1. 12 Jun, 2018 1 commit
    • Kees Cook's avatar
      treewide: kmalloc() -> kmalloc_array() · 6da2ec56
      Kees Cook authored
      
      
      The kmalloc() function has a 2-factor argument form, kmalloc_array(). This
      patch replaces cases of:
      
              kmalloc(a * b, gfp)
      
      with:
              kmalloc_array(a * b, gfp)
      
      as well as handling cases of:
      
              kmalloc(a * b * c, gfp)
      
      with:
      
              kmalloc(array3_size(a, b, c), gfp)
      
      as it's slightly less ugly than:
      
              kmalloc_array(array_size(a, b), c, gfp)
      
      This does, however, attempt to ignore constant size factors like:
      
              kmalloc(4 * 1024, gfp)
      
      though any constants defined via macros get caught up in the conversion.
      
      Any factors with a sizeof() of "unsigned char", "char", and "u8" were
      dropped, since they're redundant.
      
      The tools/ directory was manually excluded, since it has its own
      implementation of kmalloc().
      
      The Coccinelle script used for this was:
      
      // Fix redundant parens around sizeof().
      @@
      type TYPE;
      expression THING, E;
      @@
      
      (
        kmalloc(
      -	(sizeof(TYPE)) * E
      +	sizeof(TYPE) * E
        , ...)
      |
        kmalloc(
      -	(sizeof(THING)) * E
      +	sizeof(THING) * E
        , ...)
      )
      
      // Drop single-byte sizes and redundant parens.
      @@
      expression COUNT;
      typedef u8;
      typedef __u8;
      @@
      
      (
        kmalloc(
      -	sizeof(u8) * (COUNT)
      +	COUNT
        , ...)
      |
        kmalloc(
      -	sizeof(__u8) * (COUNT)
      +	COUNT
        , ...)
      |
        kmalloc(
      -	sizeof(char) * (COUNT)
      +	COUNT
        , ...)
      |
        kmalloc(
      -	sizeof(unsigned char) * (COUNT)
      +	COUNT
        , ...)
      |
        kmalloc(
      -	sizeof(u8) * COUNT
      +	COUNT
        , ...)
      |
        kmalloc(
      -	sizeof(__u8) * COUNT
      +	COUNT
        , ...)
      |
        kmalloc(
      -	sizeof(char) * COUNT
      +	COUNT
        , ...)
      |
        kmalloc(
      -	sizeof(unsigned char) * COUNT
      +	COUNT
        , ...)
      )
      
      // 2-factor product with sizeof(type/expression) and identifier or constant.
      @@
      type TYPE;
      expression THING;
      identifier COUNT_ID;
      constant COUNT_CONST;
      @@
      
      (
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(TYPE) * (COUNT_ID)
      +	COUNT_ID, sizeof(TYPE)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(TYPE) * COUNT_ID
      +	COUNT_ID, sizeof(TYPE)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(TYPE) * (COUNT_CONST)
      +	COUNT_CONST, sizeof(TYPE)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(TYPE) * COUNT_CONST
      +	COUNT_CONST, sizeof(TYPE)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(THING) * (COUNT_ID)
      +	COUNT_ID, sizeof(THING)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(THING) * COUNT_ID
      +	COUNT_ID, sizeof(THING)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(THING) * (COUNT_CONST)
      +	COUNT_CONST, sizeof(THING)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(THING) * COUNT_CONST
      +	COUNT_CONST, sizeof(THING)
        , ...)
      )
      
      // 2-factor product, only identifiers.
      @@
      identifier SIZE, COUNT;
      @@
      
      - kmalloc
      + kmalloc_array
        (
      -	SIZE * COUNT
      +	COUNT, SIZE
        , ...)
      
