[patch 01/54] mm/page_idle.c: skip offline pages

[patch 01/54] mm/page_idle.c: skip offline pages

[Andrew Morton]

From: SeongJae Park <sjpark@amazon.de>
Subject: mm/page_idle.c: skip offline pages

'Idle page tracking' users can pass random pfn that might be mapped to an
offline page.  To avoid accessing such pages, this commit modifies the
'page_idle_get_page()' to use 'pfn_to_online_page()' instead of
'pfn_valid()' and 'pfn_to_page()' combination, so that the pfn mapped to
an offline page can be skipped.

Link: http://lkml.kernel.org/r/20200605092502.18018-2-sjpark@amazon.com
Signed-off-by: SeongJae Park <sjpark@amazon.de>
Reported-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/page_idle.c |    7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

--- a/mm/page_idle.c~mm-page_idlec-skip-offline-pages
+++ a/mm/page_idle.c
@@ -4,6 +4,7 @@
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kobject.h>
+#include <linux/memory_hotplug.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/pagemap.h>
@@ -30,13 +31,9 @@
  */
 static struct page *page_idle_get_page(unsigned long pfn)
 {
-	struct page *page;
+	struct page *page = pfn_to_online_page(pfn);
 	pg_data_t *pgdat;
 
-	if (!pfn_valid(pfn))
-		return NULL;
-
-	page = pfn_to_page(pfn);
 	if (!page || !PageLRU(page) ||
 	    !get_page_unless_zero(page))
 		return NULL;
_

[patch 02/54] ipc/msg: add missing annotation for freeque()

[Andrew Morton]

From: Jules Irenge <jbi.octave@gmail.com>
Subject: ipc/msg: add missing annotation for freeque()

Sparse reports a warning at freeque()

warning: context imbalance in freeque() - unexpected unlock

The root cause is the missing annotation at freeque()

Add the missing __releases(RCU) annotation
Add the missing __releases(&msq->q_perm) annotation

Link: http://lkml.kernel.org/r/20200403160505.2832-2-jbi.octave@gmail.com
Signed-off-by: Jules Irenge <jbi.octave@gmail.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Lu Shuaibing <shuaibinglu@126.com>
Cc: Nathan Chancellor <natechancellor@gmail.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 ipc/msg.c |    2 ++
 1 file changed, 2 insertions(+)

--- a/ipc/msg.c~ipc-msg-add-missing-annotation-for-freeque
+++ a/ipc/msg.c
@@ -268,6 +268,8 @@ static void expunge_all(struct msg_queue
  * before freeque() is called. msg_ids.rwsem remains locked on exit.
  */
 static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
+	__releases(RCU)
+	__releases(&msq->q_perm)
 {
 	struct msg_msg *msg, *t;
 	struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
_

[patch 03/54] ipc/namespace.c: use a work queue to free_ipc

[Andrew Morton]

From: Giuseppe Scrivano <gscrivan@redhat.com>
Subject: ipc/namespace.c: use a work queue to free_ipc

the reason is to avoid a delay caused by the synchronize_rcu() call in
kern_umount() when the mqueue mount is freed.

the code:

\#define _GNU_SOURCE
\#include <sched.h>
\#include <error.h>
\#include <errno.h>
\#include <stdlib.h>
int main()
{
  int i;
  for (i = 0; i < 1000; i++)
    if (unshare (CLONE_NEWIPC) < 0)
      error (EXIT_FAILURE, errno, "unshare");
}

gets from

	Command being timed: "./ipc-namespace"
	User time (seconds): 0.00
	System time (seconds): 0.06
	Percent of CPU this job got: 0%
	Elapsed (wall clock) time (h:mm:ss or m:ss): 0:08.05

to

	Command being timed: "./ipc-namespace"
	User time (seconds): 0.00
	System time (seconds): 0.02
	Percent of CPU this job got: 96%
	Elapsed (wall clock) time (h:mm:ss or m:ss): 0:00.03

Link: http://lkml.kernel.org/r/20200225145419.527994-1-gscrivan@redhat.com
Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Waiman Long <longman@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Manfred Spraul <manfred@colorfullife.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/ipc_namespace.h |    2 ++
 ipc/namespace.c               |   24 ++++++++++++++++++++++--
 2 files changed, 24 insertions(+), 2 deletions(-)

--- a/include/linux/ipc_namespace.h~ipc-use-a-work-queue-to-free_ipc
+++ a/include/linux/ipc_namespace.h
@@ -68,6 +68,8 @@ struct ipc_namespace {
 	struct user_namespace *user_ns;
 	struct ucounts *ucounts;
 
+	struct llist_node mnt_llist;
+
 	struct ns_common ns;
 } __randomize_layout;
 
--- a/ipc/namespace.c~ipc-use-a-work-queue-to-free_ipc
+++ a/ipc/namespace.c
@@ -117,6 +117,10 @@ void free_ipcs(struct ipc_namespace *ns,
 
 static void free_ipc_ns(struct ipc_namespace *ns)
 {
+	/* mq_put_mnt() waits for a grace period as kern_unmount()
+	 * uses synchronize_rcu().
+	 */
+	mq_put_mnt(ns);
 	sem_exit_ns(ns);
 	msg_exit_ns(ns);
 	shm_exit_ns(ns);
@@ -127,6 +131,21 @@ static void free_ipc_ns(struct ipc_names
 	kfree(ns);
 }
 
+static LLIST_HEAD(free_ipc_list);
+static void free_ipc(struct work_struct *unused)
+{
+	struct llist_node *node = llist_del_all(&free_ipc_list);
+	struct ipc_namespace *n, *t;
+
+	llist_for_each_entry_safe(n, t, node, mnt_llist)
+		free_ipc_ns(n);
+}
+
+/*
+ * The work queue is used to avoid the cost of synchronize_rcu in kern_unmount.
+ */
+static DECLARE_WORK(free_ipc_work, free_ipc);
+
 /*
  * put_ipc_ns - drop a reference to an ipc namespace.
  * @ns: the namespace to put
@@ -148,8 +167,9 @@ void put_ipc_ns(struct ipc_namespace *ns
 	if (refcount_dec_and_lock(&ns->count, &mq_lock)) {
 		mq_clear_sbinfo(ns);
 		spin_unlock(&mq_lock);
-		mq_put_mnt(ns);
-		free_ipc_ns(ns);
+
+		if (llist_add(&ns->mnt_llist, &free_ipc_list))
+			schedule_work(&free_ipc_work);
 	}
 }
 
_

[patch 04/54] dynamic_debug: add an option to enable dynamic debug for modules only

[Andrew Morton]

From: Orson Zhai <orson.zhai@unisoc.com>
Subject: dynamic_debug: add an option to enable dynamic debug for modules only

Instead of enabling dynamic debug globally with CONFIG_DYNAMIC_DEBUG,
CONFIG_DYNAMIC_DEBUG_CORE will only enable core function of dynamic debug.
With the DYNAMIC_DEBUG_MODULE defined for any modules, dynamic debug will
be tied to them.

This is useful for people who only want to enable dynamic debug for kernel
modules without worrying about kernel image size and memory consumption is
increasing too much.

[orson.zhai@unisoc.com: v2]
  Link: http://lkml.kernel.org/r/1587408228-10861-1-git-send-email-orson.unisoc@gmail.com
Link: http://lkml.kernel.org/r/1586521984-5890-1-git-send-email-orson.unisoc@gmail.com
Signed-off-by: Orson Zhai <orson.zhai@unisoc.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/dynamic-debug-howto.rst |    5 +++++
 include/linux/dev_printk.h                        |    6 ++++--
 include/linux/dynamic_debug.h                     |    2 +-
 include/linux/net.h                               |    3 ++-
 include/linux/netdevice.h                         |    6 ++++--
 include/linux/printk.h                            |    9 ++++++---
 include/rdma/ib_verbs.h                           |    6 ++++--
 lib/Kconfig.debug                                 |   12 ++++++++++++
 lib/Makefile                                      |    2 +-
 lib/dynamic_debug.c                               |    9 +++++++--
 10 files changed, 46 insertions(+), 14 deletions(-)

--- a/Documentation/admin-guide/dynamic-debug-howto.rst~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/Documentation/admin-guide/dynamic-debug-howto.rst
@@ -13,6 +13,11 @@ kernel code to obtain additional kernel
 ``print_hex_dump_debug()``/``print_hex_dump_bytes()`` calls can be dynamically
 enabled per-callsite.
 
+If you do not want to enable dynamic debug globally (i.e. in some embedded
+system), you may set ``CONFIG_DYNAMIC_DEBUG_CORE`` as basic support of dynamic
+debug and add ``ccflags := -DDYNAMIC_DEBUG_MODULE`` into the Makefile of any
+modules which you'd like to dynamically debug later.
+
 If ``CONFIG_DYNAMIC_DEBUG`` is not set, ``print_hex_dump_debug()`` is just
 shortcut for ``print_hex_dump(KERN_DEBUG)``.
 
--- a/include/linux/dev_printk.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/dev_printk.h
@@ -109,7 +109,8 @@ void _dev_info(const struct device *dev,
 #define dev_info(dev, fmt, ...)						\
 	_dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__)
 
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define dev_dbg(dev, fmt, ...)						\
 	dynamic_dev_dbg(dev, dev_fmt(fmt), ##__VA_ARGS__)
 #elif defined(DEBUG)
@@ -181,7 +182,8 @@ do {									\
 	dev_level_ratelimited(dev_notice, dev, fmt, ##__VA_ARGS__)
 #define dev_info_ratelimited(dev, fmt, ...)				\
 	dev_level_ratelimited(dev_info, dev, fmt, ##__VA_ARGS__)
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 /* descriptor check is first to prevent flooding with "callbacks suppressed" */
 #define dev_dbg_ratelimited(dev, fmt, ...)				\
 do {									\
--- a/include/linux/dynamic_debug.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/dynamic_debug.h
@@ -48,7 +48,7 @@ struct _ddebug {
 
 
 
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG_CORE)
 int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 				const char *modname);
 extern int ddebug_remove_module(const char *mod_name);
--- a/include/linux/netdevice.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/netdevice.h
@@ -4942,7 +4942,8 @@ do {								\
 #define MODULE_ALIAS_NETDEV(device) \
 	MODULE_ALIAS("netdev-" device)
 
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define netdev_dbg(__dev, format, args...)			\
 do {								\
 	dynamic_netdev_dbg(__dev, format, ##args);		\
@@ -5012,7 +5013,8 @@ do {								\
 #define netif_info(priv, type, dev, fmt, args...)		\
 	netif_level(info, priv, type, dev, fmt, ##args)
 
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define netif_dbg(priv, type, netdev, format, args...)		\
 do {								\
 	if (netif_msg_##type(priv))				\
--- a/include/linux/net.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/net.h
@@ -264,7 +264,8 @@ do {								\
 	net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__)
 #define net_info_ratelimited(fmt, ...)				\
 	net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__)
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define net_dbg_ratelimited(fmt, ...)					\
 do {									\
 	DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);			\
--- a/include/linux/printk.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/printk.h
@@ -399,7 +399,8 @@ extern int kptr_restrict;
 
 
 /* If you are writing a driver, please use dev_dbg instead */
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #include <linux/dynamic_debug.h>
 
 /**
@@ -535,7 +536,8 @@ extern int kptr_restrict;
 #endif
 
 /* If you are writing a driver, please use dev_dbg instead */
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 /* descriptor check is first to prevent flooding with "callbacks suppressed" */
 #define pr_debug_ratelimited(fmt, ...)					\
 do {									\
@@ -582,7 +584,8 @@ static inline void print_hex_dump_bytes(
 
 #endif
 
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define print_hex_dump_debug(prefix_str, prefix_type, rowsize,	\
 			     groupsize, buf, len, ascii)	\
 	dynamic_hex_dump(prefix_str, prefix_type, rowsize,	\
--- a/include/rdma/ib_verbs.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/rdma/ib_verbs.h
@@ -100,7 +100,8 @@ void ibdev_notice(const struct ib_device
 __printf(2, 3) __cold
 void ibdev_info(const struct ib_device *ibdev, const char *format, ...);
 
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define ibdev_dbg(__dev, format, args...)                       \
 	dynamic_ibdev_dbg(__dev, format, ##args)
 #else
@@ -133,7 +134,8 @@ do {
 #define ibdev_info_ratelimited(ibdev, fmt, ...) \
 	ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__)
 
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+	(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 /* descriptor check is first to prevent flooding with "callbacks suppressed" */
 #define ibdev_dbg_ratelimited(ibdev, fmt, ...)                          \
 do {                                                                    \
--- a/lib/dynamic_debug.c~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/lib/dynamic_debug.c
@@ -1032,8 +1032,13 @@ static int __init dynamic_debug_init(voi
 	int verbose_bytes = 0;
 
 	if (&__start___verbose == &__stop___verbose) {
-		pr_warn("_ddebug table is empty in a CONFIG_DYNAMIC_DEBUG build\n");
-		return 1;
+		if (IS_ENABLED(CONFIG_DYNAMIC_DEBUG)) {
+			pr_warn("_ddebug table is empty in a CONFIG_DYNAMIC_DEBUG build\n");
+			return 1;
+		}
+		pr_info("Ignore empty _ddebug table in a CONFIG_DYNAMIC_DEBUG_CORE build\n");
+		ddebug_init_success = 1;
+		return 0;
 	}
 	iter = __start___verbose;
 	modname = iter->modname;
--- a/lib/Kconfig.debug~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/lib/Kconfig.debug
@@ -99,6 +99,7 @@ config DYNAMIC_DEBUG
 	default n
 	depends on PRINTK
 	depends on (DEBUG_FS || PROC_FS)
+	select DYNAMIC_DEBUG_CORE
 	help
 
 	  Compiles debug level messages into the kernel, which would not
@@ -165,6 +166,17 @@ config DYNAMIC_DEBUG
 	  See Documentation/admin-guide/dynamic-debug-howto.rst for additional
 	  information.
 
+config DYNAMIC_DEBUG_CORE
+	bool "Enable core function of dynamic debug support"
+	depends on PRINTK
+	depends on (DEBUG_FS || PROC_FS)
+	help
+	  Enable core functional support of dynamic debug. It is useful
+	  when you want to tie dynamic debug to your kernel modules with
+	  DYNAMIC_DEBUG_MODULE defined for each of them, especially for
+	  the case of embedded system where the kernel image size is
+	  sensitive for people.
+
 config SYMBOLIC_ERRNAME
 	bool "Support symbolic error names in printf"
 	default y if PRINTK
--- a/lib/Makefile~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/lib/Makefile
@@ -190,7 +190,7 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
 
-obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
+obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
 obj-$(CONFIG_SYMBOLIC_ERRNAME) += errname.o
 
 obj-$(CONFIG_NLATTR) += nlattr.o
_

答复: [patch 04/54] dynamic_debug: add an option to enable dynamic debug for modules only

[翟京 (Orson Zhai)]

Hi Andrew and Linus,

Could you please also add "Acked-by: Petr Mladek <pmladek@suse.com>" into this patch according to his mailing list replies at [1].

Thanks,
Orson

[1] https://lore.kernel.org/lkml/20200518095026.GL7340@linux-b0ei/


________________________________________
发件人: Andrew Morton <akpm@linux-foundation.org>
发送时间: 2020年6月8日 12:40
收件人: akpm@linux-foundation.org; corbet@lwn.net; gregkh@linuxfoundation.org; jbaron@akamai.com; linux-mm@kvack.org; mm-commits@vger.kernel.org; 翟京 (Orson Zhai); pmladek@suse.com; rdunlap@infradead.org; rostedt@goodmis.org; sergey.senozhatsky@gmail.com; torvalds@linux-foundation.org
主题: [patch 04/54] dynamic_debug: add an option to enable dynamic debug for modules only

From: Orson Zhai <orson.zhai@unisoc.com>
Subject: dynamic_debug: add an option to enable dynamic debug for modules only

Instead of enabling dynamic debug globally with CONFIG_DYNAMIC_DEBUG,
CONFIG_DYNAMIC_DEBUG_CORE will only enable core function of dynamic debug.
With the DYNAMIC_DEBUG_MODULE defined for any modules, dynamic debug will
be tied to them.

This is useful for people who only want to enable dynamic debug for kernel
modules without worrying about kernel image size and memory consumption is
increasing too much.

[orson.zhai@unisoc.com: v2]
  Link: http://lkml.kernel.org/r/1587408228-10861-1-git-send-email-orson.unisoc@gmail.com
Link: http://lkml.kernel.org/r/1586521984-5890-1-git-send-email-orson.unisoc@gmail.com
Signed-off-by: Orson Zhai <orson.zhai@unisoc.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/dynamic-debug-howto.rst |    5 +++++
 include/linux/dev_printk.h                        |    6 ++++--
 include/linux/dynamic_debug.h                     |    2 +-
 include/linux/net.h                               |    3 ++-
 include/linux/netdevice.h                         |    6 ++++--
 include/linux/printk.h                            |    9 ++++++---
 include/rdma/ib_verbs.h                           |    6 ++++--
 lib/Kconfig.debug                                 |   12 ++++++++++++
 lib/Makefile                                      |    2 +-
 lib/dynamic_debug.c                               |    9 +++++++--
 10 files changed, 46 insertions(+), 14 deletions(-)

--- a/Documentation/admin-guide/dynamic-debug-howto.rst~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/Documentation/admin-guide/dynamic-debug-howto.rst
@@ -13,6 +13,11 @@ kernel code to obtain additional kernel
 ``print_hex_dump_debug()``/``print_hex_dump_bytes()`` calls can be dynamically
 enabled per-callsite.

+If you do not want to enable dynamic debug globally (i.e. in some embedded
+system), you may set ``CONFIG_DYNAMIC_DEBUG_CORE`` as basic support of dynamic
+debug and add ``ccflags := -DDYNAMIC_DEBUG_MODULE`` into the Makefile of any
+modules which you'd like to dynamically debug later.
+
 If ``CONFIG_DYNAMIC_DEBUG`` is not set, ``print_hex_dump_debug()`` is just
 shortcut for ``print_hex_dump(KERN_DEBUG)``.

--- a/include/linux/dev_printk.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/dev_printk.h
@@ -109,7 +109,8 @@ void _dev_info(const struct device *dev,
 #define dev_info(dev, fmt, ...)                                                \
        _dev_info(dev, dev_fmt(fmt), ##__VA_ARGS__)

-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define dev_dbg(dev, fmt, ...)                                         \
        dynamic_dev_dbg(dev, dev_fmt(fmt), ##__VA_ARGS__)
 #elif defined(DEBUG)
@@ -181,7 +182,8 @@ do {                                                                        \
        dev_level_ratelimited(dev_notice, dev, fmt, ##__VA_ARGS__)
 #define dev_info_ratelimited(dev, fmt, ...)                            \
        dev_level_ratelimited(dev_info, dev, fmt, ##__VA_ARGS__)
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 /* descriptor check is first to prevent flooding with "callbacks suppressed" */
 #define dev_dbg_ratelimited(dev, fmt, ...)                             \
 do {                                                                   \
--- a/include/linux/dynamic_debug.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/dynamic_debug.h
@@ -48,7 +48,7 @@ struct _ddebug {



-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG_CORE)
 int ddebug_add_module(struct _ddebug *tab, unsigned int n,
                                const char *modname);
 extern int ddebug_remove_module(const char *mod_name);
--- a/include/linux/netdevice.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/netdevice.h
@@ -4942,7 +4942,8 @@ do {                                                              \
 #define MODULE_ALIAS_NETDEV(device) \
        MODULE_ALIAS("netdev-" device)

-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define netdev_dbg(__dev, format, args...)                     \
 do {                                                           \
        dynamic_netdev_dbg(__dev, format, ##args);              \
@@ -5012,7 +5013,8 @@ do {                                                              \
 #define netif_info(priv, type, dev, fmt, args...)              \
        netif_level(info, priv, type, dev, fmt, ##args)

-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define netif_dbg(priv, type, netdev, format, args...)         \
 do {                                                           \
        if (netif_msg_##type(priv))                             \
--- a/include/linux/net.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/net.h
@@ -264,7 +264,8 @@ do {                                                                \
        net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__)
 #define net_info_ratelimited(fmt, ...)                         \
        net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__)
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define net_dbg_ratelimited(fmt, ...)                                  \
 do {                                                                   \
        DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt);                 \
--- a/include/linux/printk.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/linux/printk.h
@@ -399,7 +399,8 @@ extern int kptr_restrict;


 /* If you are writing a driver, please use dev_dbg instead */
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #include <linux/dynamic_debug.h>

 /**
@@ -535,7 +536,8 @@ extern int kptr_restrict;
 #endif

 /* If you are writing a driver, please use dev_dbg instead */
-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 /* descriptor check is first to prevent flooding with "callbacks suppressed" */
 #define pr_debug_ratelimited(fmt, ...)                                 \
 do {                                                                   \
@@ -582,7 +584,8 @@ static inline void print_hex_dump_bytes(

 #endif

-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \
                             groupsize, buf, len, ascii)        \
        dynamic_hex_dump(prefix_str, prefix_type, rowsize,      \
--- a/include/rdma/ib_verbs.h~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/include/rdma/ib_verbs.h
@@ -100,7 +100,8 @@ void ibdev_notice(const struct ib_device
 __printf(2, 3) __cold
 void ibdev_info(const struct ib_device *ibdev, const char *format, ...);

-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 #define ibdev_dbg(__dev, format, args...)                       \
        dynamic_ibdev_dbg(__dev, format, ##args)
 #else
@@ -133,7 +134,8 @@ do {
 #define ibdev_info_ratelimited(ibdev, fmt, ...) \
        ibdev_level_ratelimited(ibdev_info, ibdev, fmt, ##__VA_ARGS__)

-#if defined(CONFIG_DYNAMIC_DEBUG)
+#if defined(CONFIG_DYNAMIC_DEBUG) || \
+       (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
 /* descriptor check is first to prevent flooding with "callbacks suppressed" */
 #define ibdev_dbg_ratelimited(ibdev, fmt, ...)                          \
 do {                                                                    \
--- a/lib/dynamic_debug.c~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/lib/dynamic_debug.c
@@ -1032,8 +1032,13 @@ static int __init dynamic_debug_init(voi
        int verbose_bytes = 0;

        if (&__start___verbose == &__stop___verbose) {
-               pr_warn("_ddebug table is empty in a CONFIG_DYNAMIC_DEBUG build\n");
-               return 1;
+               if (IS_ENABLED(CONFIG_DYNAMIC_DEBUG)) {
+                       pr_warn("_ddebug table is empty in a CONFIG_DYNAMIC_DEBUG build\n");
+                       return 1;
+               }
+               pr_info("Ignore empty _ddebug table in a CONFIG_DYNAMIC_DEBUG_CORE build\n");
+               ddebug_init_success = 1;
+               return 0;
        }
        iter = __start___verbose;
        modname = iter->modname;
--- a/lib/Kconfig.debug~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/lib/Kconfig.debug
@@ -99,6 +99,7 @@ config DYNAMIC_DEBUG
        default n
        depends on PRINTK
        depends on (DEBUG_FS || PROC_FS)
+       select DYNAMIC_DEBUG_CORE
        help

          Compiles debug level messages into the kernel, which would not
@@ -165,6 +166,17 @@ config DYNAMIC_DEBUG
          See Documentation/admin-guide/dynamic-debug-howto.rst for additional
          information.

