#include <linux/sched.h>
#include <linux/kmemleak.h>
#include <linux/xattr.h>
+#include <linux/xxhash.h>
#include "delegation.h"
#include "iostat.h"
pgoff_t page_index_max;
u64 dir_cookie;
u64 last_cookie;
- u64 dup_cookie;
loff_t current_index;
- loff_t prev_index;
__be32 verf[NFS_DIR_VERIFIER_SIZE];
unsigned long dir_verifier;
unsigned int cache_entry_index;
unsigned int buffer_fills;
unsigned int dtsize;
- signed char duped;
bool plus;
bool eob;
bool eof;
return ret;
}
+#define NFS_READDIR_COOKIE_MASK (U32_MAX >> 14)
+/*
+ * Hash algorithm allowing content addressible access to sequences
+ * of directory cookies. Content is addressed by the value of the
+ * cookie index of the first readdir entry in a page.
+ *
+ * The xxhash algorithm is chosen because it is fast, and is supposed
+ * to result in a decent flat distribution of hashes.
+ *
+ * We then select only the first 18 bits to avoid issues with excessive
+ * memory use for the page cache XArray. 18 bits should allow the caching
+ * of 262144 pages of sequences of readdir entries. Since each page holds
+ * 127 readdir entries for a typical 64-bit system, that works out to a
+ * cache of ~ 33 million entries per directory.
+ */
+static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie)
+{
+ if (cookie == 0)
+ return 0;
+ return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK;
+}
+
static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie,
u64 change_attr)
{
}
static struct page *nfs_readdir_page_get_locked(struct address_space *mapping,
- pgoff_t index, u64 last_cookie)
+ u64 last_cookie,
+ u64 change_attr)
{
+ pgoff_t index = nfs_readdir_page_cookie_hash(last_cookie);
struct page *page;
- u64 change_attr;
page = grab_cache_page(mapping, index);
if (!page)
return NULL;
- change_attr = inode_peek_iversion_raw(mapping->host);
if (PageUptodate(page)) {
if (nfs_readdir_page_validate(page, last_cookie, change_attr))
return page;
return page;
}
-static loff_t nfs_readdir_page_offset(struct page *page)
-{
- return (loff_t)page->index * (loff_t)nfs_readdir_array_maxentries();
-}
-
static u64 nfs_readdir_page_last_cookie(struct page *page)
{
struct nfs_cache_array *array;
}
static struct page *nfs_readdir_page_get_next(struct address_space *mapping,
- pgoff_t index, u64 cookie)
+ u64 cookie, u64 change_attr)
{
struct page *page;
- page = nfs_readdir_page_get_locked(mapping, index, cookie);
+ page = nfs_readdir_page_get_locked(mapping, cookie, change_attr);
if (page) {
if (nfs_readdir_page_last_cookie(page) == cookie)
return page;
desc->last_cookie = array->array[0].cookie;
}
+static void nfs_readdir_rewind_search(struct nfs_readdir_descriptor *desc)
+{
+ desc->current_index = 0;
+ desc->last_cookie = 0;
+ desc->page_index = 0;
+}
+
static int nfs_readdir_search_for_pos(struct nfs_cache_array *array,
struct nfs_readdir_descriptor *desc)
{
static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array,
struct nfs_readdir_descriptor *desc)
{
- int i;
- loff_t new_pos;
+ unsigned int i;
int status = -EAGAIN;
if (!nfs_readdir_array_cookie_in_range(array, desc->dir_cookie))
for (i = 0; i < array->size; i++) {
if (array->array[i].cookie == desc->dir_cookie) {
- struct nfs_inode *nfsi = NFS_I(file_inode(desc->file));
-
- new_pos = nfs_readdir_page_offset(desc->page) + i;
- if (desc->attr_gencount != nfsi->attr_gencount) {
- desc->duped = 0;
- desc->attr_gencount = nfsi->attr_gencount;
- } else if (new_pos < desc->prev_index) {
- if (desc->duped > 0
- && desc->dup_cookie == desc->dir_cookie) {
- if (printk_ratelimit()) {
- pr_notice("NFS: directory %pD2 contains a readdir loop."
