Merge commit 'v2.6.27-rc3' into x86/prototypes

Conflicts:

	include/asm-x86/dma-mapping.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 222 insertions, 100 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 2302d228fe04..1002f473f497 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -51,6 +51,7 @@
 #include <linux/init.h>
 #include <linux/writeback.h>
 #include <linux/memcontrol.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
@@ -61,6 +62,8 @@
 #include <linux/swapops.h>
 #include <linux/elf.h>
 
+#include "internal.h"
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 /* use the per-pgdat data instead for discontigmem - mbligh */
 unsigned long max_mapnr;
@@ -211,7 +214,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
  *
  * Must be called with pagetable lock held.
  */
-void free_pgd_range(struct mmu_gather **tlb,
+void free_pgd_range(struct mmu_gather *tlb,
                         unsigned long addr, unsigned long end,
                         unsigned long floor, unsigned long ceiling)
 {
@@ -262,16 +265,16 @@ void free_pgd_range(struct mmu_gather **tlb,
                 return;
 
         start = addr;
-        pgd = pgd_offset((*tlb)->mm, addr);
+        pgd = pgd_offset(tlb->mm, addr);
         do {
                 next = pgd_addr_end(addr, end);
                 if (pgd_none_or_clear_bad(pgd))
                         continue;
-                free_pud_range(*tlb, pgd, addr, next, floor, ceiling);
+                free_pud_range(tlb, pgd, addr, next, floor, ceiling);
         } while (pgd++, addr = next, addr != end);
 }
 
-void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
+void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
                 unsigned long floor, unsigned long ceiling)
 {
         while (vma) {
@@ -372,7 +375,8 @@ static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss)
  *
  * The calling function must still handle the error.
  */
-void print_bad_pte(struct vm_area_struct *vma, pte_t pte, unsigned long vaddr)
+static void print_bad_pte(struct vm_area_struct *vma, pte_t pte,
+                          unsigned long vaddr)
 {
         printk(KERN_ERR "Bad pte = %08llx, process = %s, "
                         "vm_flags = %lx, vaddr = %lx\n",
@@ -649,6 +653,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
         unsigned long next;
         unsigned long addr = vma->vm_start;
         unsigned long end = vma->vm_end;
+        int ret;
 
         /*
          * Don't copy ptes where a page fault will fill them correctly.
@@ -664,17 +669,33 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
         if (is_vm_hugetlb_page(vma))
                 return copy_hugetlb_page_range(dst_mm, src_mm, vma);
 
+        /*
+         * We need to invalidate the secondary MMU mappings only when
+         * there could be a permission downgrade on the ptes of the
+         * parent mm. And a permission downgrade will only happen if
+         * is_cow_mapping() returns true.
+         */
+        if (is_cow_mapping(vma->vm_flags))
+                mmu_notifier_invalidate_range_start(src_mm, addr, end);
+
+        ret = 0;
         dst_pgd = pgd_offset(dst_mm, addr);
         src_pgd = pgd_offset(src_mm, addr);
         do {
                 next = pgd_addr_end(addr, end);
                 if (pgd_none_or_clear_bad(src_pgd))
                         continue;
-                if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
-                                                vma, addr, next))
-                        return -ENOMEM;
+                if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+                                            vma, addr, next))) {
+                        ret = -ENOMEM;
+                        break;
+                }
         } while (dst_pgd++, src_pgd++, addr = next, addr != end);
-        return 0;
+
+        if (is_cow_mapping(vma->vm_flags))
+                mmu_notifier_invalidate_range_end(src_mm,
+                                                  vma->vm_start, end);
+        return ret;
 }
 
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
@@ -878,7 +899,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
         unsigned long start = start_addr;
         spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
         int fullmm = (*tlbp)->fullmm;
+        struct mm_struct *mm = vma->vm_mm;
 
+        mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
         for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
                 unsigned long end;
 
@@ -899,9 +922,23 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
                         }
 
