From 250bbbdbed93ca27c9f4d445c960a87d9f7e2044 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Tue, 20 Jun 2017 21:52:08 +0200 Subject: iio: common: st_sensors: move st_sensors_of_i2c_probe() in common code Move st_sensors_of_i2c_probe() in st_sensors_core and rename it in st_sensors_of_name_probe(). That change is necessary to add device-tree support in spi code otherwise the rest of the autodetection will fail since spi->modalias (and indio_dev->name) will be set using compatible string value that differs from standard sensor name Signed-off-by: Lorenzo Bianconi Signed-off-by: Jonathan Cameron --- include/linux/iio/common/st_sensors.h | 12 ++++++++++++ include/linux/iio/common/st_sensors_i2c.h | 10 ---------- 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 497f2b3a5a62..1f8211b6438b 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -325,4 +325,16 @@ ssize_t st_sensors_sysfs_sampling_frequency_avail(struct device *dev, ssize_t st_sensors_sysfs_scale_avail(struct device *dev, struct device_attribute *attr, char *buf); +#ifdef CONFIG_OF +void st_sensors_of_name_probe(struct device *dev, + const struct of_device_id *match, + char *name, int len); +#else +static inline void st_sensors_of_name_probe(struct device *dev, + const struct of_device_id *match, + char *name, int len) +{ +} +#endif + #endif /* ST_SENSORS_H */ diff --git a/include/linux/iio/common/st_sensors_i2c.h b/include/linux/iio/common/st_sensors_i2c.h index 254de3c7dde8..0a2c25e06d1f 100644 --- a/include/linux/iio/common/st_sensors_i2c.h +++ b/include/linux/iio/common/st_sensors_i2c.h @@ -18,16 +18,6 @@ void st_sensors_i2c_configure(struct iio_dev *indio_dev, struct i2c_client *client, struct st_sensor_data *sdata); -#ifdef CONFIG_OF -void st_sensors_of_i2c_probe(struct i2c_client *client, - const struct of_device_id *match); -#else -static inline void st_sensors_of_i2c_probe(struct i2c_client *client, - const struct of_device_id *match) -{ -} -#endif - #ifdef CONFIG_ACPI int st_sensors_match_acpi_device(struct device *dev); #else -- cgit v1.2.3 From 5ea0727b163cb5575e36397a12eade68a1f35f24 Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Wed, 14 Jun 2017 18:12:01 -0700 Subject: x86/syscalls: Check address limit on user-mode return Ensure the address limit is a user-mode segment before returning to user-mode. Otherwise a process can corrupt kernel-mode memory and elevate privileges [1]. The set_fs function sets the TIF_SETFS flag to force a slow path on return. In the slow path, the address limit is checked to be USER_DS if needed. The addr_limit_user_check function is added as a cross-architecture function to check the address limit. [1] https://bugs.chromium.org/p/project-zero/issues/detail?id=990 Signed-off-by: Thomas Garnier Signed-off-by: Thomas Gleixner Cc: Mark Rutland Cc: kernel-hardening@lists.openwall.com Cc: Catalin Marinas Cc: Will Deacon Cc: David Howells Cc: Dave Hansen Cc: Miroslav Benes Cc: Chris Metcalf Cc: Pratyush Anand Cc: Russell King Cc: Petr Mladek Cc: Rik van Riel Cc: Kees Cook Cc: Arnd Bergmann Cc: Al Viro Cc: Andy Lutomirski Cc: Josh Poimboeuf Cc: linux-arm-kernel@lists.infradead.org Cc: Will Drewry Cc: linux-api@vger.kernel.org Cc: Oleg Nesterov Cc: Andy Lutomirski Cc: Paolo Bonzini Link: http://lkml.kernel.org/r/20170615011203.144108-1-thgarnie@google.com --- include/linux/syscalls.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 980c3c9b06f8..ac0cf6fb25d6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -206,6 +206,22 @@ extern struct trace_event_functions exit_syscall_print_funcs; } \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) +#ifdef TIF_FSCHECK +/* + * Called before coming back to user-mode. Returning to user-mode with an + * address limit different than USER_DS can allow to overwrite kernel memory. + */ +static inline void addr_limit_user_check(void) +{ + + if (!test_thread_flag(TIF_FSCHECK)) + return; + + BUG_ON(!segment_eq(get_fs(), USER_DS)); + clear_thread_flag(TIF_FSCHECK); +} +#endif + asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr); asmlinkage long sys_time(time_t __user *tloc); -- cgit v1.2.3 From 9b1404c24a357332cb2a6df7c4337e943a4545fd Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 9 Jul 2017 10:34:35 -0400 Subject: msgrcv(2), msgsnd(2): move compat to native Signed-off-by: Al Viro --- include/linux/msg.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msg.h b/include/linux/msg.h index f3f302f9c197..4e5ec3cbf464 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -31,12 +31,4 @@ struct msg_queue { struct list_head q_senders; }; -/* Helper routines for sys_msgsnd and sys_msgrcv */ -extern long do_msgsnd(int msqid, long mtype, void __user *mtext, - size_t msgsz, int msgflg); -extern long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, - int msgflg, - long (*msg_fill)(void __user *, struct msg_msg *, - size_t)); - #endif /* _LINUX_MSG_H */ -- cgit v1.2.3 From 44ee454670122a959112caaa7aad86d8cacab1ff Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 9 Jul 2017 10:50:14 -0400 Subject: semtimedop(): move compat to native ... and finally kill the sodding compat_convert_timespec() Signed-off-by: Al Viro --- include/linux/compat.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 5a6a109b4a50..edae425ca8c0 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -171,15 +171,6 @@ extern int get_compat_itimerspec64(struct itimerspec64 *its, extern int put_compat_itimerspec64(const struct itimerspec64 *its, struct compat_itimerspec __user *uits); -/* - * This function convert a timespec if necessary and returns a *user - * space* pointer. If no conversion is necessary, it returns the - * initial pointer. NULL is a legitimate argument and will always - * output NULL. - */ -extern int compat_convert_timespec(struct timespec __user **, - const void __user *); - struct compat_iovec { compat_uptr_t iov_base; compat_size_t iov_len; -- cgit v1.2.3 From 9d5b86ac13c573795525ecac6ed2db39ab23e2a8 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Sun, 16 Jul 2017 10:28:22 -0400 Subject: fs/locks: Remove fl_nspid and use fs-specific l_pid for remote locks Since commit c69899a17ca4 "NFSv4: Update of VFS byte range lock must be atomic with the stateid update", NFSv4 has been inserting locks in rpciod worker context. The result is that the file_lock's fl_nspid is the kworker's pid instead of the original userspace pid. The fl_nspid is only used to represent the namespaced virtual pid number when displaying locks or returning from F_GETLK. There's no reason to set it for every inserted lock, since we can usually just look it up from fl_pid. So, instead of looking up and holding struct pid for every lock, let's just look up the virtual pid number from fl_pid when it is needed. That means we can remove fl_nspid entirely. The translaton and presentation of fl_pid should handle the following four cases: 1 - F_GETLK on a remote file with a remote lock: In this case, the filesystem should determine the l_pid to return here. Filesystems should indicate that the fl_pid represents a non-local pid value that should not be translated by returning an fl_pid <= 0. 2 - F_GETLK on a local file with a remote lock: This should be the l_pid of the lock manager process, and translated. 3 - F_GETLK on a remote file with a local lock, and 4 - F_GETLK on a local file with a local lock: These should be the translated l_pid of the local locking process. Fuse was already doing the correct thing by translating the pid into the caller's namespace. With this change we must update fuse to translate to init's pid namespace, so that the locks API can then translate from init's pid namespace into the pid namespace of the caller. With this change, the locks API will expect that if a filesystem returns a remote pid as opposed to a local pid for F_GETLK, that remote pid will be <= 0. This signifies that the pid is remote, and the locks API will forego translating that pid into the pid namespace of the local calling process. Finally, we convert remote filesystems to present remote pids using negative numbers. Have lustre, 9p, ceph, cifs, and dlm negate the remote pid returned for F_GETLK lock requests. Since local pids will never be larger than PID_MAX_LIMIT (which is currently defined as <= 4 million), but pid_t is an unsigned int, we should have plenty of room to represent remote pids with negative numbers if we assume that remote pid numbers are similarly limited. If this is not the case, then we run the risk of having a remote pid returned for which there is also a corresponding local pid. This is a problem we have now, but this patch should reduce the chances of that occurring, while also returning those remote pid numbers, for whatever that may be worth. Signed-off-by: Benjamin Coddington Signed-off-by: Jeff Layton --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7b5d6816542b..f0b108af9b02 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -999,7 +999,6 @@ struct file_lock { unsigned char fl_type; unsigned int fl_pid; int fl_link_cpu; /* what cpu's list is this on? */ - struct pid *fl_nspid; wait_queue_head_t fl_wait; struct file *fl_file; loff_t fl_start; -- cgit v1.2.3 From 788b950c62e06b02278a0fd380e1a0667996ce3c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 16 Jul 2017 21:43:33 -0400 Subject: cgroup: distinguish local and children populated states cgrp->populated_cnt counts both local (the cgroup's populated css_sets) and subtree proper (populated children) so that it's only zero when the whole subtree, including self, is empty. This patch splits the counter into two so that local and children populated states are tracked separately. It allows finer-grained tests on the state of the hierarchy which will be used to replace css_set walking local populated test. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 13 +++++++++---- include/linux/cgroup.h | 2 +- 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 09f4c7df1478..ae7bc1e70085 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -263,11 +263,16 @@ struct cgroup { /* * Each non-empty css_set associated with this cgroup contributes - * one to populated_cnt. All children with non-zero popuplated_cnt - * of their own contribute one. The count is zero iff there's no - * task in this cgroup or its subtree. + * one to nr_populated_csets. The counter is zero iff this cgroup + * doesn't have any tasks. + * + * All children which have non-zero nr_populated_csets and/or + * nr_populated_children of their own contribute one to + * nr_populated_children. The counter is zero iff this cgroup's + * subtree proper doesn't have any tasks. */ - int populated_cnt; + int nr_populated_csets; + int nr_populated_children; struct kernfs_node *kn; /* cgroup kernfs entry */ struct cgroup_file procs_file; /* handle for "cgroup.procs" */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 710a005c6b7a..308b10797a54 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -537,7 +537,7 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { - return cgrp->populated_cnt; + return cgrp->nr_populated_csets + cgrp->nr_populated_children; } /* returns ino associated with a cgroup */ -- cgit v1.2.3 From a38905e6aa1a758af003b80f3318196eadb86dfe Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:49 +0800 Subject: sctp: remove the typedef sctp_ipv4addr_param_t This patch is to remove the typedef sctp_ipv4addr_param_t, and replace with struct sctp_ipv4addr_param in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 99e866487e2f..e42095d7ce57 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -273,10 +273,10 @@ struct sctp_init_chunk { /* Section 3.3.2.1. IPv4 Address Parameter (5) */ -typedef struct sctp_ipv4addr_param { +struct sctp_ipv4addr_param { struct sctp_paramhdr param_hdr; - struct in_addr addr; -} sctp_ipv4addr_param_t; + struct in_addr addr; +}; /* Section 3.3.2.1. IPv6 Address Parameter (6) */ typedef struct sctp_ipv6addr_param { -- cgit v1.2.3 From 00987cc07e3f0f01699800cd89adf13a908cdee5 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:50 +0800 Subject: sctp: remove the typedef sctp_ipv6addr_param_t This patch is to remove the typedef sctp_ipv6addr_param_t, and replace with struct sctp_ipv6addr_param in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index e42095d7ce57..6b45c8a38642 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -279,10 +279,10 @@ struct sctp_ipv4addr_param { }; /* Section 3.3.2.1. IPv6 Address Parameter (6) */ -typedef struct sctp_ipv6addr_param { +struct sctp_ipv6addr_param { struct sctp_paramhdr param_hdr; struct in6_addr addr; -} sctp_ipv6addr_param_t; +}; /* Section 3.3.2.1 Cookie Preservative (9) */ typedef struct sctp_cookie_preserve_param { -- cgit v1.2.3 From 365ddb65e77f6b99d4aba09e0d8a096aada57815 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:51 +0800 Subject: sctp: remove the typedef sctp_cookie_preserve_param_t This patch is to remove the typedef sctp_cookie_preserve_param_t, and replace with struct sctp_cookie_preserve_param in the places where it's using this typedef. It is also to fix some indents in sctp_sf_do_5_2_6_stale(). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 6b45c8a38642..d8f9d8f8649b 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -285,10 +285,10 @@ struct sctp_ipv6addr_param { }; /* Section 3.3.2.1 Cookie Preservative (9) */ -typedef struct sctp_cookie_preserve_param { +struct sctp_cookie_preserve_param { struct sctp_paramhdr param_hdr; - __be32 lifespan_increment; -} sctp_cookie_preserve_param_t; + __be32 lifespan_increment; +}; /* Section 3.3.2.1 Host Name Address (11) */ typedef struct sctp_hostname_param { -- cgit v1.2.3 From df9af0063f154c1a4f22a5570749d185d080cf56 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:52 +0800 Subject: sctp: remove the typedef sctp_hostname_param_t Remove this typedef, there is even no places using it. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index d8f9d8f8649b..c43e9067d41a 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -291,10 +291,10 @@ struct sctp_cookie_preserve_param { }; /* Section 3.3.2.1 Host Name Address (11) */ -typedef struct sctp_hostname_param { +struct sctp_hostname_param { struct sctp_paramhdr param_hdr; uint8_t hostname[0]; -} sctp_hostname_param_t; +}; /* Section 3.3.2.1 Supported Address Types (12) */ typedef struct sctp_supported_addrs_param { -- cgit v1.2.3 From e925d506f1a21f7fd24a8fdd3e73e0810c655de4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:53 +0800 Subject: sctp: remove the typedef sctp_supported_addrs_param_t This patch is to remove the typedef sctp_supported_addrs_param_t, and replace with struct sctp_supported_addrs_param in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index c43e9067d41a..3ca3ab7302a6 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -297,10 +297,10 @@ struct sctp_hostname_param { }; /* Section 3.3.2.1 Supported Address Types (12) */ -typedef struct sctp_supported_addrs_param { +struct sctp_supported_addrs_param { struct sctp_paramhdr param_hdr; __be16 types[0]; -} sctp_supported_addrs_param_t; +}; /* Appendix A. ECN Capable (32768) */ typedef struct sctp_ecn_capable_param { -- cgit v1.2.3 From c1dd5df39be5a98c843b9352c22c5569f84bec44 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:54 +0800 Subject: sctp: remove struct sctp_ecn_capable_param Remove it, there is even no places using it. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 3ca3ab7302a6..75524829aa81 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -302,11 +302,6 @@ struct sctp_supported_addrs_param { __be16 types[0]; }; -/* Appendix A. ECN Capable (32768) */ -typedef struct sctp_ecn_capable_param { - struct sctp_paramhdr param_hdr; -} sctp_ecn_capable_param_t; - /* ADDIP Section 3.2.6 Adaptation Layer Indication */ typedef struct sctp_adaptation_ind_param { struct sctp_paramhdr param_hdr; -- cgit v1.2.3 From 85f6bd24ac579ef0926eb4c564ba1f3c8a7f8563 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:55 +0800 Subject: sctp: remove the typedef sctp_adaptation_ind_param_t This patch is to remove the typedef sctp_adaptation_ind_param_t, and replace with struct sctp_adaptation_ind_param in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 75524829aa81..72b87874ea76 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -303,10 +303,10 @@ struct sctp_supported_addrs_param { }; /* ADDIP Section 3.2.6 Adaptation Layer Indication */ -typedef struct sctp_adaptation_ind_param { +struct sctp_adaptation_ind_param { struct sctp_paramhdr param_hdr; __be32 adaptation_ind; -} sctp_adaptation_ind_param_t; +}; /* ADDIP Section 4.2.7 Supported Extensions Parameter */ typedef struct sctp_supported_ext_param { -- cgit v1.2.3 From 15328d9feede450d64ff77cac5d25bc734ec8b27 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:56 +0800 Subject: sctp: remove the typedef sctp_supported_ext_param_t This patch is to remove the typedef sctp_supported_ext_param_t, and replace with struct sctp_supported_ext_param in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 72b87874ea76..76245685f923 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -309,10 +309,10 @@ struct sctp_adaptation_ind_param { }; /* ADDIP Section 4.2.7 Supported Extensions Parameter */ -typedef struct sctp_supported_ext_param { +struct sctp_supported_ext_param { struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} sctp_supported_ext_param_t; +}; /* AUTH Section 3.1 Random */ typedef struct sctp_random_param { -- cgit v1.2.3 From b02db702face3791889a4fcf06691c086648ee89 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:57 +0800 Subject: sctp: remove the typedef sctp_random_param_t This patch is to remove the typedef sctp_random_param_t, and replace with struct sctp_random_param in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 76245685f923..9b1aa3907c9e 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -315,10 +315,10 @@ struct sctp_supported_ext_param { }; /* AUTH Section 3.1 Random */ -typedef struct sctp_random_param { +struct sctp_random_param { struct sctp_paramhdr param_hdr; __u8 random_val[0]; -} sctp_random_param_t; +}; /* AUTH Section 3.2 Chunk List */ typedef struct sctp_chunks_param { -- cgit v1.2.3 From a762a9d94d44980e3690f9de87b918376daa6428 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:58 +0800 Subject: sctp: remove the typedef sctp_chunks_param_t This patch is to remove the typedef sctp_chunks_param_t, and replace with struct sctp_chunks_param in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 9b1aa3907c9e..b52def9bcfa1 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -321,10 +321,10 @@ struct sctp_random_param { }; /* AUTH Section 3.2 Chunk List */ -typedef struct sctp_chunks_param { +struct sctp_chunks_param { struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} sctp_chunks_param_t; +}; /* AUTH Section 3.3 HMAC Algorithm */ typedef struct sctp_hmac_algo_param { -- cgit v1.2.3 From 1474774a7f0daf9878fd9537a24714f419e744ed Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 17 Jul 2017 11:29:59 +0800 Subject: sctp: remove the typedef sctp_hmac_algo_param_t This patch is to remove the typedef sctp_hmac_algo_param_t, and replace with struct sctp_hmac_algo_param in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index b52def9bcfa1..913474dfc96c 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -327,10 +327,10 @@ struct sctp_chunks_param { }; /* AUTH Section 3.3 HMAC Algorithm */ -typedef struct sctp_hmac_algo_param { +struct sctp_hmac_algo_param { struct sctp_paramhdr param_hdr; __be16 hmac_ids[0]; -} sctp_hmac_algo_param_t; +}; /* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2): * The INIT ACK chunk is used to acknowledge the initiation of an SCTP -- cgit v1.2.3 From 94e92e7ac90d06e1e839e112d3ae80b2457dbdd7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 17 Jul 2017 08:45:34 +0100 Subject: vfs: Add sb_rdonly(sb) to query the MS_RDONLY flag on s_flags Add an sb_rdonly() function to query the MS_RDONLY flag on sb->s_flags preparatory to providing an SB_RDONLY flag. Signed-off-by: David Howells --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7b5d6816542b..6ae137c1bdf6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1844,7 +1844,8 @@ struct super_operations { */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) -#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY) +static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & MS_RDONLY; } +#define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \ -- cgit v1.2.3 From e462ec50cb5fad19f6003a3d8087f4a0945dd2b1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 17 Jul 2017 08:45:35 +0100 Subject: VFS: Differentiate mount flags (MS_*) from internal superblock flags Differentiate the MS_* flags passed to mount(2) from the internal flags set in the super_block's s_flags. s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. In this patch, just the headers are altered and some kernel code where blind automated conversion isn't necessarily correct. Note that this shows up some interesting issues: (1) Some MS_* flags get translated to MNT_* flags (such as MS_NODEV -> MNT_NODEV) without passing this on to the filesystem, but some filesystems set such flags anyway. (2) The ->remount_fs() methods of some filesystems adjust the *flags argument by setting MS_* flags in it, such as MS_NOATIME - but these flags are then scrubbed by do_remount_sb() (only the occupants of MS_RMT_MASK are permitted: MS_RDONLY, MS_SYNCHRONOUS, MS_MANDLOCK, MS_I_VERSION and MS_LAZYTIME) I'm not sure what's the best way to solve all these cases. Suggested-by: Al Viro Signed-off-by: David Howells --- include/linux/fs.h | 45 ++++++++++++++++++++++++++++++++++++--------- 1 file changed, 36 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6ae137c1bdf6..3d6ee0c0ebb0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1269,6 +1269,33 @@ extern int send_sigurg(struct fown_struct *fown); struct mm_struct; +/* + * sb->s_flags. Note that these mirror the equivalent MS_* flags where + * represented in both. + */ +#define SB_RDONLY 1 /* Mount read-only */ +#define SB_NOSUID 2 /* Ignore suid and sgid bits */ +#define SB_NODEV 4 /* Disallow access to device special files */ +#define SB_NOEXEC 8 /* Disallow program execution */ +#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ +#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ +#define SB_NOATIME 1024 /* Do not update access times. */ +#define SB_NODIRATIME 2048 /* Do not update directory access times */ +#define SB_SILENT 32768 +#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ +#define SB_I_VERSION (1<<23) /* Update inode I_version field */ +#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ + +/* These sb flags are internal to the kernel */ +#define SB_SUBMOUNT (1<<26) +#define SB_NOREMOTELOCK (1<<27) +#define SB_NOSEC (1<<28) +#define SB_BORN (1<<29) +#define SB_ACTIVE (1<<30) +#define SB_NOUSER (1<<31) + /* * Umount