aboutsummaryrefslogtreecommitdiffstats
path: root/arch/arm/mm
Commit message (Collapse)AuthorAge
* [PATCH] mm: arch do_page_fault() vs in_atomic()Peter Zijlstra2006-12-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In light of the recent pagefault and filemap_copy_from_user work I've gone through all the arch pagefault handlers to make sure the inc_preempt_count() 'feature' works as expected. Several sections of code (including the new filemap_copy_from_user) rely on the fact that faults do not take locks under increased preempt count. arch/x86_64 - good arch/powerpc - good arch/cris - fixed arch/i386 - good arch/parisc - fixed arch/sh - good arch/sparc - good arch/s390 - good arch/m68k - fixed arch/ppc - good arch/alpha - fixed arch/mips - good arch/sparc64 - good arch/ia64 - good arch/arm - fixed arch/um - good arch/avr32 - good arch/h8300 - NA arch/m32r - good arch/v850 - good arch/frv - fixed arch/m68knommu - NA arch/arm26 - fixed arch/sh64 - fixed arch/xtensa - good Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Fix misc Kconfig typosMatt LaPlante2006-11-29
| | | | | | | | Fix various Kconfig typos. Signed-off-by: Matt LaPlante <kernel1@cyberdogtech.com> Acked-by: Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by: Adrian Bunk <bunk@stusta.de>
* [ARM] 3942/1: ARM: comment: consistent_sync should not be called directlyDan Williams2006-11-22
| | | | | | | | | | | /* * Note: Drivers should NOT use this function directly, as it will break * platforms with CONFIG_DMABOUNCE. * Use the driver DMA support - see dma-mapping.h (dma_sync_*) */ Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3927/1: Allow show_mem() to work with holes in memory map.Ray Lehtiniemi2006-11-07
| | | | | | | | | | | | | | | | | show_mem() was not correctly handling holes in the memory map. It was treating the freed sections of the map as though they contained valid struct page entries. This could cause incorrect debugging output or even a kernel panic. This patch keeps the struct meminfo around after system initialization so that show_mem() can use it when scanning memory. show_mem() now walks over each bank of each online node, rather than assuming that each node contains a single contiguous bank. Signed-off-by: Ray Lehtiniemi <rayl@mail.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3912/1: Make PXA270 advertise HWCAP_IWMMXT capabilityPaul Gortmaker2006-11-02
| | | | | | | | | | | | | ARM patch 3756/1 added HWCAP_IWMMXT. This patch adds support for broadcasting that info via /proc/cpuinfo and sets it for the CPU features of the PXA270. I've booted 19rc3 on a pxa270 and confirmed that the /proc/cpuinfo shows "iwmmxt" in the Features. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [PATCH] arm: it's OK to pass pointer to volatile as iounmap() argument...Al Viro2006-10-08
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Merge branch 'devel' of master.kernel.org:/home/rmk/linux-2.6-armLinus Torvalds2006-10-03
|\ | | | | | | | | | | | | | | | | | | * 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm: [ARM] 3848/1: pxafb: Add option of fixing video modes and spitz QVGA mode support [ARM] 3880/1: remove the last trace of iop31x support [ARM] 3879/1: ep93xx: instantiate platform devices for ep93xx ethernet [ARM] 3809/3: get rid of 4 megabyte kernel image size limit [ARM] Fix XIP_KERNEL build error in arch/arm/mm/mmu.c [ARM] 3874/1: Remove leftover usage of asm/timeofday.h
| * [ARM] Fix XIP_KERNEL build error in arch/arm/mm/mmu.cRussell King2006-09-30
| | | | | | | | | | | | | | XIP kernels need to know the start/end of text, but we were missing the declaration of _etext in mmu.c. Add it. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* | [PATCH] pidspace: is_init()Sukadev Bhattiprolu2006-09-29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is an updated version of Eric Biederman's is_init() patch. (http://lkml.org/lkml/2006/2/6/280). It applies cleanly to 2.6.18-rc3 and replaces a few more instances of ->pid == 1 with is_init(). Further, is_init() checks pid and thus removes dependency on Eric's other patches for now. Eric's original description: There are a lot of places in the kernel where we test for init because we give it special properties. Most significantly init must not die. This results in code all over the kernel test ->pid == 1. Introduce is_init to capture this case. With multiple pid spaces for all of the cases affected we are looking for only the first process on the system, not some other process that has pid == 1. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Serge Hallyn <serue@us.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: <lxc-devel@lists.sourceforge.net> Acked-by: Paul Mackerras <paulus@samba.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* | [PATCH] make PROT_WRITE imply PROT_READJason Baron2006-09-29
