Merge branch 'akpm' (Andrew's patch-bomb)

Merge the rest of Andrew's patches for -rc1:
 "A bunch of fixes and misc missed-out-on things.

  That'll do for -rc1.  I still have a batch of IPC patches which still
  have a possible bug report which I'm chasing down."

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (25 commits)
  keys: use keyring_alloc() to create module signing keyring
  keys: fix unreachable code
  sendfile: allows bypassing of notifier events
  SGI-XP: handle non-fatal traps
  fat: fix incorrect function comment
  Documentation: ABI: remove testing/sysfs-devices-node
  proc: fix inconsistent lock state
  linux/kernel.h: fix DIV_ROUND_CLOSEST with unsigned divisors
  memcg: don't register hotcpu notifier from ->css_alloc()
  checkpatch: warn on uapi #includes that #include <uapi/...
  revert "rtc: recycle id when unloading a rtc driver"
  mm: clean up transparent hugepage sysfs error messages
  hfsplus: add error message for the case of failure of sync fs in delayed_sync_fs() method
  hfsplus: rework processing of hfs_btree_write() returned error
  hfsplus: rework processing errors in hfsplus_free_extents()
  hfsplus: avoid crash on failed block map free
  kcmp: include linux/ptrace.h
  drivers/rtc/rtc-imxdi.c: must include <linux/spinlock.h>
  mm: cma: WARN if freed memory is still in use
  exec: do not leave bprm->interp on stack
  ...

Documentation/ABI/testing/sysfs-devices-node

-What:		/sys/devices/system/node/nodeX/compact
-Date:		February 2010
-Contact:	Mel Gorman <mel@csn.ul.ie>
-Description:
-		When this file is written to, all memory within that node
-		will be compacted. When it completes, memory will be freed
-		into blocks which have as many contiguous pages as possible

Documentation/kernel-parameters.txt

@@ -446,12 +446,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			possible to determine what the correct size should be.
 			This option provides an override for these situations.
 
-	capability.disable=
-			[SECURITY] Disable capabilities.  This would normally
-			be used only if an alternative security model is to be
-			configured.  Potentially dangerous and should only be
-			used if you are entirely sure of the consequences.
-
 	ccw_timeout_log [S390]
 			See Documentation/s390/CommonIO for details.
 

drivers/firmware/dmi_scan.c

@@ -16,6 +16,7 @@
  */
 static char dmi_empty_string[] = "        ";
 
+static u16 __initdata dmi_ver;
 /*
  * Catch too early calls to dmi_check_system():
  */
@@ -118,12 +119,12 @@ static int __init dmi_walk_early(void (*decode)(const struct dmi_header *,
 	return 0;
 }
 
-static int __init dmi_checksum(const u8 *buf)
+static int __init dmi_checksum(const u8 *buf, u8 len)
 {
 	u8 sum = 0;
 	int a;
 
-	for (a = 0; a < 15; a++)
+	for (a = 0; a < len; a++)
 		sum += buf[a];
 
 	return sum == 0;
@@ -161,8 +162,10 @@ static void __init dmi_save_uuid(const struct dmi_header *dm, int slot, int inde
 		return;
 
 	for (i = 0; i < 16 && (is_ff || is_00); i++) {
-		if(d[i] != 0x00) is_ff = 0;
-		if(d[i] != 0xFF) is_00 = 0;
+		if (d[i] != 0x00)
+			is_00 = 0;
+		if (d[i] != 0xFF)
+			is_ff = 0;
 	}
 
 	if (is_ff || is_00)
@@ -172,7 +175,15 @@ static void __init dmi_save_uuid(const struct dmi_header *dm, int slot, int inde
 	if (!s)
 		return;
 
