Merge branch 'for-3.9' of git://linux-nfs.org/~bfields/linux
Pull nfsd changes from J Bruce Fields:
"Miscellaneous bugfixes, plus:
- An overhaul of the DRC cache by Jeff Layton. The main effect is
just to make it larger. This decreases the chances of intermittent
errors especially in the UDP case. But we'll need to watch for any
reports of performance regressions.
- Containerized nfsd: with some limitations, we now support
per-container nfs-service, thanks to extensive work from Stanislav
Kinsbursky over the last year."
Some notes about conflicts, since there were *two* non-data semantic
conflicts here:
- idr_remove_all() had been added by a memory leak fix, but has since
become deprecated since idr_destroy() does it for us now.
- xs_local_connect() had been added by this branch to make AF_LOCAL
connections be synchronous, but in the meantime Trond had changed the
calling convention in order to avoid a RCU dereference.
There were a couple of more obvious actual source-level conflicts due to
the hlist traversal changes and one just due to code changes next to
each other, but those were trivial.
* 'for-3.9' of git://linux-nfs.org/~bfields/linux: (49 commits)
SUNRPC: make AF_LOCAL connect synchronous
nfsd: fix compiler warning about ambiguous types in nfsd_cache_csum
svcrpc: fix rpc server shutdown races
svcrpc: make svc_age_temp_xprts enqueue under sv_lock
lockd: nlmclnt_reclaim(): avoid stack overflow
nfsd: enable NFSv4 state in containers
nfsd: disable usermode helper client tracker in container
nfsd: use proper net while reading "exports" file
nfsd: containerize NFSd filesystem
nfsd: fix comments on nfsd_cache_lookup
SUNRPC: move cache_detail->cache_request callback call to cache_read()
SUNRPC: remove "cache_request" argument in sunrpc_cache_pipe_upcall() function
SUNRPC: rework cache upcall logic
SUNRPC: introduce cache_detail->cache_request callback
NFS: simplify and clean cache library
NFS: use SUNRPC cache creation and destruction helper for DNS cache
nfsd4: free_stid can be static
nfsd: keep a checksum of the first 256 bytes of request
sunrpc: trim off trailing checksum before returning decrypted or integrity authenticated buffer
sunrpc: fix comment in struct xdr_buf definition
...
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index da3dbd0..62c1ee1 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -9,22 +9,22 @@
*/
#include <linux/slab.h>
+#include <linux/sunrpc/addr.h>
+#include <linux/highmem.h>
+#include <net/checksum.h>
#include "nfsd.h"
#include "cache.h"
-/* Size of reply cache. Common values are:
- * 4.3BSD: 128
- * 4.4BSD: 256
- * Solaris2: 1024
- * DEC Unix: 512-4096
- */
-#define CACHESIZE 1024
+#define NFSDDBG_FACILITY NFSDDBG_REPCACHE
+
#define HASHSIZE 64
static struct hlist_head * cache_hash;
static struct list_head lru_head;
-static int cache_disabled = 1;
+static struct kmem_cache *drc_slab;
+static unsigned int num_drc_entries;
+static unsigned int max_drc_entries;
/*
* Calculate the hash index from an XID.
@@ -37,6 +37,14 @@
}
static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec);
+static void cache_cleaner_func(struct work_struct *unused);
+static int nfsd_reply_cache_shrink(struct shrinker *shrink,
+ struct shrink_control *sc);
+
+struct shrinker nfsd_reply_cache_shrinker = {
+ .shrink = nfsd_reply_cache_shrink,
+ .seeks = 1,
+};
/*
* locking for the reply cache:
@@ -44,30 +52,86 @@
* Otherwise, it when accessing _prev or _next, the lock must be held.
*/
static DEFINE_SPINLOCK(cache_lock);
+static DECLARE_DELAYED_WORK(cache_cleaner, cache_cleaner_func);
+
+/*
+ * Put a cap on the size of the DRC based on the amount of available
+ * low memory in the machine.
