- 12 Oct, 2012 40 commits
-
-
Francois Romieu authored
commit 811fd301 upstream. Realtek has specified that the post 8168c gigabit chips and the post 8105e fast ethernet chips recover automatically from a Rx FIFO overflow. The driver does not need to clear the RxFIFOOver bit of IntrStatus and it should rather avoid messing it. The implementation deserves some explanation: 1. events outside of the intr_event bit mask are now ignored. It enforces a no-processing policy for the events that either should not be there or should be ignored. 2. RxFIFOOver was already ignored in rtl_cfg_infos[RTL_CFG_1] for the whole 8168 line of chips with two exceptions: - RTL_GIGA_MAC_VER_22 since b5ba6d12 ("use RxFIFO overflow workaround for 8168c chipset."). This one should now be correctly handled. - RTL_GIGA_MAC_VER_11 (8168b) which requires a different Rx FIFO overflow processing. Though it does not conform to Realtek suggestion above, the updated driver includes no change for RTL_GIGA_MAC_VER_12 and RTL_GIGA_MAC_VER_17. Both are 8168b. RTL_GIGA_MAC_VER_12 is common and a bit old so I'd rather wait for experimental evidence that the change suggested by Realtek really helps or does not hurt in unexpected ways. Removed case statements in rtl8169_interrupt are only 8168 relevant. 3. RxFIFOOver is masked for post 8105e 810x chips, namely the sole 8105e (RTL_GIGA_MAC_VER_30) itself. Signed-off-by:
Francois Romieu <romieu@fr.zoreil.com> Cc: hayeswang <hayeswang@realtek.com> Signed-off-by:
David S. Miller <davem@davemloft.net> Reviewed-by:
Jonathan Nieder <jrnieder@gmail.com> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
hayeswang authored
commit 10953db8 upstream The link down would occur when reseting PHY. And it would take about 2 ~ 5 seconds from link down to link up. If the delay of pm_schedule_suspend is not long enough, the device would enter runtime_suspend before link up. After link up, the device would wake up and reset PHY again. Then, you would find the driver keep in a loop of runtime_suspend and rumtime_resume. Signed-off-by:
Hayes Wang <hayeswang@realtek.com> Acked-by:
-
Francois Romieu authored
commit deb9d93c upstream. 8168d and above allow jumbo frames beyond 8k. Bump the received packet length check before enabling jumbo frames on these chipsets. Frame length indication covers bits 0..13 of the first Rx descriptor 32 bits for the 8169 and 8168. I only have authoritative documentation for the allowed use of the extra (13) bit with the 8169 and 8168c. Realtek's drivers use the same mask for the 816x and the fast ethernet only 810x. Signed-off-by:
-
Francois Romieu authored
commit d58d46b5 upstream. - fix features : jumbo frames and checksumming can not be used at the same time. - introduce hw_jumbo_{enable / disable} helpers. Their content has been creatively extracted from Realtek's own drivers. As an illustration, it would be nice to know how/if the MaxTxPacketSize register operates when the device can work with a 9k jumbo frame as its documentation (8168c) can not be applied beyond ~7k. - rtl_tx_performance_tweak is moved forward. No change. Signed-off-by:
-
Francois Romieu authored
commit e03f33af upstream. When set, RxFOVF (resp. RxBOVF) is always 1 (resp. 0). Signed-off-by:
-
Hayes Wang authored
commit aaa89c08 upstream. Only 8111b needs to enable rx when shutdowning with WoL. Signed-off-by:
-
Hayes Wang authored
commit d4ed95d7 upstream. Only 8111E needs enable RxConfig bit 0 ~ 3 when suspending or shutdowning for wake on lan. Signed-off-by:
-
Paul E. McKenney authored
commit a10d206e upstream. Each grace period is supposed to have at least one callback waiting for that grace period to complete. However, if CONFIG_NO_HZ=n, an extra callback-free grace period is no big problem -- it will chew up a tiny bit of CPU time, but it will complete normally. In contrast, CONFIG_NO_HZ=y kernels have the potential for all the CPUs to go to sleep indefinitely, in turn indefinitely delaying completion of the callback-free grace period. Given that nothing is waiting on this grace period, this is also not a problem. That is, unless RCU CPU stall warnings are also enabled, as they are in recent kernels. In this case, if a CPU wakes up after at least one minute of inactivity, an RCU CPU stall warning will result. The reason that no one noticed until quite recently is that most systems have enough OS noise that they will never remain absolutely idle for a full minute. But there are some