17 Dec, 2009
5 commits
-
* git://git.infradead.org/iommu-2.6:
implement early_io{re,un}map for ia64
Revert "Intel IOMMU: Avoid memory allocation failures in dma map api calls"
intel-iommu: ignore page table validation in pass through mode
intel-iommu: Fix oops with intel_iommu=igfx_off
intel-iommu: Check for an RMRR which ends before it starts.
intel-iommu: Apply BIOS sanity checks for interrupt remapping too.
intel-iommu: Detect DMAR in hyperspace at probe time.
dmar: Fix build failure without NUMA, warn on bogus RHSA tables and don't abort
iommu: Allocate dma-remapping structures using numa locality info
intr_remap: Allocate intr-remapping table using numa locality info
dmar: Allocate queued invalidation structure using numa locality info
dmar: support for parsing Remapping Hardware Static Affinity structure -
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp:
edac, mce, amd: silence GART TLB errors
edac, mce: correct corenum reporting -
* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6: (116 commits)
V4L/DVB (13698): pms: replace asm/uaccess.h to linux/uaccess.h
V4L/DVB (13690): radio/si470x: #include
V4L/DVB (13688): au8522: modify the attributes of local filter coefficients
V4L/DVB (13687): cx231xx: use NULL when pointer is needed
V4L/DVB: Davinci VPFE Capture: remove unused #include
V4L/DVB (13685): Correct code taking the size of a pointer
V4L/DVB (13684): Fix some cut-and-paste noise in dib0090.h
V4L/DVB (13683): sanio-ms: clean up init, exit and id_table
V4L/DVB (13682): dib8000: make some constant static
V4L/DVB: lgs8gxx: Use shifts rather than multiply/divide when possible
V4L/DVB (13680b): DocBook/media: create links for included sources
V4L/DVB (13680a): DocBook/media: copy images after building HTML
V4L/DVB (13678): Add support for yet another DvbWorld, TeVii and Prof USB devices
V4L/DVB (13676): configurable IRQ mode on NetUP Dual DVB-S2 CI; IRQ from CAM processing (CI interface works faster)
V4L/DVB (13674): stv090x: Add DiSEqC envelope mode
V4L/DVB (13673): lnbp21: Implement 22 kHz tone control
V4L/DVB (13671): sh_mobile_ceu_camera: Remove frame size page alignment
V4L/DVB (13670): soc-camera: Add mt9t112 camera driver
V4L/DVB (13669): tw9910: Add sync polarity support
V4L/DVB (13668): tw9910: remove cropping
... -
* akpm: (173 commits)
genalloc: use bitmap_find_next_zero_area
ia64: use bitmap_find_next_zero_area
sparc: use bitmap_find_next_zero_area
mlx4: use bitmap_find_next_zero_area
isp1362-hcd: use bitmap_find_next_zero_area
iommu-helper: use bitmap library
bitmap: introduce bitmap_set, bitmap_clear, bitmap_find_next_zero_area
qnx4: use hweight8
qnx4fs: remove remains of the (defunct) write support
resource: constify arg to resource_size() and resource_type()
gru: send cross partition interrupts using the gru
gru: function to generate chipset IPI values
gru: update driver version number
gru: improve GRU TLB dropin statistics
gru: fix GRU interrupt race at deallocate
gru: add hugepage support
gru: fix bug in allocation of kernel contexts
gru: update GRU structures to match latest hardware spec
gru: check for correct GRU chiplet assignment
gru: remove stray local_irq_enable
... -
Although reporting of benign GART TLB errors is disabled in
__mcheck_cpu_apply_quirks, those are still being logged, and, as a
result, trip up amd64_edac. Pull up reporting check so that machines
with loaded edac module bail out early and don't spit fragments into
dmesg.Signed-off-by: Borislav Petkov
16 Dec, 2009
35 commits
-
Signed-off-by: Akinobu Mita
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Signed-off-by: Akinobu Mita
Cc: Tony Luck
Cc: Fenghua Yu
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Signed-off-by: Akinobu Mita
Acked-by: "David S. Miller"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Signed-off-by: Akinobu Mita
Reviewed-by: Roland Dreier
Cc: Yevgeny Petrilin
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Signed-off-by: Akinobu Mita
Cc: Greg Kroah-Hartman
Cc: Lothar Wassmann
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Use bitmap library and kill some unused iommu helper functions.
1. s/iommu_area_free/bitmap_clear/
2. s/iommu_area_reserve/bitmap_set/
3. Use bitmap_find_next_zero_area instead of find_next_zero_area
This cannot be simple substitution because find_next_zero_area
doesn't check the last bit of the limit in bitmap4. Remove iommu_area_free, iommu_area_reserve, and find_next_zero_area
Signed-off-by: Akinobu Mita
Cc: "David S. Miller"
Cc: Benjamin Herrenschmidt
Cc: Paul Mackerras
Cc: Thomas Gleixner
Cc: Ingo Molnar
Cc: "H. Peter Anvin"
Cc: FUJITA Tomonori
Cc: Joerg Roedel
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This introduces new bitmap functions:
bitmap_set: Set specified bit area
bitmap_clear: Clear specified bit area
bitmap_find_next_zero_area: Find free bit areaThese are mostly stolen from iommu helper. The differences are:
- Use find_next_bit instead of doing test_bit for each bit
- Rewrite bitmap_set and bitmap_clear
Instead of setting or clearing for each bit.
