summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* RDS: fix fmr pool dirty_countWengang Wang2015-08-251-6/+9
| | | | | | | | | | | | In rds_ib_flush_mr_pool(), dirty_count accounts the clean ones which is wrong. This can lead to a negative dirty count value. Lets fix it. Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* RDS: Fix rds MR reference count in rds_rdma_unuse()santosh.shilimkar@oracle.com2015-08-251-2/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | rds_rdma_unuse() drops the mr reference count which it hasn't taken. Correct way of removing mr is to remove mr from the tree and then rdma_destroy_mr() it first, then rds_mr_put() to decrement its reference count. Whichever thread holds last reference will free the mr via rds_mr_put() This bug was triggering weird null pointer crashes. One if the trace for it is captured below. BUG: unable to handle kernel NULL pointer dereference at 0000000000000104 IP: [<ffffffffa0899471>] rds_ib_free_mr+0x31/0x130 [rds_rdma] PGD 4366fa067 PUD 4366f9067 PMD 0 Oops: 0000 [#1] SMP [...] task: ffff88046da6a000 ti: ffff88046da6c000 task.ti: ffff88046da6c000 RIP: 0010:[<ffffffffa0899471>] [<ffffffffa0899471>] rds_ib_free_mr+0x31/0x130 [rds_rdma] RSP: 0018:ffff88046fa43bd8 EFLAGS: 00010286 RAX: 0000000071d38b80 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff880079e7ff40 RBP: ffff88046fa43bf8 R08: 0000000000000000 R09: 0000000000000000 R10: ffff88046fa43ca8 R11: ffff88046a802ed8 R12: ffff880079e7fa40 R13: 0000000000000000 R14: ffff880079e7ff40 R15: 0000000000000000 FS: 0000000000000000(0000) GS:ffff88046fa40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 0000000000000104 CR3: 00000004366fb000 CR4: 00000000000006e0 Stack: ffff880079e7fa40 ffff880671d38f08 ffff880079e7ff40 0000000000000296 ffff88046fa43c28 ffffffffa087a38b ffff880079e7fa40 ffff880671d38f10 0000000000000000 0000000000000292 ffff88046fa43c48 ffffffffa087a3b6 Call Trace: <IRQ> [<ffffffffa087a38b>] rds_destroy_mr+0x8b/0xa0 [rds] [<ffffffffa087a3b6>] __rds_put_mr_final+0x16/0x30 [rds] [<ffffffffa087a492>] rds_rdma_unuse+0xc2/0x120 [rds] [<ffffffffa08766d3>] rds_recv_incoming_exthdrs+0x83/0xa0 [rds] [<ffffffffa0876782>] rds_recv_incoming+0x92/0x200 [rds] [<ffffffffa0895269>] rds_ib_process_recv+0x259/0x320 [rds_rdma] [<ffffffffa08962a8>] rds_ib_recv_tasklet_fn+0x1a8/0x490 [rds_rdma] [<ffffffff810dcd78>] ? __remove_hrtimer+0x58/0x90 [<ffffffff810799e1>] tasklet_action+0xb1/0xc0 [<ffffffff81079b52>] __do_softirq+0xe2/0x290 [<ffffffff81079df6>] irq_exit+0xa6/0xb0 [<ffffffff81613915>] do_IRQ+0x65/0xf0 [<ffffffff816118ab>] common_interrupt+0x6b/0x6b Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* RDS: fix the dangling reference to rds_ib_incoming_slabsantosh.shilimkar@oracle.com2015-08-251-2/+3
| | | | | | | | | On rds_ib_frag_slab allocation failure, ensure rds_ib_incoming_slab is not pointing to the detsroyed memory. Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge tag 'batman-adv-for-davem' of git://git.open-mesh.org/linux-mergeDavid S. Miller2015-08-2537-679/+733
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Antonio Quartulli says: ==================== Included changes: - code restyling and beautification - use int kernel types instead of C99 - update kereldoc - prevent potential hlist double deletion of VLAN objects - fix gw bandwidth calculation - convert list to hlist when needed - add lockdep_asserts calls in function with lock requirements described in kerneldoc ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
| * batman-adv: beautify supported routing algorithm listMarek Lindner2015-08-251-1/+1
| | | | | | | | | | Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: Fix conditional statements indentationSven Eckelmann2015-08-251-1/+1
| | | | | | | | | | | | | | | | | | commit 29b9256e6631 ("batman-adv: consider outgoing interface in OGM sending") incorrectly indented the interface check code. Signed-off-by: Sven Eckelmann <sven@narfation.org> Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: Add lockdep_asserts for documented external locksSven Eckelmann2015-08-253-0/+11
| | | | | | | | | | | | | | | | | | | | Some functions already have documentation about locks they require inside their kerneldoc header. These can be directly tested during runtime using the lockdep asserts. Signed-off-by: Sven Eckelmann <sven@narfation.org> Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: Annotate deleting functions with external lock via lockdepSven Eckelmann2015-08-254-5/+25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Functions which use (h)list_del* are requiring correct locking when they operate on global lists. Most of the time the search in the list and the delete are done in the same function. All other cases should have it visible that they require a special lock to avoid race conditions. Lockdep asserts can be used to check these problem during runtime when the lockdep functionality is enabled. Signed-off-by: Sven Eckelmann <sven@narfation.org> Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: convert bat_priv->tt.req_list to hlistMarek Lindner2015-08-253-16/+19