embedded systems with cut-down userspace configurations that consistently get into this situation. All this begs the question of exactly how a callback-free grace period gets started in the first place. This can happen due to the fact that CPUs do not necessarily agree on which grace period is in progress. If a CPU still believes that the grace period that just completed is still ongoing, it will believe that it has callbacks that need to wait for another grace period, never mind the fact that the grace period that they were waiting for just completed. This CPU can therefore erroneously decide to start a new grace period. Note that this can happen in TREE_RCU and TREE_PREEMPT_RCU even on a single-CPU system: Deadlock considerations mean that the CPU that detected the end of the grace period is not necessarily officially informed of this fact for some time. Once this CPU notices that the earlier grace period completed, it will invoke its callbacks. It then won't have any callbacks left. If no other CPU has any callbacks, we now have a callback-free grace period. This commit therefore makes CPUs check more carefully before starting a new grace period. This new check relies on an array of tail pointers into each CPU's list of callbacks. If the CPU is up to date on which grace periods have completed, it checks to see if any callbacks follow the RCU_DONE_TAIL segment, otherwise it checks to see if any callbacks follow the RCU_WAIT_TAIL segment. The reason that this works is that the RCU_WAIT_TAIL segment will be promoted to the RCU_DONE_TAIL segment as soon as the CPU is officially notified that the old grace period has ended. This change is to cpu_needs_another_gp(), which is called in a number of places. The only one that really matters is in rcu_start_gp(), where the root rcu_node structure's ->lock is held, which prevents any other CPU from starting or completing a grace period, so that the comparison that determines whether the CPU is missing the completion of a grace period is stable. Reported-by:
Becky Bruce <bgillbruce@gmail.com> Reported-by:
Subodh Nijsure <snijsure@grid-net.com> Reported-by:
Paul Walmsley <paul@pwsan.com> Signed-off-by:
Paul E. McKenney <paul.mckenney@linaro.org> Signed-off-by:
Paul E. McKenney <paulmck@linux.vnet.ibm.com> Tested-by:
-
Alex Deucher authored
commit fb6ca6d1 upstream. There are so many quirks, lets just try and force this for all RS690s. See: https://bugs.freedesktop.org/show_bug.cgi?id=37679Signed-off-by:
Alex Deucher <alexander.deucher@amd.com> Signed-off-by:
-
Alex Deucher authored
commit 3a6d59df upstream. Fixes another system on: https://bugs.freedesktop.org/show_bug.cgi?id=37679Signed-off-by:
-
Alex Deucher authored
commit 2e3b3b10 upstream. SI asics store voltage information differently so we don't have a way to deal with it properly yet. Signed-off-by:
-
Marko Friedemann authored
commit c05fce58 upstream. Added support for Xbox Communicator to USB quirks. Signed-off-by:
Marko Friedemann <mfr@bmx-chemnitz.de> Signed-off-by:
Takashi Iwai <tiwai@suse.de> Signed-off-by:
-
David Henningsson authored
commit c1051439 upstream. While going through Ubuntu bugs, I discovered this patch being posted and a confirmation that the patch works as expected. Finding out how the hw volume really works would be preferrable to just disabling the broken one, but this would be better than nothing. Credit: sndfnsdfin (qawsnews) BugLink: https://bugs.launchpad.net/bugs/559939Signed-off-by:
David Henningsson <david.henningsson@canonical.com> Signed-off-by:
-
Omair Mohammed Abdullah authored
commit d4f1e48b upstream. When the loopback timer handler is running, calling del_timer() (for STOP trigger) will not wait for the handler to complete before deactivating the timer. The timer gets rescheduled in the handler as usual. Then a subsequent START trigger will try to start the timer using add_timer() with a timer pending leading to a kernel panic. Serialize the calls to add_timer() and del_timer() using a spin lock to avoid this. Signed-off-by:
Omair Mohammed Abdullah <omair.m.abdullah@linux.intel.com> Signed-off-by:
Vinod Koul <vinod.koul@linux.intel.com> Signed-off-by:
-
Andrea Arcangeli authored
