aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2016-06-24drm/atomic: Make drm_atomic_legacy_backoff reset crtc->acquire_ctxMaarten Lankhorst1-1/+26
Atomic updates may acquire more state than initially locked through drm_modeset_lock_crtc, running with heavy stress can cause a WARN_ON(crtc->acquire_ctx) in drm_modeset_lock_crtc: [ 601.491296] ------------[ cut here ]------------ [ 601.491366] WARNING: CPU: 0 PID: 2411 at drivers/gpu/drm/drm_modeset_lock.c:191 drm_modeset_lock_crtc+0xeb/0xf0 [drm] [ 601.491369] Modules linked in: drm i915 drm_kms_helper [ 601.491414] CPU: 0 PID: 2411 Comm: kms_cursor_lega Tainted: G U 4.7.0-rc4-patser+ #4798 [ 601.491417] Hardware name: Intel Corporation Skylake Client [ 601.491420] 0000000000000000 ffff88044d153c98 ffffffff812ead28 0000000000000000 [ 601.491425] 0000000000000000 ffff88044d153cd8 ffffffff810868e6 000000bf58058030 [ 601.491431] ffff880088b415e8 ffff880458058030 ffff88008a271548 ffff88008a271568 [ 601.491436] Call Trace: [ 601.491443] [<ffffffff812ead28>] dump_stack+0x4d/0x65 [ 601.491447] [<ffffffff810868e6>] __warn+0xc6/0xe0 [ 601.491452] [<ffffffff81086968>] warn_slowpath_null+0x18/0x20 [ 601.491472] [<ffffffffc00d4ffb>] drm_modeset_lock_crtc+0xeb/0xf0 [drm] [ 601.491491] [<ffffffffc00c5526>] drm_mode_cursor_common+0x66/0x180 [drm] [ 601.491509] [<ffffffffc00c91cc>] drm_mode_cursor_ioctl+0x3c/0x40 [drm] [ 601.491524] [<ffffffffc00bc94d>] drm_ioctl+0x14d/0x530 [drm] [ 601.491540] [<ffffffffc00c9190>] ? drm_mode_setcrtc+0x520/0x520 [drm] [ 601.491545] [<ffffffff81176aeb>] ? handle_mm_fault+0x106b/0x1430 [ 601.491550] [<ffffffff81108441>] ? stop_one_cpu+0x61/0x70 [ 601.491556] [<ffffffff811bb71d>] do_vfs_ioctl+0x8d/0x570 [ 601.491560] [<ffffffff81290d7e>] ? security_file_ioctl+0x3e/0x60 [ 601.491565] [<ffffffff811bbc74>] SyS_ioctl+0x74/0x80 [ 601.491571] [<ffffffff810e321c>] ? posix_get_monotonic_raw+0xc/0x10 [ 601.491576] [<ffffffff8175b11b>] entry_SYSCALL_64_fastpath+0x13/0x8f [ 601.491581] ---[ end trace 56f3d3d85f000d00 ]--- For good measure, test mode_config.acquire_ctx too, although this should never happen. Testcase: kms_cursor_legacy Signed-off-by: Maarten Lankhorst <[email protected]> Reviewed-by: Daniel Vetter <[email protected]> Cc: [email protected] Signed-off-by: Dave Airlie <[email protected]>
2016-06-24Merge tag 'topic/drm-misc-2016-06-22-updated' of ↵Dave Airlie109-4862/+4018
git://anongit.freedesktop.org/drm-intel into drm-next Again a pile of things all over - Conversion to rst from docbook from Jani. Looks real pretty, and the source is now actually readable (compared to horrible, horrible docbook xml)! https://01.org/linuxgraphics/gfx-docs/drm/ - device register/unregister rework from Chris, with follow-up work from Benjamin. Allows more drivers to demidlayer load/unload and others to remove a bit of boilerplate. - master/auth related cleanup, with docs - some dma-buf polish, merged by Sumit - small stuff all over (like build fixes from Arnd) Group maintainership seems to slowly take off, with both Thierry and Sumit pushing a few things. No hiccups thus far. * tag 'topic/drm-misc-2016-06-22-updated' of git://anongit.freedesktop.org/drm-intel: (68 commits) drm/vc4: Remove unused connector drm/fb-helper: Reduce READ_ONCE(master) to lockless_dereference drm/sun4i: Remove open-coded drm_connector_register_all() drm/vc4: Remove open-coded drm_connector_register_all() drm/atmel-hlcdc: Remove redundant call to drm_connector_unregister_all() drm: document drm_auth.c drm: Clear up master tracking booleans drm: Extract drm_is_current_master drm: Refactor drop/set master code a bit drm: Lobotomize set_busid nonsense for !pci drivers drm: Nuke SET_UNIQUE ioctl drm: Don't call drm_dev_set_unique from platform drivers drm/vgem: Stop calling drm_drv_set_unique drm: Use dev->name as fallback for dev->unique drm: Clean up drm_crtc.h drm: Move master pointer from drm_minor to drm_device drm: sti: rework init sequence drm: sti: use late_register and early_unregister callbacks drm/amdkfd: Clean up inline handling drm: Add callbacks for late registering ...