+config DYNAMIC_DEBUG_CORE
+       bool "Enable core function of dynamic debug support"
+       depends on PRINTK
+       depends on (DEBUG_FS || PROC_FS)
+       help
+         Enable core functional support of dynamic debug. It is useful
+         when you want to tie dynamic debug to your kernel modules with
+         DYNAMIC_DEBUG_MODULE defined for each of them, especially for
+         the case of embedded system where the kernel image size is
+         sensitive for people.
+
 config SYMBOLIC_ERRNAME
        bool "Support symbolic error names in printf"
        default y if PRINTK
--- a/lib/Makefile~dynamic_debug-add-an-option-to-enable-dynamic-debug-for-modules-only
+++ a/lib/Makefile
@@ -190,7 +190,7 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o

 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o

-obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
+obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
 obj-$(CONFIG_SYMBOLIC_ERRNAME) += errname.o

 obj-$(CONFIG_NLATTR) += nlattr.o
_
________________________________
 This email (including its attachments) is intended only for the person or entity to which it is addressed and may contain information that is privileged, confidential or otherwise protected from disclosure. Unauthorized use, dissemination, distribution or copying of this email or the information herein or taking any action in reliance on the contents of this email or the information herein, by anyone other than the intended recipient, or an employee or agent responsible for delivering the message to the intended recipient, is strictly prohibited. If you are not the intended recipient, please do not read, copy, use or disclose any part of this e-mail to others. Please notify the sender immediately and permanently delete this e-mail and any attachments if you received it in error. Internet communications cannot be guaranteed to be timely, secure, error-free or virus-free. The sender does not accept liability for any errors or omissions.
本邮件及其附件具有保密性质，受法律保护不得泄露，仅发送给本邮件所指特定收件人。严禁非经授权使用、宣传、发布或复制本邮件或其内容。若非该特定收件人，请勿阅读、复制、 使用或披露本邮件的任何内容。若误收本邮件，请从系统中永久性删除本邮件及所有附件，并以回复邮件的方式即刻告知发件人。无法保证互联网通信及时、安全、无误或防毒。发件人对任何错漏均不承担责任。

[patch 05/54] kernel: add panic_on_taint

[Andrew Morton]

From: Rafael Aquini <aquini@redhat.com>
Subject: kernel: add panic_on_taint

Analogously to the introduction of panic_on_warn, this patch introduces a
kernel option named panic_on_taint in order to provide a simple and
generic way to stop execution and catch a coredump when the kernel gets
tainted by any given flag.

This is useful for debugging sessions as it avoids having to rebuild the
kernel to explicitly add calls to panic() into the code sites that
introduce the taint flags of interest.  For instance, if one is interested
in proceeding with a post-mortem analysis at the point a given code path
is hitting a bad page (i.e.  unaccount_page_cache_page(), or slab_bug()),
a coredump can be collected by rebooting the kernel with
'panic_on_taint=0x20' amended to the command line.

Another, perhaps less frequent, use for this option would be as a means
for assuring a security policy case where only a subset of taints, or no
single taint (in paranoid mode), is allowed for the running system.  The
optional switch 'nousertaint' is handy in this particular scenario, as it
will avoid userspace induced crashes by writes to sysctl interface
/proc/sys/kernel/tainted causing false positive hits for such policies.

[akpm@linux-foundation.org: tweak kernel-parameters.txt wording]
Link: http://lkml.kernel.org/r/20200515175502.146720-1-aquini@redhat.com
Signed-off-by: Rafael Aquini <aquini@redhat.com>
Suggested-by: Qian Cai <cai@lca.pw>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Cc: Dave Young <dyoung@redhat.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Adrian Bunk <bunk@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/kdump/kdump.rst       |    8 +++
 Documentation/admin-guide/kernel-parameters.txt |   13 +++++
 Documentation/admin-guide/sysctl/kernel.rst     |    7 ++
 include/linux/kernel.h                          |    3 +
 kernel/panic.c                                  |   34 ++++++++++++++
 kernel/sysctl.c                                 |   11 ++++
 6 files changed, 75 insertions(+), 1 deletion(-)

--- a/Documentation/admin-guide/kdump/kdump.rst~kernel-add-panic_on_taint
+++ a/Documentation/admin-guide/kdump/kdump.rst
@@ -521,6 +521,14 @@ will cause a kdump to occur at the panic
 to specify this during runtime, /proc/sys/kernel/panic_on_warn can be set to 1
 to achieve the same behaviour.
 
+Trigger Kdump on add_taint()
+============================
+
+The kernel parameter panic_on_taint facilitates a conditional call to panic()
+from within add_taint() whenever the value set in this bitmask matches with the
+bit flag being set by add_taint().
+This will cause a kdump to occur at the add_taint()->panic() call.
+
 Contact
 =======
 
--- a/Documentation/admin-guide/kernel-parameters.txt~kernel-add-panic_on_taint
+++ a/Documentation/admin-guide/kernel-parameters.txt
@@ -3447,6 +3447,19 @@
 			bit 4: print ftrace buffer
 			bit 5: print all printk messages in buffer
 
+	panic_on_taint=	Bitmask for conditionally calling panic() in add_taint()
+			Format: <hex>[,nousertaint]
+			Hexadecimal bitmask representing the set of TAINT flags
+			that will cause the kernel to panic when add_taint() is
+			called with any of the flags in this set.
+			The optional switch "nousertaint" can be utilized to
+			prevent userspace forced crashes by writing to sysctl
+			/proc/sys/kernel/tainted any flagset matching with the
+			bitmask set on panic_on_taint.
+			See Documentation/admin-guide/tainted-kernels.rst for
+			extra details on the taint flags that users can pick
+			to compose the bitmask to assign to panic_on_taint.
+
 	panic_on_warn	panic() instead of WARN().  Useful to cause kdump
 			on a WARN().
 
--- a/Documentation/admin-guide/sysctl/kernel.rst~kernel-add-panic_on_taint
+++ a/Documentation/admin-guide/sysctl/kernel.rst
@@ -1239,6 +1239,13 @@ ORed together. The letters are seen in "
 
 See :doc:`/admin-guide/tainted-kernels` for more information.
 
+Note:
+  writes to this sysctl interface will fail with ``EINVAL`` if the kernel is
+  booted with the command line option ``panic_on_taint=<bitmask>,nousertaint``
+  and any of the ORed together values being written to ``tainted`` match with
+  the bitmask declared on panic_on_taint.
+  See :doc:`/admin-guide/kernel-parameters` for more details on that particular
+  kernel command line option and its optional ``nousertaint`` switch.
 
 threads-max
 ===========
--- a/include/linux/kernel.h~kernel-add-panic_on_taint
+++ a/include/linux/kernel.h
@@ -528,6 +528,8 @@ extern int panic_on_oops;
 extern int panic_on_unrecovered_nmi;
 extern int panic_on_io_nmi;
 extern int panic_on_warn;
+extern unsigned long panic_on_taint;
+extern bool panic_on_taint_nousertaint;
 extern int sysctl_panic_on_rcu_stall;
 extern int sysctl_panic_on_stackoverflow;
 
@@ -596,6 +598,7 @@ extern enum system_states {
 #define TAINT_AUX			16
 #define TAINT_RANDSTRUCT		17
 #define TAINT_FLAGS_COUNT		18
+#define TAINT_FLAGS_MAX			((1UL << TAINT_FLAGS_COUNT) - 1)
 
 struct taint_flag {
 	char c_true;	/* character printed when tainted */
--- a/kernel/panic.c~kernel-add-panic_on_taint
+++ a/kernel/panic.c
@@ -44,6 +44,8 @@ static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
 bool crash_kexec_post_notifiers;
 int panic_on_warn __read_mostly;
+unsigned long panic_on_taint;
+bool panic_on_taint_nousertaint = false;
 
 int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
@@ -434,6 +436,11 @@ void add_taint(unsigned flag, enum lockd
 		pr_warn("Disabling lock debugging due to kernel taint\n");
 
 	set_bit(flag, &tainted_mask);
+
+	if (tainted_mask & panic_on_taint) {
+		panic_on_taint = 0;
+		panic("panic_on_taint set ...");
+	}
 }
 EXPORT_SYMBOL(add_taint);
 
@@ -686,3 +693,30 @@ static int __init oops_setup(char *s)
 	return 0;
 }
 early_param("oops", oops_setup);
+
+static int __init panic_on_taint_setup(char *s)
+{
+	char *taint_str;
+
+	if (!s)
+		return -EINVAL;
+
+	taint_str = strsep(&s, ",");
+	if (kstrtoul(taint_str, 16, &panic_on_taint))
+		return -EINVAL;
+
+	/* make sure panic_on_taint doesn't hold out-of-range TAINT flags */
+	panic_on_taint &= TAINT_FLAGS_MAX;
+
+	if (!panic_on_taint)
+		return -EINVAL;
+
+	if (s && !strcmp(s, "nousertaint"))
+		panic_on_taint_nousertaint = true;
+
+	pr_info("panic_on_taint: bitmask=0x%lx nousertaint_mode=%sabled\n",
+		panic_on_taint, panic_on_taint_nousertaint ? "en" : "dis");
+
+	return 0;
+}
+early_param("panic_on_taint", panic_on_taint_setup);
--- a/kernel/sysctl.c~kernel-add-panic_on_taint
+++ a/kernel/sysctl.c
@@ -866,11 +866,20 @@ static int proc_taint(struct ctl_table *
 		return err;
 
 	if (write) {
+		int i;
+
+		/*
+		 * If we are relying on panic_on_taint not producing
+		 * false positives due to userspace input, bail out
+		 * before setting the requested taint flags.
+		 */
+		if (panic_on_taint_nousertaint && (tmptaint & panic_on_taint))
+			return -EINVAL;
+
 		/*
 		 * Poor man's atomic or. Not worth adding a primitive
 		 * to everyone's atomic.h for this
 		 */
-		int i;
 		for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) {
 			if ((tmptaint >> i) & 1)
 				add_taint(i, LOCKDEP_STILL_OK);
_

[patch 06/54] xarray.h: correct return code documentation for xa_store_{bh,irq}()

[Andrew Morton]

From: Manfred Spraul <manfred@colorfullife.com>
Subject: xarray.h: correct return code documentation for xa_store_{bh,irq}()

__xa_store() and xa_store() document that the functions can fail, and that
the return code can be an xa_err() encoded error code.

xa_store_bh() and xa_store_irq() do not document that the functions can
fail and that they can also return xa_err() encoded error codes.

Thus: Update the documentation.

Link: http://lkml.kernel.org/r/20200430111424.16634-1-manfred@colorfullife.com
Signed-off-by: Manfred Spraul <manfred@colorfullife.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/xarray.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/include/linux/xarray.h~xarrayh-correct-return-code-for-xa_store_bhirq
+++ a/include/linux/xarray.h
@@ -576,7 +576,7 @@ void __xa_clear_mark(struct xarray *, un
  *
  * Context: Any context.  Takes and releases the xa_lock while
  * disabling softirqs.
- * Return: The entry which used to be at this index.
+ * Return: The old entry at this index or xa_err() if an error happened.
  */
 static inline void *xa_store_bh(struct xarray *xa, unsigned long index,
 		void *entry, gfp_t gfp)
@@ -602,7 +602,7 @@ static inline void *xa_store_bh(struct x
  *
  * Context: Process context.  Takes and releases the xa_lock while
  * disabling interrupts.
- * Return: The entry which used to be at this index.
+ * Return: The old entry at this index or xa_err() if an error happened.
  */
 static inline void *xa_store_irq(struct xarray *xa, unsigned long index,
 		void *entry, gfp_t gfp)
_

[patch 07/54] kernel/sysctl: support setting sysctl parameters from kernel command line

[Andrew Morton]

From: Vlastimil Babka <vbabka@suse.cz>
Subject: kernel/sysctl: support setting sysctl parameters from kernel command line

Patch series "support setting sysctl parameters from kernel command line", v3.

This series adds support for something that seems like many people always
wanted but nobody added it yet, so here's the ability to set sysctl
parameters via kernel command line options in the form of
sysctl.vm.something=1

The important part is Patch 1.  The second, not so important part is an
attempt to clean up legacy one-off parameters that do the same thing as a
sysctl.  I don't want to remove them completely for compatibility reasons,
but with generic sysctl support the idea is to remove the one-off param
handlers and treat the parameters as aliases for the sysctl variants.

I have identified several parameters that mention sysctl counterparts in
Documentation/admin-guide/kernel-parameters.txt but there might be more. 
The conversion also has varying level of success:

- numa_zonelist_order is converted in Patch 2 together with adding the
  necessary infrastructure. It's easy as it doesn't really do anything but warn
  on deprecated value these days.
- hung_task_panic is converted in Patch 3, but there's a downside that now it
  only accepts 0 and 1, while previously it was any integer value
- nmi_watchdog maps to two sysctls nmi_watchdog and hardlockup_panic, so
  there's no straighforward conversion possible
- traceoff_on_warning is a flag without value and it would be required to
  handle that somehow in the conversion infractructure, which seems pointless
  for a single flag


This patch (of 5):

A recently proposed patch to add vm_swappiness command line parameter in
addition to existing sysctl [1] made me wonder why we don't have a general
support for passing sysctl parameters via command line.  Googling found
only somebody else wondering the same [2], but I haven't found any prior
discussion with reasons why not to do this.

Settings the vm_swappiness issue aside (the underlying issue might be
solved in a different way), quick search of kernel-parameters.txt shows
there are already some that exist as both sysctl and kernel parameter -
hung_task_panic, nmi_watchdog, numa_zonelist_order, traceoff_on_warning. 
A general mechanism would remove the need to add more of those one-offs
and might be handy in situations where configuration by e.g. 
/etc/sysctl.d/ is impractical.

Hence, this patch adds a new parse_args() pass that looks for parameters
prefixed by 'sysctl.' and tries to interpret them as writes to the
corresponding sys/ files using an temporary in-kernel procfs mount.  This
mechanism was suggested by Eric W.  Biederman [3], as it handles all
dynamically registered sysctl tables, even though we don't handle modular
sysctls.  Errors due to e.g.  invalid parameter name or value are reported
in the kernel log.

The processing is hooked right before the init process is loaded, as some
handlers might be more complicated than simple setters and might need some
subsystems to be initialized.  At the moment the init process can be
started and eventually execute a process writing to /proc/sys/ then it
should be also fine to do that from the kernel.

Sysctls registered later on module load time are not set by this mechanism
- it's expected that in such scenarios, setting sysctl values from
userspace is practical enough.

[1] https://lore.kernel.org/r/BL0PR02MB560167492CA4094C91589930E9FC0@BL0PR02MB5601.namprd02.prod.outlook.com/
[2] https://unix.stackexchange.com/questions/558802/how-to-set-sysctl-using-kernel-command-line-parameter
[3] https://lore.kernel.org/r/87bloj2skm.fsf@x220.int.ebiederm.org/

Link: http://lkml.kernel.org/r/20200427180433.7029-1-vbabka@suse.cz
Link: http://lkml.kernel.org/r/20200427180433.7029-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Ivan Teterevkov <ivan.teterevkov@nutanix.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: "Guilherme G . Piccoli" <gpiccoli@canonical.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/kernel-parameters.txt |    9 +
 fs/proc/proc_sysctl.c                           |  107 ++++++++++++++
 include/linux/sysctl.h                          |    4 
 init/main.c                                     |    2 
 4 files changed, 122 insertions(+)

--- a/Documentation/admin-guide/kernel-parameters.txt~kernel-sysctl-support-setting-sysctl-parameters-from-kernel-command-line
+++ a/Documentation/admin-guide/kernel-parameters.txt
@@ -4969,6 +4969,15 @@
 
 	switches=	[HW,M68k]
 
+	sysctl.*=	[KNL]
+			Set a sysctl parameter, right before loading the init
+			process, as if the value was written to the respective
+			/proc/sys/... file. Both '.' and '/' are recognized as
+			separators. Unrecognized parameters and invalid values
+			are reported in the kernel log. Sysctls registered
+			later by a loaded module cannot be set this way.
+			Example: sysctl.vm.swappiness=40
+
 	sysfs.deprecated=0|1 [KNL]
 			Enable/disable old style sysfs layout for old udev
 			on older distributions. When this option is enabled
--- a/fs/proc/proc_sysctl.c~kernel-sysctl-support-setting-sysctl-parameters-from-kernel-command-line
+++ a/fs/proc/proc_sysctl.c
@@ -14,6 +14,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/bpf-cgroup.h>
+#include <linux/mount.h>
 #include "internal.h"
 
 static const struct dentry_operations proc_sys_dentry_operations;
@@ -1703,3 +1704,109 @@ int __init proc_sys_init(void)
 
 	return sysctl_init();
 }
+
+/* Set sysctl value passed on kernel command line. */
+static int process_sysctl_arg(char *param, char *val,
+			       const char *unused, void *arg)
+{
+	char *path;
+	struct vfsmount **proc_mnt = arg;
+	struct file_system_type *proc_fs_type;
+	struct file *file;
+	int len;
+	int err;
+	loff_t pos = 0;
+	ssize_t wret;
+
+	if (strncmp(param, "sysctl", sizeof("sysctl") - 1))
+		return 0;
+
+	param += sizeof("sysctl") - 1;
+
+	if (param[0] != '/' && param[0] != '.')
+		return 0;
+
+	param++;
+
+	/*
+	 * To set sysctl options, we use a temporary mount of proc, look up the
+	 * respective sys/ file and write to it. To avoid mounting it when no
+	 * options were given, we mount it only when the first sysctl option is
+	 * found. Why not a persistent mount? There are problems with a
+	 * persistent mount of proc in that it forces userspace not to use any
+	 * proc mount options.
+	 */
+	if (!*proc_mnt) {
+		proc_fs_type = get_fs_type("proc");
+		if (!proc_fs_type) {
+			pr_err("Failed to find procfs to set sysctl from command line\n");
+			return 0;
+		}
+		*proc_mnt = kern_mount(proc_fs_type);
+		put_filesystem(proc_fs_type);
+		if (IS_ERR(*proc_mnt)) {
+			pr_err("Failed to mount procfs to set sysctl from command line\n");
+			return 0;
+		}
+	}
+
+	path = kasprintf(GFP_KERNEL, "sys/%s", param);
+	if (!path)
+		panic("%s: Failed to allocate path for %s\n", __func__, param);
+	strreplace(path, '.', '/');
+
+	file = file_open_root((*proc_mnt)->mnt_root, *proc_mnt, path, O_WRONLY, 0);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		if (err == -ENOENT)
+			pr_err("Failed to set sysctl parameter '%s=%s': parameter not found\n",
+				param, val);
+		else if (err == -EACCES)
+			pr_err("Failed to set sysctl parameter '%s=%s': permission denied (read-only?)\n",
+				param, val);
+		else
+			pr_err("Error %pe opening proc file to set sysctl parameter '%s=%s'\n",
+				file, param, val);
+		goto out;
+	}
+	len = strlen(val);
+	wret = kernel_write(file, val, len, &pos);
+	if (wret < 0) {
+		err = wret;
+		if (err == -EINVAL)
+			pr_err("Failed to set sysctl parameter '%s=%s': invalid value\n",
+				param, val);
+		else
+			pr_err("Error %pe writing to proc file to set sysctl parameter '%s=%s'\n",
+				ERR_PTR(err), param, val);
+	} else if (wret != len) {
+		pr_err("Wrote only %zd bytes of %d writing to proc file %s to set sysctl parameter '%s=%s\n",
+			wret, len, path, param, val);
+	}
+
+	err = filp_close(file, NULL);
+	if (err)
+		pr_err("Error %pe closing proc file to set sysctl parameter '%s=%s\n",
+			ERR_PTR(err), param, val);
+out:
+	kfree(path);
+	return 0;
+}
+
+void do_sysctl_args(void)
+{
+	char *command_line;
+	struct vfsmount *proc_mnt = NULL;
+
+	command_line = kstrdup(saved_command_line, GFP_KERNEL);
+	if (!command_line)
+		panic("%s: Failed to allocate copy of command line\n", __func__);
+
+	parse_args("Setting sysctl args", command_line,
+		   NULL, 0, -1, -1, &proc_mnt, process_sysctl_arg);
+
+	if (proc_mnt)
+		kern_unmount(proc_mnt);
+
+	kfree(command_line);
+}
--- a/include/linux/sysctl.h~kernel-sysctl-support-setting-sysctl-parameters-from-kernel-command-line
+++ a/include/linux/sysctl.h
@@ -197,6 +197,7 @@ struct ctl_table_header *register_sysctl
 void unregister_sysctl_table(struct ctl_table_header * table);
 
 extern int sysctl_init(void);
+void do_sysctl_args(void);
 
 extern int pwrsw_enabled;
 extern int unaligned_enabled;
@@ -235,6 +236,9 @@ static inline void setup_sysctl_set(stru
 {
 }
 
