aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2011-01-11drm/i915: fix the wrong latency value while computing wm0Yuanhan Liu1-5/+5
On Ironlake, the LP0 latency is hardcoded and in ns unit, while on Sandybridge, it comes from a register and with unit 0.1 us. So, fix the wrong latency value while computing wm0 on Ironlake and Sandybridge. Signed-off-by: Yuanhan Liu <[email protected]> Signed-off-by: Chris Wilson <[email protected]>
2011-01-11drm/i915: support low power watermarks on IronlakeJesse Barnes2-130/+133
This patch actually makes the watermark code even uglier (if that's possible), but has the advantage of sharing code between SNB and ILK at least. Longer term we should refactor the watermark stuff into its own file and clean it up now that we know how it's supposed to work. Supporting WM2 on my Vaio reduced power consumption by around 0.5W, so this patch is definitely worthwhile (though it also needs lots of test coverage). Signed-off-by: Jesse Barnes <[email protected]> [ickle: pass the watermark structs arounds] Signed-off-by: Chris Wilson <[email protected]>
2011-01-11agp/intel: Flush the chipset write buffers when changing GTT baseChris Wilson2-0/+11
Flush the chipset write buffers before and after adjusting the GTT base register, just in case. We only modify this value upon initialisation (boot and resume) so there should be no outstanding writes, however there are always those persistent PGTBL_ER that keep getting reported upon resume. Signed-off-by: Chris Wilson <[email protected]>
2011-01-11drm/i915: Workaround erratum on i830 for TAIL pointer within last 2 cachelinesChris Wilson2-3/+11
On i830 if the tail pointer is set to within 2 cachelines of the end of the buffer, the chip may hang. So instead if the tail were to land in that location, we pad the end of the buffer with NOPs, and start again at the beginning. Signed-off-by: Chris Wilson <[email protected]>
2011-01-11drm/i915: Use the mappable sizes determined by GTT for consistency.Chris Wilson2-17/+10
There should be no difference, but we can eliminate redundant code. Signed-off-by: Chris Wilson <[email protected]>
2011-01-11drm/i915: support overclocking on Sandy BridgeJesse Barnes2-0/+28
In some configuration, the PCU may allow us to overclock the GPU. Check for this case and adjust the max frequency as appropriate. Also initialize the min/max frequencies to default values as indicated by hardware. Signed-off-by: Jesse Barnes <[email protected]> Signed-off-by: Chris Wilson <[email protected]>
2011-01-11drm/i915/lvds: Always use 0 to disable the pfit controllerChris Wilson1-0/+4
... and just any combination of bits & ~PFIT_ENABLE. This way we do not attempt disable to the panel fitter controller uselessly upon intel_lvds_disable(). Signed-off-by: Chris Wilson <[email protected]>
2011-01-11drm/i915/panel: Only record the backlight level when it is enabledChris Wilson5-8/+39
By tracking the current status of the backlight we can prevent recording the value of the current backlight when we have disabled it. And so prevent restoring it to 'off' after an unbalanced sequence of intel_lvds_disable/enable. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=22672 Tested-by: Alex Riesen <[email protected]> Tested-by: Larry Finger <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Cc: [email protected]
2011-01-11drm/i915/sdvo: Defer detection of output capabilities until probingChris Wilson1-22/+11
Alex Fiestas reported an issue with his HDMI connector being misdetected as DVI unless he had something connected upon boot. By moving the decision as to whether to use HDMI or DVI encoding for the HDMI capable output until we probe the monitor means that we should avoid sending a HDMI signal to a DVI monitor and also correctly detect hardware like Alex's. However, to really determine what connector is soldered onto the wire we need to inspect the VBT sdvo child devices - but can we trust it? Reported-by: Alex Fiestas <[email protected]> Tested-by: Alex Fiestas <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=32828 Signed-off-by: Chris Wilson <[email protected]> Cc: [email protected]
2011-01-11drm/i915: fix calculation of eDP signal levels on SandybridgeYuanhan Liu2-11/+21
