1 files changed, 206 insertions, 104 deletions

diff --git a/ipc/shm.c b/ipc/shm.c
index e25c7c6106bc..a89f001a8bf0 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -29,6 +29,7 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/shm.h>
+#include <uapi/linux/shm.h>
 #include <linux/init.h>
 #include <linux/file.h>
 #include <linux/mman.h>
@@ -60,11 +61,20 @@ struct shmid_kernel /* private to the kernel */
 	time64_t		shm_ctim;
 	struct pid		*shm_cprid;
 	struct pid		*shm_lprid;
-	struct user_struct	*mlock_user;
+	struct ucounts		*mlock_ucounts;
 
-	/* The task created the shm object.  NULL if the task is dead. */
+	/*
+	 * The task created the shm object, for
+	 * task_lock(shp->shm_creator)
+	 */
 	struct task_struct	*shm_creator;
-	struct list_head	shm_clist;	/* list by creator */
+
+	/*
+	 * List by creator. task_lock(->shm_creator) required for read/write.
+	 * If list_empty(), then the creator is dead already.
+	 */
+	struct list_head	shm_clist;
+	struct ipc_namespace	*ns;
 } __randomize_layout;
 
 /* shm_mode upper byte flags */
@@ -115,6 +125,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 	struct shmid_kernel *shp;
 
 	shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+	WARN_ON(ns != shp->ns);
 
 	if (shp->shm_nattch) {
 		shp->shm_perm.mode |= SHM_DEST;
@@ -222,20 +233,51 @@ static void shm_rcu_free(struct rcu_head *head)
 	struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel,
 							shm_perm);
 	security_shm_free(&shp->shm_perm);
-	kvfree(shp);
+	kfree(shp);
+}
+
+/*
+ * It has to be called with shp locked.
+ * It must be called before ipc_rmid()
+ */
+static inline void shm_clist_rm(struct shmid_kernel *shp)
+{
+	struct task_struct *creator;
+
+	/* ensure that shm_creator does not disappear */
+	rcu_read_lock();
+
+	/*
+	 * A concurrent exit_shm may do a list_del_init() as well.
+	 * Just do nothing if exit_shm already did the work
+	 */
+	if (!list_empty(&shp->shm_clist)) {
+		/*
+		 * shp->shm_creator is guaranteed to be valid *only*
+		 * if shp->shm_clist is not empty.
+		 */
+		creator = shp->shm_creator;
+
+		task_lock(creator);
+		/*
+		 * list_del_init() is a nop if the entry was already removed
+		 * from the list.
+		 */
+		list_del_init(&shp->shm_clist);
+		task_unlock(creator);
+	}
+	rcu_read_unlock();
 }
 
-static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
+static inline void shm_rmid(struct shmid_kernel *s)
 {
-	list_del(&s->shm_clist);
-	ipc_rmid(&shm_ids(ns), &s->shm_perm);
+	shm_clist_rm(s);
+	ipc_rmid(&shm_ids(s->ns), &s->shm_perm);
 }
 
 
-static int __shm_open(struct vm_area_struct *vma)
+static int __shm_open(struct shm_file_data *sfd)
 {
-	struct file *file = vma->vm_file;
-	struct shm_file_data *sfd = shm_file_data(file);
 	struct shmid_kernel *shp;
 