      // 3-factor product with 1 sizeof(type) or sizeof(expression), with
      // redundant parens removed.
      @@
      expression THING;
      identifier STRIDE, COUNT;
      type TYPE;
      @@
      
      (
        kmalloc(
      -	sizeof(TYPE) * (COUNT) * (STRIDE)
      +	array3_size(COUNT, STRIDE, sizeof(TYPE))
        , ...)
      |
        kmalloc(
      -	sizeof(TYPE) * (COUNT) * STRIDE
      +	array3_size(COUNT, STRIDE, sizeof(TYPE))
        , ...)
      |
        kmalloc(
      -	sizeof(TYPE) * COUNT * (STRIDE)
      +	array3_size(COUNT, STRIDE, sizeof(TYPE))
        , ...)
      |
        kmalloc(
      -	sizeof(TYPE) * COUNT * STRIDE
      +	array3_size(COUNT, STRIDE, sizeof(TYPE))
        , ...)
      |
        kmalloc(
      -	sizeof(THING) * (COUNT) * (STRIDE)
      +	array3_size(COUNT, STRIDE, sizeof(THING))
        , ...)
      |
        kmalloc(
      -	sizeof(THING) * (COUNT) * STRIDE
      +	array3_size(COUNT, STRIDE, sizeof(THING))
        , ...)
      |
        kmalloc(
      -	sizeof(THING) * COUNT * (STRIDE)
      +	array3_size(COUNT, STRIDE, sizeof(THING))
        , ...)
      |
        kmalloc(
      -	sizeof(THING) * COUNT * STRIDE
      +	array3_size(COUNT, STRIDE, sizeof(THING))
        , ...)
      )
      
      // 3-factor product with 2 sizeof(variable), with redundant parens removed.
      @@
      expression THING1, THING2;
      identifier COUNT;
      type TYPE1, TYPE2;
      @@
      
      (
        kmalloc(
      -	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
      +	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
        , ...)
      |
        kmalloc(
      -	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
      +	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
        , ...)
      |
        kmalloc(
      -	sizeof(THING1) * sizeof(THING2) * COUNT
      +	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
        , ...)
      |
        kmalloc(
      -	sizeof(THING1) * sizeof(THING2) * (COUNT)
      +	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
        , ...)
      |
        kmalloc(
      -	sizeof(TYPE1) * sizeof(THING2) * COUNT
      +	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
        , ...)
      |
        kmalloc(
      -	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
      +	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
        , ...)
      )
      
      // 3-factor product, only identifiers, with redundant parens removed.
      @@
      identifier STRIDE, SIZE, COUNT;
      @@
      
      (
        kmalloc(
      -	(COUNT) * STRIDE * SIZE
      +	array3_size(COUNT, STRIDE, SIZE)
        , ...)
      |
        kmalloc(
      -	COUNT * (STRIDE) * SIZE
      +	array3_size(COUNT, STRIDE, SIZE)
        , ...)
      |
        kmalloc(
      -	COUNT * STRIDE * (SIZE)
      +	array3_size(COUNT, STRIDE, SIZE)
        , ...)
      |
        kmalloc(
      -	(COUNT) * (STRIDE) * SIZE
      +	array3_size(COUNT, STRIDE, SIZE)
        , ...)
      |
        kmalloc(
      -	COUNT * (STRIDE) * (SIZE)
      +	array3_size(COUNT, STRIDE, SIZE)
        , ...)
      |
        kmalloc(
      -	(COUNT) * STRIDE * (SIZE)
      +	array3_size(COUNT, STRIDE, SIZE)
        , ...)
      |
        kmalloc(
      -	(COUNT) * (STRIDE) * (SIZE)
      +	array3_size(COUNT, STRIDE, SIZE)
        , ...)
      |
        kmalloc(
      -	COUNT * STRIDE * SIZE
      +	array3_size(COUNT, STRIDE, SIZE)
        , ...)
      )
      
      // Any remaining multi-factor products, first at least 3-factor products,
      // when they're not all constants...
      @@
      expression E1, E2, E3;
      constant C1, C2, C3;
      @@
      
      (
        kmalloc(C1 * C2 * C3, ...)
      |
        kmalloc(
      -	(E1) * E2 * E3
      +	array3_size(E1, E2, E3)
        , ...)
      |
        kmalloc(
      -	(E1) * (E2) * E3
      +	array3_size(E1, E2, E3)
        , ...)
      |
        kmalloc(
      -	(E1) * (E2) * (E3)
      +	array3_size(E1, E2, E3)
        , ...)
      |
        kmalloc(
      -	E1 * E2 * E3
      +	array3_size(E1, E2, E3)
        , ...)
      )
      
