aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2018-11-03 23:42:16 +0100
committerIngo Molnar <mingo@kernel.org>2018-11-03 23:42:16 +0100
commit23a12ddee1ce28065b71f14ccc695b5a0c8a64ff (patch)
treecedaa1cde5b2557116e523c31552187804704093 /net
parent98f76206b33504b934209d16196477dfa519a807 (diff)
parentbcb6fb5da77c2a228adf07cc9cb1a0c2aa2001c6 (diff)
downloadlinux-23a12ddee1ce28065b71f14ccc695b5a0c8a64ff.tar.gz
Merge branch 'core/urgent' into x86/urgent, to pick up objtool fix
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'net')
-rw-r--r--net/9p/Makefile1
-rw-r--r--net/9p/client.c551
-rw-r--r--net/9p/mod.c9
-rw-r--r--net/9p/protocol.c20
-rw-r--r--net/9p/trans_fd.c64
-rw-r--r--net/9p/trans_rdma.c37
-rw-r--r--net/9p/trans_virtio.c44
-rw-r--r--net/9p/trans_xen.c17
-rw-r--r--net/9p/util.c140
-rw-r--r--net/bridge/br_multicast.c3
-rw-r--r--net/ceph/messenger.c107
-rw-r--r--net/ceph/msgpool.c27
-rw-r--r--net/ceph/osd_client.c363
-rw-r--r--net/ceph/pagelist.c20
-rw-r--r--net/core/dev.c2
-rw-r--r--net/core/filter.c21
-rw-r--r--net/core/sysctl_net_core.c10
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/udp.c2
-rw-r--r--net/ipv4/udp_diag.c1
-rw-r--r--net/sched/sch_gred.c2
-rw-r--r--net/sctp/protocol.c2
-rw-r--r--net/sunrpc/auth_gss/svcauth_gss.c41
-rw-r--r--net/sunrpc/cache.c153
-rw-r--r--net/sunrpc/svc_xprt.c2
-rw-r--r--net/sunrpc/svcauth.c74
-rw-r--r--net/sunrpc/svcauth_unix.c24
-rw-r--r--net/sunrpc/svcsock.c53
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_backchannel.c23
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c10
-rw-r--r--net/xfrm/xfrm_hash.c2
32 files changed, 1006 insertions, 823 deletions
diff --git a/net/9p/Makefile b/net/9p/Makefile
index c0486cfc85d9..aa0a5641e5d0 100644
--- a/net/9p/Makefile
+++ b/net/9p/Makefile
@@ -8,7 +8,6 @@ obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o
mod.o \
client.o \
error.o \
- util.o \
protocol.o \
trans_fd.o \
trans_common.o \
diff --git a/net/9p/client.c b/net/9p/client.c
index deae53a7dffc..5f23e18eecc0 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -231,144 +231,170 @@ free_and_return:
return ret;
}
-static struct p9_fcall *p9_fcall_alloc(int alloc_msize)
+static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc,
+ int alloc_msize)
{
- struct p9_fcall *fc;
- fc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, GFP_NOFS);
- if (!fc)
- return NULL;
+ if (likely(c->fcall_cache) && alloc_msize == c->msize) {
+ fc->sdata = kmem_cache_alloc(c->fcall_cache, GFP_NOFS);
+ fc->cache = c->fcall_cache;
+ } else {
+ fc->sdata = kmalloc(alloc_msize, GFP_NOFS);
+ fc->cache = NULL;
+ }
+ if (!fc->sdata)
+ return -ENOMEM;
fc->capacity = alloc_msize;
- fc->sdata = (char *) fc + sizeof(struct p9_fcall);
- return fc;
+ return 0;
+}
+
+void p9_fcall_fini(struct p9_fcall *fc)
+{
+ /* sdata can be NULL for interrupted requests in trans_rdma,
+ * and kmem_cache_free does not do NULL-check for us
+ */
+ if (unlikely(!fc->sdata))
+ return;
+
+ if (fc->cache)
+ kmem_cache_free(fc->cache, fc->sdata);
+ else
+ kfree(fc->sdata);
}
+EXPORT_SYMBOL(p9_fcall_fini);
+
+static struct kmem_cache *p9_req_cache;
/**
- * p9_tag_alloc - lookup/allocate a request by tag
- * @c: client session to lookup tag within
- * @tag: numeric id for transaction
- *
- * this is a simple array lookup, but will grow the
- * request_slots as necessary to accommodate transaction
- * ids which did not previously have a slot.
- *
- * this code relies on the client spinlock to manage locks, its
- * possible we should switch to something else, but I'd rather
- * stick with something low-overhead for the common case.
+ * p9_req_alloc - Allocate a new request.
+ * @c: Client session.
+ * @type: Transaction type.
+ * @max_size: Maximum packet size for this request.
*
+ * Context: Process context.
+ * Return: Pointer to new request.
*/
-
static struct p9_req_t *
-p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size)
+p9_tag_alloc(struct p9_client *c, int8_t type, unsigned int max_size)
{
- unsigned long flags;
- int row, col;
- struct p9_req_t *req;
+ struct p9_req_t *req = kmem_cache_alloc(p9_req_cache, GFP_NOFS);
int alloc_msize = min(c->msize, max_size);
+ int tag;
- /* This looks up the original request by tag so we know which
- * buffer to read the data into */
- tag++;
-
- if (tag >= c->max_tag) {
- spin_lock_irqsave(&c->lock, flags);
- /* check again since original check was outside of lock */
- while (tag >= c->max_tag) {
- row = (tag / P9_ROW_MAXTAG);
- c->reqs[row] = kcalloc(P9_ROW_MAXTAG,
- sizeof(struct p9_req_t), GFP_ATOMIC);
-
- if (!c->reqs[row]) {
- pr_err("Couldn't grow tag array\n");
- spin_unlock_irqrestore(&c->lock, flags);
- return ERR_PTR(-ENOMEM);
- }
- for (col = 0; col < P9_ROW_MAXTAG; col++) {
- req = &c->reqs[row][col];
- req->status = REQ_STATUS_IDLE;
- init_waitqueue_head(&req->wq);
- }
- c->max_tag += P9_ROW_MAXTAG;
- }
- spin_unlock_irqrestore(&c->lock, flags);
- }
- row = tag / P9_ROW_MAXTAG;
- col = tag % P9_ROW_MAXTAG;
-
- req = &c->reqs[row][col];
- if (!req->tc)
- req->tc = p9_fcall_alloc(alloc_msize);
- if (!req->rc)
- req->rc = p9_fcall_alloc(alloc_msize);
- if (!req->tc || !req->rc)
- goto grow_failed;
+ if (!req)
+ return ERR_PTR(-ENOMEM);
- p9pdu_reset(req->tc);
- p9pdu_reset(req->rc);
+ if (p9_fcall_init(c, &req->tc, alloc_msize))
+ goto free_req;
+ if (p9_fcall_init(c, &req->rc, alloc_msize))
+ goto free;
- req->tc->tag = tag-1;
+ p9pdu_reset(&req->tc);
+ p9pdu_reset(&req->rc);
req->status = REQ_STATUS_ALLOC;
+ init_waitqueue_head(&req->wq);
+ INIT_LIST_HEAD(&req->req_list);
+
+ idr_preload(GFP_NOFS);
+ spin_lock_irq(&c->lock);
+ if (type == P9_TVERSION)
+ tag = idr_alloc(&c->reqs, req, P9_NOTAG, P9_NOTAG + 1,
+ GFP_NOWAIT);
+ else
+ tag = idr_alloc(&c->reqs, req, 0, P9_NOTAG, GFP_NOWAIT);
+ req->tc.tag = tag;
+ spin_unlock_irq(&c->lock);
+ idr_preload_end();
+ if (tag < 0)
+ goto free;
+
+ /* Init ref to two because in the general case there is one ref
+ * that is put asynchronously by a writer thread, one ref
+ * temporarily given by p9_tag_lookup and put by p9_client_cb
+ * in the recv thread, and one ref put by p9_tag_remove in the
+ * main thread. The only exception is virtio that does not use
+ * p9_tag_lookup but does not have a writer thread either
+ * (the write happens synchronously in the request/zc_request
+ * callback), so p9_client_cb eats the second ref there
+ * as the pointer is duplicated directly by virtqueue_add_sgs()
+ */
+ refcount_set(&req->refcount.refcount, 2);
return req;
-grow_failed:
- pr_err("Couldn't grow tag array\n");
- kfree(req->tc);
- kfree(req->rc);
- req->tc = req->rc = NULL;
+free:
+ p9_fcall_fini(&req->tc);
+ p9_fcall_fini(&req->rc);
+free_req:
+ kmem_cache_free(p9_req_cache, req);
return ERR_PTR(-ENOMEM);
}
/**
- * p9_tag_lookup - lookup a request by tag
- * @c: client session to lookup tag within
- * @tag: numeric id for transaction
+ * p9_tag_lookup - Look up a request by tag.
+ * @c: Client session.
+ * @tag: Transaction ID.
*
+ * Context: Any context.
+ * Return: A request, or %NULL if there is no request with that tag.
*/
-
struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag)
{
- int row, col;
-
- /* This looks up the original request by tag so we know which
- * buffer to read the data into */
- tag++;
-
- if (tag >= c->max_tag)
- return NULL;
+ struct p9_req_t *req;
- row = tag / P9_ROW_MAXTAG;
- col = tag % P9_ROW_MAXTAG;
+ rcu_read_lock();
+again:
+ req = idr_find(&c->reqs, tag);
+ if (req) {
+ /* We have to be careful with the req found under rcu_read_lock
+ * Thanks to SLAB_TYPESAFE_BY_RCU we can safely try to get the
+ * ref again without corrupting other data, then check again
+ * that the tag matches once we have the ref
+ */
+ if (!p9_req_try_get(req))
+ goto again;
+ if (req->tc.tag != tag) {
+ p9_req_put(req);
+ goto again;
+ }
+ }
+ rcu_read_unlock();
- return &c->reqs[row][col];
+ return req;
}
EXPORT_SYMBOL(p9_tag_lookup);
/**
- * p9_tag_init - setup tags structure and contents
- * @c: v9fs client struct
- *
- * This initializes the tags structure for each client instance.
+ * p9_tag_remove - Remove a tag.
+ * @c: Client session.
+ * @r: Request of reference.
*
+ * Context: Any context.
*/
+static int p9_tag_remove(struct p9_client *c, struct p9_req_t *r)
+{
+ unsigned long flags;
+ u16 tag = r->tc.tag;
+
+ p9_debug(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag);
+ spin_lock_irqsave(&c->lock, flags);
+ idr_remove(&c->reqs, tag);
+ spin_unlock_irqrestore(&c->lock, flags);
+ return p9_req_put(r);
+}
-static int p9_tag_init(struct p9_client *c)
+static void p9_req_free(struct kref *ref)
{
- int err = 0;
+ struct p9_req_t *r = container_of(ref, struct p9_req_t, refcount);
+ p9_fcall_fini(&r->tc);
+ p9_fcall_fini(&r->rc);
+ kmem_cache_free(p9_req_cache, r);
+}
- c->tagpool = p9_idpool_create();
- if (IS_ERR(c->tagpool)) {
- err = PTR_ERR(c->tagpool);
- goto error;
- }
- err = p9_idpool_get(c->tagpool); /* reserve tag 0 */
- if (err < 0) {
- p9_idpool_destroy(c->tagpool);
- goto error;
- }
- c->max_tag = 0;
-error:
- return err;
+int p9_req_put(struct p9_req_t *r)
+{
+ return kref_put(&r->refcount, p9_req_free);
}
+EXPORT_SYMBOL(p9_req_put);
/**
* p9_tag_cleanup - cleans up tags structure and reclaims resources
@@ -379,52 +405,17 @@ error:
*/
static void p9_tag_cleanup(struct p9_client *c)
{
- int row, col;
-
- /* check to insure all requests are idle */
- for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
- for (col = 0; col < P9_ROW_MAXTAG; col++) {
- if (c->reqs[row][col].status != REQ_STATUS_IDLE) {
- p9_debug(P9_DEBUG_MUX,
- "Attempting to cleanup non-free tag %d,%d\n",
- row, col);
- /* TODO: delay execution of cleanup */
- return;
- }
- }
- }
-
- if (c->tagpool) {
- p9_idpool_put(0, c->tagpool); /* free reserved tag 0 */
- p9_idpool_destroy(c->tagpool);
- }
+ struct p9_req_t *req;
+ int id;
- /* free requests associated with tags */
- for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
- for (col = 0; col < P9_ROW_MAXTAG; col++) {
- kfree(c->reqs[row][col].tc);
- kfree(c->reqs[row][col].rc);
- }
- kfree(c->reqs[row]);
+ rcu_read_lock();
+ idr_for_each_entry(&c->reqs, req, id) {
+ pr_info("Tag %d still in use\n", id);
+ if (p9_tag_remove(c, req) == 0)
+ pr_warn("Packet with tag %d has still references",
+ req->tc.tag);
}
- c->max_tag = 0;
-}
-
-/**
- * p9_free_req - free a request and clean-up as necessary
- * c: client state
- * r: request to release
- *
- */
-
-static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
-{
- int tag = r->tc->tag;
- p9_debug(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag);
-
- r->status = REQ_STATUS_IDLE;
- if (tag != P9_NOTAG && p9_idpool_check(tag, c->tagpool))
- p9_idpool_put(tag, c->tagpool);
+ rcu_read_unlock();
}
/**
@@ -435,7 +426,7 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
*/
void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
{
- p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc->tag);
+ p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc.tag);
/*
* This barrier is needed to make sure any change made to req before
@@ -445,7 +436,8 @@ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
req->status = status;
wake_up(&req->wq);
- p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
+ p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc.tag);
+ p9_req_put(req);
}
EXPORT_SYMBOL(p9_client_cb);
@@ -516,18 +508,18 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
int err;
int ecode;
- err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
- if (req->rc->size >= c->msize) {
+ err = p9_parse_header(&req->rc, NULL, &type, NULL, 0);
+ if (req->rc.size >= c->msize) {
p9_debug(P9_DEBUG_ERROR,
"requested packet size too big: %d\n",
- req->rc->size);
+ req->rc.size);
return -EIO;
}
/*
* dump the response from server
* This should be after check errors which poplulate pdu_fcall.
*/
- trace_9p_protocol_dump(c, req->rc);
+ trace_9p_protocol_dump(c, &req->rc);
if (err) {
p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err);
return err;
@@ -537,7 +529,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
if (!p9_is_proto_dotl(c)) {
char *ename;
- err = p9pdu_readf(req->rc, c->proto_version, "s?d",
+ err = p9pdu_readf(&req->rc, c->proto_version, "s?d",
&ename, &ecode);
if (err)
goto out_err;
@@ -553,7 +545,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
}
kfree(ename);
} else {
- err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode);
+ err = p9pdu_readf(&req->rc, c->proto_version, "d", &ecode);
err = -ecode;
p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
@@ -587,12 +579,12 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
int8_t type;
char *ename = NULL;
- err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
+ err = p9_parse_header(&req->rc, NULL, &type, NULL, 0);
/*
* dump the response from server
* This should be after parse_header which poplulate pdu_fcall.