2016-06-24Merge branch 'drm-fixes-4.7' of git://people.freedesktop.org/~agd5f/linux ↵Dave Airlie20-157/+461
into drm-fixes A bit bigger than I would normally like, but most of the large changes are for polaris support and since polaris went upstream in 4.7, I'd like to get the fixes in so it's in good shape when the hw becomes available. The major changes only touch the polaris code so there is little chance for regressions on other asics. The rest are just the usual collection of bug fixes. * 'drm-fixes-4.7' of git://people.freedesktop.org/~agd5f/linux: drm/amd/powerplay: enable clock stretch feature for polaris drm/amdgpu/gfx8: update golden setting for polaris10 drm/amd/powerplay: enable avfs feature for polaris drm/amdgpu/atombios: add avfs struct for Polaris10/11 drm/amd/powerplay: add avfs related define for polaris drm/amd/powrplay: enable stutter_mode for polaris. drm/amd/powerplay: disable UVD SMU handshake for MCLK. drm/amd/powerplay: initialize variables which were missed. drm/amd/powerplay: enable PowerContainment feature for polaris10/11. drm/amd/powerplay: need to notify system bios pcie device ready drm/amd/powerplay: fix bug that function parameter was incorect. drm/amd/powerplay: fix logic error. drm/amdgpu: initialize amdgpu_cgs_acpi_eval_object result value drm/amdgpu: precedence bug in amdgpu_device_init() drm/amdgpu: fix num_rbs exposed to userspace (v2) drm/amdgpu: missing bounds check in amdgpu_set_pp_force_state()
2016-06-24Merge tag 'drm-sii902x' of github.com:bbrezillon/linux-at91 into drm-nextDave Airlie4-0/+511
Add basic support for the sii902x RGB -> HDMI bridge. * tag 'drm-sii902x' of github.com:bbrezillon/linux-at91: drm/bridge: Add sii902x DT bindings doc drm/bridge: Add sii902x driver
2016-06-24Merge branch 'exynos-drm-fixes' of ↵Dave Airlie6-16/+10
git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos into drm-fixes Since HW trigger mode was suppoted we have faced with a issue that Display panel didn't work correctly when trigger mode was changed in booting time. For this, we keep trigger mode with SW trigger mode in default mode like we did before. However, we will need to consider PSR(Panel Self Reflash) mode to resolve this issue fundamentally later. * 'exynos-drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/daeinki/drm-exynos: drm/exynos: use logical AND in exynos_drm_plane_check_size() drm/exynos: remove superfluous inclusions of fbdev header drm/exynos: g2d: drop the _REG postfix from the stride defines drm/exynos: don't use HW trigger for Exynos5420/5422/5800 drm/exynos: fimd: don't set .has_hw_trigger in s3c6400 driver data drm/exynos: dp: Fix NULL pointer dereference due uninitialized connector
2016-06-24Merge tag 'drm-atmel-hlcdc-fixes/for-4.7-rc5' of ↵Dave Airlie2-4/+8
github.com:bbrezillon/linux-at91 into drm-fixes Two bug fixes for the atmel-hlcdc driver. * tag 'drm-atmel-hlcdc-fixes/for-4.7-rc5' of github.com:bbrezillon/linux-at91: drm: atmel-hlcdc: Fix OF graph parsing drm: atmel-hlcdc: actually disable scaling when no scaling is required
2016-06-24Merge tag 'sunxi-drm-fixes-for-4.7' of ↵Dave Airlie6-46/+88
https://git.kernel.org/pub/scm/linux/kernel/git/mripard/linux into drm-fixes Allwinner sun4i DRM driver fixes A bunch of fixes that address: - Compilation errors in various corner cases - Move to helpers - Fix the pixel clock computation - Fix our panel probe * tag 'sunxi-drm-fixes-for-4.7' of https://git.kernel.org/pub/scm/linux/kernel/git/mripard/linux: drm: sun4i: do cleanup if RGB output init fails drm/sun4i: Convert to connector register helpers drm/sun4i: remove simplefb at probe drm/sun4i: rgb: panel is an error pointer drm/sun4i: defer only if we didn't find our panel drm/sun4i: rgb: Validate the clock rate drm/sun4i: request exact rates to our parents drm: sun4i: fix probe error handling drm: sun4i: print DMA address correctly drm/sun4i: add COMMON_CLK dependency
2016-06-24Merge tag 'drm-intel-fixes-2016-06-22' of ↵Dave Airlie4-31/+3
git://anongit.freedesktop.org/drm-intel into drm-fixes Hi Dave, just a couple of display fixes, both stable stuff. Maybe we'll be able to enable fbc by default one day. * tag 'drm-intel-fixes-2016-06-22' of git://anongit.freedesktop.org/drm-intel: drm/i915/fbc: Disable on HSW by default for now drm/i915: Revert DisplayPort fast link training feature
2016-06-24Merge branch 'linux-4.7' of git://github.com/skeggsb/linux into drm-fixesDave Airlie1-1/+2
* 'linux-4.7' of git://github.com/skeggsb/linux: drm/nouveau: fix for disabled fbdev emulation
2016-06-24drm/nouveau: fix for disabled fbdev emulationDmitrii Tcvetkov1-1/+2