                         if (unlikely(is_vm_hugetlb_page(vma))) {
-                                unmap_hugepage_range(vma, start, end);
-                                zap_work -= (end - start) /
-                                                (HPAGE_SIZE / PAGE_SIZE);
+                                /*
+                                 * It is undesirable to test vma->vm_file as it
+                                 * should be non-null for valid hugetlb area.
+                                 * However, vm_file will be NULL in the error
+                                 * cleanup path of do_mmap_pgoff. When
+                                 * hugetlbfs ->mmap method fails,
+                                 * do_mmap_pgoff() nullifies vma->vm_file
+                                 * before calling this function to clean up.
+                                 * Since no pte has actually been setup, it is
+                                 * safe to do nothing in this case.
+                                 */
+                                if (vma->vm_file) {
+                                        unmap_hugepage_range(vma, start, end, NULL);
+                                        zap_work -= (end - start) /
+                                        pages_per_huge_page(hstate_vma(vma));
+                                }
+
                                 start = end;
                         } else
                                 start = unmap_page_range(*tlbp, vma,
@@ -929,6 +966,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
                 }
         }
 out:
+        mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
         return start;   /* which is now the end (or restart) address */
 }
 
@@ -956,6 +994,29 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
         return end;
 }
 
+/**
+ * zap_vma_ptes - remove ptes mapping the vma
+ * @vma: vm_area_struct holding ptes to be zapped
+ * @address: starting address of pages to zap
+ * @size: number of bytes to zap
+ *
+ * This function only unmaps ptes assigned to VM_PFNMAP vmas.
+ *
+ * The entire address range must be fully contained within the vma.
+ *
+ * Returns 0 if successful.
+ */
+int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
+                unsigned long size)
+{
+        if (address < vma->vm_start || address + size > vma->vm_end ||
+                        !(vma->vm_flags & VM_PFNMAP))
+                return -1;
+        zap_page_range(vma, address, size, NULL);
+        return 0;
+}
+EXPORT_SYMBOL_GPL(zap_vma_ptes);
+
 /*
  * Do a quick page-table lookup for a single page.
  */
@@ -982,19 +1043,24 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
                 goto no_page_table;
 
         pud = pud_offset(pgd, address);
-        if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+        if (pud_none(*pud))
                 goto no_page_table;
-        
+        if (pud_huge(*pud)) {
+                BUG_ON(flags & FOLL_GET);
+                page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
+                goto out;
+        }
+        if (unlikely(pud_bad(*pud)))
+                goto no_page_table;
+
         pmd = pmd_offset(pud, address);
         if (pmd_none(*pmd))
                 goto no_page_table;
-
         if (pmd_huge(*pmd)) {
                 BUG_ON(flags & FOLL_GET);
                 page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
                 goto out;
         }
-
         if (unlikely(pmd_bad(*pmd)))
                 goto no_page_table;
 
@@ -1058,11 +1124,9 @@ static inline int use_zero_page(struct vm_area_struct *vma)
         if (vma->vm_flags & (VM_LOCKED | VM_SHARED))
                 return 0;
         /*
-         * And if we have a fault or a nopfn routine, it's not an
-         * anonymous region.
+         * And if we have a fault routine, it's not an anonymous region.
          */
-        return !vma->vm_ops ||
-                (!vma->vm_ops->fault && !vma->vm_ops->nopfn);
+        return !vma->vm_ops || !vma->vm_ops->fault;
 }
 
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
@@ -1338,6 +1402,11 @@ out:
  *
  * This function should only be called from a vm_ops->fault handler, and
  * in that case the handler should return NULL.
+ *
+ * vma cannot be a COW mapping.
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
  */
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
                         unsigned long pfn)
@@ -1548,6 +1617,8 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
         unsigned long next;
         int err;
 
+        BUG_ON(pud_huge(*pud));
+
         pmd = pmd_alloc(mm, pud, addr);
         if (!pmd)
                 return -ENOMEM;
@@ -1589,10 +1660,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 {
         pgd_t *pgd;
         unsigned long next;
-        unsigned long end = addr + size;
+        unsigned long start = addr, end = addr + size;
         int err;
 
         BUG_ON(addr >= end);
+        mmu_notifier_invalidate_range_start(mm, start, end);
         pgd = pgd_offset(mm, addr);
         do {
                 next = pgd_addr_end(addr, end);
@@ -1600,6 +1672,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
                 if (err)
                         break;
         } while (pgd++, addr = next, addr != end);
+        mmu_notifier_invalidate_range_end(mm, start, end);
         return err;
 }
 EXPORT_SYMBOL_GPL(apply_to_page_range);
@@ -1716,7 +1789,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
          * not dirty accountable.
          */
         if (PageAnon(old_page)) {
-                if (!TestSetPageLocked(old_page)) {
+                if (trylock_page(old_page)) {
                         reuse = can_share_swap_page(old_page);
                         unlock_page(old_page);
                 }
@@ -1812,7 +1885,7 @@ gotten:
                  * seen in the presence of one thread doing SMC and another
                  * thread doing COW.
                  */
-                ptep_clear_flush(vma, address, page_table);
+                ptep_clear_flush_notify(vma, address, page_table);
                 set_pte_at(mm, address, page_table, entry);
                 update_mmu_cache(vma, address, entry);
                 lru_cache_add_active(new_page);
@@ -2501,59 +2574,6 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
 }
 