+static inline void do_sysctl_args(void)
+{
+}
 #endif /* CONFIG_SYSCTL */
 
 int sysctl_max_threads(struct ctl_table *table, int write, void *buffer,
--- a/init/main.c~kernel-sysctl-support-setting-sysctl-parameters-from-kernel-command-line
+++ a/init/main.c
@@ -1412,6 +1412,8 @@ static int __ref kernel_init(void *unuse
 
 	rcu_end_inkernel_boot();
 
+	do_sysctl_args();
+
 	if (ramdisk_execute_command) {
 		ret = run_init_process(ramdisk_execute_command);
 		if (!ret)
_

[patch 08/54] kernel/sysctl: support handling command line aliases

[Andrew Morton]

From: Vlastimil Babka <vbabka@suse.cz>
Subject: kernel/sysctl: support handling command line aliases

We can now handle sysctl parameters on kernel command line, but
historically some parameters introduced their own command line equivalent,
which we don't want to remove for compatibility reasons.  We can however
convert them to the generic infrastructure with a table translating the
legacy command line parameters to their sysctl names, and removing the
one-off param handlers.

This patch adds the support and makes the first conversion to demonstrate
it, on the (deprecated) numa_zonelist_order parameter.

Link: http://lkml.kernel.org/r/20200427180433.7029-3-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Guilherme G . Piccoli" <gpiccoli@canonical.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Ivan Teterevkov <ivan.teterevkov@nutanix.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/proc/proc_sysctl.c |   48 ++++++++++++++++++++++++++++++++++------
 mm/page_alloc.c       |    9 -------
 2 files changed, 41 insertions(+), 16 deletions(-)

--- a/fs/proc/proc_sysctl.c~kernel-sysctl-support-handling-command-line-aliases
+++ a/fs/proc/proc_sysctl.c
@@ -1705,6 +1705,37 @@ int __init proc_sys_init(void)
 	return sysctl_init();
 }
 
+struct sysctl_alias {
+	const char *kernel_param;
+	const char *sysctl_param;
+};
+
+/*
+ * Historically some settings had both sysctl and a command line parameter.
+ * With the generic sysctl. parameter support, we can handle them at a single
+ * place and only keep the historical name for compatibility. This is not meant
+ * to add brand new aliases. When adding existing aliases, consider whether
+ * the possibly different moment of changing the value (e.g. from early_param
+ * to the moment do_sysctl_args() is called) is an issue for the specific
+ * parameter.
+ */
+static const struct sysctl_alias sysctl_aliases[] = {
+	{"numa_zonelist_order",		"vm.numa_zonelist_order" },
+	{ }
+};
+
+static const char *sysctl_find_alias(char *param)
+{
+	const struct sysctl_alias *alias;
+
+	for (alias = &sysctl_aliases[0]; alias->kernel_param != NULL; alias++) {
+		if (strcmp(alias->kernel_param, param) == 0)
+			return alias->sysctl_param;
+	}
+
+	return NULL;
+}
+
 /* Set sysctl value passed on kernel command line. */
 static int process_sysctl_arg(char *param, char *val,
 			       const char *unused, void *arg)
@@ -1718,15 +1749,18 @@ static int process_sysctl_arg(char *para
 	loff_t pos = 0;
 	ssize_t wret;
 
-	if (strncmp(param, "sysctl", sizeof("sysctl") - 1))
-		return 0;
-
-	param += sizeof("sysctl") - 1;
+	if (strncmp(param, "sysctl", sizeof("sysctl") - 1) == 0) {
+		param += sizeof("sysctl") - 1;
 
-	if (param[0] != '/' && param[0] != '.')
-		return 0;
+		if (param[0] != '/' && param[0] != '.')
+			return 0;
 
-	param++;
+		param++;
+	} else {
+		param = (char *) sysctl_find_alias(param);
+		if (!param)
+			return 0;
+	}
 
 	/*
 	 * To set sysctl options, we use a temporary mount of proc, look up the
--- a/mm/page_alloc.c~kernel-sysctl-support-handling-command-line-aliases
+++ a/mm/page_alloc.c
@@ -5575,15 +5575,6 @@ static int __parse_numa_zonelist_order(c
 	return 0;
 }
 
-static __init int setup_numa_zonelist_order(char *s)
-{
-	if (!s)
-		return 0;
-
-	return __parse_numa_zonelist_order(s);
-}
-early_param("numa_zonelist_order", setup_numa_zonelist_order);
-
 char numa_zonelist_order[] = "Node";
 
 /*
_

[patch 09/54] kernel/hung_task convert hung_task_panic boot parameter to sysctl

[Andrew Morton]

From: Vlastimil Babka <vbabka@suse.cz>
Subject: kernel/hung_task convert hung_task_panic boot parameter to sysctl

We can now handle sysctl parameters on kernel command line and have
infrastructure to convert legacy command line options that duplicate
sysctl to become a sysctl alias.

This patch converts the hung_task_panic parameter.  Note that the sysctl
handler is more strict and allows only 0 and 1, while the legacy parameter
allowed any non-zero value.  But there is little reason anyone would not
be using 1.

Link: http://lkml.kernel.org/r/20200427180433.7029-4-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Guilherme G . Piccoli" <gpiccoli@canonical.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Ivan Teterevkov <ivan.teterevkov@nutanix.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/kernel-parameters.txt |    2 +-
 fs/proc/proc_sysctl.c                           |    1 +
 kernel/hung_task.c                              |   10 ----------
 3 files changed, 2 insertions(+), 11 deletions(-)

--- a/Documentation/admin-guide/kernel-parameters.txt~kernel-hung_task-convert-hung_task_panic-boot-parameter-to-sysctl
+++ a/Documentation/admin-guide/kernel-parameters.txt
@@ -1515,7 +1515,7 @@
 			[KNL] Should the hung task detector generate panics.
 			Format: <integer>
 
-			A nonzero value instructs the kernel to panic when a
+			A value of 1 instructs the kernel to panic when a
 			hung task is detected. The default value is controlled
 			by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time
 			option. The value selected by this boot parameter can
--- a/fs/proc/proc_sysctl.c~kernel-hung_task-convert-hung_task_panic-boot-parameter-to-sysctl
+++ a/fs/proc/proc_sysctl.c
@@ -1721,6 +1721,7 @@ struct sysctl_alias {
  */
 static const struct sysctl_alias sysctl_aliases[] = {
 	{"numa_zonelist_order",		"vm.numa_zonelist_order" },
+	{"hung_task_panic",		"kernel.hung_task_panic" },
 	{ }
 };
 
--- a/kernel/hung_task.c~kernel-hung_task-convert-hung_task_panic-boot-parameter-to-sysctl
+++ a/kernel/hung_task.c
@@ -63,16 +63,6 @@ static struct task_struct *watchdog_task
 unsigned int __read_mostly sysctl_hung_task_panic =
 				CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE;
 
-static int __init hung_task_panic_setup(char *str)
-{
-	int rc = kstrtouint(str, 0, &sysctl_hung_task_panic);
-
-	if (rc)
-		return rc;
-	return 1;
-}
-__setup("hung_task_panic=", hung_task_panic_setup);
-
 static int
 hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr)
 {
_

[patch 10/54] tools/testing/selftests/sysctl/sysctl.sh: support CONFIG_TEST_SYSCTL=y

[Andrew Morton]

From: Vlastimil Babka <vbabka@suse.cz>
Subject: tools/testing/selftests/sysctl/sysctl.sh: support CONFIG_TEST_SYSCTL=y

The testing script recommends CONFIG_TEST_SYSCTL=y, but actually only
works with CONFIG_TEST_SYSCTL=m.  Testing of sysctl setting via boot param
however requires the test to be built-in, so make sure the test script
supports it.

Link: http://lkml.kernel.org/r/20200427180433.7029-5-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Luis Chamberlain <mcgrof@kernel.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Guilherme G . Piccoli" <gpiccoli@canonical.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Ivan Teterevkov <ivan.teterevkov@nutanix.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 tools/testing/selftests/sysctl/sysctl.sh |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/tools/testing/selftests/sysctl/sysctl.sh~tools-testing-selftests-sysctl-sysctlsh-support-config_test_sysctl=y
+++ a/tools/testing/selftests/sysctl/sysctl.sh
@@ -122,7 +122,7 @@ test_reqs()
 
 function load_req_mod()
 {
-	if [ ! -d $DIR ]; then
+	if [ ! -d $SYSCTL ]; then
 		if ! modprobe -q -n $TEST_DRIVER; then
 			echo "$0: module $TEST_DRIVER not found [SKIP]"
 			exit $ksft_skip
_

[patch 11/54] lib/test_sysctl: support testing of sysctl. boot parameter

[Andrew Morton]

From: Vlastimil Babka <vbabka@suse.cz>
Subject: lib/test_sysctl: support testing of sysctl. boot parameter

Testing is done by a new parameter debug.test_sysctl.boot_int which
defaults to 0 and it's expected that the tester passes a boot parameter
that sets it to 1.  The test checks if it's set to 1.  To distinguish true
failure from parameter not being set, the test checks /proc/cmdline for
the expected parameter, and whether test_sysctl is built-in and not a
module.

[vbabka@suse.cz: skip the new test if boot_int sysctl is not present]
  Link: http://lkml.kernel.org/r/305af605-1e60-cf84-fada-6ce1ca37c102@suse.cz
Link: http://lkml.kernel.org/r/20200427180433.7029-6-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Eric W . Biederman" <ebiederm@xmission.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Guilherme G . Piccoli" <gpiccoli@canonical.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Ivan Teterevkov <ivan.teterevkov@nutanix.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 lib/test_sysctl.c                        |   13 ++++++
 tools/testing/selftests/sysctl/sysctl.sh |   42 +++++++++++++++++++++
 2 files changed, 55 insertions(+)

--- a/lib/test_sysctl.c~lib-test_sysctl-support-testing-of-sysctl-boot-parameter
+++ a/lib/test_sysctl.c
@@ -44,6 +44,8 @@ struct test_sysctl_data {
 	int int_0002;
 	int int_0003[4];
 
+	int boot_int;
+
 	unsigned int uint_0001;
 
 	char string_0001[65];
@@ -61,6 +63,8 @@ static struct test_sysctl_data test_data
 	.int_0003[2] = 2,
 	.int_0003[3] = 3,
 
+	.boot_int = 0,
+
 	.uint_0001 = 314,
 
 	.string_0001 = "(none)",
@@ -92,6 +96,15 @@ static struct ctl_table test_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
+		.procname	= "boot_int",
+		.data		= &test_data.boot_int,
+		.maxlen		= sizeof(test_data.boot_int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{
 		.procname	= "uint_0001",
 		.data		= &test_data.uint_0001,
 		.maxlen		= sizeof(unsigned int),
--- a/tools/testing/selftests/sysctl/sysctl.sh~lib-test_sysctl-support-testing-of-sysctl-boot-parameter
+++ a/tools/testing/selftests/sysctl/sysctl.sh
@@ -39,6 +39,7 @@ ALL_TESTS="$ALL_TESTS 0003:1:1:int_0002"
 ALL_TESTS="$ALL_TESTS 0004:1:1:uint_0001"
 ALL_TESTS="$ALL_TESTS 0005:3:1:int_0003"
 ALL_TESTS="$ALL_TESTS 0006:50:1:bitmap_0001"
+ALL_TESTS="$ALL_TESTS 0007:1:1:boot_int"
 
 test_modprobe()
 {
@@ -752,6 +753,46 @@ sysctl_test_0006()
 	run_bitmaptest
 }
 
+sysctl_test_0007()
+{
+	TARGET="${SYSCTL}/boot_int"
+	if [ ! -f $TARGET ]; then
+		echo "Skipping test for $TARGET as it is not present ..."
+		return $ksft_skip
+	fi
+
+	if [ -d $DIR ]; then
+		echo "Boot param test only possible sysctl_test is built-in, not module:"
+		cat $TEST_DIR/config >&2
+		return $ksft_skip
+	fi
+
+	echo -n "Testing if $TARGET is set to 1 ..."
+	ORIG=$(cat "${TARGET}")
+
+	if [ x$ORIG = "x1" ]; then
+		echo "ok"
+		return 0
+	fi
+	echo "FAIL"
+	echo "Checking if /proc/cmdline contains setting of the expected parameter ..."
+	if [ ! -f /proc/cmdline ]; then
+		echo "/proc/cmdline does not exist, test inconclusive"
+		return 0
+	fi
+
+	FOUND=$(grep -c "sysctl[./]debug[./]test_sysctl[./]boot_int=1" /proc/cmdline)
+	if [ $FOUND = "1" ]; then
+		echo "Kernel param found but $TARGET is not 1, TEST FAILED"
+		rc=1
+		test_rc
+	fi
+
+	echo "Skipping test, expected kernel parameter missing."
+	echo "To perform this test, make sure kernel is booted with parameter: sysctl.debug.test_sysctl.boot_int=1"
+	return $ksft_skip
+}
+
 list_tests()
 {
 	echo "Test ID list:"
@@ -766,6 +807,7 @@ list_tests()
 	echo "0004 x $(get_test_count 0004) - tests proc_douintvec()"
 	echo "0005 x $(get_test_count 0005) - tests proc_douintvec() array"
 	echo "0006 x $(get_test_count 0006) - tests proc_do_large_bitmap()"
+	echo "0007 x $(get_test_count 0007) - tests setting sysctl from kernel boot param"
 }
 
 usage()
_

[patch 12/54] kernel/watchdog.c: convert {soft/hard}lockup boot parameters to sysctl aliases

[Andrew Morton]

From: "Guilherme G. Piccoli" <gpiccoli@canonical.com>
Subject: kernel/watchdog.c: convert {soft/hard}lockup boot parameters to sysctl aliases

After a recent change introduced by Vlastimil's series [0], kernel is
able now to handle sysctl parameters on kernel command line; also, the
series introduced a simple infrastructure to convert legacy boot
parameters (that duplicate sysctls) into sysctl aliases.

This patch converts the watchdog parameters softlockup_panic and
{hard,soft}lockup_all_cpu_backtrace to use the new alias infrastructure.
It fixes the documentation too, since the alias only accepts values 0
or 1, not the full range of integers. We also took the opportunity here
to improve the documentation of the previously converted hung_task_panic
(see the patch series [0]) and put the alias table in alphabetical order.

[0] http://lkml.kernel.org/r/20200427180433.7029-1-vbabka@suse.cz

Link: http://lkml.kernel.org/r/20200507214624.21911-1-gpiccoli@canonical.com
Signed-off-by: Guilherme G. Piccoli <gpiccoli@canonical.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/kernel-parameters.txt |   10 +--
 fs/proc/proc_sysctl.c                           |    7 +-
 kernel/watchdog.c                               |   37 +++-----------
 3 files changed, 19 insertions(+), 35 deletions(-)

--- a/Documentation/admin-guide/kernel-parameters.txt~kernel-watchdogc-convert-soft-hardlockup-boot-parameters-to-sysctl-aliases
+++ a/Documentation/admin-guide/kernel-parameters.txt
@@ -1445,7 +1445,7 @@
 	hardlockup_all_cpu_backtrace=
 			[KNL] Should the hard-lockup detector generate
 			backtraces on all cpus.
-			Format: <integer>
+			Format: 0 | 1
 
 	hashdist=	[KNL,NUMA] Large hashes allocated during boot
 			are distributed across NUMA nodes.  Defaults on
@@ -1513,7 +1513,7 @@
 
 	hung_task_panic=
 			[KNL] Should the hung task detector generate panics.
-			Format: <integer>
+			Format: 0 | 1
 
 			A value of 1 instructs the kernel to panic when a
 			hung task is detected. The default value is controlled
@@ -4665,9 +4665,9 @@
 
 	softlockup_panic=
 			[KNL] Should the soft-lockup detector generate panics.
-			Format: <integer>
+			Format: 0 | 1
 
-			A nonzero value instructs the soft-lockup detector
+			A value of 1 instructs the soft-lockup detector
 			to panic the machine when a soft-lockup occurs. It is
 			also controlled by the kernel.softlockup_panic sysctl
 			and CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC, which is the
@@ -4676,7 +4676,7 @@
 	softlockup_all_cpu_backtrace=
 			[KNL] Should the soft-lockup detector generate
 			backtraces on all cpus.
-			Format: <integer>
+			Format: 0 | 1
 
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/admin-guide/laptops/sonypi.rst
--- a/fs/proc/proc_sysctl.c~kernel-watchdogc-convert-soft-hardlockup-boot-parameters-to-sysctl-aliases
+++ a/fs/proc/proc_sysctl.c
@@ -1720,8 +1720,11 @@ struct sysctl_alias {
  * parameter.
  */
 static const struct sysctl_alias sysctl_aliases[] = {
-	{"numa_zonelist_order",		"vm.numa_zonelist_order" },
-	{"hung_task_panic",		"kernel.hung_task_panic" },
+	{"hardlockup_all_cpu_backtrace",	"kernel.hardlockup_all_cpu_backtrace" },
+	{"hung_task_panic",			"kernel.hung_task_panic" },
+	{"numa_zonelist_order",			"vm.numa_zonelist_order" },
+	{"softlockup_all_cpu_backtrace",	"kernel.softlockup_all_cpu_backtrace" },
+	{"softlockup_panic",			"kernel.softlockup_panic" },
 	{ }
 };
 
--- a/kernel/watchdog.c~kernel-watchdogc-convert-soft-hardlockup-boot-parameters-to-sysctl-aliases
+++ a/kernel/watchdog.c
@@ -50,6 +50,11 @@ struct cpumask watchdog_cpumask __read_m
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
+
+# ifdef CONFIG_SMP
+int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
+# endif /* CONFIG_SMP */
+
 /*
  * Should we panic when a soft-lockup or hard-lockup occurs:
  */
@@ -82,16 +87,6 @@ static int __init hardlockup_panic_setup
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
 
-# ifdef CONFIG_SMP
-int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
-
-static int __init hardlockup_all_cpu_backtrace_setup(char *str)
-{
-	sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
-	return 1;
-}
-__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
-# endif /* CONFIG_SMP */
 #endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /*
@@ -163,6 +158,10 @@ static void lockup_detector_update_enabl
 
 #define SOFTLOCKUP_RESET	ULONG_MAX
 
+#ifdef CONFIG_SMP
+int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+#endif
+
 /* Global variables, exported for sysctl */
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
@@ -178,13 +177,6 @@ static DEFINE_PER_CPU(unsigned long, hrt
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
 
-static int __init softlockup_panic_setup(char *str)
-{
-	softlockup_panic = simple_strtoul(str, NULL, 0);
-	return 1;
-}
-__setup("softlockup_panic=", softlockup_panic_setup);
-
 static int __init nowatchdog_setup(char *str)
 {
 	watchdog_user_enabled = 0;
@@ -206,17 +198,6 @@ static int __init watchdog_thresh_setup(
 }
 __setup("watchdog_thresh=", watchdog_thresh_setup);
 
-#ifdef CONFIG_SMP
-int __read_mostly sysctl_softlockup_all_cpu_backtrace;
-
-static int __init softlockup_all_cpu_backtrace_setup(char *str)
-{
-	sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
-	return 1;
-}
-__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
-#endif
-
 static void __lockup_detector_cleanup(void);
 
 /*
_

[patch 13/54] kernel/hung_task.c: introduce sysctl to print all traces when a hung task is detected

[Andrew Morton]

From: "Guilherme G. Piccoli" <gpiccoli@canonical.com>
Subject: kernel/hung_task.c: introduce sysctl to print all traces when a hung task is detected

Commit 401c636a0eeb ("kernel/hung_task.c: show all hung tasks before
panic") introduced a change in that we started to show all CPUs backtraces
when a hung task is detected _and_ the sysctl/kernel parameter
"hung_task_panic" is set.  The idea is good, because usually when
observing deadlocks (that may lead to hung tasks), the culprit is another
task holding a lock and not necessarily the task detected as hung.