Hello, after this commit: commit f045f459d925138fe7d6193a8c86406bda7e49da Author: Ben Skeggs <[email protected]> Date: Thu Jun 2 12:23:31 2016 +1000 drm/nouveau/fbcon: fix out-of-bounds memory accesses kernel started to oops when loading nouveau module when using GTX 780 Ti video adapter. This patch fixes the problem. Bug report: https://bugzilla.kernel.org/show_bug.cgi?id=120591 Signed-off-by: Dmitrii Tcvetkov <[email protected]> Suggested-by: Ilia Mirkin <[email protected]> Fixes: f045f459d925 ("nouveau_fbcon_init()") Signed-off-by: Ben Skeggs <[email protected]> Cc: [email protected]
2016-06-23PM / devfreq: Send the DEVFREQ_POSTCHANGE notification when target() is failedChanwoo Choi1-1/+4
This patch sends the DEVFREQ_POSTCHANGE notification when devfreq->profile->targer() is failed. The PRECHANGE/POSTCHANGE should be paired. Fixes: 0fe3a66410a3 (PM / devfreq: Add new DEVFREQ_TRANSITION_NOTIFIER notifier) Reported-by: Lin Huang <[email protected]> Signed-off-by: Chanwoo Choi <[email protected]> Signed-off-by: Rafael J. Wysocki <[email protected]>
2016-06-23cpufreq: pcc-cpufreq: Fix doorbell.access_widthMike Galbraith1-1/+1
Commit 920de6ebfab8 (ACPICA: Hardware: Enhance acpi_hw_validate_register() with access_width/bit_offset awareness) apparently exposed a latent bug, doorbell.access_width is initialized to 64, but per Lv Zheng, it should be 4, and indeed, making that change does bring pcc-cpufreq back to life. Fixes: 920de6ebfab8 (ACPICA: Hardware: Enhance acpi_hw_validate_register() with access_width/bit_offset awareness) Suggested-by: Lv Zheng <[email protected]> Signed-off-by: Mike Galbraith <[email protected]> Signed-off-by: Rafael J. Wysocki <[email protected]>
2016-06-23x86: avoid avoid passing around 'thread_info' in stack dumping codeLinus Torvalds4-23/+17
None of the code actually wants a thread_info, it all wants a task_struct, and it's just converting to a thread_info pointer much too early. No semantic change. Signed-off-by: Linus Torvalds <[email protected]>
2016-06-23locking: avoid passing around 'thread_info' in mutex debugging codeLinus Torvalds4-12/+12
None of the code actually wants a thread_info, it all wants a task_struct, and it's just converting back and forth between the two ("ti->task" to get the task_struct from the thread_info, and "task_thread_info(task)" to go the other way). No semantic change. Acked-by: Peter Zijlstra <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
2016-06-23Btrfs: Force stripesize to the value of sectorsizeChandan Rajendra2-6/+4
Btrfs code currently assumes stripesize to be same as sectorsize. However Btrfs-progs (until commit df05c7ed455f519e6e15e46196392e4757257305) has been setting btrfs_super_block->stripesize to a value of 4096. This commit makes sure that the value of btrfs_super_block->stripesize is a power of 2. Later, it unconditionally sets btrfs_root->stripesize to sectorsize. Signed-off-by: Chandan Rajendra <[email protected]> Reviewed-by: David Sterba <[email protected]> Signed-off-by: David Sterba <[email protected]> Signed-off-by: Chris Mason <[email protected]>
2016-06-23btrfs: fix disk_i_size update bug when fallocate() failsWang Xiaoguang1-1/+2
When doing truncate operation, btrfs_setsize() will first call truncate_setsize() to set new inode->i_size, but if later btrfs_truncate() fails, btrfs_setsize() will call "i_size_write(inode, BTRFS_I(inode)->disk_i_size)" to reset the inmemory inode size, now bug occurs. It's because for truncate case btrfs_ordered_update_i_size() directly uses inode->i_size to update BTRFS_I(inode)->disk_i_size, indeed we should use the "offset" argument to update disk_i_size. Here is the call graph: ==>btrfs_truncate() ====>btrfs_truncate_inode_items() ======>btrfs_ordered_update_i_size(inode, last_size, NULL); Here btrfs_ordered_update_i_size()'s offset argument is last_size. And below test case can reveal this bug: dd if=/dev/zero of=fs.img bs=$((1024*1024)) count=100 dev=$(losetup --show -f fs.img) mkdir -p /mnt/mntpoint mkfs.btrfs -f $dev mount $dev /mnt/mntpoint cd /mnt/mntpoint echo "workdir is: /mnt/mntpoint" blocksize=$((128 * 1024)) dd if=/dev/zero of=testfile bs=$blocksize count=1 sync count=$((17*1024*1024*1024/blocksize)) echo "file size is:" $((count*blocksize)) for ((i = 1; i <= $count; i++)); do i=$((i + 1)) dst_offset=$((blocksize * i)) xfs_io -f -c "reflink testfile 0 $dst_offset $blocksize"\ testfile > /dev/null done sync truncate --size 0 testfile ls -l testfile du -sh testfile exit In this case, truncate operation will fail for enospc reason and "du -sh testfile" returns value greater than 0, but testfile's size is 0, we need to reflect correct inode->i_size. Signed-off-by: Wang Xiaoguang <[email protected]> Signed-off-by: David Sterba <[email protected]> Signed-off-by: Chris Mason <[email protected]>