+ *
+ * 64MB: 8192
+ * 128MB: 11585
+ * 256MB: 16384
+ * 512MB: 23170
+ * 1GB: 32768
+ * 2GB: 46340
+ * 4GB: 65536
+ * 8GB: 92681
+ * 16GB: 131072
+ *
+ * ...with a hard cap of 256k entries. In the worst case, each entry will be
+ * ~1k, so the above numbers should give a rough max of the amount of memory
+ * used in k.
+ */
+static unsigned int
+nfsd_cache_size_limit(void)
+{
+ unsigned int limit;
+ unsigned long low_pages = totalram_pages - totalhigh_pages;
+
+ limit = (16 * int_sqrt(low_pages)) << (PAGE_SHIFT-10);
+ return min_t(unsigned int, limit, 256*1024);
+}
+
+static struct svc_cacherep *
+nfsd_reply_cache_alloc(void)
+{
+ struct svc_cacherep *rp;
+
+ rp = kmem_cache_alloc(drc_slab, GFP_KERNEL);
+ if (rp) {
+ rp->c_state = RC_UNUSED;
+ rp->c_type = RC_NOCACHE;
+ INIT_LIST_HEAD(&rp->c_lru);
+ INIT_HLIST_NODE(&rp->c_hash);
+ }
+ return rp;
+}
+
+static void
+nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
+{
+ if (rp->c_type == RC_REPLBUFF)
+ kfree(rp->c_replvec.iov_base);
+ hlist_del(&rp->c_hash);
+ list_del(&rp->c_lru);
+ --num_drc_entries;
+ kmem_cache_free(drc_slab, rp);
+}
+
+static void
+nfsd_reply_cache_free(struct svc_cacherep *rp)
+{
+ spin_lock(&cache_lock);
+ nfsd_reply_cache_free_locked(rp);
+ spin_unlock(&cache_lock);
+}
int nfsd_reply_cache_init(void)
{
- struct svc_cacherep *rp;
- int i;
+ register_shrinker(&nfsd_reply_cache_shrinker);
+ drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep),
+ 0, 0, NULL);
+ if (!drc_slab)
+ goto out_nomem;
- INIT_LIST_HEAD(&lru_head);
- i = CACHESIZE;
- while (i) {
- rp = kmalloc(sizeof(*rp), GFP_KERNEL);
- if (!rp)
- goto out_nomem;
- list_add(&rp->c_lru, &lru_head);
- rp->c_state = RC_UNUSED;
- rp->c_type = RC_NOCACHE;
- INIT_HLIST_NODE(&rp->c_hash);
- i--;
- }
-
- cache_hash = kcalloc (HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
+ cache_hash = kcalloc(HASHSIZE, sizeof(struct hlist_head), GFP_KERNEL);
if (!cache_hash)
goto out_nomem;
- cache_disabled = 0;
+ INIT_LIST_HEAD(&lru_head);
+ max_drc_entries = nfsd_cache_size_limit();
+ num_drc_entries = 0;
+
return 0;
out_nomem:
printk(KERN_ERR "nfsd: failed to allocate reply cache\n");
@@ -79,27 +143,33 @@
{
struct svc_cacherep *rp;
+ unregister_shrinker(&nfsd_reply_cache_shrinker);
+ cancel_delayed_work_sync(&cache_cleaner);
+
while (!list_empty(&lru_head)) {
rp = list_entry(lru_head.next, struct svc_cacherep, c_lru);
- if (rp->c_state == RC_DONE && rp->c_type == RC_REPLBUFF)
- kfree(rp->c_replvec.iov_base);
- list_del(&rp->c_lru);
- kfree(rp);
+ nfsd_reply_cache_free_locked(rp);
}
- cache_disabled = 1;
-
kfree (cache_hash);
cache_hash = NULL;
+
+ if (drc_slab) {
+ kmem_cache_destroy(drc_slab);
+ drc_slab = NULL;
+ }
}
/*
- * Move cache entry to end of LRU list
+ * Move cache entry to end of LRU list, and queue the cleaner to run if it's
+ * not already scheduled.
