summaryrefslogtreecommitdiffstats
path: root/include
AgeCommit message (Collapse)AuthorFilesLines
2008-04-21Merge branch 'for-linus' of ↵Linus Torvalds15-78/+144
git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-devel * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-devel: (62 commits) sched: build fix sched: better rt-group documentation sched: features fix sched: /debug/sched_features sched: add SCHED_FEAT_DEADLINE sched: debug: show a weight tree sched: fair: weight calculations sched: fair-group: de-couple load-balancing from the rb-trees sched: fair-group scheduling vs latency sched: rt-group: optimize dequeue_rt_stack sched: debug: add some debug code to handle the full hierarchy sched: fair-group: SMP-nice for group scheduling sched, cpuset: customize sched domains, core sched, cpuset: customize sched domains, docs sched: prepatory code movement sched: rt: multi level group constraints sched: task_group hierarchy sched: fix the task_group hierarchy for UID grouping sched: allow the group scheduler to have multiple levels sched: mix tasks and groups ...
2008-04-21Merge branch 'for-linus' of ↵Linus Torvalds18-426/+308
git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86 * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86: (77 commits) x86: UV startup of slave cpus x86: integrate pci-dma.c x86: don't do dma if mask is NULL. x86: return conditional to mmu x86: remove kludge from x86_64 x86: unify gfp masks x86: retry allocation if failed x86: don't try to allocate from DMA zone at first x86: use a fallback dev for i386 x86: use numa allocation function in i386 x86: remove virt_to_bus in pci-dma_64.c x86: adjust dma_free_coherent for i386 x86: move bad_dma_address x86: isolate coherent mapping functions x86: move dma_coherent functions to pci-dma.c x86: merge iommu initialization parameters x86: merge dma_supported x86: move pci fixup to pci-dma.c x86: move x86_64-specific to common code. x86: move initialization functions to pci-dma.c ...
2008-04-21Merge branch 'ro-bind.b6' of ↵Linus Torvalds3-1/+63
git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6 * 'ro-bind.b6' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (24 commits) [PATCH] r/o bind mounts: debugging for missed calls [PATCH] r/o bind mounts: honor mount writer counts at remount [PATCH] r/o bind mounts: track numbers of writers to mounts [PATCH] r/o bind mounts: check mnt instead of superblock directly [PATCH] r/o bind mounts: elevate count for xfs timestamp updates [PATCH] r/o bind mounts: make access() use new r/o helper [PATCH] r/o bind mounts: write counts for truncate() [PATCH] r/o bind mounts: elevate write count for chmod/chown callers [PATCH] r/o bind mounts: elevate write count for open()s [PATCH] r/o bind mounts: elevate write count for ioctls() [PATCH] r/o bind mounts: write count for file_update_time() [PATCH] r/o bind mounts: elevate write count for do_utimes() [PATCH] r/o bind mounts: write counts for touch_atime() [PATCH] r/o bind mounts: elevate write count for ncp_ioctl() [PATCH] r/o bind mounts: elevate write count for xattr_permission() callers [PATCH] r/o bind mounts: get write access for vfs_rename() callers [PATCH] r/o bind mounts: write counts for link/symlink [PATCH] r/o bind mounts: get callers of vfs_mknod/create/mkdir() [PATCH] r/o bind mounts: elevate write count for rmdir and unlink. [PATCH] r/o bind mounts: drop write during emergency remount ...
2008-04-21Merge git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6Linus Torvalds11-20/+170
* git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6: (27 commits) sh: Fix up L2 cache probe. sh: Fix up SH-4A part probe. sh: Add support for SH7723 CPU subtype. sh: Fix up SH7763 build. sh: Add migor_ts support to MigoR sh: Add rs5c732b RTC support to MigoR sh: Add I2C support to MigoR sh: Add I2C platform data to sh7722 sh: MigoR NAND flash support using gen_flash sh: MigoR NOR flash support using physmap-flash sh: Fix up mach-types formatting from merge damage. sh: r7780rp: Hook up the I2C and SMBus platform devices. sh: Use phyical addresses for MigoR smc91x resources sh: Use physical addresses for sh7722 USBF resources sh: Add MigoR header file Fix sh_keysc double free sh: Fix up __access_ok() check for nommu. sh: Allow optimized clear/copy page routines to be used on SH-2. sh: Hook up the rest of the SH7770 serial ports. sh: Add support for Solution Engine SH7721 board ...