2016-06-23Btrfs: fix error handling in map_private_extent_bufferLiu Bo2-2/+11
map_private_extent_buffer() can return -EINVAL in two different cases, 1. when the requested contents span two pages if nodesize is larger than pagesize, 2. when it detects something insane. The 2nd one used to be only a WARN_ON(1), and we decided to return a error to callers, but we didn't fix up all its callers, which will be addressed by this patch. Without this, btrfs may end up with 'general protection', ie. reading invalid memory. Reported-by: Vegard Nossum <[email protected]> Signed-off-by: Liu Bo <[email protected]> Signed-off-by: David Sterba <[email protected]> Signed-off-by: Chris Mason <[email protected]>
2016-06-23Btrfs: fix error return code in btrfs_init_test_fs()Wei Yongjun1-1/+1
Fix to return a negative error code from the kern_mount() error handling case instead of 0(ret is set to 0 by register_filesystem), as done elsewhere in this function. Signed-off-by: Wei Yongjun <[email protected]> Reviewed-by: Omar Sandoval <[email protected]> Signed-off-by: David Sterba <[email protected]> Signed-off-by: Chris Mason <[email protected]>
2016-06-23Merge branches '4.7-rc-misc', 'hfi1-fixes', 'i40iw-rc-fixes' and ↵Doug Ledford27-82/+161
'mellanox-rc-fixes' into k.o/for-4.7-rc
2016-06-23IB/srpt: Reduce QP buffer sizeBart Van Assche2-2/+2
The memory needed for the send and receive queues associated with a QP is proportional to the max_sge parameter. The current value of that parameter is such that with an mlx4 HCA the QP buffer size is 8 MB. Since DMA is used for communication between HCA and CPU that buffer either has to be allocated coherently or map_single() must succeed for that buffer. Since large contiguous allocations are fragile and since the maximum segment size for e.g. swiotlb is 256 KB, reduce the max_sge parameter. This patch avoids that the following text appears on the console after SRP logout and relogin on a system equipped with multiple IB HCAs: mlx4_core 0000:05:00.0: swiotlb buffer is full (sz: 8388608 bytes) swiotlb: coherent allocation failed for device 0000:05:00.0 size=8388608 CPU: 11 PID: 148 Comm: kworker/11:1 Not tainted 4.7.0-rc4-dbg+ #1 Call Trace: [<ffffffff812c6d35>] dump_stack+0x67/0x92 [<ffffffff812efe71>] swiotlb_alloc_coherent+0x141/0x150 [<ffffffff810458be>] x86_swiotlb_alloc_coherent+0x3e/0x50 [<ffffffffa03861fa>] mlx4_buf_direct_alloc.isra.5+0x9a/0x120 [mlx4_core] [<ffffffffa0386545>] mlx4_buf_alloc+0x165/0x1a0 [mlx4_core] [<ffffffffa035053d>] create_qp_common.isra.29+0x57d/0xff0 [mlx4_ib] [<ffffffffa03510da>] mlx4_ib_create_qp+0x12a/0x3f0 [mlx4_ib] [<ffffffffa031154a>] ib_create_qp+0x3a/0x250 [ib_core] [<ffffffffa055dd4b>] srpt_cm_handler+0x4bb/0xcad [ib_srpt] [<ffffffffa02c1ab0>] cm_process_work+0x20/0xf0 [ib_cm] [<ffffffffa02c3640>] cm_work_handler+0x1ac0/0x2059 [ib_cm] [<ffffffff810737ed>] process_one_work+0x19d/0x490 [<ffffffff81073b29>] worker_thread+0x49/0x490 [<ffffffff8107a0ea>] kthread+0xea/0x100 [<ffffffff815b25af>] ret_from_fork+0x1f/0x40 Fixes: b99f8e4d7bcd ("IB/srpt: convert to the generic RDMA READ/WRITE API") Signed-off-by: Bart Van Assche <[email protected]> Cc: Laurence Oberman <[email protected]> Cc: Christoph Hellwig <[email protected]> Cc: Sagi Grimberg <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23i40iw: Enable level-1 PBL for fast memory registrationShiraz Saleem2-0/+6
Set the chunk_size to enable level-1 PBL support when the fast memory page count is more than one. Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Faisal Latif <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23i40iw: Return correct max_fast_reg_page_list_lenFaisal Latif2-0/+2
Return correct value for max_fast_reg_page_list_len from i40iw_query_device(). Signed-off-by: Faisal Latif <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23i40iw: Correct status check on i40iw_get_pbleFaisal Latif1-1/+1
i40iw_get_pble returns 0 on success. Correct the check on return code. Signed-off-by: Faisal Latif <[email protected]> Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23i40iw: Correct CQ armingShiraz Saleem1-3/+6
CQ is armed for solicited events only, ignoring other notification flags. Correct this by arming for next and arming for solicited event if IB_CQ_SOLICITED is set. Also protect CQ shadow area update with spinlock. Signed-off-by: Shiraz Saleem <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/rdmavt: Correct qp_priv_alloc() return value testMike Marciniszyn2-2/+6