- "Please contact your server vendor. "
- "The file: %s has duplicate cookie %llu\n",
- desc->file, array->array[i].name, desc->dir_cookie);
- }
- status = -ELOOP;
- goto out;
- }
- desc->dup_cookie = desc->dir_cookie;
- desc->duped = -1;
- }
if (nfs_readdir_use_cookie(desc->file))
desc->ctx->pos = desc->dir_cookie;
else
- desc->ctx->pos = new_pos;
- desc->prev_index = new_pos;
+ desc->ctx->pos = desc->current_index + i;
desc->cache_entry_index = i;
return 0;
}
desc->eof = true;
} else
nfs_readdir_seek_next_array(array, desc);
-out:
return status;
}
/* Perform conversion from xdr to cache array */
static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc,
struct nfs_entry *entry,
- struct page **xdr_pages,
- unsigned int buflen,
- struct page **arrays,
- size_t narrays)
+ struct page **xdr_pages, unsigned int buflen,
+ struct page **arrays, size_t narrays,
+ u64 change_attr)
{
struct address_space *mapping = desc->file->f_mapping;
struct xdr_stream stream;
break;
arrays++;
*arrays = page = new;
- desc->page_index_max++;
} else {
- new = nfs_readdir_page_get_next(mapping,
- page->index + 1,
- entry->prev_cookie);
+ new = nfs_readdir_page_get_next(
+ mapping, entry->prev_cookie, change_attr);
if (!new)
break;
if (page != *arrays)
nfs_readdir_page_unlock_and_put(page);
page = new;
- desc->page_index_max = new->index;
}
+ desc->page_index_max++;
status = nfs_readdir_add_to_array(entry, page);
} while (!status && !entry->eof);
__be32 *verf_arg, __be32 *verf_res,
struct page **arrays, size_t narrays)
{
+ u64 change_attr;
struct page **pages;
struct page *page = *arrays;
struct nfs_entry *entry;
if (!pages)
goto out;
+ change_attr = inode_peek_iversion_raw(inode);
status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie, pages,
dtsize, verf_res);
if (status < 0)
pglen = status;
if (pglen != 0)
status = nfs_readdir_page_filler(desc, entry, pages, pglen,
- arrays, narrays);
+ arrays, narrays, change_attr);
else
nfs_readdir_page_set_eof(page);
desc->buffer_fills++;
static struct page *
nfs_readdir_page_get_cached(struct nfs_readdir_descriptor *desc)
{
- return nfs_readdir_page_get_locked(desc->file->f_mapping,
- desc->page_index,
- desc->last_cookie);
+ struct address_space *mapping = desc->file->f_mapping;
+ u64 change_attr = inode_peek_iversion_raw(mapping->host);
+
+ return nfs_readdir_page_get_locked(mapping, desc->last_cookie,
+ change_attr);
}
/*
trace_nfs_readdir_cache_fill_done(inode, res);
if (res == -EBADCOOKIE || res == -ENOTSYNC) {
invalidate_inode_pages2(desc->file->f_mapping);
- desc->page_index = 0;
+ nfs_readdir_rewind_search(desc);
trace_nfs_readdir_invalidate_cache_range(
inode, 0, MAX_LFS_FILESIZE);
return -EAGAIN;
memcmp(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf))) {
memcpy(nfsi->cookieverf, verf,
sizeof(nfsi->cookieverf));
- invalidate_inode_pages2_range(desc->file->f_mapping,
- desc->page_index_max + 1,
+ invalidate_inode_pages2_range(desc->file->f_mapping, 1,
-1);
trace_nfs_readdir_invalidate_cache_range(
- inode, desc->page_index_max + 1,
- MAX_LFS_FILESIZE);
+ inode, 1, MAX_LFS_FILESIZE);
}
}
res = nfs_readdir_search_array(desc);
int res;
do {
- if (desc->page_index == 0) {
