Merge tag 'v3.10.64' into linux-linaro-lsk

This is the 3.10.64 stable release

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 10
-SUBLEVEL = 63
+SUBLEVEL = 64
 EXTRAVERSION =
 NAME = TOSSUG Baby Fish
 

arch/s390/kernel/compat_linux.c

@@ -248,7 +248,7 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
 	struct group_info *group_info;
 	int retval;
 
-	if (!capable(CAP_SETGID))
+	if (!may_setgroups())
 		return -EPERM;
 	if ((unsigned)gidsetsize > NGROUPS_MAX)
 		return -EINVAL;

arch/x86/include/uapi/asm/ldt.h

@@ -28,6 +28,13 @@ struct user_desc {
 	unsigned int  seg_not_present:1;
 	unsigned int  useable:1;
 #ifdef __x86_64__
+	/*
+	 * Because this bit is not present in 32-bit user code, user
+	 * programs can pass uninitialized values here.  Therefore, in
+	 * any context in which a user_desc comes from a 32-bit program,
+	 * the kernel must act as though lm == 0, regardless of the
+	 * actual value.
+	 */
 	unsigned int  lm:1;
 #endif
 };

arch/x86/kernel/kvm.c

@@ -279,7 +279,14 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 static void __init paravirt_ops_setup(void)
 {
 	pv_info.name = "KVM";
-	pv_info.paravirt_enabled = 1;
+
+	/*
+	 * KVM isn't paravirt in the sense of paravirt_enabled.  A KVM
+	 * guest kernel works like a bare metal kernel with additional
+	 * features, and paravirt_enabled is about features that are
+	 * missing.
+	 */
+	pv_info.paravirt_enabled = 0;
 
 	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
 		pv_cpu_ops.io_delay = kvm_io_delay;

arch/x86/kernel/kvmclock.c

@@ -265,7 +265,6 @@ void __init kvmclock_init(void)
 #endif
 	kvm_get_preset_lpj();
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
-	pv_info.paravirt_enabled = 1;
 	pv_info.name = "KVM";
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))

arch/x86/kernel/process_64.c

@@ -279,24 +279,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
-	/*
-	 * Reload esp0, LDT and the page table pointer:
-	 */
+	/* Reload esp0 and ss1. */
 	load_sp0(tss, next);
 
-	/*
-	 * Switch DS and ES.
-	 * This won't pick up thread selector changes, but I guess that is ok.
-	 */
-	savesegment(es, prev->es);
-	if (unlikely(next->es | prev->es))
-		loadsegment(es, next->es);
-
-	savesegment(ds, prev->ds);
-	if (unlikely(next->ds | prev->ds))
-		loadsegment(ds, next->ds);
-
-
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
 	 *
@@ -305,41 +290,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	savesegment(fs, fsindex);
 	savesegment(gs, gsindex);
 
+	/*
+	 * Load TLS before restoring any segments so that segment loads
+	 * reference the correct GDT entries.
+	 */
 	load_TLS(next, cpu);
 
 	/*
-	 * Leave lazy mode, flushing any hypercalls made here.
-	 * This must be done before restoring TLS segments so
-	 * the GDT and LDT are properly updated, and must be
-	 * done before math_state_restore, so the TS bit is up
-	 * to date.
+	 * Leave lazy mode, flushing any hypercalls made here.  This
+	 * must be done after loading TLS entries in the GDT but before
+	 * loading segments that might reference them, and and it must
+	 * be done before math_state_restore, so the TS bit is up to
+	 * date.
 	 */
 	arch_end_context_switch(next_p);
 