 	shp = shm_lock(sfd->ns, sfd->id);
@@ -259,7 +301,15 @@ static int __shm_open(struct vm_area_struct *vma)
 /* This is called by fork, once for every shm attach. */
 static void shm_open(struct vm_area_struct *vma)
 {
-	int err = __shm_open(vma);
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+	int err;
+
+	/* Always call underlying open if present */
+	if (sfd->vm_ops->open)
+		sfd->vm_ops->open(vma);
+
+	err = __shm_open(sfd);
 	/*
 	 * We raced in the idr lookup or with shm_destroy().
 	 * Either way, the ID is busted.
@@ -283,13 +333,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
 	shm_file = shp->shm_file;
 	shp->shm_file = NULL;
 	ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	shm_rmid(ns, shp);
+	shm_rmid(shp);
 	shm_unlock(shp);
 	if (!is_file_hugepages(shm_file))
-		shmem_lock(shm_file, 0, shp->mlock_user);
-	else if (shp->mlock_user)
-		user_shm_unlock(i_size_read(file_inode(shm_file)),
-				shp->mlock_user);
+		shmem_lock(shm_file, 0, shp->mlock_ucounts);
 	fput(shm_file);
 	ipc_update_pid(&shp->shm_cprid, NULL);
 	ipc_update_pid(&shp->shm_lprid, NULL);
@@ -306,10 +353,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
  *
  * 2) sysctl kernel.shm_rmid_forced is set to 1.
  */
-static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+static bool shm_may_destroy(struct shmid_kernel *shp)
 {
 	return (shp->shm_nattch == 0) &&
-	       (ns->shm_rmid_forced ||
+	       (shp->ns->shm_rmid_forced ||
 		(shp->shm_perm.mode & SHM_DEST));
 }
 
@@ -319,10 +366,8 @@ static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
  * The descriptor has already been removed from the current->mm->mmap list
  * and will later be kfree()d.
  */
-static void shm_close(struct vm_area_struct *vma)
+static void __shm_close(struct shm_file_data *sfd)
 {
-	struct file *file = vma->vm_file;
-	struct shm_file_data *sfd = shm_file_data(file);
 	struct shmid_kernel *shp;
 	struct ipc_namespace *ns = sfd->ns;
 
@@ -340,7 +385,7 @@ static void shm_close(struct vm_area_struct *vma)
 	ipc_update_pid(&shp->shm_lprid, task_tgid(current));
 	shp->shm_dtim = ktime_get_real_seconds();
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
@@ -348,6 +393,18 @@ done:
 	up_write(&shm_ids(ns).rwsem);
 }
 
+static void shm_close(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+	struct shm_file_data *sfd = shm_file_data(file);
+
+	/* Always call underlying close if present */
+	if (sfd->vm_ops->close)
+		sfd->vm_ops->close(vma);
+
+	__shm_close(sfd);
+}
+
 /* Called with ns->shm_ids(ns).rwsem locked */
 static int shm_try_destroy_orphaned(int id, void *p, void *data)
 {
@@ -361,10 +418,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
 	 *
 	 * As shp->* are changed under rwsem, it's safe to skip shp locking.
 	 */
-	if (shp->shm_creator != NULL)
+	if (!list_empty(&shp->shm_clist))
 		return 0;
 
-	if (shm_may_destroy(ns, shp)) {
+	if (shm_may_destroy(shp)) {
 		shm_lock_by_ptr(shp);
 		shm_destroy(ns, shp);
 	}
@@ -382,48 +439,97 @@ void shm_destroy_orphaned(struct ipc_namespace *ns)
 /* Locking assumes this will only be called with task == current */
 void exit_shm(struct task_struct *task)
 {
-	struct ipc_namespace *ns = task->nsproxy->ipc_ns;
-	struct shmid_kernel *shp, *n;
+	for (;;) {
+		struct shmid_kernel *shp;
+		struct ipc_namespace *ns;
 
-	if (list_empty(&task->sysvshm.shm_clist))
-		return;
+		task_lock(task);
+
+		if (list_empty(&task->sysvshm.shm_clist)) {
+			task_unlock(task);
+			break;
+		}
+
+		shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel,
+				shm_clist);
 
-	/*
-	 * If kernel.shm_rmid_forced is not set then only keep track of
-	 * which shmids are orphaned, so that a later set of the sysctl
-	 * can clean them up.
-	 */
-	if (!ns->shm_rmid_forced) {
-		down_read(&shm_ids(ns).rwsem);
-		list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist)
-			shp->shm_creator = NULL;
 		/*
-		 * Only under read lock but we are only called on current
-		 * so no entry on the list will be shared.
+		 * 1) Get pointer to the ipc namespace. It is worth to say
+		 * that this pointer is guaranteed to be valid because
+		 * shp lifetime is always shorter than namespace lifetime
+		 * in which shp lives.
+		 * We taken task_lock it means that shp won't be freed.
 		 */
-		list_del(&task->sysvshm.shm_clist);
-		up_read(&shm_ids(ns).rwsem);
-		return;
-	}
+		ns = shp->ns;
 
