From 73500267c930baadadb0d02284909731baf151f7 Mon Sep 17 00:00:00 2001
From: Peter Jones <pjones@redhat.com>
Date: Mon, 8 Feb 2016 14:48:11 -0500
Subject: [PATCH 01/11] lib/ucs2_string: Add ucs2 -> utf8 helper functions

This adds ucs2_utf8size(), which tells us how big our ucs2 string is in
bytes, and ucs2_as_utf8, which translates from ucs2 to utf8..

Signed-off-by: Peter Jones <pjones@redhat.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
---
 include/linux/ucs2_string.h |  4 +++
 lib/ucs2_string.c           | 62 +++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+)

diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h
index cbb20afdbc01..bb679b48f408 100644
--- a/include/linux/ucs2_string.h
+++ b/include/linux/ucs2_string.h
@@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s);
 unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength);
 int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len);
 
+unsigned long ucs2_utf8size(const ucs2_char_t *src);
+unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src,
+			   unsigned long maxlength);
+
 #endif /* _LINUX_UCS2_STRING_H_ */
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index 6f500ef2301d..17dd74e21ef9 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -49,3 +49,65 @@ ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len)
         }
 }
 EXPORT_SYMBOL(ucs2_strncmp);
+
+unsigned long
+ucs2_utf8size(const ucs2_char_t *src)
+{
+	unsigned long i;
+	unsigned long j = 0;
+
+	for (i = 0; i < ucs2_strlen(src); i++) {
+		u16 c = src[i];
+
+		if (c > 0x800)
+			j += 3;
+		else if (c > 0x80)
+			j += 2;
+		else
+			j += 1;
+	}
+
+	return j;
+}
+EXPORT_SYMBOL(ucs2_utf8size);
+
+/*
+ * copy at most maxlength bytes of whole utf8 characters to dest from the
+ * ucs2 string src.
+ *
+ * The return value is the number of characters copied, not including the
+ * final NUL character.
+ */
+unsigned long
+ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
+{
+	unsigned int i;
+	unsigned long j = 0;
+	unsigned long limit = ucs2_strnlen(src, maxlength);
+
+	for (i = 0; maxlength && i < limit; i++) {
+		u16 c = src[i];
+
+		if (c > 0x800) {
+			if (maxlength < 3)
+				break;
+			maxlength -= 3;
+			dest[j++] = 0xe0 | (c & 0xf000) >> 12;
+			dest[j++] = 0x80 | (c & 0x0fc0) >> 8;
+			dest[j++] = 0x80 | (c & 0x003f);
+		} else if (c > 0x80) {
+			if (maxlength < 2)
+				break;
+			maxlength -= 2;
+			dest[j++] = 0xc0 | (c & 0xfe0) >> 5;
+			dest[j++] = 0x80 | (c & 0x01f);
+		} else {
+			maxlength -= 1;
+			dest[j++] = c & 0x7f;
+		}
+	}
+	if (maxlength)
+		dest[j] = '\0';
+	return j;
+}
+EXPORT_SYMBOL(ucs2_as_utf8);

From e0d64e6a880e64545ad7d55786aa84ab76bac475 Mon Sep 17 00:00:00 2001
From: Peter Jones <pjones@redhat.com>
Date: Mon, 8 Feb 2016 14:48:12 -0500
Subject: [PATCH 02/11] efi: Use ucs2_as_utf8 in efivarfs instead of open
 coding a bad version

Translate EFI's UCS-2 variable names to UTF-8 instead of just assuming
all variable names fit in ASCII.

Signed-off-by: Peter Jones <pjones@redhat.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
---
 drivers/firmware/efi/efivars.c | 30 +++++++++++-------------------
 fs/efivarfs/super.c            |  7 +++----
 2 files changed, 14 insertions(+), 23 deletions(-)

diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 756eca8c4cf8..f4ff8abc5f3e 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -540,38 +540,30 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj,
 static int
 efivar_create_sysfs_entry(struct efivar_entry *new_var)
 {
-	int i, short_name_size;
+	int short_name_size;
 	char *short_name;
-	unsigned long variable_name_size;
-	efi_char16_t *variable_name;
+	unsigned long utf8_name_size;
+	efi_char16_t *variable_name = new_var->var.VariableName;
 	int ret;
 
-	variable_name = new_var->var.VariableName;
-	variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t);
-
 	/*
-	 * Length of the variable bytes in ASCII, plus the '-' separator,
+	 * Length of the variable bytes in UTF8, plus the '-' separator,
 	 * plus the GUID, plus trailing NUL
 	 */
-	short_name_size = variable_name_size / sizeof(efi_char16_t)
-				+ 1 + EFI_VARIABLE_GUID_LEN + 1;
-
-	short_name = kzalloc(short_name_size, GFP_KERNEL);
+	utf8_name_size = ucs2_utf8size(variable_name);
+	short_name_size = utf8_name_size + 1 + EFI_VARIABLE_GUID_LEN + 1;
 
+	short_name = kmalloc(short_name_size, GFP_KERNEL);
 	if (!short_name)
 		return -ENOMEM;
 
-	/* Convert Unicode to normal chars (assume top bits are 0),
-	   ala UTF-8 */
-	for (i=0; i < (int)(variable_name_size / sizeof(efi_char16_t)); i++) {
-		short_name[i] = variable_name[i] & 0xFF;
-	}
+	ucs2_as_utf8(short_name, variable_name, short_name_size);
+
 	/* This is ugly, but necessary to separate one vendor's
 	   private variables from another's.         */
-
-	*(short_name + strlen(short_name)) = '-';
+	short_name[utf8_name_size] = '-';
 	efi_guid_to_str(&new_var->var.VendorGuid,
-			 short_name + strlen(short_name));
+			 short_name + utf8_name_size + 1);
 
 	new_var->kobj.kset = efivars_kset;
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index b8a564f29107..8651ac28ec0d 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -118,7 +118,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	struct dentry *dentry, *root = sb->s_root;
 	unsigned long size = 0;
 	char *name;
-	int len, i;
+	int len;
 	int err = -ENOMEM;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
@@ -128,15 +128,14 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	memcpy(entry->var.VariableName, name16, name_size);
 	memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
 
-	len = ucs2_strlen(entry->var.VariableName);
+	len = ucs2_utf8size(entry->var.VariableName);
 
 	/* name, plus '-', plus GUID, plus NUL*/
 	name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL);
 	if (!name)
 		goto fail;
 
-	for (i = 0; i < len; i++)
-		name[i] = entry->var.VariableName[i] & 0xFF;
+	ucs2_as_utf8(name, entry->var.VariableName, len);
 
 	name[len] = '-';
 

From 3dcb1f55dfc7631695e69df4a0d589ce5274bd07 Mon Sep 17 00:00:00 2001
From: Peter Jones <pjones@redhat.com>
Date: Mon, 8 Feb 2016 14:48:13 -0500
Subject: [PATCH 03/11] efi: Do variable name validation tests in utf8

Actually translate from ucs2 to utf8 before doing the test, and then
test against our other utf8 data, instead of fudging it.