options */ @@ -1835,7 +1862,7 @@ struct super_operations { * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * - * Exception: MS_RDONLY is always applied to the entire file system. + * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their @@ -1846,18 +1873,18 @@ struct super_operations { static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & MS_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) -#define IS_SYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS) || \ +#define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) -#define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \ +#define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) -#define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK) -#define IS_NOATIME(inode) __IS_FLG(inode, MS_RDONLY|MS_NOATIME) -#define IS_I_VERSION(inode) __IS_FLG(inode, MS_I_VERSION) +#define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) +#define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) +#define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) -#define IS_POSIXACL(inode) __IS_FLG(inode, MS_POSIXACL) +#define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) @@ -2178,7 +2205,7 @@ static inline int __mandatory_lock(struct inode *ino) } /* - * ... and these candidates should be on MS_MANDLOCK mounted fs, + * ... and these candidates should be on SB_MANDLOCK mounted fs, * otherwise these will be advisory locks */ @@ -3274,7 +3301,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode) static inline void inode_has_no_xattr(struct inode *inode) { - if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC)) + if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } -- cgit v1.2.3 From c698316661096e036b54448039b35e1c2c5809f0 Mon Sep 17 00:00:00 2001 From: Benson Leung Date: Mon, 17 Jul 2017 11:41:39 +0200 Subject: extcon: cros-ec: Add extcon-cros-ec driver to support display out This is the driver for the USB Type C cable detection mechanism built into the ChromeOS Embedded Controller on systems that have USB Type-C ports. At present, this allows for the presence of display out, but in future, it may also be used to notify host and device type cables and the presence of power. Signed-off-by: Benson Leung Signed-off-by: Enric Balletbo i Serra Acked-by: Chanwoo Choi Acked-by: Lee Jones Signed-off-by: Chanwoo Choi --- include/linux/mfd/cros_ec_commands.h | 75 ++++++++++++++++++++++++++++++++++++ 1 file changed, 75 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index 190c8f4afa02..2b16e95b9bb8 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -285,6 +285,11 @@ enum host_event_code { EC_HOST_EVENT_HANG_DETECT = 20, /* Hang detect logic detected a hang and warm rebooted the AP */ EC_HOST_EVENT_HANG_REBOOT = 21, + /* PD MCU triggering host event */ + EC_HOST_EVENT_PD_MCU = 22, + + /* EC desires to change state of host-controlled USB mux */ + EC_HOST_EVENT_USB_MUX = 28, /* * The high bit of the event mask is not used as a host event code. If @@ -2905,6 +2910,76 @@ struct ec_params_usb_pd_control { uint8_t mux; } __packed; +#define PD_CTRL_RESP_ENABLED_COMMS (1 << 0) /* Communication enabled */ +#define PD_CTRL_RESP_ENABLED_CONNECTED (1 << 1) /* Device connected */ +#define PD_CTRL_RESP_ENABLED_PD_CAPABLE (1 << 2) /* Partner is PD capable */ + +struct ec_response_usb_pd_control_v1 { + uint8_t enabled; + uint8_t role; + uint8_t polarity; + char state[32]; +} __packed; + +#define EC_CMD_USB_PD_PORTS 0x102 + +struct ec_response_usb_pd_ports { + uint8_t num_ports; +} __packed; + +#define EC_CMD_USB_PD_POWER_INFO 0x103 + +#define PD_POWER_CHARGING_PORT 0xff +struct ec_params_usb_pd_power_info { + uint8_t port; +} __packed; + +enum usb_chg_type { + USB_CHG_TYPE_NONE, + USB_CHG_TYPE_PD, + USB_CHG_TYPE_C, + USB_CHG_TYPE_PROPRIETARY, + USB_CHG_TYPE_BC12_DCP, + USB_CHG_TYPE_BC12_CDP, + USB_CHG_TYPE_BC12_SDP, + USB_CHG_TYPE_OTHER, + USB_CHG_TYPE_VBUS, + USB_CHG_TYPE_UNKNOWN, +}; + +struct usb_chg_measures { + uint16_t voltage_max; + uint16_t voltage_now; + uint16_t current_max; + uint16_t current_lim; +} __packed; + +struct ec_response_usb_pd_power_info { + uint8_t role; + uint8_t type; + uint8_t dualrole; + uint8_t reserved1; + struct usb_chg_measures meas; + uint32_t max_power; +} __packed; + +/* Get info about USB-C SS muxes */ +#define EC_CMD_USB_PD_MUX_INFO 0x11a + +struct ec_params_usb_pd_mux_info { + uint8_t port; /* USB-C port number */ +} __packed; + +/* Flags representing mux state */ +#define USB_PD_MUX_USB_ENABLED (1 << 0) +#define USB_PD_MUX_DP_ENABLED (1 << 1) +#define USB_PD_MUX_POLARITY_INVERTED (1 << 2) +#define USB_PD_MUX_HPD_IRQ (1 << 3) + +struct ec_response_usb_pd_mux_info { + uint8_t flags; /* USB_PD_MUX_*-encoded USB mux state */ +} __packed; + /*****************************************************************************/ /* * Passthru commands -- cgit v1.2.3 From c54182ec0e157988f0cafd1e8d37b68ab4210f87 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 29 Jun 2017 12:00:05 +0200 Subject: EDAC: Get rid of mci->mod_ver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is a write-only variable so get rid of it. Signed-off-by: Borislav Petkov Acked-by: Robert Richter Acked-by: Michal Simek Acked-by: Thor Thayer Acked-by: Tony Luck Cc: Mark Gross Cc: Tim Small Cc: Ranganathan Desikan Cc: "Arvind R." Cc: Jason Baron Cc: "Sören Brinkmann" Cc: Ralf Baechle Cc: David Daney Cc: Loc Ho Cc: linux-edac@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org Cc: linux-mips@linux-mips.org --- include/linux/edac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/edac.h b/include/linux/edac.h index 8ae0f45fafd6..cd75c173fd00 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -619,7 +619,6 @@ struct mem_ctl_info { */ struct device *pdev; const char *mod_name; - const char *mod_ver; const char *ctl_name; const char *dev_name; void *pvt_info; -- cgit v1.2.3 From a5d31a3f81c6fb13b381951bf6163444c0257e8b Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 15 Jun 2017 14:05:20 -0600 Subject: char_dev: extend dynamic allocation of majors into a higher range We've run into problems with running out of dynamicly assign char device majors particullarly on automated test systems with all-yes-configs. Roughly 40 dynamic assignments can be made with such kernels at this time while space is reserved for only 20. Currently, the kernel only prints a warning when dynamic allocation overflows the reserved region. And when this happens drivers that have fixed assignments can randomly fail depending on the order of initialization of other drivers. Thus, adding a new char device can cause unexpected failures in completely unrelated parts of the kernel. This patch solves the problem by extending dynamic major number allocations down from 511 once the 234-254 region fills up. Fixed majors already exist above 255 so the infrastructure to support high number majors is already in place. The patch reserves an additional 128 major numbers which should hopefully last us a while. Kernels that don't require more than 20 dynamic majors assigned (which is pretty typical) should not be affected by this change. Signed-off-by: Logan Gunthorpe Cc: Linus Torvalds Cc: Alan Cox Cc: Arnd Bergmann Cc: Linus Walleij Link: https://lkml.org/lkml/2017/6/4/107 Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7b5d6816542b..1773dcf1e318 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2473,6 +2473,10 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, #define CHRDEV_MAJOR_HASH_SIZE 255 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 +/* Marks the top and bottom of the second segment of free char majors */ +#define CHRDEV_MAJOR_DYN_EXT_START 511 +#define CHRDEV_MAJOR_DYN_EXT_END 384 + extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, -- cgit v1.2.3 From 8a932f73e5b4227bf787474b44dc70b6961d6246 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 15 Jun 2017 14:05:21 -0600 Subject: char_dev: order /proc/devices by major number Presently, the order of the char devices listed in /proc/devices is not entirely sequential. If a char device has a major number greater than CHRDEV_MAJOR_HASH_SIZE (255), it will be ordered as if its major were module 255. For example, 511 appears after 1. This patch cleans that up and prints each major number in the correct order, regardless of where they are stored in the hash table. In order to do this, we introduce CHRDEV_MAJOR_MAX as an artificial limit (chosen to be 511). It will then print all devices in major order number from 0 to the maximum. Signed-off-by: Logan Gunthorpe Cc: Linus Torvalds Cc: Greg Kroah-Hartman Cc: Alan Cox Cc: Arnd Bergmann Cc: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1773dcf1e318..b07433c335ca 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2470,7 +2470,7 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, #endif /* fs/char_dev.c */ -#define CHRDEV_MAJOR_HASH_SIZE 255 +#define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ -- cgit v1.2.3 From 133d55cdb2f1f9e258d6dc34594a6c565f10b3fd Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Fri, 16 Jun 2017 17:48:21 -0600 Subject: block: order /proc/devices by major number Presently, the order of the block devices listed in /proc/devices is not entirely sequential. If a block device has a major number greater than BLKDEV_MAJOR_HASH_SIZE (255), it will be ordered as if its major were module 255. For example, 511 appears after 1. This patch cleans that up and prints each major number in the correct order, regardless of where they are stored in the hash table. In order to do this, we introduce BLKDEV_MAJOR_MAX as an artificial limit (chosen to be 512). It will then print all devices in major order number from 0 to the maximum. Signed-off-by: Logan Gunthorpe Cc: Jens Axboe Cc: Jeff Layton Cc: "J. Bruce Fields" Signed-off-by: Greg Kroah-Hartman --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b07433c335ca..570dcc61fda6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2503,14 +2503,14 @@ static inline void unregister_chrdev(unsigned int major, const char *name) #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ #ifdef CONFIG_BLOCK -#define BLKDEV_MAJOR_HASH_SIZE 255 +#define BLKDEV_MAJOR_MAX 512 extern const char *__bdevname(dev_t, char *buffer); extern const char *bdevname(struct block_device *bdev, char *buffer); extern struct block_device *lookup_bdev(const char *); extern void blkdev_show(struct seq_file *,off_t); #else -#define BLKDEV_MAJOR_HASH_SIZE 0 +#define BLKDEV_MAJOR_MAX 0 #endif extern void init_special_inode(struct inode *, umode_t, dev_t); -- cgit v1.2.3 From c2a737eb2ea5682ffe63bc08003965496d6dc088 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 29 Jun 2017 09:39:02 +0530 Subject: debugfs: Add dummy implementation of few helpers This adds (missing) dummy implementations of debugfs_create_file_unsafe() and debugfs_create_ulong(). Signed-off-by: Viresh Kumar Signed-off-by: Greg Kroah-Hartman --- include/linux/debugfs.