The current drivers return errors from this calldown wrapped in an ERR_PTR(). The rdmavt code incorrectly tests for NULL. The code is fixed to use IS_ERR() and change ret according to the driver return value. Cc: Stable <[email protected]> # 4.6+ Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/hfi1: Don't zero out qp->s_ack_queue in rvt_reset_qpAshutosh Dixit1-6/+0
Since rvt_reset_qp already zero's out qp->s_ack_queue head and tail pointers, there is no need to zero out qp->s_ack_queue itself. Reviewed-by: Dennis Dalessandro <[email protected]> Reviewed-by: Mike Marciniszyn <[email protected]> Signed-off-by: Ashutosh Dixit <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/hfi1: Fix deadlock with txreq allocation slow pathMike Marciniszyn2-3/+2
A failure in the get_txreq() inline will result in a slow path retry using __get_txreq(). __get_txreq() attempts to procure the qp s_lock, which is already held in all callers. Fix by deleting the s_lock maintenance in __get_txreq() and add sparse syntax hooks to future proof the code. Cc: Stable <[email protected]> # 4.6+ Reviewed-by: Dennis Dalessandro <[email protected]> Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Dennis Dalessandro <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/mlx4: Prevent cross page boundary allocationChuck Lever2-18/+18
Prevent cross page boundary allocation by allocating new page, this is required to be aligned with ConnectX-3 HW requirements. Not doing that might cause to "RDMA read local protection" error. Fixes: 1b2cd0fc673c ('IB/mlx4: Support the new memory registration API') Suggested-by: Christoph Hellwig <[email protected]> Signed-off-by: Chuck Lever <[email protected]> Reviewed-by: Sagi Grimberg <[email protected]> Signed-off-by: Yishai Hadas <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/mlx4: Fix memory leak if QP creation failedDotan Barak1-1/+3
When RC, UC, or RAW QPs are created, a qp object is allocated (kzalloc). If at a later point (in procedure create_qp_common) the qp creation fails, this qp object must be freed. Fixes: 1ffeb2eb8be99 ("IB/mlx4: SR-IOV IB context objects and proxy/tunnel SQP support") Signed-off-by: Dotan Barak <[email protected]> Signed-off-by: Jack Morgenstein <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/mlx4: Verify port number in flow steering create flowYishai Hadas1-0/+3
In procedure mlx4_ib_create_flow, passing an invalid port number will cause an out-of-bounds array access. Data passed to this procedure can come from user-space. Therefore, need to validate port number before proceeding onwards. Note that we check against the number of physical ports declared at the verbs (ib core) level; When bonding is active, the verbs level sees one physical port, even though the low-level driver sees two ports. Fixes: f77c0162a339 ("IB/mlx4: Add receive flow steering support") Signed-off-by: Yishai Hadas <[email protected]> Reviewed-by: Jack Morgenstein <[email protected]> Reviewed-by: Moni Shoua <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/mlx4: Fix error flow when sending mads under SRIOVYishai Hadas1-6/+18
Fix mad send error flow to prevent double freeing address handles, and leaking tx_ring entries when SRIOV is active. If ib_mad_post_send fails, the address handle pointer in the tx_ring entry must be set to NULL (or there will be a double-free) and tx_tail must be incremented (or there will be a leak of tx_ring entries). The tx_ring is handled the same way in the send-completion handler. Fixes: 37bfc7c1e83f ("IB/mlx4: SR-IOV multiplex and demultiplex MADs") Signed-off-by: Yishai Hadas <[email protected]> Reviewed-by: Jack Morgenstein <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/mlx4: Fix the SQ size of an RC QPYishai Hadas1-1/+1
When calculating the required size of an RC QP send queue, leave enough space for masked atomic operations, which require more space than "regular" atomic operation. Fixes: 6fa8f719844b ("IB/mlx4: Add support for masked atomic operations") Signed-off-by: Yishai Hadas <[email protected]> Reviewed-by: Jack Morgenstein <[email protected]> Reviewed-by: Eran Ben Elisha <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/mlx5: Fix wrong naming of port_rcv_data counterTalat Batheesh1-1/+1
port_xmit_data is written instead of port_rcv_data. Fixes: 3efd9a11212d ('IB/mlx5: Modify MAD reading counters method to use counter registers') Signed-off-by: Talat Batheesh <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/mlx5: Fix post send fence logicEli Cohen2-3/+5
