Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:
	net/ipv4/fib_frontend.c

14 files changed, 90 insertions, 61 deletions

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 0e8157ee5d43..b6ff4a1519ab 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -97,11 +97,9 @@ struct workqueue_struct *ceph_msgr_wq;
 int ceph_msgr_init(void)
 {
         ceph_msgr_wq = create_workqueue("ceph-msgr");
-        if (IS_ERR(ceph_msgr_wq)) {
-                int ret = PTR_ERR(ceph_msgr_wq);
-                pr_err("msgr_init failed to create workqueue: %d\n", ret);
-                ceph_msgr_wq = NULL;
-                return ret;
+        if (!ceph_msgr_wq) {
+                pr_err("msgr_init failed to create workqueue\n");
+                return -ENOMEM;
         }
         return 0;
 }
@@ -540,8 +538,7 @@ static void prepare_write_message(struct ceph_connection *con)
                 /* initialize page iterator */
                 con->out_msg_pos.page = 0;
                 if (m->pages)
-                        con->out_msg_pos.page_pos =
-                                le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+                        con->out_msg_pos.page_pos = m->page_alignment;
                 else
                         con->out_msg_pos.page_pos = 0;
                 con->out_msg_pos.data_pos = 0;
@@ -1491,7 +1488,7 @@ static int read_partial_message(struct ceph_connection *con)
         struct ceph_msg *m = con->in_msg;
         int ret;
         int to, left;
-        unsigned front_len, middle_len, data_len, data_off;
+        unsigned front_len, middle_len, data_len;
         int datacrc = con->msgr->nocrc;
         int skip;
         u64 seq;
@@ -1527,19 +1524,17 @@ static int read_partial_message(struct ceph_connection *con)
         data_len = le32_to_cpu(con->in_hdr.data_len);
         if (data_len > CEPH_MSG_MAX_DATA_LEN)
                 return -EIO;
-        data_off = le16_to_cpu(con->in_hdr.data_off);
 
         /* verify seq# */
         seq = le64_to_cpu(con->in_hdr.seq);
         if ((s64)seq - (s64)con->in_seq < 1) {
-                pr_info("skipping %s%lld %s seq %lld, expected %lld\n",
+                pr_info("skipping %s%lld %s seq %lld expected %lld\n",
                         ENTITY_NAME(con->peer_name),
                         ceph_pr_addr(&con->peer_addr.in_addr),
                         seq, con->in_seq + 1);
                 con->in_base_pos = -front_len - middle_len - data_len -
                         sizeof(m->footer);
                 con->in_tag = CEPH_MSGR_TAG_READY;
-                con->in_seq++;
                 return 0;
         } else if ((s64)seq - (s64)con->in_seq > 1) {
                 pr_err("read_partial_message bad seq %lld expected %lld\n",
@@ -1576,7 +1571,7 @@ static int read_partial_message(struct ceph_connection *con)
 
                 con->in_msg_pos.page = 0;
                 if (m->pages)
-                        con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
+                        con->in_msg_pos.page_pos = m->page_alignment;
                 else
                         con->in_msg_pos.page_pos = 0;
                 con->in_msg_pos.data_pos = 0;
@@ -2301,6 +2296,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags)
 
         /* data */
         m->nr_pages = 0;
+        m->page_alignment = 0;
         m->pages = NULL;
         m->pagelist = NULL;
         m->bio = NULL;
@@ -2370,6 +2366,7 @@ static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
                                type, front_len);
                         return NULL;
                 }
+                msg->page_alignment = le16_to_cpu(hdr->data_off);
         }
         memcpy(&msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 79391994b3ed..3e20a122ffa2 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -71,6 +71,7 @@ void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
                 op->extent.length = objlen;
         }
         req->r_num_pages = calc_pages_for(off, *plen);
+        req->r_page_alignment = off & ~PAGE_MASK;
         if (op->op == CEPH_OSD_OP_WRITE)
                 op->payload_len = *plen;
 
@@ -390,6 +391,8 @@ void ceph_osdc_build_request(struct ceph_osd_request *req,
                 req->r_request->hdr.data_len = cpu_to_le32(data_len);
         }
 