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index aa86e6d8c1aa..b93efc8feecd 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -196,6 +196,14 @@ static inline struct dentry *debugfs_create_file(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_file_unsafe(const char *name, + umode_t mode, struct dentry *parent, + void *data, + const struct file_operations *fops) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_file_size(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops, @@ -289,6 +297,14 @@ static inline struct dentry *debugfs_create_u64(const char *name, umode_t mode, return ERR_PTR(-ENODEV); } +static inline struct dentry *debugfs_create_ulong(const char *name, + umode_t mode, + struct dentry *parent, + unsigned long *value) +{ + return ERR_PTR(-ENODEV); +} + static inline struct dentry *debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value) -- cgit v1.2.3 From 95c40f41cfaf34e1c07812e93aa4b3263f9953f3 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sun, 25 Jun 2017 12:30:25 -0700 Subject: vmbus: drop unused ring_buffer_info elements The elements ring_data_start_offset and priv_write_index are not used. Signed-off-by: Stephen Hemminger Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b7d7bbec74e0..5e5f966bf37f 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -124,8 +124,6 @@ struct hv_ring_buffer_info { spinlock_t ring_lock; u32 ring_datasize; /* < ring_size */ - u32 ring_data_startoffset; - u32 priv_write_index; u32 priv_read_index; u32 cached_read_index; }; -- cgit v1.2.3 From 8dd45f2ab005a1f3301296059b23b03ec3dbf79b Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sun, 25 Jun 2017 12:30:26 -0700 Subject: vmbus: refactor hv_signal_on_read The function hv_signal_on_read was defined in hyperv.h and only used in one place in ring_buffer code. Clearer to just move it inline there. Signed-off-by: Stephen Hemminger Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 49 ------------------------------------------------- 1 file changed, 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 5e5f966bf37f..308e1f9706bb 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1471,55 +1471,6 @@ hv_get_ring_buffer(const struct hv_ring_buffer_info *ring_info) return ring_info->ring_buffer->buffer; } -/* - * To optimize the flow management on the send-side, - * when the sender is blocked because of lack of - * sufficient space in the ring buffer, potential the - * consumer of the ring buffer can signal the producer. - * This is controlled by the following parameters: - * - * 1. pending_send_sz: This is the size in bytes that the - * producer is trying to send. - * 2. The feature bit feat_pending_send_sz set to indicate if - * the consumer of the ring will signal when the ring - * state transitions from being full to a state where - * there is room for the producer to send the pending packet. - */ - -static inline void hv_signal_on_read(struct vmbus_channel *channel) -{ - u32 cur_write_sz, cached_write_sz; - u32 pending_sz; - struct hv_ring_buffer_info *rbi = &channel->inbound; - - /* - * Issue a full memory barrier before making the signaling decision. - * Here is the reason for having this barrier: - * If the reading of the pend_sz (in this function) - * were to be reordered and read before we commit the new read - * index (in the calling function) we could - * have a problem. If the host were to set the pending_sz after we - * have sampled pending_sz and go to sleep before we commit the - * read index, we could miss sending the interrupt. Issue a full - * memory barrier to address this. - */ - virt_mb(); - - pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz); - /* If the other end is not blocked on write don't bother. */ - if (pending_sz == 0) - return; - - cur_write_sz = hv_get_bytes_to_write(rbi); - - if (cur_write_sz < pending_sz) - return; - - cached_write_sz = hv_get_cached_bytes_to_write(rbi); - if (cached_write_sz < pending_sz) - vmbus_setevent(channel); -} - /* * Mask off host interrupt callback notifications */ -- cgit v1.2.3 From 05d00bc94ac27d220d8a78e365d7fa3a26dcca17 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Sun, 25 Jun 2017 12:30:27 -0700 Subject: vmbus: eliminate duplicate cached index Don't need cached read index anymore now that packet iterator is used. The iterator has the original read index until the visible read_index is updated. Signed-off-by: Stephen Hemminger Signed-off-by: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 308e1f9706bb..27db4e650b8c 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -125,7 +125,6 @@ struct hv_ring_buffer_info { u32 ring_datasize; /* < ring_size */ u32 priv_read_index; - u32 cached_read_index; }; /* @@ -178,19 +177,6 @@ static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi) return write; } -static inline u32 hv_get_cached_bytes_to_write( - const struct hv_ring_buffer_info *rbi) -{ - u32 read_loc, write_loc, dsize, write; - - dsize = rbi->ring_datasize; - read_loc = rbi->cached_read_index; - write_loc = rbi->ring_buffer->write_index; - - write = write_loc >= read_loc ? dsize - (write_loc - read_loc) : - read_loc - write_loc; - return write; -} /* * VMBUS version is 32 bit entity broken up into * two 16 bit quantities: major_number. minor_number. -- cgit v1.2.3 From 68f6be656179d1f0399d77918b3e361dad420455 Mon Sep 17 00:00:00 2001 From: Anatolij Gustschin Date: Wed, 14 Jun 2017 10:36:27 -0500 Subject: fpga: Add flag to indicate SPI bitstream is bit-reversed Add a flag that is passed to the write_init() callback, indicating that the SPI bitstream starts with LSB first. SPI controllers usually send data with MSB first. If an FPGA expects bitstream data as LSB first, the data must be reversed either by the SPI controller or by the driver. Alternatively the bitstream could be prepared as bit-reversed to avoid the bit-swapping while sending. This flag indicates such bit-reversed SPI bitstream. The low-level driver will deal with the flag and perform bit-reversing if needed. Signed-off-by: Anatolij Gustschin Signed-off-by: Joshua Clayton Signed-off-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index b4ac24c4411d..01c348ca38b7 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -67,10 +67,12 @@ enum fpga_mgr_states { * FPGA Manager flags * FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported * FPGA_MGR_EXTERNAL_CONFIG: FPGA has been configured prior to Linux booting + * FPGA_MGR_BITSTREAM_LSB_FIRST: SPI bitstream bit order is LSB first */ #define FPGA_MGR_PARTIAL_RECONFIG BIT(0) #define FPGA_MGR_EXTERNAL_CONFIG BIT(1) #define FPGA_MGR_ENCRYPTED_BITSTREAM BIT(2) +#define FPGA_MGR_BITSTREAM_LSB_FIRST BIT(3) /** * struct fpga_image_info - information specific to a FPGA image -- cgit v1.2.3 From 3b88da4aba2549497ac8868877562f1b1913ca62 Mon Sep 17 00:00:00 2001 From: Joshua Clayton Date: Wed, 14 Jun 2017 10:36:31 -0500 Subject: lib: add bitrev8x4() Add a function to reverse bytes within a 32 bit word. Operate on a u32 rather than individual bytes. Signed-off-by: Joshua Clayton Signed-off-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/bitrev.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h index fb790b8449c1..b97be27e5a85 100644 --- a/include/linux/bitrev.h +++ b/include/linux/bitrev.h @@ -29,6 +29,8 @@ static inline u32 __bitrev32(u32 x) #endif /* CONFIG_HAVE_ARCH_BITREVERSE */ +#define __bitrev8x4(x) (__bitrev32(swab32(x))) + #define __constant_bitrev32(x) \ ({ \ u32 __x = x; \ @@ -50,6 +52,15 @@ static inline u32 __bitrev32(u32 x) __x; \ }) +#define __constant_bitrev8x4(x) \ +({ \ + u32 __x = x; \ + __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ + __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ + __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ + __x; \ +}) + #define __constant_bitrev8(x) \ ({ \ u8 __x = x; \ @@ -75,6 +86,14 @@ static inline u32 __bitrev32(u32 x) __bitrev16(__x); \ }) +#define bitrev8x4(x) \ +({ \ + u32 __x = x; \ + __builtin_constant_p(__x) ? \ + __constant_bitrev8x4(__x) : \ + __bitrev8x4(__x); \ + }) + #define bitrev8(x) \ ({ \ u8 __x = x; \ -- cgit v1.2.3 From b37fa56069ce61d97a77dadca8dd65e522db3387 Mon Sep 17 00:00:00 2001 From: Anatolij Gustschin Date: Wed, 14 Jun 2017 10:36:34 -0500 Subject: fpga: Add flag to indicate bitstream needs decompression Add a flag that is passed to the write_init() callback, indicating that the bitstream is compressed. The low-level driver will deal with the flag, or return an error, if compressed bitstreams are not supported. Signed-off-by: Anatolij Gustschin Reviewed-by: Andy Shevchenko Signed-off-by: Alan Tull Signed-off-by: Greg Kroah-Hartman --- include/linux/fpga/fpga-mgr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 01c348ca38b7..bfa14bc023fb 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -68,11 +68,13 @@ enum fpga_mgr_states { * FPGA_MGR_PARTIAL_RECONFIG: do partial reconfiguration if supported * FPGA_MGR_EXTERNAL_CONFIG: FPGA has been configured prior to Linux booting * FPGA_MGR_BITSTREAM_LSB_FIRST: SPI bitstream bit order is LSB first + * FPGA_MGR_COMPRESSED_BITSTREAM: FPGA bitstream is compressed */ #define FPGA_MGR_PARTIAL_RECONFIG BIT(0) #define FPGA_MGR_EXTERNAL_CONFIG BIT(1) #define FPGA_MGR_ENCRYPTED_BITSTREAM BIT(2) #define FPGA_MGR_BITSTREAM_LSB_FIRST BIT(3) +#define FPGA_MGR_COMPRESSED_BITSTREAM BIT(4) /** * struct fpga_image_info - information specific to a FPGA image -- cgit v1.2.3 From 805df2966f67a6b1a228c8e580e230b6c849b41e Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 23 Jun 2017 14:55:32 +0530 Subject: arch_topology: Change return type of topology_parse_cpu_capacity() to bool topology_parse_cpu_capacity() returns 1 on success and 0 on errors. Make it return bool instead of int as that suits the purpose better. Signed-off-by: Viresh Kumar Reviewed-by: Juri Lelli Tested-by: Juri Lelli Signed-off-by: Greg Kroah-Hartman --- include/linux/arch_topology.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 9af3c174c03a..716ce587247e 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -4,10 +4,12 @@ #ifndef _LINUX_ARCH_TOPOLOGY_H_ #define _LINUX_ARCH_TOPOLOGY_H_ +#include + void topology_normalize_cpu_scale(void); struct device_node; -int topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); +bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu); struct sched_domain; unsigned long topology_get_cpu_scale(struct sched_domain *sd, int cpu); -- cgit v1.2.3 From 814abfabef3ceed390c10d06a0cc69a86454b6cf Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:27:07 -0700 Subject: xdp: add bpf_redirect helper function This adds support for a bpf_redirect helper function to the XDP infrastructure. For now this only supports redirecting to the egress path of a port. In order to support drivers handling a xdp_buff natively this patches uses a new ndo operation ndo_xdp_xmit() that takes pushes a xdp_buff to the specified device. If the program specifies either (a) an unknown device or (b) a device that does not support the operation a BPF warning is thrown and the XDP_ABORTED error code is returned. Signed-off-by: John Fastabend Acked-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/filter.h | 4 ++++ include/linux/netdevice.h | 6 ++++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index bfef1e5734f8..64cae7a08148 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -711,7 +711,11 @@ bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); + +int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp); + void bpf_warn_invalid_xdp_action(u32 act); +void bpf_warn_invalid_xdp_redirect(u32 ifindex); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 779b23595596..77f5376005e6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -66,6 +66,7 @@ struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; struct bpf_prog; +struct xdp_buff; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -1138,6 +1139,9 @@ struct xfrmdev_ops { * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); * This function is used to set or query state related to XDP on the * netdevice. See definition of enum xdp_netdev_command for details. + * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); + * This function is used to submit a XDP packet for transmit on a + * netdevice. * */ struct net_device_ops { @@ -1323,6 +1327,8 @@ struct net_device_ops { int needed_headroom); int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); + int (*ndo_xdp_xmit)(struct net_device *dev, + struct xdp_buff *xdp); }; /** -- cgit v1.2.3 From 6103aa96ec077c976e851e0b89cc2446cb76573d Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:27:50 -0700 Subject: net: implement XDP_REDIRECT for xdp generic Add support for redirect to xdp generic creating a fall back for devices that do not yet have support and allowing test infrastructure using veth pairs to be built. Signed-off-by: John Fastabend Tested-by: Andy Gospodarek Acked-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/filter.