghav (Samsung)

author

2024-07-22 14:12 UTC #19 lore raw

Re: [PATCH v10 10/10] xfs: enable block size larger than page size support

Quoted 13 lines

fs/xfs/xfs_super.c xfs_fs_fill_super( · line 1659
Quoted 9 lines
fs/xfs/xfs_super.c +9 -0
+
+		if (mp->m_sb.sb_blocksize > max_folio_size) {
+			xfs_warn(mp,
+"block size (%u bytes) not supported; maximum folio size supported in "\
+"the page cache is (%ld bytes). Check MAX_PAGECACHE_ORDER (%d)",
+			mp->m_sb.sb_blocksize, max_folio_size,
+			MAX_PAGECACHE_ORDER);
+			error = -ENOSYS;
+			goto out_free_sb;
Nit: Continuation lines should be indented, not lined up with the next statement:

Quoted 8 lines

xfs_warn(mp,
"block size (%u bytes) not supported; maximum folio size supported in "\
"the page cache is (%ld bytes). Check MAX_PAGECACHE_ORDER (%d)",
					mp->m_sb.sb_blocksize,
					max_folio_size,
					MAX_PAGECACHE_ORDER);
			error = -ENOSYS;
			goto out_free_sb;

@Darrick: As willy pointed out, the error message is a bit long here. Can we make as follows:

"block size (%u bytes) not supported; Only block size (%ld) or less is supported "\

                                        mp->m_sb.sb_blocksize,
                                        max_folio_size);

This is similar to the previous error and it is more concise IMO.

Quoted 6 lines

With that fixed,
Reviewed-by Darrick J. Wong <[email protected]>
--D

Darrick J. Wong

2024-07-22 18:49 UTC #20 lore raw

Re: [PATCH v10 10/10] xfs: enable block size larger than page size support

Quoted 22 lines · Pankaj Raghav (Samsung)

Quoted 13 lines
fs/xfs/xfs_super.c xfs_fs_fill_super( · line 1659
Quoted 9 lines
fs/xfs/xfs_super.c +9 -0
+
+		if (mp->m_sb.sb_blocksize > max_folio_size) {
+			xfs_warn(mp,
+"block size (%u bytes) not supported; maximum folio size supported in "\
+"the page cache is (%ld bytes). Check MAX_PAGECACHE_ORDER (%d)",
+			mp->m_sb.sb_blocksize, max_folio_size,
+			MAX_PAGECACHE_ORDER);
+			error = -ENOSYS;
+			goto out_free_sb;
Nit: Continuation lines should be indented, not lined up with the next statement:
Quoted 8 lines
xfs_warn(mp,
"block size (%u bytes) not supported; maximum folio size supported in "\
"the page cache is (%ld bytes). Check MAX_PAGECACHE_ORDER (%d)",
					mp->m_sb.sb_blocksize,
					max_folio_size,
					MAX_PAGECACHE_ORDER);
			error = -ENOSYS;
			goto out_free_sb;

Quoted 8 lines

@Darrick: As willy pointed out, the error message is a bit long here. Can we make as follows:
"block size (%u bytes) not supported; Only block size (%ld) or less is supported "\
                                        mp->m_sb.sb_blocksize,
                                        max_folio_size);
This is similar to the previous error and it is more concise IMO.

Ah, ok. I suppose printing max_folio_size *and* MAX_PAGECACHE_ORDER is redundant. The shortened version above is ok by me.

--D

Quoted 7 lines

Quoted 6 lines
With that fixed,
Reviewed-by Darrick J. Wong <[email protected]>
--D

Matthew Wilcox

maintainer

2024-07-16 15:29 UTC #21 lore raw

Re: [PATCH v10 10/10] xfs: enable block size larger than page size support