*/
static void
lru_put_end(struct svc_cacherep *rp)
{
+ rp->c_timestamp = jiffies;
list_move_tail(&rp->c_lru, &lru_head);
+ schedule_delayed_work(&cache_cleaner, RC_EXPIRE);
}
/*
@@ -112,82 +182,214 @@
hlist_add_head(&rp->c_hash, cache_hash + request_hash(rp->c_xid));
}
-/*
- * Try to find an entry matching the current call in the cache. When none
- * is found, we grab the oldest unlocked entry off the LRU list.
- * Note that no operation within the loop may sleep.
- */
-int
-nfsd_cache_lookup(struct svc_rqst *rqstp)
+static inline bool
+nfsd_cache_entry_expired(struct svc_cacherep *rp)
{
- struct hlist_head *rh;
+ return rp->c_state != RC_INPROG &&
+ time_after(jiffies, rp->c_timestamp + RC_EXPIRE);
+}
+
+/*
+ * Walk the LRU list and prune off entries that are older than RC_EXPIRE.
+ * Also prune the oldest ones when the total exceeds the max number of entries.
+ */
+static void
+prune_cache_entries(void)
+{
+ struct svc_cacherep *rp, *tmp;
+
+ list_for_each_entry_safe(rp, tmp, &lru_head, c_lru) {
+ if (!nfsd_cache_entry_expired(rp) &&
+ num_drc_entries <= max_drc_entries)
+ break;
+ nfsd_reply_cache_free_locked(rp);
+ }
+
+ /*
+ * Conditionally rearm the job. If we cleaned out the list, then
+ * cancel any pending run (since there won't be any work to do).
+ * Otherwise, we rearm the job or modify the existing one to run in
+ * RC_EXPIRE since we just ran the pruner.
+ */
+ if (list_empty(&lru_head))
+ cancel_delayed_work(&cache_cleaner);
+ else
+ mod_delayed_work(system_wq, &cache_cleaner, RC_EXPIRE);
+}
+
+static void
+cache_cleaner_func(struct work_struct *unused)
+{
+ spin_lock(&cache_lock);
+ prune_cache_entries();
+ spin_unlock(&cache_lock);
+}
+
+static int
+nfsd_reply_cache_shrink(struct shrinker *shrink, struct shrink_control *sc)
+{
+ unsigned int num;
+
+ spin_lock(&cache_lock);
+ if (sc->nr_to_scan)
+ prune_cache_entries();
+ num = num_drc_entries;
+ spin_unlock(&cache_lock);
+
+ return num;
+}
+
+/*
+ * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes
+ */
+static __wsum
+nfsd_cache_csum(struct svc_rqst *rqstp)
+{
+ int idx;
+ unsigned int base;
+ __wsum csum;
+ struct xdr_buf *buf = &rqstp->rq_arg;
+ const unsigned char *p = buf->head[0].iov_base;
+ size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len,
+ RC_CSUMLEN);
+ size_t len = min(buf->head[0].iov_len, csum_len);
+
+ /* rq_arg.head first */
+ csum = csum_partial(p, len, 0);
+ csum_len -= len;
+
+ /* Continue into page array */
+ idx = buf->page_base / PAGE_SIZE;
+ base = buf->page_base & ~PAGE_MASK;
+ while (csum_len) {
+ p = page_address(buf->pages[idx]) + base;
+ len = min_t(size_t, PAGE_SIZE - base, csum_len);
+ csum = csum_partial(p, len, csum);
+ csum_len -= len;
+ base = 0;
+ ++idx;
+ }
+ return csum;
+}
+
+/*
+ * Search the request hash for an entry that matches the given rqstp.
+ * Must be called with cache_lock held. Returns the found entry or
+ * NULL on failure.