- Check the last bit of the limit
iommu-helper doesn't want to find such area
- The return value if there is no zero area
find_next_zero_area in iommu helper: returns -1
bitmap_find_next_zero_area: return >= bitmap sizeSigned-off-by: Akinobu Mita
Cc: FUJITA Tomonori
Cc: "David S. Miller"
Cc: Benjamin Herrenschmidt
Cc: Paul Mackerras
Cc: Thomas Gleixner
Cc: Ingo Molnar
Cc: "H. Peter Anvin"
Cc: Greg Kroah-Hartman
Cc: Lothar Wassmann
Cc: Roland Dreier
Cc: Yevgeny Petrilin
Cc: Tony Luck
Cc: Fenghua Yu
Cc: Joerg Roedel
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Use hweight8 instead of counting for each bit
Signed-off-by: Akinobu Mita
Acked-by: Anders Larsen
Cc: Al Viro
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
commit 945ffe54bbd56ceed62de3b908800fd7c6ffb284 ("qnx4: remove write support") removed the (defunct)
write support but missed a chunk of related, dead code.Signed-off-by: Anders Larsen
Cc: Jiri Kosina
Acked-by: Christoph Hellwig
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
resource_size() doesn't change the resource it operates on, so the res
parameter can be marked const. Same for resource_type().Signed-off-by: Jean Delvare
Reviewed-by: WANG Cong
Cc: Greg KH
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
GRU Message queue instructions are used to deliver messages to other SSIs
within the numalink domain. In most cases, a single GRU mesq instruction
will deliver both the message AND an interrupt to notify the other SSI
that a messsage is present. In some cases, however, the interrupt must be
sent explicitly.To improve resilency, the GRU driver should send these explicit interrupts
using the GRU to write the remote chipset register. Current code sends
the interrupt using a cpu instruction to write the chipset register.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Create a function to generate the value that is written to the UV hub MMR
to cause an IPI interrupt to be sent. The function will be used in the
GRU message queue error recovery code that sends IPIs to nodes in remote
partitions.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Update the version number of the GRU driver.
Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Update the TLB dropin statistics kept for each GRU context. Count TLB
dropins separate from the misses - some misses do not result in a TLB
dropin. Some of the diagnostics need both counts.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix a race where an interrupt could be received for a GRU context that has
been deallocated.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add support for hugepages. Easier than I originally thought.
Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix a bug in the assignment of GRU contexts used for kernel functions. If
a sleep occurs on the wait for a semaphore, the thread could switch cpus
and allocate resources on the wrong blade.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add a few new definitions for chipset MMR field names. This matches rev
0.7 of the hardware spec.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Simplify the code that checks for correct assignment of GRU contexts to
users.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Remove a stray local_irq_enable() in the GRU TLB dropin code.
Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Use symbol names instead of numbers for error return values for the vtop
functions.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix a GRU driver bug converting a CBR address to the context that contains
the CBR. The conversion is rarely done so performance does not matter.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add anticipatory TLB dropins for GRU TLB misses that occur on BCOPY
instructions that copy large amounts of data.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Explicitly set GRU instructions to "ACTIVE". This eliminates the need for
barriers that would have been necessary to prevent reading the instruction
"status" field before the GRU had actually started the instruction.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add additional GRU statistics & debug messages.
Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Update the GRU irq allocate/free functions to use the latest upstream
infrastructure.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix several bugs related to prefetch, ordering & speculation:
- GRU cch_allocate() instruction causes cacheable memory
to be created. Add a barriers to prevent speculation
from prefetching data before it exists.
- Add memory barriers before cache-flush instructions to ensure
that previously stored data is included in the line flushed to memory.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix bug caused by failure to allocate a GRU gts structure. The old code
failed to handle the case where the vma was invalid.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Improve existing driver self-tests. Add a new debugging test to the SGI
GRU driver for verifying the global GRU copy function.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add a debug option to the SGI GRU driver for flushing GRU cache lines from
memory. In theory this is not needed but it is useful for debugging.
This has no use by end users.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Under some conditions, mmu_notifier_register() will fail to register a
mmu_notifier. Fix the GRU driver to correctly handle these failures.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Increase the maximum address supported by the SGI GRU driver to a full 64
bits. Note that GRU addresses are not always the same as socket virtual
addresses. Sockets may not necessarily support the full 64 bits.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Improve error messages for malfunctioning GRUs. Identify the type of
instruction that is failing.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix bug in module unload. Previous code was not correctly deleting the
files in /proc.Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
This patch builds on the infrastructure introduced in the patches that
allow user specification of GRU blades & chiplets for context allocation.This patch simplifies the algorithms for migrating GRU contexts between
blades.No new functionality is introduced.
Signed-off-by: Jack Steiner
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