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Make PROT_WRITE imply PROT_READ for a number of architectures which don't support write only in hardware. While looking at this, I noticed that some architectures which do not support write only mappings already take the exact same approach. For example, in arch/alpha/mm/fault.c: " if (cause < 0) { if (!(vma->vm_flags & VM_EXEC)) goto bad_area; } else if (!cause) { /* Allow reads even for write-only mappings */ if (!(vma->vm_flags & (VM_READ | VM_WRITE))) goto bad_area; } else { if (!(vma->vm_flags & VM_WRITE)) goto bad_area; } " Thus, this patch brings other architectures which do not support write only mappings in-line and consistent with the rest. I've verified the patch on ia64, x86_64 and x86. Additional discussion: Several architectures, including x86, can not support write-only mappings. The pte for x86 reserves a single bit for protection and its two states are read only or read/write. Thus, write only is not supported in h/w. Currently, if i 'mmap' a page write-only, the first read attempt on that page creates a page fault and will SEGV. That check is enforced in arch/blah/mm/fault.c. However, if i first write that page it will fault in and the pte will be set to read/write. Thus, any subsequent reads to the page will succeed. It is this inconsistency in behavior that this patch is attempting to address. Furthermore, if the page is swapped out, and then brought back the first read will also cause a SEGV. Thus, any arbitrary read on a page can potentially result in a SEGV. According to the SuSv3 spec, "if the application requests only PROT_WRITE, the implementation may also allow read access." Also as mentioned, some archtectures, such as alpha, shown above already take the approach that i am suggesting. The counter-argument to this raised by Arjan, is that the kernel is enforcing the write only mapping the best it can given the h/w limitations. This is true, however Alan Cox, and myself would argue that the inconsitency in behavior, that is applications can sometimes work/sometimes fails is highly undesireable. If you read through the thread, i think people, came to an agreement on the last patch i posted, as nobody has objected to it... Signed-off-by: Jason Baron <jbaron@redhat.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Andi Kleen <ak@muc.de> Acked-by: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Arjan van de Ven <arjan@linux.intel.com> Acked-by: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Ian Molton <spyro@f2s.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Merge branch 'devel' of master.kernel.org:/home/rmk/linux-2.6-armLinus Torvalds2006-09-28
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm: (130 commits) [ARM] 3856/1: Add clocksource for Intel IXP4xx platforms [ARM] 3855/1: Add generic time support [ARM] 3873/1: S3C24XX: Add irq_chip names [ARM] 3872/1: S3C24XX: Apply consistant tabbing to irq_chips [ARM] 3871/1: S3C24XX: Fix ordering of EINT4..23 [ARM] nommu: confirms the CR_V bit in nommu mode [ARM] nommu: abort handler fixup for !CPU_CP15_MMU cores. [ARM] 3870/1: AT91: Start removing static memory mappings [ARM] 3869/1: AT91: NAND support for DK and KB9202 boards [ARM] 3868/1: AT91 hardware header update [ARM] 3867/1: AT91 GPIO update [ARM] 3866/1: AT91 clock update [ARM] 3865/1: AT91RM9200 header updates [ARM] 3862/2: S3C2410 - add basic power management support for AML M5900 series [ARM] kthread: switch arch/arm/kernel/apm.c [ARM] Off-by-one in arch/arm/common/icst* [ARM] 3864/1: Refactore sharpsl_pm [ARM] 3863/1: Add Locomo SPI Device [ARM] 3847/2: Convert LOMOMO to use struct device for GPIOs [ARM] Use CPU_CACHE_* where possible in asm/cacheflush.h ...