The problem with this approach is that dumping backtraces is a slightly
expensive task, specially printing that on console (and specially in many
CPU machines, as servers commonly found nowadays).  So, users that plan to
collect a kdump to investigate the hung tasks and narrow down the deadlock
definitely don't need the CPUs backtrace on dmesg/console, which will
delay the panic and pollute the log (crash tool would easily grab all CPUs
traces with 'bt -a' command).

Also, there's the reciprocal scenario: some users may be interested in
seeing the CPUs backtraces but not have the system panic when a hung task
is detected.  The current approach hence is almost as embedding a policy
in the kernel, by forcing the CPUs backtraces' dump (only) on
hung_task_panic.

This patch decouples the panic event on hung task from the CPUs backtraces
dump, by creating (and documenting) a new sysctl called
"hung_task_all_cpu_backtrace", analog to the approach taken on soft/hard
lockups, that have both a panic and an "all_cpu_backtrace" sysctl to allow
individual control.  The new mechanism for dumping the CPUs backtraces on
hung task detection respects "hung_task_warnings" by not dumping the
traces in case there's no warnings left.

Link: http://lkml.kernel.org/r/20200327223646.20779-1-gpiccoli@canonical.com
Signed-off-by: Guilherme G. Piccoli <gpiccoli@canonical.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/sysctl/kernel.rst |   14 ++++++++++++
 include/linux/sched/sysctl.h                |    7 ++++++
 kernel/hung_task.c                          |   20 ++++++++++++++++--
 kernel/sysctl.c                             |   11 +++++++++
 4 files changed, 50 insertions(+), 2 deletions(-)

--- a/Documentation/admin-guide/sysctl/kernel.rst~kernel-hung_taskc-introduce-sysctl-to-print-all-traces-when-a-hung-task-is-detected
+++ a/Documentation/admin-guide/sysctl/kernel.rst
@@ -335,6 +335,20 @@ Path for the hotplug policy agent.
 Default value is "``/sbin/hotplug``".
 
 
+hung_task_all_cpu_backtrace:
+================
+
+If this option is set, the kernel will send an NMI to all CPUs to dump
+their backtraces when a hung task is detected. This file shows up if
+CONFIG_DETECT_HUNG_TASK and CONFIG_SMP are enabled.
+
+0: Won't show all CPUs backtraces when a hung task is detected.
+This is the default behavior.
+
+1: Will non-maskably interrupt all CPUs and dump their backtraces when
+a hung task is detected.
+
+
 hung_task_panic
 ===============
 
--- a/include/linux/sched/sysctl.h~kernel-hung_taskc-introduce-sysctl-to-print-all-traces-when-a-hung-task-is-detected
+++ a/include/linux/sched/sysctl.h
@@ -7,6 +7,13 @@
 struct ctl_table;
 
 #ifdef CONFIG_DETECT_HUNG_TASK
+
+#ifdef CONFIG_SMP
+extern unsigned int sysctl_hung_task_all_cpu_backtrace;
+#else
+#define sysctl_hung_task_all_cpu_backtrace 0
+#endif /* CONFIG_SMP */
+
 extern int	     sysctl_hung_task_check_count;
 extern unsigned int  sysctl_hung_task_panic;
 extern unsigned long sysctl_hung_task_timeout_secs;
--- a/kernel/hung_task.c~kernel-hung_taskc-introduce-sysctl-to-print-all-traces-when-a-hung-task-is-detected
+++ a/kernel/hung_task.c
@@ -53,9 +53,18 @@ int __read_mostly sysctl_hung_task_warni
 static int __read_mostly did_panic;
 static bool hung_task_show_lock;
 static bool hung_task_call_panic;
+static bool hung_task_show_all_bt;
 
 static struct task_struct *watchdog_task;
 
+#ifdef CONFIG_SMP
+/*
+ * Should we dump all CPUs backtraces in a hung task event?
+ * Defaults to 0, can be changed via sysctl.
+ */
+unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace;
+#endif /* CONFIG_SMP */
+
 /*
  * Should we panic (and reboot, if panic_timeout= is set) when a
  * hung task is detected:
@@ -127,6 +136,9 @@ static void check_hung_task(struct task_
 			" disables this message.\n");
 		sched_show_task(t);
 		hung_task_show_lock = true;
+
+		if (sysctl_hung_task_all_cpu_backtrace)
+			hung_task_show_all_bt = true;
 	}
 
 	touch_nmi_watchdog();
@@ -191,10 +203,14 @@ static void check_hung_uninterruptible_t
 	rcu_read_unlock();
 	if (hung_task_show_lock)
 		debug_show_all_locks();
-	if (hung_task_call_panic) {
+
+	if (hung_task_show_all_bt) {
+		hung_task_show_all_bt = false;
 		trigger_all_cpu_backtrace();
-		panic("hung_task: blocked tasks");
 	}
+
+	if (hung_task_call_panic)
+		panic("hung_task: blocked tasks");
 }
 
 static long hung_timeout_jiffies(unsigned long last_checked,
--- a/kernel/sysctl.c~kernel-hung_taskc-introduce-sysctl-to-print-all-traces-when-a-hung-task-is-detected
+++ a/kernel/sysctl.c
@@ -2437,6 +2437,17 @@ static struct ctl_table kern_table[] = {
 	},
 #endif
 #ifdef CONFIG_DETECT_HUNG_TASK
+#ifdef CONFIG_SMP
+	{
+		.procname	= "hung_task_all_cpu_backtrace",
+		.data		= &sysctl_hung_task_all_cpu_backtrace,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif /* CONFIG_SMP */
 	{
 		.procname	= "hung_task_panic",
 		.data		= &sysctl_hung_task_panic,
_

[patch 14/54] panic: add sysctl to dump all CPUs backtraces on oops event

[Andrew Morton]

From: "Guilherme G. Piccoli" <gpiccoli@canonical.com>
Subject: panic: add sysctl to dump all CPUs backtraces on oops event

Usually when the kernel reaches an oops condition, it's a point of no
return; in case not enough debug information is available in the kernel
splat, one of the last resorts would be to collect a kernel crash dump and
analyze it.  The problem with this approach is that in order to collect
the dump, a panic is required (to kexec-load the crash kernel).  When in
an environment of multiple virtual machines, users may prefer to try
living with the oops, at least until being able to properly shutdown their
VMs / finish their important tasks.

This patch implements a way to collect a bit more debug details when an
oops event is reached, by printing all the CPUs backtraces through the
usage of NMIs (on architectures that support that).  The sysctl added (and
documented) here was called "oops_all_cpu_backtrace", and when set will
(as the name suggests) dump all CPUs backtraces.

Far from ideal, this may be the last option though for users that for some
reason cannot panic on oops.  Most of times oopses are clear enough to
indicate the kernel portion that must be investigated, but in virtual
environments it's possible to observe hypervisor/KVM issues that could
lead to oopses shown in other guests CPUs (like virtual APIC crashes). 
This patch hence aims to help debug such complex issues without resorting
to kdump.

Link: http://lkml.kernel.org/r/20200327224116.21030-1-gpiccoli@canonical.com
Signed-off-by: Guilherme G. Piccoli <gpiccoli@canonical.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/sysctl/kernel.rst |   16 ++++++++++++++++
 include/linux/kernel.h                      |    6 ++++++
 kernel/panic.c                              |   11 +++++++++++
 kernel/sysctl.c                             |   11 +++++++++++
 4 files changed, 44 insertions(+)

--- a/Documentation/admin-guide/sysctl/kernel.rst~panic-add-sysctl-to-dump-all-cpus-backtraces-on-oops-event
+++ a/Documentation/admin-guide/sysctl/kernel.rst
@@ -646,6 +646,22 @@ rate for each task.
 scanned for a given scan.
 
 
+oops_all_cpu_backtrace:
+================
+
+If this option is set, the kernel will send an NMI to all CPUs to dump
+their backtraces when an oops event occurs. It should be used as a last
+resort in case a panic cannot be triggered (to protect VMs running, for
+example) or kdump can't be collected. This file shows up if CONFIG_SMP
+is enabled.
+
+0: Won't show all CPUs backtraces when an oops is detected.
+This is the default behavior.
+
+1: Will non-maskably interrupt all CPUs and dump their backtraces when
+an oops event is detected.
+
+
 osrelease, ostype & version
 ===========================
 
--- a/include/linux/kernel.h~panic-add-sysctl-to-dump-all-cpus-backtraces-on-oops-event
+++ a/include/linux/kernel.h
@@ -520,6 +520,12 @@ static inline u32 int_sqrt64(u64 x)
 }
 #endif
 
+#ifdef CONFIG_SMP
+extern unsigned int sysctl_oops_all_cpu_backtrace;
+#else
+#define sysctl_oops_all_cpu_backtrace 0
+#endif /* CONFIG_SMP */
+
 extern void bust_spinlocks(int yes);
 extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in progress */
 extern int panic_timeout;
--- a/kernel/panic.c~panic-add-sysctl-to-dump-all-cpus-backtraces-on-oops-event
+++ a/kernel/panic.c
@@ -36,6 +36,14 @@
 #define PANIC_TIMER_STEP 100
 #define PANIC_BLINK_SPD 18
 
+#ifdef CONFIG_SMP
+/*
+ * Should we dump all CPUs backtraces in an oops event?
+ * Defaults to 0, can be changed via sysctl.
+ */
+unsigned int __read_mostly sysctl_oops_all_cpu_backtrace;
+#endif /* CONFIG_SMP */
+
 int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
 static unsigned long tainted_mask =
 	IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0;
@@ -522,6 +530,9 @@ void oops_enter(void)
 	/* can't trust the integrity of the kernel anymore: */
 	debug_locks_off();
 	do_oops_enter_exit();
+
+	if (sysctl_oops_all_cpu_backtrace)
+		trigger_all_cpu_backtrace();
 }
 
 /*
--- a/kernel/sysctl.c~panic-add-sysctl-to-dump-all-cpus-backtraces-on-oops-event
+++ a/kernel/sysctl.c
@@ -2150,6 +2150,17 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_SMP
+	{
+		.procname	= "oops_all_cpu_backtrace",
+		.data		= &sysctl_oops_all_cpu_backtrace,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+#endif /* CONFIG_SMP */
 	{
 		.procname	= "pid_max",
 		.data		= &pid_max,
_

[patch 15/54] kernel/sysctl.c: ignore out-of-range taint bits introduced via kernel.tainted

[Andrew Morton]

From: Rafael Aquini <aquini@redhat.com>
Subject: kernel/sysctl.c: ignore out-of-range taint bits introduced via kernel.tainted

Users with SYS_ADMIN capability can add arbitrary taint flags to the
running kernel by writing to /proc/sys/kernel/tainted or issuing the
command 'sysctl -w kernel.tainted=...'.  This interface, however, is open
for any integer value and this might cause an invalid set of flags being
committed to the tainted_mask bitset.

This patch introduces a simple way for proc_taint() to ignore any eventual
invalid bit coming from the user input before committing those bits to the
kernel tainted_mask.

Link: http://lkml.kernel.org/r/20200512223946.888020-1-aquini@redhat.com
Signed-off-by: Rafael Aquini <aquini@redhat.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 kernel/sysctl.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/kernel/sysctl.c~kernel-sysctl-ignore-out-of-range-taint-bits-introduced-via-kerneltainted
+++ a/kernel/sysctl.c
@@ -880,10 +880,9 @@ static int proc_taint(struct ctl_table *
 		 * Poor man's atomic or. Not worth adding a primitive
 		 * to everyone's atomic.h for this
 		 */
-		for (i = 0; i < BITS_PER_LONG && tmptaint >> i; i++) {
-			if ((tmptaint >> i) & 1)
+		for (i = 0; i < TAINT_FLAGS_COUNT; i++)
+			if ((1UL << i) & tmptaint)
 				add_taint(i, LOCKDEP_STILL_OK);
-		}
 	}
 
 	return err;
_

[patch 16/54] mm/gup.c: convert to use get_user_{page|pages}_fast_only()

[Andrew Morton]

From: Souptick Joarder <jrdr.linux@gmail.com>
Subject: mm/gup.c: convert to use get_user_{page|pages}_fast_only()

API __get_user_pages_fast() renamed to get_user_pages_fast_only() to align
with pin_user_pages_fast_only().

As part of this we will get rid of write parameter.  Instead caller will
pass FOLL_WRITE to get_user_pages_fast_only().  This will not change any
existing functionality of the API.

All the callers are changed to pass FOLL_WRITE.

Also introduce get_user_page_fast_only(), and use it in a few places that
hard-code nr_pages to 1.

Updated the documentation of the API.

Link: http://lkml.kernel.org/r/1590396812-31277-1-git-send-email-jrdr.linux@gmail.com
Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Paul Mackerras <paulus@ozlabs.org>		[arch/powerpc/kvm]
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Michal Suchanek <msuchanek@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/powerpc/kvm/book3s_64_mmu_hv.c    |    2 -
 arch/powerpc/kvm/book3s_64_mmu_radix.c |    2 -
 arch/powerpc/perf/callchain_64.c       |    4 ---
 include/linux/mm.h                     |   10 ++++++-
 kernel/events/core.c                   |    4 +--
 mm/gup.c                               |   29 ++++++++++++-----------
 virt/kvm/kvm_main.c                    |    8 ++----
 7 files changed, 32 insertions(+), 27 deletions(-)

--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c~mm-gupc-convert-to-use-get_user_pagepages_fast_only
+++ a/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -581,7 +581,7 @@ int kvmppc_book3s_hv_page_fault(struct k
 	 * We always ask for write permission since the common case
 	 * is that the page is writable.
 	 */
-	if (__get_user_pages_fast(hva, 1, 1, &page) == 1) {
+	if (get_user_page_fast_only(hva, FOLL_WRITE, &page)) {
 		write_ok = true;
 	} else {
 		/* Call KVM generic code to do the slow-path check */
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c~mm-gupc-convert-to-use-get_user_pagepages_fast_only
+++ a/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -795,7 +795,7 @@ int kvmppc_book3s_instantiate_page(struc
 	 * is that the page is writable.
 	 */
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	if (!kvm_ro && __get_user_pages_fast(hva, 1, 1, &page) == 1) {
+	if (!kvm_ro && get_user_page_fast_only(hva, FOLL_WRITE, &page)) {
 		upgrade_write = true;
 	} else {
 		unsigned long pfn;
--- a/arch/powerpc/perf/callchain_64.c~mm-gupc-convert-to-use-get_user_pagepages_fast_only
+++ a/arch/powerpc/perf/callchain_64.c
@@ -30,11 +30,9 @@ int read_user_stack_slow(void __user *pt
 	unsigned long addr = (unsigned long) ptr;
 	unsigned long offset;
 	struct page *page;
-	int nrpages;
 	void *kaddr;
 
-	nrpages = __get_user_pages_fast(addr, 1, 1, &page);
-	if (nrpages == 1) {
+	if (get_user_page_fast_only(addr, FOLL_WRITE, &page)) {
 		kaddr = page_address(page);
 
 		/* align address to page boundary */
--- a/include/linux/mm.h~mm-gupc-convert-to-use-get_user_pagepages_fast_only
+++ a/include/linux/mm.h
@@ -1824,10 +1824,16 @@ extern int mprotect_fixup(struct vm_area
 /*
  * doesn't attempt to fault and will return short.
  */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages);
+int get_user_pages_fast_only(unsigned long start, int nr_pages,
+			     unsigned int gup_flags, struct page **pages);
 int pin_user_pages_fast_only(unsigned long start, int nr_pages,
 			     unsigned int gup_flags, struct page **pages);
+
+static inline bool get_user_page_fast_only(unsigned long addr,
+			unsigned int gup_flags, struct page **pagep)
+{
+	return get_user_pages_fast_only(addr, 1, gup_flags, pagep) == 1;
+}
 /*
  * per-process(per-mm_struct) statistics.
  */
--- a/kernel/events/core.c~mm-gupc-convert-to-use-get_user_pagepages_fast_only
+++ a/kernel/events/core.c
@@ -6934,12 +6934,12 @@ static u64 perf_virt_to_phys(u64 virt)
 		 * Walking the pages tables for user address.
 		 * Interrupts are disabled, so it prevents any tear down
 		 * of the page tables.
-		 * Try IRQ-safe __get_user_pages_fast first.
+		 * Try IRQ-safe get_user_page_fast_only first.
 		 * If failed, leave phys_addr as 0.
 		 */
 		if (current->mm != NULL) {
 			pagefault_disable();
-			if (__get_user_pages_fast(virt, 1, 0, &p) == 1)
+			if (get_user_page_fast_only(virt, 0, &p))
 				phys_addr = page_to_phys(p) + virt % PAGE_SIZE;
 			pagefault_enable();
 		}
--- a/mm/gup.c~mm-gupc-convert-to-use-get_user_pagepages_fast_only
+++ a/mm/gup.c
@@ -2294,7 +2294,7 @@ pte_unmap:
  * to be special.
  *
  * For a futex to be placed on a THP tail page, get_futex_key requires a
- * __get_user_pages_fast implementation that can pin pages. Thus it's still
+ * get_user_pages_fast_only implementation that can pin pages. Thus it's still
  * useful to have gup_huge_pmd even if we can't operate on ptes.
  */
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
@@ -2699,7 +2699,7 @@ static inline void gup_pgd_range(unsigne
 
 #ifndef gup_fast_permitted
 /*
- * Check if it's allowed to use __get_user_pages_fast() for the range, or
+ * Check if it's allowed to use get_user_pages_fast_only() for the range, or
  * we need to fall back to the slow version:
  */
 static bool gup_fast_permitted(unsigned long start, unsigned long end)
@@ -2811,8 +2811,14 @@ static int internal_get_user_pages_fast(
 
 	return ret;
 }
-
-/*
+/**
+ * get_user_pages_fast_only() - pin user pages in memory
+ * @start:      starting user address
+ * @nr_pages:   number of pages from start to pin
+ * @gup_flags:  flags modifying pin behaviour
+ * @pages:      array that receives pointers to the pages pinned.
+ *              Should be at least nr_pages long.
+ *
  * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to
  * the regular GUP.
  * Note a difference with get_user_pages_fast: this always returns the
@@ -2825,8 +2831,8 @@ static int internal_get_user_pages_fast(
  * access can get ambiguous page results. If you call this function without
  * 'write' set, you'd better be sure that you're ok with that ambiguity.
  */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages)
+int get_user_pages_fast_only(unsigned long start, int nr_pages,
+			     unsigned int gup_flags, struct page **pages)
 {
 	int nr_pinned;
 	/*
@@ -2836,10 +2842,7 @@ int __get_user_pages_fast(unsigned long
 	 * FOLL_FAST_ONLY is required in order to match the API description of
 	 * this routine: no fall back to regular ("slow") GUP.
 	 */
-	unsigned int gup_flags = FOLL_GET | FOLL_FAST_ONLY;
-
-	if (write)
-		gup_flags |= FOLL_WRITE;
+	gup_flags |= FOLL_GET | FOLL_FAST_ONLY;
 
 	nr_pinned = internal_get_user_pages_fast(start, nr_pages, gup_flags,
 						 pages);
@@ -2855,7 +2858,7 @@ int __get_user_pages_fast(unsigned long
 
 	return nr_pinned;
 }
-EXPORT_SYMBOL_GPL(__get_user_pages_fast);
+EXPORT_SYMBOL_GPL(get_user_pages_fast_only);
 
 /**
  * get_user_pages_fast() - pin user pages in memory
@@ -2926,8 +2929,8 @@ int pin_user_pages_fast(unsigned long st
 EXPORT_SYMBOL_GPL(pin_user_pages_fast);
 
 /*
- * This is the FOLL_PIN equivalent of __get_user_pages_fast(). Behavior is the
- * same, except that this one sets FOLL_PIN instead of FOLL_GET.
+ * This is the FOLL_PIN equivalent of get_user_pages_fast_only(). Behavior
+ * is the same, except that this one sets FOLL_PIN instead of FOLL_GET.
  *
  * The API rules are the same, too: no negative values may be returned.
  */
--- a/virt/kvm/kvm_main.c~mm-gupc-convert-to-use-get_user_pagepages_fast_only
+++ a/virt/kvm/kvm_main.c
@@ -1740,7 +1740,6 @@ static bool hva_to_pfn_fast(unsigned lon
 			    bool *writable, kvm_pfn_t *pfn)
 {
 	struct page *page[1];
-	int npages;
 
 	/*
 	 * Fast pin a writable pfn only if it is a write fault request
@@ -1750,8 +1749,7 @@ static bool hva_to_pfn_fast(unsigned lon
 	if (!(write_fault || writable))
 		return false;
 
-	npages = __get_user_pages_fast(addr, 1, 1, page);
-	if (npages == 1) {
+	if (get_user_page_fast_only(addr, FOLL_WRITE, page)) {
 		*pfn = page_to_pfn(page[0]);
 
 		if (writable)
@@ -1791,7 +1789,7 @@ static int hva_to_pfn_slow(unsigned long
 	if (unlikely(!write_fault) && writable) {
 		struct page *wpage;
 
-		if (__get_user_pages_fast(addr, 1, 1, &wpage) == 1) {
+		if (get_user_page_fast_only(addr, FOLL_WRITE, &wpage)) {
 			*writable = true;
 			put_page(page);
 			page = wpage;
@@ -2003,7 +2001,7 @@ int gfn_to_page_many_atomic(struct kvm_m
 	if (entry < nr_pages)
 		return 0;
 
-	return __get_user_pages_fast(addr, nr_pages, 1, pages);
+	return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages);
 }
 EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
 
_

[patch 17/54] mm/gup: update pin_user_pages.rst for "case 3" (mmu notifiers)

[Andrew Morton]

From: John Hubbard <jhubbard@nvidia.com>
Subject: mm/gup: update pin_user_pages.rst for "case 3" (mmu notifiers)

Update case 3 so that it covers the use of mmu notifiers, for hardware
that does, or does not have replayable page faults.

