- 01 Dec, 2009 1 commit
-
-
H. Peter Anvin authored
The semantics the PAT code expect of is_untracked_pat_range() is "is this range completely contained inside the untracked region." This means that checkin 8a271389 was technically wrong, because the implementation needlessly confusing. The sane interface is for it to take a semiclosed range like just about everything else (as evidenced by the sheer number of "- 1"'s removed by that patch) so change the actual implementation to match. Reported-by:
Suresh Siddha <suresh.b.siddha@intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Jack Steiner <steiner@sgi.com> Signed-off-by:
H. Peter Anvin <hpa@zytor.com> LKML-Reference: <20091119202341.GA4420@sgi.com>
-
- 26 Nov, 2009 1 commit
-
-
Xiaotian Feng authored
If pat is disabled (boot with nopat), there's no need to create debugfs for it, it's empty all the time. Signed-off-by:
Xiaotian Feng <dfeng@redhat.com> Cc: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> LKML-Reference: <1259236428-16329-1-git-send-email-dfeng@redhat.com> Signed-off-by:
Ingo Molnar <mingo@elte.hu>
-
- 24 Nov, 2009 6 commits
-
-
Yinghai Lu authored
In some cases we can coalesce MTRR entries after cleanup; this may allow us to have more entries. As such, introduce clean_sort_range to to sort and coaelsce the MTRR entries. Signed-off-by:
Yinghai Lu <yinghai@kernel.org> LKML-Reference: <4B0BB9A3.5020908@kernel.org> Signed-off-by:
-
Yinghai Lu authored
Move the find_smp_config() call to before bootmem is initialized. Use reserve_early() instead of reserve_bootmem() in it. This simplifies the code, we only need to call find_smp_config() once and can remove the now unneeded reserve parameter from x86_init_mpparse::find_smp_config. We thus also reduce x86's dependency on bootmem allocations. Signed-off-by:
-
H. Peter Anvin authored
- Change is_untracked_pat_range() to return bool. - Clean up the initialization of is_untracked_pat_range() -- by default, we simply point it at is_ISA_range() directly. - Move is_untracked_pat_range to the end of struct x86_platform, since it is the newest field. Signed-off-by:
Thomas Gleixner <tglx@linutronix.de> Cc: Jack Steiner <steiner@sgi.com> LKML-Reference: <20091119202341.GA4420@sgi.com>
-
H. Peter Anvin authored
Change is_ISA_range() from a macro to an inline function. This makes it type safe, and also allows it to be assigned to a function pointer if necessary. Signed-off-by:
-
H. Peter Anvin authored
is_untracked_pat_range() -- like its components, is_ISA_range() and is_GRU_range(), takes a normal semiclosed interval (>=, <) whereas the PAT code called it as if it took a closed range (>=, <=). Fix. Although this is a bug, I believe it is non-manifest, simply because none of the callers will call this with non-page-aligned addresses. Signed-off-by:
-
H. Peter Anvin authored
Checkin fd12a0d6 made the PAT untracked range a platform configurable, but missed on occurrence of is_ISA_range() which still refers to PAT-untracked memory, and therefore should be using the configurable. Signed-off-by:
-
- 23 Nov, 2009 5 commits
-
-
Jack Steiner authored
GRU space is always mapped as WB in the page table. There is no need to track the mappings in the PAT. This also eliminates the "freeing invalid memtype" messages when the GRU space is unmapped. Signed-off-by:
Jack Steiner <steiner@sgi.com> LKML-Reference: <20091119202341.GA4420@sgi.com> [ v2: fix build failure ] Signed-off-by:
-
Cliff Wickman authored
A memory mapped register that affects the SGI UV Broadcast Assist Unit's interrupt handling may sometimes be unintialized. Remove the condition on its initialization, as that condition can be randomly satisfied by a hardware reset. Signed-off-by:
Cliff Wickman <cpw@sgi.com> Cc: <stable@kernel.org> LKML-Reference: <E1NBGB9-0005nU-Dp@eag09.americas.sgi.com> Signed-off-by:
-
Yinghai Lu authored