-	sprintf(s, "%pUB", d);
+	/*
+	 * As of version 2.6 of the SMBIOS specification, the first 3 fields of
+	 * the UUID are supposed to be little-endian encoded.  The specification
+	 * says that this is the defacto standard.
+	 */
+	if (dmi_ver >= 0x0206)
+		sprintf(s, "%pUL", d);
+	else
+		sprintf(s, "%pUB", d);
 
         dmi_ident[slot] = s;
 }
@@ -404,29 +415,57 @@ static int __init dmi_present(const char __iomem *p)
 	u8 buf[15];
 
 	memcpy_fromio(buf, p, 15);
-	if ((memcmp(buf, "_DMI_", 5) == 0) && dmi_checksum(buf)) {
+	if (dmi_checksum(buf, 15)) {
 		dmi_num = (buf[13] << 8) | buf[12];
 		dmi_len = (buf[7] << 8) | buf[6];
 		dmi_base = (buf[11] << 24) | (buf[10] << 16) |
 			(buf[9] << 8) | buf[8];
 
-		/*
-		 * DMI version 0.0 means that the real version is taken from
-		 * the SMBIOS version, which we don't know at this point.
-		 */
-		if (buf[14] != 0)
-			printk(KERN_INFO "DMI %d.%d present.\n",
-			       buf[14] >> 4, buf[14] & 0xF);
-		else
-			printk(KERN_INFO "DMI present.\n");
 		if (dmi_walk_early(dmi_decode) == 0) {
+			if (dmi_ver)
+				pr_info("SMBIOS %d.%d present.\n",
+				       dmi_ver >> 8, dmi_ver & 0xFF);
+			else {
+				dmi_ver = (buf[14] & 0xF0) << 4 |
+					   (buf[14] & 0x0F);
+				pr_info("Legacy DMI %d.%d present.\n",
+				       dmi_ver >> 8, dmi_ver & 0xFF);
+			}
 			dmi_dump_ids();
 			return 0;
 		}
 	}
+	dmi_ver = 0;
 	return 1;
 }
 
+static int __init smbios_present(const char __iomem *p)
+{
+	u8 buf[32];
+	int offset = 0;
+
+	memcpy_fromio(buf, p, 32);
+	if ((buf[5] < 32) && dmi_checksum(buf, buf[5])) {
+		dmi_ver = (buf[6] << 8) + buf[7];
+
+		/* Some BIOS report weird SMBIOS version, fix that up */
+		switch (dmi_ver) {
+		case 0x021F:
+		case 0x0221:
+			pr_debug("SMBIOS version fixup(2.%d->2.%d)\n",
+			       dmi_ver & 0xFF, 3);
+			dmi_ver = 0x0203;
+			break;
+		case 0x0233:
+			pr_debug("SMBIOS version fixup(2.%d->2.%d)\n", 51, 6);
+			dmi_ver = 0x0206;
+			break;
+		}
+		offset = 16;
+	}
+	return dmi_present(buf + offset);
+}
+
 void __init dmi_scan_machine(void)
 {
 	char __iomem *p, *q;
@@ -444,7 +483,7 @@ void __init dmi_scan_machine(void)
 		if (p == NULL)
 			goto error;
 
-		rc = dmi_present(p + 0x10); /* offset of _DMI_ string */
+		rc = smbios_present(p);
 		dmi_iounmap(p, 32);
 		if (!rc) {
 			dmi_available = 1;
@@ -462,7 +501,12 @@ void __init dmi_scan_machine(void)
 			goto error;
 
 		for (q = p; q < p + 0x10000; q += 16) {
-			rc = dmi_present(q);
+			if (memcmp(q, "_SM_", 4) == 0 && q - p <= 0xFFE0)
+				rc = smbios_present(q);
+			else if (memcmp(q, "_DMI_", 5) == 0)
+				rc = dmi_present(q);
+			else
+				continue;
 			if (!rc) {
 				dmi_available = 1;
 				dmi_iounmap(p, 0x10000);

drivers/misc/sgi-xp/xpc_main.c

@@ -53,6 +53,10 @@
 #include <linux/kthread.h>
 #include "xpc.h"
 