| | | | | | | | | | | | | | | | Since the list's tail is never accessed using a double linked list head wastes memory. Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: Fix gw_bandwidth calculation on 32 bit systemsSven Eckelmann2015-08-251-7/+42
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The TVLV for the gw_bandwidth stores everything as u32. But the gw_bandwidth reads the signed long which limits the maximum value to (2 ** 31 - 1) on systems with 4 byte long. Also the input value is always converted from either Mibit/s or Kibit/s to 100Kibit/s. This reduces the values even further when the user sets it via the default unit Kibit/s. It may even cause an integer overflow and end up with a value the user never intended. Instead read the values as u64, check for possible overflows, do the unit adjustments and then reduce the size to u32. Signed-off-by: Sven Eckelmann <sven@narfation.org> Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: Return EINVAL on invalid gw_bandwidth changeSven Eckelmann2015-08-251-2/+2
| | | | | | | | | | | | | | | | | | | | Invalid speed settings by the user are currently acknowledged as correct but not stored. Instead the return of the store operation of the file "gw_bandwidth" should indicate that the given value is not acceptable. Signed-off-by: Sven Eckelmann <sven@narfation.org> Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: prevent potential hlist double deletionMarek Lindner2015-08-251-1/+1
| | | | | | | | | | | | | | | | | | | | | | The hlist_del_rcu() call in batadv_tt_global_size_mod() does not check if the element still is part of the list prior to deletion. The atomic list counter should prevent the worst but converting to hlist_del_init_rcu() ensures the element can't be deleted more than once. Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: convert orig_node->vlan_list to hlistMarek Lindner2015-08-253-9/+10
| | | | | | | | | | | | | | | | Since the list's tail is never accessed using a double linked list head wastes memory. Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: Remove batadv_ types forward declarationsSven Eckelmann2015-08-2511-27/+0
| | | | | | | | | | | | | | | | | | | | main.h is included in every file and is the only way to access types.h. This makes forward declarations for all types defined in types.h unnecessary. Signed-off-by: Sven Eckelmann <sven@narfation.org> Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: rename batadv_new_tt_req_node to batadv_tt_req_node_newMarek Lindner2015-08-251-4/+9
| | | | | | | | | | Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: update kernel doc of batadv_tt_global_del_orig_entry()Marek Lindner2015-08-251-6/+12
| | | | | | | | | | | | | | | | | | The updated kernel doc & additional comment shall prevent accidental copy & paste errors or calling the function without the required precautions. Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: Remove multiple assignment per lineSven Eckelmann2015-08-257-17/+39
| | | | | | | | | | | | | | | | | | | | The Linux CodingStyle disallows multiple assignments in a single line. (see chapter 1) Reported-by: Markus Pargmann <mpa@pengutronix.de> Signed-off-by: Sven Eckelmann <sven@narfation.org> Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: Fix kerneldoc over 80 column linesSven Eckelmann2015-08-252-4/+4
| | | | | | | | | | | | | | | | | | | | | | Kerneldoc required single line documentation in the past (before 2009). Therefore, the 80 columns limit per line check of checkpatch was disabled for kerneldoc. But kerneldoc is not excluded anymore from it and checkpatch now enabled the check again. Signed-off-by: Sven Eckelmann <sven@narfation.org> Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
| * batman-adv: Replace C99 int types with kernel typeSven Eckelmann2015-08-2530-585/+563
| | | | | | | | | | | | | | | | | | | | (s|u)(8|16|32|64) are the preferred types in the kernel. The use of the standard C99 types u?int(8|16|32|64)_t are objected by some people and even checkpatch now warns about using them. Signed-off-by: Sven Eckelmann <sven@narfation.org> Signed-off-by: Marek Lindner <mareklindner@neomailbox.ch> Signed-off-by: Antonio Quartulli <antonio@meshcoding.com>