Also, elaborate case 4 slightly, as it was quite cryptic.

Link: http://lkml.kernel.org/r/20200527194953.11130-1-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/core-api/pin_user_pages.rst |   29 +++++++++++---------
 1 file changed, 17 insertions(+), 12 deletions(-)

--- a/Documentation/core-api/pin_user_pages.rst~mm-gup-update-pin_user_pagesrst-for-case-3-mmu-notifiers
+++ a/Documentation/core-api/pin_user_pages.rst
@@ -148,23 +148,28 @@ NOTE: Some pages, such as DAX pages, can
 because DAX pages do not have a separate page cache, and so "pinning" implies
 locking down file system blocks, which is not (yet) supported in that way.
 
-CASE 3: Hardware with page faulting support
--------------------------------------------
-Here, a well-written driver doesn't normally need to pin pages at all. However,
-if the driver does choose to do so, it can register MMU notifiers for the range,
-and will be called back upon invalidation. Either way (avoiding page pinning, or
-using MMU notifiers to unpin upon request), there is proper synchronization with
-both filesystem and mm (page_mkclean(), munmap(), etc).
+CASE 3: MMU notifier registration, with or without page faulting hardware
+-------------------------------------------------------------------------
+Device drivers can pin pages via get_user_pages*(), and register for mmu
+notifier callbacks for the memory range. Then, upon receiving a notifier
+"invalidate range" callback , stop the device from using the range, and unpin
+the pages. There may be other possible schemes, such as for example explicitly
+synchronizing against pending IO, that accomplish approximately the same thing.
 
-Therefore, neither flag needs to be set.
+Or, if the hardware supports replayable page faults, then the device driver can
+avoid pinning entirely (this is ideal), as follows: register for mmu notifier
+callbacks as above, but instead of stopping the device and unpinning in the
+callback, simply remove the range from the device's page tables.
 
-In this case, ideally, neither get_user_pages() nor pin_user_pages() should be
-called. Instead, the software should be written so that it does not pin pages.
-This allows mm and filesystems to operate more efficiently and reliably.
+Either way, as long as the driver unpins the pages upon mmu notifier callback,
+then there is proper synchronization with both filesystem and mm
+(page_mkclean(), munmap(), etc). Therefore, neither flag needs to be set.
 
 CASE 4: Pinning for struct page manipulation only
 -------------------------------------------------
-Here, normal GUP calls are sufficient, so neither flag needs to be set.
+If only struct page data (as opposed to the actual memory contents that a page
+is tracking) is affected, then normal GUP calls are sufficient, and neither flag
+needs to be set.
 
 page_maybe_dma_pinned(): the whole point of pinning
 ===================================================
_

[patch 18/54] mm/gup: introduce pin_user_pages_locked()

[Andrew Morton]

From: John Hubbard <jhubbard@nvidia.com>
Subject: mm/gup: introduce pin_user_pages_locked()

Patch series "mm/gup: introduce pin_user_pages_locked(), use it in frame_vector.c", v2.

This adds yet one more pin_user_pages*() variant, and uses that to convert
mm/frame_vector.c.

With this, along with maybe 20 or 30 other recent patches in various
trees, we are close to having the relevant gup call sites converted--with
the notable exception of the bio/block layer.


This patch (of 2):

Introduce pin_user_pages_locked(), which is nearly identical to
get_user_pages_locked() except that it sets FOLL_PIN and rejects FOLL_GET.

As with other pairs of get_user_pages*() and pin_user_pages() API calls,
it's prudent to assert that FOLL_PIN is *not* set in the get_user_pages*()
call, so add that as part of this.

[jhubbard@nvidia.com: v2]
  Link: http://lkml.kernel.org/r/20200531234131.770697-2-jhubbard@nvidia.com
Link: http://lkml.kernel.org/r/20200531234131.770697-1-jhubbard@nvidia.com
Link: http://lkml.kernel.org/r/20200527223243.884385-1-jhubbard@nvidia.com
Link: http://lkml.kernel.org/r/20200527223243.884385-2-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Souptick Joarder <jrdr.linux@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/mm.h |    2 ++
 mm/gup.c           |   36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

--- a/include/linux/mm.h~mm-gup-introduce-pin_user_pages_locked
+++ a/include/linux/mm.h
@@ -1706,6 +1706,8 @@ long pin_user_pages(unsigned long start,
 		    struct vm_area_struct **vmas);
 long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
 		    unsigned int gup_flags, struct page **pages, int *locked);
+long pin_user_pages_locked(unsigned long start, unsigned long nr_pages,
+		    unsigned int gup_flags, struct page **pages, int *locked);
 long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
 long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
--- a/mm/gup.c~mm-gup-introduce-pin_user_pages_locked
+++ a/mm/gup.c
@@ -2035,6 +2035,12 @@ long get_user_pages_locked(unsigned long
 	 */
 	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
 		return -EINVAL;
+	/*
+	 * FOLL_PIN must only be set internally by the pin_user_pages*() APIs,
+	 * never directly by the caller, so enforce that:
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_PIN))
+		return -EINVAL;
 
 	return __get_user_pages_locked(current, current->mm, start, nr_pages,
 				       pages, NULL, locked,
@@ -3058,3 +3064,33 @@ long pin_user_pages_unlocked(unsigned lo
 	return get_user_pages_unlocked(start, nr_pages, pages, gup_flags);
 }
 EXPORT_SYMBOL(pin_user_pages_unlocked);
+
+/*
+ * pin_user_pages_locked() is the FOLL_PIN variant of get_user_pages_locked().
+ * Behavior is the same, except that this one sets FOLL_PIN and rejects
+ * FOLL_GET.
+ */
+long pin_user_pages_locked(unsigned long start, unsigned long nr_pages,
+			   unsigned int gup_flags, struct page **pages,
+			   int *locked)
+{
+	/*
+	 * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+	 * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+	 * vmas.  As there are no users of this flag in this call we simply
+	 * disallow this option for now.
+	 */
+	if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+		return -EINVAL;
+
+	/* FOLL_GET and FOLL_PIN are mutually exclusive. */
+	if (WARN_ON_ONCE(gup_flags & FOLL_GET))
+		return -EINVAL;
+
+	gup_flags |= FOLL_PIN;
+	return __get_user_pages_locked(current, current->mm, start, nr_pages,
+				       pages, NULL, locked,
+				       gup_flags | FOLL_TOUCH);
+}
+EXPORT_SYMBOL(pin_user_pages_locked);
+
_

[patch 19/54] mm/gup: frame_vector: convert get_user_pages() --> pin_user_pages()

[Andrew Morton]

From: John Hubbard <jhubbard@nvidia.com>
Subject: mm/gup: frame_vector: convert get_user_pages() --> pin_user_pages()

This code was using get_user_pages*(), and all of the callers so far were
in a "Case 2" scenario (DMA/RDMA), using the categorization from [1]. 
That means that it's time to convert the get_user_pages*() + put_page()
calls to pin_user_pages*() + unpin_user_pages() calls.

There is some helpful background in [2]: basically, this is a small part
of fixing a long-standing disconnect between pinning pages, and file
systems' use of those pages.

[1] Documentation/core-api/pin_user_pages.rst

[2] "Explicit pinning of user-space pages":
    https://lwn.net/Articles/807108/

Link: http://lkml.kernel.org/r/20200527223243.884385-3-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Souptick Joarder <jrdr.linux@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/frame_vector.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

--- a/mm/frame_vector.c~mm-gup-frame_vector-convert-get_user_pages-pin_user_pages
+++ a/mm/frame_vector.c
@@ -72,7 +72,7 @@ int get_vaddr_frames(unsigned long start
 	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) {
 		vec->got_ref = true;
 		vec->is_pfns = false;
-		ret = get_user_pages_locked(start, nr_frames,
+		ret = pin_user_pages_locked(start, nr_frames,
 			gup_flags, (struct page **)(vec->ptrs), &locked);
 		goto out;
 	}
@@ -122,7 +122,6 @@ EXPORT_SYMBOL(get_vaddr_frames);
  */
 void put_vaddr_frames(struct frame_vector *vec)
 {
-	int i;
 	struct page **pages;
 
 	if (!vec->got_ref)
@@ -135,8 +134,8 @@ void put_vaddr_frames(struct frame_vecto
 	 */
 	if (WARN_ON(IS_ERR(pages)))
 		goto out;
-	for (i = 0; i < vec->nr_frames; i++)
-		put_page(pages[i]);
+
+	unpin_user_pages(pages, vec->nr_frames);
 	vec->got_ref = false;
 out:
 	vec->nr_frames = 0;
_

[patch 20/54] mm/gup: documentation fix for pin_user_pages*() APIs

[Andrew Morton]

From: John Hubbard <jhubbard@nvidia.com>
Subject: mm/gup: documentation fix for pin_user_pages*() APIs

All of the pin_user_pages*() API calls will cause pages to be dma-pinned. 
As such, they are all suitable for either DMA, RDMA, and/or Direct IO. 
The documentation should say so, but it was instead saying that three of
the API calls were only suitable for Direct IO.  This was discovered when
a reviewer wondered why an API call that specifically recommended against
Case 2 (DMA/RDMA) was being used in a DMA situation [1].

Fix this by simply deleting those claims.  The gup.c comments already
refer to the more extensive Documentation/core-api/pin_user_pages.rst,
which does have the correct guidance.  So let's just write it once, there.

[1] https://lore.kernel.org/r/20200529074658.GM30374@kadam

Link: http://lkml.kernel.org/r/20200529084515.46259-1-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Acked-by: Souptick Joarder <jrdr.linux@gmail.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/gup.c |    9 ---------
 1 file changed, 9 deletions(-)

--- a/mm/gup.c~mm-gup-documentation-fix-for-pin_user_pages-apis
+++ a/mm/gup.c
@@ -2918,9 +2918,6 @@ EXPORT_SYMBOL_GPL(get_user_pages_fast);
  *
  * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
  * see Documentation/core-api/pin_user_pages.rst for further details.
- *
- * This is intended for Case 1 (DIO) in Documentation/core-api/pin_user_pages.rst. It
- * is NOT intended for Case 2 (RDMA: long-term pins).
  */
 int pin_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages)
@@ -2994,9 +2991,6 @@ EXPORT_SYMBOL_GPL(pin_user_pages_fast_on
  *
  * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
  * see Documentation/core-api/pin_user_pages.rst for details.
- *
- * This is intended for Case 1 (DIO) in Documentation/core-api/pin_user_pages.rst. It
- * is NOT intended for Case 2 (RDMA: long-term pins).
  */
 long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
@@ -3030,9 +3024,6 @@ EXPORT_SYMBOL(pin_user_pages_remote);
  *
  * FOLL_PIN means that the pages must be released via unpin_user_page(). Please
  * see Documentation/core-api/pin_user_pages.rst for details.
- *
- * This is intended for Case 1 (DIO) in Documentation/core-api/pin_user_pages.rst. It
- * is NOT intended for Case 2 (RDMA: long-term pins).
  */
 long pin_user_pages(unsigned long start, unsigned long nr_pages,
 		    unsigned int gup_flags, struct page **pages,
_

[patch 21/54] docs: mm/gup: pin_user_pages.rst: add a "case 5"

[Andrew Morton]

From: John Hubbard <jhubbard@nvidia.com>
Subject: docs: mm/gup: pin_user_pages.rst: add a "case 5"

Patch series "vhost, docs: convert to pin_user_pages(), new "case 5""

It recently became clear to me that there are some get_user_pages*()
callers that don't fit neatly into any of the four cases that are so far
listed in pin_user_pages.rst.  vhost.c is one of those.

Add a Case 5 to the documentation, and refer to that when converting
vhost.c.

Thanks to Jan Kara for helping me (again) in understanding the interaction
between get_user_pages() and page writeback [1].

This is based on today's mmotm, which has a nearby patch to
pin_user_pages.rst that rewords cases 3 and 4.

Note that I have only compile-tested the vhost.c patch, although that does
also include cross-compiling for a few other arches.  Any run-time testing
would be greatly appreciated.

[1] https://lore.kernel.org/r/20200529070343.GL14550@quack2.suse.cz


This patch (of 2):

There are four cases listed in pin_user_pages.rst.  These are intended to
help developers figure out whether to use get_user_pages*(), or
pin_user_pages*().  However, the four cases do not cover all the
situations.  For example, drivers/vhost/vhost.c has a "pin, write to page,
set page dirty, unpin" case.

Add a fifth case, to help explain that there is a general pattern that
requires pin_user_pages*() API calls.

[jhubbard@nvidia.com: v2]
  Link: http://lkml.kernel.org/r/20200601052633.853874-2-jhubbard@nvidia.com
Link: http://lkml.kernel.org/r/20200529234309.484480-1-jhubbard@nvidia.com
Link: http://lkml.kernel.org/r/20200529234309.484480-2-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.cz>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Souptick Joarder <jrdr.linux@gmail.com>
Cc: "Michael S . Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/core-api/pin_user_pages.rst |   18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

--- a/Documentation/core-api/pin_user_pages.rst~docs-mm-gup-pin_user_pagesrst-add-a-case-5
+++ a/Documentation/core-api/pin_user_pages.rst
@@ -171,6 +171,24 @@ If only struct page data (as opposed to
 is tracking) is affected, then normal GUP calls are sufficient, and neither flag
 needs to be set.
 
+CASE 5: Pinning in order to write to the data within the page
+-------------------------------------------------------------
+Even though neither DMA nor Direct IO is involved, just a simple case of "pin,
+write to a page's data, unpin" can cause a problem. Case 5 may be considered a
+superset of Case 1, plus Case 2, plus anything that invokes that pattern. In
+other words, if the code is neither Case 1 nor Case 2, it may still require
+FOLL_PIN, for patterns like this:
+
+Correct (uses FOLL_PIN calls):
+    pin_user_pages()
+    write to the data within the pages
+    unpin_user_pages()
+
+INCORRECT (uses FOLL_GET calls):
+    get_user_pages()
+    write to the data within the pages
+    put_page()
+
 page_maybe_dma_pinned(): the whole point of pinning
 ===================================================
 
_

[patch 22/54] vhost: convert get_user_pages() --> pin_user_pages()

[Andrew Morton]

From: John Hubbard <jhubbard@nvidia.com>
Subject: vhost: convert get_user_pages() --> pin_user_pages()

This code was using get_user_pages*(), in approximately a "Case 5"
scenario (accessing the data within a page), using the categorization from
[1].  That means that it's time to convert the get_user_pages*() +
put_page() calls to pin_user_pages*() + unpin_user_pages() calls.

There is some helpful background in [2]: basically, this is a small part
of fixing a long-standing disconnect between pinning pages, and file
systems' use of those pages.

[1] Documentation/core-api/pin_user_pages.rst

[2] "Explicit pinning of user-space pages":
    https://lwn.net/Articles/807108/

Link: http://lkml.kernel.org/r/20200529234309.484480-3-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Souptick Joarder <jrdr.linux@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 drivers/vhost/vhost.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/drivers/vhost/vhost.c~vhost-convert-get_user_pages-pin_user_pages
+++ a/drivers/vhost/vhost.c
@@ -1762,15 +1762,14 @@ static int set_bit_to_user(int nr, void
 	int bit = nr + (log % PAGE_SIZE) * 8;
 	int r;
 
-	r = get_user_pages_fast(log, 1, FOLL_WRITE, &page);
+	r = pin_user_pages_fast(log, 1, FOLL_WRITE, &page);
 	if (r < 0)
 		return r;
 	BUG_ON(r != 1);
 	base = kmap_atomic(page);
 	set_bit(bit, base);
 	kunmap_atomic(base);
-	set_page_dirty_lock(page);
-	put_page(page);
+	unpin_user_pages_dirty_lock(&page, 1, true);
 	return 0;
 }
 
_

[patch 23/54] mm/mmap.c: add more sanity checks to get_unmapped_area()

[Andrew Morton]

From: Alexander Gordeev <agordeev@linux.ibm.com>
Subject: mm/mmap.c: add more sanity checks to get_unmapped_area()

Generic get_unmapped_area() function does sanity checks of address and
length of the area to be mapped.  Yet, it lacks checking against
mmap_min_addr and mmap_end limits.

At the same time the default implementation of functions
arch_get_unmapped_area[_topdown]() and some architecture callbacks do
mmap_min_addr and mmap_end checks on their own.

Put additional checks into the generic code and do not let architecture
callbacks to get away with a possible area outside of the allowed limits.

That could also relieve arch_get_unmapped_area[_topdown]() callbacks of
own address and length sanity checks.

Link: http://lkml.kernel.org/r/d14f2cff3c891ef2c4b0337d737c6f04beacb124.1584958099.git.agordeev@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/mmap.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/mm/mmap.c~mm-mmapc-add-more-sanity-checks-to-get_unmapped_area
+++ a/mm/mmap.c
@@ -2193,12 +2193,13 @@ get_unmapped_area(struct file *file, uns
 	unsigned long (*get_area)(struct file *, unsigned long,
 				  unsigned long, unsigned long, unsigned long);
 
+	const unsigned long mmap_end = arch_get_mmap_end(addr);
 	unsigned long error = arch_mmap_check(addr, len, flags);
 	if (error)
 		return error;
 
 	/* Careful about overflows.. */
-	if (len > TASK_SIZE)
+	if (len > mmap_end - mmap_min_addr)
 		return -ENOMEM;
 
 	get_area = current->mm->get_unmapped_area;
@@ -2219,7 +2220,7 @@ get_unmapped_area(struct file *file, uns
 	if (IS_ERR_VALUE(addr))
 		return addr;
 
-	if (addr > TASK_SIZE - len)
+	if ((addr < mmap_min_addr) || (addr > mmap_end - len))
 		return -ENOMEM;
 	if (offset_in_page(addr))
 		return -EINVAL;
_

[patch 24/54] mm/mmap.c: do not allow mappings outside of allowed limits

[Andrew Morton]

From: Alexander Gordeev <agordeev@linux.ibm.com>
Subject: mm/mmap.c: do not allow mappings outside of allowed limits

One can set a lowest possible address in /proc/sys/vm/mmap_min_addr 
and mmap below that bound nevertheless.

It is possible to request a fixed mapping address below mmap_min_addr and
succeed.  This update adds early checks of mmap_min_addr and mmap_end
boundaries and fixes the above issue.

Apart from it is wrong I am not aware of any existing issue.