-	/*
-	 * Destroy all already created segments, that were not yet mapped,
-	 * and mark any mapped as orphan to cover the sysctl toggling.
-	 * Destroy is skipped if shm_may_destroy() returns false.
-	 */
-	down_write(&shm_ids(ns).rwsem);
-	list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) {
-		shp->shm_creator = NULL;
+		/*
+		 * 2) If kernel.shm_rmid_forced is not set then only keep track of
+		 * which shmids are orphaned, so that a later set of the sysctl
+		 * can clean them up.
+		 */
+		if (!ns->shm_rmid_forced)
+			goto unlink_continue;
 
-		if (shm_may_destroy(ns, shp)) {
-			shm_lock_by_ptr(shp);
-			shm_destroy(ns, shp);
+		/*
+		 * 3) get a reference to the namespace.
+		 *    The refcount could be already 0. If it is 0, then
+		 *    the shm objects will be free by free_ipc_work().
+		 */
+		ns = get_ipc_ns_not_zero(ns);
+		if (!ns) {
+unlink_continue:
+			list_del_init(&shp->shm_clist);
+			task_unlock(task);
+			continue;
 		}
-	}
 
-	/* Remove the list head from any segments still attached. */
-	list_del(&task->sysvshm.shm_clist);
-	up_write(&shm_ids(ns).rwsem);
+		/*
+		 * 4) get a reference to shp.
+		 *   This cannot fail: shm_clist_rm() is called before
+		 *   ipc_rmid(), thus the refcount cannot be 0.
+		 */
+		WARN_ON(!ipc_rcu_getref(&shp->shm_perm));
+
+		/*
+		 * 5) unlink the shm segment from the list of segments
+		 *    created by current.
+		 *    This must be done last. After unlinking,
+		 *    only the refcounts obtained above prevent IPC_RMID
+		 *    from destroying the segment or the namespace.
+		 */
+		list_del_init(&shp->shm_clist);
+
+		task_unlock(task);
+
+		/*
+		 * 6) we have all references
+		 *    Thus lock & if needed destroy shp.
+		 */
+		down_write(&shm_ids(ns).rwsem);
+		shm_lock_by_ptr(shp);
+		/*
+		 * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's
+		 * safe to call ipc_rcu_putref here
+		 */
+		ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
+
+		if (ipc_valid_object(&shp->shm_perm)) {
+			if (shm_may_destroy(shp))
+				shm_destroy(ns, shp);
+			else
+				shm_unlock(shp);
+		} else {
+			/*
+			 * Someone else deleted the shp from namespace
+			 * idr/kht while we have waited.
+			 * Just unlock and continue.
+			 */
+			shm_unlock(shp);
+		}
+
+		up_write(&shm_ids(ns).rwsem);
+		put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */
+	}
 }
 
 static vm_fault_t shm_fault(struct vm_fault *vmf)
@@ -434,13 +540,13 @@ static vm_fault_t shm_fault(struct vm_fault *vmf)
 	return sfd->vm_ops->fault(vmf);
 }
 
-static int shm_split(struct vm_area_struct *vma, unsigned long addr)
+static int shm_may_split(struct vm_area_struct *vma, unsigned long addr)
 {
 	struct file *file = vma->vm_file;
 	struct shm_file_data *sfd = shm_file_data(file);
 
-	if (sfd->vm_ops->split)
-		return sfd->vm_ops->split(vma, addr);
+	if (sfd->vm_ops->may_split)
+		return sfd->vm_ops->may_split(vma, addr);
 
 	return 0;
 }
@@ -457,30 +563,25 @@ static unsigned long shm_pagesize(struct vm_area_struct *vma)
 }
 