2008-04-21Fix RCU list iterator use of 'rcu_dereference()'Linus Torvalds1-33/+15
The RCU iterators used 'rcu_dereference()' on an already-fetched RCU pointer value, which defeats the whole point of the exercise. When we dereference a pointer protected by RCU, we need to make sure that we only fetch the value _once_, because if the compiler ends up re-loading it due to register pressure, the newly reloaded value could be different from the previously fetched one, and you get inconsistent results. Cleaned-up, fixed, and the pointless list_for_each_safe_rcu #define deleted by Paul Kenney. Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-19sched: fair-group: de-couple load-balancing from the rb-treesPeter Zijlstra2-0/+4
De-couple load-balancing from the rb-trees, so that I can change their organization. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19sched: rt-group: optimize dequeue_rt_stackPeter Zijlstra1-0/+1
Now that the group hierarchy can have an arbitrary depth the O(n^2) nature of RT task dequeues will really hurt. Optimize this by providing space to store the tree path, so we can walk it the other way. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19sched: fair-group: SMP-nice for group schedulingPeter Zijlstra1-0/+1
Implement SMP nice support for the full group hierarchy. On each load-balance action, compile a sched_domain wide view of the full task_group tree. We compute the domain wide view when walking down the hierarchy, and readjust the weights when walking back up. After collecting and readjusting the domain wide view, we try to balance the tasks within the task_groups. The current approach is a naively balance each task group until we've moved the targeted amount of load. Inspired by Srivatsa Vaddsgiri's previous code and Abhishek Chandra's H-SMP paper. XXX: there will be some numerical issues due to the limited nature of SCHED_LOAD_SCALE wrt to representing a task_groups influence on the total weight. When the tree is deep enough, or the task weight small enough, we'll run out of bits. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> CC: Abhishek Chandra <chandra@cs.umn.edu> CC: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19sched, cpuset: customize sched domains, coreHidetoshi Seto4-4/+25
[rebased for sched-devel/latest] - Add a new cpuset file, having levels: sched_relax_domain_level - Modify partition_sched_domains() and build_sched_domains() to take attributes parameter passed from cpuset. - Fill newidle_idx for node domains which currently unused but might be required if sched_relax_domain_level become higher. - We can change the default level by boot option 'relax_domain_level='. Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19sched: fix the task_group hierarchy for UID groupingPeter Zijlstra1-0/+3
UID grouping doesn't actually have a task_group representing the root of the task_group tree. Add one. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19sched: allow the group scheduler to have multiple levelsDhaval Giani1-1/+1
This patch makes the group scheduler multi hierarchy aware. [a.p.zijlstra@chello.nl: rt-parts and assorted fixes] Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19sched: add new set_cpus_allowed_ptr functionMike Travis1-4/+11
Add a new function that accepts a pointer to the "newly allowed cpus" cpumask argument. int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask) The current set_cpus_allowed() function is modified to use the above but this does not result in an ABI change. And with some compiler optimization help, it may not introduce any additional overhead. Additionally, to enforce the read only nature of the new_mask arg, the "const" property is migrated to sub-functions called by set_cpus_allowed. This silences compiler warnings. Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19cpumask: add show cpu map functionsMike Travis1-6/+11
* Add cpu_sysdev_class functions to display the following maps with cpulist_scnprintf(). cpu_online_map cpu_present_map cpu_possible_map * Small change to include/linux/sysdev.h to allow the attribute name and label to be different (to avoid collision with the "attr_online" entry for bringing cpus on- and off-line.) Cc: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19x86: convert cpumask_of_cpu macro to allocated arrayMike Travis1-3/+9
* Here is a simple patch to use an allocated array of cpumasks to represent cpumask_of_cpu() instead of constructing one on the stack. It's based on the Kconfig option "HAVE_CPUMASK_OF_CPU_MAP" which is currently only set for x86_64 SMP. Otherwise the the existing cpumask_of_cpu() is used but has been changed to produce an lvalue so a pointer to it can be used. Cc: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19cpumask: add CPU_MASK_ALL_PTR macroMike Travis1-0/+6
* Add a static cpumask_t variable "CPU_MASK_ALL_PTR" to use as a pointer reference to CPU_MASK_ALL. This reduces where possible the instances where CPU_MASK_ALL allocates and fills a large array on the stack. Used only if NR_CPUS > BITS_PER_LONG. * Change init/main.c to use new set_cpus_allowed_ptr(). Depends on: [sched-devel]: sched: add new set_cpus_allowed_ptr function Cc: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19cpumask: reduce stack usage in SD_x_INIT initializersMike Travis2-43/+8
