Merge branch 'uprobes/core' of git://git.kernel.org/pub/scm/linux/kernel/git/oleg/misc into perf/urgent

Pull various uprobes bugfixes from Oleg Nesterov - mostly race and
failure path fixes.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 162 insertions, 183 deletions

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 98256bc71ee1..5cc4e7e42e68 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -78,15 +78,23 @@ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ];
  */
 static atomic_t uprobe_events = ATOMIC_INIT(0);
 
+/* Have a copy of original instruction */
+#define UPROBE_COPY_INSN        0
+/* Dont run handlers when first register/ last unregister in progress*/
+#define UPROBE_RUN_HANDLER      1
+/* Can skip singlestep */
+#define UPROBE_SKIP_SSTEP       2
+
 struct uprobe {
         struct rb_node          rb_node;        /* node in the rb tree */
         atomic_t                ref;
         struct rw_semaphore     consumer_rwsem;
+        struct mutex            copy_mutex;     /* TODO: kill me and UPROBE_COPY_INSN */
         struct list_head        pending_list;
         struct uprobe_consumer  *consumers;
         struct inode            *inode;         /* Also hold a ref to inode */
         loff_t                  offset;
-        int                     flags;
+        unsigned long           flags;
         struct arch_uprobe      arch;
 };
 
@@ -100,17 +108,12 @@ struct uprobe {
  */
 static bool valid_vma(struct vm_area_struct *vma, bool is_register)
 {
-        if (!vma->vm_file)
-                return false;
-
-        if (!is_register)
-                return true;
+        vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_SHARED;
 
-        if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED))
-                                == (VM_READ|VM_EXEC))
-                return true;
+        if (is_register)
+                flags |= VM_WRITE;
 
-        return false;
+        return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC;
 }
 
 static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset)
@@ -193,19 +196,44 @@ bool __weak is_swbp_insn(uprobe_opcode_t *insn)
         return *insn == UPROBE_SWBP_INSN;
 }
 
+static void copy_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode)
+{
+        void *kaddr = kmap_atomic(page);
+        memcpy(opcode, kaddr + (vaddr & ~PAGE_MASK), UPROBE_SWBP_INSN_SIZE);
+        kunmap_atomic(kaddr);
+}
+
+static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode)
+{
+        uprobe_opcode_t old_opcode;
+        bool is_swbp;
+
+        copy_opcode(page, vaddr, &old_opcode);
+        is_swbp = is_swbp_insn(&old_opcode);
+
+        if (is_swbp_insn(new_opcode)) {
+                if (is_swbp)            /* register: already installed? */
+                        return 0;
+        } else {
+                if (!is_swbp)           /* unregister: was it changed by us? */
+                        return 0;
+        }
+
+        return 1;
+}
+
 /*
  * NOTE:
  * Expect the breakpoint instruction to be the smallest size instruction for
  * the architecture. If an arch has variable length instruction and the
  * breakpoint instruction is not of the smallest length instruction
- * supported by that architecture then we need to modify read_opcode /
+ * supported by that architecture then we need to modify is_swbp_at_addr and
  * write_opcode accordingly. This would never be a problem for archs that
  * have fixed length instructions.
  */
 
 /*
  * write_opcode - write the opcode at a given virtual address.
- * @auprobe: arch breakpointing information.
  * @mm: the probed process address space.
  * @vaddr: the virtual address to store the opcode.
  * @opcode: opcode to be written at @vaddr.
@@ -216,8 +244,8 @@ bool __weak is_swbp_insn(uprobe_opcode_t *insn)
  * For mm @mm, write the opcode at @vaddr.
  * Return 0 (success) or a negative errno.
  */
-static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
-                        unsigned long vaddr, uprobe_opcode_t opcode)
+static int write_opcode(struct mm_struct *mm, unsigned long vaddr,
+                        uprobe_opcode_t opcode)
 {
         struct page *old_page, *new_page;
         void *vaddr_old, *vaddr_new;
@@ -226,10 +254,14 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 
 retry:
         /* Read the page with vaddr into memory */
-        ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma);
+        ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma);
         if (ret <= 0)
                 return ret;
 
+        ret = verify_opcode(old_page, vaddr, &opcode);
+        if (ret <= 0)
+                goto put_old;
+
         ret = -ENOMEM;
         new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr);
         if (!new_page)
@@ -264,63 +296,6 @@ put_old:
 }
 
 /**
- * read_opcode - read the opcode at a given virtual address.
- * @mm: the probed process address space.
- * @vaddr: the virtual address to read the opcode.
- * @opcode: location to store the read opcode.
- *
- * Called with mm->mmap_sem held (for read and with a reference to
- * mm.
- *
- * For mm @mm, read the opcode at @vaddr and store it in @opcode.
- * Return 0 (success) or a negative errno.
- */
-static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t *opcode)
-{
-        struct page *page;
-        void *vaddr_new;
-        int ret;
-
-        ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL);
-        if (ret <= 0)
-                return ret;
-
-        vaddr_new = kmap_atomic(page);
-        vaddr &= ~PAGE_MASK;
-        memcpy(opcode, vaddr_new + vaddr, UPROBE_SWBP_INSN_SIZE);
-        kunmap_atomic(vaddr_new);
-
-        put_page(page);
-
-        return 0;
-}
-
-static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr)
-{
-        uprobe_opcode_t opcode;
-        int result;
-
-        if (current->mm == mm) {
-                pagefault_disable();
-                result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr,
-                                                                sizeof(opcode));
-                pagefault_enable();
-
-                if (likely(result == 0))
-                        goto out;
-        }
-
-        result = read_opcode(mm, vaddr, &opcode);
-        if (result)
-                return result;
-out:
-        if (is_swbp_insn(&opcode))
-                return 1;
-
-        return 0;
-}
-
-/**
  * set_swbp - store breakpoint at a given address.