+#ifdef CONFIG_X86_64
+#include <asm/traps.h>
+#endif
+
 /* define two XPC debug device structures to be used with dev_dbg() et al */
 
 struct device_driver xpc_dbg_name = {
@@ -1079,6 +1083,9 @@ xpc_system_reboot(struct notifier_block *nb, unsigned long event, void *unused)
 	return NOTIFY_DONE;
 }
 
+/* Used to only allow one cpu to complete disconnect */
+static unsigned int xpc_die_disconnecting;
+
 /*
  * Notify other partitions to deactivate from us by first disengaging from all
  * references to our memory.
@@ -1092,6 +1099,9 @@ xpc_die_deactivate(void)
 	long keep_waiting;
 	long wait_to_print;
 
+	if (cmpxchg(&xpc_die_disconnecting, 0, 1))
+		return;
+
 	/* keep xpc_hb_checker thread from doing anything (just in case) */
 	xpc_exiting = 1;
 
@@ -1159,7 +1169,7 @@ xpc_die_deactivate(void)
  * about the lack of a heartbeat.
  */
 static int
-xpc_system_die(struct notifier_block *nb, unsigned long event, void *unused)
+xpc_system_die(struct notifier_block *nb, unsigned long event, void *_die_args)
 {
 #ifdef CONFIG_IA64		/* !!! temporary kludge */
 	switch (event) {
@@ -1191,7 +1201,27 @@ xpc_system_die(struct notifier_block *nb, unsigned long event, void *unused)
 		break;
 	}
 #else
-	xpc_die_deactivate();
+	struct die_args *die_args = _die_args;
+
+	switch (event) {
+	case DIE_TRAP:
+		if (die_args->trapnr == X86_TRAP_DF)
+			xpc_die_deactivate();
+
+		if (((die_args->trapnr == X86_TRAP_MF) ||
+		     (die_args->trapnr == X86_TRAP_XF)) &&
+		    !user_mode_vm(die_args->regs))
+			xpc_die_deactivate();
+
+		break;
+	case DIE_INT3:
+	case DIE_DEBUG:
+		break;
+	case DIE_OOPS:
+	case DIE_GPF:
+	default:
+		xpc_die_deactivate();
+	}
 #endif
 
 	return NOTIFY_DONE;

drivers/rtc/class.c

@@ -244,7 +244,6 @@ void rtc_device_unregister(struct rtc_device *rtc)
 		rtc_proc_del_device(rtc);
 		device_unregister(&rtc->dev);
 		rtc->ops = NULL;
-		ida_simple_remove(&rtc_ida, rtc->id);
 		mutex_unlock(&rtc->ops_lock);
 		put_device(&rtc->dev);
 	}

drivers/rtc/rtc-imxdi.c

@@ -36,6 +36,7 @@
 #include <linux/platform_device.h>
 #include <linux/rtc.h>
 #include <linux/sched.h>
+#include <linux/spinlock.h>
 #include <linux/workqueue.h>
 #include <linux/of.h>
 

fs/binfmt_misc.c

@@ -172,7 +172,10 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		goto _error;
 	bprm->argc ++;
 
-	bprm->interp = iname;	/* for binfmt_script */
+	/* Update interp in case binfmt_script needs it. */
+	retval = bprm_change_interp(iname, bprm);
+	if (retval < 0)
+		goto _error;
 
 	interp_file = open_exec (iname);
 	retval = PTR_ERR (interp_file);

fs/binfmt_script.c

@@ -80,7 +80,9 @@ static int load_script(struct linux_binprm *bprm)
 	retval = copy_strings_kernel(1, &i_name, bprm);
 	if (retval) return retval; 
 	bprm->argc++;
-	bprm->interp = interp;
+	retval = bprm_change_interp(interp, bprm);
+	if (retval < 0)
+		return retval;
 
 	/*
 	 * OK, now restart the process with the interpreter's dentry.