CPU to node mapping is set via the following sequence: 1. numa_init_array(): Set up roundrobin from cpu to online node 2. init_cpu_to_node(): Set that according to apicid_to_node[] according to srat only handle the node that is online, and leave other cpu on node without ram (aka not online) to still roundrobin. 3. later call srat_detect_node for Intel/AMD, will use first_online node or nearby node. Problem is that setup_per_cpu_areas() is not called between 2 and 3, the per_cpu for cpu on node with ram is on different node, and could put that on node with two hops away. So try to optimize this and add find_near_online_node() and call init_cpu_to_node(). Signed-off-by:
-
Yinghai Lu authored
In the NUMA bootmem setup failure path we freed nodedata_phys incorrectly. Signed-off-by:
-
Yinghai Lu authored
use find_e820_area()/reserve_early() instead. -v2: address Eric's request, to restore original semantics. will fail, if the provided address can not be used. Signed-off-by:Eric W. Biederman <ebiederm@xmission.com> LKML-Reference: <4B09E2F9.7040403@kernel.org> Signed-off-by:
-
- 19 Nov, 2009 1 commit
-
-
Jan Beulich authored
Rather than having X86_L1_CACHE_BYTES and X86_L1_CACHE_SHIFT (with inconsistent defaults), just having the latter suffices as the former can be easily calculated from it. To be consistent, also change X86_INTERNODE_CACHE_BYTES to X86_INTERNODE_CACHE_SHIFT, and set it to 7 (128 bytes) for NUMA to account for last level cache line size (which here matters more than L1 cache line size). Finally, make sure the default value for X86_L1_CACHE_SHIFT, when X86_GENERIC is selected, is being seen before that for the individual CPU model options (other than on x86-64, where GENERIC_CPU is part of the choice construct, X86_GENERIC is a separate option on ix86). Signed-off-by:
Jan Beulich <jbeulich@novell.com> Acked-by:
Ravikiran Thirumalai <kiran@scalex86.org> Acked-by:
Nick Piggin <npiggin@suse.de> LKML-Reference: <4AFD5710020000780001F8F0@vpn.id2.novell.com> Signed-off-by:
-
- 17 Nov, 2009 1 commit
-
-
Yinghai Lu authored
The current MTRR code treats WP as a form of UC. This really isn't desirable behaviour, except possibly in the case of severe MTRR shortage. Disable this, to allow legitimate uses of WP to remain unmolested. Signed-off-by:
-
- 16 Nov, 2009 6 commits
-
-
H. Peter Anvin authored
Function prototypes don't need "extern", and it is generally frowned upon to have them. Signed-off-by: -
Kees Cook authored
It is possible for x86_64 systems to lack the NX bit either due to the hardware lacking support or the BIOS having turned off the CPU capability, so NX status should be reported. Additionally, anyone booting NX-capable CPUs in 32bit mode without PAE will lack NX functionality, so this change provides feedback for that case as well. Signed-off-by:
Kees Cook <kees.cook@canonical.com> Signed-off-by:
-
H. Peter Anvin authored
The 32- and 64-bit code used very different mechanisms for enabling NX, but even the 32-bit code was enabling NX in head_32.S if it is available. Furthermore, we had a bewildering collection of tests for the available of NX. This patch: a) merges the 32-bit set_nx() and the 64-bit check_efer() function into a single x86_configure_nx() function. EFER control is left to the head code. b) eliminates the nx_enabled variable entirely. Things that need to test for NX enablement can verify __supported_pte_mask directly, and cpu_has_nx gives the supported status of NX. Signed-off-by:
-
H. Peter Anvin authored
Make set_memory_x/set_memory_nx directly aware of if NX is supported in the system or not, rather than requiring that every caller assesses that support independently. Signed-off-by:
-
H. Peter Anvin authored
Always save the value of EFER, regardless of the state of NX. Since EFER may not actually exist, use rdmsr_safe() to do so. v2: check the return value from rdmsr_safe() instead of relying on the output values being unchanged on error. Signed-off-by:Rafael J. Wysocki <rjw@sisk.pl> Cc: Pavel Machek <pavel@ucw.cz> Cc: Nigel Cunningham <nigel@tuxonice.net> LKML-Reference: <1258154897-6770-3-git-send-email-hpa@zytor.com> Acked-by:
-
H. Peter Anvin authored
