linux/arch/x86/mm/gup.c
Youquan Song b6999b1912 thp: add compound tail page _mapcount when mapped
With the 3.2-rc kernel, IOMMU 2M pages in KVM works.  But when I tried
to use IOMMU 1GB pages in KVM, I encountered an oops and the 1GB page
failed to be used.

The root cause is that 1GB page allocation calls gup_huge_pud() while 2M
page calls gup_huge_pmd.  If compound pages are used and the page is a
tail page, gup_huge_pmd() increases _mapcount to record tail page are
mapped while gup_huge_pud does not do that.

So when the mapped page is relesed, it will result in kernel oops
because the page is not marked mapped.

This patch add tail process for compound page in 1GB huge page which
keeps the same process as 2M page.

Reproduce like:
1. Add grub boot option: hugepagesz=1G hugepages=8
2. mount -t hugetlbfs -o pagesize=1G hugetlbfs /dev/hugepages
3. qemu-kvm -m 2048 -hda os-kvm.img -cpu kvm64 -smp 4 -mem-path /dev/hugepages
	-net none -device pci-assign,host=07:00.1

  kernel BUG at mm/swap.c:114!
  invalid opcode: 0000 [#1] SMP
  Call Trace:
    put_page+0x15/0x37
    kvm_release_pfn_clean+0x31/0x36
    kvm_iommu_put_pages+0x94/0xb1
    kvm_iommu_unmap_memslots+0x80/0xb6
    kvm_assign_device+0xba/0x117
    kvm_vm_ioctl_assigned_device+0x301/0xa47
    kvm_vm_ioctl+0x36c/0x3a2
    do_vfs_ioctl+0x49e/0x4e4
    sys_ioctl+0x5a/0x7c
    system_call_fastpath+0x16/0x1b
  RIP  put_compound_page+0xd4/0x168

Signed-off-by: Youquan Song <youquan.song@intel.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-12-09 07:50:28 -08:00

394 lines
10 KiB
C

/*
* Lockless get_user_pages_fast for x86
*
* Copyright (C) 2008 Nick Piggin
* Copyright (C) 2008 Novell Inc.
*/
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/vmstat.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <asm/pgtable.h>
static inline pte_t gup_get_pte(pte_t *ptep)
{
#ifndef CONFIG_X86_PAE
return ACCESS_ONCE(*ptep);
#else
/*
* With get_user_pages_fast, we walk down the pagetables without taking
* any locks. For this we would like to load the pointers atomically,
* but that is not possible (without expensive cmpxchg8b) on PAE. What
* we do have is the guarantee that a pte will only either go from not
* present to present, or present to not present or both -- it will not
* switch to a completely different present page without a TLB flush in
* between; something that we are blocking by holding interrupts off.
*
* Setting ptes from not present to present goes:
* ptep->pte_high = h;
* smp_wmb();
* ptep->pte_low = l;
*
* And present to not present goes:
* ptep->pte_low = 0;
* smp_wmb();
* ptep->pte_high = 0;
*
* We must ensure here that the load of pte_low sees l iff pte_high
* sees h. We load pte_high *after* loading pte_low, which ensures we
* don't see an older value of pte_high. *Then* we recheck pte_low,
* which ensures that we haven't picked up a changed pte high. We might
* have got rubbish values from pte_low and pte_high, but we are
* guaranteed that pte_low will not have the present bit set *unless*
* it is 'l'. And get_user_pages_fast only operates on present ptes, so
* we're safe.
*
* gup_get_pte should not be used or copied outside gup.c without being
* very careful -- it does not atomically load the pte or anything that
* is likely to be useful for you.
*/
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;
#endif
}
/*
* The performance critical leaf functions are made noinline otherwise gcc
* inlines everything into a single function which results in too much
* register pressure.
*/
static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
unsigned long mask;
pte_t *ptep;
mask = _PAGE_PRESENT|_PAGE_USER;
if (write)
mask |= _PAGE_RW;
ptep = pte_offset_map(&pmd, addr);
do {
pte_t pte = gup_get_pte(ptep);
struct page *page;
if ((pte_flags(pte) & (mask | _PAGE_SPECIAL)) != mask) {
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 noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
unsigned long mask;
pte_t pte = *(pte_t *)&pmd;
struct page *head, *page;
int refs;
mask = _PAGE_PRESENT|_PAGE_USER;
if (write)
mask |= _PAGE_RW;
if ((pte_flags(pte) & mask) != mask)
return 0;
/* hugepages are never "special" */
VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
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_large(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 noinline int gup_huge_pud(pud_t pud, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
unsigned long mask;
pte_t pte = *(pte_t *)&pud;
struct page *head, *page;
int refs;
mask = _PAGE_PRESENT|_PAGE_USER;
if (write)
mask |= _PAGE_RW;
if ((pte_flags(pte) & mask) != mask)
return 0;
/* hugepages are never "special" */
VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL);
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;
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_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_large(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 on x86.
*
* So long as we atomically load page table pointers versus teardown
* (which we do on x86, with the above PAE exception), we can follow the
* address down to the 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 nr = 0;
start &= PAGE_MASK;
addr = start;
len = (unsigned long) nr_pages << PAGE_SHIFT;
end = start + len;
if (end < start)
goto slow_irqon;
#ifdef CONFIG_X86_64
if (end >> __VIRTUAL_MASK_SHIFT)
goto slow_irqon;
#endif
/*
* 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 on x86.
*
* So long as we atomically load page table pointers versus teardown
* (which we do on x86, with the above PAE exception), we can follow the
* address down to the the page and take a ref on it.
*/
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;
{
int ret;
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;
}
}