      // And then all remaining 2 factors products when they're not all constants,
      // keeping sizeof() as the second factor argument.
      @@
      expression THING, E1, E2;
      type TYPE;
      constant C1, C2, C3;
      @@
      
      (
        kmalloc(sizeof(THING) * C2, ...)
      |
        kmalloc(sizeof(TYPE) * C2, ...)
      |
        kmalloc(C1 * C2 * C3, ...)
      |
        kmalloc(C1 * C2, ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(TYPE) * (E2)
      +	E2, sizeof(TYPE)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(TYPE) * E2
      +	E2, sizeof(TYPE)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(THING) * (E2)
      +	E2, sizeof(THING)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	sizeof(THING) * E2
      +	E2, sizeof(THING)
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	(E1) * E2
      +	E1, E2
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	(E1) * (E2)
      +	E1, E2
        , ...)
      |
      - kmalloc
      + kmalloc_array
        (
      -	E1 * E2
      +	E1, E2
        , ...)
      )
      Signed-off-by: default avatarKees Cook <keescook@chromium.org>
      6da2ec56
  2. 16 Nov, 2017 1 commit
  3. 26 Jul, 2016 1 commit
  4. 17 Mar, 2016 1 commit
  5. 21 Aug, 2015 1 commit
  6. 12 Feb, 2015 1 commit
    • Kirill A. Shutemov's avatar
      mm: fix false-positive warning on exit due mm_nr_pmds(mm) · b30fe6c7
      Kirill A. Shutemov authored
      
      
      The problem is that we check nr_ptes/nr_pmds in exit_mmap() which happens
      *before* pgd_free().  And if an arch does pte/pmd allocation in
      pgd_alloc() and frees them in pgd_free() we see offset in counters by the
      time of the checks.
      
      We tried to workaround this by offsetting expected counter value according
      to FIRST_USER_ADDRESS for both nr_pte and nr_pmd in exit_mmap().  But it
      doesn't work in some cases:
      
      1. ARM with LPAE enabled also has non-zero USER_PGTABLES_CEILING, but
         upper addresses occupied with huge pmd entries, so the trick with
         offsetting expected counter value will get really ugly: we will have
         to apply it nr_pmds, but not nr_ptes.
      
      2. Metag has non-zero FIRST_USER_ADDRESS, but doesn't do allocation
         pte/pmd page tables allocation in pgd_alloc(), just setup a pgd entry
         which is allocated at boot and shared accross all processes.
      
      The proposal is to move the check to check_mm() which happens *after*
      pgd_free() and do proper accounting during pgd_alloc() and pgd_free()
      which would bring counters to zero if nothing leaked.
      Signed-off-by: default avatarKirill A. Shutemov <kirill.shutemov@linux.intel.com>
      Reported-by: default avatarTyler Baker <tyler.baker@linaro.org>
      Tested-by: default avatarTyler Baker <tyler.baker@linaro.org>
      Tested-by: default avatarNishanth Menon <nm@ti.com>
      Cc: Russell King <linux@arm.linux.org.uk>
      Cc: James Hogan <james.hogan@imgtec.com>
      Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
      Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      b30fe6c7
  7. 29 Dec, 2013 1 commit
  8. 30 Nov, 2013 1 commit
    • Russell King's avatar
      ARM: fix booting low-vectors machines · d8aa712c
      Russell King authored
      Commit f6f91b0d (ARM: allow kuser helpers to be removed from the
      vector page) required two pages for the vectors code.  Although the
      code setting up the initial page tables was updated, the code which
      allocates page tables for new processes wasn't, neither was the code
      which tears down the mappings.  Fix this.
      
      Fixes: f6f91b0d
      
       ("ARM: allow kuser helpers to be removed from the vector page")
      Signed-off-by: default avatarRussell King <rmk+kernel@arm.linux.org.uk>
      Cc: <stable@vger.kernel.org>
      d8aa712c
  9. 28 Mar, 2012 1 commit
  10. 24 Mar, 2012 1 commit
  11. 08 Dec, 2011 1 commit
    • Catalin Marinas's avatar
      ARM: LPAE: Page table maintenance for the 3-level format · da028779
      Catalin Marinas authored
      
      
      This patch modifies the pgd/pmd/pte manipulation functions to support
      the 3-level page table format. Since there is no need for an 'ext'
      argument to cpu_set_pte_ext(), this patch conditionally defines a
      different prototype for this function when CONFIG_ARM_LPAE.
      