If the caller specified IB_SEND_FENCE in the send flags of the work request and no previous work request stated that the successive one should be fenced, the work request would be executed without a fence. This could result in RDMA read or atomic operations failure due to a MR being invalidated. Fix this by adding the mlx5 enumeration for fencing RDMA/atomic operations and fix the logic to apply this. Fixes: e126ba97dba9 ('mlx5: Add driver for Mellanox Connect-IB adapters') Signed-off-by: Eli Cohen <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/uverbs: Initialize ib_qp_init_attr with zerosMaor Gottlieb1-1/+1
Initialize ib_qp_init_attr with zeros in order to avoid from garbage in fields that won't be set with user values. Fixes: a060b5629ab06 ('IB/core: generic RDMA READ/WRITE API') Signed-off-by: Maor Gottlieb <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/core: Fix false search of the IB_SA_WELL_KNOWN_GUIDEli Cohen1-6/+10
When virtualziation is supported, VFs may send SA MADs to a GID formed by the concatenation of the subnet prefix with the IB_SA_WELL_KNOWN_GUID. When a response is required, the current code will search the local HCA's port for the received GID to figure out the GID index of the entry containing this GID. However, since this is not a real GID it will not be found and error will be printed. We change the logic to check if the destination GID is this special GID and avoid lookup in this case and use GID index 0. Fixes: a0c1b2a35087 ('IB/core: Support accessing SA in virtualized environment') Signed-off-by: Eli Cohen <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/core: Fix RoCE v1 multicast join logic issueAlex Vesker1-4/+4
During multicast join of RoCEv1, IGMP join state and max hop limit were updated incorrectly. IGMP join should be sent and marked as joined only on RoCEv2 after a successful join. Max hops should be updated to the hop limit on RoCEv2 regardless of the join state. Fixes: bee3c3c91865 ('IB/cma: Join and leave multicast groups...') Signed-off-by: Alex Vesker <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23IB/core: Fix no default GIDs when netdevice reregistersTalat Batheesh1-1/+3
Currently, when the netdevice returned by get_netdev is unregistered, we delete all GIDs (including the default GIDs) and reset their attributes. Therefore, when we re-register it, no default GIDs will be assigned (as their "default GID") attribute will be reset. Fixing this by keeping "default GID" attribute. Fixes: 03db3a2d81e6 ('IB/core: Add RoCE GID table management') Signed-off-by: Talat Batheesh <[email protected]> Signed-off-by: Leon Romanovsky <[email protected]> Signed-off-by: Doug Ledford <[email protected]>
2016-06-23x86/xen: avoid m2p lookup when setting early page table entriesDavid Vrabel1-41/+31
When page tables entries are set using xen_set_pte_init() during early boot there is no page fault handler that could handle a fault when performing an M2P lookup. In 64 bit guests (usually dom0) early_ioremap() would fault in xen_set_pte_init() because an M2P lookup faults because the MFN is in MMIO space and not mapped in the M2P. This lookup is done to see if the PFN in in the range used for the initial page table pages, so that the PTE may be set as read-only. The M2P lookup can be avoided by moving the check (and clear of RW) earlier when the PFN is still available. Reported-by: Kevin Moraga <[email protected]> Signed-off-by: David Vrabel <[email protected]> Reviewed-by: Boris Ostrovsky <[email protected]> Reviewed-by: Juergen Gross <[email protected]>
2016-06-23hwmon: (dell-smm) Cache fan_type() calls and change fan detectionPali Rohár1-5/+20
On more Dell machines (e.g. Dell Precision M3800) fan_type() call is too expensive (CPU is too long in SMM mode) and cause kernel to hang. This is bug in Dell SMM or BIOS. This patch caches type for each fan (as it should not change) and changes the way how fan presense is detected. First it try function fan_status() as was before commit f989e55452c7 ("i8k: Add support for fan labels"). And if that fails fallback to fan_type(). *_status() functions can fail in case fan is not currently accessible (e.g. present on GPU which is currently turned off). Reported-by: Tolga Cakir <[email protected]> Signed-off-by: Pali Rohár <[email protected]> Link: https://bugzilla.kernel.org/show_bug.cgi?id=112021 Cc: [email protected] # v4.0+, will need backport Tested-by: Tolga Cakir <[email protected]> Signed-off-by: Guenter Roeck <[email protected]>
2016-06-23Merge branch 'fixes' of ↵Rafael J. Wysocki2-15/+10