Some voltage swing/pre-emphasis level use the same value on eDP Sandybridge, like 400mv_0db and 600mv_0db are with the same value of (0x0 << 22). So, fix them, and point out the value if it isn't a supported voltage swing/pre-emphasis level. Signed-off-by: Yuanhan Liu <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Cc: [email protected]
2011-01-11drm/i915/crt: Check for a analog monitor in case of DVI-IDavid Müller1-5/+25
Since Linux 2.6.36 the digital output on my system (855GME + DVI-I) is not working any longer. The analog output is always activated regardless of the type of monitor attached. The culprit seems to be intel_crt_detect_ddc(), which returns true as soon as an ACK from the EDID device is received. Obviously this approach does not work with DVI-I where the analog and digital outputs share a common DDC bus. In a similar manner to the shared DDC wire, ala the "Mac Mini Hack", we need an additional check to make sure that there really is an analog device attached to the DDC. Signed-off-by: David Müller <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Cc: [email protected]
2011-01-11drm/i915: make DP training try a little harderJesse Barnes1-4/+23
When trying to do channel equalization, we need to make sure we still have clock recovery on all lanes while training. We also need to try clock recovery again if we lose the clock or if channel eq fails 5 times. We'll try clock recovery up to 5 more times before giving up entirely. Gets suspend/resume working on my Vaio again and brings us back into compliance with the DP training sequence spec. Signed-off-by: Jesse Barnes <[email protected]> Signed-off-by: Chris Wilson <[email protected]>
2011-01-11drm/i915: check eDP encoder correctly when setting modesJesse Barnes1-1/+1
We were using a stale pointer in the check which caused us to use CPU attached DP params when we should have been using PCH attached params. Signed-off-by: Jesse Barnes <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=31988 Tested-by: Jan-Hendrik Zab <[email protected]> Tested-by: Christoph Lukas <[email protected]> Signed-off-by: Chris Wilson <[email protected]> Cc: [email protected]
2011-01-11ext4: fix trimming starting with block 0 with small blocksizeJan Kara1-0/+6
When s_first_data_block is not zero (which happens e.g. when block size is 1KB) and trim ioctl is called to start trimming from block 0, the math in ext4_get_group_no_and_offset() overflows. The overall result is that ioctl returns EINVAL which is kind of unexpected and we probably don't want userspace tools to bother with internal details of filesystem structure. So just silently increase starting offset (and shorten length) when starting block is below s_first_data_block. CC: Lukas Czerner <[email protected]> Signed-off-by: Jan Kara <[email protected]> Signed-off-by: "Theodore Ts'o" <[email protected]>
2011-01-11ext4: revert buggy trim overflow patchTheodore Ts'o1-6/+0
This reverts commit 4f531501e44: ext4: fix possible overflow in ext4_trim_fs() Signed-off-by: "Theodore Ts'o" <[email protected]>
2011-01-11Merge branch 'for-linus-merged' of git://oss.sgi.com/xfs/xfsLinus Torvalds38-1920/+1997
* 'for-linus-merged' of git://oss.sgi.com/xfs/xfs: (47 commits) xfs: convert grant head manipulations to lockless algorithm xfs: introduce new locks for the log grant ticket wait queues xfs: convert log grant heads to atomic variables xfs: convert l_tail_lsn to an atomic variable. xfs: convert l_last_sync_lsn to an atomic variable xfs: make AIL tail pushing independent of the grant lock xfs: use wait queues directly for the log wait queues xfs: combine grant heads into a single 64 bit integer xfs: rework log grant space calculations xfs: fact out common grant head/log tail verification code xfs: convert log grant ticket queues to list heads xfs: use AIL bulk delete function to implement single delete xfs: use AIL bulk update function to implement single updates xfs: remove all the inodes on a buffer from the AIL in bulk xfs: consume iodone callback items on buffers as they are processed xfs: reduce the number of AIL push wakeups xfs: bulk AIL insertion during transaction commit xfs: clean up xfs_ail_delete() xfs: Pull EFI/EFD handling out from under the AIL lock xfs: fix EFI transaction cancellation. ...