*/
- trace_9p_protocol_dump(c, req->rc);
+ trace_9p_protocol_dump(c, &req->rc);
if (err) {
p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err);
return err;
@@ -607,13 +599,13 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
/* 7 = header size for RERROR; */
int inline_len = in_hdrlen - 7;
- len = req->rc->size - req->rc->offset;
+ len = req->rc.size - req->rc.offset;
if (len > (P9_ZC_HDR_SZ - 7)) {
err = -EFAULT;
goto out_err;
}
- ename = &req->rc->sdata[req->rc->offset];
+ ename = &req->rc.sdata[req->rc.offset];
if (len > inline_len) {
/* We have error in external buffer */
if (!copy_from_iter_full(ename + inline_len,
@@ -623,7 +615,7 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
}
}
ename = NULL;
- err = p9pdu_readf(req->rc, c->proto_version, "s?d",
+ err = p9pdu_readf(&req->rc, c->proto_version, "s?d",
&ename, &ecode);
if (err)
goto out_err;
@@ -639,7 +631,7 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
}
kfree(ename);
} else {
- err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode);
+ err = p9pdu_readf(&req->rc, c->proto_version, "d", &ecode);
err = -ecode;
p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
@@ -672,7 +664,7 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
int16_t oldtag;
int err;
- err = p9_parse_header(oldreq->tc, NULL, NULL, &oldtag, 1);
+ err = p9_parse_header(&oldreq->tc, NULL, NULL, &oldtag, 1);
if (err)
return err;
@@ -686,11 +678,12 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
* if we haven't received a response for oldreq,
* remove it from the list
*/
- if (oldreq->status == REQ_STATUS_SENT)
+ if (oldreq->status == REQ_STATUS_SENT) {
if (c->trans_mod->cancelled)
c->trans_mod->cancelled(c, oldreq);
+ }
- p9_free_req(c, req);
+ p9_tag_remove(c, req);
return 0;
}
@@ -698,7 +691,7 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
int8_t type, int req_size,
const char *fmt, va_list ap)
{
- int tag, err;
+ int err;
struct p9_req_t *req;
p9_debug(P9_DEBUG_MUX, "client %p op %d\n", c, type);
@@ -711,27 +704,22 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
if ((c->status == BeginDisconnect) && (type != P9_TCLUNK))
return ERR_PTR(-EIO);
- tag = P9_NOTAG;
- if (type != P9_TVERSION) {
- tag = p9_idpool_get(c->tagpool);
- if (tag < 0)
- return ERR_PTR(-ENOMEM);
- }
-
- req = p9_tag_alloc(c, tag, req_size);
+ req = p9_tag_alloc(c, type, req_size);
if (IS_ERR(req))
return req;
/* marshall the data */
- p9pdu_prepare(req->tc, tag, type);
- err = p9pdu_vwritef(req->tc, c->proto_version, fmt, ap);
+ p9pdu_prepare(&req->tc, req->tc.tag, type);
+ err = p9pdu_vwritef(&req->tc, c->proto_version, fmt, ap);
if (err)
goto reterr;
- p9pdu_finalize(c, req->tc);
- trace_9p_client_req(c, type, tag);
+ p9pdu_finalize(c, &req->tc);
+ trace_9p_client_req(c, type, req->tc.tag);
return req;
reterr:
- p9_free_req(c, req);
+ p9_tag_remove(c, req);
+ /* We have to put also the 2nd reference as it won't be used */
+ p9_req_put(req);
return ERR_PTR(err);
}
@@ -741,7 +729,7 @@ reterr:
* @type: type of request
* @fmt: protocol format string (see protocol.c)
*
- * Returns request structure (which client must free using p9_free_req)
+ * Returns request structure (which client must free using p9_tag_remove)
*/
static struct p9_req_t *
@@ -766,6 +754,8 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
err = c->trans_mod->request(c, req);
if (err < 0) {
+ /* write won't happen */
+ p9_req_put(req);
if (err != -ERESTARTSYS && err != -EFAULT)
c->status = Disconnected;
goto recalc_sigpending;
@@ -813,11 +803,11 @@ recalc_sigpending:
goto reterr;
err = p9_check_errors(c, req);
- trace_9p_client_res(c, type, req->rc->tag, err);
+ trace_9p_client_res(c, type, req->rc.tag, err);
if (!err)
return req;
reterr:
- p9_free_req(c, req);
+ p9_tag_remove(c, req);
return ERR_PTR(safe_errno(err));
}
@@ -832,7 +822,7 @@ reterr:
* @hdrlen: reader header size, This is the size of response protocol data
* @fmt: protocol format string (see protocol.c)
*
- * Returns request structure (which client must free using p9_free_req)
+ * Returns request structure (which client must free using p9_tag_remove)
*/
static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
struct iov_iter *uidata,
@@ -895,11 +885,11 @@ recalc_sigpending:
goto reterr;
err = p9_check_zc_errors(c, req, uidata, in_hdrlen);
- trace_9p_client_res(c, type, req->rc->tag, err);
+ trace_9p_client_res(c, type, req->rc.tag, err);
if (!err)
return req;
reterr:
- p9_free_req(c, req);
+ p9_tag_remove(c, req);
return ERR_PTR(safe_errno(err));
}
@@ -978,10 +968,10 @@ static int p9_client_version(struct p9_client *c)
if (IS_ERR(req))
return PTR_ERR(req);
- err = p9pdu_readf(req->rc, c->proto_version, "ds", &msize, &version);
+ err = p9pdu_readf(&req->rc, c->proto_version, "ds", &msize, &version);
if (err) {
p9_debug(P9_DEBUG_9P, "version error %d\n", err);
- trace_9p_protocol_dump(c, req->rc);
+ trace_9p_protocol_dump(c, &req->rc);
goto error;
}
@@ -1002,7 +992,7 @@ static int p9_client_version(struct p9_client *c)
error:
kfree(version);
- p9_free_req(c, req);
+ p9_tag_remove(c, req);
return err;
}
@@ -1020,20 +1010,18 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
clnt->trans_mod = NULL;
clnt->trans = NULL;
+ clnt->fcall_cache = NULL;
client_id = utsname()->nodename;
memcpy(clnt->name, client_id, strlen(client_id) + 1);
spin_lock_init(&clnt->lock);
idr_init(&clnt->fids);
-
- err = p9_tag_init(clnt);
- if (err < 0)
- goto free_client;
+ idr_init(&clnt->reqs);
err = parse_opts(options, clnt);
if (err < 0)
- goto destroy_tagpool;
+ goto free_client;
if (!clnt->trans_mod)
clnt->trans_mod = v9fs_get_default_trans();
@@ -1042,7 +1030,7 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
err = -EPROTONOSUPPORT;
p9_debug(P9_DEBUG_ERROR,
"No transport defined or default transport\n");
- goto destroy_tagpool;
+ goto free_client;
}
p9_debug(P9_DEBUG_MUX, "clnt %p trans %p msize %d protocol %d\n",
@@ -1059,14 +1047,21 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
if (err)
goto close_trans;
+ /* P9_HDRSZ + 4 is the smallest packet header we can have that is
+ * followed by data accessed from userspace by read
+ */
+ clnt->fcall_cache =
+ kmem_cache_create_usercopy("9p-fcall-cache", clnt->msize,
+ 0, 0, P9_HDRSZ + 4,
+ clnt->msize - (P9_HDRSZ + 4),
+ NULL);
+
return clnt;
close_trans:
clnt->trans_mod->close(clnt);
put_trans:
v9fs_put_trans(clnt->trans_mod);
-destroy_tagpool:
- p9_idpool_destroy(clnt->tagpool);
free_client:
kfree(clnt);
return ERR_PTR(err);
@@ -1092,6 +1087,7 @@ void p9_client_destroy(struct p9_client *clnt)
p9_tag_cleanup(clnt);
+ kmem_cache_destroy(clnt->fcall_cache);
kfree(clnt);
}
EXPORT_SYMBOL(p9_client_destroy);
@@ -1135,10 +1131,10 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "Q", &qid);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", &qid);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
- p9_free_req(clnt, req);
+ trace_9p_protocol_dump(clnt, &req->rc);
+ p9_tag_remove(clnt, req);
goto error;
}
@@ -1147,7 +1143,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
memmove(&fid->qid, &qid, sizeof(struct p9_qid));
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return fid;
error:
@@ -1192,13 +1188,13 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "R", &nwqids, &wqids);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "R", &nwqids, &wqids);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
- p9_free_req(clnt, req);
+ trace_9p_protocol_dump(clnt, &req->rc);
+ p9_tag_remove(clnt, req);
goto clunk_fid;
}
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
p9_debug(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids);
@@ -1259,9 +1255,9 @@ int p9_client_open(struct p9_fid *fid, int mode)
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto free_and_error;
}
@@ -1273,7 +1269,7 @@ int p9_client_open(struct p9_fid *fid, int mode)
fid->iounit = iounit;
free_and_error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -1303,9 +1299,9 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", qid, &iounit);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", qid, &iounit);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto free_and_error;
}
@@ -1318,7 +1314,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
ofid->iounit = iounit;
free_and_error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -1348,9 +1344,9 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto free_and_error;
}
@@ -1363,7 +1359,7 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
fid->iounit = iounit;
free_and_error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -1387,9 +1383,9 @@ int p9_client_symlink(struct p9_fid *dfid, const char *name,
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto free_and_error;
}
@@ -1397,7 +1393,7 @@ int p9_client_symlink(struct p9_fid *dfid, const char *name,
qid->type, (unsigned long long)qid->path, qid->version);
free_and_error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -1417,7 +1413,7 @@ int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, const char *newna
return PTR_ERR(req);
p9_debug(P9_DEBUG_9P, "<<< RLINK\n");
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return 0;
}
EXPORT_SYMBOL(p9_client_link);
@@ -1441,7 +1437,7 @@ int p9_client_fsync(struct p9_fid *fid, int datasync)
p9_debug(P9_DEBUG_9P, "<<< RFSYNC fid %d\n", fid->fid);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
@@ -1476,7 +1472,7 @@ again:
p9_debug(P9_DEBUG_9P, "<<< RCLUNK fid %d\n", fid->fid);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
/*
* Fid is not valid even after a failed clunk
@@ -1510,7 +1506,7 @@ int p9_client_remove(struct p9_fid *fid)
p9_debug(P9_DEBUG_9P, "<<< RREMOVE fid %d\n", fid->fid);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
if (err == -ERESTARTSYS)
p9_client_clunk(fid);
@@ -1537,7 +1533,7 @@ int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags)
}
p9_debug(P9_DEBUG_9P, "<<< RUNLINKAT fid %d %s\n", dfid->fid, name);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -1585,11 +1581,11 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
break;
}
- *err = p9pdu_readf(req->rc, clnt->proto_version,
+ *err = p9pdu_readf(&req->rc, clnt->proto_version,
"D", &count, &dataptr);
if (*err) {
- trace_9p_protocol_dump(clnt, req->rc);
- p9_free_req(clnt, req);
+ trace_9p_protocol_dump(clnt, &req->rc);
+ p9_tag_remove(clnt, req);
break;
}
if (rsize < count) {
@@ -1599,7 +1595,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
if (!count) {
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
break;
}
@@ -1609,7 +1605,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
offset += n;
if (n != count) {
*err = -EFAULT;
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
break;
}
} else {
@@ -1617,7 +1613,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
total += count;
offset += count;
}
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
}
return total;
}
@@ -1658,10 +1654,10 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
break;
}
- *err = p9pdu_readf(req->rc, clnt->proto_version, "d", &count);
+ *err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &count);
if (*err) {
- trace_9p_protocol_dump(clnt, req->rc);
- p9_free_req(clnt, req);
+ trace_9p_protocol_dump(clnt, &req->rc);
+ p9_tag_remove(clnt, req);
break;
}
if (rsize < count) {
@@ -1671,7 +1667,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
iov_iter_advance(from, count);
total += count;
offset += count;
@@ -1702,10 +1698,10 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "wS", &ignored, ret);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "wS", &ignored, ret);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
- p9_free_req(clnt, req);
+ trace_9p_protocol_dump(clnt, &req->rc);
+ p9_tag_remove(clnt, req);
goto error;
}
@@ -1722,7 +1718,7 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
from_kgid(&init_user_ns, ret->n_gid),
from_kuid(&init_user_ns, ret->n_muid));
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return ret;
error:
@@ -1755,10 +1751,10 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "A", ret);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "A", ret);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
- p9_free_req(clnt, req);
+ trace_9p_protocol_dump(clnt, &req->rc);
+ p9_tag_remove(clnt, req);
goto error;
}
@@ -1783,7 +1779,7 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
ret->st_ctime_nsec, ret->st_btime_sec, ret->st_btime_nsec,
ret->st_gen, ret->st_data_version);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return ret;
error:
@@ -1852,7 +1848,7 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
p9_debug(P9_DEBUG_9P, "<<< RWSTAT fid %d\n", fid->fid);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -1884,7 +1880,7 @@ int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr)
goto error;
}
p9_debug(P9_DEBUG_9P, "<<< RSETATTR fid %d\n", fid->fid);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -1907,12 +1903,12 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb)
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "ddqqqqqqd", &sb->type,
- &sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail,
- &sb->files, &sb->ffree, &sb->fsid, &sb->namelen);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "ddqqqqqqd", &sb->type,
+ &sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail,
+ &sb->files, &sb->ffree, &sb->fsid, &sb->namelen);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
- p9_free_req(clnt, req);
+ trace_9p_protocol_dump(clnt, &req->rc);
+ p9_tag_remove(clnt, req);
goto error;
}
@@ -1923,7 +1919,7 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb)
sb->blocks, sb->bfree, sb->bavail, sb->files, sb->ffree,
sb->fsid, (long int)sb->namelen);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -1951,7 +1947,7 @@ int p9_client_rename(struct p9_fid *fid,
p9_debug(P9_DEBUG_9P, "<<< RRENAME fid %d\n", fid->fid);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -1981,7 +1977,7 @@ int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name,
p9_debug(P9_DEBUG_9P, "<<< RRENAMEAT newdirfid %d new name %s\n",
newdirfid->fid, new_name);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -2015,13 +2011,13 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid,
err = PTR_ERR(req);
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "q", attr_size);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "q", attr_size);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