+        req->r_request->page_alignment = req->r_page_alignment;
+
         BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
         msg_size = p - msg->front.iov_base;
         msg->front.iov_len = msg_size;
@@ -419,7 +422,8 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
                                                u32 truncate_seq,
                                                u64 truncate_size,
                                                struct timespec *mtime,
-                                               bool use_mempool, int num_reply)
+                                               bool use_mempool, int num_reply,
+                                               int page_align)
 {
         struct ceph_osd_req_op ops[3];
         struct ceph_osd_request *req;
@@ -447,6 +451,10 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
         calc_layout(osdc, vino, layout, off, plen, req, ops);
         req->r_file_layout = *layout;  /* keep a copy */
 
+        /* in case it differs from natural alignment that calc_layout
+           filled in for us */
+        req->r_page_alignment = page_align;
+
         ceph_osdc_build_request(req, off, plen, ops,
                                 snapc,
                                 mtime,
@@ -1489,7 +1497,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
                         struct ceph_vino vino, struct ceph_file_layout *layout,
                         u64 off, u64 *plen,
                         u32 truncate_seq, u64 truncate_size,
-                        struct page **pages, int num_pages)
+                        struct page **pages, int num_pages, int page_align)
 {
         struct ceph_osd_request *req;
         int rc = 0;
@@ -1499,15 +1507,15 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
         req = ceph_osdc_new_request(osdc, layout, vino, off, plen,
                                     CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
                                     NULL, 0, truncate_seq, truncate_size, NULL,
-                                    false, 1);
+                                    false, 1, page_align);
         if (!req)
                 return -ENOMEM;
 
         /* it may be a short read due to an object boundary */
         req->r_pages = pages;
 
-        dout("readpages  final extent is %llu~%llu (%d pages)\n",
-             off, *plen, req->r_num_pages);
+        dout("readpages  final extent is %llu~%llu (%d pages align %d)\n",
+             off, *plen, req->r_num_pages, page_align);
 
         rc = ceph_osdc_start_request(osdc, req, false);
         if (!rc)
@@ -1533,6 +1541,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 {
         struct ceph_osd_request *req;
         int rc = 0;
+        int page_align = off & ~PAGE_MASK;
 
         BUG_ON(vino.snap != CEPH_NOSNAP);
         req = ceph_osdc_new_request(osdc, layout, vino, off, &len,
@@ -1541,7 +1550,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
                                             CEPH_OSD_FLAG_WRITE,
                                     snapc, do_sync,
                                     truncate_seq, truncate_size, mtime,
-                                    nofail, 1);
+                                    nofail, 1, page_align);
         if (!req)
                 return -ENOMEM;
 
@@ -1638,8 +1647,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
         m = ceph_msg_get(req->r_reply);
 
         if (data_len > 0) {
-                unsigned data_off = le16_to_cpu(hdr->data_off);
-                int want = calc_pages_for(data_off & ~PAGE_MASK, data_len);
+                int want = calc_pages_for(req->r_page_alignment, data_len);
 
                 if (unlikely(req->r_num_pages < want)) {
                         pr_warning("tid %lld reply %d > expected %d pages\n",
@@ -1651,6 +1659,7 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
                 }
                 m->pages = req->r_pages;
                 m->nr_pages = req->r_num_pages;
+                m->page_alignment = req->r_page_alignment;
 #ifdef CONFIG_BLOCK
                 m->bio = req->r_bio;
 #endif
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index 54caf0687155..1a040e64c69f 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -13,8 +13,7 @@
  * build a vector of user pages
  */
 struct page **ceph_get_direct_page_vector(const char __user *data,
-                                                 int num_pages,
-                                                 loff_t off, size_t len)
+                                          int num_pages, bool write_page)
 {
         struct page **pages;
         int rc;
@@ -25,24 +24,27 @@ struct page **ceph_get_direct_page_vector(const char __user *data,
 
         down_read(&current->mm->mmap_sem);
         rc = get_user_pages(current, current->mm, (unsigned long)data,
-                            num_pages, 0, 0, pages, NULL);
+                            num_pages, write_page, 0, pages, NULL);
         up_read(&current->mm->mmap_sem);
-        if (rc < 0)
+        if (rc < num_pages)
                 goto fail;
         return pages;
 
 fail:
-        kfree(pages);
+        ceph_put_page_vector(pages, rc > 0 ? rc : 0, false);
         return ERR_PTR(rc);
 }
 EXPORT_SYMBOL(ceph_get_direct_page_vector);
 
-void ceph_put_page_vector(struct page **pages, int num_pages)
+void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty)
 {
         int i;
 