2011-01-11Merge branch 'upstream-linus' of ↵Linus Torvalds18-534/+845
git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2 * 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2: (22 commits) MAINTAINERS: Update Joel Becker's email address ocfs2: Remove unused truncate function from alloc.c ocfs2/cluster: dereferencing before checking in nst_seq_show() ocfs2: fix build for OCFS2_FS_STATS not enabled ocfs2/cluster: Show o2net timing statistics ocfs2/cluster: Track process message timing stats for each socket ocfs2/cluster: Track send message timing stats for each socket ocfs2/cluster: Use ktime instead of timeval in struct o2net_sock_container ocfs2/cluster: Replace timeval with ktime in struct o2net_send_tracking ocfs2: Add DEBUG_FS dependency ocfs2/dlm: Hard code the values for enums ocfs2/dlm: Minor cleanup ocfs2/dlm: Cleanup dlmdebug.c ocfs2: Release buffer_head in case of error in ocfs2_double_lock. ocfs2/cluster: Pin the local node when o2hb thread starts ocfs2/cluster: Show pin state for each o2hb region ocfs2/cluster: Pin/unpin o2hb regions ocfs2/cluster: Remove dropped region from o2hb quorum region bitmap ocfs2/cluster: Pin the remote node item in configfs ocfs2/dlm: make existing convertion precedent over new lock ...
2011-01-11NFS fix the setting of exchange id flagAndy Adamson2-6/+27
Indicate support for referrals. Do not set any PNFS roles. Check the flags returned by the server for validity. Do not use exchange flags from an old client ID instance when recovering a client ID. Update the EXCHID4_FLAG_XXX set to RFC 5661. Signed-off-by: Andy Adamson <[email protected]> Signed-off-by: Trond Myklebust <[email protected]>
2011-01-11Merge branch 'next' of git://git.monstr.eu/linux-2.6-microblazeLinus Torvalds13-240/+214
* 'next' of git://git.monstr.eu/linux-2.6-microblaze: microblaze: remove obsolete DEBUG_BOOTMEM microblaze: trivial: Fix removed the part of line microblaze: Fix __muldi3 function for little-endian. microblaze: Clear i/dcache for sw breakpoints microblaze: Remove useless early_init_dt_check_for_initrd microblaze: Fix unaligned exception for little endian platform microblaze: Add PVR for Microblaze v8.00.b microblaze: Correct PVR access macros Revert "microblaze: Simplify syscall rutine" microblaze: Fix initramfs arch/microblaze: Remove unnecessary semicolons
2011-01-11Merge branch 'x86-urgent-for-linus' of ↵Linus Torvalds16-102/+297
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86: Fix Moorestown VRTC fixmap placement x86/gpio: Implement x86 gpio_to_irq convert function x86, UV: Fix APICID shift for Westmere processors x86: Use PCI method for enabling AMD extended config space before MSR method x86: tsc: Prevent delayed init if initial tsc calibration failed x86, lapic-timer: Increase the max_delta to 31 bits x86: Fix sparse non-ANSI function warnings in smpboot.c x86, numa: Fix CONFIG_DEBUG_PER_CPU_MAPS without NUMA emulation x86, AMD, PCI: Add AMD northbridge PCI device id for CPU families 12h and 14h x86, numa: Fix cpu to node mapping for sparse node ids x86, numa: Fake node-to-cpumask for NUMA emulation x86, numa: Fake apicid and pxm mappings for NUMA emulation x86, numa: Avoid compiling NUMA emulation functions without CONFIG_NUMA_EMU x86, numa: Reduce minimum fake node size to 32M Fix up trivial conflict in arch/x86/kernel/apic/x2apic_uv_x.c
2011-01-11Merge branch 'timers-for-linus' of ↵Linus Torvalds5-344/+426
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: rtc: Namespace fixup RTC: Remove UIE emulation RTC: Rework RTC code to use timerqueue for events Fix up trivial conflict in drivers/rtc/rtc-dev.c
2011-01-11Merge branch 'perf-fixes-for-linus' of ↵Linus Torvalds38-248/+442
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip * 'perf-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (28 commits) perf session: Fix infinite loop in __perf_session__process_events perf evsel: Support perf_evsel__open(cpus > 1 && threads > 1) perf sched: Use PTHREAD_STACK_MIN to avoid pthread_attr_setstacksize() fail perf tools: Emit clearer message for sys_perf_event_open ENOENT return perf stat: better error message for unsupported events perf sched: Fix allocation result check perf, x86: P4 PMU - Fix unflagged overflows handling dynamic debug: Fix build issue with older gcc tracing: Fix TRACE_EVENT power tracepoint creation tracing: Fix preempt count leak tracepoint: Add __rcu annotation tracing: remove duplicate null-pointer check in skb tracepoint tracing/trivial: Add missing comma in TRACE_EVENT comment tracing: Include module.h in define_trace.h x86: Save rbp in pt_regs on irq entry x86, dumpstack: Fix unused variable warning x86, NMI: Clean-up default_do_nmi() x86, NMI: Allow NMI reason io port (0x61) to be processed on any CPU x86, NMI: Remove DIE_NMI_IPI x86, NMI: Add priorities to handlers ...