+	/* Switch DS and ES.
+	 *
+	 * Reading them only returns the selectors, but writing them (if
+	 * nonzero) loads the full descriptor from the GDT or LDT.  The
+	 * LDT for next is loaded in switch_mm, and the GDT is loaded
+	 * above.
+	 *
+	 * We therefore need to write new values to the segment
+	 * registers on every context switch unless both the new and old
+	 * values are zero.
+	 *
+	 * Note that we don't need to do anything for CS and SS, as
+	 * those are saved and restored as part of pt_regs.
+	 */
+	savesegment(es, prev->es);
+	if (unlikely(next->es | prev->es))
+		loadsegment(es, next->es);
+
+	savesegment(ds, prev->ds);
+	if (unlikely(next->ds | prev->ds))
+		loadsegment(ds, next->ds);
+
 	/*
 	 * Switch FS and GS.
 	 *
-	 * Segment register != 0 always requires a reload.  Also
-	 * reload when it has changed.  When prev process used 64bit
-	 * base always reload to avoid an information leak.
+	 * These are even more complicated than FS and GS: they have
+	 * 64-bit bases are that controlled by arch_prctl.  Those bases
+	 * only differ from the values in the GDT or LDT if the selector
+	 * is 0.
+	 *
+	 * Loading the segment register resets the hidden base part of
+	 * the register to 0 or the value from the GDT / LDT.  If the
+	 * next base address zero, writing 0 to the segment register is
+	 * much faster than using wrmsr to explicitly zero the base.
+	 *
+	 * The thread_struct.fs and thread_struct.gs values are 0
+	 * if the fs and gs bases respectively are not overridden
+	 * from the values implied by fsindex and gsindex.  They
+	 * are nonzero, and store the nonzero base addresses, if
+	 * the bases are overridden.
+	 *
+	 * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
+	 * be impossible.
+	 *
+	 * Therefore we need to reload the segment registers if either
+	 * the old or new selector is nonzero, and we need to override
+	 * the base address if next thread expects it to be overridden.
+	 *
+	 * This code is unnecessarily slow in the case where the old and
+	 * new indexes are zero and the new base is nonzero -- it will
+	 * unnecessarily write 0 to the selector before writing the new
+	 * base address.
+	 *
+	 * Note: This all depends on arch_prctl being the only way that
+	 * user code can override the segment base.  Once wrfsbase and
+	 * wrgsbase are enabled, most of this code will need to change.
 	 */
 	if (unlikely(fsindex | next->fsindex | prev->fs)) {
 		loadsegment(fs, next->fsindex);
+
 		/*
-		 * Check if the user used a selector != 0; if yes
-		 *  clear 64bit base, since overloaded base is always
-		 *  mapped to the Null selector
+		 * If user code wrote a nonzero value to FS, then it also
+		 * cleared the overridden base address.
+		 *
+		 * XXX: if user code wrote 0 to FS and cleared the base
+		 * address itself, we won't notice and we'll incorrectly
+		 * restore the prior base address next time we reschdule
+		 * the process.
 		 */
 		if (fsindex)
 			prev->fs = 0;
 	}
-	/* when next process has a 64bit base use it */
 	if (next->fs)
 		wrmsrl(MSR_FS_BASE, next->fs);
 	prev->fsindex = fsindex;
 
 	if (unlikely(gsindex | next->gsindex | prev->gs)) {
 		load_gs_index(next->gsindex);
+
+		/* This works (and fails) the same way as fsindex above. */
 		if (gsindex)
 			prev->gs = 0;
 	}

arch/x86/kernel/tls.c

@@ -27,6 +27,37 @@ static int get_free_idx(void)
 	return -ESRCH;
 }
 
+static bool tls_desc_okay(const struct user_desc *info)
+{
+	if (LDT_empty(info))
+		return true;
+
+	/*
+	 * espfix is required for 16-bit data segments, but espfix
+	 * only works for LDT segments.
+	 */
+	if (!info->seg_32bit)
+		return false;
+
+	/* Only allow data segments in the TLS array. */
+	if (info->contents > 1)
+		return false;
+
+	/*
+	 * Non-present segments with DPL 3 present an interesting attack
+	 * surface.  The kernel should handle such segments correctly,
+	 * but TLS is very difficult to protect in a sandbox, so prevent
+	 * such segments from being created.
+	 *
+	 * If userspace needs to remove a TLS entry, it can still delete
+	 * it outright.
+	 */
+	if (info->seg_not_present)
+		return false;
+
+	return true;
+}
+
 static void set_tls_desc(struct task_struct *p, int idx,
 			 const struct user_desc *info, int n)
 {
@@ -66,6 +97,9 @@ int do_set_thread_area(struct task_struct *p, int idx,
 	if (copy_from_user(&info, u_info, sizeof(info)))
 		return -EFAULT;
 
+	if (!tls_desc_okay(&info))
+		return -EINVAL;
+
 	if (idx == -1)
 		idx = info.entry_number;
 
@@ -192,6 +226,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 {
 	struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
 	const struct user_desc *info;
+	int i;
 
 	if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
 	    (pos % sizeof(struct user_desc)) != 0 ||
@@ -205,6 +240,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
 	else
 		info = infobuf;
 
+	for (i = 0; i < count / sizeof(struct user_desc); i++)
+		if (!tls_desc_okay(info + i))
+			return -EINVAL;
+
 	set_tls_desc(target,
 		     GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
 		     info, count / sizeof(struct user_desc));

crypto/af_alg.c

@@ -449,6 +449,9 @@ void af_alg_complete(struct crypto_async_request *req, int err)
 {
 	struct af_alg_completion *completion = req->data;
 
