From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/fs/dax.c | 1129 +++++++++++++++++++++++++++-------------------------------
1 files changed, 530 insertions(+), 599 deletions(-)
diff --git a/kernel/fs/dax.c b/kernel/fs/dax.c
index d09701a..c0f181e 100644
--- a/kernel/fs/dax.c
+++ b/kernel/fs/dax.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* fs/dax.c - Direct Access filesystem code
* Copyright (c) 2013-2014 Intel Corporation
* Author: Matthew Wilcox <matthew.r.wilcox@intel.com>
* Author: Ross Zwisler <ross.zwisler@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
*/
#include <linux/atomic.h>
@@ -33,10 +25,21 @@
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
-#include "internal.h"
+#include <asm/pgalloc.h>
#define CREATE_TRACE_POINTS
#include <trace/events/fs_dax.h>
+
+static inline unsigned int pe_order(enum page_entry_size pe_size)
+{
+ if (pe_size == PE_SIZE_PTE)
+ return PAGE_SHIFT - PAGE_SHIFT;
+ if (pe_size == PE_SIZE_PMD)
+ return PMD_SHIFT - PAGE_SHIFT;
+ if (pe_size == PE_SIZE_PUD)
+ return PUD_SHIFT - PAGE_SHIFT;
+ return ~0;
+}
/* We choose 4096 entries - same as per-zone page wait tables */
#define DAX_WAIT_TABLE_BITS 12
@@ -45,6 +48,9 @@
/* The 'colour' (ie low bits) within a PMD of a page offset. */
#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1)
#define PG_PMD_NR (PMD_SIZE >> PAGE_SHIFT)
+
+/* The order of a PMD entry */
+#define PMD_ORDER (PMD_SHIFT - PAGE_SHIFT)
static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
@@ -59,63 +65,77 @@
fs_initcall(init_dax_wait_table);
/*
- * We use lowest available bit in exceptional entry for locking, one bit for
- * the entry size (PMD) and two more to tell us if the entry is a zero page or
- * an empty entry that is just used for locking. In total four special bits.
+ * DAX pagecache entries use XArray value entries so they can't be mistaken
+ * for pages. We use one bit for locking, one bit for the entry size (PMD)
+ * and two more to tell us if the entry is a zero page or an empty entry that
+ * is just used for locking. In total four special bits.
*
* If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE
* and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
* block allocation.
*/
-#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4)
-#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
-#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1))
-#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2))
-#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3))
+#define DAX_SHIFT (4)
+#define DAX_LOCKED (1UL << 0)
+#define DAX_PMD (1UL << 1)
+#define DAX_ZERO_PAGE (1UL << 2)
+#define DAX_EMPTY (1UL << 3)
-static unsigned long dax_radix_pfn(void *entry)
+static unsigned long dax_to_pfn(void *entry)
{
- return (unsigned long)entry >> RADIX_DAX_SHIFT;
+ return xa_to_value(entry) >> DAX_SHIFT;
}
-static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags)
+static void *dax_make_entry(pfn_t pfn, unsigned long flags)
{
- return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags |
- (pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK);
+ return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT));
}
-static unsigned int dax_radix_order(void *entry)
+static bool dax_is_locked(void *entry)
{
- if ((unsigned long)entry & RADIX_DAX_PMD)
- return PMD_SHIFT - PAGE_SHIFT;
+ return xa_to_value(entry) & DAX_LOCKED;
+}
+
+static unsigned int dax_entry_order(void *entry)
+{
+ if (xa_to_value(entry) & DAX_PMD)
+ return PMD_ORDER;
return 0;
}
-static int dax_is_pmd_entry(void *entry)
+static unsigned long dax_is_pmd_entry(void *entry)
{
- return (unsigned long)entry & RADIX_DAX_PMD;
+ return xa_to_value(entry) & DAX_PMD;
}
-static int dax_is_pte_entry(void *entry)
+static bool dax_is_pte_entry(void *entry)
{
- return !((unsigned long)entry & RADIX_DAX_PMD);
+ return !(xa_to_value(entry) & DAX_PMD);
}
static int dax_is_zero_entry(void *entry)
{
- return (unsigned long)entry & RADIX_DAX_ZERO_PAGE;
+ return xa_to_value(entry) & DAX_ZERO_PAGE;
}
static int dax_is_empty_entry(void *entry)
{
- return (unsigned long)entry & RADIX_DAX_EMPTY;
+ return xa_to_value(entry) & DAX_EMPTY;
}
/*
- * DAX radix tree locking
+ * true if the entry that was found is of a smaller order than the entry
+ * we were looking for
+ */
+static bool dax_is_conflict(void *entry)
+{
+ return entry == XA_RETRY_ENTRY;
+}
+
+/*
+ * DAX page cache entry locking
*/
struct exceptional_entry_key {
- struct address_space *mapping;
+ struct xarray *xa;
pgoff_t entry_start;
};
@@ -124,10 +144,21 @@
struct exceptional_entry_key key;
};
-static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
- pgoff_t index, void *entry, struct exceptional_entry_key *key)
+/**
+ * enum dax_wake_mode: waitqueue wakeup behaviour
+ * @WAKE_ALL: wake all waiters in the waitqueue
+ * @WAKE_NEXT: wake only the first waiter in the waitqueue
+ */
+enum dax_wake_mode {
+ WAKE_ALL,
+ WAKE_NEXT,
+};
+
+static wait_queue_head_t *dax_entry_waitqueue(struct xa_state *xas,
+ void *entry, struct exceptional_entry_key *key)
{
unsigned long hash;
+ unsigned long index = xas->xa_index;
/*
* If 'entry' is a PMD, align the 'index' that we use for the wait
@@ -136,22 +167,21 @@
*/
if (dax_is_pmd_entry(entry))
index &= ~PG_PMD_COLOUR;
-
- key->mapping = mapping;
+ key->xa = xas->xa;
key->entry_start = index;
- hash = hash_long((unsigned long)mapping ^ index, DAX_WAIT_TABLE_BITS);
+ hash = hash_long((unsigned long)xas->xa ^ index, DAX_WAIT_TABLE_BITS);
return wait_table + hash;
}
-static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mode,
- int sync, void *keyp)
+static int wake_exceptional_entry_func(wait_queue_entry_t *wait,
+ unsigned int mode, int sync, void *keyp)
{
struct exceptional_entry_key *key = keyp;
struct wait_exceptional_entry_queue *ewait =
container_of(wait, struct wait_exceptional_entry_queue, wait);
- if (key->mapping != ewait->key.mapping ||
+ if (key->xa != ewait->key.xa ||
key->entry_start != ewait->key.entry_start)
return 0;
return autoremove_wake_function(wait, mode, sync, NULL);
@@ -162,13 +192,13 @@
* The important information it's conveying is whether the entry at
* this index used to be a PMD entry.
*/
-static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
- pgoff_t index, void *entry, bool wake_all)
+static void dax_wake_entry(struct xa_state *xas, void *entry,
+ enum dax_wake_mode mode)
{
struct exceptional_entry_key key;
wait_queue_head_t *wq;
- wq = dax_entry_waitqueue(mapping, index, entry, &key);
+ wq = dax_entry_waitqueue(xas, entry, &key);
/*
* Checking for locked entry and prepare_to_wait_exclusive() happens
@@ -177,62 +207,22 @@
* must be in the waitqueue and the following check will see them.
*/
if (waitqueue_active(wq))
- __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key);
+ __wake_up(wq, TASK_NORMAL, mode == WAKE_ALL ? 0 : 1, &key);
}
/*
- * Check whether the given slot is locked. Must be called with the i_pages
- * lock held.