* Remove empty cpumask_t (and all non-zero/non-null) variables in SD_*_INIT macros. Use memset(0) to clear. Also, don't inline the initializer functions to save on stack space in build_sched_domains(). * Merge change to include/linux/topology.h that uses the new node_to_cpumask_ptr function in the nr_cpus_node macro into this patch. Depends on: [mm-patch]: asm-generic-add-node_to_cpumask_ptr-macro.patch [sched-devel]: sched: add new set_cpus_allowed_ptr function Cc: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19generic: reduce stack pressure in sched_affinityMike Travis1-1/+1
* Modify sched_affinity functions to pass cpumask_t variables by reference instead of by value. * Use new set_cpus_allowed_ptr function. Depends on: [sched-devel]: sched: add new set_cpus_allowed_ptr function Cc: Paul Jackson <pj@sgi.com> Cc: Cliff Wickman <cpw@sgi.com> Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19cpuset: modify cpuset_set_cpus_allowed to use cpumask pointerMike Travis1-6/+7
* Modify cpuset_cpus_allowed to return the currently allowed cpuset via a pointer argument instead of as the function return value. * Use new set_cpus_allowed_ptr function. * Cleanup CPU_MASK_ALL and NODE_MASK_ALL uses. Depends on: [sched-devel]: sched: add new set_cpus_allowed_ptr function Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19asm-generic: add node_to_cpumask_ptr macroMike Travis6-9/+35
Create a simple macro to always return a pointer to the node_to_cpumask(node) value. This relies on compiler optimization to remove the extra indirection: #define node_to_cpumask_ptr(v, node) \ cpumask_t _##v = node_to_cpumask(node), *v = &_##v For those systems with a large cpumask size, then a true pointer to the array element can be used: #define node_to_cpumask_ptr(v, node) \ cpumask_t *v = &(node_to_cpumask_map[node]) A node_to_cpumask_ptr_next() macro is provided to access another node_to_cpumask value. The other change is to always include asm-generic/topology.h moving the ifdef CONFIG_NUMA to this same file. Note: there are no references to either of these new macros in this patch, only the definition. Based on 2.6.25-rc5-mm1 # alpha Cc: Richard Henderson <rth@twiddle.net> # fujitsu Cc: David Howells <dhowells@redhat.com> # ia64 Cc: Tony Luck <tony.luck@intel.com> # powerpc Cc: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> # sparc Cc: David S. Miller <davem@davemloft.net> Cc: William L. Irwin <wli@holomorphy.com> # x86 Cc: H. Peter Anvin <hpa@zytor.com> Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19cpumask: add cpumask_scnprintf_len functionMike Travis2-0/+8
Add a new function cpumask_scnprintf_len() to return the number of characters needed to display "len" cpumask bits. The current method of allocating NR_CPUS bytes is incorrect as what's really needed is 9 characters per 32-bit word of cpumask bits (8 hex digits plus the seperator [','] or the terminating NULL.) This function provides the caller the means to allocate the correct string length. Cc: Paul Jackson <pj@sgi.com> Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19sched: rt-group: synchonised bandwidth periodPeter Zijlstra1-0/+7
Various SMP balancing algorithms require that the bandwidth period run in sync. Possible improvements are moving the rt_bandwidth thing into root_domain and keeping a span per rt_bandwidth which marks throttled cpus. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19time: add ns_to_ktime()Ingo Molnar1-0/+6
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19sched: remove sysctl_sched_batch_wakeup_granularityIngo Molnar1-1/+0
it's unused. Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19x86: UV startup of slave cpusJack Steiner1-0/+1
This patch changes smpboot.c so that it can start slave cpus running in UV non-unique apicid mode. The SIPI must be sent using a UV-specific mechanism. Signed-off-by: Jack Steiner <steiner@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-04-19x86: move dma_coherent functions to pci-dma.cGlauber Costa1-0/+8
They are placed in an ifdef, since they are i386 specific the structure definition goes to dma-mapping.h. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: merge iommu initialization parametersGlauber Costa1-0/+1
we merge the iommu initialization parameters in pci-dma.c Nice thing, that both architectures at least recognize the same parameters. usedac i386 parameter is marked for deprecation Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move pci fixup to pci-dma.cGlauber Costa1-1/+1
via_no_dac provides a fixup that is the same for both architectures. Move it to pci-dma.c. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: use dma_length in i386Glauber Costa1-2/+0
This is done to get the code closer to x86_64. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: delete the arch-specific dma-mapping headers.Glauber Costa3-46/+13
all the code that is left is ready to be merged as-is in dma-mapping.h. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY to dma-mapping.hGlauber Costa2-12/+14
define it conditionally to i386. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: unify dma_mapping_errorGlauber Costa3-14/+8