commit 027ef6c8 upstream. In many places !pmd_present has been converted to pmd_none. For pmds that's equivalent and pmd_none is quicker so using pmd_none is better. However (unless we delete pmd_present) we should provide an accurate pmd_present too. This will avoid the risk of code thinking the pmd is non present because it's under __split_huge_page_map, see the pmd_mknotpresent there and the comment above it. If the page has been mprotected as PROT_NONE, it would also lead to a pmd_present false negative in the same way as the race with split_huge_page. Because the PSE bit stays on at all times (both during split_huge_page and when the _PAGE_PROTNONE bit get set), we could only check for the PSE bit, but checking the PROTNONE bit too is still good to remember pmd_present must always keep PROT_NONE into account. This explains a not reproducible BUG_ON that was seldom reported on the lists. The same issue is in pmd_large, it would go wrong with both PROT_NONE and if it races with split_huge_page. Signed-off-by:
Andrea Arcangeli <aarcange@redhat.com> Acked-by:
Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mgorman@suse.de> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by:
-
Hugh Dickins authored
commit ec4d9f62 upstream. In fuzzing with trinity, lockdep protested "possible irq lock inversion dependency detected" when isolate_lru_page() reenabled interrupts while still holding the supposedly irq-safe tree_lock: invalidate_inode_pages2 invalidate_complete_page2 spin_lock_irq(&mapping->tree_lock) clear_page_mlock isolate_lru_page spin_unlock_irq(&zone->lru_lock) isolate_lru_page() is correct to enable interrupts unconditionally: invalidate_complete_page2() is incorrect to call clear_page_mlock() while holding tree_lock, which is supposed to nest inside lru_lock. Both truncate_complete_page() and invalidate_complete_page() call clear_page_mlock() before taking tree_lock to remove page from radix_tree. I guess invalidate_complete_page2() preferred to test PageDirty (again) under tree_lock before committing to the munlock; but since the page has already been unmapped, its state is already somewhat inconsistent, and no worse if clear_page_mlock() moved up. Reported-by:
Sasha Levin <levinsasha928@gmail.com> Deciphered-by:
Hugh Dickins <hughd@google.com> Acked-by:
Mel Gorman <mel@csn.ul.ie> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Cc: Ying Han <yinghan@google.com> Signed-off-by:
-
Mark Brown authored
commit 689185b7 upstream. Help UIs associate it with the matching gain control. Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
-
Jan Kara authored
commit b71fc079 upstream. Code tracking when transaction needs to be committed on fdatasync(2) forgets to handle a situation when only inode's i_size is changed. Thus in such situations fdatasync(2) doesn't force transaction with new i_size to disk and that can result in wrong i_size after a crash. Fix the issue by updating inode's i_datasync_tid whenever its size is updated. Reported-by:
Kristian Nielsen <knielsen@knielsen-hq.org> Signed-off-by:
Jan Kara <jack@suse.cz> Signed-off-by:
-
Bernd Schubert authored
commit 6a08f447 upstream. ext4_special_inode_operations have their own ifdef CONFIG_EXT4_FS_XATTR to mask those methods. And ext4_iget also always sets it, so there is an inconsistency. Signed-off-by:
Bernd Schubert <bernd.schubert@itwm.fraunhofer.de> Signed-off-by:
"Theodore Ts'o" <tytso@mit.edu> Signed-off-by:
-
Dmitry Monakhov authored
commit f066055a upstream. Proper block swap for inodes with full journaling enabled is truly non obvious task. In order to be on a safe side let's explicitly disable it for now. Signed-off-by:
Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by:
-
Yinghai Lu authored
commit 1965f66e upstream. For bridges with "secondary > subordinate", i.e., invalid bus number apertures, we don't enumerate anything behind the bridge unless the user specified "pci=assign-busses". This patch makes us automatically try to reassign the downstream bus numbers in this case (just for that bridge, not for all bridges as "pci=assign-busses" does). We don't discover all the devices on the Intel DP43BF motherboard without this change (or "pci=assign-busses") because its BIOS configures a bridge as: pci 0000:00:1e.0: PCI bridge to [bus 20-08] (subtractive decode) [bhelgaas: changelog, change message to dev_info] Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=18412 Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=625754Reported-by:
Brian C. Huffman <bhuffman@graze.net> Reported-by:
VL <vl.homutov@gmail.com> Tested-by:
Yinghai Lu <yinghai@kernel.org> Signed-off-by:
Bjorn Helgaas <bhelgaas@google.com>
-
Martin Peschke authored