2011-01-11Merge branch 'for-linus' of ↵Linus Torvalds39-492/+4083
git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc: (39 commits) mmc: davinci: add support for SDIO irq handling mmc: fix division by zero in MMC core mmc: tmio_mmc: fix CMD irq handling mmc: tmio_mmc: handle missing HW interrupts mfd: sh_mobile_sdhi: activate SDIO IRQ for tmio_mmc mmc: tmio_mmc: implement SDIO IRQ support mfd: sdhi: require the tmio-mmc driver to bounce unaligned buffers mmc: tmio_mmc: silence compiler warnings mmc: tmio_mmc: implement a bounce buffer for unaligned DMA mmc: tmio_mmc: merge the private header into the driver mmc: tmio_mmc: fix PIO fallback on DMA descriptor allocation failure mmc: tmio_mmc: allow multi-element scatter-gather lists mmc: Register debugfs dir before calling card probe function. mmc: MMC_BLOCK_MINORS should depend on MMC_BLOCK. mmc: Explain why we make adjacent mmc_bus_{put,get} calls during rescan. mmc: Fix sd/sdio/mmc initialization frequency retries mmc: fix mmc_set_bus_width_ddr() call without bus-width-test cap mmc: dw_mmc: Add Synopsys DesignWare mmc host driver. mmc: add sdhci-tegra driver for Tegra SoCs mmc: sdhci: add quirk for max len ADMA descriptors ...
2011-01-11fs/9p: Don't set dentry->d_op in create routinesAneesh Kumar K.V2-19/+0
We do set dentry->d_op in lookup even in case of EOENT entries. That implies we should have dentry->d_op already set when create/mkdir/mknod/link/symlink routines are called Signed-off-by: Aneesh Kumar K.V <[email protected]> Signed-off-by: Eric Van Hensbergen <[email protected]>
2011-01-11fs/9p: fix spelling typoEric Van Hensbergen1-1/+1
introduced a typo somehow during a hand merge Reported by: Aneesh Kumar K.V <[email protected]> Signed-off-by: Eric Van Hensbergen <[email protected]>
2011-01-11fs/9p: TREADLINK bugfixM. Mohan Kumar1-36/+22
Remove v9fs_vfs_readlink_dotl function and use generic_readlink. Update v9fs_vfs_follow_link_dotl function to accommodate this change Signed-off-by: M. Mohan Kumar <[email protected]> Reported-by: Dr. David Alan Gilbert <[email protected]> Signed-off-by: Venkateswararao Jujjuri <[email protected]> Signed-off-by: Eric Van Hensbergen <[email protected]>
2011-01-11net/9p: Use proper data typesM. Mohan Kumar1-12/+10
Use proper data types for storing the count of the binary blob and length of a string. Without this patch length calculation of string will always result in -1 because of comparision between signed and unsigned integer. Signed-off-by: M. Mohan Kumar <[email protected]> Signed-off-by: Venkateswararao Jujjuri <[email protected]> Signed-off-by: Eric Van Hensbergen <[email protected]>
2011-01-11fs/9p: Simplify the .L create operationAneesh Kumar K.V1-47/+28
Signed-off-by: Aneesh Kumar K.V <[email protected]> Signed-off-by: Venkateswararao Jujjuri <[email protected]> Signed-off-by: Eric Van Hensbergen <[email protected]>
2011-01-11fs/9p: Move dotl inode operations into a seperate fileAneesh Kumar K.V4-862/+916
Source Code Reorganization Signed-off-by: Aneesh Kumar K.V <[email protected]> Signed-off-by: Venkateswararao Jujjuri <[email protected]> Signed-off-by: Eric Van Hensbergen <[email protected]>
2011-01-11fs/9p: fix menu presentationRandy Dunlap1-1/+4
Make the 9P_FS kconfig options subordinate to the 9P_FS kconfig symbol in the menu presentation instead of them all being at the same level. Signed-off-by: Randy Dunlap <[email protected]> Signed-off-by: Eric Van Hensbergen <[email protected]>
2011-01-11fs/9p: Fix the return error on default acl removalAneesh Kumar K.V1-1/+1
If we don't have default ACL, then trying to remove default acl on a file should return 0. Signed-off-by: Aneesh Kumar K.V <[email protected]> Signed-off-by: Venkateswararao Jujjuri <[email protected]>
2011-01-11fs/9p: Remove unnecessary semicolonsJoe Perches2-2/+2
Signed-off-by: Joe Perches <[email protected]> Signed-off-by: Eric Van Hensbergen <[email protected]>
2011-01-11x86: Fix Moorestown VRTC fixmap placementArjan van de Ven1-2/+2