Signed-off-by: Peter Jones <pjones@redhat.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
---
 drivers/firmware/efi/vars.c | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 70a0fb10517f..5c5fde3e6c37 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -189,10 +189,19 @@ static const struct variable_validate variable_validate[] = {
 };
 
 bool
-efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len)
+efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size)
 {
 	int i;
-	u16 *unicode_name = var_name;
+	unsigned long utf8_size;
+	u8 *utf8_name;
+
+	utf8_size = ucs2_utf8size(var_name);
+	utf8_name = kmalloc(utf8_size + 1, GFP_KERNEL);
+	if (!utf8_name)
+		return false;
+
+	ucs2_as_utf8(utf8_name, var_name, utf8_size);
+	utf8_name[utf8_size] = '\0';
 
 	for (i = 0; variable_validate[i].validate != NULL; i++) {
 		const char *name = variable_validate[i].name;
@@ -200,28 +209,29 @@ efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len)
 
 		for (match = 0; ; match++) {
 			char c = name[match];
-			u16 u = unicode_name[match];
-
-			/* All special variables are plain ascii */
-			if (u > 127)
-				return true;
+			char u = utf8_name[match];
 
 			/* Wildcard in the matching name means we've matched */
-			if (c == '*')
+			if (c == '*') {
+				kfree(utf8_name);
 				return variable_validate[i].validate(var_name,
-							     match, data, len);
+							match, data, data_size);
+			}
 
 			/* Case sensitive match */
 			if (c != u)
 				break;
 
 			/* Reached the end of the string while matching */
-			if (!c)
+			if (!c) {
+				kfree(utf8_name);
 				return variable_validate[i].validate(var_name,
-							     match, data, len);
+							match, data, data_size);
+			}
 		}
 	}
 
+	kfree(utf8_name);
 	return true;
 }
 EXPORT_SYMBOL_GPL(efivar_validate);

From 8282f5d9c17fe15a9e658c06e3f343efae1a2a2f Mon Sep 17 00:00:00 2001
From: Peter Jones <pjones@redhat.com>
Date: Mon, 8 Feb 2016 14:48:14 -0500
Subject: [PATCH 04/11] efi: Make our variable validation list include the guid

All the variables in this list so far are defined to be in the global
namespace in the UEFI spec, so this just further ensures we're
validating the variables we think we are.

Including the guid for entries will become more important in future
patches when we decide whether or not to allow deletion of variables
based on presence in this list.

Signed-off-by: Peter Jones <pjones@redhat.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
---
 drivers/firmware/efi/efivars.c |  5 ++--
 drivers/firmware/efi/vars.c    | 52 +++++++++++++++++++++-------------
 include/linux/efi.h            |  3 +-
 3 files changed, 38 insertions(+), 22 deletions(-)

diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index f4ff8abc5f3e..10e6774ab2a2 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -221,7 +221,7 @@ sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor,
 	}
 
 	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(name, data, size) == false) {
+	    efivar_validate(vendor, name, data, size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
@@ -447,7 +447,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj,
 	}
 
 	if ((attributes & ~EFI_VARIABLE_MASK) != 0 ||
-	    efivar_validate(name, data, size) == false) {
+	    efivar_validate(new_var->VendorGuid, name, data,
+			    size) == false) {
 		printk(KERN_ERR "efivars: Malformed variable content\n");
 		return -EINVAL;
 	}
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 5c5fde3e6c37..9a53da21e7b6 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -165,31 +165,42 @@ validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer,
 }
 
 struct variable_validate {
+	efi_guid_t vendor;
 	char *name;
 	bool (*validate)(efi_char16_t *var_name, int match, u8 *data,
 			 unsigned long len);
 };
 
+/*
+ * This is the list of variables we need to validate.
+ *
+ * If it has a validate() method that's not NULL, it'll go into the
+ * validation routine.  If not, it is assumed valid.
+ *
+ * Note that it's sorted by {vendor,name}, but globbed names must come after
+ * any other name with the same prefix.
+ */
 static const struct variable_validate variable_validate[] = {
-	{ "BootNext", validate_uint16 },
-	{ "BootOrder", validate_boot_order },
-	{ "DriverOrder", validate_boot_order },
-	{ "Boot*", validate_load_option },
-	{ "Driver*", validate_load_option },
-	{ "ConIn", validate_device_path },
-	{ "ConInDev", validate_device_path },
-	{ "ConOut", validate_device_path },
-	{ "ConOutDev", validate_device_path },
-	{ "ErrOut", validate_device_path },
-	{ "ErrOutDev", validate_device_path },
-	{ "Timeout", validate_uint16 },
-	{ "Lang", validate_ascii_string },
-	{ "PlatformLang", validate_ascii_string },
-	{ "", NULL },
+	{ EFI_GLOBAL_VARIABLE_GUID, "BootNext", validate_uint16 },
+	{ EFI_GLOBAL_VARIABLE_GUID, "BootOrder", validate_boot_order },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Boot*", validate_load_option },
+	{ EFI_GLOBAL_VARIABLE_GUID, "DriverOrder", validate_boot_order },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Driver*", validate_load_option },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConIn", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConInDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConOut", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ConOutDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 },
+	{ NULL_GUID, "", NULL },
 };
 
 bool
-efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size)
+efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+		unsigned long data_size)
 {
 	int i;
 	unsigned long utf8_size;
@@ -203,9 +214,12 @@ efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size)
 	ucs2_as_utf8(utf8_name, var_name, utf8_size);
 	utf8_name[utf8_size] = '\0';
 