commit d436de8c upstream. __scsi_remove_device (e.g. due to dev_loss_tmo) calls zfcp_scsi_slave_destroy which in turn sends a close LUN FSF request to the adapter. After 30 seconds without response, zfcp_erp_timeout_handler kicks the ERP thread failing the close LUN ERP action. zfcp_erp_wait in zfcp_erp_lun_shutdown_wait and thus zfcp_scsi_slave_destroy returns and then scsi_device is no longer valid. Sometime later the response to the close LUN FSF request may finally come in. However, commit b62a8d9b "[SCSI] zfcp: Use SCSI device data zfcp_scsi_dev instead of zfcp_unit" introduced a number of attempts to unconditionally access struct zfcp_scsi_dev through struct scsi_device causing a use-after-free. This leads to an Oops due to kernel page fault in one of: zfcp_fsf_abort_fcp_command_handler, zfcp_fsf_open_lun_handler, zfcp_fsf_close_lun_handler, zfcp_fsf_req_trace, zfcp_fsf_fcp_handler_common. Move dereferencing of zfcp private data zfcp_scsi_dev allocated in scsi_device via scsi_transport_reserve_device after the check for potentially aborted FSF request and thus no longer valid scsi_device. Only then assign sdev_to_zfcp(sdev) to the local auto variable struct zfcp_scsi_dev *zfcp_sdev. Signed-off-by:
Martin Peschke <mpeschke@linux.vnet.ibm.com> Signed-off-by:
Steffen Maier <maier@linux.vnet.ibm.com> Signed-off-by:
James Bottomley <JBottomley@Parallels.com> Signed-off-by:
-
Steffen Maier authored
commit d99b601b upstream. Upstream commit f3450c7b "[SCSI] zfcp: Replace local reference counting with common kref" accidentally dropped a reference count check before tearing down zfcp_ports that are potentially in use by zfcp_units. Even remote ports in use can be removed causing unreachable garbage objects zfcp_ports with zfcp_units. Thus units won't come back even after a manual port_rescan. The kref of zfcp_port->dev.kobj is already used by the driver core. We cannot re-use it to track the number of zfcp_units. Re-introduce our own counter for units per port and check on port_remove. Signed-off-by:
Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by:
-
Julia Lawall authored
commit ca579c9f upstream. If list_for_each_entry, etc complete a traversal of the list, the iterator variable ends up pointing to an address at an offset from the list head, and not a meaningful structure. Thus this value should not be used after the end of the iterator. Replace port->adapter->scsi_host by adapter->scsi_host. This problem was found using Coccinelle (http://coccinelle.lip6.fr/). Oversight in upsteam commit of v2.6.37 a1ca4831 "[SCSI] zfcp: Move ACL/CFDC code to zfcp_cfdc.c" which merged the content of zfcp_erp_port_access_changed(). Signed-off-by:
Julia Lawall <Julia.Lawall@lip6.fr> Signed-off-by:
-
Steffen Maier authored
commit cb452149 upstream. If the mapping of FCP device bus ID and corresponding subchannel is modified while the Linux image is suspended, the resume of FCP devices can fail. During resume, zfcp gets callbacks from cio regarding the modified subchannels but they can be arbitrarily mixed with the restore/resume callback. Since the cio callbacks would trigger adapter recovery, zfcp could wakeup before the resume callback. Therefore, ignore the cio callbacks regarding subchannels while being suspended. We can safely do so, since zfcp does not deal itself with subchannels. For problem determination purposes, we still trace the ignored callback events. The following kernel messages could be seen on resume: kernel: <WWPN>: parent <FCP device bus ID> should not be sleeping As part of adapter reopen recovery, zfcp performs auto port scanning which can erroneously try to register new remote ports with scsi_transport_fc and the device core code complains about the parent (adapter) still sleeping. kernel: zfcp.3dff9c: <FCP device bus ID>:\ Setting up the QDIO connection to the FCP adapter failed <last kernel message repeated 3 more times> kernel: zfcp.574d43: <FCP device bus ID>:\ ERP cannot recover an error on the FCP device In such cases, the adapter gave up recovery and remained blocked along with its child objects: remote ports and LUNs/scsi devices. Even the adapter shutdown as part of giving up recovery failed because the ccw device state remained disconnected. Later, the corresponding remote ports ran into dev_loss_tmo. As a result, the LUNs were erroneously not available again after resume. Even a manually triggered adapter recovery (e.g. sysfs attribute failed, or device offline/online via sysfs) could not recover the adapter due to the remaining disconnected state of the corresponding ccw device. Signed-off-by:
-
Steffen Maier authored
commit 0100998d upstream. Duplicate fssrh_2 from a54ca0f6 "[SCSI] zfcp: Redesign of the debug tracing for HBA records." complicates distinction of generic status read response from local link up. Duplicate fsscth1 from 2c55b750 "[SCSI] zfcp: Redesign of the debug tracing for SAN records." complicates distinction of good common transport response from invalid port handle. Signed-off-by:
-
Matt Carlson authored
[ Upstream commit cf9ecf4b ] On the earliest TSO capable devices, TSO was accomplished through firmware. The TSO cannot coexist with ASF management firmware though. The tg3 driver determines whether or not ASF is enabled by calling tg3_get_eeprom_hw_cfg(), which checks a particular bit of NIC memory. Commit dabc5c67, entitled "tg3: Move TSO_CAPABLE assignment", accidentally moved the code that determines TSO capabilities earlier than the call to tg3_get_eeprom_hw_cfg(). As a consequence, the driver was attempting to determine TSO capabilities before it had all the data it needed to make the decision. This patch fixes the problem by revisiting and reevaluating the decision after tg3_get_eeprom_hw_cfg() is called. Signed-off-by:
Matt Carlson <mcarlson@broadcom.com> Signed-off-by:
Michael Chan <mchan@broadcom.com> Signed-off-by:
-
Ed Cashin authored
[ Upstream commit 8babe8cc ] In order for the network layer to see that AoE requires no checksumming in a generic way, the packets must be marked as requiring no checksum, so we make this requirement explicit with the assertion. Signed-off-by:
Ed Cashin <ecashin@coraid.com> Signed-off-by:
-
Ed Cashin authored
[ Upstream commit c0d680e5 ] A change in a series of VLAN-related changes appears to have inadvertently disabled the use of the scatter gather feature of network cards for transmission of non-IP ethernet protocols like ATA over Ethernet (AoE). Below is a reference to the commit that introduces a "harmonize_features" function that turns off scatter gather when the NIC does not support hardware checksumming for the ethernet protocol of an sk buff. commit f01a5236 Author: Jesse Gross <jesse@nicira.com> Date: Sun Jan 9 06:23:31 2011 +0000 net offloading: Generalize netif_get_vlan_features(). The can_checksum_protocol function is not equipped to consider a protocol that does not require checksumming. Calling it for a protocol that requires no checksum is inappropriate. The patch below has harmonize_features call can_checksum_protocol when the protocol needs a checksum, so that the network layer is not forced to perform unnecessary skb linearization on the transmission of AoE packets. Unnecessary linearization results in decreased performance and increased memory pressure, as reported here: http://www.spinics.net/lists/linux-mm/msg15184.html The problem has probably not been widely experienced yet, because only recently has the kernel.org-distributed aoe driver acquired the ability to use payloads of over a page in size, with the patchset recently included in the mm tree: https://lkml.org/lkml/2012/8/28/140 The coraid.com-distributed aoe driver already could use payloads of greater than a page in size, but its users generally do not use the newest kernels. Signed-off-by:
-
Alan Cox authored
[ Upstream commit 6cf5c951 ] Check for an error from this and if so bail properly. Signed-off-by:
Alan Cox <alan@linux.intel.com> Signed-off-by:
-
Eric Dumazet authored
[ Upstream commit c0cc88a7 ] While investigating l2tp bug, I hit a bug in eth_type_trans(), because not enough bytes were pulled in skb head. Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Eric Dumazet authored
[ Upstream commit 96af69ea ] mip6_mh_filter() should not modify its input, or else its caller would need to recompute ipv6_hdr() if skb->head is reallocated. Use skb_header_pointer() instead of pskb_may_pull() Signed-off-by:
-
Eric Dumazet authored
[ Upstream commit 1b05c4b5 ] icmpv6_filter() should not modify its input, or else its caller would need to recompute ipv6_hdr() if skb->head is reallocated. Use skb_header_pointer() instead of pskb_may_pull() and change the prototype to make clear both sk and skb are const. Also, if icmpv6 header cannot be found, do not deliver the packet, as we do in IPv4. Signed-off-by:
-
Eric Dumazet authored