The x86 fixmaps need to be all together... unfortunately the VRTC one was misplaced. This patch makes sure the MRST VRTC fixmap is put prior to the __end_of_permanent_fixed_addresses marker. Signed-off-by: Arjan van de Ven <[email protected]> Signed-off-by: Alan Cox <[email protected]> LKML-Reference: <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
2011-01-11x86/gpio: Implement x86 gpio_to_irq convert functionAlek Du1-4/+1
We need this for x86 MID platforms where GPIO interrupts are used. No special magic is needed so the default 1:1 behaviour will do nicely. Signed-off-by: Alek Du <[email protected]> Signed-off-by: Jacob Pan <[email protected]> Signed-off-by: Alan Cox <[email protected]> LKML-Reference: <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
2011-01-11x86, UV: Fix APICID shift for Westmere processorsJack Steiner1-1/+1
Westmere processors use a different algorithm for assigning APICIDs on SGI UV systems. The location of the node number within the apicid is now a function of the processor type. Signed-off-by: Jack Steiner <[email protected]> LKML-Reference: <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
2011-01-11x86: Use PCI method for enabling AMD extended config space before MSR methodJan Beulich4-28/+63
While both methods should work equivalently well for the native case, the Xen Dom0 case can't reliably work with the MSR one, since there's no guarantee that the virtual CPUs it has available fully cover all necessary physical ones. As per the suggestion of Robert Richter the patch only adds the PCI method, but leaves the MSR one as a fallback to cover new systems the PCI IDs of which may not have got added to the code base yet. The only change in v2 is the breaking out of the new CPI initialization method into a separate function, as requested by Ingo. Signed-off-by: Jan Beulich <[email protected]> Acked-by: Robert Richter <[email protected]> Cc: Andreas Herrmann3 <[email protected]> Cc: Joerg Roedel <[email protected]> Cc: Jeremy Fitzhardinge <[email protected]> LKML-Reference: <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
2011-01-11x86: tsc: Prevent delayed init if initial tsc calibration failedThomas Gleixner1-1/+1
commit a8760ec (x86: Check tsc available/disabled in the delayed init function) missed to prevent the setup of the delayed init function in case the initial tsc calibration failed. This results in the same divide by zero bug as we have seen without the tsc disabled check. Skip the delayed work setup when tsc_khz (the initial calibration value) is 0. Bisected-and-tested-by: Kirill A. Shutemov <[email protected]> Cc: John Stultz <[email protected]> Signed-off-by: Thomas Gleixner <[email protected]>
2011-01-11powerpc/pseries: Fix VPHN build errors on non-SMP systemsJesse Larrew2-12/+17
The header asm/hvcall.h was previously included indirectly via smp.h. On non-SMP systems, however, these declarations are excluded and the build breaks. This is easily fixed by including asm/hvcall.h directly. The VPHN feature is only meaningful on NUMA systems that implement the SPLPAR option, so exclude the VPHN code on systems without SPLPAR enabled. Also, expose unmap_cpu_from_node() on systems with SPLPAR enabled, even if CONFIG_HOTPLUG_CPU is disabled. Lastly, map_cpu_to_node() is now needed by VPHN to manipulate the node masks after boot time, so remove the __cpuinit annotation to fix a section mismatch. Signed-off-by: Jesse Larrew <[email protected]>
2011-01-11Merge remote branch 'gcl/next' into nextBenjamin Herrenschmidt937-8190/+11426
2011-01-10Merge branch 'master' into for-linus-mergedAlex Elder38-1920/+1997
This merge pulls the XFS master branch into the latest Linus master. This results in a merge conflict whose best fix is not obvious. I manually fixed the conflict, in "fs/xfs/xfs_iget.c". Dave Chinner had done work that resulted in RCU freeing of inodes separate from what Nick Piggin had done, and their results differed slightly in xfs_inode_free(). The fix updates Nick's call_rcu() with the use of VFS_I(), while incorporating needed updates to some XFS inode fields implemented in Dave's series. Dave's RCU callback function has also been removed. Signed-off-by: Alex Elder <[email protected]>