+ */
+static struct svc_cacherep *
+nfsd_cache_search(struct svc_rqst *rqstp, __wsum csum)
+{
struct svc_cacherep *rp;
+ struct hlist_head *rh;
__be32 xid = rqstp->rq_xid;
u32 proto = rqstp->rq_prot,
vers = rqstp->rq_vers,
proc = rqstp->rq_proc;
+
+ rh = &cache_hash[request_hash(xid)];
+ hlist_for_each_entry(rp, rh, c_hash) {
+ if (xid == rp->c_xid && proc == rp->c_proc &&
+ proto == rp->c_prot && vers == rp->c_vers &&
+ rqstp->rq_arg.len == rp->c_len && csum == rp->c_csum &&
+ rpc_cmp_addr(svc_addr(rqstp), (struct sockaddr *)&rp->c_addr) &&
+ rpc_get_port(svc_addr(rqstp)) == rpc_get_port((struct sockaddr *)&rp->c_addr))
+ return rp;
+ }
+ return NULL;
+}
+
+/*
+ * Try to find an entry matching the current call in the cache. When none
+ * is found, we try to grab the oldest expired entry off the LRU list. If
+ * a suitable one isn't there, then drop the cache_lock and allocate a
+ * new one, then search again in case one got inserted while this thread
+ * didn't hold the lock.
+ */
+int
+nfsd_cache_lookup(struct svc_rqst *rqstp)
+{
+ struct svc_cacherep *rp, *found;
+ __be32 xid = rqstp->rq_xid;
+ u32 proto = rqstp->rq_prot,
+ vers = rqstp->rq_vers,
+ proc = rqstp->rq_proc;
+ __wsum csum;
unsigned long age;
int type = rqstp->rq_cachetype;
int rtn;
rqstp->rq_cacherep = NULL;
- if (cache_disabled || type == RC_NOCACHE) {
+ if (type == RC_NOCACHE) {
nfsdstats.rcnocache++;
return RC_DOIT;
}
+ csum = nfsd_cache_csum(rqstp);
+
spin_lock(&cache_lock);
rtn = RC_DOIT;
- rh = &cache_hash[request_hash(xid)];
- hlist_for_each_entry(rp, rh, c_hash) {
- if (rp->c_state != RC_UNUSED &&
- xid == rp->c_xid && proc == rp->c_proc &&
- proto == rp->c_prot && vers == rp->c_vers &&
- time_before(jiffies, rp->c_timestamp + 120*HZ) &&
- memcmp((char*)&rqstp->rq_addr, (char*)&rp->c_addr, sizeof(rp->c_addr))==0) {
- nfsdstats.rchits++;
- goto found_entry;
+ rp = nfsd_cache_search(rqstp, csum);
+ if (rp)
+ goto found_entry;
+
+ /* Try to use the first entry on the LRU */
+ if (!list_empty(&lru_head)) {
+ rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
+ if (nfsd_cache_entry_expired(rp) ||
+ num_drc_entries >= max_drc_entries) {
+ lru_put_end(rp);
+ prune_cache_entries();
+ goto setup_entry;
}
}
+
+ /* Drop the lock and allocate a new entry */
+ spin_unlock(&cache_lock);
+ rp = nfsd_reply_cache_alloc();
+ if (!rp) {
+ dprintk("nfsd: unable to allocate DRC entry!\n");
+ return RC_DOIT;
+ }
+ spin_lock(&cache_lock);
+ ++num_drc_entries;
+
+ /*
+ * Must search again just in case someone inserted one
+ * after we dropped the lock above.
+ */
+ found = nfsd_cache_search(rqstp, csum);
+ if (found) {
+ nfsd_reply_cache_free_locked(rp);
+ rp = found;
+ goto found_entry;
+ }
+
+ /*
+ * We're keeping the one we just allocated. Are we now over the
+ * limit? Prune one off the tip of the LRU in trade for the one we
+ * just allocated if so.