-	for (i = 0; variable_validate[i].validate != NULL; i++) {
+	for (i = 0; variable_validate[i].name[0] != '\0'; i++) {
 		const char *name = variable_validate[i].name;
-		int match;
+		int match = 0;
+
+		if (efi_guidcmp(vendor, variable_validate[i].vendor))
+			continue;
 
 		for (match = 0; ; match++) {
 			char c = name[match];
@@ -862,7 +876,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes,
 
 	*set = false;
 
-	if (efivar_validate(name, data, *size) == false)
+	if (efivar_validate(*vendor, name, data, *size) == false)
 		return -EINVAL;
 
 	/*
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 569b5a866bb1..16ca611aabc8 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1199,7 +1199,8 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *),
 struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 				       struct list_head *head, bool remove);
 
-bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len);
+bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+		     unsigned long data_size);
 
 extern struct work_struct efivar_work;
 void efivar_run_worker(void);

From ed8b0de5a33d2a2557dce7f9429dca8cb5bc5879 Mon Sep 17 00:00:00 2001
From: Peter Jones <pjones@redhat.com>
Date: Mon, 8 Feb 2016 14:48:15 -0500
Subject: [PATCH 05/11] efi: Make efivarfs entries immutable by default

"rm -rf" is bricking some peoples' laptops because of variables being
used to store non-reinitializable firmware driver data that's required
to POST the hardware.

These are 100% bugs, and they need to be fixed, but in the mean time it
shouldn't be easy to *accidentally* brick machines.

We have to have delete working, and picking which variables do and don't
work for deletion is quite intractable, so instead make everything
immutable by default (except for a whitelist), and make tools that
aren't quite so broad-spectrum unset the immutable flag.

Signed-off-by: Peter Jones <pjones@redhat.com>
Tested-by: Lee, Chun-Yi <jlee@suse.com>
Acked-by: Matthew Garrett <mjg59@coreos.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
---
 Documentation/filesystems/efivarfs.txt        |  7 ++
 drivers/firmware/efi/vars.c                   | 87 ++++++++++++++-----
 fs/efivarfs/file.c                            | 70 +++++++++++++++
 fs/efivarfs/inode.c                           | 30 ++++---
 fs/efivarfs/internal.h                        |  3 +-
 fs/efivarfs/super.c                           |  9 +-
 include/linux/efi.h                           |  2 +
 tools/testing/selftests/efivarfs/efivarfs.sh  | 19 +++-
 .../testing/selftests/efivarfs/open-unlink.c  | 72 ++++++++++++++-
 9 files changed, 258 insertions(+), 41 deletions(-)

diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt
index c477af086e65..686a64bba775 100644
--- a/Documentation/filesystems/efivarfs.txt
+++ b/Documentation/filesystems/efivarfs.txt
@@ -14,3 +14,10 @@ filesystem.
 efivarfs is typically mounted like this,
 
 	mount -t efivarfs none /sys/firmware/efi/efivars
+
+Due to the presence of numerous firmware bugs where removing non-standard
+UEFI variables causes the system firmware to fail to POST, efivarfs
+files that are not well-known standardized variables are created
+as immutable files.  This doesn't prevent removal - "chattr -i" will work -
+but it does prevent this kind of failure from being accomplished
+accidentally.
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 9a53da21e7b6..50f10bad2604 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -172,10 +172,12 @@ struct variable_validate {
 };
 
 /*
- * This is the list of variables we need to validate.
+ * This is the list of variables we need to validate, as well as the
+ * whitelist for what we think is safe not to default to immutable.
  *
  * If it has a validate() method that's not NULL, it'll go into the
- * validation routine.  If not, it is assumed valid.
+ * validation routine.  If not, it is assumed valid, but still used for
+ * whitelisting.
  *
  * Note that it's sorted by {vendor,name}, but globbed names must come after
  * any other name with the same prefix.
@@ -193,11 +195,37 @@ static const struct variable_validate variable_validate[] = {
 	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path },
 	{ EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path },
 	{ EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string },
+	{ EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL },
 	{ EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string },
 	{ EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 },
 	{ NULL_GUID, "", NULL },
 };
 
+static bool
+variable_matches(const char *var_name, size_t len, const char *match_name,
+		 int *match)
+{
+	for (*match = 0; ; (*match)++) {
+		char c = match_name[*match];
+		char u = var_name[*match];
+
+		/* Wildcard in the matching name means we've matched */
+		if (c == '*')
+			return true;
+
+		/* Case sensitive match */
+		if (!c && *match == len)
+			return true;
+
+		if (c != u)
+			return false;
+
+		if (!c)
+			return true;
+	}
+	return true;
+}
+
 bool
 efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 		unsigned long data_size)
@@ -221,35 +249,48 @@ efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 		if (efi_guidcmp(vendor, variable_validate[i].vendor))
 			continue;
 
-		for (match = 0; ; match++) {
-			char c = name[match];
-			char u = utf8_name[match];
-
-			/* Wildcard in the matching name means we've matched */
-			if (c == '*') {
-				kfree(utf8_name);
-				return variable_validate[i].validate(var_name,
-							match, data, data_size);
-			}
-
-			/* Case sensitive match */
-			if (c != u)
+		if (variable_matches(utf8_name, utf8_size+1, name, &match)) {
+			if (variable_validate[i].validate == NULL)
 				break;
-
-			/* Reached the end of the string while matching */
-			if (!c) {
-				kfree(utf8_name);
-				return variable_validate[i].validate(var_name,
-							match, data, data_size);
-			}
+			kfree(utf8_name);
+			return variable_validate[i].validate(var_name, match,
+							     data, data_size);
 		}
 	}
-
 	kfree(utf8_name);
 	return true;
 }
 EXPORT_SYMBOL_GPL(efivar_validate);
 
+bool
+efivar_variable_is_removable(efi_guid_t vendor, const char *var_name,
+			     size_t len)
+{
+	int i;
+	bool found = false;
+	int match = 0;
+
+	/*
+	 * Check if our variable is in the validated variables list
+	 */
+	for (i = 0; variable_validate[i].name[0] != '\0'; i++) {
+		if (efi_guidcmp(variable_validate[i].vendor, vendor))
+			continue;
+
+		if (variable_matches(var_name, len,
+				     variable_validate[i].name, &match)) {
+			found = true;
+			break;
+		}
+	}
+
+	/*
+	 * If it's in our list, it is removable.
+	 */
+	return found;
+}
+EXPORT_SYMBOL_GPL(efivar_variable_is_removable);
+
 static efi_status_t
 check_var_size(u32 attributes, unsigned long size)
 {
diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index c424e4813ec8..d48e0d261d78 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -10,6 +10,7 @@
 #include <linux/efi.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/mount.h>
 
