aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSteve Capper <steve.capper@linaro.org>2013-10-07 10:47:28 +0100
committerSteve Capper <steve.capper@linaro.org>2014-09-01 11:50:21 +0100
commitc771688e21fcfbe91388b15dabe7d5e597338d98 (patch)
tree0d57b778269511f3fef7b199cd1485df4b3ec783
parentfad01e866afdbe01a1f3ec06a39c3a8b9e197014 (diff)
downloadlinux-c771688e21fcfbe91388b15dabe7d5e597338d98.tar.gz
mm: Introduce a general RCU get_user_pages_fast.
get_user_pages_fast attempts to pin user pages by walking the page tables directly and avoids taking locks. Thus the walker needs to be protected from page table pages being freed from under it, and needs to block any THP splits. One way to achieve this is to have the walker disable interrupts, and rely on IPIs from the TLB flushing code blocking before the page table pages are freed. On some platforms we have hardware broadcast of TLB invalidations, thus the TLB flushing code doesn't necessarily need to broadcast IPIs; and spuriously broadcasting IPIs can hurt system performance if done too often. This problem has been solved on PowerPC and Sparc by batching up page table pages belonging to more than one mm_user, then scheduling an rcu_sched callback to free the pages. This RCU page table free logic has been promoted to core code and is activated when one enables HAVE_RCU_TABLE_FREE. Unfortunately, these architectures implement their own get_user_pages_fast routines. The RCU page table free logic coupled with a an IPI broadcast on THP split (which is a rare event), allows one to protect a page table walker by merely disabling the interrupts during the walk. This patch provides a general RCU implementation of get_user_pages_fast that can be used by architectures that perform hardware broadcast of TLB invalidations. It is based heavily on the PowerPC implementation by Nick Piggin. Signed-off-by: Steve Capper <steve.capper@linaro.org> Tested-by: Dann Frazier <dann.frazier@canonical.com> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> [steve.capper@linaro.org: backported to 3.15-rc8]
-rw-r--r--mm/Kconfig3
-rw-r--r--mm/Makefile1
-rw-r--r--mm/gup.c287
3 files changed, 291 insertions, 0 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 1b5a95f0fa0..e446feca147 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -134,6 +134,9 @@ config HAVE_MEMBLOCK
config HAVE_MEMBLOCK_NODE_MAP
boolean
+config HAVE_GENERIC_RCU_GUP
+ boolean
+
config ARCH_DISCARD_MEMBLOCK
boolean
diff --git a/mm/Makefile b/mm/Makefile
index b484452dac5..c5dfe95376c 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -28,6 +28,7 @@ else
obj-y += bootmem.o
endif
+obj-$(CONFIG_HAVE_GENERIC_RCU_GUP) += gup.o
obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
obj-$(CONFIG_BOUNCE) += bounce.o
diff --git a/mm/gup.c b/mm/gup.c
new file mode 100644
index 00000000000..16acafa4737
--- /dev/null
+++ b/mm/gup.c
@@ -0,0 +1,287 @@
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/spinlock.h>
+
+#include <linux/hugetlb.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+
+#include <linux/sched.h>
+#include <linux/rwsem.h>
+#include <asm/pgtable.h>
+
+#include "internal.h"
+
+#ifdef __HAVE_ARCH_PTE_SPECIAL
+static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
+ int write, struct page **pages, int *nr)
+{
+ pte_t *ptep, *ptem;
+ int ret = 0;
+
+ ptem = ptep = pte_offset_map(&pmd, addr);
+ do {
+ pte_t pte = ACCESS_ONCE(*ptep);
+ struct page *page;
+
+ if (!pte_present(pte) || pte_special(pte)
+ || (write && !pte_write(pte)))
+ goto pte_unmap;
+
+ VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+ page = pte_page(pte);
+
+ if (!page_cache_get_speculative(page))
+ goto pte_unmap;
+
+ if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+ put_page(page);
+ goto pte_unmap;
+ }
+
+ pages[*nr] = page;
+ (*nr)++;
+
+ } while (ptep++, addr += PAGE_SIZE, addr != end);
+
+ ret = 1;
+
+pte_unmap:
+ pte_unmap(ptem);
+ return ret;
+}
+#else
+
+/*
+ * If we can't determine whether or not a pte is special, then fail immediately
+ * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not
+ * to be special.