+ */
+ if (num_drc_entries >= max_drc_entries)
+ nfsd_reply_cache_free_locked(list_first_entry(&lru_head,
+ struct svc_cacherep, c_lru));
+
+setup_entry:
nfsdstats.rcmisses++;
-
- /* This loop shouldn't take more than a few iterations normally */
- {
- int safe = 0;
- list_for_each_entry(rp, &lru_head, c_lru) {
- if (rp->c_state != RC_INPROG)
- break;
- if (safe++ > CACHESIZE) {
- printk("nfsd: loop in repcache LRU list\n");
- cache_disabled = 1;
- goto out;
- }
- }
- }
-
- /* All entries on the LRU are in-progress. This should not happen */
- if (&rp->c_lru == &lru_head) {
- static int complaints;
-
- printk(KERN_WARNING "nfsd: all repcache entries locked!\n");
- if (++complaints > 5) {
- printk(KERN_WARNING "nfsd: disabling repcache.\n");
- cache_disabled = 1;
- }
- goto out;
- }
-
rqstp->rq_cacherep = rp;
rp->c_state = RC_INPROG;
rp->c_xid = xid;
rp->c_proc = proc;
- memcpy(&rp->c_addr, svc_addr_in(rqstp), sizeof(rp->c_addr));
+ rpc_copy_addr((struct sockaddr *)&rp->c_addr, svc_addr(rqstp));
+ rpc_set_port((struct sockaddr *)&rp->c_addr, rpc_get_port(svc_addr(rqstp)));
rp->c_prot = proto;
rp->c_vers = vers;
- rp->c_timestamp = jiffies;
+ rp->c_len = rqstp->rq_arg.len;
+ rp->c_csum = csum;
hash_refile(rp);
+ lru_put_end(rp);
/* release any buffer */
if (rp->c_type == RC_REPLBUFF) {
@@ -200,9 +402,9 @@
return rtn;
found_entry:
+ nfsdstats.rchits++;
/* We found a matching entry which is either in progress or done. */
age = jiffies - rp->c_timestamp;
- rp->c_timestamp = jiffies;
lru_put_end(rp);
rtn = RC_DROPIT;
@@ -231,7 +433,7 @@
break;
default:
printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type);
- rp->c_state = RC_UNUSED;
+ nfsd_reply_cache_free_locked(rp);
}
goto out;
@@ -256,11 +458,11 @@
void
nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp)
{
- struct svc_cacherep *rp;
+ struct svc_cacherep *rp = rqstp->rq_cacherep;
struct kvec *resv = &rqstp->rq_res.head[0], *cachv;
int len;
- if (!(rp = rqstp->rq_cacherep) || cache_disabled)
+ if (!rp)
return;
len = resv->iov_len - ((char*)statp - (char*)resv->iov_base);
@@ -268,7 +470,7 @@
/* Don't cache excessive amounts of data and XDR failures */
if (!statp || len > (256 >> 2)) {
- rp->c_state = RC_UNUSED;
+ nfsd_reply_cache_free(rp);
return;
}
@@ -282,21 +484,21 @@
cachv = &rp->c_replvec;
cachv->iov_base = kmalloc(len << 2, GFP_KERNEL);
if (!cachv->iov_base) {
- spin_lock(&cache_lock);
- rp->c_state = RC_UNUSED;
- spin_unlock(&cache_lock);
+ nfsd_reply_cache_free(rp);
return;
}
cachv->iov_len = len << 2;
memcpy(cachv->iov_base, statp, len << 2);
break;
+ case RC_NOCACHE:
+ nfsd_reply_cache_free(rp);
+ return;
}
spin_lock(&cache_lock);
lru_put_end(rp);
rp->c_secure = rqstp->rq_secure;
rp->c_type = cachetype;
rp->c_state = RC_DONE;
- rp->c_timestamp = jiffies;
spin_unlock(&cache_lock);
return;
}