[PATCH v9 46/61] shmem: Convert shmem_add_to_page_cache to XArray

[Matthew Wilcox]

From: Matthew Wilcox 

This removes the last caller of radix_tree_maybe_preload_order().
Simpler code, unless we run out of memory for new xa_nodes partway through
inserting entries into the xarray.  Hopefully we can support multi-index
entries in the page cache soon and all the awful code goes away.

Signed-off-by: Matthew Wilcox 
---
 mm/shmem.c | 87 --
 1 file changed, 39 insertions(+), 48 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 49f42dc9e1dc..fb06fb3e644a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -558,9 +558,10 @@ static unsigned long shmem_unused_huge_shrink(struct 
shmem_sb_info *sbinfo,
  */
 static int shmem_add_to_page_cache(struct page *page,
   struct address_space *mapping,
-  pgoff_t index, void *expected)
+  pgoff_t index, void *expected, gfp_t gfp)
 {
-   int error, nr = hpage_nr_pages(page);
+   XA_STATE(xas, >i_pages, index);
+   unsigned long i, nr = 1UL << compound_order(page);
 
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(index != round_down(index, nr), page);
@@ -569,49 +570,47 @@ static int shmem_add_to_page_cache(struct page *page,
VM_BUG_ON(expected && PageTransHuge(page));
 
page_ref_add(page, nr);
-   page->mapping = mapping;
page->index = index;
+   page->mapping = mapping;
 
-   xa_lock_irq(>i_pages);
-   if (PageTransHuge(page)) {
-   void __rcu **results;
-   pgoff_t idx;
-   int i;
-
-   error = 0;
-   if (radix_tree_gang_lookup_slot(>i_pages,
-   , , index, 1) &&
-   idx < index + HPAGE_PMD_NR) {
-   error = -EEXIST;
+   do {
+   xas_lock_irq();
+   xas_create_range(, index + nr - 1);
+   if (xas_error())
+   goto unlock;
+   for (i = 0; i < nr; i++) {
+   void *entry = xas_load();
+   if (entry != expected)
+   xas_set_err(, -ENOENT);
+   if (xas_error())
+   goto undo;
+   xas_store(, page + i);
+   xas_next();
}
-
-   if (!error) {
-   for (i = 0; i < HPAGE_PMD_NR; i++) {
-   error = radix_tree_insert(>i_pages,
-   index + i, page + i);
-   VM_BUG_ON(error);
-   }
+   if (PageTransHuge(page)) {
count_vm_event(THP_FILE_ALLOC);
+   __inc_node_page_state(page, NR_SHMEM_THPS);
}
-   } else if (!expected) {
-   error = radix_tree_insert(>i_pages, index, page);
-   } else {
-   error = shmem_xa_replace(mapping, index, expected, page);
-   }
-
-   if (!error) {
mapping->nrpages += nr;
-   if (PageTransHuge(page))
-   __inc_node_page_state(page, NR_SHMEM_THPS);
__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
__mod_node_page_state(page_pgdat(page), NR_SHMEM, nr);
-   xa_unlock_irq(>i_pages);
-   } else {
+   goto unlock;
+undo:
+   while (i-- > 0) {
+   xas_store(, NULL);
+   xas_prev();
+   }
+unlock:
+   xas_unlock_irq();
+   } while (xas_nomem(, gfp));
+
+   if (xas_error()) {
page->mapping = NULL;
-   xa_unlock_irq(>i_pages);
page_ref_sub(page, nr);
+   return xas_error();
}
-   return error;
+
+   return 0;
 }
 
 /*
@@ -1159,7 +1158,7 @@ static int shmem_unuse_inode(struct shmem_inode_info 
*info,
 */
if (!error)
error = shmem_add_to_page_cache(*pagep, mapping, index,
-   radswap);
+   radswap, gfp);
if (error != -ENOMEM) {
/*
 * Truncation and eviction use free_swap_and_cache(), which
@@ -1680,7 +1679,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t 
index,
false);
if (!error) {
error = shmem_add_to_page_cache(page, mapping, index,
-   swp_to_radix_entry(swap));
+   swp_to_radix_entry(swap), gfp);
/*
 * We already confirmed swap under page lock, and make
 * no memory 

[PATCH v9 46/61] shmem: Convert shmem_add_to_page_cache to XArray

[Matthew Wilcox]

From: Matthew Wilcox 

This removes the last caller of radix_tree_maybe_preload_order().
Simpler code, unless we run out of memory for new xa_nodes partway through
inserting entries into the xarray.  Hopefully we can support multi-index
entries in the page cache soon and all the awful code goes away.