+	if (err == -EINPROGRESS)
+		return;
+
 	completion->err = err;
 	complete(&completion->completion);
 }

drivers/md/bitmap.c

@@ -883,7 +883,6 @@ void bitmap_unplug(struct bitmap *bitmap)
 {
 	unsigned long i;
 	int dirty, need_write;
-	int wait = 0;
 
 	if (!bitmap || !bitmap->storage.filemap ||
 	    test_bit(BITMAP_STALE, &bitmap->flags))
@@ -901,16 +900,13 @@ void bitmap_unplug(struct bitmap *bitmap)
 			clear_page_attr(bitmap, i, BITMAP_PAGE_PENDING);
 			write_page(bitmap, bitmap->storage.filemap[i], 0);
 		}
-		if (dirty)
-			wait = 1;
-	}
-	if (wait) { /* if any writes were performed, we need to wait on them */
-		if (bitmap->storage.file)
-			wait_event(bitmap->write_wait,
-				   atomic_read(&bitmap->pending_writes)==0);
-		else
-			md_super_wait(bitmap->mddev);
 	}
+	if (bitmap->storage.file)
+		wait_event(bitmap->write_wait,
+			   atomic_read(&bitmap->pending_writes)==0);
+	else
+		md_super_wait(bitmap->mddev);
+
 	if (test_bit(BITMAP_WRITE_ERROR, &bitmap->flags))
 		bitmap_file_kick(bitmap);
 }

drivers/md/dm-bufio.c

@@ -529,6 +529,19 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t block,
 		end_io(&b->bio, r);
 }
 
+static void inline_endio(struct bio *bio, int error)
+{
+	bio_end_io_t *end_fn = bio->bi_private;
+
+	/*
+	 * Reset the bio to free any attached resources
+	 * (e.g. bio integrity profiles).
+	 */
+	bio_reset(bio);
+
+	end_fn(bio, error);
+}
+
 static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 			   bio_end_io_t *end_io)
 {
@@ -540,7 +553,12 @@ static void use_inline_bio(struct dm_buffer *b, int rw, sector_t block,
 	b->bio.bi_max_vecs = DM_BUFIO_INLINE_VECS;
 	b->bio.bi_sector = block << b->c->sectors_per_block_bits;
 	b->bio.bi_bdev = b->c->bdev;
-	b->bio.bi_end_io = end_io;
+	b->bio.bi_end_io = inline_endio;
+	/*
+	 * Use of .bi_private isn't a problem here because
+	 * the dm_buffer's inline bio is local to bufio.
+	 */
+	b->bio.bi_private = end_io;
 
 	/*
 	 * We assume that if len >= PAGE_SIZE ptr is page-aligned.

drivers/md/persistent-data/dm-space-map-metadata.c

@@ -493,7 +493,9 @@ static int sm_bootstrap_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count
 {
 	struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
 
-	return smm->ll.nr_blocks;
+	*count = smm->ll.nr_blocks;
+
+	return 0;
 }
 
 static int sm_bootstrap_get_nr_free(struct dm_space_map *sm, dm_block_t *count)

drivers/mfd/tc6393xb.c

@@ -263,6 +263,17 @@ static int tc6393xb_ohci_disable(struct platform_device *dev)
 	return 0;
 }
 
+static int tc6393xb_ohci_suspend(struct platform_device *dev)
+{
+	struct tc6393xb_platform_data *tcpd = dev_get_platdata(dev->dev.parent);
+
+	/* We can't properly store/restore OHCI state, so fail here */
+	if (tcpd->resume_restore)
+		return -EBUSY;
+
+	return tc6393xb_ohci_disable(dev);
+}
+
 static int tc6393xb_fb_enable(struct platform_device *dev)
 {
 	struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
@@ -403,7 +414,7 @@ static struct mfd_cell tc6393xb_cells[] = {
 		.num_resources = ARRAY_SIZE(tc6393xb_ohci_resources),
 		.resources = tc6393xb_ohci_resources,
 		.enable = tc6393xb_ohci_enable,
-		.suspend = tc6393xb_ohci_disable,
+		.suspend = tc6393xb_ohci_suspend,
 		.resume = tc6393xb_ohci_enable,
 		.disable = tc6393xb_ohci_disable,
 	},

drivers/mmc/card/block.c

@@ -257,7 +257,7 @@ static ssize_t force_ro_show(struct device *dev, struct device_attribute *attr,
 	int ret;
 	struct mmc_blk_data *md = mmc_blk_get(dev_to_disk(dev));
 
-	ret = snprintf(buf, PAGE_SIZE, "%d",
+	ret = snprintf(buf, PAGE_SIZE, "%d\n",
 		       get_disk_ro(dev_to_disk(dev)) ^
 		       md->read_only);
 	mmc_blk_put(md);

drivers/scsi/megaraid/megaraid_sas_base.c

@@ -933,7 +933,7 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
 	abort_fr->abort_mfi_phys_addr_hi = 0;
 
 	cmd->sync_cmd = 1;
-	cmd->cmd_status = 0xFF;
+	cmd->cmd_status = ENODATA;
 
 	instance->instancet->issue_dcmd(instance, cmd);
 

fs/btrfs/disk-io.c

@@ -3857,12 +3857,6 @@ again:
 		if (ret)
 			break;
 