- */
-static inline int slot_locked(struct address_space *mapping, void **slot)
-{
- unsigned long entry = (unsigned long)
- radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
- return entry & RADIX_DAX_ENTRY_LOCK;
-}
-
-/*
- * Mark the given slot as locked. Must be called with the i_pages lock held.
- */
-static inline void *lock_slot(struct address_space *mapping, void **slot)
-{
- unsigned long entry = (unsigned long)
- radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-
- entry |= RADIX_DAX_ENTRY_LOCK;
- radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
- return (void *)entry;
-}
-
-/*
- * Mark the given slot as unlocked. Must be called with the i_pages lock held.
- */
-static inline void *unlock_slot(struct address_space *mapping, void **slot)
-{
- unsigned long entry = (unsigned long)
- radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock);
-
- entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
- radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry);
- return (void *)entry;
-}
-
-static void put_unlocked_mapping_entry(struct address_space *mapping,
- pgoff_t index, void *entry);
-
-/*
- * Lookup entry in radix tree, wait for it to become unlocked if it is
- * exceptional entry and return it. The caller must call
- * put_unlocked_mapping_entry() when he decided not to lock the entry or
- * put_locked_mapping_entry() when he locked the entry and now wants to
- * unlock it.
+ * Look up entry in page cache, wait for it to become unlocked if it
+ * is a DAX entry and return it. The caller must subsequently call
+ * put_unlocked_entry() if it did not lock the entry or dax_unlock_entry()
+ * if it did. The entry returned may have a larger order than @order.
+ * If @order is larger than the order of the entry found in i_pages, this
+ * function returns a dax_is_conflict entry.
*
* Must be called with the i_pages lock held.
*/
-static void *get_unlocked_mapping_entry(struct address_space *mapping,
- pgoff_t index, void ***slotp)
+static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
{
- void *entry, **slot;
+ void *entry;
struct wait_exceptional_entry_queue ewait;
wait_queue_head_t *wq;
@@ -240,23 +230,22 @@
ewait.wait.func = wake_exceptional_entry_func;
for (;;) {
- entry = __radix_tree_lookup(&mapping->i_pages, index, NULL,
- &slot);
- if (!entry ||
- WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) ||
- !slot_locked(mapping, slot)) {
- if (slotp)
- *slotp = slot;
+ entry = xas_find_conflict(xas);
+ if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
return entry;
- }
+ if (dax_entry_order(entry) < order)
+ return XA_RETRY_ENTRY;
+ if (!dax_is_locked(entry))
+ return entry;
- wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key);
+ wq = dax_entry_waitqueue(xas, entry, &ewait.key);
prepare_to_wait_exclusive(wq, &ewait.wait,
TASK_UNINTERRUPTIBLE);
- xa_unlock_irq(&mapping->i_pages);
+ xas_unlock_irq(xas);
+ xas_reset(xas);
schedule();
finish_wait(wq, &ewait.wait);
- xa_lock_irq(&mapping->i_pages);
+ xas_lock_irq(xas);
}
}
@@ -265,8 +254,7 @@
* (it's cycled in clear_inode() after removing the entries from i_pages)
* After we call xas_unlock_irq(), we cannot touch xas->xa.
*/
-static void wait_entry_unlocked(struct address_space *mapping, pgoff_t index,
- void ***slotp, void *entry)
+static void wait_entry_unlocked(struct xa_state *xas, void *entry)
{
struct wait_exceptional_entry_queue ewait;
wait_queue_head_t *wq;
@@ -274,7 +262,7 @@
init_wait(&ewait.wait);
ewait.wait.func = wake_exceptional_entry_func;
- wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key);
+ wq = dax_entry_waitqueue(xas, entry, &ewait.key);
/*
* Unlike get_unlocked_entry() there is no guarantee that this
* path ever successfully retrieves an unlocked entry before an
@@ -282,45 +270,43 @@
* never successfully performs its own wake up.
*/
prepare_to_wait(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);
- xa_unlock_irq(&mapping->i_pages);
+ xas_unlock_irq(xas);
schedule();
finish_wait(wq, &ewait.wait);
}
-static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
+static void put_unlocked_entry(struct xa_state *xas, void *entry,
+ enum dax_wake_mode mode)
{
- void *entry, **slot;
-
- xa_lock_irq(&mapping->i_pages);
- entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot);
- if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
- !slot_locked(mapping, slot))) {
- xa_unlock_irq(&mapping->i_pages);
- return;
- }
- unlock_slot(mapping, slot);
- xa_unlock_irq(&mapping->i_pages);
- dax_wake_mapping_entry_waiter(mapping, index, entry, false);
-}
-
-static void put_locked_mapping_entry(struct address_space *mapping,
- pgoff_t index)
-{
- unlock_mapping_entry(mapping, index);
+ if (entry && !dax_is_conflict(entry))
+ dax_wake_entry(xas, entry, mode);
}
/*
- * Called when we are done with radix tree entry we looked up via
- * get_unlocked_mapping_entry() and which we didn't lock in the end.
+ * We used the xa_state to get the entry, but then we locked the entry and
+ * dropped the xa_lock, so we know the xa_state is stale and must be reset
+ * before use.
*/
-static void put_unlocked_mapping_entry(struct address_space *mapping,
- pgoff_t index, void *entry)
+static void dax_unlock_entry(struct xa_state *xas, void *entry)
{
- if (!entry)
- return;
+ void *old;
- /* We have to wake up next waiter for the radix tree entry lock */
- dax_wake_mapping_entry_waiter(mapping, index, entry, false);
+ BUG_ON(dax_is_locked(entry));
+ xas_reset(xas);
+ xas_lock_irq(xas);
+ old = xas_store(xas, entry);
+ xas_unlock_irq(xas);
+ BUG_ON(!dax_is_locked(old));
+ dax_wake_entry(xas, entry, WAKE_NEXT);
+}
+
+/*
+ * Return: The entry stored at this location before it was locked.
+ */
+static void *dax_lock_entry(struct xa_state *xas, void *entry)
+{
+ unsigned long v = xa_to_value(entry);
+ return xas_store(xas, xa_mk_value(v | DAX_LOCKED));
}
static unsigned long dax_entry_size(void *entry)
@@ -335,9 +321,9 @@
return PAGE_SIZE;
}
-static unsigned long dax_radix_end_pfn(void *entry)
+static unsigned long dax_end_pfn(void *entry)
{
- return dax_radix_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
+ return dax_to_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
}
/*
@@ -345,8 +331,8 @@
* 'empty' and 'zero' entries.
*/
#define for_each_mapped_pfn(entry, pfn) \
- for (pfn = dax_radix_pfn(entry); \
- pfn < dax_radix_end_pfn(entry); pfn++)
+ for (pfn = dax_to_pfn(entry); \
+ pfn < dax_end_pfn(entry); pfn++)
/*
* TODO: for reflink+dax we need a way to associate a single page with
@@ -403,18 +389,25 @@
return NULL;
}
-bool dax_lock_mapping_entry(struct page *page)
+/*
+ * dax_lock_mapping_entry - Lock the DAX entry corresponding to a page
+ * @page: The page whose entry we want to lock
+ *
+ * Context: Process context.
+ * Return: A cookie to pass to dax_unlock_page() or 0 if the entry could
+ * not be locked.
+ */
+dax_entry_t dax_lock_page(struct page *page)
{
- pgoff_t index;
- struct inode *inode;
- bool did_lock = false;
- void *entry = NULL, **slot;
- struct address_space *mapping;
+ XA_STATE(xas, NULL, 0);
+ void *entry;
+ /* Ensure page->mapping isn't freed while we look at it */
rcu_read_lock();
for (;;) {
- mapping = READ_ONCE(page->mapping);
+ struct address_space *mapping = READ_ONCE(page->mapping);
+ entry = NULL;
if (!mapping || !dax_mapping(mapping))
break;
@@ -425,101 +418,93 @@
* otherwise we would not have a valid pfn_to_page()
* translation.