fs/exec.c

@@ -1175,9 +1175,24 @@ void free_bprm(struct linux_binprm *bprm)
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
+	/* If a binfmt changed the interp, free it. */
+	if (bprm->interp != bprm->filename)
+		kfree(bprm->interp);
 	kfree(bprm);
 }
 
+int bprm_change_interp(char *interp, struct linux_binprm *bprm)
+{
+	/* If a binfmt changed the interp, free it first. */
+	if (bprm->interp != bprm->filename)
+		kfree(bprm->interp);
+	bprm->interp = kstrdup(interp, GFP_KERNEL);
+	if (!bprm->interp)
+		return -ENOMEM;
+	return 0;
+}
+EXPORT_SYMBOL(bprm_change_interp);
+
 /*
  * install the new credentials for this executable
  */

fs/fat/dir.c

@@ -461,8 +461,7 @@ static int fat_parse_short(struct super_block *sb,
 }
 
 /*
- * Return values: negative -> error, 0 -> not found, positive -> found,
- * value is the total amount of slots, including the shortname entry.
+ * Return values: negative -> error/not found, 0 -> found.
  */
 int fat_search_long(struct inode *inode, const unsigned char *name,
 		    int name_len, struct fat_slot_info *sinfo)
@@ -1255,7 +1254,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots,
 
 	sinfo->nr_slots = nr_slots;
 
-	/* First stage: search free direcotry entries */
+	/* First stage: search free directory entries */
 	free_slots = nr_bhs = 0;
 	bh = prev = NULL;
 	pos = 0;

fs/fat/inode.c

@@ -1344,7 +1344,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	sbi->dir_entries = get_unaligned_le16(&b->dir_entries);
 	if (sbi->dir_entries & (sbi->dir_per_block - 1)) {
 		if (!silent)
-			fat_msg(sb, KERN_ERR, "bogus directroy-entries per block"
+			fat_msg(sb, KERN_ERR, "bogus directory-entries per block"
 			       " (%u)", sbi->dir_entries);
 		brelse(bh);
 		goto out_invalid;

fs/fat/misc.c

@@ -135,6 +135,10 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster)
 		}
 		if (ret < 0)
 			return ret;
+		/*
+		 * FIXME:Although we can add this cache, fat_cache_add() is
+		 * assuming to be called after linear search with fat_cache_id.
+		 */
 //		fat_cache_add(inode, new_fclus, new_dclus);
 	} else {
 		MSDOS_I(inode)->i_start = new_dclus;

fs/hfsplus/bitmap.c

@@ -176,12 +176,14 @@ int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count)
 	dprint(DBG_BITMAP, "block_free: %u,%u\n", offset, count);
 	/* are all of the bits in range? */
 	if ((offset + count) > sbi->total_blocks)
-		return -2;
+		return -ENOENT;
 
 	mutex_lock(&sbi->alloc_mutex);
 	mapping = sbi->alloc_file->i_mapping;
 	pnr = offset / PAGE_CACHE_BITS;
 	page = read_mapping_page(mapping, pnr, NULL);
+	if (IS_ERR(page))
+		goto kaboom;
 	pptr = kmap(page);
 	curr = pptr + (offset & (PAGE_CACHE_BITS - 1)) / 32;
 	end = pptr + PAGE_CACHE_BITS / 32;
@@ -214,6 +216,8 @@ int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count)
 		set_page_dirty(page);
 		kunmap(page);
 		page = read_mapping_page(mapping, ++pnr, NULL);
+		if (IS_ERR(page))
+			goto kaboom;
 		pptr = kmap(page);
 		curr = pptr;
 		end = pptr + PAGE_CACHE_BITS / 32;
@@ -232,4 +236,11 @@ int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count)
 	mutex_unlock(&sbi->alloc_mutex);
 
 	return 0;
+
+kaboom:
+	printk(KERN_CRIT "hfsplus: unable to mark blocks free: error %ld\n",
+			PTR_ERR(page));
+	mutex_unlock(&sbi->alloc_mutex);
+
+	return -EIO;
 }

fs/hfsplus/btree.c

@@ -159,7 +159,7 @@ void hfs_btree_close(struct hfs_btree *tree)
 	kfree(tree);
 }
 