-
-/*
- * do_no_pfn() tries to create a new page mapping for a page without
- * a struct_page backing it
- *
- * As this is called only for pages that do not currently exist, we
- * do not need to flush old virtual caches or the TLB.
- *
- * We enter with non-exclusive mmap_sem (to exclude vma changes,
- * but allow concurrent faults), and pte mapped but not yet locked.
- * We return with mmap_sem still held, but pte unmapped and unlocked.
- *
- * It is expected that the ->nopfn handler always returns the same pfn
- * for a given virtual mapping.
- *
- * Mark this `noinline' to prevent it from bloating the main pagefault code.
- */
-static noinline int do_no_pfn(struct mm_struct *mm, struct vm_area_struct *vma,
-                     unsigned long address, pte_t *page_table, pmd_t *pmd,
-                     int write_access)
-{
-        spinlock_t *ptl;
-        pte_t entry;
-        unsigned long pfn;
-
-        pte_unmap(page_table);
-        BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
-        BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
-
-        pfn = vma->vm_ops->nopfn(vma, address & PAGE_MASK);
-
-        BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn));
-
-        if (unlikely(pfn == NOPFN_OOM))
-                return VM_FAULT_OOM;
-        else if (unlikely(pfn == NOPFN_SIGBUS))
-                return VM_FAULT_SIGBUS;
-        else if (unlikely(pfn == NOPFN_REFAULT))
-                return 0;
-
-        page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
-
-        /* Only go through if we didn't race with anybody else... */
-        if (pte_none(*page_table)) {
-                entry = pfn_pte(pfn, vma->vm_page_prot);
-                if (write_access)
-                        entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-                set_pte_at(mm, address, page_table, entry);
-        }
-        pte_unmap_unlock(page_table, ptl);
-        return 0;
-}
-
 /*
  * Fault of a previously existing named mapping. Repopulate the pte
  * from the encoded file_pte if possible. This enables swappable
@@ -2614,9 +2634,6 @@ static inline int handle_pte_fault(struct mm_struct *mm,
                                 if (likely(vma->vm_ops->fault))
                                         return do_linear_fault(mm, vma, address,
                                                 pte, pmd, write_access, entry);
-                                if (unlikely(vma->vm_ops->nopfn))
-                                        return do_no_pfn(mm, vma, address, pte,
-                                                         pmd, write_access);
                         }
                         return do_anonymous_page(mm, vma, address,
                                                  pte, pmd, write_access);
@@ -2748,16 +2765,26 @@ int make_pages_present(unsigned long addr, unsigned long end)
 
         vma = find_vma(current->mm, addr);
         if (!vma)
-                return -1;
+                return -ENOMEM;
         write = (vma->vm_flags & VM_WRITE) != 0;
         BUG_ON(addr >= end);
         BUG_ON(end > vma->vm_end);
         len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
         ret = get_user_pages(current, current->mm, addr,
                         len, write, 0, NULL, NULL);
-        if (ret < 0)
+        if (ret < 0) {
+                /*
+                   SUS require strange return value to mlock
+                    - invalid addr generate to ENOMEM.
+                    - out of memory should generate EAGAIN.
+                */
+                if (ret == -EFAULT)
+                        ret = -ENOMEM;
+                else if (ret == -ENOMEM)
+                        ret = -EAGAIN;
                 return ret;
-        return ret == len ? 0 : -1;
+        }
+        return ret == len ? 0 : -ENOMEM;
 }
 
 #if !defined(__HAVE_ARCH_GATE_AREA)
@@ -2804,6 +2831,86 @@ int in_gate_area_no_task(unsigned long addr)
 