*/
- inode = mapping->host;
- if (S_ISCHR(inode->i_mode)) {
- did_lock = true;
+ entry = (void *)~0UL;
+ if (S_ISCHR(mapping->host->i_mode))
break;
- }
- xa_lock_irq(&mapping->i_pages);
+ xas.xa = &mapping->i_pages;
+ xas_lock_irq(&xas);
if (mapping != page->mapping) {
- xa_unlock_irq(&mapping->i_pages);
+ xas_unlock_irq(&xas);
continue;
}
- index = page->index;
-
- entry = __radix_tree_lookup(&mapping->i_pages, index,
- NULL, &slot);
- if (!entry) {
- xa_unlock_irq(&mapping->i_pages);
- break;
- } else if (slot_locked(mapping, slot)) {
+ xas_set(&xas, page->index);
+ entry = xas_load(&xas);
+ if (dax_is_locked(entry)) {
rcu_read_unlock();
- wait_entry_unlocked(mapping, index, &slot, entry);
+ wait_entry_unlocked(&xas, entry);
rcu_read_lock();
continue;
}
- lock_slot(mapping, slot);
- did_lock = true;
- xa_unlock_irq(&mapping->i_pages);
+ dax_lock_entry(&xas, entry);
+ xas_unlock_irq(&xas);
break;
}
rcu_read_unlock();
-
- return did_lock;
+ return (dax_entry_t)entry;
}
-void dax_unlock_mapping_entry(struct page *page)
+void dax_unlock_page(struct page *page, dax_entry_t cookie)
{
struct address_space *mapping = page->mapping;
- struct inode *inode = mapping->host;
+ XA_STATE(xas, &mapping->i_pages, page->index);
- if (S_ISCHR(inode->i_mode))
+ if (S_ISCHR(mapping->host->i_mode))
return;
- unlock_mapping_entry(mapping, page->index);
+ dax_unlock_entry(&xas, (void *)cookie);
}
/*
- * Find radix tree entry at given index. If it points to an exceptional entry,
- * return it with the radix tree entry locked. If the radix tree doesn't
- * contain given index, create an empty exceptional entry for the index and
- * return with it locked.
+ * Find page cache entry at given index. If it is a DAX entry, return it
+ * with the entry locked. If the page cache doesn't contain an entry at
+ * that index, add a locked empty entry.
*
- * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will
- * either return that locked entry or will return an error. This error will
- * happen if there are any 4k entries within the 2MiB range that we are
- * requesting.
+ * When requesting an entry with size DAX_PMD, grab_mapping_entry() will
+ * either return that locked entry or will return VM_FAULT_FALLBACK.
+ * This will happen if there are any PTE entries within the PMD range
+ * that we are requesting.
*
- * We always favor 4k entries over 2MiB entries. There isn't a flow where we
- * evict 4k entries in order to 'upgrade' them to a 2MiB entry. A 2MiB
- * insertion will fail if it finds any 4k entries already in the tree, and a
- * 4k insertion will cause an existing 2MiB entry to be unmapped and
- * downgraded to 4k entries. This happens for both 2MiB huge zero pages as
- * well as 2MiB empty entries.
+ * We always favor PTE entries over PMD entries. There isn't a flow where we
+ * evict PTE entries in order to 'upgrade' them to a PMD entry. A PMD
+ * insertion will fail if it finds any PTE entries already in the tree, and a
+ * PTE insertion will cause an existing PMD entry to be unmapped and
+ * downgraded to PTE entries. This happens for both PMD zero pages as
+ * well as PMD empty entries.
*
- * The exception to this downgrade path is for 2MiB DAX PMD entries that have
- * real storage backing them. We will leave these real 2MiB DAX entries in
- * the tree, and PTE writes will simply dirty the entire 2MiB DAX entry.
+ * The exception to this downgrade path is for PMD entries that have
+ * real storage backing them. We will leave these real PMD entries in
+ * the tree, and PTE writes will simply dirty the entire PMD entry.
*
* Note: Unlike filemap_fault() we don't honor FAULT_FLAG_RETRY flags. For
* persistent memory the benefit is doubtful. We can add that later if we can
* show it helps.
+ *
+ * On error, this function does not return an ERR_PTR. Instead it returns
+ * a VM_FAULT code, encoded as an xarray internal entry. The ERR_PTR values
+ * overlap with xarray value entries.
*/
-static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
- unsigned long size_flag)
+static void *grab_mapping_entry(struct xa_state *xas,
+ struct address_space *mapping, unsigned int order)
{
- bool pmd_downgrade = false; /* splitting 2MiB entry into 4k entries? */
- void *entry, **slot;
+ unsigned long index = xas->xa_index;
+ bool pmd_downgrade; /* splitting PMD entry into PTE entries? */
+ void *entry;
-restart:
- xa_lock_irq(&mapping->i_pages);
- entry = get_unlocked_mapping_entry(mapping, index, &slot);
-
- if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) {
- entry = ERR_PTR(-EIO);
- goto out_unlock;
- }
+retry:
+ pmd_downgrade = false;
+ xas_lock_irq(xas);
+ entry = get_unlocked_entry(xas, order);
if (entry) {
- if (size_flag & RADIX_DAX_PMD) {
- if (dax_is_pte_entry(entry)) {
- put_unlocked_mapping_entry(mapping, index,
- entry);
- entry = ERR_PTR(-EEXIST);
- goto out_unlock;
- }
- } else { /* trying to grab a PTE entry */
+ if (dax_is_conflict(entry))
+ goto fallback;
+ if (!xa_is_value(entry)) {
+ xas_set_err(xas, -EIO);
+ goto out_unlock;
+ }
+
+ if (order == 0) {
if (dax_is_pmd_entry(entry) &&
(dax_is_zero_entry(entry) ||
dax_is_empty_entry(entry))) {
@@ -528,92 +513,69 @@
}
}
- /* No entry for given index? Make sure radix tree is big enough. */
- if (!entry || pmd_downgrade) {
- int err;
+ if (pmd_downgrade) {
+ /*
+ * Make sure 'entry' remains valid while we drop
+ * the i_pages lock.
+ */
+ dax_lock_entry(xas, entry);
- if (pmd_downgrade) {
- /*
- * Make sure 'entry' remains valid while we drop
- * the i_pages lock.
- */
- entry = lock_slot(mapping, slot);
- }
-
- xa_unlock_irq(&mapping->i_pages);
/*
* Besides huge zero pages the only other thing that gets
* downgraded are empty entries which don't need to be
* unmapped.
*/
- if (pmd_downgrade && dax_is_zero_entry(entry))
- unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
- PG_PMD_NR, false);
-
- err = radix_tree_preload(
- mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
- if (err) {
- if (pmd_downgrade)
- put_locked_mapping_entry(mapping, index);
- return ERR_PTR(err);
- }
- xa_lock_irq(&mapping->i_pages);
-
- if (!entry) {
- /*
- * We needed to drop the i_pages lock while calling
- * radix_tree_preload() and we didn't have an entry to
- * lock. See if another thread inserted an entry at
- * our index during this time.