-void hfs_btree_write(struct hfs_btree *tree)
+int hfs_btree_write(struct hfs_btree *tree)
 {
 	struct hfs_btree_header_rec *head;
 	struct hfs_bnode *node;
@@ -168,7 +168,7 @@ void hfs_btree_write(struct hfs_btree *tree)
 	node = hfs_bnode_find(tree, 0);
 	if (IS_ERR(node))
 		/* panic? */
-		return;
+		return -EIO;
 	/* Load the header */
 	page = node->page[0];
 	head = (struct hfs_btree_header_rec *)(kmap(page) +
@@ -186,6 +186,7 @@ void hfs_btree_write(struct hfs_btree *tree)
 	kunmap(page);
 	set_page_dirty(page);
 	hfs_bnode_put(node);
+	return 0;
 }
 
 static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx)

fs/hfsplus/extents.c

@@ -329,6 +329,7 @@ static int hfsplus_free_extents(struct super_block *sb,
 {
 	u32 count, start;
 	int i;
+	int err = 0;
 
 	hfsplus_dump_extent(extent);
 	for (i = 0; i < 8; extent++, i++) {
@@ -345,18 +346,33 @@ static int hfsplus_free_extents(struct super_block *sb,
 	for (;;) {
 		start = be32_to_cpu(extent->start_block);
 		if (count <= block_nr) {
-			hfsplus_block_free(sb, start, count);
+			err = hfsplus_block_free(sb, start, count);
+			if (err) {
+				printk(KERN_ERR "hfs: can't free extent\n");
+				dprint(DBG_EXTENT, " start: %u count: %u\n",
+					start, count);
+			}
 			extent->block_count = 0;
 			extent->start_block = 0;
 			block_nr -= count;
 		} else {
 			count -= block_nr;
-			hfsplus_block_free(sb, start + count, block_nr);
+			err = hfsplus_block_free(sb, start + count, block_nr);
+			if (err) {
+				printk(KERN_ERR "hfs: can't free extent\n");
+				dprint(DBG_EXTENT, " start: %u count: %u\n",
+					start, count);
+			}
 			extent->block_count = cpu_to_be32(count);
 			block_nr = 0;
 		}
-		if (!block_nr || !i)
-			return 0;
+		if (!block_nr || !i) {
+			/*
+			 * Try to free all extents and
+			 * return only last error
+			 */
+			return err;
+		}
 		i--;
 		extent--;
 		count = be32_to_cpu(extent->block_count);

fs/hfsplus/hfsplus_fs.h

@@ -335,7 +335,7 @@ int hfsplus_block_free(struct super_block *, u32, u32);
 /* btree.c */
 struct hfs_btree *hfs_btree_open(struct super_block *, u32);
 void hfs_btree_close(struct hfs_btree *);
-void hfs_btree_write(struct hfs_btree *);
+int hfs_btree_write(struct hfs_btree *);
 struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *);
 void hfs_bmap_free(struct hfs_bnode *);
 

fs/hfsplus/super.c

@@ -127,8 +127,14 @@ static int hfsplus_system_write_inode(struct inode *inode)
 		hfsplus_mark_mdb_dirty(inode->i_sb);
 	}
 	hfsplus_inode_write_fork(inode, fork);
-	if (tree)
-		hfs_btree_write(tree);
+	if (tree) {
+		int err = hfs_btree_write(tree);
+		if (err) {
+			printk(KERN_ERR "hfs: b-tree write err: %d, ino %lu\n",
+					err, inode->i_ino);
+			return err;
+		}
+	}
 	return 0;
 }
 
