#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
#include <asm/e820.h>
#include <asm/processor.h>
#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/proto.h>
+#include <asm/pat.h>
/*
* The current flushing context - we pass it instead of 5 arguments:
int numpages;
int flushtlb;
unsigned long pfn;
+ unsigned force_split : 1;
};
#ifdef CONFIG_X86_64
#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+# define debug_pagealloc 1
+#else
+# define debug_pagealloc 0
+#endif
+
static inline int
within(unsigned long addr, unsigned long start, unsigned long end)
{
int i, do_split = 1;
unsigned int level;
+ if (cpa->force_split)
+ return 1;
+
spin_lock_irqsave(&pgd_lock, flags);
/*
* Check for races, another CPU might have split this page
static LIST_HEAD(page_pool);
static unsigned long pool_size, pool_pages, pool_low;
-static unsigned long pool_used, pool_failed, pool_refill;
+static unsigned long pool_used, pool_failed;
-static void cpa_fill_pool(void)
+static void cpa_fill_pool(struct page **ret)
{
- struct page *p;
gfp_t gfp = GFP_KERNEL;
+ unsigned long flags;
+ struct page *p;
- /* Do not allocate from interrupt context */
- if (in_irq() || irqs_disabled())
- return;
/*
- * Check unlocked. I does not matter when we have one more
- * page in the pool. The bit lock avoids recursive pool
- * allocations:
+ * Avoid recursion (on debug-pagealloc) and also signal
+ * our priority to get to these pagetables:
*/
- if (pool_pages >= pool_size || test_and_set_bit_lock(0, &pool_refill))
+ if (current->flags & PF_MEMALLOC)
return;
+ current->flags |= PF_MEMALLOC;
-#ifdef CONFIG_DEBUG_PAGEALLOC
/*
- * We could do:
- * gfp = in_atomic() ? GFP_ATOMIC : GFP_KERNEL;
- * but this fails on !PREEMPT kernels
+ * Allocate atomically from atomic contexts:
*/
- gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;
-#endif
+ if (in_atomic() || irqs_disabled() || debug_pagealloc)
+ gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;
- while (pool_pages < pool_size) {
+ while (pool_pages < pool_size || (ret && !*ret)) {
p = alloc_pages(gfp, 0);
if (!p) {
pool_failed++;
break;
}
- spin_lock_irq(&pgd_lock);
+ /*
+ * 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_irq(&pgd_lock);
+ spin_unlock_irqrestore(&pgd_lock, flags);
}
- clear_bit_unlock(0, &pool_refill);
+
+ current->flags &= ~PF_MEMALLOC;
}
#define SHIFT_MB (20 - PAGE_SHIFT)
* GiB. Shift MiB to Gib and multiply the result by
* POOL_PAGES_PER_GB:
*/
- gb = ((si.totalram >> SHIFT_MB) + ROUND_MB_GB) >> SHIFT_MB_GB;
- pool_size = POOL_PAGES_PER_GB * 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();
+ cpa_fill_pool(NULL);
printk(KERN_DEBUG
"CPA: page pool initialized %lu of %lu pages preallocated\n",
pool_pages, pool_size);
spin_lock_irqsave(&pgd_lock, flags);
if (list_empty(&page_pool)) {
spin_unlock_irqrestore(&pgd_lock, flags);
- return -ENOMEM;
+ 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;
}
- 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:
}
static int change_page_attr_set_clr(unsigned long addr, int numpages,
- pgprot_t mask_set, pgprot_t mask_clr)
+ pgprot_t mask_set, pgprot_t mask_clr,
+ int force_split)
{
struct cpa_data cpa;
int ret, cache, checkalias;
*/
mask_set = canon_pgprot(mask_set);
mask_clr = canon_pgprot(mask_clr);
- if (!pgprot_val(mask_set) && !pgprot_val(mask_clr))
+ if (!pgprot_val(mask_set) && !pgprot_val(mask_clr) && !force_split)
return 0;
/* Ensure we are PAGE_SIZE aligned */
cpa.mask_set = mask_set;
cpa.mask_clr = mask_clr;
cpa.flushtlb = 0;
+ cpa.force_split = force_split;
/* No alias checking for _NX bit modifications */
checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;
cpa_flush_all(cache);
out:
- cpa_fill_pool();
+ cpa_fill_pool(NULL);
+
return ret;
}
static inline int change_page_attr_set(unsigned long addr, int numpages,
pgprot_t mask)
{
- return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0));
+ return change_page_attr_set_clr(addr, numpages, mask, __pgprot(0), 0);
}
static inline int change_page_attr_clear(unsigned long addr, int numpages,
pgprot_t mask)
{
- return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask);
+ return change_page_attr_set_clr(addr, numpages, __pgprot(0), mask, 0);
}
-int set_memory_uc(unsigned long addr, int numpages)
+int _set_memory_uc(unsigned long addr, int numpages)
{
return change_page_attr_set(addr, numpages,
- __pgprot(_PAGE_PCD | _PAGE_PWT));
+ __pgprot(_PAGE_CACHE_UC));
+}
+
+int set_memory_uc(unsigned long addr, int numpages)
+{
+ if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
+ _PAGE_CACHE_UC, NULL))
+ return -EINVAL;
+
+ return _set_memory_uc(addr, numpages);
}
EXPORT_SYMBOL(set_memory_uc);
-int set_memory_wb(unsigned long addr, int numpages)
+int _set_memory_wc(unsigned long addr, int numpages)
+{
+ return change_page_attr_set(addr, numpages,
+ __pgprot(_PAGE_CACHE_WC));
+}
+
+int set_memory_wc(unsigned long addr, int numpages)
+{
+ if (!pat_wc_enabled)
+ return set_memory_uc(addr, numpages);
+
+ if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
+ _PAGE_CACHE_WC, NULL))
+ return -EINVAL;
+
+ return _set_memory_wc(addr, numpages);
+}
+EXPORT_SYMBOL(set_memory_wc);
+
+int _set_memory_wb(unsigned long addr, int numpages)
{
return change_page_attr_clear(addr, numpages,
- __pgprot(_PAGE_PCD | _PAGE_PWT));
+ __pgprot(_PAGE_CACHE_MASK));
+}
+
+int set_memory_wb(unsigned long addr, int numpages)
+{
+ free_memtype(addr, addr + numpages * PAGE_SIZE);
+
+ return _set_memory_wb(addr, numpages);
}
EXPORT_SYMBOL(set_memory_wb);
return change_page_attr_clear(addr, numpages, __pgprot(_PAGE_PRESENT));
}
+int set_memory_4k(unsigned long addr, int numpages)
+{
+ return change_page_attr_set_clr(addr, numpages, __pgprot(0),
+ __pgprot(0), 1);
+}
+
int set_pages_uc(struct page *page, int numpages)
{
unsigned long addr = (unsigned long)page_address(page);
* Try to refill the page pool here. We can do this only after
* the tlb flush.
*/
- cpa_fill_pool();
+ 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,
+};
+
+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)
+{
+ unsigned int level;
+ pte_t *pte;
+
+ if (PageHighMem(page))
+ return false;
+
+ pte = lookup_address((unsigned long)page_address(page), &level);
+ return (pte_val(*pte) & _PAGE_PRESENT);
+}
+
+#endif /* CONFIG_HIBERNATION */
+
+#endif /* CONFIG_DEBUG_PAGEALLOC */
+
/*
* The testcases use internal knowledge of the implementation that shouldn't
* be exposed to the rest of the kernel. Include these directly here.
projects / linux-2.6-omap-h63xx.git / blobdiff