-        for (i = 0; i < num_pages; i++)
+        for (i = 0; i < num_pages; i++) {
+                if (dirty)
+                        set_page_dirty_lock(pages[i]);
                 put_page(pages[i]);
+        }
         kfree(pages);
 }
 EXPORT_SYMBOL(ceph_put_page_vector);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 82a4369ae150..a20e5d3bbfa0 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -181,8 +181,7 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 {
         int ret = 0;
 
-        if (rule->iifindex && (rule->iifindex != fl->iif) &&
-            !(fl->flags & FLOWI_FLAG_MATCH_ANY_IIF))
+        if (rule->iifindex && (rule->iifindex != fl->iif))
                 goto out;
 
         if (rule->oifindex && (rule->oifindex != fl->oif))
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 9f8bb68911e4..1d2cdd43a878 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -159,13 +159,19 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 {
         struct flowi fl = {
                 .fl4_dst = addr,
-                .flags = FLOWI_FLAG_MATCH_ANY_IIF
         };
         struct fib_result res = { 0 };
         struct net_device *dev = NULL;
+        struct fib_table *local_table;
+
+#ifdef CONFIG_IP_MULTIPLE_TABLES
+        res.r = NULL;
+#endif
 
         rcu_read_lock();
-        if (fib_lookup(net, &fl, &res)) {
+        local_table = fib_get_table(net, RT_TABLE_LOCAL);
+        if (!local_table ||
+            fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) {
                 rcu_read_unlock();
                 return NULL;
         }
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d8b4f4d0d66e..f1defb7d88e8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2562,9 +2562,10 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp,
                         goto out;
 
                 /* RACE: Check return value of inet_select_addr instead. */
-                if (rcu_dereference(dev_out->ip_ptr) == NULL)
-                        goto out;       /* Wrong error code */
-
+                if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) {
+                        err = -ENETUNREACH;
+                        goto out;
+                }
                 if (ipv4_is_local_multicast(oldflp->fl4_dst) ||
                     ipv4_is_lbcast(oldflp->fl4_dst)) {
                         if (!fl.fl4_src)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f4011027543d..856f68466d49 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2000,7 +2000,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 get_req:
                         req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket];
                 }
-                sk        = sk_next(st->syn_wait_sk);
+                sk        = sk_nulls_next(st->syn_wait_sk);
                 st->state = TCP_SEQ_STATE_LISTENING;
                 read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
         } else {
@@ -2009,7 +2009,7 @@ get_req:
                 if (reqsk_queue_len(&icsk->icsk_accept_queue))
                         goto start_req;
                 read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
-                sk = sk_next(sk);
+                sk = sk_nulls_next(sk);
         }
 get_sk:
         sk_nulls_for_each_from(sk, node) {
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 7f097989cde2..c9890e25cd4c 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -45,7 +45,6 @@
 #include <linux/capability.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <linux/smp_lock.h>
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/slab.h>
@@ -2281,6 +2280,16 @@ static int irda_getsockopt(struct socket *sock, int level, int optname,
 
         switch (optname) {
         case IRLMP_ENUMDEVICES:
+
+                /* Offset to first device entry */
+                offset = sizeof(struct irda_device_list) -
+                        sizeof(struct irda_device_info);
+
+                if (len < offset) {
+                        err = -EINVAL;
+                        goto out;
+                }
+
                 /* Ask lmp for the current discovery log */
                 discoveries = irlmp_get_discoveries(&list.len, self->mask.word,
                                                     self->nslots);
@@ -2291,15 +2300,9 @@ static int irda_getsockopt(struct socket *sock, int level, int optname,
                 }
 
                 /* Write total list length back to client */
-                if (copy_to_user(optval, &list,
-                                 sizeof(struct irda_device_list) -
-                                 sizeof(struct irda_device_info)))
+                if (copy_to_user(optval, &list, offset))
                         err = -EFAULT;
 
-                /* Offset to first device entry */
-                offset = sizeof(struct irda_device_list) -
-                        sizeof(struct irda_device_info);
-
                 /* Copy the list itself - watch for overflow */
                 if (list.len > 2048) {
                         err = -EINVAL;
diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c
index 7fa86373de41..7c567b8aa89a 100644
--- a/net/irda/irnet/irnet_ppp.c
+++ b/net/irda/irnet/irnet_ppp.c
@@ -15,7 +15,6 @@
 
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include "irnet_ppp.h"          /* Private header */
 /* Please put other headers in irnet.h - Thanks */
 
