Merge branch 'master' of ssh://master.kernel.org/pub/scm/linux/kernel/git/kaber/nf-2.6

1 files changed, 59 insertions, 21 deletions

diff --git a/mm/memory.c b/mm/memory.c
index e48945ab362b..9da8cab1b1b0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1486,9 +1486,9 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                 struct vm_area_struct *vma;
 
                 vma = find_extend_vma(mm, start);
-                if (!vma && in_gate_area(tsk, start)) {
+                if (!vma && in_gate_area(mm, start)) {
                         unsigned long pg = start & PAGE_MASK;
-                        struct vm_area_struct *gate_vma = get_gate_vma(tsk);
+                        struct vm_area_struct *gate_vma = get_gate_vma(mm);
                         pgd_t *pgd;
                         pud_t *pud;
                         pmd_t *pmd;
@@ -1569,6 +1569,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                                         fault_flags |= FAULT_FLAG_WRITE;
                                 if (nonblocking)
                                         fault_flags |= FAULT_FLAG_ALLOW_RETRY;
+                                if (foll_flags & FOLL_NOWAIT)
+                                        fault_flags |= (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT);
 
                                 ret = handle_mm_fault(mm, vma, start,
                                                         fault_flags);
@@ -1589,13 +1591,17 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                                                 return i ? i : -EFAULT;
                                         BUG();
                                 }
-                                if (ret & VM_FAULT_MAJOR)
-                                        tsk->maj_flt++;
-                                else
-                                        tsk->min_flt++;
+
+                                if (tsk) {
+                                        if (ret & VM_FAULT_MAJOR)
+                                                tsk->maj_flt++;
+                                        else
+                                                tsk->min_flt++;
+                                }
 
                                 if (ret & VM_FAULT_RETRY) {
-                                        *nonblocking = 0;
+                                        if (nonblocking)
+                                                *nonblocking = 0;
                                         return i;
                                 }
 
@@ -1638,7 +1644,8 @@ EXPORT_SYMBOL(__get_user_pages);
 
 /**
  * get_user_pages() - pin user pages in memory
- * @tsk:        task_struct of target task
+ * @tsk:        the task_struct to use for page fault accounting, or
+ *              NULL if faults are not to be recorded.
  * @mm:         mm_struct of target mm
  * @start:      starting user address
  * @nr_pages:   number of pages from start to pin
@@ -2764,7 +2771,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
         swp_entry_t entry;
         pte_t pte;
         int locked;
-        struct mem_cgroup *ptr = NULL;
+        struct mem_cgroup *ptr;
         int exclusive = 0;
         int ret = 0;
 
@@ -3496,7 +3503,7 @@ static int __init gate_vma_init(void)
 __initcall(gate_vma_init);
 #endif
 
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 #ifdef AT_SYSINFO_EHDR
         return &gate_vma;
@@ -3505,7 +3512,7 @@ struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
 #endif
 }
 
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 #ifdef AT_SYSINFO_EHDR
         if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END))
@@ -3646,20 +3653,15 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 #endif
 
 /*
- * Access another process' address space.
- * Source/target buffer must be kernel space,
- * Do not walk the page table directly, use get_user_pages
+ * Access another process' address space as given in mm.  If non-NULL, use the
+ * given task for page fault accounting.
  */
-int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write)
+static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm,
+                unsigned long addr, void *buf, int len, int write)
 {
-        struct mm_struct *mm;
         struct vm_area_struct *vma;
         void *old_buf = buf;
 
-        mm = get_task_mm(tsk);
-        if (!mm)
-                return 0;
-
         down_read(&mm->mmap_sem);
         /* ignore errors, just check how much was successfully transferred */
         while (len) {
@@ -3708,11 +3710,47 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
                 addr += bytes;
         }
         up_read(&mm->mmap_sem);
-        mmput(mm);
 
         return buf - old_buf;
 }
 
+/**
+ * access_remote_vm - access another process' address space
+ * @mm:         the mm_struct of the target address space
+ * @addr:       start address to access
+ * @buf:        source or destination buffer
+ * @len:        number of bytes to transfer
+ * @write:      whether the access is a write
+ *
+ * The caller must hold a reference on @mm.
+ */
+int access_remote_vm(struct mm_struct *mm, unsigned long addr,
+                void *buf, int len, int write)
+{
+        return __access_remote_vm(NULL, mm, addr, buf, len, write);
+}
+
+/*
+ * Access another process' address space.
+ * Source/target buffer must be kernel space,
+ * Do not walk the page table directly, use get_user_pages
+ */
+int access_process_vm(struct task_struct *tsk, unsigned long addr,
+                void *buf, int len, int write)
+{
+        struct mm_struct *mm;
+        int ret;
+
+        mm = get_task_mm(tsk);
+        if (!mm)
+                return 0;
+
+        ret = __access_remote_vm(tsk, mm, addr, buf, len, write);
+        mmput(mm);
+
+        return ret;
+}
+
 /*
  * Print the name of a VMA.
  */