We provide a map_error function in pci-base_32.c to make sure i386 keeps with the same behaviour it used to. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: provide a bad_dma_address symbol for i386Glauber Costa2-1/+2
It's initially 0, since we don't expect any DMA there. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: align to clflush sizeGlauber Costa1-1/+1
Do it instead of using the conservative approach we're currently doing. This is the way x86_64 does, and this patch makes this piece of code the same between them, ready to be integrated. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_supported and dma_set_mask to pci-dma_32.cGlauber Costa3-33/+3
This is the way x86_64 does, so this make them equal. They have to be extern now in the header, and the extern definition is moved to the common dma-mapping.h header. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_cache_sync to common headerGlauber Costa3-14/+6
they are the same in both architectures. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: dma-ops on highmem fixIngo Molnar1-4/+6
Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_map_page and dma_unmap_page to common headerGlauber Costa3-19/+14
They are similar enough to do this move. the macro version is ugly, and we use inline functions instead. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move alloc and free coherent to common headerGlauber Costa3-20/+10
they are the same between architectures. (except for the fact that x86_64 has duplicate code) move them to dma-mapping.h Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_sync_sg_for_device to common headerGlauber Costa3-19/+11
i386 gets an empty function. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_sync_sg_for_cpu to common headerGlauber Costa3-17/+9
i386 gets an empty function. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_sync_single_range_for_device to common headerGlauber Costa3-20/+14
i386 gets an empty function. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_sync_single_range_for_cpu to common headerGlauber Costa3-19/+11
i386 gets an empty function. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_sync_single_for_device to common headerGlauber Costa3-18/+11
i386 gets an empty function. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_sync_single_for_cpu to common headerGlauber Costa3-17/+12
i386 gets an empty function. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_unmap_sg to common headerGlauber Costa3-16/+9
i386 gets an empty function. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_map_sg to common headerGlauber Costa3-28/+7
the old i386 implementation is moved to pci-base_32.c Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_unmap_single to common headerGlauber Costa3-15/+10
i386 base does not need it, so it gets an empty function. Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: implement dma_map_single through dma_opsGlauber Costa3-19/+10
That's already the name of the game for x86_64. For i386, we add a pci-base_32.c, that will hold the default operations. The function call itself goes through dma-mapping.h , the common header Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: move dma_ops struct definition to dma-mapping.hGlauber Costa2-49/+54
take it off the x86_64 specific header Signed-off-by: Glauber Costa <gcosta@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-04-19x86: reserve dma32 early for gartYinghai Lu1-0/+1
a system with 256 GB of RAM, when NUMA is disabled crashes the following way: Your BIOS doesn't leave a aperture memory hole Please enable the IOMMU option in the BIOS setup This costs you 64 MB of RAM Cannot allocate aperture memory hole (ffff8101c0000000,65536K) Kernel panic - not syncing: Not enough memory for aperture Pid: 0, comm: swapper Not tainted 2.6.25-rc4-x86-latest.git #33 Call Trace: [<ffffffff84037c62>] panic+0xb2/0x190 [<ffffffff840381fc>] ? release_console_sem+0x7c/0x250 [<ffffffff847b1628>] ? __alloc_bootmem_nopanic+0x48/0x90 [<ffffffff847b0ac9>] ? free_bootmem+0x29/0x50 [<ffffffff847ac1f7>] gart_iommu_hole_init+0x5e7/0x680 [<ffffffff847b255b>] ? alloc_large_system_hash+0x16b/0x310 [<ffffffff84506a2f>] ? _etext+0x0/0x1 [<ffffffff847a2e8c>] pci_iommu_alloc+0x1c/0x40 [<ffffffff847ac795>] mem_init+0x45/0x1a0 [<ffffffff8479ff35>] start_kernel+0x295/0x380 [<ffffffff8479f1c2>] _sinittext+0x1c2/0x230 the root cause is : memmap PMD is too big, [ffffe200e0600000-ffffe200e07fffff] PMD ->ffff81383c000000 on node 0 almost near 4G..., and vmemmap_alloc_block will use up the ram under 4G. solution will be: 1. make memmap allocation get memory above 4G... 2. reserve some dma32 range early before we try to set up memmap for all. and release that before pci_iommu_alloc, so gart or swiotlb could get some range under 4g limit for sure. the patch is using method 2. because method1 may need more code to handle SPARSEMEM and SPASEMEM_VMEMMAP will get Your BIOS doesn't leave a aperture memory hole Please enable the IOMMU option in the BIOS setup This costs you 64 MB of RAM Mapping aperture over 65536 KB of RAM @ 4000000 Memory: 264245736k/268959744k available (8484k kernel code, 4187464k reserved, 4004k data, 724k init) Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
generated by cgit v1.2.3 (git 2.46.0) at 2026-03-17 22:57:13 +0000