| * [ARM] nommu: confirms the CR_V bit in nommu modeHyok S. Choi2006-09-28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | In nommu mode, the exception vector location depends on the platforms. Some of the implementations may have some special exception control forwarding method in their ROM/flash and for some of them has its own re-mapping mechanism by the h/w. This patch introduces a special configuration CONFIG_CPU_HIGH_VECTOR which turns on the CR_V bit in nommu mode. The CR_V bit is turned off by default. This feature depends on CP15 and does not supported by ARM740. Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] nommu: abort handler fixup for !CPU_CP15_MMU cores.Hyok S. Choi2006-09-28
| | | | | | | | | | | | | | | | | | | | There is no FSR/FAR register on no-CP15 or MPU cores. This patch adds a dummy abort handler which returns zero for the base restored Data Abort model !CPU_CP15_MMU cores. The abort-lv4t.S is still used with the fix-up for the base updated Data Abort model cores. Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] Make !MMU CPUs depend on !MMURussell King2006-09-27
| | | | | | | | | | | | | | Don't offer non-MMU based CPUs for selection when CONFIG_MMU is set. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] nommu: add ARM946E-S core supportHyok S. Choi2006-09-27
| | | | | | | | | | | | | | | | | | | | | | This patch adds ARM946E-S core support which has typically 8KB I&D cache. It has a MPU and supports ARMv5TE instruction set. Because the ARM946E-S core can be synthesizable with various cache size, CONFIG_CPU_DCACHE_SIZE is defined for vendor specific configurations. Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] nommu: add ARM940T core supportHyok S. Choi2006-09-27
| | | | | | | | | | | | | | | | This patch adds ARM940T core support which has 4KB D-cache, 4KB I-cache and a MPU. Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] nommu: add ARM9TDMI core supportHyok S. Choi2006-09-27
| | | | | | | | | | | | | | | | This patch adds ARM9TDMI core support which has no cache and no CP15 register(no memory control unit). Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] nommu: add ARM740T core supportHyok S. Choi2006-09-27
| | | | | | | | | | | | | | This patch adds ARM740T core support which has a MPU and 4KB or 8KB cache. Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] nommu: add ARM7TDMI core supportHyok S. Choi2006-09-27
| | | | | | | | | | | | | | | | This patch adds ARM7TDMI core support which has no cache and no CP15 register(no memory control unit). Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] nommu: manage the CP15 thingsHyok S. Choi2006-09-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | All the current CP15 access codes in ARM arch can be categorized and conditioned by the defines as follows: Related operation Safe condition a. any CP15 access !CPU_CP15 b. alignment trap CPU_CP15_MMU c. D-cache(C-bit) CPU_CP15 d. I-cache CPU_CP15 && !( CPU_ARM610 || CPU_ARM710 || CPU_ARM720 || CPU_ARM740 || CPU_XSCALE || CPU_XSC3 ) e. alternate vector CPU_CP15 && !CPU_ARM740 f. TTB CPU_CP15_MMU g. Domain CPU_CP15_MMU h. FSR/FAR CPU_CP15_MMU For example, alternate vector is supported if and only if "CPU_CP15 && !CPU_ARM740" is satisfied. Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] nommu: defines CPU_CP15, CPU_CP15_MMU and CPU_CP15_MPUHyok S. Choi2006-09-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | By merging of uClinux/ARM, we need to treat various CPU cores which have MMU, MPU or even none for memory management. The memory management coprocessors are controlled by CP15 register set and the ARM core family can be categorized by 5 groups by the register ; G-a. CP15 is MMU : 610, 710, 720, 920, 922, 925, 926, 1020, 1020e, 1022, v6 and the derivations sa1100, sa110, xscale, xsc3. G-b. CP15 is MPU : 740, 940, 946, 996, 1156. G-c. CP15 is MPU or MMU : 1026 (selectable by schematic design) G-d. CP15 is exist, but nothing for memory managemnt : 966, 968. G-e. no-CP15 : 7tdmi, 9tdmi, 9e, 9ej This patch defines CPU_CP15, CPU_CP15_MMU and CPU_CP15_MPU. Thus the family can be defined as : - CPU_CP15 only : G-d - CPU_CP15_MMU(implies CPU_CP15) : G-a, G-c(selectable) - CPU_CP15_MPU(implies CPU_CP15) : G-b, G-c(selectable) - !CPU_CP15 : G-e Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] do_bad_area() always takes current and current->active_mmRussell King2006-09-27