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 64cae7a08148..10df7daf5ec6 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -712,6 +712,7 @@ bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp); void bpf_warn_invalid_xdp_action(u32 act); -- cgit v1.2.3 From 5acaee0a8964c9bab7775ab8bedcd1f66a2a1011 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:28:35 -0700 Subject: xdp: add trace event for xdp redirect This adds a trace event for xdp redirect which may help when debugging XDP programs that use redirect bpf commands. Signed-off-by: John Fastabend Acked-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/filter.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 10df7daf5ec6..ce8211fa91c7 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -713,7 +713,9 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb); -int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp); +int xdp_do_redirect(struct net_device *dev, + struct xdp_buff *xdp, + struct bpf_prog *prog); void bpf_warn_invalid_xdp_action(u32 act); void bpf_warn_invalid_xdp_redirect(u32 ifindex); -- cgit v1.2.3 From 546ac1ffb70d25b56c1126940e5ec639c4dd7413 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:28:56 -0700 Subject: bpf: add devmap, a map for storing net device references Device map (devmap) is a BPF map, primarily useful for networking applications, that uses a key to lookup a reference to a netdevice. The map provides a clean way for BPF programs to build virtual port to physical port maps. Additionally, it provides a scoping function for the redirect action itself allowing multiple optimizations. Future patches will leverage the map to provide batching at the XDP layer. Another optimization/feature, that is not yet implemented, would be to support multiple netdevices per key to support efficient multicast and broadcast support. Signed-off-by: John Fastabend Acked-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/bpf_types.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 3d137c33d664..b1e1035ca24b 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -35,3 +35,6 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) +#ifdef CONFIG_NET +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +#endif -- cgit v1.2.3 From 97f91a7cf04ff605845c20948b8a80e54cbd3376 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:29:18 -0700 Subject: bpf: add bpf_redirect_map helper routine BPF programs can use the devmap with a bpf_redirect_map() helper routine to forward packets to netdevice in map. Signed-off-by: John Fastabend Signed-off-by: Jesper Dangaard Brouer Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b69e7a5869ff..d0d3281ac678 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -379,4 +379,7 @@ extern const struct bpf_func_proto bpf_get_stackid_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +/* Map specifics */ +struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); + #endif /* _LINUX_BPF_H */ -- cgit v1.2.3 From 11393cc9b9be2a1f61559e6fb9c27bc8fa20b1ff Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:29:40 -0700 Subject: xdp: Add batching support to redirect map For performance reasons we want to avoid updating the tail pointer in the driver tx ring as much as possible. To accomplish this we add batching support to the redirect path in XDP. This adds another ndo op "xdp_flush" that is used to inform the driver that it should bump the tail pointer on the TX ring. Signed-off-by: John Fastabend Signed-off-by: Jesper Dangaard Brouer Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 2 ++ include/linux/filter.h | 7 +++++++ include/linux/netdevice.h | 5 ++++- 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d0d3281ac678..6850a760dc94 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -381,5 +381,7 @@ u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); /* Map specifics */ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +void __dev_map_insert_ctx(struct bpf_map *map, u32 index); +void __dev_map_flush(struct bpf_map *map); #endif /* _LINUX_BPF_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index ce8211fa91c7..3323ee91c172 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -712,10 +712,17 @@ bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); +/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the + * same cpu context. Further for best results no more than a single map + * for the do_redirect/do_flush pair should be used. This limitation is + * because we only track one map and force a flush when the map changes. + * This does not appear to be a real limiation for existing software. + */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); +void xdp_do_flush_map(void); void bpf_warn_invalid_xdp_action(u32 act); void bpf_warn_invalid_xdp_redirect(u32 ifindex); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 77f5376005e6..03b104908235 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1142,7 +1142,9 @@ struct xfrmdev_ops { * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); * This function is used to submit a XDP packet for transmit on a * netdevice. - * + * void (*ndo_xdp_flush)(struct net_device *dev); + * This function is used to inform the driver to flush a paticular + * xpd tx queue. Must be called on same CPU as xdp_xmit. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1329,6 +1331,7 @@ struct net_device_ops { struct netdev_xdp *xdp); int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); + void (*ndo_xdp_flush)(struct net_device *dev); }; /** -- cgit v1.2.3 From 2ddf71e23cc246e95af72a6deed67b4a50a7b81c Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 09:30:02 -0700 Subject: net: add notifier hooks for devmap bpf map The BPF map devmap holds a refcnt on the net_device structure when it is in the map. We need to do this to ensure on driver unload we don't lose a dev reference. However, its not very convenient to have to manually unload the map when destroying a net device so add notifier handlers to do the cleanup automatically. But this creates a race between update/destroy BPF syscall and programs and the unregister netdev hook. Unfortunately, the best I could come up with is either to live with requiring manual removal of net devices from the map before removing the net device OR to add a mutex in devmap to ensure the map is not modified while we are removing a device. The fallout also requires that BPF programs no longer update/delete the map from the BPF program side because the mutex may sleep and this can not be done from inside an rcu critical section. This is not a real problem though because I have not come up with any use cases where this is actually useful in practice. If/when we come up with a compelling user for this we may need to revisit this. Signed-off-by: John Fastabend Acked-by: Daniel Borkmann Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 3323ee91c172..d19ed3c15e1e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -716,7 +716,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. - * This does not appear to be a real limiation for existing software. + * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb); int xdp_do_redirect(struct net_device *dev, -- cgit v1.2.3 From 880388aa3c07fdea4f9b85e35641753017b1852f Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 3 Jul 2017 07:29:12 -0700 Subject: net: Remove all references to SKB_GSO_UDP. Such packets are no longer possible. Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 5209b5ed2a64..32fb046f2173 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -18,9 +18,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; break; - case VIRTIO_NET_HDR_GSO_UDP: - gso_type = SKB_GSO_UDP; - break; default: return -EINVAL; } @@ -73,8 +70,6 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (sinfo->gso_type & SKB_GSO_UDP) - hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) -- cgit v1.2.3 From d9d30adf56777c402c0027c0e6ae21f17cc0a365 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 3 Jul 2017 07:31:57 -0700 Subject: net: Kill NETIF_F_UFO and SKB_GSO_UDP. No longer used. Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 4 +--- include/linux/netdevice.h | 1 - include/linux/skbuff.h | 31 +++++++++++++++---------------- 3 files changed, 16 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 1d4737cffc71..ebd273627334 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -36,7 +36,6 @@ enum { /**/NETIF_F_GSO_SHIFT, /* keep the order of SKB_GSO_* bits */ NETIF_F_TSO_BIT /* ... TCPv4 segmentation */ = NETIF_F_GSO_SHIFT, - NETIF_F_UFO_BIT, /* ... UDPv4 fragmentation */ NETIF_F_GSO_ROBUST_BIT, /* ... ->SKB_GSO_DODGY */ NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */ NETIF_F_TSO_MANGLEID_BIT, /* ... IPV4 ID mangling allowed */ @@ -118,7 +117,6 @@ enum { #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) #define NETIF_F_TSO __NETIF_F(TSO) -#define NETIF_F_UFO __NETIF_F(UFO) #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) @@ -172,7 +170,7 @@ enum { NETIF_F_FSO) /* List of features with software fallbacks. */ -#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_UFO | \ +#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \ NETIF_F_GSO_SCTP) /* diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 03b104908235..c60351b84323 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4098,7 +4098,6 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); - BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbe29b6c9bd6..4d7a284ba3ee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -463,39 +463,38 @@ enum { enum { SKB_GSO_TCPV4 = 1 << 0, - SKB_GSO_UDP = 1 << 1, /* This indicates the skb is from an untrusted source. */ - SKB_GSO_DODGY = 1 << 2, + SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ - SKB_GSO_TCP_ECN = 1 << 3, + SKB_GSO_TCP_ECN = 1 << 2, - SKB_GSO_TCP_FIXEDID = 1 << 4, + SKB_GSO_TCP_FIXEDID = 1 << 3, - SKB_GSO_TCPV6 = 1 << 5, + SKB_GSO_TCPV6 = 1 << 4, - SKB_GSO_FCOE = 1 << 6, + SKB_GSO_FCOE = 1 << 5, - SKB_GSO_GRE = 1 << 7, + SKB_GSO_GRE = 1 << 6, - SKB_GSO_GRE_CSUM = 1 << 8, + SKB_GSO_GRE_CSUM = 1 << 7, - SKB_GSO_IPXIP4 = 1 << 9, + SKB_GSO_IPXIP4 = 1 << 8, - SKB_GSO_IPXIP6 = 1 << 10, + SKB_GSO_IPXIP6 = 1 << 9, - SKB_GSO_UDP_TUNNEL = 1 << 11, + SKB_GSO_UDP_TUNNEL = 1 << 10, - SKB_GSO_UDP_TUNNEL_CSUM = 1 << 12, + SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, - SKB_GSO_PARTIAL = 1 << 13, + SKB_GSO_PARTIAL = 1 << 12, - SKB_GSO_TUNNEL_REMCSUM = 1 << 14, + SKB_GSO_TUNNEL_REMCSUM = 1 << 13, - SKB_GSO_SCTP = 1 << 15, + SKB_GSO_SCTP = 1 << 14, - SKB_GSO_ESP = 1 << 16, + SKB_GSO_ESP = 1 << 15, }; #if BITS_PER_LONG > 32 -- cgit v1.2.3 From 06dc75ab06943fcc126a951a0680980ad5cb75c6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 17 Jul 2017 18:56:54 +0200 Subject: net: Revert "net: add function to allocate sk_buff head without data area" It was added for netlink mmap tx, there are no callers in the tree. The commit also added a check for skb->head != NULL in kfree_skb path, remove that too -- all skbs ought to have skb->head set. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4d7a284ba3ee..4093552be1de 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -944,12 +944,6 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } -struct sk_buff *__alloc_skb_head(gfp_t priority, int node); -static inline struct sk_buff *alloc_skb_head(gfp_t priority) -{ - return __alloc_skb_head(priority, -1); -} - struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); -- cgit v1.2.3 From 46f55cffa47330b99537985a50d92945d4b34658 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 17 Jul 2017 21:56:48 -0700 Subject: net: fix build error in devmap helper calls Initial patches missed case with CONFIG_BPF_SYSCALL not set. Fixes: 11393cc9b9be ("xdp: Add batching support to redirect map") Fixes: 97f91a7cf04f ("bpf: add bpf_redirect_map helper routine") Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/bpf.h | 25 ++++++++++++++++++++----- 1 file changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6850a760dc94..6353c7474dba 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -318,6 +318,12 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); + +/* Map specifics */ +struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +void __dev_map_insert_ctx(struct bpf_map *map, u32 index); +void __dev_map_flush(struct bpf_map *map); + #else static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -356,6 +362,20 @@ static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } + +static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} + +static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) +{ +} + +static inline void __dev_map_flush(struct bpf_map *map) +{ +} #endif /* CONFIG_BPF_SYSCALL */ /* verifier prototypes for helper functions called from eBPF programs */ @@ -379,9 +399,4 @@ extern const struct bpf_func_proto bpf_get_stackid_proto; void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); -/* Map specifics */ -struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); -void __dev_map_insert_ctx(struct bpf_map *map, u32 index); -void __dev_map_flush(struct bpf_map *map); - #endif /* _LINUX_BPF_H */ -- cgit v1.2.3 From 3cf29931453215536916d0c4da953fce1911ced3 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 14 Jul 2017 19:38:36 +0900 Subject: LSM: Remove security_task_create() hook. Since commit a79be238600d1a03 ("selinux: Use task_alloc hook rather than task_create hook") changed to use task_alloc hook, task_create hook is no longer used. Signed-off-by: Tetsuo Handa Signed-off-by: James Morris --- include/linux/lsm_hooks.h | 7 ------- include/linux/security.h | 6 ------ 2 files changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 3cc9d77c7527..575703cb17b8 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -529,11 +529,6 @@ * * Security hooks for task operations. * - * @task_create: - * Check permission before creating a child process. See the clone(2) - * manual page for definitions of the @clone_flags. - * @clone_flags contains the flags indicating what should be shared. - * Return 0 if permission is granted. * @task_alloc: * @task task being allocated. * @clone_flags contains the flags indicating what should be shared. @@ -1509,7 +1504,6 @@ union security_list_options { int (*file_receive)(struct file *file); int (*file_open)(struct file *file, const struct cred *cred); - int (*task_create)(unsigned long clone_flags); int (*task_alloc)(struct task_struct *task, unsigned long clone_flags); void (*task_free)(struct task_struct *task); int (*cred_alloc_blank)(struct cred *cred, gfp_t gfp); @@ -1784,7 +1778,6 @@ struct security_hook_heads { struct list_head file_send_sigiotask; struct list_head file_receive; struct list_head file_open; - struct list_head task_create; struct list_head task_alloc; struct list_head task_free; struct list_head cred_alloc_blank; diff --git a/include/linux/security.h b/include/linux/security.h index b6ea1dc9cc9d..458e24bea2d4 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -318,7 +318,6 @@ int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig); int security_file_receive(struct file *file); int security_file_open(struct file *file, const struct cred *cred); -int security_task_create(unsigned long clone_flags); int security_task_alloc(struct task_struct *task, unsigned long clone_flags); void security_task_free(struct task_struct *task); int security_cred_alloc_blank(struct cred *cred, gfp_t gfp); @@ -885,11 +884,6 @@ static inline int security_file_open(struct file *file, return 0; } -static inline int security_task_create(unsigned long clone_flags) -{ - return 0; -} - static inline int security_task_alloc(struct task_struct *task, unsigned long clone_flags) { -- cgit v1.2.3 From 7744ccdbc16f0ac4adae21b3678af93775b3a386 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:03 -0500 Subject: x86/mm: Add Secure Memory Encryption (SME) support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support for Secure Memory Encryption (SME). This initial support provides a Kconfig entry to build the SME support into the kernel and defines the memory encryption mask that will be used in subsequent patches to mark pages as encrypted. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Matt Fleming Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/a6c34d16caaed3bc3e2d6f0987554275bd291554.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/mem_encrypt.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/mem_encrypt.h (limited to 'include/linux') diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h new file mode 100644 index 000000000000..59769f7287e4 --- /dev/null +++ b/include/linux/mem_encrypt.h @@ -0,0 +1,35 @@ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __MEM_ENCRYPT_H__ +#define __MEM_ENCRYPT_H__ + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_ARCH_HAS_MEM_ENCRYPT + +#include + +#else /* !CONFIG_ARCH_HAS_MEM_ENCRYPT */ + +#define sme_me_mask 0UL + +#endif /* CONFIG_ARCH_HAS_MEM_ENCRYPT */ + +static inline bool sme_active(void) +{ + return !!sme_me_mask; +} + +#endif /* __ASSEMBLY__ */ + +#endif /* __MEM_ENCRYPT_H__ */ -- cgit v1.2.3 From 5868f3651fa0dff96a57f94d49247d3ef320ebe2 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:05 -0500 Subject: x86/mm: Add support to enable SME in early boot processing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support to the early boot code to use Secure Memory Encryption (SME). Since the kernel has been loaded into memory in a decrypted state, encrypt the kernel in place and update the early pagetables with the memory encryption mask so that new pagetable entries will use memory encryption. The routines to set the encryption mask and perform the encryption are stub routines for now with functionality to be added in a later patch. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Matt Fleming Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/e52ad781f085224bf835b3caff9aa3aee6febccb.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/mem_encrypt.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h index 59769f7287e4..570f4fcff13f 100644 --- a/include/linux/mem_encrypt.h +++ b/include/linux/mem_encrypt.h @@ -30,6 +30,11 @@ static inline bool sme_active(void) return !!sme_me_mask; } +static inline unsigned long sme_get_me_mask(void) +{ + return sme_me_mask; +} + #endif /* __ASSEMBLY__ */ #endif /* __MEM_ENCRYPT_H__ */ -- cgit v1.2.3 From 21729f81ce8ae76a6995681d40e16f7ce8075db4 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:07 -0500 Subject: x86/mm: Provide general kernel support for memory encryption MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Changes to the existing page table macros will allow the SME support to be enabled in a simple fashion with minimal changes to files that use these macros. Since the memory encryption mask will now be part of the regular pagetable macros, we introduce two new macros (_PAGE_TABLE_NOENC and _KERNPG_TABLE_NOENC) to allow for early pagetable creation/initialization without the encryption mask before SME becomes active. Two new pgprot() macros are defined to allow setting or clearing the page encryption mask. The FIXMAP_PAGE_NOCACHE define is introduced for use with MMIO. SME does not support encryption for MMIO areas so this define removes the encryption mask from the page attribute. Two new macros are introduced (__sme_pa() / __sme_pa_nodebug()) to allow creating a physical address with the encryption mask. These are used when working with the cr3 register so that the PGD can be encrypted. The current __va() macro is updated so that the virtual address is generated based off of the physical address without the encryption mask thus allowing the same virtual address to be generated regardless of whether encryption is enabled for that physical location or not. Also, an early initialization function is added for SME. If SME is active, this function: - Updates the early_pmd_flags so that early page faults create mappings with the encryption mask. - Updates the __supported_pte_mask to include the encryption mask. - Updates the protection_map entries to include the encryption mask so that user-space allocations will automatically have the encryption mask applied. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Matt Fleming Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/b36e952c4c39767ae7f0a41cf5345adf27438480.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/mem_encrypt.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h index 570f4fcff13f..1255f09f5e42 100644 --- a/include/linux/mem_encrypt.h +++ b/include/linux/mem_encrypt.h @@ -35,6 +35,14 @@ static inline unsigned long sme_get_me_mask(void) return sme_me_mask; } +/* + * The __sme_set() and __sme_clr() macros are useful for adding or removing + * the encryption mask from a value (e.g. when dealing with pagetable + * entries). + */ +#define __sme_set(x) ((unsigned long)(x) | sme_me_mask) +#define __sme_clr(x) ((unsigned long)(x) & ~sme_me_mask) + #endif /* __ASSEMBLY__ */ #endif /* __MEM_ENCRYPT_H__ */ -- cgit v1.2.3 From a19d66c56af1c52b8b463bf94d21116ae8c1aa5a Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:13 -0500 Subject: efi: Add an EFI table address match function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a function that will determine if a supplied physical address matches the address of an EFI table. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Reviewed-by: Matt Fleming Reviewed-by: Borislav Petkov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/e1e06441d80f44776df391e0e4cb485b345b7518.