+ */
+static inline int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
+ int write, struct page **pages, int *nr)
+{
+ return 0;
+}
+#endif /* __HAVE_ARCH_PTE_SPECIAL */
+
+static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
+ unsigned long end, int write, struct page **pages, int *nr)
+{
+ struct page *head, *page, *tail;
+ int refs;
+
+ if (write && !pmd_write(orig))
+ return 0;
+
+ refs = 0;
+ head = pmd_page(orig);
+ page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+ tail = page;
+ do {
+ VM_BUG_ON(compound_head(page) != head);
+ pages[*nr] = page;
+ (*nr)++;
+ page++;
+ refs++;
+ } while (addr += PAGE_SIZE, addr != end);
+
+ if (!page_cache_add_speculative(head, refs)) {
+ *nr -= refs;
+ return 0;
+ }
+
+ if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
+ *nr -= refs;
+ while (refs--)
+ put_page(head);
+ return 0;
+ }
+
+ /*
+ * Any tail pages need their mapcount reference taken before we
+ * return. (This allows the THP code to bump their ref count when
+ * they are split into base pages).
+ */
+ while (refs--) {
+ if (PageTail(tail))
+ get_huge_page_tail(tail);
+ tail++;
+ }
+
+ return 1;
+}
+
+static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
+ unsigned long end, int write, struct page **pages, int *nr)
+{
+ struct page *head, *page, *tail;
+ int refs;
+
+ if (write && !pud_write(orig))
+ return 0;
+
+ refs = 0;
+ head = pud_page(orig);
+ page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+ tail = page;
+ do {
+ VM_BUG_ON(compound_head(page) != head);
+ pages[*nr] = page;
+ (*nr)++;
+ page++;
+ refs++;
+ } while (addr += PAGE_SIZE, addr != end);
+
+ if (!page_cache_add_speculative(head, refs)) {
+ *nr -= refs;
+ return 0;
+ }
+
+ if (unlikely(pud_val(orig) != pud_val(*pudp))) {
+ *nr -= refs;
+ while (refs--)
+ put_page(head);
+ return 0;
+ }
+
+ while (refs--) {
+ if (PageTail(tail))
+ get_huge_page_tail(tail);
+ tail++;
+ }
+
+ 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 = ACCESS_ONCE(*pmdp);
+ next = pmd_addr_end(addr, end);
+ if (pmd_none(pmd) || pmd_trans_splitting(pmd))
+ return 0;
+
+ if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) {
+ if (!gup_huge_pmd(pmd, pmdp, 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_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end,
+ int write, struct page **pages, int *nr)
+{
+ unsigned long next;
+ pud_t *pudp;
+
+ pudp = pud_offset(pgdp, addr);
+ do {
+ pud_t pud = ACCESS_ONCE(*pudp);
+ next = pud_addr_end(addr, end);
+ if (pud_none(pud))
+ return 0;
+ if (pud_huge(pud)) {
+ if (!gup_huge_pud(pud, pudp, 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, 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,
+ start, len)))
+ return 0;
+
+ /*
+ * Disable interrupts, we use the nested form as we can already
+ * have interrupts disabled by get_futex_key.
+ *
+ * With interrupts disabled, we block page table pages from being
+ * freed from under us. See mmu_gather_tlb in asm-generic/tlb.h
+ * for more details.
+ *
+ * We do not adopt an rcu_read_lock(.) here as we also want to
+ * block IPIs that come from THPs splitting.
+ */
+
+ local_irq_save(flags);
+ pgdp = pgd_offset(mm, addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ if (pgd_none(*pgdp))
+ break;
+ else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr))
+ break;
+ } while (pgdp++, addr = next, addr != end);
+ local_irq_restore(flags);
+
+ return nr;
+}
+
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+ struct page **pages)
+{
+ struct mm_struct *mm = current->mm;
+ int nr, ret;
+
+ start &= PAGE_MASK;
+ nr = __get_user_pages_fast(start, nr_pages, write, pages);
+ ret = nr;
+
+ if (nr < nr_pages) {
+ /* 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,
+ nr_pages - nr, 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;
+}