| | | | | | | | | | | | | | | | | | Since do_bad_area() always takes the currently active task and (supposed to) take the currently active MM, there's no point passing them to this function. Instead, obtain references to them inside do_bad_area(). Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] Add setup_mm_for_reboot() for nommuRussell King2006-09-27
| | | | | | | | | | | | Add an empty setup_mm_for_reboot() function for nommu machines. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] Rename mm-armv.c to pgd.cRussell King2006-09-27
| | | | | | | | | | | | | | mm-armv.c now only contains the pgd allocation/freeing code, so rename it to have a more sensible filename. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] Move rest of MMU setup code from mm-armv.c to mmu.cRussell King2006-09-27
| | | | | | | | | | | | | | | | | | If we're going to have mmu.c for code which is specific to the MMU machines, we might as well move the other MMU initialisation specific code from mm-armv.c into this new file. This also allows us to make some functions static. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] Split ARM MM initialisation for !mmuRussell King2006-09-27
| | | | | | | | | | | | | | Move the MMU specific code from init.c into mmu.c, and add nommu fixups to nommu.c Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] Separate page table manipulation code from bootmem initialisationRussell King2006-09-27
| | | | | | | | | | | | | | | | nommu does not require the page table manipulation code in the bootmem initialisation paths. Move this into separate inline functions. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] 3859/1: Fix devicemaps_init() XIP_KERNEL odd 1MiB XIP_PHYS_ADDR ↵George G. Davis2006-09-27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | translation error The ARM XIP_KERNEL map created in devicemaps_init() is wrong. The map.pfn is rounded down to an even 1MiB section boundary which results in va/pa translations errors when XIP_PHYS_ADDR starts on an odd 1MiB boundary and this causes the kernel to hang. This patch fixes ARM XIP_KERNEL translation errors for the odd 1MiB XIP_PHYS_ADDR boundary case. Signed-off-by: George G. Davis <gdavis@mvista.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] 3853/1: Fix flush_ptrace_access() thinko for nonaliasing VIPT cache caseGeorge G. Davis2006-09-25
| | | | | | | | | | | | | | | | | | | | Fix thinko in the flush_ptrace_access() "if (expr)" for the ARM VIPT non-aliasing cache case. We only need to flush cache when VM_EXEC is set in vma->vm_flags but "if (expr) always evaluates to true on UP systems for the ARM VIPT non-aliasing cache case. Signed-off-by: George G. Davis <gdavis@mvista.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] 3817/1: iop3xx: split the iop3xx mach into iop32x and iop33xLennert Buytenhek2006-09-25
| | | | | | | | | | | | | | | | | | Split the iop3xx mach type into iop32x and iop33x -- split the config symbols, and move the code in the mach-iop3xx directory to the mach-iop32x and mach-iop33x directories. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] 3814/1: move 80200 dma_inv_range() erratum check out of lineLennert Buytenhek2006-09-25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | On stepping A0/A1 of the 80200, invalidating D-cache by line doesn't clear the dirty bits, which means that if we invalidate a dirty line, the dirty data can still be written back to memory later on. To work around this, dma_inv_range() on these two processors is implemented as dma_flush_range() (i.e. do a clean D-cache line before doing the invalidate D-cache line.) For this, we currently have a processor ID check in xscale_dma_inv_range(), but a better solution is to add a separate cache_fns and proc_info for A0/A1 80200. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] 3813/1: prevent >= 4G /dev/mem mmap()Lennert Buytenhek2006-09-25
| | | | | | | | | | | | | | | | | | | | | | | | Prevent userland from mapping in physical address regions >= 4G by checking for that in valid_mmap_phys_addr_range(). Unfortunately, we cannot override valid_mmap_phys_addr_range() without also overriding valid_phys_addr_range(), so copy drivers/char/mem.c's version of valid_phys_addr_range() over to arch/arm/mm/mmap.c as well. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] Move mmu.c out of the wayRussell King2006-09-20