* | enic: reduce ioread in devcmd2Govindarajulu Varadarajan2015-08-252-3/+6
| | | | | | | | | | | | | | | | posted_index is RO in firmware. We need not do ioread everytime to get posted index. Store posted index locally. Signed-off-by: Govindarajulu Varadarajan <_govind@gmx.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | r8169: Add values missing in @get_stats64 from HW countersCorinna Vinschen2015-08-251-14/+149
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The r8169 driver collects statistical information returned by @get_stats64 by counting them in the driver itself, even though many (but not all) of the values are already collected by tally counters (TCs) in the NIC. Some of these TC values are not returned by @get_stats64. Especially the received multicast packages are missing from /proc/net/dev. Rectify this by fetching the TCs and returning them from rtl8169_get_stats64. The counters collected in the driver obviously disappear as soon as the driver is unloaded so after a driver is loaded the counters always start at 0. The TCs on the other hand are only reset by a power cycle. Without further considerations the values collected by the driver would not match up against the TC values. This patch introduces a new function rtl8169_reset_counters which resets the TCs. Also, since rtl8169_reset_counters shares most of its code with rtl8169_update_counters, refactor the shared code into two new functions rtl8169_map_counters and rtl8169_unmap_counters. Unfortunately chip versions prior to RTL_GIGA_MAC_VER_19 don't allow to reset the TCs programatically. Therefore introduce an addition to the rtl8169_private struct and a function rtl8169_init_counter_offsets to store the TCs at first rtl_open. Use these values as offsets in rtl8169_get_stats64. Propagate a failure to reset *and* update the counters up to rtl_open and emit a warning message, if so. Signed-off-by: Corinna Vinschen <vinschen@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | rds: Fix improper gfp_t usage.David S. Miller2015-08-251-1/+1
| | | | | | | | | | | | | | | | | | | | >> net/rds/ib_recv.c:382:28: sparse: incorrect type in initializer (different base types) net/rds/ib_recv.c:382:28: expected int [signed] can_wait net/rds/ib_recv.c:382:28: got restricted gfp_t net/rds/ib_recv.c:828:23: sparse: cast to restricted __le64 Reported-by: kbuild test robot <fengguang.wu@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | MAINTAINERS: update vmxnet3 driver maintainerShrikrishna Khare2015-08-251-1/+1
| | | | | | | | | | | | | | | | | | Shreyas Bhatewara would no longer maintain the vmxnet3 driver. Taking over the role of vmxnet3 maintainer. Signed-off-by: Shrikrishna Khare <skhare@vmware.com> Signed off-by: Shreyas Bhatewara <sbhatewara@vmware.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | vxlan: fix multiple inclusion of vxlan.hJiri Benc2015-08-251-1/+2
| | | | | | | | | | | | | | | | | | | | The vxlan_get_sk_family inline function was added after the last #endif, making multiple inclusion of net/vxlan.h fail. Move it to the proper place. Reported-by: Mark Rustad <mark.d.rustad@intel.com> Fixes: 705cc62f6728c ("vxlan: provide access function for vxlan socket address family") Signed-off-by: Jiri Benc <jbenc@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | MAINTAINERS: Add VRF entryDavid Ahern2015-08-251-0/+8
| | | | | | | | | | | | | | Add entry for new VRF device driver. Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | route: fix a use-after-freeWANG Cong2015-08-251-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes the following crash: general protection fault: 0000 [#1] SMP DEBUG_PAGEALLOC CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.2.0-rc7+ #166 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 task: ffff88010656d280 ti: ffff880106570000 task.ti: ffff880106570000 RIP: 0010:[<ffffffff8182f91b>] [<ffffffff8182f91b>] dst_destroy+0xa6/0xef RSP: 0018:ffff880107603e38 EFLAGS: 00010202 RAX: 0000000000000001 RBX: ffff8800d225a000 RCX: ffffffff82250fd0 RDX: 0000000000000001 RSI: ffffffff82250fd0 RDI: 6b6b6b6b6b6b6b6b RBP: ffff880107603e58 R08: 0000000000000001 R09: 0000000000000001 R10: 000000000000b530 R11: ffff880107609000 R12: 0000000000000000 R13: ffffffff82343c40 R14: 0000000000000000 R15: ffffffff8182fb4f FS: 0000000000000000(0000) GS:ffff880107600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007fcabd9d3000 CR3: 00000000d7279000 CR4: 00000000000006e0 Stack: ffffffff82250fd0 ffff8801077d6f00 ffffffff82253c40 ffff8800d225a000 ffff880107603e68 ffffffff8182fb5d ffff880107603f08 