- */
- entry = __radix_tree_lookup(&mapping->i_pages, index,
- NULL, &slot);
- if (entry) {
- radix_tree_preload_end();
- xa_unlock_irq(&mapping->i_pages);
- goto restart;
- }
+ if (dax_is_zero_entry(entry)) {
+ xas_unlock_irq(xas);
+ unmap_mapping_pages(mapping,
+ xas->xa_index & ~PG_PMD_COLOUR,
+ PG_PMD_NR, false);
+ xas_reset(xas);
+ xas_lock_irq(xas);
}
- if (pmd_downgrade) {
- dax_disassociate_entry(entry, mapping, false);
- radix_tree_delete(&mapping->i_pages, index);
- mapping->nrexceptional--;
- dax_wake_mapping_entry_waiter(mapping, index, entry,
- true);
- }
-
- entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY);
-
- err = __radix_tree_insert(&mapping->i_pages, index,
- dax_radix_order(entry), entry);
- radix_tree_preload_end();
- if (err) {
- xa_unlock_irq(&mapping->i_pages);
- /*
- * Our insertion of a DAX entry failed, most likely
- * because we were inserting a PMD entry and it
- * collided with a PTE sized entry at a different
- * index in the PMD range. We haven't inserted
- * anything into the radix tree and have no waiters to
- * wake.
- */
- return ERR_PTR(err);
- }
- /* Good, we have inserted empty locked entry into the tree. */
- mapping->nrexceptional++;
- xa_unlock_irq(&mapping->i_pages);
- return entry;
+ dax_disassociate_entry(entry, mapping, false);
+ xas_store(xas, NULL); /* undo the PMD join */
+ dax_wake_entry(xas, entry, WAKE_ALL);
+ mapping->nrexceptional--;
+ entry = NULL;
+ xas_set(xas, index);
}
- entry = lock_slot(mapping, slot);
- out_unlock:
- xa_unlock_irq(&mapping->i_pages);
+
+ if (entry) {
+ dax_lock_entry(xas, entry);
+ } else {
+ unsigned long flags = DAX_EMPTY;
+
+ if (order > 0)
+ flags |= DAX_PMD;
+ entry = dax_make_entry(pfn_to_pfn_t(0), flags);
+ dax_lock_entry(xas, entry);
+ if (xas_error(xas))
+ goto out_unlock;
+ mapping->nrexceptional++;
+ }
+
+out_unlock:
+ xas_unlock_irq(xas);
+ if (xas_nomem(xas, mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM))
+ goto retry;
+ if (xas->xa_node == XA_ERROR(-ENOMEM))
+ return xa_mk_internal(VM_FAULT_OOM);
+ if (xas_error(xas))
+ return xa_mk_internal(VM_FAULT_SIGBUS);
return entry;
+fallback:
+ xas_unlock_irq(xas);
+ return xa_mk_internal(VM_FAULT_FALLBACK);
}
/**
- * dax_layout_busy_page - find first pinned page in @mapping
+ * dax_layout_busy_page_range - find first pinned page in @mapping
* @mapping: address space to scan for a page with ref count > 1
+ * @start: Starting offset. Page containing 'start' is included.
+ * @end: End offset. Page containing 'end' is included. If 'end' is LLONG_MAX,
+ * pages from 'start' till the end of file are included.
*
* DAX requires ZONE_DEVICE mapped pages. These pages are never
* 'onlined' to the page allocator so they are considered idle when
@@ -626,13 +588,15 @@
* to be able to run unmap_mapping_range() and subsequently not race
* mapping_mapped() becoming true.
*/
-struct page *dax_layout_busy_page(struct address_space *mapping)
+struct page *dax_layout_busy_page_range(struct address_space *mapping,
+ loff_t start, loff_t end)
{
- pgoff_t indices[PAGEVEC_SIZE];
+ void *entry;
+ unsigned int scanned = 0;
struct page *page = NULL;
- struct pagevec pvec;
- pgoff_t index, end;
- unsigned i;
+ pgoff_t start_idx = start >> PAGE_SHIFT;
+ pgoff_t end_idx;
+ XA_STATE(xas, &mapping->i_pages, start_idx);
/*
* In the 'limited' case get_user_pages() for dax is disabled.
@@ -643,112 +607,93 @@
if (!dax_mapping(mapping) || !mapping_mapped(mapping))
return NULL;
- pagevec_init(&pvec);
- index = 0;
- end = -1;
-
+ /* If end == LLONG_MAX, all pages from start to till end of file */
+ if (end == LLONG_MAX)
+ end_idx = ULONG_MAX;
+ else
+ end_idx = end >> PAGE_SHIFT;
/*
* If we race get_user_pages_fast() here either we'll see the
- * elevated page count in the pagevec_lookup and wait, or
+ * elevated page count in the iteration and wait, or
* get_user_pages_fast() will see that the page it took a reference
* against is no longer mapped in the page tables and bail to the
* get_user_pages() slow path. The slow path is protected by
* pte_lock() and pmd_lock(). New references are not taken without
- * holding those locks, and unmap_mapping_range() will not zero the
+ * holding those locks, and unmap_mapping_pages() will not zero the
* pte or pmd without holding the respective lock, so we are
* guaranteed to either see new references or prevent new
* references from being established.
*/
- unmap_mapping_range(mapping, 0, 0, 0);
+ unmap_mapping_pages(mapping, start_idx, end_idx - start_idx + 1, 0);
- while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE),
- indices)) {
- pgoff_t nr_pages = 1;
-
- for (i = 0; i < pagevec_count(&pvec); i++) {
- struct page *pvec_ent = pvec.pages[i];
- void *entry;
-
- index = indices[i];
- if (index >= end)
- break;
-
- if (WARN_ON_ONCE(
- !radix_tree_exceptional_entry(pvec_ent)))
- continue;
-
- xa_lock_irq(&mapping->i_pages);
- entry = get_unlocked_mapping_entry(mapping, index, NULL);
- if (entry) {
- page = dax_busy_page(entry);
- /*
- * Account for multi-order entries at
- * the end of the pagevec.
- */
- if (i + 1 >= pagevec_count(&pvec))
- nr_pages = 1UL << dax_radix_order(entry);
- }
- put_unlocked_mapping_entry(mapping, index, entry);
- xa_unlock_irq(&mapping->i_pages);
- if (page)
- break;
- }
-
- /*
- * We don't expect normal struct page entries to exist in our
- * tree, but we keep these pagevec calls so that this code is
- * consistent with the common pattern for handling pagevecs
- * throughout the kernel.
- */
- pagevec_remove_exceptionals(&pvec);
- pagevec_release(&pvec);
- index += nr_pages;
-
+ xas_lock_irq(&xas);
+ xas_for_each(&xas, entry, end_idx) {
+ if (WARN_ON_ONCE(!xa_is_value(entry)))
+ continue;
+ if (unlikely(dax_is_locked(entry)))
+ entry = get_unlocked_entry(&xas, 0);
+ if (entry)
+ page = dax_busy_page(entry);
+ put_unlocked_entry(&xas, entry, WAKE_NEXT);
if (page)
break;
+ if (++scanned % XA_CHECK_SCHED)
+ continue;
+
+ xas_pause(&xas);
+ xas_unlock_irq(&xas);
+ cond_resched();
+ xas_lock_irq(&xas);
}
+ xas_unlock_irq(&xas);
return page;
+}
+EXPORT_SYMBOL_GPL(dax_layout_busy_page_range);
+
+struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+ return dax_layout_busy_page_range(mapping, 0, LLONG_MAX);
}
EXPORT_SYMBOL_GPL(dax_layout_busy_page);
-static int __dax_invalidate_mapping_entry(struct address_space *mapping,
+static int __dax_invalidate_entry(struct address_space *mapping,
pgoff_t index, bool trunc)
{
+ XA_STATE(xas, &mapping->i_pages, index);
int ret = 0;
void *entry;
- struct radix_tree_root *pages = &mapping->i_pages;
- xa_lock_irq(pages);
- entry = get_unlocked_mapping_entry(mapping, index, NULL);
- if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)))
+ xas_lock_irq(&xas);
+ entry = get_unlocked_entry(&xas, 0);
+ if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
goto out;
if (!trunc &&
- (radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) ||
- radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE)))
+ (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY) ||
+ xas_get_mark(&xas, PAGECACHE_TAG_TOWRITE)))
goto out;
dax_disassociate_entry(entry, mapping, trunc);
- radix_tree_delete(pages, index);
+ xas_store(&xas, NULL);
mapping->nrexceptional--;
ret = 1;
out:
- put_unlocked_mapping_entry(mapping, index, entry);
- xa_unlock_irq(pages);
+ put_unlocked_entry(&xas, entry, WAKE_ALL);
+ xas_unlock_irq(&xas);
return ret;
}
+
/*
- * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
- * entry to get unlocked before deleting it.