 #include "internal.h"
 
@@ -103,9 +104,78 @@ out_free:
 	return size;
 }
 
+static int
+efivarfs_ioc_getxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int i_flags;
+	unsigned int flags = 0;
+
+	i_flags = inode->i_flags;
+	if (i_flags & S_IMMUTABLE)
+		flags |= FS_IMMUTABLE_FL;
+
+	if (copy_to_user(arg, &flags, sizeof(flags)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+efivarfs_ioc_setxflags(struct file *file, void __user *arg)
+{
+	struct inode *inode = file->f_mapping->host;
+	unsigned int flags;
+	unsigned int i_flags = 0;
+	int error;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (copy_from_user(&flags, arg, sizeof(flags)))
+		return -EFAULT;
+
+	if (flags & ~FS_IMMUTABLE_FL)
+		return -EOPNOTSUPP;
+
+	if (!capable(CAP_LINUX_IMMUTABLE))
+		return -EPERM;
+
+	if (flags & FS_IMMUTABLE_FL)
+		i_flags |= S_IMMUTABLE;
+
+
+	error = mnt_want_write_file(file);
+	if (error)
+		return error;
+
+	inode_lock(inode);
+	inode_set_flags(inode, i_flags, S_IMMUTABLE);
+	inode_unlock(inode);
+
+	mnt_drop_write_file(file);
+
+	return 0;
+}
+
+long
+efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p)
+{
+	void __user *arg = (void __user *)p;
+
+	switch (cmd) {
+	case FS_IOC_GETFLAGS:
+		return efivarfs_ioc_getxflags(file, arg);
+	case FS_IOC_SETFLAGS:
+		return efivarfs_ioc_setxflags(file, arg);
+	}
+
+	return -ENOTTY;
+}
+
 const struct file_operations efivarfs_file_operations = {
 	.open	= simple_open,
 	.read	= efivarfs_file_read,
 	.write	= efivarfs_file_write,
 	.llseek	= no_llseek,
+	.unlocked_ioctl = efivarfs_file_ioctl,
 };
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 3381b9da9ee6..e2ab6d0497f2 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -15,7 +15,8 @@
 #include "internal.h"
 
 struct inode *efivarfs_get_inode(struct super_block *sb,
-				const struct inode *dir, int mode, dev_t dev)
+				const struct inode *dir, int mode,
+				dev_t dev, bool is_removable)
 {
 	struct inode *inode = new_inode(sb);
 
@@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
 		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+		inode->i_flags = is_removable ? 0 : S_IMMUTABLE;
 		switch (mode & S_IFMT) {
 		case S_IFREG:
 			inode->i_fop = &efivarfs_file_operations;
@@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid)
 static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 			  umode_t mode, bool excl)
 {
-	struct inode *inode;
+	struct inode *inode = NULL;
 	struct efivar_entry *var;
 	int namelen, i = 0, err = 0;
+	bool is_removable = false;
 
 	if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len))
 		return -EINVAL;
 
-	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0);
-	if (!inode)
-		return -ENOMEM;
-
 	var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL);
-	if (!var) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!var)
+		return -ENOMEM;
 
 	/* length of the variable name itself: remove GUID and separator */
 	namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
@@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 	efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1,
 			&var->var.VendorGuid);
 
+	if (efivar_variable_is_removable(var->var.VendorGuid,
+					 dentry->d_name.name, namelen))
+		is_removable = true;
+
+	inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable);
+	if (!inode) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	for (i = 0; i < namelen; i++)
 		var->var.VariableName[i] = dentry->d_name.name[i];
 
@@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 out:
 	if (err) {
 		kfree(var);
-		iput(inode);
+		if (inode)
+			iput(inode);
 	}
 	return err;
 }
diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
index b5ff16addb7c..b4505188e799 100644
--- a/fs/efivarfs/internal.h
+++ b/fs/efivarfs/internal.h
@@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations;
 extern const struct inode_operations efivarfs_dir_inode_operations;
 extern bool efivarfs_valid_name(const char *str, int len);
 extern struct inode *efivarfs_get_inode(struct super_block *sb,
-			const struct inode *dir, int mode, dev_t dev);
+			const struct inode *dir, int mode, dev_t dev,
+			bool is_removable);
 
 extern struct list_head efivarfs_list;
 
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 8651ac28ec0d..dd029d13ea61 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -120,6 +120,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 	char *name;
 	int len;
 	int err = -ENOMEM;
+	bool is_removable = false;
 
 	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
@@ -137,13 +138,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor,
 
 	ucs2_as_utf8(name, entry->var.VariableName, len);
 
+	if (efivar_variable_is_removable(entry->var.VendorGuid, name, len))
+		is_removable = true;
+
 	name[len] = '-';
 
 	efi_guid_to_str(&entry->var.VendorGuid, name + len + 1);
 
 	name[len + EFI_VARIABLE_GUID_LEN+1] = '\0';
 
-	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0);
+	inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0,
+				   is_removable);
 	if (!inode)
 		goto fail_name;
 
@@ -199,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_d_op		= &efivarfs_d_ops;
 	sb->s_time_gran         = 1;
 
-	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0);
+	inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true);
 	if (!inode)
 		return -ENOMEM;
 	inode->i_op = &efivarfs_dir_inode_operations;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 16ca611aabc8..47be3ad7d3e5 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1201,6 +1201,8 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid,
 
 bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
 		     unsigned long data_size);
+bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
+				  size_t len);
 
 extern struct work_struct efivar_work;
 void efivar_run_worker(void);
diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh
index 77edcdcc016b..057278448515 100755
--- a/tools/testing/selftests/efivarfs/efivarfs.sh
+++ b/tools/testing/selftests/efivarfs/efivarfs.sh
@@ -88,7 +88,11 @@ test_delete()
 		exit 1
 	fi
 
-	rm $file
+	rm $file 2>/dev/null
+	if [ $? -ne 0 ]; then
+		chattr -i $file
+		rm $file
+	fi
 
 	if [ -e $file ]; then
 		echo "$file couldn't be deleted" >&2
@@ -111,6 +115,7 @@ test_zero_size_delete()
 		exit 1
 	fi
 