- p9_free_req(clnt, req);
+ trace_9p_protocol_dump(clnt, &req->rc);
+ p9_tag_remove(clnt, req);
goto clunk_fid;
}
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
p9_debug(P9_DEBUG_9P, "<<< RXATTRWALK fid %d size %llu\n",
attr_fid->fid, *attr_size);
return attr_fid;
@@ -2055,7 +2051,7 @@ int p9_client_xattrcreate(struct p9_fid *fid, const char *name,
goto error;
}
p9_debug(P9_DEBUG_9P, "<<< RXATTRCREATE fid %d\n", fid->fid);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -2103,9 +2099,9 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
goto error;
}
- err = p9pdu_readf(req->rc, clnt->proto_version, "D", &count, &dataptr);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "D", &count, &dataptr);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto free_and_error;
}
if (rsize < count) {
@@ -2118,11 +2114,11 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
if (non_zc)
memmove(data, dataptr, count);
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return count;
free_and_error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
error:
return err;
}
@@ -2144,16 +2140,16 @@ int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode,
if (IS_ERR(req))
return PTR_ERR(req);
- err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto error;
}
p9_debug(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type,
(unsigned long long)qid->path, qid->version);
error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return err;
}
@@ -2175,16 +2171,16 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
if (IS_ERR(req))
return PTR_ERR(req);
- err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto error;
}
p9_debug(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type,
(unsigned long long)qid->path, qid->version);
error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return err;
}
@@ -2210,14 +2206,14 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status)
if (IS_ERR(req))
return PTR_ERR(req);
- err = p9pdu_readf(req->rc, clnt->proto_version, "b", status);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "b", status);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto error;
}
p9_debug(P9_DEBUG_9P, "<<< RLOCK status %i\n", *status);
error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return err;
}
@@ -2241,18 +2237,18 @@ int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock)
if (IS_ERR(req))
return PTR_ERR(req);
- err = p9pdu_readf(req->rc, clnt->proto_version, "bqqds", &glock->type,
- &glock->start, &glock->length, &glock->proc_id,
- &glock->client_id);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "bqqds", &glock->type,
+ &glock->start, &glock->length, &glock->proc_id,
+ &glock->client_id);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto error;
}
p9_debug(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld "
"proc_id %d client_id %s\n", glock->type, glock->start,
glock->length, glock->proc_id, glock->client_id);
error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return err;
}
EXPORT_SYMBOL(p9_client_getlock_dotl);
@@ -2271,14 +2267,25 @@ int p9_client_readlink(struct p9_fid *fid, char **target)
if (IS_ERR(req))
return PTR_ERR(req);
- err = p9pdu_readf(req->rc, clnt->proto_version, "s", target);
+ err = p9pdu_readf(&req->rc, clnt->proto_version, "s", target);
if (err) {
- trace_9p_protocol_dump(clnt, req->rc);
+ trace_9p_protocol_dump(clnt, &req->rc);
goto error;
}
p9_debug(P9_DEBUG_9P, "<<< RREADLINK target %s\n", *target);
error:
- p9_free_req(clnt, req);
+ p9_tag_remove(clnt, req);
return err;
}
EXPORT_SYMBOL(p9_client_readlink);
+
+int __init p9_client_init(void)
+{
+ p9_req_cache = KMEM_CACHE(p9_req_t, SLAB_TYPESAFE_BY_RCU);
+ return p9_req_cache ? 0 : -ENOMEM;
+}
+
+void __exit p9_client_exit(void)
+{
+ kmem_cache_destroy(p9_req_cache);
+}
diff --git a/net/9p/mod.c b/net/9p/mod.c
index 253ba824a325..0da56d6af73b 100644
--- a/net/9p/mod.c
+++ b/net/9p/mod.c
@@ -171,11 +171,17 @@ void v9fs_put_trans(struct p9_trans_module *m)
*/
static int __init init_p9(void)
{
+ int ret;
+
+ ret = p9_client_init();
+ if (ret)
+ return ret;
+
p9_error_init();
pr_info("Installing 9P2000 support\n");
p9_trans_fd_init();
- return 0;
+ return ret;
}
/**
@@ -188,6 +194,7 @@ static void __exit exit_p9(void)
pr_info("Unloading 9P2000 support\n");
p9_trans_fd_exit();
+ p9_client_exit();
}
module_init(init_p9)
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 4a1e1dd30b52..462ba144cb39 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -46,10 +46,15 @@ p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
void p9stat_free(struct p9_wstat *stbuf)
{
kfree(stbuf->name);
+ stbuf->name = NULL;
kfree(stbuf->uid);
+ stbuf->uid = NULL;
kfree(stbuf->gid);
+ stbuf->gid = NULL;
kfree(stbuf->muid);
+ stbuf->muid = NULL;
kfree(stbuf->extension);
+ stbuf->extension = NULL;
}
EXPORT_SYMBOL(p9stat_free);
@@ -566,9 +571,10 @@ int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st)
if (ret) {
p9_debug(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret);
trace_9p_protocol_dump(clnt, &fake_pdu);
+ return ret;
}
- return ret;
+ return fake_pdu.offset;
}
EXPORT_SYMBOL(p9stat_read);
@@ -617,13 +623,19 @@ int p9dirent_read(struct p9_client *clnt, char *buf, int len,
if (ret) {
p9_debug(P9_DEBUG_9P, "<<< p9dirent_read failed: %d\n", ret);
trace_9p_protocol_dump(clnt, &fake_pdu);
- goto out;
+ return ret;
}
- strcpy(dirent->d_name, nameptr);
+ ret = strscpy(dirent->d_name, nameptr, sizeof(dirent->d_name));
+ if (ret < 0) {
+ p9_debug(P9_DEBUG_ERROR,
+ "On the wire dirent name too long: %s\n",
+ nameptr);
+ kfree(nameptr);
+ return ret;
+ }
kfree(nameptr);
-out:
return fake_pdu.offset;
}
EXPORT_SYMBOL(p9dirent_read);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index e2ef3c782c53..f868cf6fba79 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -131,7 +131,8 @@ struct p9_conn {
int err;
struct list_head req_list;
struct list_head unsent_req_list;
- struct p9_req_t *req;
+ struct p9_req_t *rreq;
+ struct p9_req_t *wreq;
char tmp_buf[7];
struct p9_fcall rc;
int wpos;
@@ -291,7 +292,6 @@ static void p9_read_work(struct work_struct *work)
__poll_t n;
int err;
struct p9_conn *m;
- int status = REQ_STATUS_ERROR;
m = container_of(work, struct p9_conn, rq);
@@ -322,7 +322,7 @@ static void p9_read_work(struct work_struct *work)
m->rc.offset += err;
/* header read in */
- if ((!m->req) && (m->rc.offset == m->rc.capacity)) {
+ if ((!m->rreq) && (m->rc.offset == m->rc.capacity)) {
p9_debug(P9_DEBUG_TRANS, "got new header\n");
/* Header size */
@@ -346,23 +346,23 @@ static void p9_read_work(struct work_struct *work)
"mux %p pkt: size: %d bytes tag: %d\n",
m, m->rc.size, m->rc.tag);
- m->req = p9_tag_lookup(m->client, m->rc.tag);
- if (!m->req || (m->req->status != REQ_STATUS_SENT)) {
+ m->rreq = p9_tag_lookup(m->client, m->rc.tag);
+ if (!m->rreq || (m->rreq->status != REQ_STATUS_SENT)) {
p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n",
m->rc.tag);
err = -EIO;
goto error;
}
- if (m->req->rc == NULL) {
+ if (!m->rreq->rc.sdata) {
p9_debug(P9_DEBUG_ERROR,
"No recv fcall for tag %d (req %p), disconnecting!\n",
- m->rc.tag, m->req);
- m->req = NULL;
+ m->rc.tag, m->rreq);
+ m->rreq = NULL;
err = -EIO;
goto error;
}
- m->rc.sdata = (char *)m->req->rc + sizeof(struct p9_fcall);
+ m->rc.sdata = m->rreq->rc.sdata;
memcpy(m->rc.sdata, m->tmp_buf, m->rc.capacity);
m->rc.capacity = m->rc.size;
}
@@ -370,20 +370,27 @@ static void p9_read_work(struct work_struct *work)
/* packet is read in
* not an else because some packets (like clunk) have no payload
*/
- if ((m->req) && (m->rc.offset == m->rc.capacity)) {
+ if ((m->rreq) && (m->rc.offset == m->rc.capacity)) {
p9_debug(P9_DEBUG_TRANS, "got new packet\n");
- m->req->rc->size = m->rc.offset;
+ m->rreq->rc.size = m->rc.offset;
spin_lock(&m->client->lock);
- if (m->req->status != REQ_STATUS_ERROR)
- status = REQ_STATUS_RCVD;
- list_del(&m->req->req_list);
- /* update req->status while holding client->lock */
- p9_client_cb(m->client, m->req, status);
+ if (m->rreq->status == REQ_STATUS_SENT) {
+ list_del(&m->rreq->req_list);
+ p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD);
+ } else {
+ spin_unlock(&m->client->lock);
+ p9_debug(P9_DEBUG_ERROR,
+ "Request tag %d errored out while we were reading the reply\n",
+ m->rc.tag);
+ err = -EIO;
+ goto error;
+ }
spin_unlock(&m->client->lock);
m->rc.sdata = NULL;
m->rc.offset = 0;
m->rc.capacity = 0;
- m->req = NULL;
+ p9_req_put(m->rreq);
+ m->rreq = NULL;
}
end_clear:
@@ -469,9 +476,11 @@ static void p9_write_work(struct work_struct *work)
p9_debug(P9_DEBUG_TRANS, "move req %p\n", req);
list_move_tail(&req->req_list, &m->req_list);
- m->wbuf = req->tc->sdata;
- m->wsize = req->tc->size;
+ m->wbuf = req->tc.sdata;
+ m->wsize = req->tc.size;
m->wpos = 0;
+ p9_req_get(req);
+ m->wreq = req;
spin_unlock(&m->client->lock);
}
@@ -492,8 +501,11 @@ static void p9_write_work(struct work_struct *work)
}
m->wpos += err;
- if (m->wpos == m->wsize)
+ if (m->wpos == m->wsize) {
m->wpos = m->wsize = 0;
+ p9_req_put(m->wreq);
+ m->wreq = NULL;
+ }
end_clear:
clear_bit(Wworksched, &m->wsched);
@@ -663,7 +675,7 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
struct p9_conn *m = &ts->conn;
p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n",
- m, current, req->tc, req->tc->id);
+ m, current, &req->tc, req->tc.id);
if (m->err < 0)
return m->err;
@@ -694,6 +706,7 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
if (req->status == REQ_STATUS_UNSENT) {
list_del(&req->req_list);
req->status = REQ_STATUS_FLSHD;
+ p9_req_put(req);
ret = 0;
}
spin_unlock(&client->lock);
@@ -711,6 +724,7 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
spin_lock(&client->lock);
list_del(&req->req_list);
spin_unlock(&client->lock);
+ p9_req_put(req);
return 0;
}
@@ -862,7 +876,15 @@ static void p9_conn_destroy(struct p9_conn *m)
p9_mux_poll_stop(m);
cancel_work_sync(&m->rq);
+ if (m->rreq) {
+ p9_req_put(m->rreq);
+ m->rreq = NULL;
+ }
cancel_work_sync(&m->wq);
+ if (m->wreq) {
+ p9_req_put(m->wreq);
+ m->wreq = NULL;
+ }
p9_conn_cancel(m, -ECONNRESET);
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index b513cffeeb3c..119103bfa82e 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -122,7 +122,7 @@ struct p9_rdma_context {
dma_addr_t busa;
union {
struct p9_req_t *req;
- struct p9_fcall *rc;
+ struct p9_fcall rc;
};
};
@@ -274,8 +274,7 @@ p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
case RDMA_CM_EVENT_DISCONNECTED:
if (rdma)
rdma->state = P9_RDMA_CLOSED;
- if (c)
- c->status = Disconnected;
+ c->status = Disconnected;
break;
case RDMA_CM_EVENT_TIMEWAIT_EXIT:
@@ -320,8 +319,8 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc)
if (wc->status != IB_WC_SUCCESS)
goto err_out;
- c->rc->size = wc->byte_len;
- err = p9_parse_header(c->rc, NULL, NULL, &tag, 1);
+ c->rc.size = wc->byte_len;
+ err = p9_parse_header(&c->rc, NULL, NULL, &tag, 1);
if (err)
goto err_out;
@@ -331,12 +330,13 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc)
/* Check that we have not yet received a reply for this request.
*/
- if (unlikely(req->rc)) {
+ if (unlikely(req->rc.sdata)) {
pr_err("Duplicate reply for request %d", tag);
goto err_out;
}
- req->rc = c->rc;
+ req->rc.size = c->rc.size;
+ req->rc.sdata = c->rc.sdata;
p9_client_cb(client, req, REQ_STATUS_RCVD);
out:
@@ -361,9 +361,10 @@ send_done(struct ib_cq *cq, struct ib_wc *wc)
container_of(wc->wr_cqe, struct p9_rdma_context, cqe);
ib_dma_unmap_single(rdma->cm_id->device,
- c->busa, c->req->tc->size,
+ c->busa, c->req->tc.size,
DMA_TO_DEVICE);
up(&rdma->sq_sem);
+ p9_req_put(c->req);
kfree(c);
}
@@ -401,7 +402,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c)
struct ib_sge sge;
c->busa = ib_dma_map_single(rdma->cm_id->device,
- c->rc->sdata, client->msize,
+ c->rc.sdata, client->msize,
DMA_FROM_DEVICE);
if (ib_dma_mapping_error(rdma->cm_id->device, c->busa))
goto error;
@@ -443,9 +444,9 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
**/
if (unlikely(atomic_read(&rdma->excess_rc) > 0)) {
if ((atomic_sub_return(1, &rdma->excess_rc) >= 0)) {
- /* Got one ! */
- kfree(req->rc);
- req->rc = NULL;
+ /* Got one! */
+ p9_fcall_fini(&req->rc);
+ req->rc.sdata = NULL;
goto dont_need_post_recv;
} else {
/* We raced and lost. */
@@ -459,7 +460,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
err = -ENOMEM;
goto recv_error;
}
- rpl_context->rc = req->rc;
+ rpl_context->rc.sdata = req->rc.sdata;
/*
* Post a receive buffer for this request. We need to ensure
@@ -475,11 +476,11 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
err = post_recv(client, rpl_context);
if (err) {
- p9_debug(P9_DEBUG_FCALL, "POST RECV failed\n");
+ p9_debug(P9_DEBUG_ERROR, "POST RECV failed: %d\n", err);
goto recv_error;
}
/* remove posted receive buffer from request structure */
- req->rc = NULL;
+ req->rc.sdata = NULL;
dont_need_post_recv:
/* Post the request */
@@ -491,7 +492,7 @@ dont_need_post_recv:
c->req = req;
c->busa = ib_dma_map_single(rdma->cm_id->device,
- c->req->tc->sdata, c->req->tc->size,
+ c->req->tc.sdata, c->req->tc.size,
DMA_TO_DEVICE);
if (ib_dma_mapping_error(rdma->cm_id->device, c->busa)) {
err = -EIO;
@@ -501,7 +502,7 @@ dont_need_post_recv:
c->cqe.done = send_done;
sge.addr = c->busa;
- sge.length = c->req->tc->size;
+ sge.length = c->req->tc.size;
sge.lkey = rdma->pd->local_dma_lkey;
wr.next = NULL;
@@ -544,7 +545,7 @@ dont_need_post_recv:
recv_error:
kfree(rpl_context);
spin_lock_irqsave(&rdma->req_lock, flags);
- if (rdma->state < P9_RDMA_CLOSING) {
+ if (err != -EINTR && rdma->state < P9_RDMA_CLOSING) {
rdma->state = P9_RDMA_CLOSING;
spin_unlock_irqrestore(&rdma->req_lock, flags);
rdma_disconnect(rdma->cm_id);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 7728b0acde09..eb596c2ed546 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -155,7 +155,7 @@ static void req_done(struct virtqueue *vq)
}
if (len) {
- req->rc->size = len;
+ req->rc.size = len;
p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
}
}
@@ -207,6 +207,13 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
return 1;
}
+/* Reply won't come, so drop req ref */
+static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req)
+{
+ p9_req_put(req);
+ return 0;
+}
+
/**
* pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
* this takes a list of pages.