@@ -226,6 +232,7 @@ static int hfsplus_sync_fs(struct super_block *sb, int wait)
 
 static void delayed_sync_fs(struct work_struct *work)
 {
+	int err;
 	struct hfsplus_sb_info *sbi;
 
 	sbi = container_of(work, struct hfsplus_sb_info, sync_work.work);
@@ -234,7 +241,9 @@ static void delayed_sync_fs(struct work_struct *work)
 	sbi->work_queued = 0;
 	spin_unlock(&sbi->work_lock);
 
-	hfsplus_sync_fs(sbi->alloc_file->i_sb, 1);
+	err = hfsplus_sync_fs(sbi->alloc_file->i_sb, 1);
+	if (err)
+		printk(KERN_ERR "hfs: delayed sync fs err %d\n", err);
 }
 
 void hfsplus_mark_mdb_dirty(struct super_block *sb)

fs/proc/generic.c

@@ -352,18 +352,18 @@ int proc_alloc_inum(unsigned int *inum)
 	if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL))
 		return -ENOMEM;
 
-	spin_lock(&proc_inum_lock);
+	spin_lock_bh(&proc_inum_lock);
 	error = ida_get_new(&proc_inum_ida, &i);
-	spin_unlock(&proc_inum_lock);
+	spin_unlock_bh(&proc_inum_lock);
 	if (error == -EAGAIN)
 		goto retry;
 	else if (error)
 		return error;
 
 	if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
-		spin_lock(&proc_inum_lock);
+		spin_lock_bh(&proc_inum_lock);
 		ida_remove(&proc_inum_ida, i);
-		spin_unlock(&proc_inum_lock);
+		spin_unlock_bh(&proc_inum_lock);
 		return -ENOSPC;
 	}
 	*inum = PROC_DYNAMIC_FIRST + i;
@@ -372,9 +372,9 @@ int proc_alloc_inum(unsigned int *inum)
 
 void proc_free_inum(unsigned int inum)
 {
-	spin_lock(&proc_inum_lock);
+	spin_lock_bh(&proc_inum_lock);
 	ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
-	spin_unlock(&proc_inum_lock);
+	spin_unlock_bh(&proc_inum_lock);
 }
 
 static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)

fs/read_write.c

@@ -935,6 +935,8 @@ ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count,
 	if (retval > 0) {
 		add_rchar(current, retval);
 		add_wchar(current, retval);
+		fsnotify_access(in.file);
+		fsnotify_modify(out.file);
 	}
 
 	inc_syscr(current);

include/linux/binfmts.h

@@ -112,6 +112,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm,
 			   unsigned long stack_top,
 			   int executable_stack);
 extern int bprm_mm_init(struct linux_binprm *bprm);
+extern int bprm_change_interp(char *interp, struct linux_binprm *bprm);
 extern int copy_strings_kernel(int argc, const char *const *argv,
 			       struct linux_binprm *bprm);
 extern int prepare_bprm_creds(struct linux_binprm *bprm);

include/linux/kernel.h

@@ -77,13 +77,15 @@
 
 /*
  * Divide positive or negative dividend by positive divisor and round
- * to closest integer. Result is undefined for negative divisors.
+ * to closest integer. Result is undefined for negative divisors and
+ * for negative dividends if the divisor variable type is unsigned.
  */
 #define DIV_ROUND_CLOSEST(x, divisor)(			\
 {							\
 	typeof(x) __x = x;				\
 	typeof(divisor) __d = divisor;			\
-	(((typeof(x))-1) > 0 || (__x) > 0) ?		\
+	(((typeof(x))-1) > 0 ||				\
+	 ((typeof(divisor))-1) > 0 || (__x) > 0) ?	\
 		(((__x) + ((__d) / 2)) / (__d)) :	\
 		(((__x) - ((__d) / 2)) / (__d));	\
 }							\

kernel/kcmp.c

@@ -4,6 +4,7 @@
 #include <linux/string.h>
 #include <linux/random.h>
 #include <linux/module.h>
+#include <linux/ptrace.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/cache.h>

kernel/modsign_pubkey.c

@@ -34,18 +34,15 @@ static __init int module_verify_init(void)
 {
 	pr_notice("Initialise module verification\n");
 