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/efi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 8269bcb8ccf7..8e24f099bd3f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1091,6 +1091,8 @@ static inline bool efi_enabled(int feature) return test_bit(feature, &efi.flags) != 0; } extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); + +extern bool efi_is_table_address(unsigned long phys_addr); #else static inline bool efi_enabled(int feature) { @@ -1104,6 +1106,11 @@ efi_capsule_pending(int *reset_type) { return false; } + +static inline bool efi_is_table_address(unsigned long phys_addr) +{ + return false; +} #endif extern int efi_status_to_err(efi_status_t status); -- cgit v1.2.3 From f99afd08a45fbbd9ce35a7624ffd1d850a1906c0 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:14 -0500 Subject: efi: Update efi_mem_type() to return an error rather than 0 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The efi_mem_type() function currently returns a 0, which maps to EFI_RESERVED_TYPE, if the function is unable to find a memmap entry for the supplied physical address. Returning EFI_RESERVED_TYPE implies that a memmap entry exists, when it doesn't. Instead of returning 0, change the function to return a negative error value when no memmap entry is found. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Reviewed-by: Matt Fleming Reviewed-by: Borislav Petkov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/7fbf40a9dc414d5da849e1ddcd7f7c1285e4e181.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/efi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 8e24f099bd3f..4e47f78430be 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -985,7 +985,7 @@ static inline void efi_esrt_init(void) { } extern int efi_config_parse_tables(void *config_tables, int count, int sz, efi_config_table_type_t *arch_tables); extern u64 efi_get_iobase (void); -extern u32 efi_mem_type (unsigned long phys_addr); +extern int efi_mem_type(unsigned long phys_addr); extern u64 efi_mem_attributes (unsigned long phys_addr); extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size); extern int __init efi_uart_console_only (void); -- cgit v1.2.3 From 8f716c9b5febf6ed0f5fedb7c9407cd0c25b2796 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:16 -0500 Subject: x86/mm: Add support to access boot related data in the clear MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Boot data (such as EFI related data) is not encrypted when the system is booted because UEFI/BIOS does not run with SME active. In order to access this data properly it needs to be mapped decrypted. Update early_memremap() to provide an arch specific routine to modify the pagetable protection attributes before they are applied to the new mapping. This is used to remove the encryption mask for boot related data. Update memremap() to provide an arch specific routine to determine if RAM remapping is allowed. RAM remapping will cause an encrypted mapping to be generated. By preventing RAM remapping, ioremap_cache() will be used instead, which will provide a decrypted mapping of the boot related data. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Reviewed-by: Matt Fleming Reviewed-by: Borislav Petkov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/81fb6b4117a5df6b9f2eda342f81bbef4b23d2e5.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/io.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index 2195d9ea4aaa..32e30e8fb9db 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -157,6 +157,8 @@ enum { MEMREMAP_WB = 1 << 0, MEMREMAP_WT = 1 << 1, MEMREMAP_WC = 1 << 2, + MEMREMAP_ENC = 1 << 3, + MEMREMAP_DEC = 1 << 4, }; void *memremap(resource_size_t offset, size_t size, unsigned long flags); -- cgit v1.2.3 From c7753208a94c73d5beb1e4bd843081d6dc7d4678 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:21 -0500 Subject: x86, swiotlb: Add memory encryption support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since DMA addresses will effectively look like 48-bit addresses when the memory encryption mask is set, SWIOTLB is needed if the DMA mask of the device performing the DMA does not support 48-bits. SWIOTLB will be initialized to create decrypted bounce buffers for use by these devices. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Matt Fleming Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/aa2d29b78ae7d508db8881e46a3215231b9327a7.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/swiotlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 4ee479f2f355..15e7160751a8 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -35,6 +35,7 @@ int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose); extern unsigned long swiotlb_nr_tbl(void); unsigned long swiotlb_size_or_default(void); extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs); +extern void __init swiotlb_update_mem_attributes(void); /* * Enumeration for sync targets -- cgit v1.2.3 From 648babb7078c6310d2af5b8aa01f086030916968 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:22 -0500 Subject: swiotlb: Add warnings for use of bounce buffers with SME MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add warnings to let the user know when bounce buffers are being used for DMA when SME is active. Since the bounce buffers are not in encrypted memory, these notifications are to allow the user to determine some appropriate action - if necessary. Actions can range from utilizing an IOMMU, replacing the device with another device that can support 64-bit DMA, ignoring the message if the device isn't used much, etc. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Matt Fleming Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/d112564053c3f2e86ca634a8d4fa4abc0eb53a6a.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/dma-mapping.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 843ab866e0f4..fce2369ecf82 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -10,6 +10,7 @@ #include #include #include +#include /** * List of possible attributes associated with a DMA mapping. The semantics @@ -548,6 +549,12 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) return 0; } +static inline void dma_check_mask(struct device *dev, u64 mask) +{ + if (sme_active() && (mask < (((u64)sme_get_me_mask() << 1) - 1))) + dev_warn(dev, "SME is active, device will require DMA bounce buffers\n"); +} + static inline int dma_supported(struct device *dev, u64 mask) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -564,6 +571,9 @@ static inline int dma_set_mask(struct device *dev, u64 mask) { if (!dev->dma_mask || !dma_supported(dev, mask)) return -EIO; + + dma_check_mask(dev, mask); + *dev->dma_mask = mask; return 0; } @@ -583,6 +593,9 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask) { if (!dma_supported(dev, mask)) return -EIO; + + dma_check_mask(dev, mask); + dev->coherent_dma_mask = mask; return 0; } -- cgit v1.2.3 From bba4ed011a52d494aa7ef5e08cf226709bbf3f60 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:28 -0500 Subject: x86/mm, kexec: Allow kexec to be used with SME MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Provide support so that kexec can be used to boot a kernel when SME is enabled. Support is needed to allocate pages for kexec without encryption. This is needed in order to be able to reboot in the kernel in the same manner as originally booted. Additionally, when shutting down all of the CPUs we need to be sure to flush the caches and then halt. This is needed when booting from a state where SME was not active into a state where SME is active (or vice-versa). Without these steps, it is possible for cache lines to exist for the same physical location but tagged both with and without the encryption bit. This can cause random memory corruption when caches are flushed depending on which cacheline is written last. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Matt Fleming Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/b95ff075db3e7cd545313f2fb609a49619a09625.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/kexec.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index dd056fab9e35..2b7590f5483a 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -327,6 +327,14 @@ static inline void *boot_phys_to_virt(unsigned long entry) return phys_to_virt(boot_phys_to_phys(entry)); } +#ifndef arch_kexec_post_alloc_pages +static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp) { return 0; } +#endif + +#ifndef arch_kexec_pre_free_pages +static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { } +#endif + #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; struct task_struct; -- cgit v1.2.3 From 77af0ae44e4a74f58dd741babdacec32fc8042b1 Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Tue, 27 Jun 2017 08:58:04 -0500 Subject: crypto: ccp - Fix some line spacing Add/remove blank lines as appropriate. Signed-off-by: Gary R Hook Signed-off-by: Herbert Xu --- include/linux/ccp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ccp.h b/include/linux/ccp.h index 3285c944194a..c03ee844a99d 100644 --- a/include/linux/ccp.h +++ b/include/linux/ccp.h @@ -20,7 +20,6 @@ #include #include - struct ccp_device; struct ccp_cmd; -- cgit v1.2.3 From 720419f01832f7e697cb80480b97b2a1e96045cd Mon Sep 17 00:00:00 2001 From: Brijesh Singh Date: Thu, 6 Jul 2017 09:59:14 -0500 Subject: crypto: ccp - Introduce the AMD Secure Processor device The CCP device is part of the AMD Secure Processor. In order to expand the usage of the AMD Secure Processor, create a framework that allows functional components of the AMD Secure Processor to be initialized and handled appropriately. Signed-off-by: Brijesh Singh Acked-by: Gary R Hook Signed-off-by: Herbert Xu --- include/linux/ccp.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ccp.h b/include/linux/ccp.h index c03ee844a99d..3fd9a6dac344 100644 --- a/include/linux/ccp.h +++ b/include/linux/ccp.h @@ -23,8 +23,7 @@ struct ccp_device; struct ccp_cmd; -#if defined(CONFIG_CRYPTO_DEV_CCP_DD) || \ - defined(CONFIG_CRYPTO_DEV_CCP_DD_MODULE) +#if defined(CONFIG_CRYPTO_DEV_SP_CCP) /** * ccp_present - check if a CCP device is present @@ -70,7 +69,7 @@ unsigned int ccp_version(void); */ int ccp_enqueue_cmd(struct ccp_cmd *cmd); -#else /* CONFIG_CRYPTO_DEV_CCP_DD is not enabled */ +#else /* CONFIG_CRYPTO_DEV_CCP_SP_DEV is not enabled */ static inline int ccp_present(void) { @@ -87,7 +86,7 @@ static inline int ccp_enqueue_cmd(struct ccp_cmd *cmd) return -ENODEV; } -#endif /* CONFIG_CRYPTO_DEV_CCP_DD */ +#endif /* CONFIG_CRYPTO_DEV_SP_CCP */ /***** AES engine *****/ -- cgit v1.2.3 From f384b352cbf0310fd20c379c4710408c70e769b6 Mon Sep 17 00:00:00 2001 From: Cyrille Pitchen Date: Mon, 26 Jun 2017 15:10:00 +0200 Subject: mtd: spi-nor: parse Serial Flash Discoverable Parameters (SFDP) tables This patch adds support to the JESD216 rev B standard and parses the SFDP tables to dynamically initialize the 'struct spi_nor_flash_parameter'. Signed-off-by: Cyrille Pitchen Reviewed-by: Marek Vasut --- include/linux/mtd/spi-nor.