 #ifdef CONFIG_NUMA
-static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
+static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
 {
-	struct file *file = vma->vm_file;
-	struct shm_file_data *sfd = shm_file_data(file);
+	struct shm_file_data *sfd = shm_file_data(vma->vm_file);
 	int err = 0;
 
 	if (sfd->vm_ops->set_policy)
-		err = sfd->vm_ops->set_policy(vma, new);
+		err = sfd->vm_ops->set_policy(vma, mpol);
 	return err;
 }
 
 static struct mempolicy *shm_get_policy(struct vm_area_struct *vma,
-					unsigned long addr)
+					unsigned long addr, pgoff_t *ilx)
 {
-	struct file *file = vma->vm_file;
-	struct shm_file_data *sfd = shm_file_data(file);
-	struct mempolicy *pol = NULL;
+	struct shm_file_data *sfd = shm_file_data(vma->vm_file);
+	struct mempolicy *mpol = vma->vm_policy;
 
 	if (sfd->vm_ops->get_policy)
-		pol = sfd->vm_ops->get_policy(vma, addr);
-	else if (vma->vm_policy)
-		pol = vma->vm_policy;
-
-	return pol;
+		mpol = sfd->vm_ops->get_policy(vma, addr, ilx);
+	return mpol;
 }
 #endif
 
@@ -494,13 +595,13 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma)
 	 * IPC ID that was removed, and possibly even reused by another shm
 	 * segment already.  Propagate this case as an error to caller.
 	 */
-	ret = __shm_open(vma);
+	ret = __shm_open(sfd);
 	if (ret)
 		return ret;
 
 	ret = call_mmap(sfd->file, vma);
 	if (ret) {
-		shm_close(vma);
+		__shm_close(sfd);
 		return ret;
 	}
 	sfd->vm_ops = vma->vm_ops;
@@ -582,7 +683,7 @@ static const struct vm_operations_struct shm_vm_ops = {
 	.open	= shm_open,	/* callback for a new vm-area open */
 	.close	= shm_close,	/* callback for when the vm-area is released */
 	.fault	= shm_fault,
-	.split	= shm_split,
+	.may_split = shm_may_split,
 	.pagesize = shm_pagesize,
 #if defined(CONFIG_NUMA)
 	.set_policy = shm_set_policy,
@@ -619,18 +720,18 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 			ns->shm_tot + numpages > ns->shm_ctlall)
 		return -ENOSPC;
 
-	shp = kvmalloc(sizeof(*shp), GFP_KERNEL);
+	shp = kmalloc(sizeof(*shp), GFP_KERNEL_ACCOUNT);
 	if (unlikely(!shp))
 		return -ENOMEM;
 
 	shp->shm_perm.key = key;
 	shp->shm_perm.mode = (shmflg & S_IRWXUGO);
-	shp->mlock_user = NULL;
+	shp->mlock_ucounts = NULL;
 
 	shp->shm_perm.security = NULL;
 	error = security_shm_alloc(&shp->shm_perm);
 	if (error) {
-		kvfree(shp);
+		kfree(shp);
 		return error;
 	}
 
@@ -650,8 +751,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 		if (shmflg & SHM_NORESERVE)
 			acctflag = VM_NORESERVE;
 		file = hugetlb_file_setup(name, hugesize, acctflag,
-				  &shp->mlock_user, HUGETLB_SHMFS_INODE,
-				(shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
+				HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK);
 	} else {
 		/*
 		 * Do not allow no accounting for OVERCOMMIT_NEVER, even
@@ -680,7 +780,11 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	if (error < 0)
 		goto no_id;
 
+	shp->ns = ns;
+
+	task_lock(current);
 	list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
+	task_unlock(current);
 
 	/*
 	 * shmid gets reported as "inode#" in /proc/pid/maps.
@@ -698,8 +802,6 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 no_id:
 	ipc_update_pid(&shp->shm_cprid, NULL);
 	ipc_update_pid(&shp->shm_lprid, NULL);
-	if (is_file_hugepages(file) && shp->mlock_user)
-		user_shm_unlock(size, shp->mlock_user);
 	fput(file);
 	ipc_rcu_putref(&shp->shm_perm, shm_rcu_free);
 	return error;
@@ -1105,12 +1207,12 @@ static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd)
 		goto out_unlock0;
 
 	if (cmd == SHM_LOCK) {
-		struct user_struct *user = current_user();
+		struct ucounts *ucounts = current_ucounts();
 