@@ -273,12 +280,12 @@ req_retry:
out_sgs = in_sgs = 0;
/* Handle out VirtIO ring buffers */
out = pack_sg_list(chan->sg, 0,
- VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+ VIRTQUEUE_NUM, req->tc.sdata, req->tc.size);
if (out)
sgs[out_sgs++] = chan->sg;
in = pack_sg_list(chan->sg, out,
- VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity);
+ VIRTQUEUE_NUM, req->rc.sdata, req->rc.capacity);
if (in)
sgs[out_sgs + in_sgs++] = chan->sg + out;
@@ -404,6 +411,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
struct scatterlist *sgs[4];
size_t offs;
int need_drop = 0;
+ int kicked = 0;
p9_debug(P9_DEBUG_TRANS, "virtio request\n");
@@ -411,29 +419,33 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
__le32 sz;
int n = p9_get_mapped_pages(chan, &out_pages, uodata,
outlen, &offs, &need_drop);
- if (n < 0)
- return n;
+ if (n < 0) {
+ err = n;
+ goto err_out;
+ }
out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
if (n != outlen) {
__le32 v = cpu_to_le32(n);
- memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+ memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4);
outlen = n;
}
/* The size field of the message must include the length of the
* header and the length of the data. We didn't actually know
* the length of the data until this point so add it in now.
*/
- sz = cpu_to_le32(req->tc->size + outlen);
- memcpy(&req->tc->sdata[0], &sz, sizeof(sz));
+ sz = cpu_to_le32(req->tc.size + outlen);
+ memcpy(&req->tc.sdata[0], &sz, sizeof(sz));
} else if (uidata) {
int n = p9_get_mapped_pages(chan, &in_pages, uidata,
inlen, &offs, &need_drop);
- if (n < 0)
- return n;
+ if (n < 0) {
+ err = n;
+ goto err_out;
+ }
in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
if (n != inlen) {
__le32 v = cpu_to_le32(n);
- memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+ memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4);
inlen = n;
}
}
@@ -445,7 +457,7 @@ req_retry_pinned:
/* out data */
out = pack_sg_list(chan->sg, 0,
- VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+ VIRTQUEUE_NUM, req->tc.sdata, req->tc.size);
if (out)
sgs[out_sgs++] = chan->sg;
@@ -464,7 +476,7 @@ req_retry_pinned:
* alloced memory and payload onto the user buffer.
*/
in = pack_sg_list(chan->sg, out,
- VIRTQUEUE_NUM, req->rc->sdata, in_hdr_len);
+ VIRTQUEUE_NUM, req->rc.sdata, in_hdr_len);
if (in)
sgs[out_sgs + in_sgs++] = chan->sg + out;
@@ -498,6 +510,7 @@ req_retry_pinned:
}
virtqueue_kick(chan->vq);
spin_unlock_irqrestore(&chan->lock, flags);
+ kicked = 1;
p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
err = wait_event_killable(req->wq, req->status >= REQ_STATUS_RCVD);
/*
@@ -518,6 +531,10 @@ err_out:
}
kvfree(in_pages);
kvfree(out_pages);
+ if (!kicked) {
+ /* reply won't come */
+ p9_req_put(req);
+ }
return err;
}
@@ -750,6 +767,7 @@ static struct p9_trans_module p9_virtio_trans = {
.request = p9_virtio_request,
.zc_request = p9_virtio_zc_request,
.cancel = p9_virtio_cancel,
+ .cancelled = p9_virtio_cancelled,
/*
* We leave one entry for input and one entry for response
* headers. We also skip one more entry to accomodate, address
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index c2d54ac76bfd..e2fbf3677b9b 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -141,7 +141,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
struct xen_9pfs_front_priv *priv = NULL;
RING_IDX cons, prod, masked_cons, masked_prod;
unsigned long flags;
- u32 size = p9_req->tc->size;
+ u32 size = p9_req->tc.size;
struct xen_9pfs_dataring *ring;
int num;
@@ -154,7 +154,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
if (!priv || priv->client != client)
return -EINVAL;
- num = p9_req->tc->tag % priv->num_rings;
+ num = p9_req->tc.tag % priv->num_rings;
ring = &priv->rings[num];
again:
@@ -176,7 +176,7 @@ again:
masked_prod = xen_9pfs_mask(prod, XEN_9PFS_RING_SIZE);
masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE);
- xen_9pfs_write_packet(ring->data.out, p9_req->tc->sdata, size,
+ xen_9pfs_write_packet(ring->data.out, p9_req->tc.sdata, size,
&masked_prod, masked_cons, XEN_9PFS_RING_SIZE);
p9_req->status = REQ_STATUS_SENT;
@@ -185,6 +185,7 @@ again:
ring->intf->out_prod = prod;
spin_unlock_irqrestore(&ring->lock, flags);
notify_remote_via_irq(ring->irq);
+ p9_req_put(p9_req);
return 0;
}
@@ -229,12 +230,12 @@ static void p9_xen_response(struct work_struct *work)
continue;
}
- memcpy(req->rc, &h, sizeof(h));
- req->rc->offset = 0;
+ memcpy(&req->rc, &h, sizeof(h));
+ req->rc.offset = 0;
masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE);
/* Then, read the whole packet (including the header) */
- xen_9pfs_read_packet(req->rc->sdata, ring->data.in, h.size,
+ xen_9pfs_read_packet(req->rc.sdata, ring->data.in, h.size,
masked_prod, &masked_cons,
XEN_9PFS_RING_SIZE);
@@ -391,8 +392,8 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev,
unsigned int max_rings, max_ring_order, len = 0;
versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len);
- if (!len)
- return -EINVAL;
+ if (IS_ERR(versions))
+ return PTR_ERR(versions);
if (strcmp(versions, "1")) {
kfree(versions);
return -EINVAL;
diff --git a/net/9p/util.c b/net/9p/util.c
deleted file mode 100644
index 55ad98277e85..000000000000
--- a/net/9p/util.c
+++ /dev/null
@@ -1,140 +0,0 @@
-/*
- * net/9p/util.c
- *
- * This file contains some helper functions
- *
- * Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
- * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
- * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that 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.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to:
- * Free Software Foundation
- * 51 Franklin Street, Fifth Floor
- * Boston, MA 02111-1301 USA
- *
- */
-
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/sched.h>
-#include <linux/parser.h>
-#include <linux/idr.h>
-#include <linux/slab.h>
-#include <net/9p/9p.h>
-
-/**
- * struct p9_idpool - per-connection accounting for tag idpool
- * @lock: protects the pool
- * @pool: idr to allocate tag id from
- *
- */
-
-struct p9_idpool {
- spinlock_t lock;
- struct idr pool;
-};
-
-/**
- * p9_idpool_create - create a new per-connection id pool
- *
- */
-
-struct p9_idpool *p9_idpool_create(void)
-{
- struct p9_idpool *p;
-
- p = kmalloc(sizeof(struct p9_idpool), GFP_KERNEL);
- if (!p)
- return ERR_PTR(-ENOMEM);
-
- spin_lock_init(&p->lock);
- idr_init(&p->pool);
-
- return p;
-}
-EXPORT_SYMBOL(p9_idpool_create);
-
-/**
- * p9_idpool_destroy - create a new per-connection id pool
- * @p: idpool to destroy
- */
-
-void p9_idpool_destroy(struct p9_idpool *p)
-{
- idr_destroy(&p->pool);
- kfree(p);
-}
-EXPORT_SYMBOL(p9_idpool_destroy);
-
-/**
- * p9_idpool_get - allocate numeric id from pool
- * @p: pool to allocate from
- *
- * Bugs: This seems to be an awful generic function, should it be in idr.c with
- * the lock included in struct idr?
- */
-
-int p9_idpool_get(struct p9_idpool *p)
-{
- int i;
- unsigned long flags;
-
- idr_preload(GFP_NOFS);
- spin_lock_irqsave(&p->lock, flags);
-
- /* no need to store exactly p, we just need something non-null */
- i = idr_alloc(&p->pool, p, 0, 0, GFP_NOWAIT);
-
- spin_unlock_irqrestore(&p->lock, flags);
- idr_preload_end();
- if (i < 0)
- return -1;
-
- p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", i, p);
- return i;
-}
-EXPORT_SYMBOL(p9_idpool_get);
-
-/**
- * p9_idpool_put - release numeric id from pool
- * @id: numeric id which is being released
- * @p: pool to release id into
- *
- * Bugs: This seems to be an awful generic function, should it be in idr.c with
- * the lock included in struct idr?
- */
-
-void p9_idpool_put(int id, struct p9_idpool *p)
-{
- unsigned long flags;
-
- p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", id, p);
-
- spin_lock_irqsave(&p->lock, flags);
- idr_remove(&p->pool, id);
- spin_unlock_irqrestore(&p->lock, flags);
-}
-EXPORT_SYMBOL(p9_idpool_put);
-
-/**
- * p9_idpool_check - check if the specified id is available
- * @id: id to check
- * @p: pool to check
- */
-
-int p9_idpool_check(int id, struct p9_idpool *p)
-{
- return idr_find(&p->pool, id) != NULL;
-}
-EXPORT_SYMBOL(p9_idpool_check);
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 41cdafbf2ebe..6bac0d6b7b94 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1428,8 +1428,7 @@ static void br_multicast_query_received(struct net_bridge *br,
* is 0.0.0.0 should not be added to router port list.
*/
if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) ||
- (saddr->proto == htons(ETH_P_IPV6) &&
- !ipv6_addr_any(&saddr->u.ip6)))
+ saddr->proto == htons(ETH_P_IPV6))
br_multicast_mark_router(br, port);
}
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 0a187196aeed..88e35830198c 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -156,7 +156,6 @@ static bool con_flag_test_and_set(struct ceph_connection *con,
/* Slab caches for frequently-allocated structures */
static struct kmem_cache *ceph_msg_cache;
-static struct kmem_cache *ceph_msg_data_cache;
/* static tag bytes (protocol control messages) */
static char tag_msg = CEPH_MSGR_TAG_MSG;
@@ -235,23 +234,11 @@ static int ceph_msgr_slab_init(void)
if (!ceph_msg_cache)
return -ENOMEM;
- BUG_ON(ceph_msg_data_cache);
- ceph_msg_data_cache = KMEM_CACHE(ceph_msg_data, 0);
- if (ceph_msg_data_cache)
- return 0;
-
- kmem_cache_destroy(ceph_msg_cache);
- ceph_msg_cache = NULL;
-
- return -ENOMEM;
+ return 0;
}
static void ceph_msgr_slab_exit(void)
{
- BUG_ON(!ceph_msg_data_cache);
- kmem_cache_destroy(ceph_msg_data_cache);
- ceph_msg_data_cache = NULL;
-
BUG_ON(!ceph_msg_cache);
kmem_cache_destroy(ceph_msg_cache);
ceph_msg_cache = NULL;
@@ -1141,16 +1128,13 @@ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor)
static void ceph_msg_data_cursor_init(struct ceph_msg *msg, size_t length)
{
struct ceph_msg_data_cursor *cursor = &msg->cursor;
- struct ceph_msg_data *data;
BUG_ON(!length);
BUG_ON(length > msg->data_length);
- BUG_ON(list_empty(&msg->data));
+ BUG_ON(!msg->num_data_items);
- cursor->data_head = &msg->data;
cursor->total_resid = length;
- data = list_first_entry(&msg->data, struct ceph_msg_data, links);
- cursor->data = data;
+ cursor->data = msg->data;
__ceph_msg_data_cursor_init(cursor);
}
@@ -1231,8 +1215,7 @@ static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
if (!cursor->resid && cursor->total_resid) {
WARN_ON(!cursor->last_piece);
- BUG_ON(list_is_last(&cursor->data->links, cursor->data_head));
- cursor->data = list_next_entry(cursor->data, links);
+ cursor->data++;
__ceph_msg_data_cursor_init(cursor);
new_piece = true;
}
@@ -1248,9 +1231,6 @@ static size_t sizeof_footer(struct ceph_connection *con)
static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
{
- BUG_ON(!msg);
- BUG_ON(!data_len);
-
/* Initialize data cursor */
ceph_msg_data_cursor_init(msg, (size_t)data_len);
@@ -1590,7 +1570,7 @@ static int write_partial_message_data(struct ceph_connection *con)
dout("%s %p msg %p\n", __func__, con, msg);
- if (list_empty(&msg->data))
+ if (!msg->num_data_items)
return -EINVAL;
/*
@@ -2347,8 +2327,7 @@ static int read_partial_msg_data(struct ceph_connection *con)
u32 crc = 0;
int ret;
- BUG_ON(!msg);
- if (list_empty(&msg->data))
+ if (!msg->num_data_items)
return -EIO;
if (do_datacrc)
@@ -3256,32 +3235,16 @@ bool ceph_con_keepalive_expired(struct ceph_connection *con,
return false;
}
-static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type)
+static struct ceph_msg_data *ceph_msg_data_add(struct ceph_msg *msg)
{
- struct ceph_msg_data *data;
-
- if (WARN_ON(!ceph_msg_data_type_valid(type)))
- return NULL;
-
- data = kmem_cache_zalloc(ceph_msg_data_cache, GFP_NOFS);
- if (!data)
- return NULL;
-
- data->type = type;
- INIT_LIST_HEAD(&data->links);
-
- return data;
+ BUG_ON(msg->num_data_items >= msg->max_data_items);
+ return &msg->data[msg->num_data_items++];
}
static void ceph_msg_data_destroy(struct ceph_msg_data *data)
{
- if (!data)
- return;
-
- WARN_ON(!list_empty(&data->links));
if (data->type == CEPH_MSG_DATA_PAGELIST)
ceph_pagelist_release(data->pagelist);
- kmem_cache_free(ceph_msg_data_cache, data);
}
void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
@@ -3292,13 +3255,12 @@ void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
BUG_ON(!pages);
BUG_ON(!length);
- data = ceph_msg_data_create(CEPH_MSG_DATA_PAGES);
- BUG_ON(!data);
+ data = ceph_msg_data_add(msg);
+ data->type = CEPH_MSG_DATA_PAGES;
data->pages = pages;
data->length = length;
data->alignment = alignment & ~PAGE_MASK;
- list_add_tail(&data->links, &msg->data);
msg->data_length += length;
}
EXPORT_SYMBOL(ceph_msg_data_add_pages);
@@ -3311,11 +3273,11 @@ void ceph_msg_data_add_pagelist(struct ceph_msg *msg,
BUG_ON(!pagelist);
BUG_ON(!pagelist->length);
- data = ceph_msg_data_create(CEPH_MSG_DATA_PAGELIST);
- BUG_ON(!data);
+ data = ceph_msg_data_add(msg);
+ data->type = CEPH_MSG_DATA_PAGELIST;
+ refcount_inc(&pagelist->refcnt);
data->pagelist = pagelist;
- list_add_tail(&data->links, &msg->data);
msg->data_length += pagelist->length;
}
EXPORT_SYMBOL(ceph_msg_data_add_pagelist);
@@ -3326,12 +3288,11 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos,
{
struct ceph_msg_data *data;
- data = ceph_msg_data_create(CEPH_MSG_DATA_BIO);
- BUG_ON(!data);
+ data = ceph_msg_data_add(msg);
+ data->type = CEPH_MSG_DATA_BIO;
data->bio_pos = *bio_pos;
data->bio_length = length;
- list_add_tail(&data->links, &msg->data);
msg->data_length += length;
}
EXPORT_SYMBOL(ceph_msg_data_add_bio);
@@ -3342,11 +3303,10 @@ void ceph_msg_data_add_bvecs(struct ceph_msg *msg,
{
struct ceph_msg_data *data;
- data = ceph_msg_data_create(CEPH_MSG_DATA_BVECS);
- BUG_ON(!data);
+ data = ceph_msg_data_add(msg);
+ data->type = CEPH_MSG_DATA_BVECS;
data->bvec_pos = *bvec_pos;
- list_add_tail(&data->links, &msg->data);
msg->data_length += bvec_pos->iter.bi_size;
}
EXPORT_SYMBOL(ceph_msg_data_add_bvecs);
@@ -3355,8 +3315,8 @@ EXPORT_SYMBOL(ceph_msg_data_add_bvecs);
* construct a new message with given type, size
* the new msg has a ref count of 1.
