Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  deal with races in /proc/*/{syscall,stack,personality}
  proc: enable writing to /proc/pid/mem
  proc: make check_mem_permission() return an mm_struct on success
  proc: hold cred_guard_mutex in check_mem_permission()
  proc: disable mem_write after exec
  mm: implement access_remote_vm
  mm: factor out main logic of access_process_vm
  mm: use mm_struct to resolve gate vma's in __get_user_pages
  mm: arch: rename in_gate_area_no_task to in_gate_area_no_mm
  mm: arch: make in_gate_area take an mm_struct instead of a task_struct
  mm: arch: make get_gate_vma take an mm_struct instead of a task_struct
  x86: mark associated mm when running a task in 32 bit compatibility mode
  x86: add context tag to mark mm when running a task in 32-bit compatibility mode
  auxv: require the target to be tracable (or yourself)
  close race in /proc/*/environ
  report errors in /proc/*/*map* sanely
  pagemap: close races with suid execve
  make sessionid permissions in /proc/*/task/* match those in /proc/*
  fix leaks in path_lookupat()

Fix up trivial conflicts in fs/proc/base.c

arch/powerpc/kernel/vdso.c

@@ -820,17 +820,17 @@ static int __init vdso_init(void)
 }
 arch_initcall(vdso_init);
 
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 	return 0;
 }
 
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
 {
 	return 0;
 }
 
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 	return NULL;
 }

arch/s390/kernel/vdso.c

@@ -337,17 +337,17 @@ static int __init vdso_init(void)
 }
 arch_initcall(vdso_init);
 
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 	return 0;
 }
 
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
 {
 	return 0;
 }
 
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 	return NULL;
 }

arch/sh/kernel/vsyscall/vsyscall.c

@@ -94,17 +94,17 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 	return NULL;
 }
 
-struct vm_area_struct *get_gate_vma(struct task_struct *task)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 	return NULL;
 }
 
-int in_gate_area(struct task_struct *task, unsigned long address)
+int in_gate_area(struct mm_struct *mm, unsigned long address)
 {
 	return 0;
 }
 
-int in_gate_area_no_task(unsigned long address)
+int in_gate_area_no_mm(unsigned long address)
 {
 	return 0;
 }

arch/x86/ia32/ia32_aout.c

@@ -298,6 +298,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	/* OK, This is the point of no return */
 	set_personality(PER_LINUX);
 	set_thread_flag(TIF_IA32);
+	current->mm->context.ia32_compat = 1;
 
 	setup_new_exec(bprm);
 

arch/x86/include/asm/mmu.h

@@ -13,6 +13,12 @@ typedef struct {
 	int size;
 	struct mutex lock;
 	void *vdso;
+
+#ifdef CONFIG_X86_64
+	/* True if mm supports a task running in 32 bit compatibility mode. */
+	unsigned short ia32_compat;
+#endif
+
 } mm_context_t;
 
 #ifdef CONFIG_SMP

arch/x86/kernel/process_64.c

@@ -501,6 +501,10 @@ void set_personality_64bit(void)
 	/* Make sure to be in 64bit mode */
 	clear_thread_flag(TIF_IA32);
 
+	/* Ensure the corresponding mm is not marked. */
+	if (current->mm)
+		current->mm->context.ia32_compat = 0;
+
 	/* TBD: overwrites user setup. Should have two bits.
 	   But 64bit processes have always behaved this way,
 	   so it's not too bad. The main problem is just that
@@ -516,6 +520,10 @@ void set_personality_ia32(void)
 	set_thread_flag(TIF_IA32);
 	current->personality |= force_personality32;
 
+	/* Mark the associated mm as containing 32-bit tasks. */
+	if (current->mm)
+		current->mm->context.ia32_compat = 1;
+
 	/* Prepare the first "return" to user space */
 	current_thread_info()->status |= TS_COMPAT;
 }

arch/x86/mm/init_64.c

@@ -862,18 +862,18 @@ static struct vm_area_struct gate_vma = {
 	.vm_flags	= VM_READ | VM_EXEC
 };
 