| | | | | | | | | | | | | | Rename mmu.c to context.c - it's the ARMv6 ASID context handling code rather than generic "mmu" handling code. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * [ARM] Cleanup arch/arm/mm a littleRussell King2006-09-20
| | | | | | | | | | | | | | | | | | | | Move top_pmd into arch/arm/mm/mm.h - nothing outside arch/arm/mm references it. Move the repeated definition of TOP_PTE into mm/mm.h, as well as a few function prototypes. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* | [PATCH] Standardize pxx_page macrosDave McCracken2006-09-26
|/ | | | | | | | | | | | | | | | | | | | | One of the changes necessary for shared page tables is to standardize the pxx_page macros. pte_page and pmd_page have always returned the struct page associated with their entry, while pte_page_kernel and pmd_page_kernel have returned the kernel virtual address. pud_page and pgd_page, on the other hand, return the kernel virtual address. Shared page tables needs pud_page and pgd_page to return the actual page structures. There are very few actual users of these functions, so it is simple to standardize their usage. Since this is basic cleanup, I am submitting these changes as a standalone patch. Per Hugh Dickins' comments about it, I am also changing the pxx_page_kernel macros to pxx_page_vaddr to clarify their meaning. Signed-off-by: Dave McCracken <dmccr@us.ibm.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* [ARM] 3780/1: Fix iop321 cpuidDan Williams2006-09-14
| | | | | | | | | Patch from Dan Williams commit a6a38a66224c7c578cfed2f584b440c81af0c3ae changed the iop321 id to a value that does not work with all platforms. Change the mask to permit bit 11. Tested on an iq80321 600Mhz CRB. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3773/1: Add the HWCAP_VFP bit for the ARM926 CPUsCatalin Marinas2006-09-06
| | | | | | | | | | Patch from Catalin Marinas The ARM926EJ-S CPU has the VFP coprocessor and therefore it should be shown in the /proc/cpuinfo if CONFIG_VFP is enabled. Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3762/1: Fix ptrace cache coherency bug for ARM1136 VIPT nonaliasing ↵George G. Davis2006-09-02
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Harvard caches Patch from George G. Davis Resolve ARM1136 VIPT non-aliasing cache coherency issues observed when using ptrace to set breakpoints and cleanup copy_{to,from}_user_page() while we're here as requested by Russell King because "it's also far too heavy on non-v6 CPUs". NOTES: 1. Only access_process_vm() calls copy_{to,from}_user_page(). 2. access_process_vm() calls get_user_pages() to pin down the "page". 3. get_user_pages() calls flush_dcache_page(page) which ensures cache coherency between kernel and userspace mappings of "page". However flush_dcache_page(page) may not invalidate I-Cache over this range for all cases, specifically, I-Cache is not invalidated for the VIPT non-aliasing case. So memory is consistent between kernel and user space mappings of "page" but I-Cache may still be hot over this range. IOW, we don't have to worry about flush_cache_page() before memcpy(). 4. Now, for the copy_to_user_page() case, after memcpy(), we must flush the caches so memory is consistent with kernel cache entries and invalidate the I-Cache if this mm region is executable. We don't need to do anything after memcpy() for the copy_from_user_page() case since kernel cache entries will be invalidated via the same process above if we access "page" again. The flush_ptrace_access() function (borrowed from SPARC64 implementation) is added to handle cache flushing after memcpy() for the copy_to_user_page() case. Signed-off-by: George G. Davis <gdavis@mvista.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3761/1: fix armv4t breakage after adding thumb interworking to ↵Lennert Buytenhek2006-08-28
| | | | | | | | | | | | | | | | userspace helpers Patch from Lennert Buytenhek On armv4t systems, we have always compiled the kernel with -march=armv4 instead of -march=armv4t, which means that any use of bx will bomb out. Commit ba9b5d76372dc290b6ca04dad93927a22c2ac49a introduced the use of bx in the kernel, which means we need to compile with -march=armv4t on armv4t systems now. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3734/1: Fix the unused variable warning in __iounmap()Catalin Marinas2006-07-29