+	chattr -i $file
 	printf "$attrs" > $file
 
 	if [ -e $file ]; then
@@ -141,7 +146,11 @@ test_valid_filenames()
 			echo "$file could not be created" >&2
 			ret=1
 		else
-			rm $file
+			rm $file 2>/dev/null
+			if [ $? -ne 0 ]; then
+				chattr -i $file
+				rm $file
+			fi
 		fi
 	done
 
@@ -174,7 +183,11 @@ test_invalid_filenames()
 
 		if [ -e $file ]; then
 			echo "Creating $file should have failed" >&2
-			rm $file
+			rm $file 2>/dev/null
+			if [ $? -ne 0 ]; then
+				chattr -i $file
+				rm $file
+			fi
 			ret=1
 		fi
 	done
diff --git a/tools/testing/selftests/efivarfs/open-unlink.c b/tools/testing/selftests/efivarfs/open-unlink.c
index 8c0764407b3c..4af74f733036 100644
--- a/tools/testing/selftests/efivarfs/open-unlink.c
+++ b/tools/testing/selftests/efivarfs/open-unlink.c
@@ -1,10 +1,68 @@
+#include <errno.h>
 #include <stdio.h>
 #include <stdint.h>
 #include <stdlib.h>
 #include <unistd.h>
+#include <sys/ioctl.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
+#include <linux/fs.h>
+
+static int set_immutable(const char *path, int immutable)
+{
+	unsigned int flags;
+	int fd;
+	int rc;
+	int error;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	rc = ioctl(fd, FS_IOC_GETFLAGS, &flags);
+	if (rc < 0) {
+		error = errno;
+		close(fd);
+		errno = error;
+		return rc;
+	}
+
+	if (immutable)
+		flags |= FS_IMMUTABLE_FL;
+	else
+		flags &= ~FS_IMMUTABLE_FL;
+
+	rc = ioctl(fd, FS_IOC_SETFLAGS, &flags);
+	error = errno;
+	close(fd);
+	errno = error;
+	return rc;
+}
+
+static int get_immutable(const char *path)
+{
+	unsigned int flags;
+	int fd;
+	int rc;
+	int error;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	rc = ioctl(fd, FS_IOC_GETFLAGS, &flags);
+	if (rc < 0) {
+		error = errno;
+		close(fd);
+		errno = error;
+		return rc;
+	}
+	close(fd);
+	if (flags & FS_IMMUTABLE_FL)
+		return 1;
+	return 0;
+}
 
 int main(int argc, char **argv)
 {
@@ -27,7 +85,7 @@ int main(int argc, char **argv)
 	buf[4] = 0;
 
 	/* create a test variable */
-	fd = open(path, O_WRONLY | O_CREAT);
+	fd = open(path, O_WRONLY | O_CREAT, 0600);
 	if (fd < 0) {
 		perror("open(O_WRONLY)");
 		return EXIT_FAILURE;
@@ -41,6 +99,18 @@ int main(int argc, char **argv)
 
 	close(fd);
 
+	rc = get_immutable(path);
+	if (rc < 0) {
+		perror("ioctl(FS_IOC_GETFLAGS)");
+		return EXIT_FAILURE;
+	} else if (rc) {
+		rc = set_immutable(path, 0);
+		if (rc < 0) {
+			perror("ioctl(FS_IOC_SETFLAGS)");
+			return EXIT_FAILURE;
+		}
+	}
+
 	fd = open(path, O_RDONLY);
 	if (fd < 0) {
 		perror("open");

From e246eb568bc4cbbdd8a30a3c11151ff9b7ca7312 Mon Sep 17 00:00:00 2001
From: Matt Fleming <matt@codeblueprint.co.uk>
Date: Mon, 15 Feb 2016 10:34:05 +0000
Subject: [PATCH 06/11] efi: Add pstore variables to the deletion whitelist

Laszlo explains why this is a good idea,

 'This is because the pstore filesystem can be backed by UEFI variables,
  and (for example) a crash might dump the last kilobytes of the dmesg
  into a number of pstore entries, each entry backed by a separate UEFI
  variable in the above GUID namespace, and with a variable name
  according to the above pattern.

  Please see "drivers/firmware/efi/efi-pstore.c".

  While this patch series will not prevent the user from deleting those
  UEFI variables via the pstore filesystem (i.e., deleting a pstore fs
  entry will continue to delete the backing UEFI variable), I think it
  would be nice to preserve the possibility for the sysadmin to delete
  Linux-created UEFI variables that carry portions of the crash log,
  *without* having to mount the pstore filesystem.'

There's also no chance of causing machines to become bricked by
deleting these variables, which is the whole purpose of excluding
things from the whitelist.

Use the LINUX_EFI_CRASH_GUID guid and a wildcard '*' for the match so
that we don't have to update the string in the future if new variable
name formats are created for crash dump variables.

Reported-by: Laszlo Ersek <lersek@redhat.com>
Acked-by: Peter Jones <pjones@redhat.com>
Tested-by: Peter Jones <pjones@redhat.com>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>
Cc: "Lee, Chun-Yi" <jlee@suse.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
---
 drivers/firmware/efi/vars.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 50f10bad2604..7f2ea21c730d 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -198,6 +198,7 @@ static const struct variable_validate variable_validate[] = {
 	{ EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL },
 	{ EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string },
 	{ EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 },
+	{ LINUX_EFI_CRASH_GUID, "*", NULL },
 	{ NULL_GUID, "", NULL },
 };
 

From a68075908a37850918ad96b056acc9ac4ce1bd90 Mon Sep 17 00:00:00 2001
From: Jason Andryuk <jandryuk@gmail.com>
Date: Fri, 12 Feb 2016 23:13:33 +0000
Subject: [PATCH 07/11] lib/ucs2_string: Correct ucs2 -> utf8 conversion

The comparisons should be >= since 0x800 and 0x80 require an additional bit
to store.

For the 3 byte case, the existing shift would drop off 2 more bits than
intended.

For the 2 byte case, there should be 5 bits bits in byte 1, and 6 bits in
byte 2.