https://git.kernel.org/pub/scm/linux/kernel/git/mzx/devfreq into pm-devfreq Pull devfreq fixes for v4.7 from MyungJoo Ham. * 'fixes' of https://git.kernel.org/pub/scm/linux/kernel/git/mzx/devfreq: PM / devfreq: fix initialization of current frequency in last status PM / devfreq: exynos-nocp: Remove incorrect IS_ERR() check PM / devfreq: remove double put_device PM / devfreq: fix double call put_device PM / devfreq: fix duplicated kfree on devfreq pointer PM / devfreq: devm_kzalloc to have dev pointer more precisely
2016-06-23xen/pciback: Fix conf_space read/write overlap check.Andrey Grodzovsky1-4/+2
Current overlap check is evaluating to false a case where a filter field is fully contained (proper subset) of a r/w request. This change applies classical overlap check instead to include all the scenarios. More specifically, for (Hilscher GmbH CIFX 50E-DP(M/S)) device driver the logic is such that the entire confspace is read and written in 4 byte chunks. In this case as an example, CACHE_LINE_SIZE, LATENCY_TIMER and PCI_BIST are arriving together in one call to xen_pcibk_config_write() with offset == 0xc and size == 4. With the exsisting overlap check the LATENCY_TIMER field (offset == 0xd, length == 1) is fully contained in the write request and hence is excluded from write, which is incorrect. Signed-off-by: Andrey Grodzovsky <[email protected]> Reviewed-by: Boris Ostrovsky <[email protected]> Reviewed-by: Jan Beulich <[email protected]> Cc: <[email protected]> Signed-off-by: David Vrabel <[email protected]>
2016-06-23x86/xen: fix upper bound of pmd loop in xen_cleanhighmap()Juergen Gross1-1/+1
xen_cleanhighmap() is operating on level2_kernel_pgt only. The upper bound of the loop setting non-kernel-image entries to zero should not exceed the size of level2_kernel_pgt. Reported-by: Linus Torvalds <[email protected]> Signed-off-by: Juergen Gross <[email protected]> Signed-off-by: David Vrabel <[email protected]>
2016-06-23xen/balloon: Fix declared-but-not-defined warningRoss Lagerwall1-15/+13
Fix a declared-but-not-defined warning when building with XEN_BALLOON_MEMORY_HOTPLUG=n. This fixes a regression introduced by commit dfd74a1edfab ("xen/balloon: Fix crash when ballooning on x86 32 bit PAE"). Signed-off-by: Ross Lagerwall <[email protected]> Acked-by: Juergen Gross <[email protected]> Signed-off-by: David Vrabel <[email protected]>
2016-06-22Btrfs: don't do nocow check unless we have toJosef Bacik1-22/+22
Before we write into prealloc/nocow space we have to make sure that there are no references to the extents we are writing into, which means checking the extent tree and csum tree in the case of nocow. So we don't want to do the nocow dance unless we can't reserve data space, since it's a serious drag on performance. With the following sequence fallocate -l10737418240 /mnt/btrfs-test/file cp --reflink /mnt/btrfs-test/file /mnt/btrfs-test/link fio --name=randwrite --rw=randwrite --bs=4k --filename=/mnt/btrfs-test/file \ --end_fsync=1 we get the worst case scenario where we have to fall back on to doing the check anyway. Without this patch lat (usec): min=5, max=111598, avg=27.65, stdev=124.51 write: io=10240MB, bw=126876KB/s, iops=31718, runt= 82646msec With this patch lat (usec): min=3, max=91210, avg=14.09, stdev=110.62 write: io=10240MB, bw=212753KB/s, iops=53188, runt= 49286msec We get twice the throughput, half of the runtime, and half of the average latency. Thanks, Signed-off-by: Josef Bacik <[email protected]> [ PAGE_CACHE_ removal related fixups ] Signed-off-by: David Sterba <[email protected]> Signed-off-by: Chris Mason <[email protected]>
2016-06-22btrfs: fix deadlock in delayed_ref_async_startChris Mason1-9/+11
"Btrfs: track transid for delayed ref flushing" was deadlocking on btrfs_attach_transaction because its not safe to call from the async delayed ref start code. This commit brings back btrfs_join_transaction instead and checks for a blocked commit. Signed-off-by: Josef Bacik <[email protected]> Signed-off-by: Chris Mason <[email protected]>
2016-06-22Btrfs: track transid for delayed ref flushingJosef Bacik4-5/+16
Using the offwakecputime bpf script I noticed most of our time was spent waiting on the delayed ref throttling. This is what is supposed to happen, but sometimes the transaction can commit and then we're waiting for throttling that doesn't matter anymore. So change this stuff to be a little smarter by tracking the transid we were in when we initiated the throttling. If the transaction we get is different then we can just bail out. This resulted in a 50% speedup in my fs_mark test, and reduced the amount of time spent throttling by 60 seconds over the entire run (which is about 30 minutes). Thanks, Signed-off-by: Josef Bacik <[email protected]> Signed-off-by: Chris Mason <[email protected]>