-	modsign_keyring = key_alloc(&key_type_keyring, ".module_sign",
-				    KUIDT_INIT(0), KGIDT_INIT(0),
-				    current_cred(),
-				    (KEY_POS_ALL & ~KEY_POS_SETATTR) |
-				    KEY_USR_VIEW | KEY_USR_READ,
-				    KEY_ALLOC_NOT_IN_QUOTA);
+	modsign_keyring = keyring_alloc(".module_sign",
+					KUIDT_INIT(0), KGIDT_INIT(0),
+					current_cred(),
+					((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+					 KEY_USR_VIEW | KEY_USR_READ),
+					KEY_ALLOC_NOT_IN_QUOTA, NULL);
 	if (IS_ERR(modsign_keyring))
 		panic("Can't allocate module signing keyring\n");
 
-	if (key_instantiate_and_link(modsign_keyring, NULL, 0, NULL, NULL) < 0)
-		panic("Can't instantiate module signing keyring\n");
-
 	return 0;
 }
 

mm/compaction.c

@@ -17,6 +17,21 @@
 #include <linux/balloon_compaction.h>
 #include "internal.h"
 
+#ifdef CONFIG_COMPACTION
+static inline void count_compact_event(enum vm_event_item item)
+{
+	count_vm_event(item);
+}
+
+static inline void count_compact_events(enum vm_event_item item, long delta)
+{
+	count_vm_events(item, delta);
+}
+#else
+#define count_compact_event(item) do { } while (0)
+#define count_compact_events(item, delta) do { } while (0)
+#endif
+
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
 #define CREATE_TRACE_POINTS
@@ -303,10 +318,9 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	if (blockpfn == end_pfn)
 		update_pageblock_skip(cc, valid_page, total_isolated, false);
 
-	count_vm_events(COMPACTFREE_SCANNED, nr_scanned);
+	count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
 	if (total_isolated)
-		count_vm_events(COMPACTISOLATED, total_isolated);
-
+		count_compact_events(COMPACTISOLATED, total_isolated);
 	return total_isolated;
 }
 
@@ -613,9 +627,9 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
-	count_vm_events(COMPACTMIGRATE_SCANNED, nr_scanned);
+	count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned);
 	if (nr_isolated)
-		count_vm_events(COMPACTISOLATED, nr_isolated);
+		count_compact_events(COMPACTISOLATED, nr_isolated);
 
 	return low_pfn;
 }
@@ -1110,7 +1124,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	if (!order || !may_enter_fs || !may_perform_io)
 		return rc;
 
-	count_vm_event(COMPACTSTALL);
+	count_compact_event(COMPACTSTALL);
 
 #ifdef CONFIG_CMA
 	if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)

mm/huge_memory.c

@@ -574,19 +574,19 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
 
 	*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
 	if (unlikely(!*hugepage_kobj)) {
-		printk(KERN_ERR "hugepage: failed kobject create\n");
+		printk(KERN_ERR "hugepage: failed to create transparent hugepage kobject\n");
 		return -ENOMEM;
 	}
 
 	err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group);
 	if (err) {
-		printk(KERN_ERR "hugepage: failed register hugeage group\n");
+		printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n");
 		goto delete_obj;
 	}
 
 	err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group);
 	if (err) {
-		printk(KERN_ERR "hugepage: failed register hugeage group\n");
+		printk(KERN_ERR "hugepage: failed to register transparent hugepage group\n");
 		goto remove_hp_group;
 	}
 

mm/memcontrol.c

@@ -6090,7 +6090,6 @@ mem_cgroup_css_alloc(struct cgroup *cont)
 						&per_cpu(memcg_stock, cpu);
 			INIT_WORK(&stock->work, drain_local_stock);
 		}
-		hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
 	} else {
 		parent = mem_cgroup_from_cont(cont->parent);
 		memcg->use_hierarchy = parent->use_hierarchy;
@@ -6756,6 +6755,19 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.use_id = 1,
 };
 