Signed-off-by: Jason Andryuk <jandryuk@gmail.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Matthew Garrett <mjg59@coreos.com>
Cc: "Lee, Chun-Yi" <jlee@suse.com>
Signed-off-by: Matt Fleming <matt@codeblueprint.co.uk>
---
 lib/ucs2_string.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
index 17dd74e21ef9..f0b323abb4c6 100644
--- a/lib/ucs2_string.c
+++ b/lib/ucs2_string.c
@@ -59,9 +59,9 @@ ucs2_utf8size(const ucs2_char_t *src)
 	for (i = 0; i < ucs2_strlen(src); i++) {
 		u16 c = src[i];
 
-		if (c > 0x800)
+		if (c >= 0x800)
 			j += 3;
-		else if (c > 0x80)
+		else if (c >= 0x80)
 			j += 2;
 		else
 			j += 1;
@@ -88,19 +88,19 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength)
 	for (i = 0; maxlength && i < limit; i++) {
 		u16 c = src[i];
 
-		if (c > 0x800) {
+		if (c >= 0x800) {
 			if (maxlength < 3)
 				break;
 			maxlength -= 3;
 			dest[j++] = 0xe0 | (c & 0xf000) >> 12;
-			dest[j++] = 0x80 | (c & 0x0fc0) >> 8;
+			dest[j++] = 0x80 | (c & 0x0fc0) >> 6;
 			dest[j++] = 0x80 | (c & 0x003f);
-		} else if (c > 0x80) {
+		} else if (c >= 0x80) {
 			if (maxlength < 2)
 				break;
 			maxlength -= 2;
-			dest[j++] = 0xc0 | (c & 0xfe0) >> 5;
-			dest[j++] = 0x80 | (c & 0x01f);
+			dest[j++] = 0xc0 | (c & 0x7c0) >> 6;
+			dest[j++] = 0x80 | (c & 0x03f);
 		} else {
 			maxlength -= 1;
 			dest[j++] = c & 0x7f;

From ee9737c924706aaa72c2ead93e3ad5644681dc1c Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hpe.com>
Date: Thu, 11 Feb 2016 14:24:16 -0700
Subject: [PATCH 08/11] x86/uaccess/64: Make the __copy_user_nocache() assembly
 code more readable

Add comments to __copy_user_nocache() to clarify its procedures
and alignment requirements.

Also change numeric branch target labels to named local labels.

No code changed:

 arch/x86/lib/copy_user_64.o:

    text    data     bss     dec     hex filename
    1239       0       0    1239     4d7 copy_user_64.o.before
    1239       0       0    1239     4d7 copy_user_64.o.after

 md5:
    58bed94c2db98c1ca9a2d46d0680aaae  copy_user_64.o.before.asm
    58bed94c2db98c1ca9a2d46d0680aaae  copy_user_64.o.after.asm

Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Cc: <stable@vger.kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: brian.boylston@hpe.com
Cc: dan.j.williams@intel.com
Cc: linux-nvdimm@lists.01.org
Cc: micah.parrish@hpe.com
Cc: ross.zwisler@linux.intel.com
Cc: vishal.l.verma@intel.com
Link: http://lkml.kernel.org/r/1455225857-12039-2-git-send-email-toshi.kani@hpe.com
[ Small readability edits and added object file comparison. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/lib/copy_user_64.S | 114 +++++++++++++++++++++++-------------
 1 file changed, 73 insertions(+), 41 deletions(-)

diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 982ce34f4a9b..a644aad1f112 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -232,17 +232,30 @@ ENDPROC(copy_user_enhanced_fast_string)
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
- * This will force destination/source out of cache for more performance.
+ * This will force destination out of cache for more performance.
+ *
+ * Note: Cached memory copy is used when destination or size is not
+ * naturally aligned. That is:
+ *  - Require 8-byte alignment when size is 8 bytes or larger.
  */
 ENTRY(__copy_user_nocache)
 	ASM_STAC
+
+	/* If size is less than 8 bytes, go to byte copy */
 	cmpl $8,%edx
-	jb 20f		/* less then 8 bytes, go to byte copy loop */
+	jb .L_1b_cache_copy_entry
+
+	/* If destination is not 8-byte aligned, "cache" copy to align it */
 	ALIGN_DESTINATION
+
+	/* Set 4x8-byte copy count and remainder */
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_8b_nocache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4x8-byte nocache loop-copy */
+.L_4x8b_nocache_copy_loop:
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -262,60 +275,79 @@ ENTRY(__copy_user_nocache)
 	leaq 64(%rsi),%rsi
 	leaq 64(%rdi),%rdi
 	decl %ecx
-	jnz 1b
-17:	movl %edx,%ecx
+	jnz .L_4x8b_nocache_copy_loop
+
+	/* Set 8-byte copy count and remainder */
+.L_8b_nocache_copy_entry:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
-	jz 20f
-18:	movq (%rsi),%r8
-19:	movnti %r8,(%rdi)
+	jz .L_1b_cache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 8-byte nocache loop-copy */
+.L_8b_nocache_copy_loop:
+20:	movq (%rsi),%r8
+21:	movnti %r8,(%rdi)
 	leaq 8(%rsi),%rsi
 	leaq 8(%rdi),%rdi
 	decl %ecx
-	jnz 18b
-20:	andl %edx,%edx
-	jz 23f
+	jnz .L_8b_nocache_copy_loop
+
+	/* If no byte left, we're done */
+.L_1b_cache_copy_entry:
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* Perform byte "cache" loop-copy for the remainder */
 	movl %edx,%ecx
-21:	movb (%rsi),%al
-22:	movb %al,(%rdi)
+.L_1b_cache_copy_loop:
+40:	movb (%rsi),%al
+41:	movb %al,(%rdi)
 	incq %rsi
 	incq %rdi
 	decl %ecx
-	jnz 21b
-23:	xorl %eax,%eax
+	jnz .L_1b_cache_copy_loop
+
+	/* Finished copying; fence the prior stores */
+.L_finish_copy:
+	xorl %eax,%eax
 	ASM_CLAC
 	sfence
 	ret
 
 	.section .fixup,"ax"
-30:	shll $6,%ecx
+.L_fixup_4x8b_copy:
+	shll $6,%ecx
 	addl %ecx,%edx
-	jmp 60f
-40:	lea (%rdx,%rcx,8),%rdx
-	jmp 60f
-50:	movl %ecx,%edx
-60:	sfence
+	jmp .L_fixup_handle_tail
+.L_fixup_8b_copy:
+	lea (%rdx,%rcx,8),%rdx
+	jmp .L_fixup_handle_tail
+.L_fixup_1b_copy:
+	movl %ecx,%edx
+.L_fixup_handle_tail:
+	sfence
 	jmp copy_user_handle_tail
 	.previous
 