ffffffff810d795e ffffffff810d7648 ffff880106574000 ffff88010656d280 ffff88010656d280 Call Trace: <IRQ> [<ffffffff8182fb5d>] dst_destroy_rcu+0xe/0x1d [<ffffffff810d795e>] rcu_process_callbacks+0x618/0x7eb [<ffffffff810d7648>] ? rcu_process_callbacks+0x302/0x7eb [<ffffffff8182fb4f>] ? dst_gc_task+0x1eb/0x1eb [<ffffffff8107e11b>] __do_softirq+0x178/0x39f [<ffffffff8107e52e>] irq_exit+0x41/0x95 [<ffffffff81a4f215>] smp_apic_timer_interrupt+0x34/0x40 [<ffffffff81a4d5cd>] apic_timer_interrupt+0x6d/0x80 <EOI> [<ffffffff8100b968>] ? default_idle+0x21/0x32 [<ffffffff8100b966>] ? default_idle+0x1f/0x32 [<ffffffff8100bf19>] arch_cpu_idle+0xf/0x11 [<ffffffff810b0bc7>] default_idle_call+0x1f/0x21 [<ffffffff810b0dce>] cpu_startup_entry+0x1ad/0x273 [<ffffffff8102fe67>] start_secondary+0x135/0x156 dst is freed right before lwtstate_put(), this is not correct... Fixes: 61adedf3e3f1 ("route: move lwtunnel state to dst_entry") Acked-by: Jiri Benc <jbenc@redhat.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net-next: Fix warning while make xmldocs caused by skbuff.cMasanari Iida2015-08-251-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fix following warnings. .//net/core/skbuff.c:407: warning: No description found for parameter 'len' .//net/core/skbuff.c:407: warning: Excess function parameter 'length' description in '__netdev_alloc_skb' .//net/core/skbuff.c:476: warning: No description found for parameter 'len' .//net/core/skbuff.c:476: warning: Excess function parameter 'length' description in '__napi_alloc_skb' Signed-off-by: Masanari Iida <standby24x7@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ppp: implement x-netns supportGuillaume Nault2015-08-251-2/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Let packets move from one netns to the other at PPP encapsulation and decapsulation time. PPP units and channels remain in the netns in which they were originally created. Only the net_device may move to a different namespace. Cross netns handling is thus transparent to lower PPP layers (PPPoE, L2TP, etc.). PPP devices are automatically unregistered when their netns gets removed. So read() and poll() on the unit file descriptor will respectively receive EOF and POLLHUP. Channels aren't affected. Signed-off-by: Guillaume Nault <g.nault@alphalink.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: sun4i-emac: Claim emac sramHans de Goede2015-08-251-2/+11
| | | | | | | | | | | | | | | | Claim the emac sram ourselves, rather then relying on the bootloader having mapped the sram to the emac controller during boot. Signed-off-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | inetpeer: remove dead codeDavid Ahern2015-08-251-67/+0
| | | | | | | | | | | | | | Remove various inlined functions not referenced in the kernel. Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net/mlx5e: Avoid accessing NULL pointer at ndo_select_queueRana Shahout2015-08-253-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | To avoid multiply/division operations on the data path, we hold a {channel, tc}==>txq mapping table. We held this mapping table inside the channel object that is being destroyed upon some configuration operations (e.g MTU change). So in case ndo_select_queue occurs during such a configuration operation, it may access a NULL channel pointer, resulting in kernel panic. To fix this issue we moved the {channel, tc}==>txq mapping table outside the channel object so that it will be available also during such configuration operations. Signed-off-by: Rana Shahout <ranas@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | ah4: Fix error return in ah_input().David S. Miller2015-08-251-1/+3
| | | | | | | | | | | | Noticed by Herbert Xu. Signed-off-by: David S. Miller <davem@davemloft.net>
* | ah6: fix error return codeJulia Lawall2015-08-251-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Return a negative error code on failure. A simplified version of the semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) // <smpl> @@ identifier ret; expression e1,e2; @@ ( if (\(ret < 0\|ret != 0\)) { ... return ret; } | ret = 0 ) ... when != ret = e1 when != &ret *if(...) { ... when != ret = e2 when forall return ret; } // </smpl> Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