[ Upstream commit ab43ed8b ] icmp_filter() should not modify its input, or else its caller would need to recompute ip_hdr() if skb->head is reallocated. Use skb_header_pointer() instead of pskb_may_pull() and change the prototype to make clear both sk and skb are const. Signed-off-by:
-
Eric Dumazet authored
[ Upstream commit 3e10986d ] Its possible to use RAW sockets to get a crash in tcp_set_keepalive() / sk_reset_timer() Fix is to make sure socket is a SOCK_STREAM one. Reported-by:
Dave Jones <davej@redhat.com> Signed-off-by:
-
Chema Gonzalez authored
[ Upstream commit 68622342 ] In the current rxhash calculation function, while the sorting of the ports/addrs is coherent (you get the same rxhash for packets sharing the same 4-tuple, in both directions), ports and addrs are sorted independently. This implies packets from a connection between the same addresses but crossed ports hash to the same rxhash. For example, traffic between A=S:l and B=L:s is hashed (in both directions) from {L, S, {s, l}}. The same rxhash is obtained for packets between C=S:s and D=L:l. This patch ensures that you either swap both addrs and ports, or you swap none. Traffic between A and B, and traffic between C and D, get their rxhash from different sources ({L, S, {l, s}} for A<->B, and {L, S, {s, l}} for C<->D) The patch is co-written with Eric Dumazet <edumazet@google.com> Signed-off-by:
Chema Gonzalez <chema@google.com> Signed-off-by:
-
Xiaodong Xu authored
[ Upstream commit 2b018d57 ] When PPPOE is running over a virtual ethernet interface (e.g., a bonding interface) and the user tries to delete the interface in case the PPPOE state is ZOMBIE, the kernel will loop forever while unregistering net_device for the reference count is not decreased to zero which should have been done with dev_put(). Signed-off-by:
Xiaodong Xu <stid.smth@gmail.com> Signed-off-by:
-
Thomas Graf authored
[ Upstream commit 4c3a5bda ] SCTP charges wmem_alloc via sctp_set_owner_w() in sctp_sendmsg() and via skb_set_owner_w() in sctp_packet_transmit(). If a sender runs out of sndbuf it will sleep in sctp_wait_for_sndbuf() and expects to be waken up by __sctp_write_space(). Buffer space charged via sctp_set_owner_w() is released in sctp_wfree() which calls __sctp_write_space() directly. Buffer space charged via skb_set_owner_w() is released via sock_wfree() which calls sk->sk_write_space() _if_ SOCK_USE_WRITE_QUEUE is not set. sctp_endpoint_init() sets SOCK_USE_WRITE_QUEUE on all sockets. Therefore if sctp_packet_transmit() manages to queue up more than sndbuf bytes, sctp_wait_for_sndbuf() will never be woken up again unless it is interrupted by a signal. This could be fixed by clearing the SOCK_USE_WRITE_QUEUE flag but ... Charging for the data twice does not make sense in the first place, it leads to overcharging sndbuf by a factor 2. Therefore this patch only charges a single byte in wmem_alloc when transmitting an SCTP packet to ensure that the socket stays alive until the packet has been released. This means that control chunks are no longer accounted for in wmem_alloc which I believe is not a problem as skb->truesize will typically lead to overcharging anyway and thus compensates for any control overhead. Signed-off-by:
Thomas Graf <tgraf@suug.ch> CC: Vlad Yasevich <vyasevic@redhat.com> CC: Neil Horman <nhorman@tuxdriver.com> CC: David Miller <davem@davemloft.net> Acked-by:
Vlad Yasevich <vyasevich@gmail.com> Signed-off-by:
-
Michal Kubeček authored
[ Upstream commit 15c04175 ] If recv() syscall is called for a TCP socket so that - IOAT DMA is used - MSG_WAITALL flag is used - requested length is bigger than sk_rcvbuf - enough data has already arrived to bring rcv_wnd to zero then when tcp_recvmsg() gets to calling sk_wait_data(), receive window can be still zero while sk_async_wait_queue exhausts enough space to keep it zero. As this queue isn't cleaned until the tcp_service_net_dma() call, sk_wait_data() cannot receive any data and blocks forever. If zero receive window and non-empty sk_async_wait_queue is detected before calling sk_wait_data(), process the queue first. Signed-off-by:
Michal Kubecek <mkubecek@suse.cz> Signed-off-by:
-
Gao feng authored
[ Upstream commit 6825a26c ] as we hold dst_entry before we call __ip6_del_rt, so we should alse call dst_release not only return -ENOENT when the rt6_info is ip6_null_entry. and we already hold the dst entry, so I think it's safe to call dst_release out of the write-read lock. Signed-off-by:
Gao feng <gaofeng@cn.fujitsu.com> Signed-off-by:
-