      The patch also introduces the L_PGD_SWAPPER flag to mark pgd entries
      pointing to pmd tables pre-allocated in the swapper_pg_dir and avoid
      trying to free them at run-time. This flag is 0 with the classic page
      table format.
      Signed-off-by: default avatarCatalin Marinas <catalin.marinas@arm.com>
      da028779
  12. 21 Feb, 2011 1 commit
  13. 14 Jan, 2011 1 commit
  14. 22 Dec, 2010 1 commit
  15. 26 Nov, 2010 2 commits
  16. 26 Oct, 2010 1 commit
  17. 30 Mar, 2010 1 commit
    • Tejun Heo's avatar
      include cleanup: Update gfp.h and slab.h includes to prepare for breaking... · 5a0e3ad6
      Tejun Heo authored
      include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
      
      percpu.h is included by sched.h and module.h and thus ends up being
      included when building most .c files.  percpu.h includes slab.h which
      in turn includes gfp.h making everything defined by the two files
      universally available and complicating inclusion dependencies.
      
      percpu.h -> slab.h dependency is about to be removed.  Prepare for
      this change by updating users of gfp and slab facilities include those
      headers directly instead of assuming availability.  As this conversion
      needs to touch large number of source files, the following script is
      used as the basis of conversion.
      
        http://userweb.kernel.org/~tj/misc/slabh-sweep.py
      
      
      
      The script does the followings.
      
      * Scan files for gfp and slab usages and update includes such that
        only the necessary includes are there.  ie. if only gfp is used,
        gfp.h, if slab is used, slab.h.
      
      * When the script inserts a new include, it looks at the include
        blocks and try to put the new include such that its order conforms
        to its surrounding.  It's put in the include block which contains
        core kernel includes, in the same order that the rest are ordered -
        alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
        doesn't seem to be any matching order.
      
      * If the script can't find a place to put a new include (mostly
        because the file doesn't have fitting include block), it prints out
        an error message indicating which .h file needs to be added to the
        file.
      
      The conversion was done in the following steps.
      
      1. The initial automatic conversion of all .c files updated slightly
         over 4000 files, deleting around 700 includes and adding ~480 gfp.h
         and ~3000 slab.h inclusions.  The script emitted errors for ~400
         files.
      
      2. Each error was manually checked.  Some didn't need the inclusion,
         some needed manual addition while adding it to implementation .h or
         embedding .c file was more appropriate for others.  This step added
         inclusions to around 150 files.
      
      3. The script was run again and the output was compared to the edits
         from #2 to make sure no file was left behind.
      
      4. Several build tests were done and a couple of problems were fixed.
         e.g. lib/decompress_*.c used malloc/free() wrappers around slab
         APIs requiring slab.h to be added manually.
      
      5. The script was run on all .h files but without automatically
         editing them as sprinkling gfp.h and slab.h inclusions around .h
         files could easily lead to inclusion dependency hell.  Most gfp.h
         inclusion directives were ignored as stuff from gfp.h was usually
         wildly available and often used in preprocessor macros.  Each
         slab.h inclusion directive was examined and added manually as
         necessary.
      
      6. percpu.h was updated not to include slab.h.
      
      7. Build test were done on the following configurations and failures
         were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
         distributed build env didn't work with gcov compiles) and a few
         more options had to be turned off depending on archs to make things
         build (like ipr on powerpc/64 which failed due to missing writeq).
      
         * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
         * powerpc and powerpc64 SMP allmodconfig
         * sparc and sparc64 SMP allmodconfig
         * ia64 SMP allmodconfig
         * s390 SMP allmodconfig
         * alpha SMP allmodconfig
         * um on x86_64 SMP allmodconfig
      
      8. percpu.h modifications were reverted so that it could be applied as
         a separate patch and serve as bisection point.
      