2011-01-10Merge branches 'cxgb4', 'ipath', 'ipoib', 'mlx4', 'mthca', 'nes', 'qib' and ↵Roland Dreier32-531/+887
'srp' into for-next
2011-01-10IB/qib: Fix refcount leak in lkey/rkey validationMike Marciniszyn1-16/+14
The mr optimization introduced a reference count leak on an exception test. The lock/refcount manipulation is moved down and the problematic exception test now calls bail to insure that the lock is released. Additional fixes as suggested by Ralph Campbell <[email protected]>: - reduce lock scope of dma regions - use explicit values on returns vs. automatic ret value Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Improve SERDES tunning on QMH boardsMike Marciniszyn1-3/+23
Improve the QMH SERDES tunning on initial driver load by having the driver go through a link state change. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Unnecessary delayed completions on RC connectionMike Marciniszyn1-0/+24
Currently on receipt of a response message (ACKs, RDMA Response, Atomic Responses etc.) if the SDMA completion counter is not advanced the driver delays the completion of the WQE. In most cases this is overly pessimistic as the response (ACK) to a previously transmitted send implies that the send is complete. Ensure that SDMA queue is progressed appropriately before determining if a send has delayed completions. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Issue pre-emptive NAKs on eager buffer overflowMike Marciniszyn1-4/+137
Under congestion resulting in eager buffer overflow attempt to send pre-emptive NAKs if header queue entries with TID errors are generated and a valid header is present. This prevents long timeouts and flow restarts if a trailing set of packets are dropped due to eager overflows. Pre-emptive NAKs are currently only supported for RDMA writes. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: RDMA lkey/rkey validation is inefficient for large MRsMike Marciniszyn3-23/+60
The current code loops during rkey/lkey validiation to isolate the MR for the RDMA, which is expensive when the current operation is inside a very large memory region. This fix optimizes rkey/lkey validation routines for user memory regions and fast memory regions. The MR entry can be isolated by shifts/mods instead of looping. The existing loop is preserved for phys memory regions for now. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Change QPN incrementMike Marciniszyn1-1/+1
Changing from +1 to +2 allows for better QP distribution across receive contexts. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Add fix missing from earlier patchMike Marciniszyn1-31/+24
The upstream code was missing part of a receive/error race fix from the internal tree. Add the missing part, which makes future merges possible. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Change receive queue/QPN selectionMike Marciniszyn4-31/+15
The basic idea is that on SusieQ, the difficult part of mapping QPN to context is handled by the mapping registers so the generic QPN allocation doesn't need to worry about chip specifics. For Monty and Linda, there is no mapping table so the qpt->mask (same as dd->qpn_mask), is used to see if the QPN to context falls within [zero..dd->n_krcv_queues). Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
2011-01-10IB/qib: Fix interrupt mitigationMike Marciniszyn5-8/+12
For SusieQ we need to write to the interrupt timer register before updating the header queue head with interrupt count. This is to ensure that the timer is enabled properly and a receive available interrupt is delivered. Otherwise this interrupt can be lost if the receiver header/eager queues are full before the timer is enabled. Signed-off-by: Mike Marciniszyn <[email protected]> Signed-off-by: Roland Dreier <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.