Merge branch 'for-5.17/struct-slab' into for-linus

Series "Separate struct slab from struct page" v4

This is originally an offshoot of the folio work by Matthew. One of the more
complex parts of the struct page definition are the parts used by the slab
allocators. It would be good for the MM in general if struct slab were its own
data type, and it also helps to prevent tail pages from slipping in anywhere.
As Matthew requested in his proof of concept series, I have taken over the
development of this series, so it's a mix of patches from him (often modified
by me) and my own.

One big difference is the use of coccinelle to perform the relatively trivial
parts of the conversions automatically and at once, instead of a larger number
of smaller incremental reviewable steps. Thanks to Julia Lawall and Luis
Chamberlain for all their help!

Another notable difference is (based also on review feedback) I don't represent
with a struct slab the large kmalloc allocations which are not really a slab,
but use page allocator directly. When going from an object address to a struct
slab, the code tests first folio slab flag, and only if it's set it converts to
struct slab. This makes the struct slab type stronger.

Finally, although Matthew's version didn't use any of the folio work, the
initial support has been merged meanwhile so my version builds on top of it
where appropriate. This eliminates some of the redundant compound_head()
being performed e.g. when testing the slab flag.

To sum up, after this series, struct page fields used by slab allocators are
moved from struct page to a new struct slab, that uses the same physical
storage. The availability of the fields is further distinguished by the
selected slab allocator implementation. The advantages include:

- Similar to folios, if the slab is of order > 0, struct slab always is
  guaranteed to be the head page. Additionally it's guaranteed to be an actual
  slab page, not a large kmalloc. This removes uncertainty and potential for
  bugs.
- It's not possible to accidentally use fields of the slab implementation that's
  not configured.
- Other subsystems cannot use slab's fields in struct page anymore (some
  existing non-slab usages had to be adjusted in this series), so slab
  implementations have more freedom in rearranging them in the struct slab.

Link: https://lore.kernel.org/all/20220104001046.12263-1-vbabka@suse.cz/

1 files changed, 32 insertions, 30 deletions

diff --git a/mm/slob.c b/mm/slob.c
index 03deee1e6a94..60c5842215f1 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -30,7 +30,7 @@
  * If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
  * alloc_pages() directly, allocating compound pages so the page order
  * does not have to be separately tracked.
- * These objects are detected in kfree() because PageSlab()
+ * These objects are detected in kfree() because folio_test_slab()
  * is false for them.
  *
  * SLAB is emulated on top of SLOB by simply calling constructors and
@@ -105,21 +105,21 @@ static LIST_HEAD(free_slob_large);
 /*
  * slob_page_free: true for pages on free_slob_pages list.
  */
-static inline int slob_page_free(struct page *sp)
+static inline int slob_page_free(struct slab *slab)
 {
-	return PageSlobFree(sp);
+	return PageSlobFree(slab_page(slab));
 }
 
-static void set_slob_page_free(struct page *sp, struct list_head *list)
+static void set_slob_page_free(struct slab *slab, struct list_head *list)
 {
-	list_add(&sp->slab_list, list);
-	__SetPageSlobFree(sp);
+	list_add(&slab->slab_list, list);
+	__SetPageSlobFree(slab_page(slab));
 }
 
-static inline void clear_slob_page_free(struct page *sp)
+static inline void clear_slob_page_free(struct slab *slab)
 {
-	list_del(&sp->slab_list);
-	__ClearPageSlobFree(sp);
+	list_del(&slab->slab_list);
+	__ClearPageSlobFree(slab_page(slab));
 }
 
