The patch titled Quicklist support for x86_64 has been added to the -mm tree. Its filename is quicklist-support-for-x86_64.patch *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find out what to do about this ------------------------------------------------------ Subject: Quicklist support for x86_64 From: Christoph Lameter <clameter@xxxxxxx> This adds caching of pgds and puds, pmds, pte. That way we can avoid costly zeroing and initialization of special mappings in the pgd. A second quicklist is useful to separate out PGD handling. We can carry the initialized pgds over to the next process needing them. Also clean up the pgd_list handling to use regular list macros. There is no need anymore to avoid the lru field. Move the add/removal of the pgds to the pgdlist into the constructor / destructor. That way the implementation is congruent with i386. Signed-off-by: Christoph Lameter <clameter@xxxxxxx> Cc: "David S. Miller" <davem@xxxxxxxxxxxxx> Cc: Andi Kleen <ak@xxxxxxx> Cc: "Luck, Tony" <tony.luck@xxxxxxxxx> Cc: William Lee Irwin III <wli@xxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- arch/x86_64/Kconfig | 8 +++ arch/x86_64/kernel/process.c | 1 arch/x86_64/kernel/smp.c | 2 include/asm-x86_64/pgalloc.h | 73 ++++++++++++++++++++++----------- include/asm-x86_64/pgtable.h | 1 5 files changed, 59 insertions(+), 26 deletions(-) diff -puN arch/x86_64/Kconfig~quicklist-support-for-x86_64 arch/x86_64/Kconfig --- a/arch/x86_64/Kconfig~quicklist-support-for-x86_64 +++ a/arch/x86_64/Kconfig @@ -56,6 +56,14 @@ config ZONE_DMA bool default y +config QUICKLIST + bool + default y + +config NR_QUICK + int + default 2 + config ISA bool diff -puN arch/x86_64/kernel/process.c~quicklist-support-for-x86_64 arch/x86_64/kernel/process.c --- a/arch/x86_64/kernel/process.c~quicklist-support-for-x86_64 +++ a/arch/x86_64/kernel/process.c @@ -207,6 +207,7 @@ void cpu_idle (void) if (__get_cpu_var(cpu_idle_state)) __get_cpu_var(cpu_idle_state) = 0; + check_pgt_cache(); rmb(); idle = pm_idle; if (!idle) diff -puN arch/x86_64/kernel/smp.c~quicklist-support-for-x86_64 arch/x86_64/kernel/smp.c --- a/arch/x86_64/kernel/smp.c~quicklist-support-for-x86_64 +++ a/arch/x86_64/kernel/smp.c @@ -242,7 +242,7 @@ void flush_tlb_mm (struct mm_struct * mm } if (!cpus_empty(cpu_mask)) flush_tlb_others(cpu_mask, mm, FLUSH_ALL); - + check_pgt_cache(); preempt_enable(); } EXPORT_SYMBOL(flush_tlb_mm); diff -puN include/asm-x86_64/pgalloc.h~quicklist-support-for-x86_64 include/asm-x86_64/pgalloc.h --- a/include/asm-x86_64/pgalloc.h~quicklist-support-for-x86_64 +++ a/include/asm-x86_64/pgalloc.h @@ -4,6 +4,10 @@ #include <asm/pda.h> #include <linux/threads.h> #include <linux/mm.h> +#include <linux/quicklist.h> + +#define QUICK_PGD 0 /* We preserve special mappings over free */ +#define QUICK_PT 1 /* Other page table pages that are zero on free */ #define pmd_populate_kernel(mm, pmd, pte) \ set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte))) @@ -20,23 +24,23 @@ static inline void pmd_populate(struct m static inline void pmd_free(pmd_t *pmd) { BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - free_page((unsigned long)pmd); + quicklist_free(QUICK_PT, NULL, pmd); } static inline pmd_t *pmd_alloc_one (struct mm_struct *mm, unsigned long addr) { - return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + return (pmd_t *)quicklist_alloc(QUICK_PT, GFP_KERNEL|__GFP_REPEAT, NULL); } static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + return (pud_t *)quicklist_alloc(QUICK_PT, GFP_KERNEL|__GFP_REPEAT, NULL); } static inline void pud_free (pud_t *pud) { BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - free_page((unsigned long)pud); + quicklist_free(QUICK_PT, NULL, pud); } static inline void pgd_list_add(pgd_t *pgd) @@ -57,41 +61,57 @@ static inline void pgd_list_del(pgd_t *p spin_unlock(&pgd_lock); } -static inline pgd_t *pgd_alloc(struct mm_struct *mm) +static inline void pgd_ctor(void *x) { unsigned boundary; - pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); - if (!pgd) - return NULL; - pgd_list_add(pgd); + pgd_t *pgd = x; + struct page *page = virt_to_page(pgd); + /* * Copy kernel pointers in from init. - * Could keep a freelist or slab