Link: http://lkml.kernel.org/r/d6da1319114a331095052638f0ffa3ccb0be58f1.1584958099.git.agordeev@linux.ibm.com
Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/mmap.c |   23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

--- a/mm/mmap.c~mm-mmapc-do-not-allow-mappings-outside-of-allowed-limits
+++ a/mm/mmap.c
@@ -62,6 +62,14 @@
 #define arch_mmap_check(addr, len, flags)	(0)
 #endif
 
+#ifndef arch_get_mmap_end
+#define arch_get_mmap_end(addr)	(TASK_SIZE)
+#endif
+
+#ifndef arch_get_mmap_base
+#define arch_get_mmap_base(addr, base) (base)
+#endif
+
 #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
 const int mmap_rnd_bits_min = CONFIG_ARCH_MMAP_RND_BITS_MIN;
 const int mmap_rnd_bits_max = CONFIG_ARCH_MMAP_RND_BITS_MAX;
@@ -1369,6 +1377,7 @@ unsigned long do_mmap(struct file *file,
 			unsigned long pgoff, unsigned long *populate,
 			struct list_head *uf)
 {
+	const unsigned long mmap_end = arch_get_mmap_end(addr);
 	struct mm_struct *mm = current->mm;
 	int pkey = 0;
 
@@ -1391,8 +1400,12 @@ unsigned long do_mmap(struct file *file,
 	if (flags & MAP_FIXED_NOREPLACE)
 		flags |= MAP_FIXED;
 
-	if (!(flags & MAP_FIXED))
+	if (flags & MAP_FIXED) {
+		if ((addr < mmap_min_addr) || (addr > mmap_end))
+			return -ENOMEM;
+	} else {
 		addr = round_hint_to_min(addr);
+	}
 
 	/* Careful about overflows.. */
 	len = PAGE_ALIGN(len);
@@ -2074,14 +2087,6 @@ unsigned long vm_unmapped_area(struct vm
 	return addr;
 }
 
-#ifndef arch_get_mmap_end
-#define arch_get_mmap_end(addr)	(TASK_SIZE)
-#endif
-
-#ifndef arch_get_mmap_base
-#define arch_get_mmap_base(addr, base) (base)
-#endif
-
 /* Get an address range which is currently unmapped.
  * For shmat() with addr=0.
  *
_

Re: [patch 24/54] mm/mmap.c: do not allow mappings outside of allowed limits

[Linus Torvalds]

On Sun, Jun 7, 2020 at 9:41 PM Andrew Morton <akpm@linux-foundation.org> wrote:
>
> One can set a lowest possible address in /proc/sys/vm/mmap_min_addr
> and mmap below that bound nevertheless.

Well, /proc/sys/vm/mmap_min_addr actually sets "dac_mmap_min_addr"
directly, and then indirectly sets mmap_min_addr with slightly
different rules.

> It is possible to request a fixed mapping address below mmap_min_addr and
> succeed.  This update adds early checks of mmap_min_addr and mmap_end
> boundaries and fixes the above issue.
>
> Apart from it is wrong I am not aware of any existing issue.

Hmm. I think your patch is generally fine, although a few things worries me:

 - the "mmap_end" check seems wrong. It should be something like

        if (len > mmap_end || addr > mmap_end-len)

   shouldn't it?

 - the limit we _do_ test is that "dac_mmap_min_addr", and we allow
lower limits for CAP_SYS_RAWIO

 - I think this will break vm86 mode on 32-bit x86. Have you tested that?

In other words, I think the reason we don't do that hard check of
mmap_min_addr is exactly that vm86 issue. If we were to force a hard
check, we're now making it impossible to use vm86 mode.

So I'm dropping this patch, because it is not clear that this was
fully thought through.

And if it *was* intentional, and people knew about the vm86 issues,
and the thing about dac_mmap_min_addr and the check in
cap_mmap_addr(), then it should be mentioned in the commit message.

That said, I'd be more than willing to move the "cap_mmap_addr()"
check into the mm layer and make it a whole lot more obvious.

And I'd also be more than willing to really make the difference
between "dac_mmap_min_addr" and "mmap_min_addr" actually meaningful,
and really enforce "mmap_min_addr", because right now it's a
half-baked feature that isn't actually used for anything but hinting
and the grow-down issue.

And that, in turn, is because of those vm86 issues, but also because
we've historically had programs that wanted some legacy behavior and
did a mmap() of a zero-page at the 0 address (because that's how some
old Unix environments worked - I htink legacy parisc or similar).

            Linus

Re: [patch 24/54] mm/mmap.c: do not allow mappings outside of allowed limits

[Linus Torvalds]

On Mon, Jun 8, 2020 at 10:50 AM Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> So I'm dropping this patch, because it is not clear that this was
> fully thought through.

Side note: I'm also dropping 23/54, just because they go together, and
because of how mmap_min_addr really isn't a hard limit (as things
stand today). The logic in 23/54 fundamentally has that "it's a hard
limit" issue.

                    Linus

[patch 25/54] arm: fix the flush_icache_range arguments in set_fiq_handler

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: arm: fix the flush_icache_range arguments in set_fiq_handler

Patch series "sort out the flush_icache_range mess", v2.

flush_icache_range is mostly used for kernel address, except for the
following cases:

 - the nommu brk and mmap implementations,
 - the read_code helper that is only used for binfmt_flat, binfmt_elf_fdpic,
   and binfmt_aout including the broken ia32 compat version
 - binfmt_flat itself,

none of which really are used by a typical MMU enabled kernel, as a.out
can only be build for alpha and m68k to start with.

But strangely enough commit ae92ef8a4424 ("PATCH] flush icache in correct
context") added a "set_fs(KERNEL_DS)" around the flush_icache_range call
in the module loader, because apparently m68k assumed user pointers.

This series first cleans up the cacheflush implementations, largely by
switching as much as possible to the asm-generic version after a few
preparations, then moves the misnamed current flush_icache_user_range to a
new name, to finally introduce a real flush_icache_user_range to be used
for the above use cases to flush the instruction cache for a userspace
address range.  The last patch then drops the set_fs in the module code
and moves it into the m68k implementation.


This patch (of 29):

The arguments passed look bogus, try to fix them to something that seems
to make sense.

Link: http://lkml.kernel.org/r/20200515143646.3857579-1-hch@lst.de
Link: http://lkml.kernel.org/r/20200515143646.3857579-2-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Roman Zippel <zippel@linux-m68k.org>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Michal Simek <monstr@monstr.eu>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Aurelien Jacquiot <jacquiot.aurelien@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Cain <bcain@codeaurora.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chris Zankel <chris@zankel.net>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: Guan Xuetao <gxt@pku.edu.cn>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nick Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmerdabbelt@google.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Richard Weinberger <richard@nod.at>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/arm/kernel/fiq.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/arm/kernel/fiq.c~arm-fix-the-flush_icache_range-arguments-in-set_fiq_handler
+++ a/arch/arm/kernel/fiq.c
@@ -98,8 +98,8 @@ void set_fiq_handler(void *start, unsign
 
 	memcpy(base + offset, start, length);
 	if (!cache_is_vipt_nonaliasing())
-		flush_icache_range((unsigned long)base + offset, offset +
-				   length);
+		flush_icache_range((unsigned long)base + offset,
+				   (unsigned long)base + offset + length);
 	flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length);
 }
 
_

[patch 26/54] nds32: unexport flush_icache_page

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: nds32: unexport flush_icache_page

flush_icache_page is only used by mm/memory.c.

Link: http://lkml.kernel.org/r/20200515143646.3857579-3-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/nds32/mm/cacheflush.c |    1 -
 1 file changed, 1 deletion(-)

--- a/arch/nds32/mm/cacheflush.c~nds32-unexport-flush_icache_page
+++ a/arch/nds32/mm/cacheflush.c
@@ -35,7 +35,6 @@ void flush_icache_page(struct vm_area_st
 	kunmap_atomic((void *)kaddr);
 	local_irq_restore(flags);
 }
-EXPORT_SYMBOL(flush_icache_page);
 
 void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
 	                     unsigned long addr, int len)
_

[patch 27/54] powerpc: unexport flush_icache_user_range

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: powerpc: unexport flush_icache_user_range

flush_icache_user_range is only used by copy_to_user_page, which is
only used by core VM code.

Link: http://lkml.kernel.org/r/20200515143646.3857579-4-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/powerpc/mm/mem.c |    1 -
 1 file changed, 1 deletion(-)

--- a/arch/powerpc/mm/mem.c~powerpc-unexport-flush_icache_user_range
+++ a/arch/powerpc/mm/mem.c
@@ -586,7 +586,6 @@ void flush_icache_user_range(struct vm_a
 	flush_icache_range(maddr, maddr + len);
 	kunmap(page);
 }
-EXPORT_SYMBOL(flush_icache_user_range);
 
 /*
  * System memory should not be in /proc/iomem but various tools expect it
_

[patch 28/54] unicore32: remove flush_cache_user_range

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: unicore32: remove flush_cache_user_range

flush_cache_user_range is an ARMism not used by any generic or unicore32
specific code.

Link: http://lkml.kernel.org/r/20200515143646.3857579-5-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Guan Xuetao <gxt@pku.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/unicore32/include/asm/cacheflush.h |    8 --------
 1 file changed, 8 deletions(-)

--- a/arch/unicore32/include/asm/cacheflush.h~unicore32-remove-flush_cache_user_range
+++ a/arch/unicore32/include/asm/cacheflush.h
@@ -133,14 +133,6 @@ extern void flush_cache_page(struct vm_a
 #define flush_cache_dup_mm(mm) flush_cache_mm(mm)
 
 /*
- * flush_cache_user_range is used when we want to ensure that the
- * Harvard caches are synchronised for the user space address range.
- * This is used for the UniCore private sys_cacheflush system call.
- */
-#define flush_cache_user_range(vma, start, end) \
-	__cpuc_coherent_user_range((start) & PAGE_MASK, PAGE_ALIGN(end))
-
-/*
  * Perform necessary cache operations to ensure that data previously
  * stored within this range of addresses can be executed by the CPU.
  */
_

[patch 29/54] asm-generic: fix the inclusion guards for cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: asm-generic: fix the inclusion guards for cacheflush.h

cacheflush.h uses a somewhat to generic include guard name that clashes
with various arch files.  Use a more specific one.

Link: http://lkml.kernel.org/r/20200515143646.3857579-6-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/asm-generic/cacheflush.h |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/include/asm-generic/cacheflush.h~asm-generic-fix-the-inclusion-guards-for-cacheflushh
+++ a/include/asm-generic/cacheflush.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_CACHEFLUSH_H
-#define __ASM_CACHEFLUSH_H
+#ifndef _ASM_GENERIC_CACHEFLUSH_H
+#define _ASM_GENERIC_CACHEFLUSH_H
 
 /* Keep includes the same across arches.  */
 #include <linux/mm.h>
@@ -109,4 +109,4 @@ static inline void flush_cache_vunmap(un
 	memcpy(dst, src, len)
 #endif
 
-#endif /* __ASM_CACHEFLUSH_H */
+#endif /* _ASM_GENERIC_CACHEFLUSH_H */
_

[patch 30/54] asm-generic: don't include <linux/mm.h> in cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: asm-generic: don't include <linux/mm.h> in cacheflush.h

This seems to lead to some crazy include loops when using
asm-generic/cacheflush.h on more architectures, so leave it to the arch
header for now.

[hch@lst.de: fix warning]
  Link: http://lkml.kernel.org/r/20200520173520.GA11199@lst.de
Link: http://lkml.kernel.org/r/20200515143646.3857579-7-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Will Deacon <will@kernel.org>
Cc: Nick Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Anton Ivanov <anton.ivanov@cambridgegreys.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/um/include/asm/tlb.h                  |    2 ++
 arch/x86/include/asm/cacheflush.h          |    2 ++
 drivers/media/platform/omap3isp/ispvideo.c |    2 +-
 drivers/nvdimm/pmem.c                      |    3 ++-
 include/asm-generic/cacheflush.h           |    3 ---
 5 files changed, 7 insertions(+), 5 deletions(-)

--- a/arch/um/include/asm/tlb.h~asm-generic-dont-include-linux-mmh-in-cacheflushh
+++ a/arch/um/include/asm/tlb.h
@@ -2,6 +2,8 @@
 #ifndef __UM_TLB_H
 #define __UM_TLB_H
 
+#include <linux/mm.h>
+
 #include <asm/tlbflush.h>
 #include <asm-generic/cacheflush.h>
 #include <asm-generic/tlb.h>
--- a/arch/x86/include/asm/cacheflush.h~asm-generic-dont-include-linux-mmh-in-cacheflushh
+++ a/arch/x86/include/asm/cacheflush.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_CACHEFLUSH_H
 #define _ASM_X86_CACHEFLUSH_H
 
+#include <linux/mm.h>
+
 /* Caches aren't brain-dead on the intel. */
 #include <asm-generic/cacheflush.h>
 #include <asm/special_insns.h>
--- a/drivers/media/platform/omap3isp/ispvideo.c~asm-generic-dont-include-linux-mmh-in-cacheflushh
+++ a/drivers/media/platform/omap3isp/ispvideo.c
@@ -10,7 +10,6 @@
  *	     Sakari Ailus <sakari.ailus@iki.fi>
  */
 
-#include <asm/cacheflush.h>
 #include <linux/clk.h>
 #include <linux/mm.h>
 #include <linux/module.h>
@@ -19,6 +18,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <asm/cacheflush.h>
 
 #include <media/v4l2-dev.h>
 #include <media/v4l2-ioctl.h>
--- a/drivers/nvdimm/pmem.c~asm-generic-dont-include-linux-mmh-in-cacheflushh
+++ a/drivers/nvdimm/pmem.c
@@ -7,7 +7,6 @@
  * Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
  */
 
-#include <asm/cacheflush.h>
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
 #include <linux/init.h>
@@ -25,6 +24,8 @@
 #include <linux/dax.h>
 #include <linux/nd.h>
 #include <linux/backing-dev.h>
+#include <linux/mm.h>
+#include <asm/cacheflush.h>
 #include "pmem.h"
 #include "pfn.h"
 #include "nd.h"
--- a/include/asm-generic/cacheflush.h~asm-generic-dont-include-linux-mmh-in-cacheflushh
+++ a/include/asm-generic/cacheflush.h
@@ -2,9 +2,6 @@
 #ifndef _ASM_GENERIC_CACHEFLUSH_H
 #define _ASM_GENERIC_CACHEFLUSH_H
 
-/* Keep includes the same across arches.  */
-#include <linux/mm.h>
-
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
 
 /*
_

[patch 31/54] asm-generic: improve the flush_dcache_page stub

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: asm-generic: improve the flush_dcache_page stub

There is a magic ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE cpp symbol that
guards non-stub availability of flush_dcache_pagge.  Use that to
check if flush_dcache_pagg is implemented.

Link: http://lkml.kernel.org/r/20200515143646.3857579-8-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/asm-generic/cacheflush.h |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/include/asm-generic/cacheflush.h~asm-generic-improve-the-flush_dcache_page-stub
+++ a/include/asm-generic/cacheflush.h
@@ -2,8 +2,6 @@
 #ifndef _ASM_GENERIC_CACHEFLUSH_H
 #define _ASM_GENERIC_CACHEFLUSH_H
 
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-
 /*
  * The cache doesn't need to be flushed when TLB entries change when
  * the cache is mapped to physical memory, not virtual memory
@@ -42,12 +40,14 @@ static inline void flush_cache_page(stru
 }
 #endif
 
-#ifndef flush_dcache_page
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 static inline void flush_dcache_page(struct page *page)
 {
 }
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
 #endif
 
+
 #ifndef flush_dcache_mmap_lock
 static inline void flush_dcache_mmap_lock(struct address_space *mapping)
 {
_

[patch 32/54] alpha: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: alpha: use asm-generic/cacheflush.h

Alpha needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Link: http://lkml.kernel.org/r/20200515143646.3857579-9-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/alpha/include/asm/cacheflush.h |   28 +++++---------------------
 1 file changed, 6 insertions(+), 22 deletions(-)

--- a/arch/alpha/include/asm/cacheflush.h~alpha-use-asm-generic-cacheflushh
+++ a/arch/alpha/include/asm/cacheflush.h
@@ -4,19 +4,6 @@
 
 #include <linux/mm.h>
 
-/* Caches aren't brain-dead on the Alpha. */
-#define flush_cache_all()			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page)			do { } while (0)
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-#define flush_cache_vmap(start, end)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
-
 /* Note that the following two definitions are _highly_ dependent
    on the contexts in which they are used in the kernel.  I personally
    think it is criminal how loosely defined these macros are.  */
@@ -59,20 +46,17 @@ flush_icache_user_range(struct vm_area_s
 			mm->context[smp_processor_id()] = 0;
 	}
 }
-#else
+#define flush_icache_user_range flush_icache_user_range
+#else /* CONFIG_SMP */
 extern void flush_icache_user_range(struct vm_area_struct *vma,
 		struct page *page, unsigned long addr, int len);
-#endif
+#define flush_icache_user_range flush_icache_user_range
+#endif /* CONFIG_SMP */
 
 /* This is used only in __do_fault and do_swap_page.  */
 #define flush_icache_page(vma, page) \
-  flush_icache_user_range((vma), (page), 0, 0)
+	flush_icache_user_range((vma), (page), 0, 0)
 
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-do { memcpy(dst, src, len); \
-     flush_icache_user_range(vma, page, vaddr, len); \
-} while (0)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
+#include <asm-generic/cacheflush.h>
 
 #endif /* _ALPHA_CACHEFLUSH_H */
_

[patch 33/54] arm64: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: arm64: use asm-generic/cacheflush.h

ARM64 needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Link: http://lkml.kernel.org/r/20200515143646.3857579-10-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/arm64/include/asm/cacheflush.h |   46 ++------------------------
 1 file changed, 5 insertions(+), 41 deletions(-)

--- a/arch/arm64/include/asm/cacheflush.h~arm64-use-asm-generic-cacheflushh
+++ a/arch/arm64/include/asm/cacheflush.h
@@ -94,20 +94,7 @@ static inline void flush_icache_range(un
 
 	kick_all_cpus_sync();
 }
-
-static inline void flush_cache_mm(struct mm_struct *mm)
-{
-}
-
-static inline void flush_cache_page(struct vm_area_struct *vma,
-				    unsigned long user_addr, unsigned long pfn)
-{
-}
-
-static inline void flush_cache_range(struct vm_area_struct *vma,
-				     unsigned long start, unsigned long end)
-{
-}
+#define flush_icache_range flush_icache_range
 
 /*
  * Cache maintenance functions used by the DMA API. No to be used directly.
@@ -123,12 +110,7 @@ extern void __dma_flush_area(const void
  */
 extern void copy_to_user_page(struct vm_area_struct *, struct page *,
 	unsigned long, void *, const void *, unsigned long);
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	do {							\
-		memcpy(dst, src, len);				\
-	} while (0)
-
-#define flush_cache_dup_mm(mm) flush_cache_mm(mm)
+#define copy_to_user_page copy_to_user_page
 
 /*
  * flush_dcache_page is used when the kernel has written to the page
@@ -154,29 +136,11 @@ static __always_inline void __flush_icac
 	dsb(ish);
 }
 
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-
-/*
- * We don't appear to need to do anything here.  In fact, if we did, we'd
- * duplicate cache flushing elsewhere performed by flush_dcache_page().
- */
-#define flush_icache_page(vma,page)	do { } while (0)
-
-/*
- * Not required on AArch64 (PIPT or VIPT non-aliasing D-cache).
- */
-static inline void flush_cache_vmap(unsigned long start, unsigned long end)
-{
-}
-
-static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
-{
-}
-
 int set_memory_valid(unsigned long addr, int numpages, int enable);
 
 int set_direct_map_invalid_noflush(struct page *page);
 int set_direct_map_default_noflush(struct page *page);
 
-#endif
+#include <asm-generic/cacheflush.h>
+
+#endif /* __ASM_CACHEFLUSH_H */
_

[patch 34/54] c6x: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: c6x: use asm-generic/cacheflush.h

C6x needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Link: http://lkml.kernel.org/r/20200515143646.3857579-11-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mark Salter <msalter@redhat.com>
Cc: Aurelien Jacquiot <jacquiot.aurelien@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/c6x/include/asm/cacheflush.h |   19 +------------------
 1 file changed, 1 insertion(+), 18 deletions(-)

--- a/arch/c6x/include/asm/cacheflush.h~c6x-use-asm-generic-cacheflushh
+++ a/arch/c6x/include/asm/cacheflush.h
@@ -17,21 +17,6 @@
 #include <asm/string.h>
 
 /*
- * virtually-indexed cache management (our cache is physically indexed)
- */
-#define flush_cache_all()			do {} while (0)
-#define flush_cache_mm(mm)			do {} while (0)
-#define flush_cache_dup_mm(mm)			do {} while (0)
-#define flush_cache_range(mm, start, end)	do {} while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do {} while (0)
-#define flush_cache_vmap(start, end)		do {} while (0)
-#define flush_cache_vunmap(start, end)		do {} while (0)
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page)			do {} while (0)
-#define flush_dcache_mmap_lock(mapping)		do {} while (0)
-#define flush_dcache_mmap_unlock(mapping)	do {} while (0)
-
-/*
  * physically-indexed cache management
  */
 #define flush_icache_range(s, e)				  \
@@ -49,14 +34,12 @@ do {								  \
 			(unsigned long) page_address(page) + PAGE_SIZE)); \
 } while (0)
 