+ * Delete DAX entry at @index from @mapping. Wait for it
+ * to be unlocked before deleting it.
*/
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
{
- int ret = __dax_invalidate_mapping_entry(mapping, index, true);
+ int ret = __dax_invalidate_entry(mapping, index, true);
/*
* This gets called from truncate / punch_hole path. As such, the caller
* must hold locks protecting against concurrent modifications of the
- * radix tree (usually fs-private i_mmap_sem for writing). Since the
- * caller has seen exceptional entry for this index, we better find it
+ * page cache (usually fs-private i_mmap_sem for writing). Since the
+ * caller has seen a DAX entry for this index, we better find it
* at that index as well...
*/
WARN_ON_ONCE(!ret);
@@ -756,34 +701,38 @@
}
/*
- * Invalidate exceptional DAX entry if it is clean.
+ * Invalidate DAX entry if it is clean.
*/
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
pgoff_t index)
{
- return __dax_invalidate_mapping_entry(mapping, index, false);
+ return __dax_invalidate_entry(mapping, index, false);
}
-static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
- sector_t sector, size_t size, struct page *to,
- unsigned long vaddr)
+static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_dev,
+ sector_t sector, struct page *to, unsigned long vaddr)
{
void *vto, *kaddr;
pgoff_t pgoff;
long rc;
int id;
- rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+ rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
if (rc)
return rc;
id = dax_read_lock();
- rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, NULL);
+ rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(PAGE_SIZE), &kaddr, NULL);
if (rc < 0) {
dax_read_unlock(id);
return rc;
}
vto = kmap_atomic(to);
+#ifdef CONFIG_ARM
+#ifndef copy_user_page
+#define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
+#endif
+#endif
copy_user_page(vto, (void __force *)kaddr, vaddr, to);
kunmap_atomic(vto);
dax_read_unlock(id);
@@ -797,64 +746,57 @@
* already in the tree, we will skip the insertion and just dirty the PMD as
* appropriate.
*/
-static void *dax_insert_mapping_entry(struct address_space *mapping,
- struct vm_fault *vmf,
- void *entry, pfn_t pfn_t,
- unsigned long flags, bool dirty)
+static void *dax_insert_entry(struct xa_state *xas,
+ struct address_space *mapping, struct vm_fault *vmf,
+ void *entry, pfn_t pfn, unsigned long flags, bool dirty)
{
- struct radix_tree_root *pages = &mapping->i_pages;
- unsigned long pfn = pfn_t_to_pfn(pfn_t);
- pgoff_t index = vmf->pgoff;
- void *new_entry;
+ void *new_entry = dax_make_entry(pfn, flags);
if (dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
- if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) {
+ if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) {
+ unsigned long index = xas->xa_index;
/* we are replacing a zero page with block mapping */
if (dax_is_pmd_entry(entry))
unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
- PG_PMD_NR, false);
+ PG_PMD_NR, false);
else /* pte entry */
- unmap_mapping_pages(mapping, vmf->pgoff, 1, false);
+ unmap_mapping_pages(mapping, index, 1, false);
}
- xa_lock_irq(pages);
- new_entry = dax_radix_locked_entry(pfn, flags);
- if (dax_entry_size(entry) != dax_entry_size(new_entry)) {
+ xas_reset(xas);
+ xas_lock_irq(xas);
+ if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
+ void *old;
+
dax_disassociate_entry(entry, mapping, false);
dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address);
- }
-
- if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
/*
- * Only swap our new entry into the radix tree if the current
+ * Only swap our new entry into the page cache if the current
* entry is a zero page or an empty entry. If a normal PTE or
- * PMD entry is already in the tree, we leave it alone. This
+ * PMD entry is already in the cache, we leave it alone. This
* means that if we are trying to insert a PTE and the
* existing entry is a PMD, we will just leave the PMD in the
* tree and dirty it if necessary.
*/
- struct radix_tree_node *node;
- void **slot;
- void *ret;
-
- ret = __radix_tree_lookup(pages, index, &node, &slot);
- WARN_ON_ONCE(ret != entry);
- __radix_tree_replace(pages, node, slot,
- new_entry, NULL);
+ old = dax_lock_entry(xas, new_entry);
+ WARN_ON_ONCE(old != xa_mk_value(xa_to_value(entry) |
+ DAX_LOCKED));
entry = new_entry;
+ } else {
+ xas_load(xas); /* Walk the xa_state */
}
if (dirty)
- radix_tree_tag_set(pages, index, PAGECACHE_TAG_DIRTY);
+ xas_set_mark(xas, PAGECACHE_TAG_DIRTY);
- xa_unlock_irq(pages);
+ xas_unlock_irq(xas);
return entry;
}
-static inline unsigned long
-pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
+static inline
+unsigned long pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
{
unsigned long address;
@@ -864,8 +806,8 @@
}
/* Walk all mappings of a given index of a file and writeprotect them */
-static void dax_mapping_entry_mkclean(struct address_space *mapping,
- pgoff_t index, unsigned long pfn)
+static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
+ unsigned long pfn)
{
struct vm_area_struct *vma;
pte_t pte, *ptep = NULL;
@@ -874,7 +816,8 @@
i_mmap_lock_read(mapping);
vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
- unsigned long address, start, end;
+ struct mmu_notifier_range range;
+ unsigned long address;
cond_resched();
@@ -884,11 +827,12 @@
address = pgoff_address(index, vma);
/*
- * Note because we provide start/end to follow_pte_pmd it will
- * call mmu_notifier_invalidate_range_start() on our behalf
- * before taking any lock.
+ * follow_invalidate_pte() will use the range to call
+ * mmu_notifier_invalidate_range_start() on our behalf before
+ * taking any lock.
*/
- if (follow_pte_pmd(vma->vm_mm, address, &start, &end, &ptep, &pmdp, &ptl))
+ if (follow_invalidate_pte(vma->vm_mm, address, &range, &ptep,
+ &pmdp, &ptl))
continue;
/*
@@ -907,7 +851,8 @@
if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
goto unlock_pmd;
- flush_cache_page(vma, address, pfn);
+ flush_cache_range(vma, address,
+ address + HPAGE_PMD_SIZE);
pmd = pmdp_invalidate(vma, address, pmdp);
pmd = pmd_wrprotect(pmd);
pmd = pmd_mkclean(pmd);
@@ -930,50 +875,53 @@
pte_unmap_unlock(ptep, ptl);
}
- mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
+ mmu_notifier_invalidate_range_end(&range);
}
i_mmap_unlock_read(mapping);
}
-static int dax_writeback_one(struct dax_device *dax_dev,
- struct address_space *mapping, pgoff_t index, void *entry)
+static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
+ struct address_space *mapping, void *entry)
{
- struct radix_tree_root *pages = &mapping->i_pages;
- void *entry2, **slot;
- unsigned long pfn;
+ unsigned long pfn, index, count;
long ret = 0;
- size_t size;
/*
* A page got tagged dirty in DAX mapping? Something is seriously
* wrong.
