Interrupt context no longer splits large page in cpa(). So we can do away with cpa memory pool code. Signed-off-by: Suresh Siddha --- Index: tip/arch/x86/mm/pageattr.c =================================================================== --- tip.orig/arch/x86/mm/pageattr.c 2008-09-23 13:47:45.000000000 -0700 +++ tip/arch/x86/mm/pageattr.c 2008-09-23 13:47:51.000000000 -0700 @@ -447,114 +447,17 @@ return do_split; } -static LIST_HEAD(page_pool); -static unsigned long pool_size, pool_pages, pool_low; -static unsigned long pool_used, pool_failed; - -static void cpa_fill_pool(struct page **ret) -{ - gfp_t gfp = GFP_KERNEL; - unsigned long flags; - struct page *p; - - /* - * Avoid recursion (on debug-pagealloc) and also signal - * our priority to get to these pagetables: - */ - if (current->flags & PF_MEMALLOC) - return; - current->flags |= PF_MEMALLOC; - - /* - * Allocate atomically from atomic contexts: - */ - if (in_atomic() || irqs_disabled() || debug_pagealloc) - gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN; - - while (pool_pages < pool_size || (ret && !*ret)) { - p = alloc_pages(gfp, 0); - if (!p) { - pool_failed++; - break; - } - /* - * If the call site needs a page right now, provide it: - */ - if (ret && !*ret) { - *ret = p; - continue; - } - spin_lock_irqsave(&pgd_lock, flags); - list_add(&p->lru, &page_pool); - pool_pages++; - spin_unlock_irqrestore(&pgd_lock, flags); - } - - current->flags &= ~PF_MEMALLOC; -} - -#define SHIFT_MB (20 - PAGE_SHIFT) -#define ROUND_MB_GB ((1 << 10) - 1) -#define SHIFT_MB_GB 10 -#define POOL_PAGES_PER_GB 16 - -void __init cpa_init(void) -{ - struct sysinfo si; - unsigned long gb; - - si_meminfo(&si); - /* - * Calculate the number of pool pages: - * - * Convert totalram (nr of pages) to MiB and round to the next - * GiB. Shift MiB to Gib and multiply the result by - * POOL_PAGES_PER_GB: - */ - if (debug_pagealloc) { - gb = ((si.totalram >> SHIFT_MB) + ROUND_MB_GB) >> SHIFT_MB_GB; - pool_size = POOL_PAGES_PER_GB * gb; - } else { - pool_size = 1; - } - pool_low = pool_size; - - cpa_fill_pool(NULL); - printk(KERN_DEBUG - "CPA: page pool initialized %lu of %lu pages preallocated\n", - pool_pages, pool_size); -} - static int split_large_page(pte_t *kpte, unsigned long address) { unsigned long flags, pfn, pfninc = 1; unsigned int i, level; pte_t *pbase, *tmp; pgprot_t ref_prot; - struct page *base; + struct page *base = alloc_pages(GFP_KERNEL, 0); + if (!base) + return -ENOMEM; - /* - * Get a page from the pool. The pool list is protected by the - * pgd_lock, which we have to take anyway for the split - * operation: - */ spin_lock_irqsave(&pgd_lock, flags); - if (list_empty(&page_pool)) { - spin_unlock_irqrestore(&pgd_lock, flags); - base = NULL; - cpa_fill_pool(&base); - if (!base) - return -ENOMEM; - spin_lock_irqsave(&pgd_lock, flags); - } else { - base = list_first_entry(&page_pool, struct page, lru); - list_del(&base->lru); - pool_pages--; - - if (pool_pages < pool_low) - pool_low = pool_pages; - } - /* * Check for races, another CPU might have split this page * up for us already: @@ -611,11 +514,8 @@ * If we dropped out via the lookup_address check under * pgd_lock then stick the page back into the pool: */ - if (base) { - list_add(&base->lru, &page_pool); - pool_pages++; - } else - pool_used++; + if (base) + __free_page(base); spin_unlock_irqrestore(&pgd_lock, flags); return 0; @@ -899,8 +799,6 @@ cpa_flush_all(cache); out: - cpa_fill_pool(NULL); - return ret; } @@ -1178,53 +1076,8 @@ * but that can deadlock->flush only current cpu: */ __flush_tlb_all(); - - /* - * Try to refill the page pool here. We can do this only after - * the tlb flush. - */ - cpa_fill_pool(NULL); } -#ifdef CONFIG_DEBUG_FS -static int dpa_show(struct seq_file *m, void *v) -{ - seq_puts(m, "DEBUG_PAGEALLOC\n"); - seq_printf(m, "pool_size : %lu\n", pool_size); - seq_printf(m, "pool_pages : %lu\n", pool_pages); - seq_printf(m, "pool_low : %lu\n", pool_low); - seq_printf(m, "pool_used : %lu\n", pool_used); - seq_printf(m, "pool_failed : %lu\n", pool_failed); - - return 0; -} - -static int dpa_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, dpa_show, NULL); -} - -static const struct file_operations dpa_fops = { - .open = dpa_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static int __init debug_pagealloc_proc_init(void) -{ - struct dentry *de; - - de = debugfs_create_file("debug_pagealloc", 0600, NULL, NULL, - &dpa_fops); - if (!de) - return -ENOMEM; - - return 0; -} -__initcall(debug_pagealloc_proc_init); -#endif - #ifdef CONFIG_HIBERNATION bool kernel_page_present(struct page *page) Index: tip/arch/x86/mm/init_64.c =================================================================== --- tip.orig/arch/x86/mm/init_64.c 2008-09-23 13:46:14.000000000 -0700 +++ tip/arch/x86/mm/init_64.c 2008-09-23 13:47:51.000000000 -0700 @@ -944,8 +944,6 @@ reservedpages << (PAGE_SHIFT-10), datasize >> 10, initsize >> 10); - - cpa_init(); } void free_init_pages(char *what, unsigned long begin, unsigned long end) Index: tip/arch/x86/mm/init_32.c =================================================================== --- tip.orig/arch/x86/mm/init_32.c 2008-09-23 13:46:14.000000000 -0700 +++ tip/arch/x86/mm/init_32.c 2008-09-23 13:47:51.000000000 -0700 @@ -1053,7 +1053,6 @@ if (boot_cpu_data.wp_works_ok < 0) test_wp_bit(); - cpa_init(); save_pg_dir(); zap_low_mappings(); } Index: tip/include/asm-x86/cacheflush.h =================================================================== --- tip.orig/include/asm-x86/cacheflush.h 2008-09-23 13:45:48.000000000 -0700 +++ tip/include/asm-x86/cacheflush.h 2008-09-23 13:47:51.000000000 -0700 @@ -99,8 +99,6 @@ void clflush_cache_range(void *addr, unsigned int size); -void cpa_init(void); - #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); extern const int rodata_test_data; -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/