From 4c21e2f2441dc5fbb957b030333f5a3f2d02dea7 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Sat, 29 Oct 2005 18:16:40 -0700 Subject: [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 Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mremap.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'mm/mremap.c') diff --git a/mm/mremap.c b/mm/mremap.c index 8de77b632a20..b535438c363c 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -72,7 +72,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct address_space *mapping = NULL; struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; - spinlock_t *old_ptl; + spinlock_t *old_ptl, *new_ptl; if (vma->vm_file) { /* @@ -88,8 +88,15 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_vma->vm_truncate_count = 0; } + /* + * We don't have to worry about the ordering of src and dst + * pte locks because exclusive mmap_sem prevents deadlock. + */ old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl); new_pte = pte_offset_map_nested(new_pmd, new_addr); + new_ptl = pte_lockptr(mm, new_pmd); + if (new_ptl != old_ptl) + spin_lock(new_ptl); for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, new_pte++, new_addr += PAGE_SIZE) { @@ -101,6 +108,8 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, set_pte_at(mm, new_addr, new_pte, pte); } + if (new_ptl != old_ptl) + spin_unlock(new_ptl); pte_unmap_nested(new_pte - 1); pte_unmap_unlock(old_pte - 1, old_ptl); if (mapping) -- cgit v1.2.3-59-g8ed1b