*/
-struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
- bool can_fail)
+struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items,
+ gfp_t flags, bool can_fail)
{
struct ceph_msg *m;
@@ -3370,7 +3330,6 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
INIT_LIST_HEAD(&m->list_head);
kref_init(&m->kref);
- INIT_LIST_HEAD(&m->data);
/* front */
if (front_len) {
@@ -3385,6 +3344,15 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
}
m->front_alloc_len = m->front.iov_len = front_len;
+ if (max_data_items) {
+ m->data = kmalloc_array(max_data_items, sizeof(*m->data),
+ flags);
+ if (!m->data)
+ goto out2;
+
+ m->max_data_items = max_data_items;
+ }
+
dout("ceph_msg_new %p front %d\n", m, front_len);
return m;
@@ -3401,6 +3369,13 @@ out:
}
return NULL;
}
+EXPORT_SYMBOL(ceph_msg_new2);
+
+struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
+ bool can_fail)
+{
+ return ceph_msg_new2(type, front_len, 0, flags, can_fail);
+}
EXPORT_SYMBOL(ceph_msg_new);
/*
@@ -3496,13 +3471,14 @@ static void ceph_msg_free(struct ceph_msg *m)
{
dout("%s %p\n", __func__, m);
kvfree(m->front.iov_base);
+ kfree(m->data);
kmem_cache_free(ceph_msg_cache, m);
}
static void ceph_msg_release(struct kref *kref)
{
struct ceph_msg *m = container_of(kref, struct ceph_msg, kref);
- struct ceph_msg_data *data, *next;
+ int i;
dout("%s %p\n", __func__, m);
WARN_ON(!list_empty(&m->list_head));
@@ -3515,11 +3491,8 @@ static void ceph_msg_release(struct kref *kref)
m->middle = NULL;
}
- list_for_each_entry_safe(data, next, &m->data, links) {
- list_del_init(&data->links);
- ceph_msg_data_destroy(data);
- }
- m->data_length = 0;
+ for (i = 0; i < m->num_data_items; i++)
+ ceph_msg_data_destroy(&m->data[i]);
if (m->pool)
ceph_msgpool_put(m->pool, m);
diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c
index 72571535883f..e3ecb80cd182 100644
--- a/net/ceph/msgpool.c
+++ b/net/ceph/msgpool.c
@@ -14,7 +14,8 @@ static void *msgpool_alloc(gfp_t gfp_mask, void *arg)
struct ceph_msgpool *pool = arg;
struct ceph_msg *msg;
- msg = ceph_msg_new(pool->type, pool->front_len, gfp_mask, true);
+ msg = ceph_msg_new2(pool->type, pool->front_len, pool->max_data_items,
+ gfp_mask, true);
if (!msg) {
dout("msgpool_alloc %s failed\n", pool->name);
} else {
@@ -35,11 +36,13 @@ static void msgpool_free(void *element, void *arg)
}
int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
- int front_len, int size, bool blocking, const char *name)
+ int front_len, int max_data_items, int size,
+ const char *name)
{
dout("msgpool %s init\n", name);
pool->type = type;
pool->front_len = front_len;
+ pool->max_data_items = max_data_items;
pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool);
if (!pool->pool)
return -ENOMEM;
@@ -53,18 +56,21 @@ void ceph_msgpool_destroy(struct ceph_msgpool *pool)
mempool_destroy(pool->pool);
}
-struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool,
- int front_len)
+struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len,
+ int max_data_items)
{
struct ceph_msg *msg;
- if (front_len > pool->front_len) {
- dout("msgpool_get %s need front %d, pool size is %d\n",
- pool->name, front_len, pool->front_len);
- WARN_ON(1);
+ if (front_len > pool->front_len ||
+ max_data_items > pool->max_data_items) {
+ pr_warn_ratelimited("%s need %d/%d, pool %s has %d/%d\n",
+ __func__, front_len, max_data_items, pool->name,
+ pool->front_len, pool->max_data_items);
+ WARN_ON_ONCE(1);
/* try to alloc a fresh message */
- return ceph_msg_new(pool->type, front_len, GFP_NOFS, false);
+ return ceph_msg_new2(pool->type, front_len, max_data_items,
+ GFP_NOFS, false);
}
msg = mempool_alloc(pool->pool, GFP_NOFS);
@@ -80,6 +86,9 @@ void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg)
msg->front.iov_len = pool->front_len;
msg->hdr.front_len = cpu_to_le32(pool->front_len);
+ msg->data_length = 0;
+ msg->num_data_items = 0;
+
kref_init(&msg->kref); /* retake single ref */
mempool_free(msg, pool->pool);
}
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 60934bd8796c..d23a9f81f3d7 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -126,6 +126,9 @@ static void ceph_osd_data_init(struct ceph_osd_data *osd_data)
osd_data->type = CEPH_OSD_DATA_TYPE_NONE;
}
+/*
+ * Consumes @pages if @own_pages is true.
+ */
static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data,
struct page **pages, u64 length, u32 alignment,
bool pages_from_pool, bool own_pages)
@@ -138,6 +141,9 @@ static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data,
osd_data->own_pages = own_pages;
}
+/*
+ * Consumes a ref on @pagelist.
+ */
static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data,
struct ceph_pagelist *pagelist)
{
@@ -362,6 +368,8 @@ static void ceph_osd_data_release(struct ceph_osd_data *osd_data)
num_pages = calc_pages_for((u64)osd_data->alignment,
(u64)osd_data->length);
ceph_release_page_vector(osd_data->pages, num_pages);
+ } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) {
+ ceph_pagelist_release(osd_data->pagelist);
}
ceph_osd_data_init(osd_data);
}
@@ -402,6 +410,9 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
case CEPH_OSD_OP_LIST_WATCHERS:
ceph_osd_data_release(&op->list_watchers.response_data);
break;
+ case CEPH_OSD_OP_COPY_FROM:
+ ceph_osd_data_release(&op->copy_from.osd_data);
+ break;
default:
break;
}
@@ -606,12 +617,15 @@ static int ceph_oloc_encoding_size(const struct ceph_object_locator *oloc)
return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0);
}
-int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
+static int __ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp,
+ int num_request_data_items,
+ int num_reply_data_items)
{
struct ceph_osd_client *osdc = req->r_osdc;
struct ceph_msg *msg;
int msg_size;
+ WARN_ON(req->r_request || req->r_reply);
WARN_ON(ceph_oid_empty(&req->r_base_oid));
WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
@@ -633,9 +647,11 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
msg_size += 4 + 8; /* retry_attempt, features */
if (req->r_mempool)
- msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
+ msg = ceph_msgpool_get(&osdc->msgpool_op, msg_size,
+ num_request_data_items);
else
- msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp, true);
+ msg = ceph_msg_new2(CEPH_MSG_OSD_OP, msg_size,
+ num_request_data_items, gfp, true);
if (!msg)
return -ENOMEM;
@@ -648,9 +664,11 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
msg_size += req->r_num_ops * sizeof(struct ceph_osd_op);
if (req->r_mempool)
- msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
+ msg = ceph_msgpool_get(&osdc->msgpool_op_reply, msg_size,
+ num_reply_data_items);
else
- msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, msg_size, gfp, true);
+ msg = ceph_msg_new2(CEPH_MSG_OSD_OPREPLY, msg_size,
+ num_reply_data_items, gfp, true);
if (!msg)
return -ENOMEM;
@@ -658,7 +676,6 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
return 0;
}
-EXPORT_SYMBOL(ceph_osdc_alloc_messages);
static bool osd_req_opcode_valid(u16 opcode)
{
@@ -671,6 +688,65 @@ __CEPH_FORALL_OSD_OPS(GENERATE_CASE)
}
}
+static void get_num_data_items(struct ceph_osd_request *req,
+ int *num_request_data_items,
+ int *num_reply_data_items)
+{
+ struct ceph_osd_req_op *op;
+
+ *num_request_data_items = 0;
+ *num_reply_data_items = 0;
+
+ for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) {
+ switch (op->op) {
+ /* request */
+ case CEPH_OSD_OP_WRITE:
+ case CEPH_OSD_OP_WRITEFULL:
+ case CEPH_OSD_OP_SETXATTR:
+ case CEPH_OSD_OP_CMPXATTR:
+ case CEPH_OSD_OP_NOTIFY_ACK:
+ case CEPH_OSD_OP_COPY_FROM:
+ *num_request_data_items += 1;
+ break;
+
+ /* reply */
+ case CEPH_OSD_OP_STAT:
+ case CEPH_OSD_OP_READ:
+ case CEPH_OSD_OP_LIST_WATCHERS:
+ *num_reply_data_items += 1;
+ break;
+
+ /* both */
+ case CEPH_OSD_OP_NOTIFY:
+ *num_request_data_items += 1;
+ *num_reply_data_items += 1;
+ break;
+ case CEPH_OSD_OP_CALL:
+ *num_request_data_items += 2;
+ *num_reply_data_items += 1;
+ break;
+
+ default:
+ WARN_ON(!osd_req_opcode_valid(op->op));
+ break;
+ }
+ }
+}
+
+/*
+ * oid, oloc and OSD op opcode(s) must be filled in before this function
+ * is called.
+ */
+int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
+{
+ int num_request_data_items, num_reply_data_items;
+
+ get_num_data_items(req, &num_request_data_items, &num_reply_data_items);
+ return __ceph_osdc_alloc_messages(req, gfp, num_request_data_items,
+ num_reply_data_items);
+}
+EXPORT_SYMBOL(ceph_osdc_alloc_messages);
+
/*
* This is an osd op init function for opcodes that have no data or
* other information associated with them. It also serves as a
@@ -767,22 +843,19 @@ void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
EXPORT_SYMBOL(osd_req_op_extent_dup_last);
int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
- u16 opcode, const char *class, const char *method)
+ const char *class, const char *method)
{
- struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
- opcode, 0);
+ struct ceph_osd_req_op *op;
struct ceph_pagelist *pagelist;
size_t payload_len = 0;
size_t size;
- BUG_ON(opcode != CEPH_OSD_OP_CALL);
+ op = _osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0);
- pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS);
+ pagelist = ceph_pagelist_alloc(GFP_NOFS);
if (!pagelist)
return -ENOMEM;
- ceph_pagelist_init(pagelist);
-
op->cls.class_name = class;
size = strlen(class);
BUG_ON(size > (size_t) U8_MAX);
@@ -815,12 +888,10 @@ int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR);
- pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
+ pagelist = ceph_pagelist_alloc(GFP_NOFS);
if (!pagelist)
return -ENOMEM;
- ceph_pagelist_init(pagelist);
-
payload_len = strlen(name);
op->xattr.name_len = payload_len;
ceph_pagelist_append(pagelist, name, payload_len);
@@ -900,12 +971,6 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
static u32 osd_req_encode_op(struct ceph_osd_op *dst,
const struct ceph_osd_req_op *src)
{
- if (WARN_ON(!osd_req_opcode_valid(src->op))) {
- pr_err("unrecognized osd opcode %d\n", src->op);
-
- return 0;
- }
-
switch (src->op) {
case CEPH_OSD_OP_STAT:
break;
@@ -955,6 +1020,14 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst,
case CEPH_OSD_OP_CREATE:
case CEPH_OSD_OP_DELETE:
break;
+ case CEPH_OSD_OP_COPY_FROM:
+ dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid);
+ dst->copy_from.src_version =
+ cpu_to_le64(src->copy_from.src_version);
+ dst->copy_from.flags = src->copy_from.flags;
+ dst->copy_from.src_fadvise_flags =
+ cpu_to_le32(src->copy_from.src_fadvise_flags);
+ break;
default:
pr_err("unsupported osd opcode %s\n",
ceph_osd_op_name(src->op));
@@ -1038,7 +1111,15 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
if (flags & CEPH_OSD_FLAG_WRITE)
req->r_data_offset = off;
- r = ceph_osdc_alloc_messages(req, GFP_NOFS);
+ if (num_ops > 1)
+ /*
+ * This is a special case for ceph_writepages_start(), but it
+ * also covers ceph_uninline_data(). If more multi-op request
+ * use cases emerge, we will need a separate helper.
+ */
+ r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_ops, 0);
+ else
+ r = ceph_osdc_alloc_messages(req, GFP_NOFS);
if (r)
goto fail;
@@ -1845,48 +1926,55 @@ static bool should_plug_request(struct ceph_osd_request *req)
return true;
}
-static void setup_request_data(struct ceph_osd_request *req,
- struct ceph_msg *msg)
+/*
+ * Keep get_num_data_items() in sync with this function.
