Merge branch 'next/generic' into mips-for-linux-next

4 files changed, 338 insertions, 57 deletions

diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index 4d8c1623eee2..3ca2a065cf76 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -3,8 +3,8 @@
 #
 
 obj-y				+= cache.o dma-default.o extable.o fault.o \
-				   init.o mmap.o tlbex.o tlbex-fault.o uasm.o \
-				   page.o
+				   gup.o init.o mmap.o page.o tlbex.o \
+				   tlbex-fault.o uasm.o
 
 obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
diff --git a/arch/mips/mm/gup.c b/arch/mips/mm/gup.c
new file mode 100644
index 000000000000..33aadbcf170b
--- /dev/null
+++ b/arch/mips/mm/gup.c
@@ -0,0 +1,315 @@
+/*
+ * Lockless get_user_pages_fast for MIPS
+ *
+ * Copyright (C) 2008 Nick Piggin
+ * Copyright (C) 2008 Novell Inc.
+ * Copyright (C) 2011 Ralf Baechle
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmstat.h>
+#include <linux/highmem.h>
+#include <linux/swap.h>
+#include <linux/hugetlb.h>
+
+#include <asm/pgtable.h>
+
+static inline pte_t gup_get_pte(pte_t *ptep)
+{
+#if defined(CONFIG_64BIT_PHYS_ADDR) && defined(CONFIG_CPU_MIPS32)
+	pte_t pte;
+
+retry:
+	pte.pte_low = ptep->pte_low;
+	smp_rmb();
+	pte.pte_high = ptep->pte_high;
+	smp_rmb();
+	if (unlikely(pte.pte_low != ptep->pte_low))
+		goto retry;
+
+	return pte;
+#else
+	return ACCESS_ONCE(*ptep);
+#endif
+}
+
+static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
+			int write, struct page **pages, int *nr)
+{
+	pte_t *ptep = pte_offset_map(&pmd, addr);
+	do {
+		pte_t pte = gup_get_pte(ptep);
+		struct page *page;
+
+		if (!pte_present(pte) ||
+		    pte_special(pte) || (write && !pte_write(pte))) {
+			pte_unmap(ptep);
+			return 0;
+		}
+		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		page = pte_page(pte);
+		get_page(page);
+		SetPageReferenced(page);
+		pages[*nr] = page;
+		(*nr)++;
+
+	} while (ptep++, addr += PAGE_SIZE, addr != end);
+
+	pte_unmap(ptep - 1);
+	return 1;
+}
+
+static inline void get_head_page_multiple(struct page *page, int nr)
+{
+	VM_BUG_ON(page != compound_head(page));
+	VM_BUG_ON(page_count(page) == 0);
+	atomic_add(nr, &page->_count);
+	SetPageReferenced(page);
+}
+
+static int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end,
+			int write, struct page **pages, int *nr)
+{
+	pte_t pte = *(pte_t *)&pmd;
+	struct page *head, *page;
+	int refs;
+
+	if (write && !pte_write(pte))
+		return 0;
+	/* hugepages are never "special" */
+	VM_BUG_ON(pte_special(pte));
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		if (PageTail(page))
+			get_huge_page_tail(page);
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	get_head_page_multiple(head, refs);
+	return 1;
+}
+
+static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
+			int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pmd_t *pmdp;
+
+	pmdp = pmd_offset(&pud, addr);
+	do {
+		pmd_t pmd = *pmdp;
+
+		next = pmd_addr_end(addr, end);
+		/*
+		 * The pmd_trans_splitting() check below explains why
+		 * pmdp_splitting_flush has to flush the tlb, to stop
+		 * this gup-fast code from running while we set the
+		 * splitting bit in the pmd. Returning zero will take
+		 * the slow path that will call wait_split_huge_page()
+		 * if the pmd is still in splitting state. gup-fast
+		 * can't because it has irq disabled and
+		 * wait_split_huge_page() would never return as the
+		 * tlb flush IPI wouldn't run.
+		 */
+		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
+			return 0;
+		if (unlikely(pmd_huge(pmd))) {
+			if (!gup_huge_pmd(pmd, addr, next, write, pages,nr))
+				return 0;
+		} else {
+			if (!gup_pte_range(pmd, addr, next, write, pages,nr))
+				return 0;
+		}
+	} while (pmdp++, addr = next, addr != end);