-
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
 do {						     \
 	memcpy(dst, src, len);			     \
 	flush_icache_range((unsigned) (dst), (unsigned) (dst) + (len)); \
 } while (0)
 
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
+#include <asm-generic/cacheflush.h>
 
 #endif /* _ASM_C6X_CACHEFLUSH_H */
_

[patch 35/54] hexagon: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: hexagon: use asm-generic/cacheflush.h

Hexagon needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Link: http://lkml.kernel.org/r/20200515143646.3857579-12-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Brian Cain <bcain@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/hexagon/include/asm/cacheflush.h |   19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

--- a/arch/hexagon/include/asm/cacheflush.h~hexagon-use-asm-generic-cacheflushh
+++ a/arch/hexagon/include/asm/cacheflush.h
@@ -25,29 +25,17 @@
 #define LINESIZE	32
 #define LINEBITS	5
 
-#define flush_cache_all()			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page)			do { } while (0)
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-#define flush_icache_page(vma, pg)		do { } while (0)
-#define flush_icache_user_range(vma, pg, adr, len)	do { } while (0)
-#define flush_cache_vmap(start, end)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
-
 /*
  * Flush Dcache range through current map.
  */
 extern void flush_dcache_range(unsigned long start, unsigned long end);
+#define flush_dcache_range flush_dcache_range
 
 /*
  * Flush Icache range through current map.
  */
 extern void flush_icache_range(unsigned long start, unsigned long end);
+#define flush_icache_range flush_icache_range
 
 /*
  * Memory-management related flushes are there to ensure in non-physically
@@ -78,6 +66,7 @@ static inline void update_mmu_cache(stru
 
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		       unsigned long vaddr, void *dst, void *src, int len);
+#define copy_to_user_page copy_to_user_page
 
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
 	memcpy(dst, src, len)
@@ -85,4 +74,6 @@ void copy_to_user_page(struct vm_area_st
 extern void hexagon_inv_dcache_range(unsigned long start, unsigned long end);
 extern void hexagon_clean_dcache_range(unsigned long start, unsigned long end);
 
+#include <asm-generic/cacheflush.h>
+
 #endif
_

[patch 36/54] ia64: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: ia64: use asm-generic/cacheflush.h

IA64 needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Link: http://lkml.kernel.org/r/20200515143646.3857579-13-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/ia64/include/asm/cacheflush.h |   28 ++-------------------------
 1 file changed, 3 insertions(+), 25 deletions(-)

--- a/arch/ia64/include/asm/cacheflush.h~ia64-use-asm-generic-cacheflushh
+++ a/arch/ia64/include/asm/cacheflush.h
@@ -12,44 +12,22 @@
 
 #include <asm/page.h>
 
-/*
- * Cache flushing routines.  This is the kind of stuff that can be very expensive, so try
- * to avoid them whenever possible.
- */
-
-#define flush_cache_all()			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
-#define flush_icache_page(vma,page)		do { } while (0)
-#define flush_cache_vmap(start, end)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
-
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 #define flush_dcache_page(page)			\
 do {						\
 	clear_bit(PG_arch_1, &(page)->flags);	\
 } while (0)
 
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-
-extern void flush_icache_range (unsigned long start, unsigned long end);
+extern void flush_icache_range(unsigned long start, unsigned long end);
+#define flush_icache_range flush_icache_range
 extern void clflush_cache_range(void *addr, int size);
 
-
 #define flush_icache_user_range(vma, page, user_addr, len)					\
 do {												\
 	unsigned long _addr = (unsigned long) page_address(page) + ((user_addr) & ~PAGE_MASK);	\
 	flush_icache_range(_addr, _addr + (len));						\
 } while (0)
 
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-do { memcpy(dst, src, len); \
-     flush_icache_user_range(vma, page, vaddr, len); \
-} while (0)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
+#include <asm-generic/cacheflush.h>
 
 #endif /* _ASM_IA64_CACHEFLUSH_H */
_

[patch 37/54] microblaze: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: microblaze: use asm-generic/cacheflush.h

Microblaze needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Link: http://lkml.kernel.org/r/20200515143646.3857579-14-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Michal Simek <monstr@monstr.eu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/microblaze/include/asm/cacheflush.h |   29 +--------------------
 1 file changed, 2 insertions(+), 27 deletions(-)

--- a/arch/microblaze/include/asm/cacheflush.h~microblaze-use-asm-generic-cacheflushh
+++ a/arch/microblaze/include/asm/cacheflush.h
@@ -57,9 +57,6 @@ void microblaze_cache_init(void);
 #define invalidate_icache()				mbc->iin();
 #define invalidate_icache_range(start, end)		mbc->iinr(start, end);
 
-#define flush_icache_user_range(vma, pg, adr, len)	flush_icache();
-#define flush_icache_page(vma, pg)			do { } while (0)
-
 #define enable_dcache()					mbc->de();
 #define disable_dcache()				mbc->dd();
 /* FIXME for LL-temac driver */
@@ -77,27 +74,9 @@ do { \
 	flush_dcache_range((unsigned) (addr), (unsigned) (addr) + PAGE_SIZE); \
 } while (0);
 
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-
-#define flush_cache_dup_mm(mm)				do { } while (0)
-#define flush_cache_vmap(start, end)			do { } while (0)
-#define flush_cache_vunmap(start, end)			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-
 #define flush_cache_page(vma, vmaddr, pfn) \
 	flush_dcache_range(pfn << PAGE_SHIFT, (pfn << PAGE_SHIFT) + PAGE_SIZE);
 
-/* MS: kgdb code use this macro, wrong len with FLASH */
-#if 0
-#define flush_cache_range(vma, start, len)	{	\
-	flush_icache_range((unsigned) (start), (unsigned) (start) + (len)); \
-	flush_dcache_range((unsigned) (start), (unsigned) (start) + (len)); \
-}
-#endif
-
-#define flush_cache_range(vma, start, len) do { } while (0)
-
 static inline void copy_to_user_page(struct vm_area_struct *vma,
 				     struct page *page, unsigned long vaddr,
 				     void *dst, void *src, int len)
@@ -109,12 +88,8 @@ static inline void copy_to_user_page(str
 		flush_dcache_range(addr, addr + PAGE_SIZE);
 	}
 }
+#define copy_to_user_page copy_to_user_page
 
-static inline void copy_from_user_page(struct vm_area_struct *vma,
-				       struct page *page, unsigned long vaddr,
-				       void *dst, void *src, int len)
-{
-	memcpy(dst, src, len);
-}
+#include <asm-generic/cacheflush.h>
 
 #endif /* _ASM_MICROBLAZE_CACHEFLUSH_H */
_

[patch 38/54] m68knommu: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: m68knommu: use asm-generic/cacheflush.h

m68knommu needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Link: http://lkml.kernel.org/r/20200515143646.3857579-15-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/m68k/include/asm/cacheflush_no.h |   19 ++-----------------
 1 file changed, 2 insertions(+), 17 deletions(-)

--- a/arch/m68k/include/asm/cacheflush_no.h~m68knommu-use-asm-generic-cacheflushh
+++ a/arch/m68k/include/asm/cacheflush_no.h
@@ -9,25 +9,8 @@
 #include <asm/mcfsim.h>
 
 #define flush_cache_all()			__flush_cache_all()
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr)		do { } while (0)
 #define flush_dcache_range(start, len)		__flush_dcache_all()
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-#define flush_dcache_page(page)			do { } while (0)
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 #define flush_icache_range(start, len)		__flush_icache_all()
-#define flush_icache_page(vma,pg)		do { } while (0)
-#define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
-#define flush_cache_vmap(start, end)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
-
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
 
 void mcf_cache_push(void);
 
@@ -98,4 +81,6 @@ static inline void cache_clear(unsigned
 	__clear_cache_all();
 }
 
+#include <asm-generic/cacheflush.h>
+
 #endif /* _M68KNOMMU_CACHEFLUSH_H */
_

[patch 39/54] openrisc: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: openrisc: use asm-generic/cacheflush.h

OpenRISC needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Link: http://lkml.kernel.org/r/20200515143646.3857579-16-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Stafford Horne <shorne@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/openrisc/include/asm/cacheflush.h |   31 ++++-------------------
 1 file changed, 6 insertions(+), 25 deletions(-)

--- a/arch/openrisc/include/asm/cacheflush.h~openrisc-use-asm-generic-cacheflushh
+++ a/arch/openrisc/include/asm/cacheflush.h
@@ -62,31 +62,12 @@ static inline void flush_dcache_page(str
 	clear_bit(PG_dc_clean, &page->flags);
 }
 
-/*
- * Other interfaces are not required since we do not have virtually
- * indexed or tagged caches. So we can use the default here.
- */
-#define flush_cache_all()				do { } while (0)
-#define flush_cache_mm(mm)				do { } while (0)
-#define flush_cache_dup_mm(mm)				do { } while (0)
-#define flush_cache_range(vma, start, end)		do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)		do { } while (0)
-#define flush_dcache_mmap_lock(mapping)			do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)		do { } while (0)
-#define flush_icache_range(start, end)			do { } while (0)
-#define flush_icache_page(vma, pg)			do { } while (0)
-#define flush_icache_user_range(vma, pg, adr, len)	do { } while (0)
-#define flush_cache_vmap(start, end)			do { } while (0)
-#define flush_cache_vunmap(start, end)			do { } while (0)
+#define flush_icache_user_range(vma, page, addr, len)	\
+do {							\
+	if (vma->vm_flags & VM_EXEC)			\
+		sync_icache_dcache(page);		\
+} while (0)
 
-#define copy_to_user_page(vma, page, vaddr, dst, src, len)           \
-	do {                                                         \
-		memcpy(dst, src, len);                               \
-		if (vma->vm_flags & VM_EXEC)                         \
-			sync_icache_dcache(page);                    \
-	} while (0)
-
-#define copy_from_user_page(vma, page, vaddr, dst, src, len)         \
-	memcpy(dst, src, len)
+#include <asm-generic/cacheflush.h>
 
 #endif /* __ASM_CACHEFLUSH_H */
_

[patch 40/54] powerpc: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: powerpc: use asm-generic/cacheflush.h

Power needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Also remove the pointless __KERNEL__ ifdef while we're at it.

Link: http://lkml.kernel.org/r/20200515143646.3857579-17-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/powerpc/include/asm/cacheflush.h |   42 +++++-------------------
 1 file changed, 10 insertions(+), 32 deletions(-)

--- a/arch/powerpc/include/asm/cacheflush.h~powerpc-use-asm-generic-cacheflushh
+++ a/arch/powerpc/include/asm/cacheflush.h
@@ -4,23 +4,9 @@
 #ifndef _ASM_POWERPC_CACHEFLUSH_H
 #define _ASM_POWERPC_CACHEFLUSH_H
 
-#ifdef __KERNEL__
-
 #include <linux/mm.h>
 #include <asm/cputable.h>
 
-/*
- * No cache flushing is required when address mappings are changed,
- * because the caches on PowerPCs are physically addressed.
- */
-#define flush_cache_all()			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
-#define flush_icache_page(vma, page)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
-
 #ifdef CONFIG_PPC_BOOK3S_64
 /*
  * Book3s has no ptesync after setting a pte, so without this ptesync it's
@@ -33,20 +19,20 @@ static inline void flush_cache_vmap(unsi
 {
 	asm volatile("ptesync" ::: "memory");
 }
-#else
-static inline void flush_cache_vmap(unsigned long start, unsigned long end) { }
-#endif
+#define flush_cache_vmap flush_cache_vmap
+#endif /* CONFIG_PPC_BOOK3S_64 */
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *page);
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
 void flush_icache_range(unsigned long start, unsigned long stop);
-extern void flush_icache_user_range(struct vm_area_struct *vma,
-				    struct page *page, unsigned long addr,
-				    int len);
-extern void flush_dcache_icache_page(struct page *page);
+#define flush_icache_range flush_icache_range
+
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+		unsigned long addr, int len);
+#define flush_icache_user_range flush_icache_user_range
+
+void flush_dcache_icache_page(struct page *page);
 void __flush_dcache_icache(void *page);
 
 /**
@@ -111,14 +97,6 @@ static inline void invalidate_dcache_ran
 	mb();	/* sync */
 }
 
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-	do { \
-		memcpy(dst, src, len); \
-		flush_icache_user_range(vma, page, vaddr, len); \
-	} while (0)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
-
-#endif /* __KERNEL__ */
+#include <asm-generic/cacheflush.h>
 
 #endif /* _ASM_POWERPC_CACHEFLUSH_H */
_

[patch 41/54] riscv: use asm-generic/cacheflush.h

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: riscv: use asm-generic/cacheflush.h

RISC-V needs almost no cache flushing routines of its own.  Rely on
asm-generic/cacheflush.h for the defaults.

Also remove the pointless __KERNEL__ ifdef while we're at it.

Link: http://lkml.kernel.org/r/20200515143646.3857579-18-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>
Acked-by: Palmer Dabbelt <palmerdabbelt@google.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/riscv/include/asm/cacheflush.h |   62 +-------------------------
 1 file changed, 3 insertions(+), 59 deletions(-)

--- a/arch/riscv/include/asm/cacheflush.h~riscv-use-asm-generic-cacheflushh
+++ a/arch/riscv/include/asm/cacheflush.h
@@ -8,65 +8,6 @@
 
 #include <linux/mm.h>
 
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-
-/*
- * The cache doesn't need to be flushed when TLB entries change when
- * the cache is mapped to physical memory, not virtual memory
- */
-static inline void flush_cache_all(void)
-{
-}
-
-static inline void flush_cache_mm(struct mm_struct *mm)
-{
-}
-
-static inline void flush_cache_dup_mm(struct mm_struct *mm)
-{
-}
-
-static inline void flush_cache_range(struct vm_area_struct *vma,
-				     unsigned long start,
-				     unsigned long end)
-{
-}
-
-static inline void flush_cache_page(struct vm_area_struct *vma,
-				    unsigned long vmaddr,
-				    unsigned long pfn)
-{
-}
-
-static inline void flush_dcache_mmap_lock(struct address_space *mapping)
-{
-}
-
-static inline void flush_dcache_mmap_unlock(struct address_space *mapping)
-{
-}
-
-static inline void flush_icache_page(struct vm_area_struct *vma,
-				     struct page *page)
-{
-}
-
-static inline void flush_cache_vmap(unsigned long start, unsigned long end)
-{
-}
-
-static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
-{
-}
-
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-	do { \
-		memcpy(dst, src, len); \
-		flush_icache_user_range(vma, page, vaddr, len); \
-	} while (0)
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-	memcpy(dst, src, len)
-
 static inline void local_flush_icache_all(void)
 {
 	asm volatile ("fence.i" ::: "memory");
@@ -79,6 +20,7 @@ static inline void flush_dcache_page(str
 	if (test_bit(PG_dcache_clean, &page->flags))
 		clear_bit(PG_dcache_clean, &page->flags);
 }
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 
 /*
  * RISC-V doesn't have an instruction to flush parts of the instruction cache,
@@ -105,4 +47,6 @@ void flush_icache_mm(struct mm_struct *m
 #define SYS_RISCV_FLUSH_ICACHE_LOCAL 1UL
 #define SYS_RISCV_FLUSH_ICACHE_ALL   (SYS_RISCV_FLUSH_ICACHE_LOCAL)
 
+#include <asm-generic/cacheflush.h>
+
 #endif /* _ASM_RISCV_CACHEFLUSH_H */
_

[patch 42/54] arm,sparc,unicore32: remove flush_icache_user_range

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: arm,sparc,unicore32: remove flush_icache_user_range

flush_icache_user_range is only used by <asm-generic/cacheflush.h>, so
remove it from the architectures that implement it, but don't use
<asm-generic/cacheflush.h>.

Link: http://lkml.kernel.org/r/20200515143646.3857579-19-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Russell King <linux@armlinux.org.uk>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Guan Xuetao <gxt@pku.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/arm/include/asm/cacheflush.h       |    3 ---
 arch/sparc/include/asm/cacheflush_32.h  |    2 --
 arch/sparc/include/asm/cacheflush_64.h  |    1 -
 arch/unicore32/include/asm/cacheflush.h |    3 ---
 4 files changed, 9 deletions(-)

--- a/arch/arm/include/asm/cacheflush.h~armsparcunicore32-remove-flush_icache_user_range
+++ a/arch/arm/include/asm/cacheflush.h
@@ -318,9 +318,6 @@ extern void flush_kernel_dcache_page(str
 #define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
 #define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
 
-#define flush_icache_user_range(vma,page,addr,len) \
-	flush_dcache_page(page)
-
 /*
  * We don't appear to need to do anything here.  In fact, if we did, we'd
  * duplicate cache flushing elsewhere performed by flush_dcache_page().
--- a/arch/sparc/include/asm/cacheflush_32.h~armsparcunicore32-remove-flush_icache_user_range
+++ a/arch/sparc/include/asm/cacheflush_32.h
@@ -17,8 +17,6 @@
 #define flush_icache_range(start, end)		do { } while (0)
 #define flush_icache_page(vma, pg)		do { } while (0)
 
-#define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
-
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
 	do {							\
 		flush_cache_page(vma, vaddr, page_to_pfn(page));\
--- a/arch/sparc/include/asm/cacheflush_64.h~armsparcunicore32-remove-flush_icache_user_range
+++ a/arch/sparc/include/asm/cacheflush_64.h
@@ -49,7 +49,6 @@ void __flush_dcache_range(unsigned long
 void flush_dcache_page(struct page *page);
 
 #define flush_icache_page(vma, pg)	do { } while(0)
-#define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
 
 void flush_ptrace_access(struct vm_area_struct *, struct page *,
 			 unsigned long uaddr, void *kaddr,
--- a/arch/unicore32/include/asm/cacheflush.h~armsparcunicore32-remove-flush_icache_user_range
+++ a/arch/unicore32/include/asm/cacheflush.h
@@ -162,9 +162,6 @@ extern void flush_dcache_page(struct pag
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 
-#define flush_icache_user_range(vma, page, addr, len)	\
-	flush_dcache_page(page)
-
 /*
  * We don't appear to need to do anything here.  In fact, if we did, we'd
  * duplicate cache flushing elsewhere performed by flush_dcache_page().
_

[patch 43/54] mm: rename flush_icache_user_range to flush_icache_user_page

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: mm: rename flush_icache_user_range to flush_icache_user_page

The function currently known as flush_icache_user_range only operates
on a single page.  Rename it to flush_icache_user_page as we'll need
the name flush_icache_user_range for something else soon.