cache of those because the kernel - * part never changes. */ boundary = pgd_index(__PAGE_OFFSET); - memset(pgd, 0, boundary * sizeof(pgd_t)); memcpy(pgd + boundary, - init_level4_pgt + boundary, - (PTRS_PER_PGD - boundary) * sizeof(pgd_t)); + init_level4_pgt + boundary, + (PTRS_PER_PGD - boundary) * sizeof(pgd_t)); + + spin_lock(&pgd_lock); + list_add(&page->lru, &pgd_list); + spin_unlock(&pgd_lock); +} + +static inline void pgd_dtor(void *x) +{ + pgd_t *pgd = x; + struct page *page = virt_to_page(pgd); + + spin_lock(&pgd_lock); + list_del(&page->lru); + spin_unlock(&pgd_lock); +} + +static inline pgd_t *pgd_alloc(struct mm_struct *mm) +{ + pgd_t *pgd = (pgd_t *)quicklist_alloc(QUICK_PGD, + GFP_KERNEL|__GFP_REPEAT, pgd_ctor); return pgd; } static inline void pgd_free(pgd_t *pgd) { BUG_ON((unsigned long)pgd & (PAGE_SIZE-1)); - pgd_list_del(pgd); - free_page((unsigned long)pgd); + quicklist_free(QUICK_PGD, pgd_dtor, pgd); } static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + return (pte_t *)quicklist_alloc(QUICK_PT, GFP_KERNEL|__GFP_REPEAT, NULL); } static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) { - void *p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + void *p = (void *)quicklist_alloc(QUICK_PT, GFP_KERNEL|__GFP_REPEAT, NULL); + if (!p) return NULL; return virt_to_page(p); @@ -103,17 +123,22 @@ static inline struct page *pte_alloc_one static inline void pte_free_kernel(pte_t *pte) { BUG_ON((unsigned long)pte & (PAGE_SIZE-1)); - free_page((unsigned long)pte); + quicklist_free(QUICK_PT, NULL, pte); } static inline void pte_free(struct page *pte) { - __free_page(pte); -} + quicklist_free_page(QUICK_PT, NULL, pte); +} -#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte)) +#define __pte_free_tlb(tlb,pte) quicklist_free_page(QUICK_PT, NULL,(pte)) -#define __pmd_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) -#define __pud_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) +#define __pmd_free_tlb(tlb,x) quicklist_free(QUICK_PT, NULL, (x)) +#define __pud_free_tlb(tlb,x) quicklist_free(QUICK_PT, NULL, (x)) +static inline void check_pgt_cache(void) +{ + quicklist_trim(QUICK_PGD, pgd_dtor, 25, 16); + quicklist_trim(QUICK_PT, NULL, 25, 16); +} #endif /* _X86_64_PGALLOC_H */ diff -puN include/asm-x86_64/pgtable.h~quicklist-support-for-x86_64 include/asm-x86_64/pgtable.h --- a/include/asm-x86_64/pgtable.h~quicklist-support-for-x86_64 +++ a/include/asm-x86_64/pgtable.h @@ -425,7 +425,6 @@ extern int kern_addr_valid(unsigned long #define HAVE_ARCH_UNMAPPED_AREA #define pgtable_cache_init() do { } while (0) -#define check_pgt_cache() do { } while (0) #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 _ Patches currently in -mm which might be from clameter@xxxxxxx are slab-introduce-krealloc.patch slab-introduce-krealloc-fix.patch paravirt_ops-allow-paravirt-backend-to-choose-kernel-pmd-sharing.patch add-apply_to_page_range-which-applies-a-function-to-a-pte-range.patch safer-nr_node_ids-and-nr_node_ids-determination-and-initial.patch use-zvc-counters-to-establish-exact-size-of-dirtyable-pages.patch slab-ensure-cache_alloc_refill-terminates.patch smaps-extract-pmd-walker-from-smaps-code.patch smaps-add-pages-referenced-count-to-smaps.patch smaps-add-clear_refs-file-to-clear-reference.patch smaps-add-clear_refs-file-to-clear-reference-fix.patch smaps-add-clear_refs-file-to-clear-reference-fix-fix.patch slab-use-num_possible_cpus-in-enable_cpucache.patch i386-use-page-allocator-to-allocate-thread_info-structure.patch slub-core.patch slub-fix-numa-bootstrap.patch slub-use-correct-flags-to-check-for-dma-cache.patch slub-treat-slab_hwcache_align-as-a-mininum-and-not-as-the-alignment.patch slub-add-slabinfo-tool.patch make-page-private-usable-in-compound-pages-v1.patch add-virt_to_head_page-and-consolidate-code-in-slab-and-slub.patch quicklists-for-page-table-pages.patch quicklist-support-for-ia64.patch quicklist-support-for-x86_64.patch quicklist-support-for-sparc64.patch extend-print_symbol-capability-fix.patch slab-shutdown-cache_reaper-when-cpu-goes-down.patch mm-implement-swap-prefetching.patch readahead-state-based-method-aging-accounting.patch - To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html