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
 #ifdef CONFIG_IA32_EMULATION
-	if (test_tsk_thread_flag(tsk, TIF_IA32))
+	if (!mm || mm->context.ia32_compat)
 		return NULL;
 #endif
 	return &gate_vma;
 }
 
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
 {
-	struct vm_area_struct *vma = get_gate_vma(task);
+	struct vm_area_struct *vma = get_gate_vma(mm);
 
 	if (!vma)
 		return 0;
@@ -882,11 +882,11 @@ int in_gate_area(struct task_struct *task, unsigned long addr)
 }
 
 /*
- * Use this when you have no reliable task/vma, typically from interrupt
- * context. It is less reliable than using the task's vma and may give
- * false positives:
+ * Use this when you have no reliable mm, typically from interrupt
+ * context. It is less reliable than using a task's mm and may give
+ * false positives.
  */
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 	return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
 }

arch/x86/vdso/vdso32-setup.c

@@ -417,24 +417,25 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 	return NULL;
 }
 
-struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
 {
-	struct mm_struct *mm = tsk->mm;
-
-	/* Check to see if this task was created in compat vdso mode */
+	/*
+	 * Check to see if the corresponding task was created in compat vdso
+	 * mode.
+	 */
 	if (mm && mm->context.vdso == (void *)VDSO_HIGH_BASE)
 		return &gate_vma;
 	return NULL;
 }
 
-int in_gate_area(struct task_struct *task, unsigned long addr)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
 {
-	const struct vm_area_struct *vma = get_gate_vma(task);
+	const struct vm_area_struct *vma = get_gate_vma(mm);
 
 	return vma && addr >= vma->vm_start && addr < vma->vm_end;
 }
 
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 	return 0;
 }

fs/binfmt_elf.c

@@ -1906,7 +1906,7 @@ static int elf_core_dump(struct coredump_params *cprm)
 	segs = current->mm->map_count;
 	segs += elf_core_extra_phdrs();
 
-	gate_vma = get_gate_vma(current);
+	gate_vma = get_gate_vma(current->mm);
 	if (gate_vma != NULL)
 		segs++;
 

fs/namei.c

@@ -1650,13 +1650,16 @@ static int path_lookupat(int dfd, const char *name,
 			err = -ECHILD;
 	}
 
-	if (!err)
+	if (!err) {
 		err = handle_reval_path(nd);
+		if (err)
+			path_put(&nd->path);
+	}
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY) {
 		if (!nd->inode->i_op->lookup) {
 			path_put(&nd->path);
-			return -ENOTDIR;
+			err = -ENOTDIR;
 		}
 	}
 

fs/proc/task_mmu.c

@@ -121,14 +121,14 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
 	if (!priv->task)
-		return NULL;
+		return ERR_PTR(-ESRCH);
 
 	mm = mm_for_maps(priv->task);
-	if (!mm)
-		return NULL;
+	if (!mm || IS_ERR(mm))
+		return mm;
 	down_read(&mm->mmap_sem);
 
-	tail_vma = get_gate_vma(priv->task);
+	tail_vma = get_gate_vma(priv->task->mm);
 	priv->tail_vma = tail_vma;
 
 	/* Start with last addr hint */
@@ -279,7 +279,8 @@ static int show_map(struct seq_file *m, void *v)
 	show_map_vma(m, vma);
 
 	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
+		m->version = (vma != get_gate_vma(task->mm))
+			? vma->vm_start : 0;
 	return 0;
 }
 
@@ -468,7 +469,8 @@ static int show_smap(struct seq_file *m, void *v)
 			(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
 
 	if (m->count < m->size)  /* vma is copied successfully */
-		m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
+		m->version = (vma != get_gate_vma(task->mm))
+			? vma->vm_start : 0;
 	return 0;
 }
 