+ */
+static void setup_request_data(struct ceph_osd_request *req)
{
- u32 data_len = 0;
- int i;
+ struct ceph_msg *request_msg = req->r_request;
+ struct ceph_msg *reply_msg = req->r_reply;
+ struct ceph_osd_req_op *op;
- if (!list_empty(&msg->data))
+ if (req->r_request->num_data_items || req->r_reply->num_data_items)
return;
- WARN_ON(msg->data_length);
- for (i = 0; i < req->r_num_ops; i++) {
- struct ceph_osd_req_op *op = &req->r_ops[i];
-
+ WARN_ON(request_msg->data_length || reply_msg->data_length);
+ for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) {
switch (op->op) {
/* request */
case CEPH_OSD_OP_WRITE:
case CEPH_OSD_OP_WRITEFULL:
WARN_ON(op->indata_len != op->extent.length);
- ceph_osdc_msg_data_add(msg, &op->extent.osd_data);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->extent.osd_data);
break;
case CEPH_OSD_OP_SETXATTR:
case CEPH_OSD_OP_CMPXATTR:
WARN_ON(op->indata_len != op->xattr.name_len +
op->xattr.value_len);
- ceph_osdc_msg_data_add(msg, &op->xattr.osd_data);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->xattr.osd_data);
break;
case CEPH_OSD_OP_NOTIFY_ACK:
- ceph_osdc_msg_data_add(msg,
+ ceph_osdc_msg_data_add(request_msg,
&op->notify_ack.request_data);
break;
+ case CEPH_OSD_OP_COPY_FROM:
+ ceph_osdc_msg_data_add(request_msg,
+ &op->copy_from.osd_data);
+ break;
/* reply */
case CEPH_OSD_OP_STAT:
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->raw_data_in);
break;
case CEPH_OSD_OP_READ:
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->extent.osd_data);
break;
case CEPH_OSD_OP_LIST_WATCHERS:
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->list_watchers.response_data);
break;
@@ -1895,25 +1983,23 @@ static void setup_request_data(struct ceph_osd_request *req,
WARN_ON(op->indata_len != op->cls.class_len +
op->cls.method_len +
op->cls.indata_len);
- ceph_osdc_msg_data_add(msg, &op->cls.request_info);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->cls.request_info);
/* optional, can be NONE */
- ceph_osdc_msg_data_add(msg, &op->cls.request_data);
+ ceph_osdc_msg_data_add(request_msg,
+ &op->cls.request_data);
/* optional, can be NONE */
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->cls.response_data);
break;
case CEPH_OSD_OP_NOTIFY:
- ceph_osdc_msg_data_add(msg,
+ ceph_osdc_msg_data_add(request_msg,
&op->notify.request_data);
- ceph_osdc_msg_data_add(req->r_reply,
+ ceph_osdc_msg_data_add(reply_msg,
&op->notify.response_data);
break;
}
-
- data_len += op->indata_len;
}
-
- WARN_ON(data_len != msg->data_length);
}
static void encode_pgid(void **p, const struct ceph_pg *pgid)
@@ -1961,7 +2047,7 @@ static void encode_request_partial(struct ceph_osd_request *req,
req->r_data_offset || req->r_snapc);
}
- setup_request_data(req, msg);
+ setup_request_data(req);
encode_spgid(&p, &req->r_t.spgid); /* actual spg */
ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */
@@ -3001,11 +3087,21 @@ static void linger_submit(struct ceph_osd_linger_request *lreq)
struct ceph_osd_client *osdc = lreq->osdc;
struct ceph_osd *osd;
+ down_write(&osdc->lock);
+ linger_register(lreq);
+ if (lreq->is_watch) {
+ lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id;
+ lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id;
+ } else {
+ lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id;
+ }
+
calc_target(osdc, &lreq->t, NULL, false);
osd = lookup_create_osd(osdc, lreq->t.osd, true);
link_linger(osd, lreq);
send_linger(lreq);
+ up_write(&osdc->lock);
}
static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq)
@@ -4318,9 +4414,7 @@ static void handle_watch_notify(struct ceph_osd_client *osdc,
lreq->notify_id, notify_id);
} else if (!completion_done(&lreq->notify_finish_wait)) {
struct ceph_msg_data *data =
- list_first_entry_or_null(&msg->data,
- struct ceph_msg_data,
- links);
+ msg->num_data_items ? &msg->data[0] : NULL;
if (data) {
if (lreq->preply_pages) {
@@ -4476,6 +4570,23 @@ alloc_linger_request(struct ceph_osd_linger_request *lreq)
ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
+ return req;
+}
+
+static struct ceph_osd_request *
+alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode)
+{
+ struct ceph_osd_request *req;
+
+ req = alloc_linger_request(lreq);
+ if (!req)
+ return NULL;
+
+ /*
+ * Pass 0 for cookie because we don't know it yet, it will be
+ * filled in by linger_submit().
+ */
+ osd_req_op_watch_init(req, 0, 0, watch_opcode);
if (ceph_osdc_alloc_messages(req, GFP_NOIO)) {
ceph_osdc_put_request(req);
@@ -4514,27 +4625,19 @@ ceph_osdc_watch(struct ceph_osd_client *osdc,
lreq->t.flags = CEPH_OSD_FLAG_WRITE;
ktime_get_real_ts64(&lreq->mtime);
- lreq->reg_req = alloc_linger_request(lreq);
+ lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH);
if (!lreq->reg_req) {
ret = -ENOMEM;
goto err_put_lreq;
}
- lreq->ping_req = alloc_linger_request(lreq);
+ lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING);
if (!lreq->ping_req) {
ret = -ENOMEM;
goto err_put_lreq;
}
- down_write(&osdc->lock);
- linger_register(lreq); /* before osd_req_op_* */
- osd_req_op_watch_init(lreq->reg_req, 0, lreq->linger_id,
- CEPH_OSD_WATCH_OP_WATCH);
- osd_req_op_watch_init(lreq->ping_req, 0, lreq->linger_id,
- CEPH_OSD_WATCH_OP_PING);
linger_submit(lreq);
- up_write(&osdc->lock);
-
ret = linger_reg_commit_wait(lreq);
if (ret) {
linger_cancel(lreq);
@@ -4599,11 +4702,10 @@ static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which,
op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
- pl = kmalloc(sizeof(*pl), GFP_NOIO);
+ pl = ceph_pagelist_alloc(GFP_NOIO);
if (!pl)
return -ENOMEM;
- ceph_pagelist_init(pl);
ret = ceph_pagelist_encode_64(pl, notify_id);
ret |= ceph_pagelist_encode_64(pl, cookie);
if (payload) {
@@ -4641,12 +4743,12 @@ int ceph_osdc_notify_ack(struct ceph_osd_client *osdc,
ceph_oloc_copy(&req->r_base_oloc, oloc);
req->r_flags = CEPH_OSD_FLAG_READ;
- ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
+ payload_len);
if (ret)
goto out_put_req;
- ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
- payload_len);
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
if (ret)
goto out_put_req;
@@ -4670,11 +4772,10 @@ static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
op->notify.cookie = cookie;
- pl = kmalloc(sizeof(*pl), GFP_NOIO);
+ pl = ceph_pagelist_alloc(GFP_NOIO);
if (!pl)
return -ENOMEM;
- ceph_pagelist_init(pl);
ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */
ret |= ceph_pagelist_encode_32(pl, timeout);
ret |= ceph_pagelist_encode_32(pl, payload_len);
@@ -4733,29 +4834,30 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
goto out_put_lreq;
}
+ /*
+ * Pass 0 for cookie because we don't know it yet, it will be
+ * filled in by linger_submit().
+ */
+ ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout,
+ payload, payload_len);
+ if (ret)
+ goto out_put_lreq;
+
/* for notify_id */
pages = ceph_alloc_page_vector(1, GFP_NOIO);
if (IS_ERR(pages)) {
ret = PTR_ERR(pages);
goto out_put_lreq;
}
-
- down_write(&osdc->lock);
- linger_register(lreq); /* before osd_req_op_* */
- ret = osd_req_op_notify_init(lreq->reg_req, 0, lreq->linger_id, 1,
- timeout, payload, payload_len);
- if (ret) {
- linger_unregister(lreq);
- up_write(&osdc->lock);
- ceph_release_page_vector(pages, 1);
- goto out_put_lreq;
- }
ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify,
response_data),
pages, PAGE_SIZE, 0, false, true);
- linger_submit(lreq);
- up_write(&osdc->lock);
+ ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO);
+ if (ret)
+ goto out_put_lreq;
+
+ linger_submit(lreq);
ret = linger_reg_commit_wait(lreq);
if (!ret)
ret = linger_notify_finish_wait(lreq);
@@ -4881,10 +4983,6 @@ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
ceph_oloc_copy(&req->r_base_oloc, oloc);
req->r_flags = CEPH_OSD_FLAG_READ;
- ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
- if (ret)
- goto out_put_req;
-
pages = ceph_alloc_page_vector(1, GFP_NOIO);
if (IS_ERR(pages)) {
ret = PTR_ERR(pages);
@@ -4896,6 +4994,10 @@ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
response_data),
pages, PAGE_SIZE, 0, false, true);
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ if (ret)
+ goto out_put_req;
+
ceph_osdc_start_request(osdc, req, false);
ret = ceph_osdc_wait_request(osdc, req);
if (ret >= 0) {
@@ -4958,11 +5060,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
ceph_oloc_copy(&req->r_base_oloc, oloc);
req->r_flags = flags;
- ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
- if (ret)
- goto out_put_req;
-
- ret = osd_req_op_cls_init(req, 0, CEPH_OSD_OP_CALL, class, method);
+ ret = osd_req_op_cls_init(req, 0, class, method);
if (ret)
goto out_put_req;
@@ -4973,6 +5071,10 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
osd_req_op_cls_response_data_pages(req, 0, &resp_page,
*resp_len, 0, false, false);
+ ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+ if (ret)
+ goto out_put_req;
+
ceph_osdc_start_request(osdc, req, false);
ret = ceph_osdc_wait_request(osdc, req);
if (ret >= 0) {
@@ -5021,11 +5123,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
goto out_map;
err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
- PAGE_SIZE, 10, true, "osd_op");
+ PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op");
if (err < 0)
goto out_mempool;
err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
- PAGE_SIZE, 10, true, "osd_op_reply");
+ PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10,
+ "osd_op_reply");
if (err < 0)
goto out_msgpool;
@@ -5168,6 +5271,80 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
}
EXPORT_SYMBOL(ceph_osdc_writepages);
+static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
+ u64 src_snapid, u64 src_version,
+ struct ceph_object_id *src_oid,
+ struct ceph_object_locator *src_oloc,
+ u32 src_fadvise_flags,
+ u32 dst_fadvise_flags,
+ u8 copy_from_flags)
+{
+ struct ceph_osd_req_op *op;
+ struct page **pages;
+ void *p, *end;
+
+ pages = ceph_alloc_page_vector(1, GFP_KERNEL);
+ if (IS_ERR(pages))
+ return PTR_ERR(pages);
+
+ op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM, dst_fadvise_flags);
+ op->copy_from.snapid = src_snapid;
+ op->copy_from.src_version = src_version;
+ op->copy_from.flags = copy_from_flags;
+ op->copy_from.src_fadvise_flags = src_fadvise_flags;
+
+ p = page_address(pages[0]);
+ end = p + PAGE_SIZE;
+ ceph_encode_string(&p, end, src_oid->name, src_oid->name_len);
+ encode_oloc(&p, end, src_oloc);
+ op->indata_len = PAGE_SIZE - (end - p);
+
+ ceph_osd_data_pages_init(&op->copy_from.osd_data, pages,
+ op->indata_len, 0, false, true);
+ return 0;
+}
+
+int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
+ u64 src_snapid, u64 src_version,
+ struct ceph_object_id *src_oid,
+ struct ceph_object_locator *src_oloc,
+ u32 src_fadvise_flags,
+ struct ceph_object_id *dst_oid,
+ struct ceph_object_locator *dst_oloc,
+ u32 dst_fadvise_flags,
+ u8 copy_from_flags)
+{
+ struct ceph_osd_request *req;
+ int ret;
+
+ req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL);
+ if (!req)
+ return -ENOMEM;
+
+ req->r_flags = CEPH_OSD_FLAG_WRITE;
+
+ ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc);
+ ceph_oid_copy(&req->r_t.base_oid, dst_oid);
+
+ ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid,
+ src_oloc, src_fadvise_flags,
+ dst_fadvise_flags, copy_from_flags);
+ if (ret)
+ goto out;
+
+ ret = ceph_osdc_alloc_messages(req, GFP_KERNEL);
+ if (ret)
+ goto out;
+
+ ceph_osdc_start_request(osdc, req, false);
+ ret = ceph_osdc_wait_request(osdc, req);
+
+out:
+ ceph_osdc_put_request(req);
+ return ret;
+}
+EXPORT_SYMBOL(ceph_osdc_copy_from);
+
int __init ceph_osdc_setup(void)
{
size_t size = sizeof(struct ceph_osd_request) +
@@ -5295,7 +5472,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
u32 front_len = le32_to_cpu(hdr->front_len);
u32 data_len = le32_to_cpu(hdr->data_len);
- m = ceph_msg_new(type, front_len, GFP_NOIO, false);
+ m = ceph_msg_new2(type, front_len, 1, GFP_NOIO, false);
if (!m)
return NULL;
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
index 2ea0564771d2..65e34f78b05d 100644
--- a/net/ceph/pagelist.c
+++ b/net/ceph/pagelist.c
@@ -6,6 +6,26 @@
#include <linux/highmem.h>
#include <linux/ceph/pagelist.h>
+struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags)
+{
+ struct ceph_pagelist *pl;
+
+ pl = kmalloc(sizeof(*pl), gfp_flags);
+ if (!pl)
+ return NULL;
+
+ INIT_LIST_HEAD(&pl->head);
+ pl->mapped_tail = NULL;
+ pl->length = 0;
+ pl->room = 0;
+ INIT_LIST_HEAD(&pl->free_list);
+ pl->num_pages_free = 0;
+ refcount_set(&pl->refcnt, 1);
+
+ return pl;
+}
+EXPORT_SYMBOL(ceph_pagelist_alloc);
+
static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
{
if (pl->mapped_tail) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 022ad73d6253..77d43ae2a7bb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5457,7 +5457,7 @@ static void gro_flush_oldest(struct list_head *head)
/* Do not adjust napi->gro_hash[].count, caller is adding a new
* SKB to the chain.
*/
- list_del(&oldest->list);
+ skb_list_del_init(oldest);
napi_gro_complete(oldest);
}
diff --git a/net/core/filter.c b/net/core/filter.c
index 35c6933c2622..e521c5ebc7d1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5264,8 +5264,6 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_msg_pull_data_proto;
case BPF_FUNC_msg_push_data:
return &bpf_msg_push_data_proto;
- case BPF_FUNC_get_local_storage:
- return &bpf_get_local_storage_proto;
default:
return bpf_base_func_proto(func_id);
}
@@ -5296,8 +5294,6 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_sk_redirect_map_proto;
case BPF_FUNC_sk_redirect_hash:
return &bpf_sk_redirect_hash_proto;
- case BPF_FUNC_get_local_storage:
- return &bpf_get_local_storage_proto;
#ifdef CONFIG_INET
case BPF_FUNC_sk_lookup_tcp:
return &bpf_sk_lookup_tcp_proto;
@@ -5496,7 +5492,13 @@ static bool cg_skb_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range(struct __sk_buff, flow_keys):
return false;
+ case bpf_ctx_range(struct __sk_buff, data):
+ case bpf_ctx_range(struct __sk_buff, data_end):
+ if (!capable(CAP_SYS_ADMIN))
+ return false;
+ break;
}
+
if (type == BPF_WRITE) {
switch (off) {
case bpf_ctx_range(struct __sk_buff, mark):
@@ -5638,6 +5640,15 @@ static bool sock_filter_is_valid_access(int off, int size,
prog->expected_attach_type);
}
+static int bpf_noop_prologue(struct bpf_insn *insn_buf, bool direct_write,
+ const struct bpf_prog *prog)
+{
+ /* Neither direct read nor direct write requires any preliminary
+ * action.