Signed-off-by: Matthew Wilcox 
---
 mm/shmem.c | 87 --
 1 file changed, 39 insertions(+), 48 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 49f42dc9e1dc..fb06fb3e644a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -558,9 +558,10 @@ static unsigned long shmem_unused_huge_shrink(struct 
shmem_sb_info *sbinfo,
  */
 static int shmem_add_to_page_cache(struct page *page,
   struct address_space *mapping,
-  pgoff_t index, void *expected)
+  pgoff_t index, void *expected, gfp_t gfp)
 {
-   int error, nr = hpage_nr_pages(page);
+   XA_STATE(xas, >i_pages, index);
+   unsigned long i, nr = 1UL << compound_order(page);
 
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(index != round_down(index, nr), page);
@@ -569,49 +570,47 @@ static int shmem_add_to_page_cache(struct page *page,
VM_BUG_ON(expected && PageTransHuge(page));
 
page_ref_add(page, nr);
-   page->mapping = mapping;
page->index = index;
+   page->mapping = mapping;
 
-   xa_lock_irq(>i_pages);
-   if (PageTransHuge(page)) {
-   void __rcu **results;
-   pgoff_t idx;
-   int i;
-
-   error = 0;
-   if (radix_tree_gang_lookup_slot(>i_pages,
-   , , index, 1) &&
-   idx < index + HPAGE_PMD_NR) {
-   error = -EEXIST;
+   do {
+   xas_lock_irq();
+   xas_create_range(, index + nr - 1);
+   if (xas_error())
+   goto unlock;
+   for (i = 0; i < nr; i++) {
+   void *entry = xas_load();
+   if (entry != expected)
+   xas_set_err(, -ENOENT);
+   if (xas_error())
+   goto undo;
+   xas_store(, page + i);
+   xas_next();
}
-
-   if (!error) {
-   for (i = 0; i < HPAGE_PMD_NR; i++) {
-   error = radix_tree_insert(>i_pages,
-   index + i, page + i);
-   VM_BUG_ON(error);
-   }
+   if (PageTransHuge(page)) {
count_vm_event(THP_FILE_ALLOC);
+   __inc_node_page_state(page, NR_SHMEM_THPS);
}
-   } else if (!expected) {
-   error = radix_tree_insert(>i_pages, index, page);
-   } else {
-   error = shmem_xa_replace(mapping, index, expected, page);
-   }
-
-   if (!error) {
mapping->nrpages += nr;
-   if (PageTransHuge(page))
-   __inc_node_page_state(page, NR_SHMEM_THPS);
__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
__mod_node_page_state(page_pgdat(page), NR_SHMEM, nr);
-   xa_unlock_irq(>i_pages);
-   } else {
+   goto unlock;
+undo:
+   while (i-- > 0) {
+   xas_store(, NULL);
+   xas_prev();
+   }
+unlock:
+   xas_unlock_irq();
+   } while (xas_nomem(, gfp));
+
+   if (xas_error()) {
page->mapping = NULL;
-   xa_unlock_irq(>i_pages);
page_ref_sub(page, nr);
+   return xas_error();
}
-   return error;
+
+   return 0;
 }
 
 /*
@@ -1159,7 +1158,7 @@ static int shmem_unuse_inode(struct shmem_inode_info 
*info,
 */
if (!error)
error = shmem_add_to_page_cache(*pagep, mapping, index,
-   radswap);
+   radswap, gfp);
if (error != -ENOMEM) {
/*
 * Truncation and eviction use free_swap_and_cache(), which
@@ -1680,7 +1679,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t 
index,
false);
if (!error) {
error = shmem_add_to_page_cache(page, mapping, index,
-   swp_to_radix_entry(swap));
+   swp_to_radix_entry(swap), gfp);
/*
 * We already confirmed swap under page lock, and make
 * no memory allocation here, so usually no possibility
@@