Use symbolic constants rather than hard-coded values when setting EFER.NX in head_32.S, and do a more rigorous test for the validity of the response when probing for the extended CPUID range. Signed-off-by:
-
- 11 Nov, 2009 1 commit
-
-
Yinghai Lu authored
Instead of using bootmem, try find_e820_area()/reserve_early(), and call acpi_reserve_memory() early, to allocate the wakeup trampoline code area below 1M. This is more reliable, and it also removes a dependency on bootmem. -v2: change function name to acpi_reserve_wakeup_memory(), as suggested by Rafael. Signed-off-by:
-
- 08 Nov, 2009 1 commit
-
-
Randy Dunlap authored
k8.h uses struct bootnode but does not #include a header file for it, so provide a simple declaration for it. arch/x86/include/asm/k8.h:13: warning: 'struct bootnode' declared inside parameter list arch/x86/include/asm/k8.h:13: warning: its scope is only this definition or declaration, which is probably not what you want Signed-off-by:
Randy Dunlap <randy.dunlap@oracle.com> Acked-by:
David Rientjes <rientjes@google.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> LKML-Reference: <20091028160955.d27ccb16.randy.dunlap@oracle.com> Signed-off-by:
-
- 02 Nov, 2009 3 commits
-
-
Suresh Siddha authored
set_kernel_text_rw()/set_kernel_text_ro() are marking pages starting from _text to __start_rodata as RW or RO. With CONFIG_DEBUG_RODATA, there might be free pages (associated with padding the sections to 2MB large page boundary) between text and rodata sections that are given back to page allocator. So we should use only use the start (__text) and end (__stop___ex_table) of the text section in set_kernel_text_rw()/set_kernel_text_ro(). Signed-off-by:
Steven Rostedt <rostedt@goodmis.org> Tested-by:
-
Suresh Siddha authored
On x86_64, kernel text mappings are mapped read-only with CONFIG_DEBUG_RODATA. So use the kernel identity mapping instead of the kernel text mapping to modify the kernel text. Signed-off-by:
-
Suresh Siddha authored
Steven Rostedt reported that we are unconditionally making the kernel text mapping as read-only. i.e., if someone does cpa() to the kernel text area for setting/clearing any page table attribute, we unconditionally clear the read-write attribute for the kernel text mapping that is set at compile time. We should delay (to forbid the write attribute) and enforce only after the kernel has mapped the text as read-only. Reported-by:
-
- 27 Oct, 2009 1 commit
-
-
Steven Rostedt authored
The commit 74e08179 x86-64: align RODATA kernel section to 2MB with CONFIG_DEBUG_RODATA prevents text sections from becoming read/write using set_memory_rw. The dynamic ftrace changes all text pages to read/write just before converting the calls to tracing to nops, and vice versa. I orginally just added a flag to allow this transaction when ftrace did the change, but I also found that when the CPA testing was running it would remove the read/write as well, and ftrace does not do the text conversion on boot up, and the CPA changes caused the dynamic tracer to fail on self tests. The current solution I have is to simply not to prevent change_page_attr from setting the RW bit for kernel text pages. Reported-by:
-
- 24 Oct, 2009 1 commit
-
-
Alexander Potashev authored
A single 'movl' is shorter than the 'xorl'-'orl' pair. No change in behaviour. Signed-off-by:
Alexander Potashev <aspotashev@gmail.com> LKML-Reference: <1256341043-4928-1-git-send-email-aspotashev@gmail.com> Signed-off-by:
-
- 23 Oct, 2009 1 commit
-
-
Minchan Kim authored
commit cc9f7a0c changed add_one_highpage_init. We don't use pfn any more. Let's remove unnecessary argument. This patch doesn't chage function behavior. This patch is based on v2.6.32-rc5. Signed-off-by:
Minchan Kim <minchan.kim@gmail.com> Cc: Yinghai Lu <yhlu.kernel@gmail.com> LKML-Reference: <20091022112722.adc8e55c.minchan.kim@barrios-desktop> Signed-off-by:
-
- 20 Oct, 2009 3 commits
-
-
Suresh Siddha authored
Add a comment explaining why RODATA is aligned to 2 MB. Signed-off-by:
-
Suresh Siddha authored