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index 798d9b9462e2..9109262abd24 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -93,7 +93,7 @@ config MAC80211_MESH
 config MAC80211_LEDS
         bool "Enable LED triggers"
         depends on MAC80211
-        select NEW_LEDS
+        depends on LEDS_CLASS
         select LEDS_TRIGGERS
         ---help---
           This option enables a few LED triggers for different
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 01a3f2630eaf..5e9d3bc6a2d9 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1831,9 +1831,11 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 
                         fwd_skb = skb_copy(skb, GFP_ATOMIC);
 
-                        if (!fwd_skb && net_ratelimit())
+                        if (!fwd_skb && net_ratelimit()) {
                                 printk(KERN_DEBUG "%s: failed to clone mesh frame\n",
                                                    sdata->name);
+                                goto out;
+                        }
 
                         fwd_hdr =  (struct ieee80211_hdr *) fwd_skb->data;
                         memcpy(fwd_hdr->addr2, sdata->vif.addr, ETH_ALEN);
@@ -1871,6 +1873,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
                 }
         }
 
+ out:
         if (is_multicast_ether_addr(hdr->addr1) ||
             sdata->dev->flags & IFF_PROMISC)
                 return RX_CONTINUE;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 9dab9573be41..92ce94f5146b 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -989,20 +989,26 @@ call_refreshresult(struct rpc_task *task)
         dprint_status(task);
 
         task->tk_status = 0;
-        task->tk_action = call_allocate;
-        if (status >= 0 && rpcauth_uptodatecred(task))
-                return;
+        task->tk_action = call_refresh;
         switch (status) {
-        case -EACCES:
-                rpc_exit(task, -EACCES);
-                return;
-        case -ENOMEM:
-                rpc_exit(task, -ENOMEM);
+        case 0:
+                if (rpcauth_uptodatecred(task))
+                        task->tk_action = call_allocate;
                 return;
         case -ETIMEDOUT:
                 rpc_delay(task, 3*HZ);
+        case -EAGAIN:
+                status = -EACCES;
+                if (!task->tk_cred_retry)
+                        break;
+                task->tk_cred_retry--;
+                dprintk("RPC: %5u %s: retry refresh creds\n",
+                                task->tk_pid, __func__);
+                return;
         }
-        task->tk_action = call_refresh;
+        dprintk("RPC: %5u %s: refresh creds failed with error %d\n",
+                                task->tk_pid, __func__, status);
+        rpc_exit(task, status);
 }
 
 /*
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index f71a73107ae9..80df89d957ba 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -115,9 +115,7 @@ EXPORT_SYMBOL_GPL(svc_seq_show);
  */
 struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt)
 {
-        struct rpc_iostats *new;
-        new = kcalloc(clnt->cl_maxproc, sizeof(struct rpc_iostats), GFP_KERNEL);
-        return new;
+        return kcalloc(clnt->cl_maxproc, sizeof(struct rpc_iostats), GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(rpc_alloc_iostats);
 
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index c82fe739fbdc..3f2c5559ca1a 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -5,7 +5,6 @@
  */
 
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
@@ -213,6 +212,7 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
         spin_lock(&svc_xprt_class_lock);
         list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
                 struct svc_xprt *newxprt;
+                unsigned short newport;
 
                 if (strcmp(xprt_name, xcl->xcl_name))
                         continue;
@@ -231,8 +231,9 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
                 spin_lock_bh(&serv->sv_lock);
                 list_add(&newxprt->xpt_list, &serv->sv_permsocks);
                 spin_unlock_bh(&serv->sv_lock);
+                newport = svc_xprt_local_port(newxprt);
                 clear_bit(XPT_BUSY, &newxprt->xpt_flags);
-                return svc_xprt_local_port(newxprt);
+                return newport;
         }
  err:
         spin_unlock(&svc_xprt_class_lock);
@@ -426,8 +427,13 @@ void svc_xprt_received(struct svc_xprt *xprt)
 {
         BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags));
         xprt->xpt_pool = NULL;
+        /* As soon as we clear busy, the xprt could be closed and
+         * 'put', so we need a reference to call svc_xprt_enqueue with:
+         */
+        svc_xprt_get(xprt);
         clear_bit(XPT_BUSY, &xprt->xpt_flags);
         svc_xprt_enqueue(xprt);
+        svc_xprt_put(xprt);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_received);