+ */
+ return 0;
+}
+
static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write,
const struct bpf_prog *prog, int drop_verdict)
{
@@ -7204,6 +7215,7 @@ const struct bpf_verifier_ops xdp_verifier_ops = {
.get_func_proto = xdp_func_proto,
.is_valid_access = xdp_is_valid_access,
.convert_ctx_access = xdp_convert_ctx_access,
+ .gen_prologue = bpf_noop_prologue,
};
const struct bpf_prog_ops xdp_prog_ops = {
@@ -7302,6 +7314,7 @@ const struct bpf_verifier_ops sk_msg_verifier_ops = {
.get_func_proto = sk_msg_func_proto,
.is_valid_access = sk_msg_is_valid_access,
.convert_ctx_access = sk_msg_convert_ctx_access,
+ .gen_prologue = bpf_noop_prologue,
};
const struct bpf_prog_ops sk_msg_prog_ops = {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index b1a2c5e38530..37b4667128a3 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -279,7 +279,6 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
return ret;
}
-# ifdef CONFIG_HAVE_EBPF_JIT
static int
proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
@@ -290,7 +289,6 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
-# endif
#endif
static struct ctl_table net_core_table[] = {
@@ -397,6 +395,14 @@ static struct ctl_table net_core_table[] = {
.extra2 = &one,
},
# endif
+ {
+ .procname = "bpf_jit_limit",
+ .data = &bpf_jit_limit,
+ .maxlen = sizeof(int),
+ .mode = 0600,
+ .proc_handler = proc_dointvec_minmax_bpf_restricted,
+ .extra1 = &one,
+ },
#endif
{
.procname = "netdev_tstamp_prequeue",
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index f5c9ef2586de..411dd7a90046 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -19,7 +19,7 @@
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/vmalloc.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1834818ed07b..9e6bc4d6daa7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -262,7 +262,7 @@
#include <linux/net.h>
#include <linux/socket.h>
#include <linux/random.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/cache.h>
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ca3ed931f2a9..1976fddb9e00 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -81,7 +81,7 @@
#include <linux/uaccess.h>
#include <asm/ioctls.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/types.h>
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index d9ad986c7b2c..5cbb9be05295 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -42,6 +42,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
rcu_read_lock();
if (req->sdiag_family == AF_INET)
+ /* src and dst are swapped for historical reasons */
sk = __udp4_lib_lookup(net,
req->id.idiag_src[0], req->id.idiag_sport,
req->id.idiag_dst[0], req->id.idiag_dport,
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index cbe4831f46f4..4a042abf844c 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -413,7 +413,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) {
if (tb[TCA_GRED_LIMIT] != NULL)
sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
- return gred_change_table_def(sch, opt);
+ return gred_change_table_def(sch, tb[TCA_GRED_DPS]);
}
if (tb[TCA_GRED_PARMS] == NULL ||
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index e948db29ab53..9b277bd36d1a 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -46,7 +46,7 @@
#include <linux/netdevice.h>
#include <linux/inetdevice.h>
#include <linux/seq_file.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/slab.h>
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 860f2a1bbb67..1ece4bc3eb8d 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -76,6 +76,7 @@ struct rsi {
struct xdr_netobj in_handle, in_token;
struct xdr_netobj out_handle, out_token;
int major_status, minor_status;
+ struct rcu_head rcu_head;
};
static struct rsi *rsi_update(struct cache_detail *cd, struct rsi *new, struct rsi *old);
@@ -89,13 +90,21 @@ static void rsi_free(struct rsi *rsii)
kfree(rsii->out_token.data);
}
-static void rsi_put(struct kref *ref)
+static void rsi_free_rcu(struct rcu_head *head)
{
- struct rsi *rsii = container_of(ref, struct rsi, h.ref);
+ struct rsi *rsii = container_of(head, struct rsi, rcu_head);
+
rsi_free(rsii);
kfree(rsii);
}
+static void rsi_put(struct kref *ref)
+{
+ struct rsi *rsii = container_of(ref, struct rsi, h.ref);
+
+ call_rcu(&rsii->rcu_head, rsi_free_rcu);
+}
+
static inline int rsi_hash(struct rsi *item)
{
return hash_mem(item->in_handle.data, item->in_handle.len, RSI_HASHBITS)
@@ -282,7 +291,7 @@ static struct rsi *rsi_lookup(struct cache_detail *cd, struct rsi *item)
struct cache_head *ch;
int hash = rsi_hash(item);
- ch = sunrpc_cache_lookup(cd, &item->h, hash);
+ ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash);
if (ch)
return container_of(ch, struct rsi, h);
else
@@ -330,6 +339,7 @@ struct rsc {
struct svc_cred cred;
struct gss_svc_seq_data seqdata;
struct gss_ctx *mechctx;
+ struct rcu_head rcu_head;
};
static struct rsc *rsc_update(struct cache_detail *cd, struct rsc *new, struct rsc *old);
@@ -343,12 +353,22 @@ static void rsc_free(struct rsc *rsci)
free_svc_cred(&rsci->cred);
}
+static void rsc_free_rcu(struct rcu_head *head)
+{
+ struct rsc *rsci = container_of(head, struct rsc, rcu_head);
+
+ kfree(rsci->handle.data);
+ kfree(rsci);
+}
+
static void rsc_put(struct kref *ref)
{
struct rsc *rsci = container_of(ref, struct rsc, h.ref);
- rsc_free(rsci);
- kfree(rsci);
+ if (rsci->mechctx)
+ gss_delete_sec_context(&rsci->mechctx);
+ free_svc_cred(&rsci->cred);
+ call_rcu(&rsci->rcu_head, rsc_free_rcu);
}
static inline int
@@ -542,7 +562,7 @@ static struct rsc *rsc_lookup(struct cache_detail *cd, struct rsc *item)
struct cache_head *ch;
int hash = rsc_hash(item);
- ch = sunrpc_cache_lookup(cd, &item->h, hash);
+ ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash);
if (ch)
return container_of(ch, struct rsc, h);
else
@@ -1764,14 +1784,21 @@ out_err:
}
static void
-svcauth_gss_domain_release(struct auth_domain *dom)
+svcauth_gss_domain_release_rcu(struct rcu_head *head)
{
+ struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head);
struct gss_domain *gd = container_of(dom, struct gss_domain, h);
kfree(dom->name);
kfree(gd);
}
+static void
+svcauth_gss_domain_release(struct auth_domain *dom)
+{
+ call_rcu(&dom->rcu_head, svcauth_gss_domain_release_rcu);
+}
+
static struct auth_ops svcauthops_gss = {
.name = "rpcsec_gss",
.owner = THIS_MODULE,
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 109fbe591e7b..f96345b1180e 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -54,28 +54,33 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail)
h->last_refresh = now;
}
-struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
- struct cache_head *key, int hash)
+static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail,
+ struct cache_head *key,
+ int hash)
{
- struct cache_head *new = NULL, *freeme = NULL, *tmp = NULL;
- struct hlist_head *head;
-
- head = &detail->hash_table[hash];
-
- read_lock(&detail->hash_lock);
+ struct hlist_head *head = &detail->hash_table[hash];
+ struct cache_head *tmp;
- hlist_for_each_entry(tmp, head, cache_list) {
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(tmp, head, cache_list) {
if (detail->match(tmp, key)) {
if (cache_is_expired(detail, tmp))
- /* This entry is expired, we will discard it. */
- break;
- cache_get(tmp);
- read_unlock(&detail->hash_lock);
+ continue;
+ tmp = cache_get_rcu(tmp);
+ rcu_read_unlock();
return tmp;
}
}
- read_unlock(&detail->hash_lock);
- /* Didn't find anything, insert an empty entry */
+ rcu_read_unlock();
+ return NULL;
+}
+
+static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
+ struct cache_head *key,
+ int hash)
+{
+ struct cache_head *new, *tmp, *freeme = NULL;
+ struct hlist_head *head = &detail->hash_table[hash];
new = detail->alloc();
if (!new)
@@ -87,35 +92,46 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
cache_init(new, detail);
detail->init(new, key);
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
/* check if entry appeared while we slept */
- hlist_for_each_entry(tmp, head, cache_list) {
+ hlist_for_each_entry_rcu(tmp, head, cache_list) {
if (detail->match(tmp, key)) {
if (cache_is_expired(detail, tmp)) {
- hlist_del_init(&tmp->cache_list);
+ hlist_del_init_rcu(&tmp->cache_list);
detail->entries --;
freeme = tmp;
break;
}
cache_get(tmp);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_put(new, detail);
return tmp;
}
}
- hlist_add_head(&new->cache_list, head);
+ hlist_add_head_rcu(&new->cache_list, head);
detail->entries++;
cache_get(new);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
if (freeme)
cache_put(freeme, detail);
return new;
}
-EXPORT_SYMBOL_GPL(sunrpc_cache_lookup);
+struct cache_head *sunrpc_cache_lookup_rcu(struct cache_detail *detail,
+ struct cache_head *key, int hash)
+{
+ struct cache_head *ret;
+
+ ret = sunrpc_cache_find_rcu(detail, key, hash);
+ if (ret)
+ return ret;
+ /* Didn't find anything, insert an empty entry */
+ return sunrpc_cache_add_entry(detail, key, hash);
+}
+EXPORT_SYMBOL_GPL(sunrpc_cache_lookup_rcu);
static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch);
@@ -151,18 +167,18 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
struct cache_head *tmp;
if (!test_bit(CACHE_VALID, &old->flags)) {
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
if (!test_bit(CACHE_VALID, &old->flags)) {
if (test_bit(CACHE_NEGATIVE, &new->flags))
set_bit(CACHE_NEGATIVE, &old->flags);
else
detail->update(old, new);
cache_fresh_locked(old, new->expiry_time, detail);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_fresh_unlocked(old, detail);
return old;
}
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
}
/* We need to insert a new entry */
tmp = detail->alloc();
@@ -173,7 +189,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
cache_init(tmp, detail);
detail->init(tmp, old);
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
if (test_bit(CACHE_NEGATIVE, &new->flags))
set_bit(CACHE_NEGATIVE, &tmp->flags);
else
@@ -183,7 +199,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
cache_get(tmp);
cache_fresh_locked(tmp, new->expiry_time, detail);
cache_fresh_locked(old, 0, detail);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_fresh_unlocked(tmp, detail);
cache_fresh_unlocked(old, detail);
cache_put(old, detail);
@@ -223,7 +239,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h
{
int rv;
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
rv = cache_is_valid(h);
if (rv == -EAGAIN) {
set_bit(CACHE_NEGATIVE, &h->flags);
@@ -231,7 +247,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h
detail);
rv = -ENOENT;
}
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_fresh_unlocked(h, detail);
return rv;
}
@@ -341,7 +357,7 @@ static struct delayed_work cache_cleaner;
void sunrpc_init_cache_detail(struct cache_detail *cd)
{
- rwlock_init(&cd->hash_lock);
+ spin_lock_init(&cd->hash_lock);
INIT_LIST_HEAD(&cd->queue);
spin_lock(&cache_list_lock);
cd->nextcheck = 0;
@@ -361,11 +377,11 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd)
{
cache_purge(cd);
spin_lock(&cache_list_lock);
- write_lock(&cd->hash_lock);
+ spin_lock(&cd->hash_lock);
if (current_detail == cd)
current_detail = NULL;
list_del_init(&cd->others);
- write_unlock(&cd->hash_lock);
+ spin_unlock(&cd->hash_lock);
spin_unlock(&cache_list_lock);
if (list_empty(&cache_list)) {
/* module must be being unloaded so its safe to kill the worker */
@@ -422,7 +438,7 @@ static int cache_clean(void)
struct hlist_head *head;
struct hlist_node *tmp;
- write_lock(&current_detail->hash_lock);
+ spin_lock(&current_detail->hash_lock);
/* Ok, now to clean this strand */
@@ -433,13 +449,13 @@ static int cache_clean(void)
if (!cache_is_expired(current_detail, ch))
continue;
- hlist_del_init(&ch->cache_list);
+ hlist_del_init_rcu(&ch->cache_list);
current_detail->entries--;
rv = 1;
break;
}
- write_unlock(&current_detail->hash_lock);
+ spin_unlock(&current_detail->hash_lock);
d = current_detail;
if (!ch)
current_index ++;
@@ -494,9 +510,9 @@ void cache_purge(struct cache_detail *detail)
struct hlist_node *tmp = NULL;
int i = 0;
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
if (!detail->entries) {
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
return;
}
@@ -504,17 +520,17 @@ void cache_purge(struct cache_detail *detail)
for (i = 0; i < detail->hash_size; i++) {
head = &detail->hash_table[i];
hlist_for_each_entry_safe(ch, tmp, head, cache_list) {
- hlist_del_init(&ch->cache_list);
+ hlist_del_init_rcu(&ch->cache_list);
detail->entries--;
set_bit(CACHE_CLEANED, &ch->flags);
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
cache_fresh_unlocked(ch, detail);
cache_put(ch, detail);
- write_lock(&detail->hash_lock);
+ spin_lock(&detail->hash_lock);
}
}
- write_unlock(&detail->hash_lock);
+ spin_unlock(&detail->hash_lock);
}
EXPORT_SYMBOL_GPL(cache_purge);
@@ -1289,21 +1305,19 @@ EXPORT_SYMBOL_GPL(qword_get);
* get a header, then pass each real item in the cache
*/
-void *cache_seq_start(struct seq_file *m, loff_t *pos)
- __acquires(cd->hash_lock)
+static void *__cache_seq_start(struct seq_file *m, loff_t *pos)
{
loff_t n = *pos;
unsigned int hash, entry;
struct cache_head *ch;
struct cache_detail *cd = m->private;
- read_lock(&cd->hash_lock);
if (!n--)
return SEQ_START_TOKEN;
hash = n >> 32;
entry = n & ((1LL<<32) - 1);
- hlist_for_each_entry(ch, &cd->hash_table[hash], cache_list)
+ hlist_for_each_entry_rcu(ch, &cd->hash_table[hash], cache_list)
if (!entry--)
return ch;
n &= ~((1LL<<32) - 1);
@@ -1315,12 +1329,12 @@ void *cache_seq_start(struct seq_file *m, loff_t *pos)
if (hash >= cd->hash_size)
return NULL;
*pos = n+1;
- return hlist_entry_safe(cd->hash_table[hash].first,
+ return hlist_entry_safe(rcu_dereference_raw(
+ hlist_first_rcu(&cd->hash_table[hash])),
struct cache_head, cache_list);
}
-EXPORT_SYMBOL_GPL(cache_seq_start);
-void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
+static void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
{
struct cache_head *ch = p;
int hash = (*pos >> 32);
@@ -1333,7 +1347,8 @@ void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
*pos += 1LL<<32;
} else {
++*pos;
- return hlist_entry_safe(ch->cache_list.next,
+ return hlist_entry_safe(rcu_dereference_raw(
+ hlist_next_rcu(&ch->cache_list)),
struct cache_head, cache_list);
}
*pos &= ~((1LL<<32) - 1);