* | mlxsw: fix error return codeJulia Lawall2015-08-251-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Return a negative error code on failure. A simplified version of the semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) // <smpl> @@ identifier ret; expression e1,e2; @@ ( if (\(ret < 0\|ret != 0\)) { ... return ret; } | ret = 0 ) ... when != ret = e1 when != &ret *if(...) { ... when != ret = e2 when forall return ret; } // </smpl> Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | net: davinci_emac: fix error return codeJulia Lawall2015-08-251-1/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Propagate error code on failure. A simplified version of the semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) // <smpl> @@ identifier ret; expression e1,e2; @@ ( if (\(ret < 0\|ret != 0\)) { ... return ret; } | ret = 0 ) ... when != ret = e1 when != &ret *if(...) { ... when != ret = e2 when forall return ret; } // </smpl> Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr> Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge branch 'rds-assorted-bug-fixes'David S. Miller2015-08-2511-38/+153
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Santosh Shilimkar says: ==================== RDS: Assorted bug fixes We would like to improve RDS upstream support and in that context, I started playing with it. But run into number of issues including as basic is RDS IB RDMA doesn't work. As part of the debug, I ended up creating the $subject series which has bunch of assorted fixes. At least with this series I can run RDS IB RDMA and other tests successfully. Some of these fixes have been done by Chris Meson, Andy Grover and Zach Brown while at Oracle. There are still more kinks with FMR and error handling and I plan to address them in a follow up series. Series generated against Linus's master(v4.2-rc-7) but also applies against next-next cleanly. Its tested on Oracle hardware with IB fabric for both bcopy as well as RDMA mode. I don't have access to iWARP hardware so any testing help on iWARP hardware appreciated. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: check for valid cm_id before initiating connectionsantosh.shilimkar@oracle.com2015-08-251-2/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Connection could have been dropped while the route is being resolved so check for valid cm_id before initiating the connection. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: return EMSGSIZE for oversize requests before processing/queueingMukesh Kacker2015-08-251-5/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | rds_send_queue_rm() allows for the "current datagram" being queued to exceed SO_SNDBUF thresholds by checking bytes queued without counting in length of current datagram. (Since sk_sndbuf is set to twice requested SO_SNDBUF value as a kernel heuristic this is usually fine!) If this "current datagram" squeezing past the threshold is itself many times the size of the sk_sndbuf threshold itself then even twice the SO_SNDBUF does not save us and it gets queued but cannot be transmitted. Threads block and deadlock and device becomes unusable. The check for this datagram not exceeding SNDBUF thresholds (EMSGSIZE) is not done on this datagram as that check is only done if queueing attempt fails. (Datagrams that follow this datagram fail queueing attempts, go through the check and eventually trip EMSGSIZE error but zero length datagrams silently fail!) This fix moves the check for datagrams exceeding SNDBUF limits before any processing or queueing is attempted and returns EMSGSIZE early in the rds_sndmsg() code. This change also ensures that all datagrams get checked for exceeding SNDBUF/sk_sndbuf size limits and the large datagrams that exceed those limits do not get to rds_send_queue_rm() code for processing. Signed-off-by: Mukesh Kacker <mukesh.kacker@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: make sure rds_send_drop_to properly takes the m_rs_locksantosh.shilimkar@oracle.com2015-08-251-1/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | rds_send_drop_to() is used during socket tear down to find all the messages on the socket and flush them . It can race with the acking code unless it takes the m_rs_lock on each and every message. This plugs a hole where we didn't take m_rs_lock on any message that didn't have the RDS_MSG_ON_CONN set. Taking m_rs_lock avoids double frees and other memory corruptions as the ack code trusts the message m_rs pointer on a socket that had actually been freed. We must take m_rs_lock to access m_rs. Because of lock nesting and rs access, we also need to acquire rs_lock. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: Don't destroy the rdma id until after we're done using itSantosh Shilimkar2015-08-251-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | During connection resets, we are destroying the rdma id too soon. We can't destroy it when it is still in use. So lets move rdma_destroy_id() after we clear the rings. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: Fix assertion level from fatal to warningsantosh.shilimkar@oracle.com2015-08-252-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fix the asserion level since its not fatal and can be hit in normal execution paths. There is no need to take the system down. We keep the WARN_ON() to detect the condition if we get here with bad pages. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: Make sure we do a signaled send for large-sendsantosh.shilimkar@oracle.com2015-08-251-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | WR(Work Requests )always generate a WC(Work Completion) with signaled send. Default RDS ib code is setup for un-signaled completion. Since RDS connction is persistent, we can end up sending the data even after large-send when the remote end is not active(for any reason). By doing a signaled send at least once per large-send, we can at least detect the problem in work completion handler there by avoiding sending more data to inactive remote. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: Mark message mapped before transmitsantosh.shilimkar@oracle.com2015-08-251-8/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | rds_send_xmit() marks the rds message map flag after xmit_[rdma/atomic]() which is clearly wrong. We need to maintain the ownership between transport and rds. Also take care of error path. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: add a sock_destruct callback debug aidsantosh.shilimkar@oracle.com2015-08-251-0/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This helps to detect the accidental processes/apps trying to destroy the RDS socket which they are sharing with other processes/apps. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: check for congestion updates during rds_send_xmitsantosh.shilimkar@oracle.com2015-08-251-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | Ensure we don't keep sending the data if the link is congested. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: make sure we post recv bufferssantosh.shilimkar@oracle.com2015-08-255-8/+57
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If we get an ENOMEM during rds_ib_recv_refill, we might never come back and refill again later. Patch makes sure to kick krdsd into helping out. To achieve this we add RDS_RECV_REFILL flag and update in the refill path based on that so that at least some therad will keep posting receive buffers. Since krdsd and softirq both might race for refill, we decide to schedule on work queue based on ring_low instead of ring_empty. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: don't update ip address tables if the address hasn't changedsantosh.shilimkar@oracle.com2015-08-251-2/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the ip address tables hasn't changed, there is no need to remove them only to be added back again. Lets fix it. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: destroy the ib state earlier during shutdownsantosh.shilimkar@oracle.com2015-08-251-8/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Destroy ib state early during shutdown. Otherwise we can get callbacks after the QP isn't really able to handle them. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: always free recv frag as we free its ring entrysantosh.shilimkar@oracle.com2015-08-251-3/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We were still seeing rare occurrences of the WARN_ON(recv->r_frag) which indicates that the recv refill path was finding allocated frags in ring entries that were marked free. These were usually followed by OOM crashes. They only seem to be occurring in the presence of completion errors and connection resets. This patch ensures that we free the frag as we mark the ring entry free. This should stop the refill path from finding allocated frags in ring entries that were marked free. Reviewed-by: Ajaykumar Hotchandani <ajaykumar.hotchandani@oracle.com> Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | RDS: restore return value in rds_cmsg_rdma_args()santosh.shilimkar@oracle.com2015-08-251-0/+2
|/ / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In rds_cmsg_rdma_args() 'ret' is used by rds_pin_pages() which returns number of pinned pages on success. And the same value is returned to the caller of rds_cmsg_rdma_args() on success which is not intended. Commit f4a3fc03c1d7 ("RDS: Clean up error handling in rds_cmsg_rdma_args") removed the 'ret = 0' line which broke RDS RDMA mode. Fix it by restoring the return value on rds_pin_pages() success keeping the clean-up in place. Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-12 08:02:20 +0000