 #define SLOB_UNIT sizeof(slob_t)
@@ -234,7 +234,7 @@ static void slob_free_pages(void *b, int order)
  *         freelist, in this case @page_removed_from_list will be set to
  *         true (set to false otherwise).
  */
-static void *slob_page_alloc(struct page *sp, size_t size, int align,
+static void *slob_page_alloc(struct slab *sp, size_t size, int align,
 			      int align_offset, bool *page_removed_from_list)
 {
 	slob_t *prev, *cur, *aligned = NULL;
@@ -301,7 +301,8 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align,
 static void *slob_alloc(size_t size, gfp_t gfp, int align, int node,
 							int align_offset)
 {
-	struct page *sp;
+	struct folio *folio;
+	struct slab *sp;
 	struct list_head *slob_list;
 	slob_t *b = NULL;
 	unsigned long flags;
@@ -323,7 +324,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node,
 		 * If there's a node specification, search for a partial
 		 * page with a matching node id in the freelist.
 		 */
-		if (node != NUMA_NO_NODE && page_to_nid(sp) != node)
+		if (node != NUMA_NO_NODE && slab_nid(sp) != node)
 			continue;
 #endif
 		/* Enough room on this page? */
@@ -358,8 +359,9 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node,
 		b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node);
 		if (!b)
 			return NULL;
-		sp = virt_to_page(b);
-		__SetPageSlab(sp);
+		folio = virt_to_folio(b);
+		__folio_set_slab(folio);
+		sp = folio_slab(folio);
 
 		spin_lock_irqsave(&slob_lock, flags);
 		sp->units = SLOB_UNITS(PAGE_SIZE);
@@ -381,7 +383,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node,
  */
 static void slob_free(void *block, int size)
 {
-	struct page *sp;
+	struct slab *sp;
 	slob_t *prev, *next, *b = (slob_t *)block;
 	slobidx_t units;
 	unsigned long flags;
@@ -391,7 +393,7 @@ static void slob_free(void *block, int size)
 		return;
 	BUG_ON(!size);
 
-	sp = virt_to_page(block);
+	sp = virt_to_slab(block);
 	units = SLOB_UNITS(size);
 
 	spin_lock_irqsave(&slob_lock, flags);
@@ -401,8 +403,7 @@ static void slob_free(void *block, int size)
 		if (slob_page_free(sp))
 			clear_slob_page_free(sp);
 		spin_unlock_irqrestore(&slob_lock, flags);
-		__ClearPageSlab(sp);
-		page_mapcount_reset(sp);
+		__folio_clear_slab(slab_folio(sp));
 		slob_free_pages(b, 0);
 		return;
 	}
@@ -462,10 +463,10 @@ out:
 }
 
 #ifdef CONFIG_PRINTK
-void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
+void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
 {
 	kpp->kp_ptr = object;
-	kpp->kp_page = page;
+	kpp->kp_slab = slab;
 }
 #endif
 
@@ -544,7 +545,7 @@ EXPORT_SYMBOL(__kmalloc_node_track_caller);
 
 void kfree(const void *block)
 {
-	struct page *sp;
+	struct folio *sp;
 
 	trace_kfree(_RET_IP_, block);
 
@@ -552,16 +553,17 @@ void kfree(const void *block)
 		return;
 	kmemleak_free(block);
 
-	sp = virt_to_page(block);
-	if (PageSlab(sp)) {
+	sp = virt_to_folio(block);
+	if (folio_test_slab(sp)) {
 		int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 		unsigned int *m = (unsigned int *)(block - align);
 		slob_free(m, *m + align);
 	} else {
-		unsigned int order = compound_order(sp);
-		mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B,
+		unsigned int order = folio_order(sp);
+
+		mod_node_page_state(folio_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B,
 				    -(PAGE_SIZE << order));
-		__free_pages(sp, order);
+		__free_pages(folio_page(sp, 0), order);
 
 	}
 }
@@ -570,7 +572,7 @@ EXPORT_SYMBOL(kfree);
 /* can't use ksize for kmem_cache_alloc memory, only kmalloc */
 size_t __ksize(const void *block)
 {
-	struct page *sp;
+	struct folio *folio;
 	int align;
 	unsigned int *m;
 
@@ -578,9 +580,9 @@ size_t __ksize(const void *block)
 	if (unlikely(block == ZERO_SIZE_PTR))
 		return 0;
 
-	sp = virt_to_page(block);
-	if (unlikely(!PageSlab(sp)))
-		return page_size(sp);
+	folio = virt_to_folio(block);
+	if (unlikely(!folio_test_slab(folio)))
+		return folio_size(folio);
 
 	align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 	m = (unsigned int *)(block - align);