-	_ASM_EXTABLE(1b,30b)
-	_ASM_EXTABLE(2b,30b)
-	_ASM_EXTABLE(3b,30b)
-	_ASM_EXTABLE(4b,30b)
-	_ASM_EXTABLE(5b,30b)
-	_ASM_EXTABLE(6b,30b)
-	_ASM_EXTABLE(7b,30b)
-	_ASM_EXTABLE(8b,30b)
-	_ASM_EXTABLE(9b,30b)
-	_ASM_EXTABLE(10b,30b)
-	_ASM_EXTABLE(11b,30b)
-	_ASM_EXTABLE(12b,30b)
-	_ASM_EXTABLE(13b,30b)
-	_ASM_EXTABLE(14b,30b)
-	_ASM_EXTABLE(15b,30b)
-	_ASM_EXTABLE(16b,30b)
-	_ASM_EXTABLE(18b,40b)
-	_ASM_EXTABLE(19b,40b)
-	_ASM_EXTABLE(21b,50b)
-	_ASM_EXTABLE(22b,50b)
+	_ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
+	_ASM_EXTABLE(20b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(21b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(40b,.L_fixup_1b_copy)
+	_ASM_EXTABLE(41b,.L_fixup_1b_copy)
 ENDPROC(__copy_user_nocache)

From a82eee7424525e34e98d821dd059ce14560a1e35 Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hpe.com>
Date: Thu, 11 Feb 2016 14:24:17 -0700
Subject: [PATCH 09/11] x86/uaccess/64: Handle the caching of 4-byte nocache
 copies properly in __copy_user_nocache()

Data corruption issues were observed in tests which initiated
a system crash/reset while accessing BTT devices.  This problem
is reproducible.

The BTT driver calls pmem_rw_bytes() to update data in pmem
devices.  This interface calls __copy_user_nocache(), which
uses non-temporal stores so that the stores to pmem are
persistent.

__copy_user_nocache() uses non-temporal stores when a request
size is 8 bytes or larger (and is aligned by 8 bytes).  The
BTT driver updates the BTT map table, which entry size is
4 bytes.  Therefore, updates to the map table entries remain
cached, and are not written to pmem after a crash.

Change __copy_user_nocache() to use non-temporal store when
a request size is 4 bytes.  The change extends the current
byte-copy path for a less-than-8-bytes request, and does not
add any overhead to the regular path.

Reported-and-tested-by: Micah Parrish <micah.parrish@hpe.com>
Reported-and-tested-by: Brian Boylston <brian.boylston@hpe.com>
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Cc: <stable@vger.kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: linux-nvdimm@lists.01.org
Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com
[ Small readability edits. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/lib/copy_user_64.S | 36 ++++++++++++++++++++++++++++++++----
 1 file changed, 32 insertions(+), 4 deletions(-)

diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index a644aad1f112..27f89c79a44b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -237,13 +237,14 @@ ENDPROC(copy_user_enhanced_fast_string)
  * Note: Cached memory copy is used when destination or size is not
  * naturally aligned. That is:
  *  - Require 8-byte alignment when size is 8 bytes or larger.
+ *  - Require 4-byte alignment when size is 4 bytes.
  */
 ENTRY(__copy_user_nocache)
 	ASM_STAC
 
-	/* If size is less than 8 bytes, go to byte copy */
+	/* If size is less than 8 bytes, go to 4-byte copy */
 	cmpl $8,%edx
-	jb .L_1b_cache_copy_entry
+	jb .L_4b_nocache_copy_entry
 
 	/* If destination is not 8-byte aligned, "cache" copy to align it */
 	ALIGN_DESTINATION
@@ -282,7 +283,7 @@ ENTRY(__copy_user_nocache)
 	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
-	jz .L_1b_cache_copy_entry	/* jump if count is 0 */
+	jz .L_4b_nocache_copy_entry	/* jump if count is 0 */
 
 	/* Perform 8-byte nocache loop-copy */
 .L_8b_nocache_copy_loop:
@@ -294,11 +295,33 @@ ENTRY(__copy_user_nocache)
 	jnz .L_8b_nocache_copy_loop
 
 	/* If no byte left, we're done */
-.L_1b_cache_copy_entry:
+.L_4b_nocache_copy_entry:
+	andl %edx,%edx
+	jz .L_finish_copy
+
+	/* If destination is not 4-byte aligned, go to byte copy: */
+	movl %edi,%ecx
+	andl $3,%ecx
+	jnz .L_1b_cache_copy_entry
+
+	/* Set 4-byte copy count (1 or 0) and remainder */
+	movl %edx,%ecx
+	andl $3,%edx
+	shrl $2,%ecx
+	jz .L_1b_cache_copy_entry	/* jump if count is 0 */
+
+	/* Perform 4-byte nocache copy: */
+30:	movl (%rsi),%r8d
+31:	movnti %r8d,(%rdi)
+	leaq 4(%rsi),%rsi
+	leaq 4(%rdi),%rdi
+
+	/* If no bytes left, we're done: */
 	andl %edx,%edx
 	jz .L_finish_copy
 
 	/* Perform byte "cache" loop-copy for the remainder */
+.L_1b_cache_copy_entry:
 	movl %edx,%ecx
 .L_1b_cache_copy_loop:
 40:	movb (%rsi),%al
@@ -323,6 +346,9 @@ ENTRY(__copy_user_nocache)
 .L_fixup_8b_copy:
 	lea (%rdx,%rcx,8),%rdx
 	jmp .L_fixup_handle_tail
+.L_fixup_4b_copy:
+	lea (%rdx,%rcx,4),%rdx
+	jmp .L_fixup_handle_tail
 .L_fixup_1b_copy:
 	movl %ecx,%edx
 .L_fixup_handle_tail:
@@ -348,6 +374,8 @@ ENTRY(__copy_user_nocache)
 	_ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
 	_ASM_EXTABLE(20b,.L_fixup_8b_copy)
 	_ASM_EXTABLE(21b,.L_fixup_8b_copy)
+	_ASM_EXTABLE(30b,.L_fixup_4b_copy)
+	_ASM_EXTABLE(31b,.L_fixup_4b_copy)
 	_ASM_EXTABLE(40b,.L_fixup_1b_copy)
 	_ASM_EXTABLE(41b,.L_fixup_1b_copy)
 ENDPROC(__copy_user_nocache)

From 4e7f9df25874cedbbc604a5c5c2e7a6efe662387 Mon Sep 17 00:00:00 2001
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Thu, 11 Feb 2016 01:05:01 +0200
Subject: [PATCH 10/11] hpet: Drop stale URLs