*/
- if (WARN_ON(!radix_tree_exceptional_entry(entry)))
+ if (WARN_ON(!xa_is_value(entry)))
return -EIO;
- xa_lock_irq(pages);
- entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
- /* Entry got punched out / reallocated? */
- if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2)))
- goto put_unlocked;
- /*
- * Entry got reallocated elsewhere? No need to writeback. We have to
- * compare pfns as we must not bail out due to difference in lockbit
- * or entry type.
- */
- if (dax_radix_pfn(entry2) != dax_radix_pfn(entry))
- goto put_unlocked;
- if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
- dax_is_zero_entry(entry))) {
- ret = -EIO;
- goto put_unlocked;
+ if (unlikely(dax_is_locked(entry))) {
+ void *old_entry = entry;
+
+ entry = get_unlocked_entry(xas, 0);
+
+ /* Entry got punched out / reallocated? */
+ if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
+ goto put_unlocked;
+ /*
+ * Entry got reallocated elsewhere? No need to writeback.
+ * We have to compare pfns as we must not bail out due to
+ * difference in lockbit or entry type.
+ */
+ if (dax_to_pfn(old_entry) != dax_to_pfn(entry))
+ goto put_unlocked;
+ if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
+ dax_is_zero_entry(entry))) {
+ ret = -EIO;
+ goto put_unlocked;
+ }
+
+ /* Another fsync thread may have already done this entry */
+ if (!xas_get_mark(xas, PAGECACHE_TAG_TOWRITE))
+ goto put_unlocked;
}
- /* Another fsync thread may have already written back this entry */
- if (!radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE))
- goto put_unlocked;
/* Lock the entry to serialize with page faults */
- entry = lock_slot(mapping, slot);
+ dax_lock_entry(xas, entry);
+
/*
* We can clear the tag now but we have to be careful so that concurrent
* dax_writeback_one() calls for the same index cannot finish before we
@@ -981,37 +929,39 @@
* at the entry only under the i_pages lock and once they do that
* they will see the entry locked and wait for it to unlock.
*/
- radix_tree_tag_clear(pages, index, PAGECACHE_TAG_TOWRITE);
- xa_unlock_irq(pages);
+ xas_clear_mark(xas, PAGECACHE_TAG_TOWRITE);
+ xas_unlock_irq(xas);
/*
- * Even if dax_writeback_mapping_range() was given a wbc->range_start
- * in the middle of a PMD, the 'index' we are given will be aligned to
- * the start index of the PMD, as will the pfn we pull from 'entry'.
+ * If dax_writeback_mapping_range() was given a wbc->range_start
+ * in the middle of a PMD, the 'index' we use needs to be
+ * aligned to the start of the PMD.
* This allows us to flush for PMD_SIZE and not have to worry about
* partial PMD writebacks.
*/
- pfn = dax_radix_pfn(entry);
- size = PAGE_SIZE << dax_radix_order(entry);
+ pfn = dax_to_pfn(entry);
+ count = 1UL << dax_entry_order(entry);
+ index = xas->xa_index & ~(count - 1);
- dax_mapping_entry_mkclean(mapping, index, pfn);
- dax_flush(dax_dev, page_address(pfn_to_page(pfn)), size);
+ dax_entry_mkclean(mapping, index, pfn);
+ dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE);
/*
* After we have flushed the cache, we can clear the dirty tag. There
* cannot be new dirty data in the pfn after the flush has completed as
* the pfn mappings are writeprotected and fault waits for mapping
* entry lock.
*/
- xa_lock_irq(pages);
- radix_tree_tag_clear(pages, index, PAGECACHE_TAG_DIRTY);
- xa_unlock_irq(pages);
- trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
- put_locked_mapping_entry(mapping, index);
+ xas_reset(xas);
+ xas_lock_irq(xas);
+ xas_store(xas, entry);
+ xas_clear_mark(xas, PAGECACHE_TAG_DIRTY);
+ dax_wake_entry(xas, entry, WAKE_NEXT);
+
+ trace_dax_writeback_one(mapping->host, index, count);
return ret;
put_unlocked:
- put_unlocked_mapping_entry(mapping, index, entry2);
- xa_unlock_irq(pages);
+ put_unlocked_entry(xas, entry, WAKE_NEXT);
return ret;
}
@@ -1021,15 +971,14 @@
* on persistent storage prior to completion of the operation.
*/
int dax_writeback_mapping_range(struct address_space *mapping,
- struct block_device *bdev, struct writeback_control *wbc)
+ struct dax_device *dax_dev, struct writeback_control *wbc)
{
+ XA_STATE(xas, &mapping->i_pages, wbc->range_start >> PAGE_SHIFT);
struct inode *inode = mapping->host;
- pgoff_t start_index, end_index;
- pgoff_t indices[PAGEVEC_SIZE];
- struct dax_device *dax_dev;
- struct pagevec pvec;
- bool done = false;
- int i, ret = 0;
+ pgoff_t end_index = wbc->range_end >> PAGE_SHIFT;
+ void *entry;
+ int ret = 0;
+ unsigned int scanned = 0;
if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
return -EIO;
@@ -1037,45 +986,28 @@
if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
return 0;
- dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
- if (!dax_dev)
- return -EIO;
+ trace_dax_writeback_range(inode, xas.xa_index, end_index);
- start_index = wbc->range_start >> PAGE_SHIFT;
- end_index = wbc->range_end >> PAGE_SHIFT;
+ tag_pages_for_writeback(mapping, xas.xa_index, end_index);
- trace_dax_writeback_range(inode, start_index, end_index);
-
- tag_pages_for_writeback(mapping, start_index, end_index);
-
- pagevec_init(&pvec);
- while (!done) {
- pvec.nr = find_get_entries_tag(mapping, start_index,
- PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE,
- pvec.pages, indices);
-
- if (pvec.nr == 0)
+ xas_lock_irq(&xas);
+ xas_for_each_marked(&xas, entry, end_index, PAGECACHE_TAG_TOWRITE) {
+ ret = dax_writeback_one(&xas, dax_dev, mapping, entry);
+ if (ret < 0) {
+ mapping_set_error(mapping, ret);
break;
-
- for (i = 0; i < pvec.nr; i++) {
- if (indices[i] > end_index) {
- done = true;
- break;
- }
-
- ret = dax_writeback_one(dax_dev, mapping, indices[i],
- pvec.pages[i]);
- if (ret < 0) {
- mapping_set_error(mapping, ret);
- goto out;
- }
}
- start_index = indices[pvec.nr - 1] + 1;
+ if (++scanned % XA_CHECK_SCHED)
+ continue;
+
+ xas_pause(&xas);
+ xas_unlock_irq(&xas);
+ cond_resched();
+ xas_lock_irq(&xas);
}
-out:
- put_dax(dax_dev);
- trace_dax_writeback_range_done(inode, start_index, end_index);
- return (ret < 0 ? ret : 0);
+ xas_unlock_irq(&xas);
+ trace_dax_writeback_range_done(inode, xas.xa_index, end_index);
+ return ret;
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
@@ -1123,69 +1055,63 @@
* If this page is ever written to we will re-fault and change the mapping to
* point to real DAX storage instead.