      Given the fact that I had only a couple of failures from tests on step
      6, I'm fairly confident about the coverage of this conversion patch.
      If there is a breakage, it's likely to be something in one of the arch
      headers which should be easily discoverable easily on most builds of
      the specific arch.
      Signed-off-by: default avatarTejun Heo <tj@kernel.org>
      Guess-its-ok-by: default avatarChristoph Lameter <cl@linux-foundation.org>
      Cc: Ingo Molnar <mingo@redhat.com>
      Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
      5a0e3ad6
  18. 27 Nov, 2008 1 commit
    • Russell King's avatar
      [ARM] remove memzero() · 59f0cb0f
      Russell King authored
      
      
      As suggested by Andrew Morton, remove memzero() - it's not supported
      on other architectures so use of it is a potential build breaking bug.
      Since the compiler optimizes memset(x,0,n) to __memzero() perfectly
      well, we don't miss out on the underlying benefits of memzero().
      Signed-off-by: default avatarRussell King <rmk+kernel@arm.linux.org.uk>
      59f0cb0f
  19. 01 Mar, 2008 1 commit
  20. 05 Feb, 2008 1 commit
  21. 13 Dec, 2006 1 commit
    • Russell King's avatar
      [ARM] Unuse another Linux PTE bit · ad1ae2fe
      Russell King authored
      
      
      L_PTE_ASID is not really required to be stored in every PTE, since we
      can identify it via the address passed to set_pte_at().  So, create
      set_pte_ext() which takes the address of the PTE to set, the Linux
      PTE value, and the additional CPU PTE bits which aren't encoded in
      the Linux PTE value.
      Signed-off-by: default avatarRussell King <rmk+kernel@arm.linux.org.uk>
      ad1ae2fe
  22. 27 Sep, 2006 2 commits
  23. 20 Sep, 2006 1 commit
  24. 30 Jun, 2006 2 commits
  25. 29 Jun, 2006 1 commit
    • Russell King's avatar
      [ARM] Set bit 4 on section mappings correctly depending on CPU · 8799ee9f
      Russell King authored
      
      
      On some CPUs, bit 4 of section mappings means "update the
      cache when written to".  On others, this bit is required to
      be one, and others it's required to be zero.  Finally, on
      ARMv6 and above, setting it turns on "no execute" and prevents
      speculative prefetches.
      
      With all these combinations, no one value fits all CPUs, so we
      have to pick a value depending on the CPU type, and the area
      we're mapping.
      Signed-off-by: default avatarRussell King <rmk+kernel@arm.linux.org.uk>
      8799ee9f
  26. 31 May, 2006 1 commit
  27. 01 Apr, 2006 1 commit
    • Lennert Buytenhek's avatar
      [ARM] 3439/2: xsc3: add I/O coherency support · 23759dc6
      Lennert Buytenhek authored
      
      
      Patch from Lennert Buytenhek
      
      This patch adds support for the I/O coherent cache available on the
      xsc3.  The approach is to provide a simple API to determine whether the
      chipset supports coherency by calling arch_is_coherent() and then
      setting the appropriate system memory PTE and PMD bits.  In addition,
      we call this API on dma_alloc_coherent() and dma_map_single() calls.
      A generic version exists that will compile out all the coherency-related
      code that is not needed on the majority of ARM systems.
      
      Note that we do not check for coherency in the dma_alloc_writecombine()
      function as that still requires a special PTE setting.  We also don't
      touch dma_mmap_coherent() as that is a special ARM-only API that is by
      definition only used on non-coherent system.
      Signed-off-by: default avatarDeepak Saxena <dsaxena@plexity.net>
      Signed-off-by: default avatarLennert Buytenhek <buytenh@wantstofly.org>
      Signed-off-by: default avatarRussell King <rmk+kernel@arm.linux.org.uk>
      23759dc6
  28. 28 Mar, 2006 1 commit
    • Lennert Buytenhek's avatar
      [ARM] 3377/2: add support for intel xsc3 core · 23bdf86a
      Lennert Buytenhek authored
      
      
      Patch from Lennert Buytenhek
      
      This patch adds support for the new XScale v3 core.  This is an
      ARMv5 ISA core with the following additions:
      
      - L2 cache
      - I/O coherency support (on select chipsets)
      - Low-Locality Reference cache attributes (replaces mini-cache)
      - Supersections (v6 compatible)
      - 36-bit addressing (v6 compatible)
      - Single instruction cache line clean/invalidate
      - LRU cache replacement (vs round-robin)
      
      I attempted to merge the XSC3 support into proc-xscale.S, but XSC3
      cores have separate errata and have to handle things like L2, so it
      is simpler to keep it separate.
      