+
+	return 1;
+}
+
+static int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end,
+			int write, struct page **pages, int *nr)
+{
+	pte_t pte = *(pte_t *)&pud;
+	struct page *head, *page;
+	int refs;
+
+	if (write && !pte_write(pte))
+		return 0;
+	/* hugepages are never "special" */
+	VM_BUG_ON(pte_special(pte));
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	get_head_page_multiple(head, refs);
+	return 1;
+}
+
+static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pud_t *pudp;
+
+	pudp = pud_offset(&pgd, addr);
+	do {
+		pud_t pud = *pudp;
+
+		next = pud_addr_end(addr, end);
+		if (pud_none(pud))
+			return 0;
+		if (unlikely(pud_huge(pud))) {
+			if (!gup_huge_pud(pud, addr, next, write, pages,nr))
+				return 0;
+		} else {
+			if (!gup_pmd_range(pud, addr, next, write, pages,nr))
+				return 0;
+		}
+	} while (pudp++, addr = next, addr != end);
+
+	return 1;
+}
+
+/*
+ * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
+ * back to the regular GUP.
+ */
+int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			  struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next;
+	unsigned long flags;
+	pgd_t *pgdp;
+	int nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+					(void __user *)start, len)))
+		return 0;
+
+	/*
+	 * XXX: batch / limit 'nr', to avoid large irq off latency
+	 * needs some instrumenting to determine the common sizes used by
+	 * important workloads (eg. DB2), and whether limiting the batch
+	 * size will decrease performance.
+	 *
+	 * It seems like we're in the clear for the moment. Direct-IO is
+	 * the main guy that batches up lots of get_user_pages, and even
+	 * they are limited to 64-at-a-time which is not so many.
+	 */
+	/*
+	 * This doesn't prevent pagetable teardown, but does prevent
+	 * the pagetables and pages from being freed.
+	 *
+	 * So long as we atomically load page table pointers versus teardown,
+	 * we can follow the address down to the page and take a ref on it.
+	 */
+	local_irq_save(flags);
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			break;
+		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+			break;
+	} while (pgdp++, addr = next, addr != end);
+	local_irq_restore(flags);
+
+	return nr;
+}
+
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @write:	whether pages will be written to
+ * @pages:	array that receives pointers to the pages pinned.
+ * 		Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno.
+ */
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next;
+	pgd_t *pgdp;
+	int ret, nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+
+	end = start + len;
+	if (end < start)
+		goto slow_irqon;
+
+	/* XXX: batch / limit 'nr' */
+	local_irq_disable();
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			goto slow;
+		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+			goto slow;
+	} while (pgdp++, addr = next, addr != end);
+	local_irq_enable();
+
+	VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
+	return nr;
+slow:
+	local_irq_enable();
+
+slow_irqon:
+	/* Try to get the remaining pages with get_user_pages */
+	start += nr << PAGE_SHIFT;
+	pages += nr;
+
+	down_read(&mm->mmap_sem);
+	ret = get_user_pages(current, mm, start,
+				(end - start) >> PAGE_SHIFT,
+				write, 0, pages, NULL);
+	up_read(&mm->mmap_sem);
+
+	/* Have to be a bit careful with return values */
+	if (nr > 0) {
+		if (ret < 0)
+			ret = nr;
+		else
+			ret += nr;
+	}
+	return ret;
+}
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index b7ebc4fa89bc..3b3ffd439cd7 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -304,9 +304,14 @@ int page_is_ram(unsigned long pagenr)
 	for (i = 0; i < boot_mem_map.nr_map; i++) {
 		unsigned long addr, end;
 