Looks like the HPET spec at intel.com got moved.
It isn't hard to find so drop the link, just mention
the revision assumed.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Clemens Ladisch <clemens@ladisch.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-doc@vger.kernel.org
Link: http://lkml.kernel.org/r/1455145462-3877-1-git-send-email-mst@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/timers/hpet.txt | 4 +---
 arch/x86/Kconfig              | 4 ++--
 drivers/char/hpet.c           | 2 +-
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt
index 767392ffd31e..a484d2c109d7 100644
--- a/Documentation/timers/hpet.txt
+++ b/Documentation/timers/hpet.txt
@@ -1,9 +1,7 @@
 		High Precision Event Timer Driver for Linux
 
 The High Precision Event Timer (HPET) hardware follows a specification
-by Intel and Microsoft which can be found at
-
-	http://www.intel.com/hardwaredesign/hpetspec_1.pdf
+by Intel and Microsoft, revision 1.
 
 Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision")
 and up to 32 comparators.  Normally three or more comparators are provided,
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ab2ed5328f0a..c46662f64c39 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -778,8 +778,8 @@ config HPET_TIMER
 	  HPET is the next generation timer replacing legacy 8254s.
 	  The HPET provides a stable time base on SMP
 	  systems, unlike the TSC, but it is more expensive to access,
-	  as it is off-chip.  You can find the HPET spec at
-	  <http://www.intel.com/hardwaredesign/hpetspec_1.pdf>.
+	  as it is off-chip.  The interface used is documented
+	  in the HPET spec, revision 1.
 
 	  You can safely choose Y here.  However, HPET will only be
 	  activated if the platform and the BIOS support this feature.
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 240b6cf1d97c..be54e5331a45 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -42,7 +42,7 @@
 /*
  * The High Precision Event Timer driver.
  * This driver is closely modelled after the rtc.c driver.
- * http://www.intel.com/hardwaredesign/hpetspec_1.pdf
+ * See HPET spec revision 1.
  */
 #define	HPET_USER_FREQ	(64)
 #define	HPET_DRIFT	(500)

From f4eafd8bcd5229e998aa252627703b8462c3b90f Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hpe.com>
Date: Wed, 17 Feb 2016 18:16:54 -0700
Subject: [PATCH 11/11] x86/mm: Fix vmalloc_fault() to handle large pages
 properly

A kernel page fault oops with the callstack below was observed
when a read syscall was made to a pmem device after a huge amount
(>512GB) of vmalloc ranges was allocated by ioremap() on a x86_64
system:

     BUG: unable to handle kernel paging request at ffff880840000ff8
     IP: vmalloc_fault+0x1be/0x300
     PGD c7f03a067 PUD 0
     Oops: 0000 [#1] SM
     Call Trace:
        __do_page_fault+0x285/0x3e0
        do_page_fault+0x2f/0x80
        ? put_prev_entity+0x35/0x7a0
        page_fault+0x28/0x30
        ? memcpy_erms+0x6/0x10
        ? schedule+0x35/0x80
        ? pmem_rw_bytes+0x6a/0x190 [nd_pmem]
        ? schedule_timeout+0x183/0x240
        btt_log_read+0x63/0x140 [nd_btt]
         :
        ? __symbol_put+0x60/0x60
        ? kernel_read+0x50/0x80
        SyS_finit_module+0xb9/0xf0
        entry_SYSCALL_64_fastpath+0x1a/0xa4

Since v4.1, ioremap() supports large page (pud/pmd) mappings in
x86_64 and PAE.  vmalloc_fault() however assumes that the vmalloc
range is limited to pte mappings.

vmalloc faults do not normally happen in ioremap'd ranges since
ioremap() sets up the kernel page tables, which are shared by
user processes.  pgd_ctor() sets the kernel's PGD entries to
user's during fork().  When allocation of the vmalloc ranges
crosses a 512GB boundary, ioremap() allocates a new pud table
and updates the kernel PGD entry to point it.  If user process's
PGD entry does not have this update yet, a read/write syscall
to the range will cause a vmalloc fault, which hits the Oops
above as it does not handle a large page properly.

Following changes are made to vmalloc_fault().

64-bit:

 - No change for the PGD sync operation as it handles large
   pages already.
 - Add pud_huge() and pmd_huge() to the validation code to
   handle large pages.
 - Change pud_page_vaddr() to pud_pfn() since an ioremap range
   is not directly mapped (while the if-statement still works
   with a bogus addr).
 - Change pmd_page() to pmd_pfn() since an ioremap range is not
   backed by struct page (while the if-statement still works
   with a bogus addr).

32-bit:
 - No change for the sync operation since the index3 PGD entry
   covers the entire vmalloc range, which is always valid.
   (A separate change to sync PGD entry is necessary if this
    memory layout is changed regardless of the page size.)
 - Add pmd_huge() to the validation code to handle large pages.
   This is for completeness since vmalloc_fault() won't happen
   in ioremap'd ranges as its PGD entry is always valid.

Reported-by: Henning Schild <henning.schild@siemens.com>
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: <stable@vger.kernel.org> # 4.1+
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: linux-mm@kvack.org
Cc: linux-nvdimm@lists.01.org
Link: http://lkml.kernel.org/r/1455758214-24623-1-git-send-email-toshi.kani@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/mm/fault.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index eef44d9a3f77..e830c71a1323 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!pmd_k)
 		return -1;
 
+	if (pmd_huge(*pmd_k))
+		return 0;
+
 	pte_k = pte_offset_kernel(pmd_k, address);
 	if (!pte_present(*pte_k))
 		return -1;
@@ -360,8 +363,6 @@ void vmalloc_sync_all(void)
  * 64-bit:
  *
  *   Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
  */
 static noinline int vmalloc_fault(unsigned long address)
 {
@@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pud_none(*pud_ref))
 		return -1;
 
-	if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
+	if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
 		BUG();
 
+	if (pud_huge(*pud))
+		return 0;
+
 	pmd = pmd_offset(pud, address);
 	pmd_ref = pmd_offset(pud_ref, address);
 	if (pmd_none(*pmd_ref))
 		return -1;
 
-	if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+	if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
 		BUG();
 
+	if (pmd_huge(*pmd))
+		return 0;
+
 	pte_ref = pte_offset_kernel(pmd_ref, address);
 	if (!pte_present(*pte_ref))
 		return -1;