*/
-static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
- struct vm_fault *vmf)
+static vm_fault_t dax_load_hole(struct xa_state *xas,
+ struct address_space *mapping, void **entry,
+ struct vm_fault *vmf)
{
struct inode *inode = mapping->host;
unsigned long vaddr = vmf->address;
pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
vm_fault_t ret;
- dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE,
- false);
+ *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
+ DAX_ZERO_PAGE, false);
+
ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
trace_dax_load_hole(inode, vmf, ret);
return ret;
}
-static bool dax_range_is_aligned(struct block_device *bdev,
- unsigned int offset, unsigned int length)
+s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
{
- unsigned short sector_size = bdev_logical_block_size(bdev);
+ sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
+ pgoff_t pgoff;
+ long rc, id;
+ void *kaddr;
+ bool page_aligned = false;
+ unsigned offset = offset_in_page(pos);
+ unsigned size = min_t(u64, PAGE_SIZE - offset, length);
- if (!IS_ALIGNED(offset, sector_size))
- return false;
- if (!IS_ALIGNED(length, sector_size))
- return false;
+ if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) &&
+ (size == PAGE_SIZE))
+ page_aligned = true;
- return true;
-}
+ rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff);
+ if (rc)
+ return rc;
-int __dax_zero_page_range(struct block_device *bdev,
- struct dax_device *dax_dev, sector_t sector,
- unsigned int offset, unsigned int size)
-{
- if (dax_range_is_aligned(bdev, offset, size)) {
- sector_t start_sector = sector + (offset >> 9);
+ id = dax_read_lock();
- return blkdev_issue_zeroout(bdev, start_sector,
- size >> 9, GFP_NOFS, 0);
- } else {
- pgoff_t pgoff;
- long rc, id;
- void *kaddr;
-
- rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
- if (rc)
- return rc;
-
- id = dax_read_lock();
- rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
- if (rc < 0) {
- dax_read_unlock(id);
- return rc;
- }
- memset(kaddr + offset, 0, size);
- dax_flush(dax_dev, kaddr + offset, size);
+ if (page_aligned)
+ rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
+ else
+ rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
+ if (rc < 0) {
dax_read_unlock(id);
+ return rc;
}
- return 0;
+
+ if (!page_aligned) {
+ memset(kaddr + offset, 0, size);
+ dax_flush(iomap->dax_dev, kaddr + offset, size);
+ }
+ dax_read_unlock(id);
+ return size;
}
-EXPORT_SYMBOL_GPL(__dax_zero_page_range);
static loff_t
dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
- struct iomap *iomap)
+ struct iomap *iomap, struct iomap *srcmap)
{
struct block_device *bdev = iomap->bdev;
struct dax_device *dax_dev = iomap->dax_dev;
@@ -1295,7 +1221,7 @@
unsigned flags = 0;
if (iov_iter_rw(iter) == WRITE) {
- lockdep_assert_held_exclusive(&inode->i_rwsem);
+ lockdep_assert_held_write(&inode->i_rwsem);
flags |= IOMAP_WRITE;
} else {
lockdep_assert_held(&inode->i_rwsem);
@@ -1322,9 +1248,7 @@
{
if (error == 0)
return VM_FAULT_NOPAGE;
- if (error == -ENOMEM)
- return VM_FAULT_OOM;
- return VM_FAULT_SIGBUS;
+ return vmf_error(error);
}
/*
@@ -1343,10 +1267,12 @@
{
struct vm_area_struct *vma = vmf->vma;
struct address_space *mapping = vma->vm_file->f_mapping;
+ XA_STATE(xas, &mapping->i_pages, vmf->pgoff);
struct inode *inode = mapping->host;
unsigned long vaddr = vmf->address;
loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
- struct iomap iomap = { 0 };
+ struct iomap iomap = { .type = IOMAP_HOLE };
+ struct iomap srcmap = { .type = IOMAP_HOLE };
unsigned flags = IOMAP_FAULT;
int error, major = 0;
bool write = vmf->flags & FAULT_FLAG_WRITE;
@@ -1369,9 +1295,9 @@
if (write && !vmf->cow_page)
flags |= IOMAP_WRITE;
- entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
- if (IS_ERR(entry)) {
- ret = dax_fault_return(PTR_ERR(entry));
+ entry = grab_mapping_entry(&xas, mapping, 0);
+ if (xa_is_internal(entry)) {
+ ret = xa_to_internal(entry);
goto out;
}
@@ -1391,7 +1317,7 @@
* the file system block size to be equal the page size, which means
* that we never have to deal with more than a single extent here.
*/
- error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
+ error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap, &srcmap);
if (iomap_errp)
*iomap_errp = error;
if (error) {
@@ -1412,8 +1338,8 @@
clear_user_highpage(vmf->cow_page, vaddr);
break;
case IOMAP_MAPPED:
- error = copy_user_dax(iomap.bdev, iomap.dax_dev,
- sector, PAGE_SIZE, vmf->cow_page, vaddr);
+ error = copy_cow_page_dax(iomap.bdev, iomap.dax_dev,
+ sector, vmf->cow_page, vaddr);
break;
default:
WARN_ON_ONCE(1);
@@ -1444,7 +1370,7 @@
if (error < 0)
goto error_finish_iomap;
- entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
+ entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
0, write && !sync);
/*
@@ -1472,10 +1398,10 @@
case IOMAP_UNWRITTEN:
case IOMAP_HOLE:
if (!write) {
- ret = dax_load_hole(mapping, entry, vmf);
+ ret = dax_load_hole(&xas, mapping, &entry, vmf);
goto finish_iomap;
}
- /*FALLTHRU*/
+ fallthrough;
default:
WARN_ON_ONCE(1);
error = -EIO;
@@ -1499,21 +1425,22 @@
ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
}
unlock_entry:
- put_locked_mapping_entry(mapping, vmf->pgoff);
+ dax_unlock_entry(&xas, entry);
out:
trace_dax_pte_fault_done(inode, vmf, ret);
return ret | major;
}
#ifdef CONFIG_FS_DAX_PMD
-static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
- void *entry)
+static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
+ struct iomap *iomap, void **entry)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
unsigned long pmd_addr = vmf->address & PMD_MASK;
+ struct vm_area_struct *vma = vmf->vma;
struct inode *inode = mapping->host;
+ pgtable_t pgtable = NULL;
struct page *zero_page;
- void *ret = NULL;
spinlock_t *ptl;
pmd_t pmd_entry;
pfn_t pfn;
@@ -1524,8 +1451,14 @@
goto fallback;
pfn = page_to_pfn_t(zero_page);
- ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
- RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
+ *entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
+ DAX_PMD | DAX_ZERO_PAGE, false);
+
+ if (arch_needs_pgtable_deposit()) {
+ pgtable = pte_alloc_one(vma->vm_mm);
+ if (!pgtable)
+ return VM_FAULT_OOM;
+ }
ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
if (!pmd_none(*(vmf->pmd))) {
@@ -1533,15 +1466,21 @@
goto fallback;
}
+ if (pgtable) {
+ pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
+ mm_inc_nr_ptes(vma->vm_mm);
+ }
pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
pmd_entry = pmd_mkhuge(pmd_entry);
set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
spin_unlock(ptl);
- trace_dax_pmd_load_hole(inode, vmf, zero_page, ret);
+ trace_dax_pmd_load_hole(inode, vmf, zero_page, *entry);
return VM_FAULT_NOPAGE;
fallback:
- trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, ret);
+ if (pgtable)
+ pte_free(vma->vm_mm, pgtable);
+ trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry);
return VM_FAULT_FALLBACK;
}
@@ -1550,14 +1489,16 @@
{
struct vm_area_struct *vma = vmf->vma;
struct address_space *mapping = vma->vm_file->f_mapping;
+ XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_ORDER);
unsigned long pmd_addr = vmf->address & PMD_MASK;
bool write = vmf->flags & FAULT_FLAG_WRITE;
bool sync;
unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
struct inode *inode = mapping->host;
vm_fault_t result = VM_FAULT_FALLBACK;
- struct iomap iomap = { 0 };
- pgoff_t max_pgoff, pgoff;
+ struct iomap iomap = { .type = IOMAP_HOLE };
+ struct iomap srcmap = { .type = IOMAP_HOLE };
+ pgoff_t max_pgoff;
void *entry;
loff_t pos;
int error;
@@ -1568,7 +1509,6 @@
* supposed to hold locks serializing us with truncate / punch hole so
* this is a reliable test.