-		/* opt_discard */
-		if (btrfs_test_opt(root, DISCARD))
-			ret = btrfs_error_discard_extent(root, start,
-							 end + 1 - start,
-							 NULL);
-
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
 		btrfs_error_unpin_extent_range(root, start, end);
 		cond_resched();

fs/btrfs/extent-tree.c

@@ -5277,7 +5277,8 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 	update_global_block_rsv(fs_info);
 }
 
-static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end,
+			      const bool return_free_space)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_group_cache *cache = NULL;
@@ -5301,7 +5302,8 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 
 		if (start < cache->last_byte_to_unpin) {
 			len = min(len, cache->last_byte_to_unpin - start);
-			btrfs_add_free_space(cache, start, len);
+			if (return_free_space)
+				btrfs_add_free_space(cache, start, len);
 		}
 
 		start += len;
@@ -5364,7 +5366,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 						   end + 1 - start, NULL);
 
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
-		unpin_extent_range(root, start, end);
+		unpin_extent_range(root, start, end, true);
 		cond_resched();
 	}
 
@@ -8564,7 +8566,7 @@ out:
 
 int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 {
-	return unpin_extent_range(root, start, end);
+	return unpin_extent_range(root, start, end, false);
 }
 
 int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,

fs/btrfs/extent_map.c

@@ -263,8 +263,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
 	if (!em)
 		goto out;
 
-	if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags))
-		list_move(&em->list, &tree->modified_extents);
 	em->generation = gen;
 	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
 	em->mod_start = em->start;

fs/ecryptfs/crypto.c

@@ -2102,7 +2102,6 @@ ecryptfs_decode_from_filename(unsigned char *dst, size_t *dst_size,
 			break;
 		case 2:
 			dst[dst_byte_offset++] |= (src_byte);
-			dst[dst_byte_offset] = 0;
 			current_bit_offset = 0;
 			break;
 		}

fs/ecryptfs/file.c

@@ -196,23 +196,11 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
 {
 	int rc = 0;
 	struct ecryptfs_crypt_stat *crypt_stat = NULL;
-	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct dentry *ecryptfs_dentry = file->f_path.dentry;
 	/* Private value of ecryptfs_dentry allocated in
 	 * ecryptfs_lookup() */
 	struct ecryptfs_file_info *file_info;
 
-	mount_crypt_stat = &ecryptfs_superblock_to_private(
-		ecryptfs_dentry->d_sb)->mount_crypt_stat;
-	if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
-	    && ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR)
-		|| (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC)
-		|| (file->f_flags & O_APPEND))) {
-		printk(KERN_WARNING "Mount has encrypted view enabled; "
-		       "files may only be read\n");
-		rc = -EPERM;
-		goto out;
-	}
 	/* Released in ecryptfs_release or end of function if failure */
 	file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
 	ecryptfs_set_file_private(file, file_info);

fs/ecryptfs/main.c

@@ -494,6 +494,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 {
 	struct super_block *s;
 	struct ecryptfs_sb_info *sbi;
+	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	struct ecryptfs_dentry_info *root_info;
 	const char *err = "Getting sb failed";
 	struct inode *inode;
@@ -512,6 +513,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		err = "Error parsing options";
 		goto out;
 	}
+	mount_crypt_stat = &sbi->mount_crypt_stat;
 
 	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s)) {
@@ -558,11 +560,19 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 
 	/**
 	 * Set the POSIX ACL flag based on whether they're enabled in the lower
-	 * mount. Force a read-only eCryptfs mount if the lower mount is ro.
-	 * Allow a ro eCryptfs mount even when the lower mount is rw.
+	 * mount.
 	 */
 	s->s_flags = flags & ~MS_POSIXACL;
-	s->s_flags |= path.dentry->d_sb->s_flags & (MS_RDONLY | MS_POSIXACL);
+	s->s_flags |= path.dentry->d_sb->s_flags & MS_POSIXACL;
+
+	/**
+	 * Force a read-only eCryptfs mount when:
+	 *   1) The lower mount is ro
+	 *   2) The ecryptfs_encrypted_view mount option is specified
+	 */
+	if (path.dentry->d_sb->s_flags & MS_RDONLY ||
+	    mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
+		s->s_flags |= MS_RDONLY;
 
 	s->s_maxbytes = path.dentry->d_sb->s_maxbytes;
 	s->s_blocksize = path.dentry->d_sb->s_blocksize;