 #endif  /* __HAVE_ARCH_GATE_AREA */
 
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+static resource_size_t follow_phys(struct vm_area_struct *vma,
+                        unsigned long address, unsigned int flags,
+                        unsigned long *prot)
+{
+        pgd_t *pgd;
+        pud_t *pud;
+        pmd_t *pmd;
+        pte_t *ptep, pte;
+        spinlock_t *ptl;
+        resource_size_t phys_addr = 0;
+        struct mm_struct *mm = vma->vm_mm;
+
+        VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP)));
+
+        pgd = pgd_offset(mm, address);
+        if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
+                goto no_page_table;
+
+        pud = pud_offset(pgd, address);
+        if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+                goto no_page_table;
+
+        pmd = pmd_offset(pud, address);
+        if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+                goto no_page_table;
+
+        /* We cannot handle huge page PFN maps. Luckily they don't exist. */
+        if (pmd_huge(*pmd))
+                goto no_page_table;
+
+        ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+        if (!ptep)
+                goto out;
+
+        pte = *ptep;
+        if (!pte_present(pte))
+                goto unlock;
+        if ((flags & FOLL_WRITE) && !pte_write(pte))
+                goto unlock;
+        phys_addr = pte_pfn(pte);
+        phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */
+
+        *prot = pgprot_val(pte_pgprot(pte));
+
+unlock:
+        pte_unmap_unlock(ptep, ptl);
+out:
+        return phys_addr;
+no_page_table:
+        return 0;
+}
+
+int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
+                        void *buf, int len, int write)
+{
+        resource_size_t phys_addr;
+        unsigned long prot = 0;
+        void *maddr;
+        int offset = addr & (PAGE_SIZE-1);
+
+        if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+                return -EINVAL;
+
+        phys_addr = follow_phys(vma, addr, write, &prot);
+
+        if (!phys_addr)
+                return -EINVAL;
+
+        maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot);
+        if (write)
+                memcpy_toio(maddr + offset, buf, len);
+        else
+                memcpy_fromio(buf, maddr + offset, len);
+        iounmap(maddr);
+
+        return len;
+}
+#endif
+
 /*
  * Access another process' address space.
  * Source/target buffer must be kernel space,
@@ -2813,7 +2920,6 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 {
         struct mm_struct *mm;
         struct vm_area_struct *vma;
-        struct page *page;
         void *old_buf = buf;
 
         mm = get_task_mm(tsk);
@@ -2825,28 +2931,44 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
         while (len) {
                 int bytes, ret, offset;
                 void *maddr;
+                struct page *page = NULL;
 
                 ret = get_user_pages(tsk, mm, addr, 1,
                                 write, 1, &page, &vma);
-                if (ret <= 0)
-                        break;
-
-                bytes = len;
-                offset = addr & (PAGE_SIZE-1);
-                if (bytes > PAGE_SIZE-offset)
-                        bytes = PAGE_SIZE-offset;
-
-                maddr = kmap(page);
-                if (write) {
-                        copy_to_user_page(vma, page, addr,
-                                          maddr + offset, buf, bytes);
-                        set_page_dirty_lock(page);
+                if (ret <= 0) {
+                        /*
+                         * Check if this is a VM_IO | VM_PFNMAP VMA, which
+                         * we can access using slightly different code.
+                         */
+#ifdef CONFIG_HAVE_IOREMAP_PROT
+                        vma = find_vma(mm, addr);
+                        if (!vma)
+                                break;
+                        if (vma->vm_ops && vma->vm_ops->access)
+                                ret = vma->vm_ops->access(vma, addr, buf,
+                                                          len, write);
+                        if (ret <= 0)
+#endif
+                                break;
+                        bytes = ret;
                 } else {
-                        copy_from_user_page(vma, page, addr,
-                                            buf, maddr + offset, bytes);
+                        bytes = len;
+                        offset = addr & (PAGE_SIZE-1);
+                        if (bytes > PAGE_SIZE-offset)
+                                bytes = PAGE_SIZE-offset;
+
+                        maddr = kmap(page);
+                        if (write) {
+                                copy_to_user_page(vma, page, addr,
+                                                  maddr + offset, buf, bytes);
+                                set_page_dirty_lock(page);
+                        } else {
+                                copy_from_user_page(vma, page, addr,
+                                                    buf, maddr + offset, bytes);
+                        }
+                        kunmap(page);
+                        page_cache_release(page);
                 }
-                kunmap(page);
-                page_cache_release(page);
                 len -= bytes;
                 buf += bytes;
                 addr += bytes;