another .33 patch

diff --git a/queue-2.6.33/series b/queue-2.6.33/series
index 98b2622099f9fb40ea6f3a0f2567440a9f786895..8134d96af6e61465050d3b03ec664c86a8e378ac 100644 (file)
--- a/queue-2.6.33/series
+++ b/queue-2.6.33/series
@@ -120,3 +120,4 @@ kvm-x86-emulator-check-cpl-level-during-privilege-instruction-emulation.patch
 sched-fix-sched_mv_power_savings-for-smt.patch
 sched-fix-smt-scheduler-regression-in-find_busiest_queue.patch
 sched-don-t-use-possibly-stale-sched_class.patch
+x86-mm-allow-highmem-user-page-tables-to-be-disabled-at-boot-time.patch

diff --git a/queue-2.6.33/x86-mm-allow-highmem-user-page-tables-to-be-disabled-at-boot-time.patch b/queue-2.6.33/x86-mm-allow-highmem-user-page-tables-to-be-disabled-at-boot-time.patch
new file mode 100644 (file)
index 0000000..8dfd936
--- /dev/null
+++ b/queue-2.6.33/x86-mm-allow-highmem-user-page-tables-to-be-disabled-at-boot-time.patch
@@ -0,0 +1,158 @@
+From 14315592009c17035cac81f4954d5a1f4d71e489 Mon Sep 17 00:00:00 2001
+From: Ian Campbell <ian.campbell@citrix.com>
+Date: Wed, 17 Feb 2010 10:38:10 +0000
+Subject: x86, mm: Allow highmem user page tables to be disabled at boot time
+
+From: Ian Campbell <ian.campbell@citrix.com>
+
+commit 14315592009c17035cac81f4954d5a1f4d71e489 upstream.
+
+Distros generally (I looked at Debian, RHEL5 and SLES11) seem to
+enable CONFIG_HIGHPTE for any x86 configuration which has highmem
+enabled. This means that the overhead applies even to machines which
+have a fairly modest amount of high memory and which therefore do not
+really benefit from allocating PTEs in high memory but still pay the
+price of the additional mapping operations.
+
+Running kernbench on a 4G box I found that with CONFIG_HIGHPTE=y but
+no actual highptes being allocated there was a reduction in system
+time used from 59.737s to 55.9s.
+
+With CONFIG_HIGHPTE=y and highmem PTEs being allocated:
+  Average Optimal load -j 4 Run (std deviation):
+  Elapsed Time 175.396 (0.238914)
+  User Time 515.983 (5.85019)
+  System Time 59.737 (1.26727)
+  Percent CPU 263.8 (71.6796)
+  Context Switches 39989.7 (4672.64)
+  Sleeps 42617.7 (246.307)
+
+With CONFIG_HIGHPTE=y but with no highmem PTEs being allocated:
+  Average Optimal load -j 4 Run (std deviation):
+  Elapsed Time 174.278 (0.831968)
+  User Time 515.659 (6.07012)
+  System Time 55.9 (1.07799)
+  Percent CPU 263.8 (71.266)
+  Context Switches 39929.6 (4485.13)
+  Sleeps 42583.7 (373.039)
+
+This patch allows the user to control the allocation of PTEs in
+highmem from the command line ("userpte=nohigh") but retains the
+status-quo as the default.
+
+It is possible that some simple heuristic could be developed which
+allows auto-tuning of this option however I don't have a sufficiently
+large machine available to me to perform any particularly meaningful
+experiments. We could probably handwave up an argument for a threshold
+at 16G of total RAM.
+
+Assuming 768M of lowmem we have 196608 potential lowmem PTE
+pages. Each page can map 2M of RAM in a PAE-enabled configuration,
+meaning a maximum of 384G of RAM could potentially be mapped using
+lowmem PTEs.
+
+Even allowing generous factor of 10 to account for other required
+lowmem allocations, generous slop to account for page sharing (which
+reduces the total amount of RAM mappable by a given number of PT
+pages) and other innacuracies in the estimations it would seem that
+even a 32G machine would not have a particularly pressing need for
+highmem PTEs. I think 32G could be considered to be at the upper bound
+of what might be sensible on a 32 bit machine (although I think in
+practice 64G is still supported).
+
+It's seems questionable if HIGHPTE is even a win for any amount of RAM
+you would sensibly run a 32 bit kernel on rather than going 64 bit.
+
+Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
+LKML-Reference: <1266403090-20162-1-git-send-email-ian.campbell@citrix.com>
+Signed-off-by: H. Peter Anvin <hpa@zytor.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
+
+---
+ Documentation/kernel-parameters.txt |    7 +++++++
+ arch/x86/include/asm/pgalloc.h      |    5 +++++
+ arch/x86/mm/pgtable.c               |   31 ++++++++++++++++++++++++++-----
+ 3 files changed, 38 insertions(+), 5 deletions(-)
+
+--- a/Documentation/kernel-parameters.txt
++++ b/Documentation/kernel-parameters.txt
+@@ -2703,6 +2703,13 @@ and is between 256 and 4096 characters.
+                                       medium is write-protected).
+                       Example: quirks=0419:aaf5:rl,0421:0433:rc
+ 
++      userpte=
++                      [X86] Flags controlling user PTE allocations.
++
++                              nohigh = do not allocate PTE pages in
++                                      HIGHMEM regardless of setting
++                                      of CONFIG_HIGHPTE.
++
+       vdso=           [X86,SH]
+                       vdso=2: enable compat VDSO (default with COMPAT_VDSO)
+                       vdso=1: enable VDSO (default)
+--- a/arch/x86/include/asm/pgalloc.h
++++ b/arch/x86/include/asm/pgalloc.h
+@@ -23,6 +23,11 @@ static inline void paravirt_release_pud(
+ #endif
+ 
+ /*
++ * Flags to use when allocating a user page table page.
++ */
++extern gfp_t __userpte_alloc_gfp;
++
++/*
+  * Allocate and free page tables.
+  */
+ extern pgd_t *pgd_alloc(struct mm_struct *);
+--- a/arch/x86/mm/pgtable.c
++++ b/arch/x86/mm/pgtable.c
+@@ -6,6 +6,14 @@
+ 
+ #define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
+ 
++#ifdef CONFIG_HIGHPTE
++#define PGALLOC_USER_GFP __GFP_HIGHMEM
++#else
++#define PGALLOC_USER_GFP 0
++#endif
++
++gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP;
++
+ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
+ {
+       return (pte_t *)__get_free_page(PGALLOC_GFP);
+@@ -15,16 +23,29 @@ pgtable_t pte_alloc_one(struct mm_struct
+ {
+       struct page *pte;
+ 
+-#ifdef CONFIG_HIGHPTE
+-      pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0);
+-#else
+-      pte = alloc_pages(PGALLOC_GFP, 0);
+-#endif
++      pte = alloc_pages(__userpte_alloc_gfp, 0);
+       if (pte)
+               pgtable_page_ctor(pte);
+       return pte;
+ }
+ 
++static int __init setup_userpte(char *arg)
++{
++      if (!arg)
++              return -EINVAL;
++
++      /*
++       * "userpte=nohigh" disables allocation of user pagetables in
++       * high memory.
++       */
++      if (strcmp(arg, "nohigh") == 0)
++              __userpte_alloc_gfp &= ~__GFP_HIGHMEM;
++      else
++              return -EINVAL;
++      return 0;
++}
++early_param("userpte", setup_userpte);
++
+ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
+ {
+       pgtable_page_dtor(pte);