| | | | | | | | | | Patch from Catalin Marinas This patch adds #ifdef around some variables in the arch/arm/mm/ioremap.c file. Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3737/1: Export ARM copy/clear_user_page symbolsGeorge G. Davis2006-07-29
| | | | | | | | | | | | | | | | | Patch from George G. Davis As reported by various folks on the ARM Linux kernel mailing list, the video-buf.ko driver has undefined references on all ARM machines which use it as observed during `make modules`: Warning: "v4wb_clear_user_page" [drivers/media/video/video-buf.ko] undefined! Similar warnings exist for all ARM machines which use this driver. So this change adds the missing EXPORT_SYMBOLs to allow using this driver as a module. Signed-off-by: George G. Davis <gdavis@mvista.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3736/1: xscale: don't mis-report 80219 as an iop32xLennert Buytenhek2006-07-29
| | | | | | | | | | | | | | | Patch from Lennert Buytenhek The IOP 80219 xscale CPU is a stripped down version of the IOP32x. But the fact that the 80219 and IOP32x are very similar doesn't mean that they need to share a cpu table entry. It's also somewhat confusing for the end user to see the 80219 reported as an IOP32x, so this patch splits the IOP32x cpu table entry to make a separate entry for the 80219. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] Fix warning in consistent.cRussell King2006-07-03
| | | | | | | | No need for 'cr' to be a local variable, which is unused in the SMP case, and only used once in the UP case. Just call get_cr() directly. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] Fix bad asm instruction in proc-arm925.SRussell King2006-07-03
| | | | Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] More missing proc-macros.S includesRussell King2006-07-03
| | | | Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [ARM] 3708/2: fix SMP build after section ioremap changesLennert Buytenhek2006-07-03
| | | | | | | | | | Patch from Lennert Buytenhek Commit ff0daca525dde796382b9ccd563f169df2571211 broke the SMP build, this patch fixes it up again. Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* [PATCH] ARM: Fixup missing includes in arch/arm/mm/proc-<cputype>.SThomas Gleixner2006-07-02
| | | | | | | | For several proc-<cputype>.S files the include of proc-macros.S is missing. Make it compile and work again. Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* Merge branch 'devel' of master.kernel.org:/home/rmk/linux-2.6-armLinus Torvalds2006-07-02
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm: (44 commits) [ARM] 3541/2: workaround for PXA27x erratum E7 [ARM] nommu: provide a way for correct control register value selection [ARM] 3705/1: add supersection support to ioremap() [ARM] 3707/1: iwmmxt: use the generic thread notifier infrastructure [ARM] 3706/2: ep93xx: add cirrus logic edb9315a support [ARM] 3704/1: format IOP Kconfig with tabs, create more consistency [ARM] 3703/1: Add help description for ARCH_EP80219 [ARM] 3678/1: MMC: Make OMAP MMC work [ARM] 3677/1: OMAP: Update H2 defconfig [ARM] 3676/1: ARM: OMAP: Fix dmtimers and timer32k to compile on OMAP1 [ARM] Add section support to ioremap [ARM] Fix sa11x0 SDRAM selection [ARM] Set bit 4 on section mappings correctly depending on CPU [ARM] 3666/1: TRIZEPS4 [1/5] core ARM: OMAP: Multiplexing for 24xx GPMC wait pin monitoring ARM: OMAP: Fix SRAM to use MT_MEMORY instead of MT_DEVICE ARM: OMAP: Update dmtimers ARM: OMAP: Make clock variables static ARM: OMAP: Fix GPMC compilation when DEBUG is defined ARM: OMAP: Mux updates for external DMA and GPIO ...
| * [ARM] 3541/2: workaround for PXA27x erratum E7Nicolas Pitre2006-07-01
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Patch from Nicolas Pitre According to the Intel PXA27x Processor Family Specification Update document (doc.nr. 280071-009) erratum E7, some care must be taken to locate the disabling and re-enabling of the MMU to the beginning of a cache line to avoid problems in some circumstances. Credits to Simon Vogl <simon.vogl@researchstudios.at> for bringing this up. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
| * Merge nommu branchRussell King2006-07-01
| |\
generated by cgit v1.2.2 (git 2.25.0) at 2024-11-11 23:42:28 -0500