@@ -764,8 +766,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!task)
 		goto out;
 
-	ret = -EACCES;
-	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+	mm = mm_for_maps(task);
+	ret = PTR_ERR(mm);
+	if (!mm || IS_ERR(mm))
 		goto out_task;
 
 	ret = -EINVAL;
@@ -778,10 +781,6 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!count)
 		goto out_task;
 
-	mm = get_task_mm(task);
-	if (!mm)
-		goto out_task;
-
 	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
 	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
 	ret = -ENOMEM;

fs/proc/task_nommu.c

@@ -199,13 +199,13 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 	/* pin the task and mm whilst we play with them */
 	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
 	if (!priv->task)
-		return NULL;
+		return ERR_PTR(-ESRCH);
 
 	mm = mm_for_maps(priv->task);
-	if (!mm) {
+	if (!mm || IS_ERR(mm)) {
 		put_task_struct(priv->task);
 		priv->task = NULL;
-		return NULL;
+		return mm;
 	}
 	down_read(&mm->mmap_sem);
 

include/linux/mm.h

@@ -982,6 +982,8 @@ static inline int handle_mm_fault(struct mm_struct *mm,
 
 extern int make_pages_present(unsigned long addr, unsigned long end);
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
+extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
+		void *buf, int len, int write);
 
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long start, int len, unsigned int foll_flags,
@@ -1592,13 +1594,13 @@ static inline bool kernel_page_present(struct page *page) { return true; }
 #endif /* CONFIG_HIBERNATION */
 #endif
 
-extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk);
+extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
 #ifdef	__HAVE_ARCH_GATE_AREA
-int in_gate_area_no_task(unsigned long addr);
-int in_gate_area(struct task_struct *task, unsigned long addr);
+int in_gate_area_no_mm(unsigned long addr);
+int in_gate_area(struct mm_struct *mm, unsigned long addr);
 #else
-int in_gate_area_no_task(unsigned long addr);
-#define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);})
+int in_gate_area_no_mm(unsigned long addr);
+#define in_gate_area(mm, addr) ({(void)mm; in_gate_area_no_mm(addr);})
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
 int drop_caches_sysctl_handler(struct ctl_table *, int,

kernel/kallsyms.c

@@ -64,14 +64,14 @@ static inline int is_kernel_text(unsigned long addr)
 	if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) ||
 	    arch_is_kernel_text(addr))
 		return 1;
-	return in_gate_area_no_task(addr);
+	return in_gate_area_no_mm(addr);
 }
 
 static inline int is_kernel(unsigned long addr)
 {
 	if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end)
 		return 1;
-	return in_gate_area_no_task(addr);
+	return in_gate_area_no_mm(addr);
 }
 
 static int is_ksym_addr(unsigned long addr)

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;
@@ -1591,10 +1591,13 @@ 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) {
 					if (nonblocking)
@@ -1641,7 +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
@@ -3499,7 +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;
@@ -3508,7 +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))
@@ -3649,20 +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) {
@@ -3711,11 +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.
  */

mm/mlock.c

@@ -237,7 +237,7 @@ long mlock_vma_pages_range(struct vm_area_struct *vma,
 
 	if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
 			is_vm_hugetlb_page(vma) ||
-			vma == get_gate_vma(current))) {
+			vma == get_gate_vma(current->mm))) {
 
 		__mlock_vma_pages_range(vma, start, end, NULL);
 
@@ -332,7 +332,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	int lock = newflags & VM_LOCKED;
 
 	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
-	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current))
+	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
 		goto out;	/* don't set VM_LOCKED,  don't count */
 
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);

mm/nommu.c

@@ -1963,7 +1963,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 	return -ENOMEM;
 }
 
-int in_gate_area_no_task(unsigned long addr)
+int in_gate_area_no_mm(unsigned long addr)
 {
 	return 0;
 }