-		err = shmem_lock(shm_file, 1, user);
+		err = shmem_lock(shm_file, 1, ucounts);
 		if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) {
 			shp->shm_perm.mode |= SHM_LOCKED;
-			shp->mlock_user = user;
+			shp->mlock_ucounts = ucounts;
 		}
 		goto out_unlock0;
 	}
@@ -1118,9 +1220,9 @@ static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd)
 	/* SHM_UNLOCK */
 	if (!(shp->shm_perm.mode & SHM_LOCKED))
 		goto out_unlock0;
-	shmem_lock(shm_file, 0, shp->mlock_user);
+	shmem_lock(shm_file, 0, shp->mlock_ucounts);
 	shp->shm_perm.mode &= ~SHM_LOCKED;
-	shp->mlock_user = NULL;
+	shp->mlock_ucounts = NULL;
 	get_file(shm_file);
 	ipc_unlock_object(&shp->shm_perm);
 	rcu_read_unlock();
@@ -1556,7 +1658,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 			goto invalid;
 	}
 
-	addr = do_mmap(file, addr, size, prot, flags, 0, &populate, NULL);
+	addr = do_mmap(file, addr, size, prot, flags, 0, 0, &populate, NULL);
 	*raddr = addr;
 	err = 0;
 	if (IS_ERR_VALUE(addr))
@@ -1573,7 +1675,8 @@ out_nattch:
 	down_write(&shm_ids(ns).rwsem);
 	shp = shm_lock(ns, shmid);
 	shp->shm_nattch--;
-	if (shm_may_destroy(ns, shp))
+
+	if (shm_may_destroy(shp))
 		shm_destroy(ns, shp);
 	else
 		shm_unlock(shp);
@@ -1630,7 +1733,7 @@ long ksys_shmdt(char __user *shmaddr)
 #ifdef CONFIG_MMU
 	loff_t size = 0;
 	struct file *file;
-	struct vm_area_struct *next;
+	VMA_ITERATOR(vmi, mm, addr);
 #endif
 
 	if (addr & ~PAGE_MASK)
@@ -1660,12 +1763,9 @@ long ksys_shmdt(char __user *shmaddr)
 	 * match the usual checks anyway. So assume all vma's are
 	 * above the starting address given.
 	 */
-	vma = find_vma(mm, addr);
 
 #ifdef CONFIG_MMU
-	while (vma) {
-		next = vma->vm_next;
-
+	for_each_vma(vmi, vma) {
 		/*
 		 * Check if the starting address would match, i.e. it's
 		 * a fragment created by mprotect() and/or munmap(), or it
@@ -1682,7 +1782,8 @@ long ksys_shmdt(char __user *shmaddr)
 			 */
 			file = vma->vm_file;
 			size = i_size_read(file_inode(vma->vm_file));
-			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL);
+			do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end,
+				      NULL, false);
 			/*
 			 * We discovered the size of the shm segment, so
 			 * break out of here and fall through to the next
@@ -1690,10 +1791,9 @@ long ksys_shmdt(char __user *shmaddr)
 			 * searching for matching vma's.
 			 */
 			retval = 0;
-			vma = next;
+			vma = vma_next(&vmi);
 			break;
 		}
-		vma = next;
 	}
 
 	/*
@@ -1703,17 +1803,19 @@ long ksys_shmdt(char __user *shmaddr)
 	 */
 	size = PAGE_ALIGN(size);
 	while (vma && (loff_t)(vma->vm_end - addr) <= size) {
-		next = vma->vm_next;
-
 		/* finding a matching vma now does not alter retval */
 		if ((vma->vm_ops == &shm_vm_ops) &&
 		    ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) &&
-		    (vma->vm_file == file))
-			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL);
-		vma = next;
+		    (vma->vm_file == file)) {
+			do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end,
+				      NULL, false);
+		}
+
+		vma = vma_next(&vmi);
 	}
 
 #else	/* CONFIG_MMU */
+	vma = vma_lookup(mm, addr);
 	/* under NOMMU conditions, the exact address to be destroyed must be
 	 * given
 	 */