+/*
+ * The rest of init is performed during ->css_alloc() for root css which
+ * happens before initcalls.  hotcpu_notifier() can't be done together as
+ * it would introduce circular locking by adding cgroup_lock -> cpu hotplug
+ * dependency.  Do it from a subsys_initcall().
+ */
+static int __init mem_cgroup_init(void)
+{
+	hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
+	return 0;
+}
+subsys_initcall(mem_cgroup_init);
+
 #ifdef CONFIG_MEMCG_SWAP
 static int __init enable_swap_account(char *s)
 {

mm/page-writeback.c

@@ -200,6 +200,18 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 		x += zone_page_state(z, NR_FREE_PAGES) +
 		     zone_reclaimable_pages(z) - z->dirty_balance_reserve;
 	}
+	/*
+	 * Unreclaimable memory (kernel memory or anonymous memory
+	 * without swap) can bring down the dirtyable pages below
+	 * the zone's dirty balance reserve and the above calculation
+	 * will underflow.  However we still want to add in nodes
+	 * which are below threshold (negative values) to get a more
+	 * accurate calculation but make sure that the total never
+	 * underflows.
+	 */
+	if ((long)x < 0)
+		x = 0;
+
 	/*
 	 * Make sure that the number of highmem pages is never larger
 	 * than the number of the total dirtyable memory. This can only
@@ -222,8 +234,8 @@ static unsigned long global_dirtyable_memory(void)
 {
 	unsigned long x;
 
-	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages() -
-	    dirty_balance_reserve;
+	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
+	x -= min(x, dirty_balance_reserve);
 
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);
@@ -290,9 +302,12 @@ static unsigned long zone_dirtyable_memory(struct zone *zone)
 	 * highmem zone can hold its share of dirty pages, so we don't
 	 * care about vm_highmem_is_dirtyable here.
 	 */
-	return zone_page_state(zone, NR_FREE_PAGES) +
-	       zone_reclaimable_pages(zone) -
-	       zone->dirty_balance_reserve;
+	unsigned long nr_pages = zone_page_state(zone, NR_FREE_PAGES) +
+		zone_reclaimable_pages(zone);
+
+	/* don't allow this to underflow */
+	nr_pages -= min(nr_pages, zone->dirty_balance_reserve);
+	return nr_pages;
 }
 
 /**

mm/page_alloc.c

@@ -5978,8 +5978,15 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 
 void free_contig_range(unsigned long pfn, unsigned nr_pages)
 {
-	for (; nr_pages--; ++pfn)
-		__free_page(pfn_to_page(pfn));
+	unsigned int count = 0;
+
+	for (; nr_pages--; pfn++) {
+		struct page *page = pfn_to_page(pfn);
+
+		count += page_count(page) != 1;
+		__free_page(page);
+	}
+	WARN(count != 0, "%d pages are still in use!\n", count);
 }
 #endif
 

scripts/checkpatch.pl

@@ -2226,8 +2226,11 @@ sub process {
 			my $path = $1;
 			if ($path =~ m{//}) {
 				ERROR("MALFORMED_INCLUDE",
-				      "malformed #include filename\n" .
-					$herecurr);
+				      "malformed #include filename\n" . $herecurr);
+			}
+			if ($path =~ "^uapi/" && $realfile =~ m@\binclude/uapi/@) {
+				ERROR("UAPI_INCLUDE",
+				      "No #include in ...include/uapi/... should use a uapi/ path prefix\n" . $herecurr);
 			}
 		}
 

security/keys/process_keys.c

@@ -367,8 +367,6 @@ key_ref_t search_my_process_keyrings(struct key_type *type,
 
 		switch (PTR_ERR(key_ref)) {
 		case -EAGAIN: /* no key */
-			if (ret)
-				break;
 		case -ENOKEY: /* negative key */
 			ret = key_ref;
 			break;