@@ -1345,18 +1360,32 @@ void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
if (hash >= cd->hash_size)
return NULL;
++*pos;
- return hlist_entry_safe(cd->hash_table[hash].first,
+ return hlist_entry_safe(rcu_dereference_raw(
+ hlist_first_rcu(&cd->hash_table[hash])),
struct cache_head, cache_list);
}
EXPORT_SYMBOL_GPL(cache_seq_next);
-void cache_seq_stop(struct seq_file *m, void *p)
- __releases(cd->hash_lock)
+void *cache_seq_start_rcu(struct seq_file *m, loff_t *pos)
+ __acquires(RCU)
{
- struct cache_detail *cd = m->private;
- read_unlock(&cd->hash_lock);
+ rcu_read_lock();
+ return __cache_seq_start(m, pos);
+}
+EXPORT_SYMBOL_GPL(cache_seq_start_rcu);
+
+void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos)
+{
+ return cache_seq_next(file, p, pos);
+}
+EXPORT_SYMBOL_GPL(cache_seq_next_rcu);
+
+void cache_seq_stop_rcu(struct seq_file *m, void *p)
+ __releases(RCU)
+{
+ rcu_read_unlock();
}
-EXPORT_SYMBOL_GPL(cache_seq_stop);
+EXPORT_SYMBOL_GPL(cache_seq_stop_rcu);
static int c_show(struct seq_file *m, void *p)
{
@@ -1384,9 +1413,9 @@ static int c_show(struct seq_file *m, void *p)
}
static const struct seq_operations cache_content_op = {
- .start = cache_seq_start,
- .next = cache_seq_next,
- .stop = cache_seq_stop,
+ .start = cache_seq_start_rcu,
+ .next = cache_seq_next_rcu,
+ .stop = cache_seq_stop_rcu,
.show = c_show,
};
@@ -1844,13 +1873,13 @@ EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs);
void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h)
{
- write_lock(&cd->hash_lock);
+ spin_lock(&cd->hash_lock);
if (!hlist_unhashed(&h->cache_list)){
- hlist_del_init(&h->cache_list);
+ hlist_del_init_rcu(&h->cache_list);
cd->entries--;
- write_unlock(&cd->hash_lock);
+ spin_unlock(&cd->hash_lock);
cache_put(h, cd);
} else
- write_unlock(&cd->hash_lock);
+ spin_unlock(&cd->hash_lock);
}
EXPORT_SYMBOL_GPL(sunrpc_cache_unhash);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 87533fbb96cf..51d36230b6e3 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -987,7 +987,7 @@ static void call_xpt_users(struct svc_xprt *xprt)
spin_lock(&xprt->xpt_lock);
while (!list_empty(&xprt->xpt_users)) {
u = list_first_entry(&xprt->xpt_users, struct svc_xpt_user, list);
- list_del(&u->list);
+ list_del_init(&u->list);
u->callback(u);
}
spin_unlock(&xprt->xpt_lock);
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index bb8db3cb8032..775b8c94265b 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -27,12 +27,32 @@
extern struct auth_ops svcauth_null;
extern struct auth_ops svcauth_unix;
-static DEFINE_SPINLOCK(authtab_lock);
-static struct auth_ops *authtab[RPC_AUTH_MAXFLAVOR] = {
- [0] = &svcauth_null,
- [1] = &svcauth_unix,
+static struct auth_ops __rcu *authtab[RPC_AUTH_MAXFLAVOR] = {
+ [RPC_AUTH_NULL] = (struct auth_ops __force __rcu *)&svcauth_null,
+ [RPC_AUTH_UNIX] = (struct auth_ops __force __rcu *)&svcauth_unix,
};
+static struct auth_ops *
+svc_get_auth_ops(rpc_authflavor_t flavor)
+{
+ struct auth_ops *aops;
+
+ if (flavor >= RPC_AUTH_MAXFLAVOR)
+ return NULL;
+ rcu_read_lock();
+ aops = rcu_dereference(authtab[flavor]);
+ if (aops != NULL && !try_module_get(aops->owner))
+ aops = NULL;
+ rcu_read_unlock();
+ return aops;
+}
+
+static void
+svc_put_auth_ops(struct auth_ops *aops)
+{
+ module_put(aops->owner);
+}
+
int
svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
{
@@ -45,14 +65,11 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
dprintk("svc: svc_authenticate (%d)\n", flavor);
- spin_lock(&authtab_lock);
- if (flavor >= RPC_AUTH_MAXFLAVOR || !(aops = authtab[flavor]) ||
- !try_module_get(aops->owner)) {
- spin_unlock(&authtab_lock);
+ aops = svc_get_auth_ops(flavor);
+ if (aops == NULL) {
*authp = rpc_autherr_badcred;
return SVC_DENIED;
}
- spin_unlock(&authtab_lock);
rqstp->rq_auth_slack = 0;
init_svc_cred(&rqstp->rq_cred);
@@ -82,7 +99,7 @@ int svc_authorise(struct svc_rqst *rqstp)
if (aops) {
rv = aops->release(rqstp);
- module_put(aops->owner);
+ svc_put_auth_ops(aops);
}
return rv;
}
@@ -90,13 +107,14 @@ int svc_authorise(struct svc_rqst *rqstp)
int
svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops)
{
+ struct auth_ops *old;
int rv = -EINVAL;
- spin_lock(&authtab_lock);
- if (flavor < RPC_AUTH_MAXFLAVOR && authtab[flavor] == NULL) {
- authtab[flavor] = aops;
- rv = 0;
+
+ if (flavor < RPC_AUTH_MAXFLAVOR) {
+ old = cmpxchg((struct auth_ops ** __force)&authtab[flavor], NULL, aops);
+ if (old == NULL || old == aops)
+ rv = 0;
}
- spin_unlock(&authtab_lock);
return rv;
}
EXPORT_SYMBOL_GPL(svc_auth_register);
@@ -104,10 +122,8 @@ EXPORT_SYMBOL_GPL(svc_auth_register);
void
svc_auth_unregister(rpc_authflavor_t flavor)
{
- spin_lock(&authtab_lock);
if (flavor < RPC_AUTH_MAXFLAVOR)
- authtab[flavor] = NULL;
- spin_unlock(&authtab_lock);
+ rcu_assign_pointer(authtab[flavor], NULL);
}
EXPORT_SYMBOL_GPL(svc_auth_unregister);
@@ -127,10 +143,11 @@ static struct hlist_head auth_domain_table[DN_HASHMAX];
static DEFINE_SPINLOCK(auth_domain_lock);
static void auth_domain_release(struct kref *kref)
+ __releases(&auth_domain_lock)
{
struct auth_domain *dom = container_of(kref, struct auth_domain, ref);
- hlist_del(&dom->hash);
+ hlist_del_rcu(&dom->hash);
dom->flavour->domain_release(dom);
spin_unlock(&auth_domain_lock);
}
@@ -159,7 +176,7 @@ auth_domain_lookup(char *name, struct auth_domain *new)
}
}
if (new)
- hlist_add_head(&new->hash, head);
+ hlist_add_head_rcu(&new->hash, head);
spin_unlock(&auth_domain_lock);
return new;
}
@@ -167,6 +184,21 @@ EXPORT_SYMBOL_GPL(auth_domain_lookup);
struct auth_domain *auth_domain_find(char *name)
{
- return auth_domain_lookup(name, NULL);
+ struct auth_domain *hp;
+ struct hlist_head *head;
+
+ head = &auth_domain_table[hash_str(name, DN_HASHBITS)];
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(hp, head, hash) {
+ if (strcmp(hp->name, name)==0) {
+ if (!kref_get_unless_zero(&hp->ref))
+ hp = NULL;
+ rcu_read_unlock();
+ return hp;
+ }
+ }
+ rcu_read_unlock();
+ return NULL;
}
EXPORT_SYMBOL_GPL(auth_domain_find);
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index af7f28fb8102..fb9041b92f72 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -37,20 +37,26 @@ struct unix_domain {
extern struct auth_ops svcauth_null;
extern struct auth_ops svcauth_unix;
-static void svcauth_unix_domain_release(struct auth_domain *dom)
+static void svcauth_unix_domain_release_rcu(struct rcu_head *head)
{
+ struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head);
struct unix_domain *ud = container_of(dom, struct unix_domain, h);
kfree(dom->name);
kfree(ud);
}
+static void svcauth_unix_domain_release(struct auth_domain *dom)
+{
+ call_rcu(&dom->rcu_head, svcauth_unix_domain_release_rcu);
+}
+
struct auth_domain *unix_domain_find(char *name)
{
struct auth_domain *rv;
struct unix_domain *new = NULL;
- rv = auth_domain_lookup(name, NULL);
+ rv = auth_domain_find(name);
while(1) {
if (rv) {
if (new && rv != &new->h)
@@ -91,6 +97,7 @@ struct ip_map {
char m_class[8]; /* e.g. "nfsd" */
struct in6_addr m_addr;
struct unix_domain *m_client;
+ struct rcu_head m_rcu;
};
static void ip_map_put(struct kref *kref)
@@ -101,7 +108,7 @@ static void ip_map_put(struct kref *kref)
if (test_bit(CACHE_VALID, &item->flags) &&
!test_bit(CACHE_NEGATIVE, &item->flags))
auth_domain_put(&im->m_client->h);
- kfree(im);
+ kfree_rcu(im, m_rcu);
}
static inline int hash_ip6(const struct in6_addr *ip)
@@ -280,9 +287,9 @@ static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class,
strcpy(ip.m_class, class);
ip.m_addr = *addr;
- ch = sunrpc_cache_lookup(cd, &ip.h,
- hash_str(class, IP_HASHBITS) ^
- hash_ip6(addr));
+ ch = sunrpc_cache_lookup_rcu(cd, &ip.h,
+ hash_str(class, IP_HASHBITS) ^
+ hash_ip6(addr));
if (ch)
return container_of(ch, struct ip_map, h);
@@ -412,6 +419,7 @@ struct unix_gid {
struct cache_head h;
kuid_t uid;
struct group_info *gi;
+ struct rcu_head rcu;
};
static int unix_gid_hash(kuid_t uid)
@@ -426,7 +434,7 @@ static void unix_gid_put(struct kref *kref)
if (test_bit(CACHE_VALID, &item->flags) &&
!test_bit(CACHE_NEGATIVE, &item->flags))
put_group_info(ug->gi);
- kfree(ug);
+ kfree_rcu(ug, rcu);
}
static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew)
@@ -619,7 +627,7 @@ static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, kuid_t uid)
struct cache_head *ch;
ug.uid = uid;
- ch = sunrpc_cache_lookup(cd, &ug.h, unix_gid_hash(uid));
+ ch = sunrpc_cache_lookup_rcu(cd, &ug.h, unix_gid_hash(uid));
if (ch)
return container_of(ch, struct unix_gid, h);
else
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index db8bb6b3a2b0..3b525accaa68 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -325,59 +325,34 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
/*
* Generic recvfrom routine.
*/
-static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
- int buflen)
+static ssize_t svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov,
+ unsigned int nr, size_t buflen, unsigned int base)
{
struct svc_sock *svsk =
container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
- struct msghdr msg = {
- .msg_flags = MSG_DONTWAIT,
- };
- int len;
+ struct msghdr msg = { NULL };
+ ssize_t len;
rqstp->rq_xprt_hlen = 0;
clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nr, buflen);
- len = sock_recvmsg(svsk->sk_sock, &msg, msg.msg_flags);
+ if (base != 0) {
+ iov_iter_advance(&msg.msg_iter, base);
+ buflen -= base;
+ }
+ len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT);
/* If we read a full record, then assume there may be more
* data to read (stream based sockets only!)
*/
if (len == buflen)
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
- dprintk("svc: socket %p recvfrom(%p, %zu) = %d\n",
+ dprintk("svc: socket %p recvfrom(%p, %zu) = %zd\n",
svsk, iov[0].iov_base, iov[0].iov_len, len);
return len;
}
-static int svc_partial_recvfrom(struct svc_rqst *rqstp,
- struct kvec *iov, int nr,
- int buflen, unsigned int base)
-{
- size_t save_iovlen;
- void *save_iovbase;
- unsigned int i;
- int ret;
-
- if (base == 0)
- return svc_recvfrom(rqstp, iov, nr, buflen);
-
- for (i = 0; i < nr; i++) {
- if (iov[i].iov_len > base)
- break;
- base -= iov[i].iov_len;
- }
- save_iovlen = iov[i].iov_len;
- save_iovbase = iov[i].iov_base;
- iov[i].iov_len -= base;
- iov[i].iov_base += base;
- ret = svc_recvfrom(rqstp, &iov[i], nr - i, buflen);
- iov[i].iov_len = save_iovlen;
- iov[i].iov_base = save_iovbase;
- return ret;
-}
-
/*
* Set socket snd and rcv buffer lengths
*/
@@ -962,7 +937,8 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen;
iov.iov_len = want;
- if ((len = svc_recvfrom(rqstp, &iov, 1, want)) < 0)
+ len = svc_recvfrom(rqstp, &iov, 1, want, 0);
+ if (len < 0)
goto error;
svsk->sk_tcplen += len;
@@ -1088,14 +1064,13 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
vec = rqstp->rq_vec;
- pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0],
- svsk->sk_datalen + want);
+ pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], base + want);
rqstp->rq_respages = &rqstp->rq_pages[pnum];
rqstp->rq_next_page = rqstp->rq_respages + 1;
/* Now receive data */
- len = svc_partial_recvfrom(rqstp, vec, pnum, want, base);
+ len = svc_recvfrom(rqstp, vec, pnum, base + want, base);
if (len >= 0) {
svsk->sk_tcplen += len;
svsk->sk_datalen += len;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index d3a1a237cee6..f3c147d70286 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -5,8 +5,6 @@
* Support for backward direction RPCs on RPC/RDMA (server-side).
*/
-#include <linux/module.h>
-
#include <linux/sunrpc/svc_rdma.h>
#include "xprt_rdma.h"
@@ -32,7 +30,6 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
struct kvec *dst, *src = &rcvbuf->head[0];
struct rpc_rqst *req;
- unsigned long cwnd;
u32 credits;
size_t len;
__be32 xid;
@@ -66,6 +63,8 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
if (dst->iov_len < len)
goto out_unlock;
memcpy(dst->iov_base, p, len);
+ xprt_pin_rqst(req);
+ spin_unlock(&xprt->queue_lock);
credits = be32_to_cpup(rdma_resp + 2);
if (credits == 0)
@@ -74,15 +73,13 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
credits = r_xprt->rx_buf.rb_bc_max_requests;
spin_lock_bh(&xprt->transport_lock);
- cwnd = xprt->cwnd;
xprt->cwnd = credits << RPC_CWNDSHIFT;
- if (xprt->cwnd > cwnd)
- xprt_release_rqst_cong(req->rq_task);
spin_unlock_bh(&xprt->transport_lock);
-
+ spin_lock(&xprt->queue_lock);
ret = 0;
xprt_complete_rqst(req->rq_task, rcvbuf->len);
+ xprt_unpin_rqst(req);
rcvbuf->len = 0;
out_unlock:
@@ -251,7 +248,6 @@ xprt_rdma_bc_put(struct rpc_xprt *xprt)
dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
xprt_free(xprt);
- module_put(THIS_MODULE);
}
static const struct rpc_xprt_ops xprt_rdma_bc_procs = {
@@ -323,20 +319,9 @@ xprt_setup_rdma_bc(struct xprt_create *args)
args->bc_xprt->xpt_bc_xprt = xprt;
xprt->bc_xprt = args->bc_xprt;
- if (!try_module_get(THIS_MODULE))
- goto out_fail;
-
/* Final put for backchannel xprt is in __svc_rdma_free */
xprt_get(xprt);
return xprt;
-
-out_fail:
- xprt_rdma_free_addresses(xprt);
- args->bc_xprt->xpt_bc_xprt = NULL;
- args->bc_xprt->xpt_bc_xps = NULL;
- xprt_put(xprt);
- xprt_free(xprt);
- return ERR_PTR(-EINVAL);
}
struct xprt_class xprt_rdma_bc = {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 2848cafd4a17..2f7ec8912f49 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -475,10 +475,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
/* Qualify the transport resource defaults with the
* capabilities of this particular device */
- newxprt->sc_max_send_sges = dev->attrs.max_send_sge;
- /* transport hdr, head iovec, one page list entry, tail iovec */
- if (newxprt->sc_max_send_sges < 4) {
- pr_err("svcrdma: too few Send SGEs available (%d)\n",
+ /* Transport header, head iovec, tail iovec */
+ newxprt->sc_max_send_sges = 3;
+ /* Add one SGE per page list entry */
+ newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE;
+ if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) {
+ pr_err("svcrdma: too few Send SGEs available (%d needed)\n",
newxprt->sc_max_send_sges);
goto errout;
}
diff --git a/net/xfrm/xfrm_hash.c b/net/xfrm/xfrm_hash.c
index 2ad33ce1ea17..eca8d84d99bf 100644
--- a/net/xfrm/xfrm_hash.c
+++ b/net/xfrm/xfrm_hash.c
@@ -6,7 +6,7 @@
#include <linux/kernel.h>
#include <linux/mm.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/xfrm.h>