summaryrefslogtreecommitdiff
path: root/arch/mips/mm
diff options
context:
space:
mode:
authorHillf Danton <dhillf@gmail.com>2011-11-22 14:38:03 (GMT)
committerRalf Baechle <ralf@linux-mips.org>2011-12-07 22:03:45 (GMT)
commitb1c10bea620f79109b5cc9935267bea4f6f29ac6 (patch)
tree2b529b61862b6f5b3834a174c246a18b0255f28a /arch/mips/mm
parent5639bc4a64786c94eba3d2ba6a4ff4b290da1fb1 (diff)
downloadlinux-b1c10bea620f79109b5cc9935267bea4f6f29ac6.tar.xz
MIPS: Add fast get_user_pages
Gup is used in a few cases, say futex. This work is derived from the x86 version, and operations of pte and pmd are adapted to the defines of MIPS in straight forward manner. [ralf@linux-mips.org: Fixed up reject in arch/mips/mm/Makefile due to whitespace formatting differences. Fixed build error in gup.c due to conflicting changes elsewhere in the kernel.] Signed-off-by: Hillf Danton <dhillf@gmail.com> Cc: David Daney <david.daney@cavium.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/2859/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Diffstat (limited to 'arch/mips/mm')
-rw-r--r--arch/mips/mm/Makefile4
-rw-r--r--arch/mips/mm/gup.c315
2 files changed, 317 insertions, 2 deletions
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index 4d8c162..3ca2a06 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 0000000..33aadbc
--- /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;
+}