CONFIG_DEBUG_RODATA chops the large pages spanning boundaries of kernel text/rodata/data to small 4KB pages as they are mapped with different attributes (text as RO, RODATA as RO and NX etc). On x86_64, preserve the large page mappings for kernel text/rodata/data boundaries when CONFIG_DEBUG_RODATA is enabled. This is done by allowing the RODATA section to be hugepage aligned and having same RWX attributes for the 2MB page boundaries Extra Memory pages padding the sections will be freed during the end of the boot and the kernel identity mappings will have different RWX permissions compared to the kernel text mappings. Kernel identity mappings to these physical pages will be mapped with smaller pages but large page mappings are still retained for kernel text,rodata,data mappings. Signed-off-by:
-
Suresh Siddha authored
In the first 2MB, kernel text is co-located with kernel static page tables setup by head_64.S. CONFIG_DEBUG_RODATA chops this 2MB large page mapping to small 4KB pages as we mark the kernel text as RO, leaving the static page tables as RW. With CONFIG_DEBUG_RODATA disabled, OLTP run on NHM-EP shows 1% improvement with 2% reduction in system time and 1% improvement in iowait idle time. To recover this, move the kernel static page tables to .data section, so that we don't have to break the first 2MB of kernel text to small pages with CONFIG_DEBUG_RODATA. Signed-off-by:
-
- 12 Oct, 2009 4 commits
-
-
David Rientjes authored
Add interleaved NUMA emulation support This patch interleaves emulated nodes over the system's physical nodes. This is required for interleave optimizations since mempolicies, for example, operate by iterating over a nodemask and act without knowledge of node distances. It can also be used for testing memory latencies and NUMA bugs in the kernel. There're a couple of ways to do this: - divide the number of emulated nodes by the number of physical nodes and allocate the result on each physical node, or - allocate each successive emulated node on a different physical node until all memory is exhausted. The disadvantage of the first option is, depending on the asymmetry in node capacities of each physical node, emulated nodes may substantially differ in size on a particular physical node compared to another. The disadvantage of the second option is, also depending on the asymmetry in node capacities of each physical node, there may be more emulated nodes allocated on a single physical node as another. This patch implements the second option; we sacrifice the possibility that we may have slightly more emulated nodes on a particular physical node compared to another in lieu of node size asymmetry. [ Note that "node capacity" of a physical node is not only a function of its addressable range, but also is affected by subtracting out the amount of reserved memory over that range. NUMA emulation only deals with available, non-reserved memory quantities. ] We ensure there is at least a minimal amount of available memory allocated to each node. We also make sure that at least this amount of available memory is available in ZONE_DMA32 for any node that includes both ZONE_DMA32 and ZONE_NORMAL. This patch also cleans the emulation code up by no longer passing the statically allocated struct bootnode array among the various functions. This init.data array is not allocated on the stack since it may be very large and thus it may be accessed at file scope. The WARN_ON() for nodes_cover_memory() when faking proximity domains is removed since it relies on successive nodes always having greater start addresses than previous nodes; with interleaving this is no longer always true. Signed-off-by:
-
David Rientjes authored
This is the counterpart to "x86: export k8 physical topology" for SRAT. It is not as invasive because the acpi code already seperates node setup into detection and registration steps, with the exception of registering e820 active regions in acpi_numa_memory_affinity_init(). This is now moved to acpi_scan_nodes() if NUMA emulation is disabled or deferred. acpi_numa_init() now returns a value which specifies whether an underlying SRAT was located. If so, that topology can be used by the emulation code to interleave emulated nodes over physical nodes or to register the nodes for ACPI. acpi_get_nodes() may now be used to export the srat physical topology of the machine for NUMA emulation. Signed-off-by:
-
David Rientjes authored
To eventually interleave emulated nodes over physical nodes, we need to know the physical topology of the machine without actually registering it. This does the k8 node setup in two parts: detection and registration. NUMA emulation can then used the physical topology detected to setup the address ranges of emulated nodes accordingly. If emulation isn't used, the k8 nodes are registered as normal. Two formals are added to the x86 NUMA setup functions: `acpi' and `k8'. These represent whether ACPI or K8 NUMA has been detected; both cannot be true at the same time. This specifies to the NUMA emulation code whether an underlying physical NUMA topology exists and which interface to use. This patch deals solely with separating the k8 setup path into Northbridge detection and registration steps and leaves the ACPI changes for a subsequent patch. The `acpi' formal is added here, however, to avoid touching all the header files again in the next patch. This approach also ensures emulated nodes will not span physical nodes so the true memory latency is not misrepresented. k8_get_nodes() may now be used to export the k8 physical topology of the machine for NUMA emulation. Signed-off-by:
-
David Rientjes authored
Convert all printk's in arch/x86/mm/k8topology_64.c to use pr_info() or pr_err() appropriately. Adds log levels for messages currently lacking them. Signed-off-by:
-
- 11 Oct, 2009 4 commits
-
-
Linus Torvalds authored
This reverts commit db8be50c, as per http://bugzilla.kernel.org/show_bug.cgi?id=14374 http://marc.info/?l=linux-kernel&m=125446885705223&w=4 We simply can't do the USB handoff at FIXUP_HEADER time, since it will often require us to have valid IO mappings etc. But that in turn requires a whole different approach, not this trivial one-liner. Maybe we could teach all the USB quirk handoff handlers to only do the quirk if the device has all its registers set up (since if it isn't initialized, it's unlikely to be active), but regardless that will need a whole lot more code than just saying "let's do it really early". The proper fix is almost certainly to just leave the legacy IOMMU mappings active until after all devices have been initialized. Reported-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Linus Torvalds authored
-
Yinghai Lu authored
As reported in http://bugzilla.kernel.org/show_bug.cgi?id=13940 on some system when acpi are enabled, acpi clears some BAR for some devices without reason, and kernel will need to allocate devices for them. It then apparently hits some undocumented resource conflict, resulting in non-working devices. Try to increase alignment to get more safe range for unassigned devices. Signed-off-by:
-
git://git390.marist.edu/pub/scm/linux-2.6Linus Torvalds authored
* 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6: (21 commits) [S390] dasd: fix race condition in resume code [S390] Add EX_TABLE for addressing exception in usercopy functions. [S390] 64-bit register support for 31-bit processes [S390] hibernate: Use correct place for CPU address in lowcore [S390] pm: ignore time spend in suspended state [S390] zcrypt: Improve some comments [S390] zcrypt: Fix sparse warning. [S390] perf_counter: fix vdso detection [S390] ftrace: drop nmi protection [S390] compat: fix truncate system call wrapper [S390] Provide arch specific mdelay implementation. [S390] Fix enabled udelay for short delays. [S390] cio: allow setting boxed devices offline [S390] cio: make not operational handling consistent [S390] cio: make disconnected handling consistent [S390] Fix memory leak in /proc/cio_ignore [S390] cio: channel path memory leak [S390] module: fix memory leak in s390 module loader [S390] Enable kmemleak on s390. [S390] 3270 console build fix ...
-