      L2 cache support is currently a build option because the L2 enable
      bit must be set before we enable the MMU and there is no easy way to
      capture command line parameters at this point.
      
      There are still optimizations that can be done such as using LLR for
      copypage (in theory using the exisiting mini-cache code) but those
      can be addressed down the road.
      Signed-off-by: default avatarDeepak Saxena <dsaxena@plexity.net>
      Signed-off-by: default avatarLennert Buytenhek <buytenh@wantstofly.org>
      Signed-off-by: default avatarRussell King <rmk+kernel@arm.linux.org.uk>
      23bdf86a
  29. 26 Jan, 2006 1 commit
  30. 03 Jan, 2006 1 commit
    • Russell King's avatar
      [ARM] Cleanup ARM includes · 78ff18a4
      Russell King authored
      
      
      arch/arm/kernel/entry-armv.S has contained a comment suggesting
      that asm/hardware.h and asm/arch/irqs.h should be moved into the
      asm/arch/entry-macro.S include.  So move the includes to these
      two files as required.
      
      Add missing includes (asm/hardware.h, asm/io.h) to asm/arch/system.h
      includes which use those facilities, and remove asm/io.h from
      kernel/process.c.
      
      Remove other unnecessary includes from arch/arm/kernel, arch/arm/mm
      and arch/arm/mach-footbridge.
      Signed-off-by: default avatarRussell King <rmk+kernel@arm.linux.org.uk>
      78ff18a4
  31. 07 Nov, 2005 1 commit
  32. 03 Nov, 2005 1 commit
  33. 30 Oct, 2005 2 commits
    • Hugh Dickins's avatar
      [PATCH] mm: split page table lock · 4c21e2f2
      Hugh Dickins authored
      
      
      Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with
      a many-threaded application which concurrently initializes different parts of
      a large anonymous area.
      
      This patch corrects that, by using a separate spinlock per page table page, to
      guard the page table entries in that page, instead of using the mm's single
      page_table_lock.  (But even then, page_table_lock is still used to guard page
      table allocation, and anon_vma allocation.)
      
      In this implementation, the spinlock is tucked inside the struct page of the
      page table page: with a BUILD_BUG_ON in case it overflows - which it would in
      the case of 32-bit PA-RISC with spinlock debugging enabled.
      
      Splitting the lock is not quite for free: another cacheline access.  Ideally,
      I suppose we would use split ptlock only for multi-threaded processes on
      multi-cpu machines; but deciding that dynamically would have its own costs.
      So for now enable it by config, at some number of cpus - since the Kconfig
      language doesn't support inequalities, let preprocessor compare that with
      NR_CPUS.  But I don't think it's worth being user-configurable: for good
      testing of both split and unsplit configs, split now at 4 cpus, and perhaps
      change that to 8 later.
      
      There is a benefit even for singly threaded processes: kswapd can be attacking
      one part of the mm while another part is busy faulting.
      Signed-off-by: default avatarHugh Dickins <hugh@veritas.com>
      Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      4c21e2f2
    • Hugh Dickins's avatar
      [PATCH] mm: arches skip ptlock · b462705a
      Hugh Dickins authored
      
      
      Convert those few architectures which are calling pud_alloc, pmd_alloc,
      pte_alloc_map on a user mm, not to take the page_table_lock first, nor drop it
      after.  Each of these can continue to use pte_alloc_map, no need to change
      over to pte_alloc_map_lock, they're neither racy nor swappable.
      
      In the sparc64 io_remap_pfn_range, flush_tlb_range then falls outside of the
      page_table_lock: that's okay, on sparc64 it's like flush_tlb_mm, and that has
      always been called from outside of page_table_lock in dup_mmap.
      Signed-off-by: default avatarHugh Dickins <hugh@veritas.com>
      Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
      Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      b462705a
  34. 28 Oct, 2005 3 commits