*/
- pgoff = linear_page_index(vma, pmd_addr);
max_pgoff = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
@@ -1577,7 +1517,7 @@
* Make sure that the faulting address's PMD offset (color) matches
* the PMD offset from the start of the file. This is necessary so
* that a PMD range in the page table overlaps exactly with a PMD
- * range in the radix tree.
+ * range in the page cache.
*/
if ((vmf->pgoff & PG_PMD_COLOUR) !=
((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR))
@@ -1593,24 +1533,26 @@
if ((pmd_addr + PMD_SIZE) > vma->vm_end)
goto fallback;
- if (pgoff >= max_pgoff) {
+ if (xas.xa_index >= max_pgoff) {
result = VM_FAULT_SIGBUS;
goto out;
}
/* If the PMD would extend beyond the file size */
- if ((pgoff | PG_PMD_COLOUR) >= max_pgoff)
+ if ((xas.xa_index | PG_PMD_COLOUR) >= max_pgoff)
goto fallback;
/*
- * grab_mapping_entry() will make sure we get a 2MiB empty entry, a
- * 2MiB zero page entry or a DAX PMD. If it can't (because a 4k page
- * is already in the tree, for instance), it will return -EEXIST and
- * we just fall back to 4k entries.
+ * grab_mapping_entry() will make sure we get an empty PMD entry,
+ * a zero PMD entry or a DAX PMD. If it can't (because a PTE
+ * entry is already in the array, for instance), it will return
+ * VM_FAULT_FALLBACK.
*/
- entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
- if (IS_ERR(entry))
+ entry = grab_mapping_entry(&xas, mapping, PMD_ORDER);
+ if (xa_is_internal(entry)) {
+ result = xa_to_internal(entry);
goto fallback;
+ }
/*
* It is possible, particularly with mixed reads & writes to private
@@ -1629,8 +1571,9 @@
* setting up a mapping, so really we're using iomap_begin() as a way
* to look up our filesystem block.
*/
- pos = (loff_t)pgoff << PAGE_SHIFT;
- error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
+ pos = (loff_t)xas.xa_index << PAGE_SHIFT;
+ error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap,
+ &srcmap);
if (error)
goto unlock_entry;
@@ -1645,8 +1588,8 @@
if (error < 0)
goto finish_iomap;
- entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
- RADIX_DAX_PMD, write && !sync);
+ entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
+ DAX_PMD, write && !sync);
/*
* If we are doing synchronous page fault and inode needs fsync,
@@ -1669,7 +1612,7 @@
case IOMAP_HOLE:
if (WARN_ON_ONCE(write))
break;
- result = dax_pmd_load_hole(vmf, &iomap, entry);
+ result = dax_pmd_load_hole(&xas, vmf, &iomap, &entry);
break;
default:
WARN_ON_ONCE(1);
@@ -1692,7 +1635,7 @@
&iomap);
}
unlock_entry:
- put_locked_mapping_entry(mapping, pgoff);
+ dax_unlock_entry(&xas, entry);
fallback:
if (result == VM_FAULT_FALLBACK) {
split_huge_pmd(vma, vmf->pmd, vmf->address);
@@ -1737,53 +1680,46 @@
}
EXPORT_SYMBOL_GPL(dax_iomap_fault);
-/**
+/*
* dax_insert_pfn_mkwrite - insert PTE or PMD entry into page tables
* @vmf: The description of the fault
- * @pe_size: Size of entry to be inserted
* @pfn: PFN to insert
+ * @order: Order of entry to insert.
*
- * This function inserts writeable PTE or PMD entry into page tables for mmaped
- * DAX file. It takes care of marking corresponding radix tree entry as dirty
- * as well.
+ * This function inserts a writeable PTE or PMD entry into the page tables
+ * for an mmaped DAX file. It also marks the page cache entry as dirty.
*/
-static vm_fault_t dax_insert_pfn_mkwrite(struct vm_fault *vmf,
- enum page_entry_size pe_size,
- pfn_t pfn)
+static vm_fault_t
+dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
{
struct address_space *mapping = vmf->vma->vm_file->f_mapping;
- void *entry, **slot;
- pgoff_t index = vmf->pgoff;
+ XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, order);
+ void *entry;
vm_fault_t ret;
- xa_lock_irq(&mapping->i_pages);
- entry = get_unlocked_mapping_entry(mapping, index, &slot);
+ xas_lock_irq(&xas);
+ entry = get_unlocked_entry(&xas, order);
/* Did we race with someone splitting entry or so? */
- if (!entry ||
- (pe_size == PE_SIZE_PTE && !dax_is_pte_entry(entry)) ||
- (pe_size == PE_SIZE_PMD && !dax_is_pmd_entry(entry))) {
- put_unlocked_mapping_entry(mapping, index, entry);
- xa_unlock_irq(&mapping->i_pages);
+ if (!entry || dax_is_conflict(entry) ||
+ (order == 0 && !dax_is_pte_entry(entry))) {
+ put_unlocked_entry(&xas, entry, WAKE_NEXT);
+ xas_unlock_irq(&xas);
trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
VM_FAULT_NOPAGE);
return VM_FAULT_NOPAGE;
}
- radix_tree_tag_set(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY);
- entry = lock_slot(mapping, slot);
- xa_unlock_irq(&mapping->i_pages);
- switch (pe_size) {
- case PE_SIZE_PTE:
+ xas_set_mark(&xas, PAGECACHE_TAG_DIRTY);
+ dax_lock_entry(&xas, entry);
+ xas_unlock_irq(&xas);
+ if (order == 0)
ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
- break;
#ifdef CONFIG_FS_DAX_PMD
- case PE_SIZE_PMD:
+ else if (order == PMD_ORDER)
ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE);
- break;
#endif
- default:
+ else
ret = VM_FAULT_FALLBACK;
- }
- put_locked_mapping_entry(mapping, index);
+ dax_unlock_entry(&xas, entry);
trace_dax_insert_pfn_mkwrite(mapping->host, vmf, ret);
return ret;
}
@@ -1803,17 +1739,12 @@
{
int err;
loff_t start = ((loff_t)vmf->pgoff) << PAGE_SHIFT;
- size_t len = 0;
+ unsigned int order = pe_order(pe_size);
+ size_t len = PAGE_SIZE << order;
- if (pe_size == PE_SIZE_PTE)
- len = PAGE_SIZE;
- else if (pe_size == PE_SIZE_PMD)
- len = PMD_SIZE;
- else
- WARN_ON_ONCE(1);
err = vfs_fsync_range(vmf->vma->vm_file, start, start + len - 1, 1);
if (err)
return VM_FAULT_SIGBUS;
- return dax_insert_pfn_mkwrite(vmf, pe_size, pfn);
+ return dax_insert_pfn_mkwrite(vmf, pfn, order);
}
EXPORT_SYMBOL_GPL(dax_finish_sync_fault);
--
Gitblit v1.6.2