[PATCH] mm: split page table lock

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: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 8 insertions, 6 deletions

diff --git a/arch/arm/mm/mm-armv.c b/arch/arm/mm/mm-armv.c
index 60f3e039bac2..1221fdde1769 100644
--- a/arch/arm/mm/mm-armv.c
+++ b/arch/arm/mm/mm-armv.c
@@ -229,6 +229,7 @@ void free_pgd_slow(pgd_t *pgd)
         pte = pmd_page(*pmd);
         pmd_clear(pmd);
         dec_page_state(nr_page_table_pages);
+        pte_lock_deinit(pte);
         pte_free(pte);
         pmd_free(pmd);
 free:
diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c
index 4eaec0f3525b..2c67dfe5a6b3 100644
--- a/arch/frv/mm/pgalloc.c
+++ b/arch/frv/mm/pgalloc.c
@@ -87,14 +87,14 @@ static inline void pgd_list_add(pgd_t *pgd)
         if (pgd_list)
                 pgd_list->private = (unsigned long) &page->index;
         pgd_list = page;
-        page->private = (unsigned long) &pgd_list;
+        set_page_private(page, (unsigned long)&pgd_list);
 }
 
 static inline void pgd_list_del(pgd_t *pgd)
 {
         struct page *next, **pprev, *page = virt_to_page(pgd);
         next = (struct page *) page->index;
-        pprev = (struct page **) page->private;
+        pprev = (struct page **)page_private(page);
         *pprev = next;
         if (next)
                 next->private = (unsigned long) pprev;
diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c
index dcdce2c6c532..39c099f15b5f 100644
--- a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -188,19 +188,19 @@ static inline void pgd_list_add(pgd_t *pgd)
         struct page *page = virt_to_page(pgd);
         page->index = (unsigned long)pgd_list;
         if (pgd_list)
-                pgd_list->private = (unsigned long)&page->index;
+                set_page_private(pgd_list, (unsigned long)&page->index);
         pgd_list = page;
-        page->private = (unsigned long)&pgd_list;
+        set_page_private(page, (unsigned long)&pgd_list);
 }
 
 static inline void pgd_list_del(pgd_t *pgd)
 {
         struct page *next, **pprev, *page = virt_to_page(pgd);
         next = (struct page *)page->index;
-        pprev = (struct page **)page->private;
+        pprev = (struct page **)page_private(page);
         *pprev = next;
         if (next)
-                next->private = (unsigned long)pprev;
+                set_page_private(next, (unsigned long)pprev);
 }
 
 void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused)
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index 02cf36e0331a..9e5e39cea821 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -144,6 +144,7 @@ void destroy_context_skas(struct mm_struct *mm)
 
         if(!proc_mm || !ptrace_faultinfo){
                 free_page(mmu->id.stack);
+                pte_lock_deinit(virt_to_page(mmu->last_page_table));
                 pte_free_kernel((pte_t *) mmu->last_page_table);
                 dec_page_state(nr_page_table_pages);
 #ifdef CONFIG_3_LEVEL_PGTABLES