-		if (boot_mem_map.map[i].type != BOOT_MEM_RAM)
+		switch (boot_mem_map.map[i].type) {
+		case BOOT_MEM_RAM:
+		case BOOT_MEM_INIT_RAM:
+			break;
+		default:
 			/* not usable memory */
 			continue;
+		}
 
 		addr = PFN_UP(boot_mem_map.map[i].addr);
 		end = PFN_DOWN(boot_mem_map.map[i].addr +
@@ -379,7 +384,7 @@ void __init mem_init(void)
 
 	reservedpages = ram = 0;
 	for (tmp = 0; tmp < max_low_pfn; tmp++)
-		if (page_is_ram(tmp)) {
+		if (page_is_ram(tmp) && pfn_valid(tmp)) {
 			ram++;
 			if (PageReserved(pfn_to_page(tmp)))
 				reservedpages++;
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index d163455552b0..2dc625346c40 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -121,22 +121,30 @@ void local_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 
 	if (cpu_context(cpu, mm) != 0) {
 		unsigned long size, flags;
+		int huge = is_vm_hugetlb_page(vma);
 
 		ENTER_CRITICAL(flags);
-		size = (end - start + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-		size = (size + 1) >> 1;
+		if (huge) {
+			start = round_down(start, HPAGE_SIZE);
+			end = round_up(end, HPAGE_SIZE);
+			size = (end - start) >> HPAGE_SHIFT;
+		} else {
+			start = round_down(start, PAGE_SIZE << 1);
+			end = round_up(end, PAGE_SIZE << 1);
+			size = (end - start) >> (PAGE_SHIFT + 1);
+		}
 		if (size <= current_cpu_data.tlbsize/2) {
 			int oldpid = read_c0_entryhi();
 			int newpid = cpu_asid(cpu, mm);
 
-			start &= (PAGE_MASK << 1);
-			end += ((PAGE_SIZE << 1) - 1);
-			end &= (PAGE_MASK << 1);
 			while (start < end) {
 				int idx;
 
 				write_c0_entryhi(start | newpid);
-				start += (PAGE_SIZE << 1);
+				if (huge)
+					start += HPAGE_SIZE;
+				else
+					start += (PAGE_SIZE << 1);
 				mtc0_tlbw_hazard();
 				tlb_probe();
 				tlb_probe_hazard();
@@ -369,51 +377,6 @@ void add_wired_entry(unsigned long entrylo0, unsigned long entrylo1,
 	EXIT_CRITICAL(flags);
 }
 
-/*
- * Used for loading TLB entries before trap_init() has started, when we
- * don't actually want to add a wired entry which remains throughout the
- * lifetime of the system
- */
-
-static int temp_tlb_entry __cpuinitdata;
-
-__init int add_temporary_entry(unsigned long entrylo0, unsigned long entrylo1,
-			       unsigned long entryhi, unsigned long pagemask)
-{
-	int ret = 0;
-	unsigned long flags;
-	unsigned long wired;
-	unsigned long old_pagemask;
-	unsigned long old_ctx;
-
-	ENTER_CRITICAL(flags);
-	/* Save old context and create impossible VPN2 value */
-	old_ctx = read_c0_entryhi();
-	old_pagemask = read_c0_pagemask();
-	wired = read_c0_wired();
-	if (--temp_tlb_entry < wired) {
-		printk(KERN_WARNING
-		       "No TLB space left for add_temporary_entry\n");
-		ret = -ENOSPC;
-		goto out;
-	}
-
-	write_c0_index(temp_tlb_entry);
-	write_c0_pagemask(pagemask);
-	write_c0_entryhi(entryhi);
-	write_c0_entrylo0(entrylo0);
-	write_c0_entrylo1(entrylo1);
-	mtc0_tlbw_hazard();
-	tlb_write_indexed();
-	tlbw_use_hazard();
-
-	write_c0_entryhi(old_ctx);
-	write_c0_pagemask(old_pagemask);
-out:
-	EXIT_CRITICAL(flags);
-	return ret;
-}
-
 static int __cpuinitdata ntlb;
 static int __init set_ntlb(char *str)
 {
@@ -451,8 +414,6 @@ void __cpuinit tlb_init(void)
 		write_c0_pagegrain(pg);
 	}
 
-	temp_tlb_entry = current_cpu_data.tlbsize - 1;
-
         /* From this point on the ARC firmware is dead.  */
 	local_flush_tlb_all();