- desc->current_index = 0;
- desc->prev_index = 0;
- desc->last_cookie = 0;
- }
res = find_and_lock_cache_page(desc);
} while (res == -EAGAIN);
return res;
desc->ctx->pos = desc->dir_cookie;
else
desc->ctx->pos++;
- if (desc->duped != 0)
- desc->duped = 1;
}
if (array->page_is_eof)
desc->eof = !desc->eob;
desc->page_index = 0;
desc->cache_entry_index = 0;
desc->last_cookie = desc->dir_cookie;
- desc->duped = 0;
desc->page_index_max = 0;
trace_nfs_readdir_uncached(desc->file, desc->verf, desc->last_cookie,
for (i = 0; i < sz && arrays[i]; i++)
nfs_readdir_page_array_free(arrays[i]);
out:
+ if (!nfs_readdir_use_cookie(desc->file))
+ nfs_readdir_rewind_search(desc);
desc->page_index_max = -1;
kfree(arrays);
dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status);
static void nfs_readdir_handle_cache_misses(struct inode *inode,
struct nfs_readdir_descriptor *desc,
- pgoff_t page_index,
unsigned int cache_misses)
{
if (desc->ctx->pos == 0 ||
cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD)
return;
- if (invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1) == 0)
+ if (invalidate_mapping_pages(inode->i_mapping, 0, -1) == 0)
return;
- trace_nfs_readdir_invalidate_cache_range(
- inode, (loff_t)(page_index + 1) << PAGE_SHIFT,
- MAX_LFS_FILESIZE);
+ trace_nfs_readdir_invalidate_cache_range(inode, 0, MAX_LFS_FILESIZE);
}
/* The file offset position represents the dirent entry number. A
struct nfs_open_dir_context *dir_ctx = file->private_data;
struct nfs_readdir_descriptor *desc;
unsigned int cache_hits, cache_misses;
- pgoff_t page_index;
int res;
dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",
spin_lock(&file->f_lock);
desc->dir_cookie = dir_ctx->dir_cookie;
- desc->dup_cookie = dir_ctx->dup_cookie;
- desc->duped = dir_ctx->duped;
- page_index = dir_ctx->page_index;
- desc->page_index = page_index;
+ desc->page_index = dir_ctx->page_index;
desc->last_cookie = dir_ctx->last_cookie;
desc->attr_gencount = dir_ctx->attr_gencount;
desc->eof = dir_ctx->eof;
}
desc->plus = nfs_use_readdirplus(inode, ctx, cache_hits, cache_misses);
- nfs_readdir_handle_cache_misses(inode, desc, page_index, cache_misses);
+ nfs_readdir_handle_cache_misses(inode, desc, cache_misses);
do {
res = readdir_search_pagecache(desc);
}
if (res == -ETOOSMALL && desc->plus) {
nfs_zap_caches(inode);
- desc->page_index = 0;
desc->plus = false;
desc->eof = false;
continue;
spin_lock(&file->f_lock);
dir_ctx->dir_cookie = desc->dir_cookie;
- dir_ctx->dup_cookie = desc->dup_cookie;
dir_ctx->last_cookie = desc->last_cookie;
- dir_ctx->duped = desc->duped;
dir_ctx->attr_gencount = desc->attr_gencount;
dir_ctx->page_index = desc->page_index;
dir_ctx->eof = desc->eof;
if (offset != filp->f_pos) {
filp->f_pos = offset;
dir_ctx->page_index = 0;
- if (!nfs_readdir_use_cookie(filp))
+ if (!nfs_readdir_use_cookie(filp)) {
dir_ctx->dir_cookie = 0;
- else
+ dir_ctx->last_cookie = 0;
+ } else {
dir_ctx->dir_cookie = offset;
- if (offset == 0)
- memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf));
- dir_ctx->duped = 0;
+ dir_ctx->last_cookie = offset;
+ }
dir_ctx->eof = false;
}
spin_unlock(&filp->f_lock);
projects / linux.git / commitdiff