Link: http://lkml.kernel.org/r/20200515143646.3857579-20-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Greentime Hu <green.hu@gmail.com>
Cc: Vincent Chen <deanbo422@gmail.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/alpha/include/asm/cacheflush.h    |   10 +++++-----
 arch/alpha/kernel/smp.c                |    2 +-
 arch/ia64/include/asm/cacheflush.h     |    2 +-
 arch/m68k/include/asm/cacheflush_mm.h  |    4 ++--
 arch/m68k/mm/cache.c                   |    2 +-
 arch/nds32/include/asm/cacheflush.h    |    4 ++--
 arch/nds32/mm/cacheflush.c             |    2 +-
 arch/openrisc/include/asm/cacheflush.h |    2 +-
 arch/powerpc/include/asm/cacheflush.h  |    4 ++--
 arch/powerpc/mm/mem.c                  |    2 +-
 arch/riscv/include/asm/cacheflush.h    |    3 ++-
 include/asm-generic/cacheflush.h       |    6 +++---
 kernel/events/uprobes.c                |    2 +-
 13 files changed, 23 insertions(+), 22 deletions(-)

--- a/arch/alpha/include/asm/cacheflush.h~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/alpha/include/asm/cacheflush.h
@@ -35,7 +35,7 @@ extern void smp_imb(void);
 
 extern void __load_new_mm_context(struct mm_struct *);
 static inline void
-flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 			unsigned long addr, int len)
 {
 	if (vma->vm_flags & VM_EXEC) {
@@ -46,16 +46,16 @@ flush_icache_user_range(struct vm_area_s
 			mm->context[smp_processor_id()] = 0;
 	}
 }
-#define flush_icache_user_range flush_icache_user_range
+#define flush_icache_user_page flush_icache_user_page
 #else /* CONFIG_SMP */
-extern void flush_icache_user_range(struct vm_area_struct *vma,
+extern void flush_icache_user_page(struct vm_area_struct *vma,
 		struct page *page, unsigned long addr, int len);
-#define flush_icache_user_range flush_icache_user_range
+#define flush_icache_user_page flush_icache_user_page
 #endif /* CONFIG_SMP */
 
 /* This is used only in __do_fault and do_swap_page.  */
 #define flush_icache_page(vma, page) \
-	flush_icache_user_range((vma), (page), 0, 0)
+	flush_icache_user_page((vma), (page), 0, 0)
 
 #include <asm-generic/cacheflush.h>
 
--- a/arch/alpha/kernel/smp.c~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/alpha/kernel/smp.c
@@ -740,7 +740,7 @@ ipi_flush_icache_page(void *x)
 }
 
 void
-flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 			unsigned long addr, int len)
 {
 	struct mm_struct *mm = vma->vm_mm;
--- a/arch/ia64/include/asm/cacheflush.h~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/ia64/include/asm/cacheflush.h
@@ -22,7 +22,7 @@ extern void flush_icache_range(unsigned
 #define flush_icache_range flush_icache_range
 extern void clflush_cache_range(void *addr, int size);
 
-#define flush_icache_user_range(vma, page, user_addr, len)					\
+#define flush_icache_user_page(vma, page, user_addr, len)					\
 do {												\
 	unsigned long _addr = (unsigned long) page_address(page) + ((user_addr) & ~PAGE_MASK);	\
 	flush_icache_range(_addr, _addr + (len));						\
--- a/arch/m68k/include/asm/cacheflush_mm.h~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/m68k/include/asm/cacheflush_mm.h
@@ -254,7 +254,7 @@ static inline void __flush_page_to_ram(v
 #define flush_dcache_mmap_unlock(mapping)	do { } while (0)
 #define flush_icache_page(vma, page)	__flush_page_to_ram(page_address(page))
 
-extern void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+extern void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 				    unsigned long addr, int len);
 extern void flush_icache_range(unsigned long address, unsigned long endaddr);
 
@@ -264,7 +264,7 @@ static inline void copy_to_user_page(str
 {
 	flush_cache_page(vma, vaddr, page_to_pfn(page));
 	memcpy(dst, src, len);
-	flush_icache_user_range(vma, page, vaddr, len);
+	flush_icache_user_page(vma, page, vaddr, len);
 }
 static inline void copy_from_user_page(struct vm_area_struct *vma,
 				       struct page *page, unsigned long vaddr,
--- a/arch/m68k/mm/cache.c~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/m68k/mm/cache.c
@@ -106,7 +106,7 @@ void flush_icache_range(unsigned long ad
 }
 EXPORT_SYMBOL(flush_icache_range);
 
-void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 			     unsigned long addr, int len)
 {
 	if (CPU_IS_COLDFIRE) {
--- a/arch/nds32/include/asm/cacheflush.h~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/nds32/include/asm/cacheflush.h
@@ -44,9 +44,9 @@ void invalidate_kernel_vmap_range(void *
 #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages)
 
 #else
-void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 	                     unsigned long addr, int len);
-#define flush_icache_user_range flush_icache_user_range
+#define flush_icache_user_page flush_icache_user_page
 
 #include <asm-generic/cacheflush.h>
 #endif
--- a/arch/nds32/mm/cacheflush.c~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/nds32/mm/cacheflush.c
@@ -36,7 +36,7 @@ void flush_icache_page(struct vm_area_st
 	local_irq_restore(flags);
 }
 
-void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 	                     unsigned long addr, int len)
 {
 	unsigned long kaddr;
--- a/arch/openrisc/include/asm/cacheflush.h~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/openrisc/include/asm/cacheflush.h
@@ -62,7 +62,7 @@ static inline void flush_dcache_page(str
 	clear_bit(PG_dc_clean, &page->flags);
 }
 
-#define flush_icache_user_range(vma, page, addr, len)	\
+#define flush_icache_user_page(vma, page, addr, len)	\
 do {							\
 	if (vma->vm_flags & VM_EXEC)			\
 		sync_icache_dcache(page);		\
--- a/arch/powerpc/include/asm/cacheflush.h~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/powerpc/include/asm/cacheflush.h
@@ -28,9 +28,9 @@ extern void flush_dcache_page(struct pag
 void flush_icache_range(unsigned long start, unsigned long stop);
 #define flush_icache_range flush_icache_range
 
-void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 		unsigned long addr, int len);
-#define flush_icache_user_range flush_icache_user_range
+#define flush_icache_user_page flush_icache_user_page
 
 void flush_dcache_icache_page(struct page *page);
 void __flush_dcache_icache(void *page);
--- a/arch/powerpc/mm/mem.c~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/powerpc/mm/mem.c
@@ -577,7 +577,7 @@ void copy_user_page(void *vto, void *vfr
 	flush_dcache_page(pg);
 }
 
-void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 			     unsigned long addr, int len)
 {
 	unsigned long maddr;
--- a/arch/riscv/include/asm/cacheflush.h~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/arch/riscv/include/asm/cacheflush.h
@@ -27,7 +27,8 @@ static inline void flush_dcache_page(str
  * so instead we just flush the whole thing.
  */
 #define flush_icache_range(start, end) flush_icache_all()
-#define flush_icache_user_range(vma, pg, addr, len) flush_icache_mm(vma->vm_mm, 0)
+#define flush_icache_user_page(vma, pg, addr, len) \
+	flush_icache_mm(vma->vm_mm, 0)
 
 #ifndef CONFIG_SMP
 
--- a/include/asm-generic/cacheflush.h~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/include/asm-generic/cacheflush.h
@@ -73,8 +73,8 @@ static inline void flush_icache_page(str
 }
 #endif
 
-#ifndef flush_icache_user_range
-static inline void flush_icache_user_range(struct vm_area_struct *vma,
+#ifndef flush_icache_user_page
+static inline void flush_icache_user_page(struct vm_area_struct *vma,
 					   struct page *page,
 					   unsigned long addr, int len)
 {
@@ -97,7 +97,7 @@ static inline void flush_cache_vunmap(un
 #define copy_to_user_page(vma, page, vaddr, dst, src, len)	\
 	do { \
 		memcpy(dst, src, len); \
-		flush_icache_user_range(vma, page, vaddr, len); \
+		flush_icache_user_page(vma, page, vaddr, len); \
 	} while (0)
 #endif
 
--- a/kernel/events/uprobes.c~mm-rename-flush_icache_user_range-to-flush_icache_user_page
+++ a/kernel/events/uprobes.c
@@ -1668,7 +1668,7 @@ void __weak arch_uprobe_copy_ixol(struct
 	copy_to_page(page, vaddr, src, len);
 
 	/*
-	 * We probably need flush_icache_user_range() but it needs vma.
+	 * We probably need flush_icache_user_page() but it needs vma.
 	 * This should work on most of architectures by default. If
 	 * architecture needs to do something different it can define
 	 * its own version of the function.
_

[patch 44/54] asm-generic: add a flush_icache_user_range stub

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: asm-generic: add a flush_icache_user_range stub

Define flush_icache_user_range to flush_icache_range unless the
architecture provides its own implementation.

Link: http://lkml.kernel.org/r/20200515143646.3857579-21-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/asm-generic/cacheflush.h |    4 ++++
 1 file changed, 4 insertions(+)

--- a/include/asm-generic/cacheflush.h~asm-generic-add-a-flush_icache_user_range-stub
+++ a/include/asm-generic/cacheflush.h
@@ -66,6 +66,10 @@ static inline void flush_icache_range(un
 }
 #endif
 
+#ifndef flush_icache_user_range
+#define flush_icache_user_range flush_icache_range
+#endif
+
 #ifndef flush_icache_page
 static inline void flush_icache_page(struct vm_area_struct *vma,
 				     struct page *page)
_

[patch 45/54] sh: implement flush_icache_user_range

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: sh: implement flush_icache_user_range

The SuperH implementation of flush_icache_range seems to be able to
cope with user addresses.  Just define flush_icache_user_range to
flush_icache_range.

Link: http://lkml.kernel.org/r/20200515143646.3857579-22-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/sh/include/asm/cacheflush.h |    1 +
 1 file changed, 1 insertion(+)

--- a/arch/sh/include/asm/cacheflush.h~sh-implement-flush_icache_user_range
+++ a/arch/sh/include/asm/cacheflush.h
@@ -46,6 +46,7 @@ extern void flush_cache_range(struct vm_
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *page);
 extern void flush_icache_range(unsigned long start, unsigned long end);
+#define flush_icache_user_range flush_icache_range
 extern void flush_icache_page(struct vm_area_struct *vma,
 				 struct page *page);
 extern void flush_cache_sigtramp(unsigned long address);
_

[patch 46/54] xtensa: implement flush_icache_user_range

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: xtensa: implement flush_icache_user_range

The Xtensa implementation of flush_icache_range seems to be able to
cope with user addresses.  Just define flush_icache_user_range to
flush_icache_range.

[jcmvbkbc@gmail.com: fix flush_icache_user_range in noMMU configs]
  Link: http://lkml.kernel.org/r/20200525221556.4270-1-jcmvbkbc@gmail.com
Link: http://lkml.kernel.org/r/20200515143646.3857579-23-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/xtensa/include/asm/cacheflush.h |    2 ++
 1 file changed, 2 insertions(+)

--- a/arch/xtensa/include/asm/cacheflush.h~xtensa-implement-flush_icache_user_range
+++ a/arch/xtensa/include/asm/cacheflush.h
@@ -145,6 +145,8 @@ void local_flush_cache_page(struct vm_ar
 
 #endif
 
+#define flush_icache_user_range flush_icache_range
+
 /* Ensure consistency between data and instruction cache. */
 #define local_flush_icache_range(start, end)				\
 	do {								\
_

[patch 47/54] arm: rename flush_cache_user_range to flush_icache_user_range

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: arm: rename flush_cache_user_range to flush_icache_user_range

flush_icache_user_range will be the name for a generic primitive.
Move the arm name so that arm already has an implementation.

Link: http://lkml.kernel.org/r/20200515143646.3857579-24-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Russell King <linux@armlinux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/arm/include/asm/cacheflush.h |    4 ++--
 arch/arm/kernel/traps.c           |    2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

--- a/arch/arm/include/asm/cacheflush.h~arm-rename-flush_cache_user_range-to-flush_icache_user_range
+++ a/arch/arm/include/asm/cacheflush.h
@@ -258,11 +258,11 @@ extern void flush_cache_page(struct vm_a
 #define flush_cache_dup_mm(mm) flush_cache_mm(mm)
 
 /*
- * flush_cache_user_range is used when we want to ensure that the
+ * flush_icache_user_range is used when we want to ensure that the
  * Harvard caches are synchronised for the user space address range.
  * This is used for the ARM private sys_cacheflush system call.
  */
-#define flush_cache_user_range(s,e)	__cpuc_coherent_user_range(s,e)
+#define flush_icache_user_range(s,e)	__cpuc_coherent_user_range(s,e)
 
 /*
  * Perform necessary cache operations to ensure that data previously
--- a/arch/arm/kernel/traps.c~arm-rename-flush_cache_user_range-to-flush_icache_user_range
+++ a/arch/arm/kernel/traps.c
@@ -566,7 +566,7 @@ __do_cache_op(unsigned long start, unsig
 		if (fatal_signal_pending(current))
 			return 0;
 
-		ret = flush_cache_user_range(start, start + chunk);
+		ret = flush_icache_user_range(start, start + chunk);
 		if (ret)
 			return ret;
 
_

[patch 48/54] m68k: implement flush_icache_user_range

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: m68k: implement flush_icache_user_range

Rename the current flush_icache_range to flush_icache_user_range as per
commit ae92ef8a4424 ("PATCH] flush icache in correct context") there seems
to be an assumption that it operates on user addresses.  Add a
flush_icache_range around it that for now is a no-op.

Link: http://lkml.kernel.org/r/20200515143646.3857579-25-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/m68k/include/asm/cacheflush_mm.h |    2 ++
 arch/m68k/mm/cache.c                  |    7 ++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

--- a/arch/m68k/include/asm/cacheflush_mm.h~m68k-implement-flush_icache_user_range
+++ a/arch/m68k/include/asm/cacheflush_mm.h
@@ -257,6 +257,8 @@ static inline void __flush_page_to_ram(v
 extern void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
 				    unsigned long addr, int len);
 extern void flush_icache_range(unsigned long address, unsigned long endaddr);
+extern void flush_icache_user_range(unsigned long address,
+		unsigned long endaddr);
 
 static inline void copy_to_user_page(struct vm_area_struct *vma,
 				     struct page *page, unsigned long vaddr,
--- a/arch/m68k/mm/cache.c~m68k-implement-flush_icache_user_range
+++ a/arch/m68k/mm/cache.c
@@ -73,7 +73,7 @@ static unsigned long virt_to_phys_slow(u
 
 /* Push n pages at kernel virtual address and clear the icache */
 /* RZ: use cpush %bc instead of cpush %dc, cinv %ic */
-void flush_icache_range(unsigned long address, unsigned long endaddr)
+void flush_icache_user_range(unsigned long address, unsigned long endaddr)
 {
 	if (CPU_IS_COLDFIRE) {
 		unsigned long start, end;
@@ -104,6 +104,11 @@ void flush_icache_range(unsigned long ad
 			      : "di" (FLUSH_I));
 	}
 }
+
+void flush_icache_range(unsigned long address, unsigned long endaddr)
+{
+	flush_icache_user_range(address, endaddr);
+}
 EXPORT_SYMBOL(flush_icache_range);
 
 void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
_

[patch 49/54] exec: only build read_code when needed

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: exec: only build read_code when needed

Only build read_code when binary formats that use it are built into the
kernel.

Link: http://lkml.kernel.org/r/20200515143646.3857579-26-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/exec.c |    3 +++
 1 file changed, 3 insertions(+)

--- a/fs/exec.c~exec-only-build-read_code-when-needed
+++ a/fs/exec.c
@@ -1053,6 +1053,8 @@ out:
 }
 EXPORT_SYMBOL_GPL(kernel_read_file_from_fd);
 
+#if defined(CONFIG_HAVE_AOUT) || defined(CONFIG_BINFMT_FLAT) || \
+    defined(CONFIG_BINFMT_ELF_FDPIC)
 ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
 {
 	ssize_t res = vfs_read(file, (void __user *)addr, len, &pos);
@@ -1061,6 +1063,7 @@ ssize_t read_code(struct file *file, uns
 	return res;
 }
 EXPORT_SYMBOL(read_code);
+#endif
 
 /*
  * Maps the mm_struct mm into the current task struct.
_

[patch 50/54] exec: use flush_icache_user_range in read_code

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: exec: use flush_icache_user_range in read_code

read_code operates on user addresses.

Link: http://lkml.kernel.org/r/20200515143646.3857579-27-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/exec.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/exec.c~exec-use-flush_icache_user_range-in-read_code
+++ a/fs/exec.c
@@ -1059,7 +1059,7 @@ ssize_t read_code(struct file *file, uns
 {
 	ssize_t res = vfs_read(file, (void __user *)addr, len, &pos);
 	if (res > 0)
-		flush_icache_range(addr, addr + len);
+		flush_icache_user_range(addr, addr + len);
 	return res;
 }
 EXPORT_SYMBOL(read_code);
_

[patch 51/54] binfmt_flat: use flush_icache_user_range

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: binfmt_flat: use flush_icache_user_range

load_flat_file works on user addresses.

Link: http://lkml.kernel.org/r/20200515143646.3857579-28-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 fs/binfmt_flat.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/fs/binfmt_flat.c~binfmt_flat-use-flush_icache_user_range
+++ a/fs/binfmt_flat.c
@@ -854,7 +854,7 @@ static int load_flat_file(struct linux_b
 #endif /* CONFIG_BINFMT_FLAT_OLD */
 	}
 
-	flush_icache_range(start_code, end_code);
+	flush_icache_user_range(start_code, end_code);
 
 	/* zero the BSS,  BRK and stack areas */
 	if (clear_user((void __user *)(datapos + data_len), bss_len +
_

[patch 52/54] nommu: use flush_icache_user_range in brk and mmap

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: nommu: use flush_icache_user_range in brk and mmap

These obviously operate on user addresses.

Link: http://lkml.kernel.org/r/20200515143646.3857579-29-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Greg Ungerer <gerg@linux-m68k.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/nommu.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/mm/nommu.c~nommu-use-flush_icache_user_range-in-brk-and-mmap
+++ a/mm/nommu.c
@@ -433,7 +433,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	/*
 	 * Ok, looks good - let it rip.
 	 */
-	flush_icache_range(mm->brk, brk);
+	flush_icache_user_range(mm->brk, brk);
 	return mm->brk = brk;
 }
 
@@ -1277,7 +1277,7 @@ share:
 	/* we flush the region from the icache only when the first executable
 	 * mapping of it is made  */
 	if (vma->vm_flags & VM_EXEC && !region->vm_icache_flushed) {
-		flush_icache_range(region->vm_start, region->vm_end);
+		flush_icache_user_range(region->vm_start, region->vm_end);
 		region->vm_icache_flushed = true;
 	}
 
_

[patch 53/54] module: move the set_fs hack for flush_icache_range to m68k

[Andrew Morton]

From: Christoph Hellwig <hch@lst.de>
Subject: module: move the set_fs hack for flush_icache_range to m68k

flush_icache_range generally operates on kernel addresses, but for some
reason m68k needed a set_fs override.  Move that into the m68k code insted
of keeping it in the module loader.

Link: http://lkml.kernel.org/r/20200515143646.3857579-30-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Jessica Yu <jeyu@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Yonghong Song <yhs@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/m68k/mm/cache.c |    4 ++++
 kernel/module.c      |    8 --------
 2 files changed, 4 insertions(+), 8 deletions(-)

--- a/arch/m68k/mm/cache.c~module-move-the-set_fs-hack-for-flush_icache_range-to-m68k
+++ a/arch/m68k/mm/cache.c
@@ -107,7 +107,11 @@ void flush_icache_user_range(unsigned lo
 
 void flush_icache_range(unsigned long address, unsigned long endaddr)
 {
+	mm_segment_t old_fs = get_fs();
+
+	set_fs(KERNEL_DS);
 	flush_icache_user_range(address, endaddr);
+	set_fs(old_fs);
 }
 EXPORT_SYMBOL(flush_icache_range);
 
--- a/kernel/module.c~module-move-the-set_fs-hack-for-flush_icache_range-to-m68k
+++ a/kernel/module.c
@@ -3344,12 +3344,6 @@ static int check_module_license_and_vers
 
 static void flush_module_icache(const struct module *mod)
 {
-	mm_segment_t old_fs;
-
-	/* flush the icache in correct context */
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-
 	/*
 	 * Flush the instruction cache, since we've played with text.
 	 * Do it before processing of module parameters, so the module
@@ -3361,8 +3355,6 @@ static void flush_module_icache(const st
 				   + mod->init_layout.size);
 	flush_icache_range((unsigned long)mod->core_layout.base,
 			   (unsigned long)mod->core_layout.base + mod->core_layout.size);
-
-	set_fs(old_fs);
 }
 
 int __weak module_frob_arch_sections(Elf_Ehdr *hdr,
_

[patch 54/54] doc: cgroup: update note about conditions when oom killer is invoked

[Andrew Morton]

From: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Subject: doc: cgroup: update note about conditions when oom killer is invoked

Starting from v4.19 commit 29ef680ae7c2 ("memcg, oom: move out_of_memory
back to the charge path") cgroup oom killer is no longer invoked only from
page faults.  Now it implements the same semantics as global OOM killer:
allocation context invokes OOM killer and keeps retrying until success.

[akpm@linux-foundation.org: fixes per Randy]
Link: http://lkml.kernel.org/r/158894738928.208854.5244393925922074518.stgit@buzz
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/cgroup-v2.rst |   17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

--- a/Documentation/admin-guide/cgroup-v2.rst~doc-cgroup-update-note-about-conditions-when-oom-killer-is-invoked
+++ a/Documentation/admin-guide/cgroup-v2.rst
@@ -1170,6 +1170,13 @@ PAGE_SIZE multiple when read back.
 	Under certain circumstances, the usage may go over the limit
 	temporarily.
 
+	In default configuration regular 0-order allocations always
+	succeed unless OOM killer chooses current task as a victim.
+
+	Some kinds of allocations don't invoke the OOM killer.
+	Caller could retry them differently, return into userspace
+	as -ENOMEM or silently ignore in cases like disk readahead.
+
 	This is the ultimate protection mechanism.  As long as the
 	high limit is used and monitored properly, this limit's
 	utility is limited to providing the final safety net.
@@ -1226,17 +1233,9 @@ PAGE_SIZE multiple when read back.
 		The number of time the cgroup's memory usage was
 		reached the limit and allocation was about to fail.
 
-		Depending on context result could be invocation of OOM
-		killer and retrying allocation or failing allocation.
-
-		Failed allocation in its turn could be returned into
-		userspace as -ENOMEM or silently ignored in cases like
-		disk readahead.  For now OOM in memory cgroup kills
-		tasks iff shortage has happened inside page fault.
-
 		This event is not raised if the OOM killer is not
 		considered as an option, e.g. for failed high-order
-		allocations.
+		allocations or if caller asked to not retry attempts.
 
 	  oom_kill
 		The number of processes belonging to this cgroup
_