2016-06-23powerpc/bpf/jit: Disable classic BPF JIT on ppc64leNaveen N. Rao1-1/+1
Classic BPF JIT was never ported completely to work on little endian powerpc. However, it can be enabled and will crash the system when used. As such, disable use of BPF JIT on ppc64le. Fixes: 7c105b63bd98 ("powerpc: Add CONFIG_CPU_LITTLE_ENDIAN kernel config option.") Reported-by: Thadeu Lima de Souza Cascardo <[email protected]> Signed-off-by: Naveen N. Rao <[email protected]> Acked-by: Thadeu Lima de Souza Cascardo <[email protected]> Signed-off-by: Michael Ellerman <[email protected]>
2016-06-23powerpc: Fix faults caused by radix patching of SLB miss handlerMichael Ellerman1-3/+4
As part of the Radix MMU support we added some feature sections in the SLB miss handler. These are intended to catch the case that we incorrectly take an SLB miss when Radix is enabled, and instead of crashing weirdly they bail out to a well defined exit path and trigger an oops. However the way they were written meant the bailout case was enabled by default until we did CPU feature patching. On powermacs the early debug prints in setup_system() can cause an SLB miss, which happens before code patching, and so the SLB miss handler would incorrectly bailout and crash during boot. Fix it by inverting the sense of the feature section, so that the code which is in place at boot is correct for the hash case. Once we determine we are using Radix - which will never happen on a powermac - only then do we patch in the bailout case which unconditionally jumps. Fixes: caca285e5ab4 ("powerpc/mm/radix: Use STD_MMU_64 to properly isolate hash related code") Reported-by: Denis Kirjanov <[email protected]> Tested-by: Denis Kirjanov <[email protected]> Reviewed-by: Aneesh Kumar K.V <[email protected]> Signed-off-by: Michael Ellerman <[email protected]>
2016-06-23UBIFS: Implement ->migratepage()Kirill A. Shutemov1-0/+24
During page migrations UBIFS might get confused and the following assert triggers: [ 213.480000] UBIFS assert failed in ubifs_set_page_dirty at 1451 (pid 436) [ 213.490000] CPU: 0 PID: 436 Comm: drm-stress-test Not tainted 4.4.4-00176-geaa802524636-dirty #1008 [ 213.490000] Hardware name: Allwinner sun4i/sun5i Families [ 213.490000] [<c0015e70>] (unwind_backtrace) from [<c0012cdc>] (show_stack+0x10/0x14) [ 213.490000] [<c0012cdc>] (show_stack) from [<c02ad834>] (dump_stack+0x8c/0xa0) [ 213.490000] [<c02ad834>] (dump_stack) from [<c0236ee8>] (ubifs_set_page_dirty+0x44/0x50) [ 213.490000] [<c0236ee8>] (ubifs_set_page_dirty) from [<c00fa0bc>] (try_to_unmap_one+0x10c/0x3a8) [ 213.490000] [<c00fa0bc>] (try_to_unmap_one) from [<c00fadb4>] (rmap_walk+0xb4/0x290) [ 213.490000] [<c00fadb4>] (rmap_walk) from [<c00fb1bc>] (try_to_unmap+0x64/0x80) [ 213.490000] [<c00fb1bc>] (try_to_unmap) from [<c010dc28>] (migrate_pages+0x328/0x7a0) [ 213.490000] [<c010dc28>] (migrate_pages) from [<c00d0cb0>] (alloc_contig_range+0x168/0x2f4) [ 213.490000] [<c00d0cb0>] (alloc_contig_range) from [<c010ec00>] (cma_alloc+0x170/0x2c0) [ 213.490000] [<c010ec00>] (cma_alloc) from [<c001a958>] (__alloc_from_contiguous+0x38/0xd8) [ 213.490000] [<c001a958>] (__alloc_from_contiguous) from [<c001ad44>] (__dma_alloc+0x23c/0x274) [ 213.490000] [<c001ad44>] (__dma_alloc) from [<c001ae08>] (arm_dma_alloc+0x54/0x5c) [ 213.490000] [<c001ae08>] (arm_dma_alloc) from [<c035cecc>] (drm_gem_cma_create+0xb8/0xf0) [ 213.490000] [<c035cecc>] (drm_gem_cma_create) from [<c035cf20>] (drm_gem_cma_create_with_handle+0x1c/0xe8) [ 213.490000] [<c035cf20>] (drm_gem_cma_create_with_handle) from [<c035d088>] (drm_gem_cma_dumb_create+0x3c/0x48) [ 213.490000] [<c035d088>] (drm_gem_cma_dumb_create) from [<c0341ed8>] (drm_ioctl+0x12c/0x444) [ 213.490000] [<c0341ed8>] (drm_ioctl) from [<c0121adc>] (do_vfs_ioctl+0x3f4/0x614) [ 213.490000] [<c0121adc>] (do_vfs_ioctl) from [<c0121d30>] (SyS_ioctl+0x34/0x5c) [ 213.490000] [<c0121d30>] (SyS_ioctl) from [<c000f2c0>] (ret_fast_syscall+0x0/0x34) UBIFS is using PagePrivate() which can have different meanings across filesystems. Therefore the generic page migration code cannot handle this case correctly. We have to implement our own migration function which basically does a plain copy but also duplicates the page private flag. UBIFS is not a block device filesystem and cannot use buffer_migrate_page(). Cc: [email protected] Signed-off-by: Kirill A. Shutemov <[email protected]> [rw: Massaged changelog, build fixes, etc...] Signed-off-by: Richard Weinberger <[email protected]> Acked-by: Christoph Hellwig <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.