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 55faa2f07cca..0df3638ff0b8 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -41,6 +41,8 @@ #define SPINOR_OP_WREN 0x06 /* Write enable */ #define SPINOR_OP_RDSR 0x05 /* Read status register */ #define SPINOR_OP_WRSR 0x01 /* Write status register 1 byte */ +#define SPINOR_OP_RDSR2 0x3f /* Read status register 2 */ +#define SPINOR_OP_WRSR2 0x3e /* Write status register 2 */ #define SPINOR_OP_READ 0x03 /* Read data bytes (low frequency) */ #define SPINOR_OP_READ_FAST 0x0b /* Read data bytes (high frequency) */ #define SPINOR_OP_READ_1_1_2 0x3b /* Read data bytes (Dual Output SPI) */ @@ -56,6 +58,7 @@ #define SPINOR_OP_CHIP_ERASE 0xc7 /* Erase whole flash chip */ #define SPINOR_OP_SE 0xd8 /* Sector erase (usually 64KiB) */ #define SPINOR_OP_RDID 0x9f /* Read JEDEC ID */ +#define SPINOR_OP_RDSFDP 0x5a /* Read SFDP */ #define SPINOR_OP_RDCR 0x35 /* Read configuration register */ #define SPINOR_OP_RDFSR 0x70 /* Read flag status register */ @@ -128,6 +131,9 @@ /* Configuration Register bits. */ #define CR_QUAD_EN_SPAN BIT(1) /* Spansion Quad I/O */ +/* Status Register 2 bits. */ +#define SR2_QUAD_EN_BIT7 BIT(7) + /* Supported SPI protocols */ #define SNOR_PROTO_INST_MASK GENMASK(23, 16) #define SNOR_PROTO_INST_SHIFT 16 -- cgit v1.2.3 From 7375ae3a0b79ea072f4c672039f08f5db633b9e1 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Mon, 17 Jul 2017 16:10:34 -0500 Subject: compiler-gcc.h: Introduce __nostackprotector function attribute MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Create a new function attribute, __nostackprotector, that can used to turn off stack protection on a per function basis. Signed-off-by: Tom Lendacky Reviewed-by: Thomas Gleixner Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brijesh Singh Cc: Dave Young Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Larry Woodman Cc: Linus Torvalds Cc: Matt Fleming Cc: Michael S. Tsirkin Cc: Paolo Bonzini Cc: Peter Zijlstra Cc: Radim Krčmář Cc: Rik van Riel Cc: Toshimitsu Kani Cc: kasan-dev@googlegroups.com Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/0576fd5c74440ad0250f16ac6609ecf587812456.1500319216.git.thomas.lendacky@amd.com Signed-off-by: Ingo Molnar --- include/linux/compiler-gcc.h | 2 ++ include/linux/compiler.h | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cd4bbe8242bd..c28cedde973f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -166,6 +166,8 @@ #if GCC_VERSION >= 40100 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) + +#define __nostackprotector __attribute__((__optimize__("no-stack-protector"))) #endif #if GCC_VERSION >= 40300 diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 219f82f3ec1a..3f8c88e29a46 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -470,6 +470,10 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #define __visible #endif +#ifndef __nostackprotector +# define __nostackprotector +#endif + /* * Assume alignment of return value. */ -- cgit v1.2.3 From 17c82e206d2a3cd876b64921c59116f1ecdce6ad Mon Sep 17 00:00:00 2001 From: Vivek Gautam Date: Mon, 22 May 2017 16:53:25 +0530 Subject: reset: Add APIs to manage array of resets Many devices may want to request a bunch of resets and control them. So it's better to manage them as an array. Add APIs to _get() an array of reset_control, reusing the _assert(), _deassert(), and _reset() APIs for single reset controls. Since reset controls already may control multiple reset lines with a single hardware bit, from the user perspective, reset control arrays are not at all different from single reset controls. Note that these APIs don't guarantee that the reset lines managed in the array are handled in any particular order. Cc: Felipe Balbi Cc: Jon Hunter Signed-off-by: Vivek Gautam [p.zabel@pengutronix.de: changed API to hide reset control arrays behind struct reset_control] Signed-off-by: Philipp Zabel --- include/linux/reset.h | 68 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index 13d8681210d5..56463f37f3e6 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -25,6 +25,11 @@ struct reset_control *__devm_reset_control_get(struct device *dev, int __must_check device_reset(struct device *dev); +struct reset_control *devm_reset_control_array_get(struct device *dev, + bool shared, bool optional); +struct reset_control *of_reset_control_array_get(struct device_node *np, + bool shared, bool optional); + static inline int device_reset_optional(struct device *dev) { return device_reset(dev); @@ -89,6 +94,18 @@ static inline struct reset_control *__devm_reset_control_get( return optional ? NULL : ERR_PTR(-ENOTSUPP); } +static inline struct reset_control * +devm_reset_control_array_get(struct device *dev, bool shared, bool optional) +{ + return optional ? NULL : ERR_PTR(-ENOTSUPP); +} + +static inline struct reset_control * +of_reset_control_array_get(struct device_node *np, bool shared, bool optional) +{ + return optional ? NULL : ERR_PTR(-ENOTSUPP); +} + #endif /* CONFIG_RESET_CONTROLLER */ /** @@ -374,4 +391,55 @@ static inline struct reset_control *devm_reset_control_get_by_index( { return devm_reset_control_get_exclusive_by_index(dev, index); } + +/* + * APIs to manage a list of reset controllers + */ +static inline struct reset_control * +devm_reset_control_array_get_exclusive(struct device *dev) +{ + return devm_reset_control_array_get(dev, false, false); +} + +static inline struct reset_control * +devm_reset_control_array_get_shared(struct device *dev) +{ + return devm_reset_control_array_get(dev, true, false); +} + +static inline struct reset_control * +devm_reset_control_array_get_optional_exclusive(struct device *dev) +{ + return devm_reset_control_array_get(dev, false, true); +} + +static inline struct reset_control * +devm_reset_control_array_get_optional_shared(struct device *dev) +{ + return devm_reset_control_array_get(dev, true, true); +} + +static inline struct reset_control * +of_reset_control_array_get_exclusive(struct device_node *node) +{ + return of_reset_control_array_get(node, false, false); +} + +static inline struct reset_control * +of_reset_control_array_get_shared(struct device_node *node) +{ + return of_reset_control_array_get(node, true, false); +} + +static inline struct reset_control * +of_reset_control_array_get_optional_exclusive(struct device_node *node) +{ + return of_reset_control_array_get(node, false, true); +} + +static inline struct reset_control * +of_reset_control_array_get_optional_shared(struct device_node *node) +{ + return of_reset_control_array_get(node, true, true); +} #endif -- cgit v1.2.3 From 7051b88a35c7dde5705923833117e14f9cc17d92 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Tue, 18 Jul 2017 15:59:27 -0700 Subject: net: make dev_close and related functions void There is no useful return value from dev_close. All paths return 0. Change dev_close and helper functions to void. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c60351b84323..614642eb7eb7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2432,8 +2432,8 @@ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev); -int dev_close(struct net_device *dev); -int dev_close_many(struct list_head *head, bool unlink); +void dev_close(struct net_device *dev); +void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); -- cgit v1.2.3 From a2b426267c56773201f968fdb5eda6ab9ae94e34 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 29 Apr 2017 14:12:15 -0500 Subject: userns,pidns: Verify the userns for new pid namespaces It is pointless and confusing to allow a pid namespace hierarchy and the user namespace hierarchy to get out of sync. The owner of a child pid namespace should be the owner of the parent pid namespace or a descendant of the owner of the parent pid namespace. Otherwise it is possible to construct scenarios where a process has a capability over a parent pid namespace but does not have the capability over a child pid namespace. Which confusingly makes permission checks non-transitive. It requires use of setns into a pid namespace (but not into a user namespace) to create such a scenario. Add the function in_userns to help in making this determination. v2: Optimized in_userns by using level as suggested by: Kirill Tkhai Ref: 49f4d8b93ccf ("pidns: Capture the user namespace and filter ns_last_pid") Signed-off-by: "Eric W. Biederman" --- include/linux/user_namespace.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 32354b4b4b2b..4005877bb8b6 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -112,8 +112,9 @@ extern ssize_t proc_projid_map_write(struct file *, const char __user *, size_t, extern ssize_t proc_setgroups_write(struct file *, const char __user *, size_t, loff_t *); extern int proc_setgroups_show(struct seq_file *m, void *v); extern bool userns_may_setgroups(const struct user_namespace *ns); +extern bool in_userns(const struct user_namespace *ancestor, + const struct user_namespace *child); extern bool current_in_userns(const struct user_namespace *target_ns); - struct ns_common *ns_get_owner(struct ns_common *ns); #else @@ -144,6 +145,12 @@ static inline bool userns_may_setgroups(const struct user_namespace *ns) return true; } +static inline bool in_userns(const struct user_namespace *ancestor, + const struct user_namespace *child) +{ + return true; +} + static inline bool current_in_userns(const struct user_namespace *target_ns) { return true; -- cgit v1.2.3 From 727f8914477e4642c7d1ff381667cdc4178b40c6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Jul 2017 10:39:26 +0100 Subject: rxrpc: Expose UAPI definitions to userspace Move UAPI definitions from the internal header and place them in a UAPI header file so that userspace can make use of them. Signed-off-by: David Howells --- include/linux/rxrpc.h | 79 --------------------------------------------------- 1 file changed, 79 deletions(-) delete mode 100644 include/linux/rxrpc.h (limited to 'include/linux') diff --git a/include/linux/rxrpc.h b/include/linux/rxrpc.h deleted file mode 100644 index 7343f71783dc..000000000000 --- a/include/linux/rxrpc.h +++ /dev/null @@ -1,79 +0,0 @@ -/* AF_RXRPC parameters - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _LINUX_RXRPC_H -#define _LINUX_RXRPC_H - -#include -#include - -/* - * RxRPC socket address - */ -struct sockaddr_rxrpc { - sa_family_t srx_family; /* address family */ - u16 srx_service; /* service desired */ - u16 transport_type; /* type of transport socket (SOCK_DGRAM) */ - u16 transport_len; /* length of transport address */ - union { - sa_family_t family; /* transport address family */ - struct sockaddr_in sin; /* IPv4 transport address */ - struct sockaddr_in6 sin6; /* IPv6 transport address */ - } transport; -}; - -/* - * RxRPC socket options - */ -#define RXRPC_SECURITY_KEY 1 /* [clnt] set client security key */ -#define RXRPC_SECURITY_KEYRING 2 /* [srvr] set ring of server security keys */ -#define RXRPC_EXCLUSIVE_CONNECTION 3 /* Deprecated; use RXRPC_EXCLUSIVE_CALL instead */ -#define RXRPC_MIN_SECURITY_LEVEL 4 /* minimum security level */ -#define RXRPC_UPGRADEABLE_SERVICE 5 /* Upgrade service[0] -> service[1] */ -#define RXRPC_SUPPORTED_CMSG 6 /* Get highest supported control message type */ - -/* - * RxRPC control messages - * - If neither abort or accept are specified, the message is a data message. - * - terminal messages mean that a user call ID tag can be recycled - * - s/r/- indicate whether these are applicable to sendmsg() and/or recvmsg() - */ -enum rxrpc_cmsg_type { - RXRPC_USER_CALL_ID = 1, /* sr: user call ID specifier */ - RXRPC_ABORT = 2, /* sr: abort request / notification [terminal] */ - RXRPC_ACK = 3, /* -r: [Service] RPC op final ACK received [terminal] */ - RXRPC_NET_ERROR = 5, /* -r: network error received [terminal] */ - RXRPC_BUSY = 6, /* -r: server busy received [terminal] */ - RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */ - RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */ - RXRPC_ACCEPT = 9, /* s-: [Service] accept request */ - RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ - RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ - RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ - RXRPC__SUPPORTED -}; - -/* - * RxRPC security levels - */ -#define RXRPC_SECURITY_PLAIN 0 /* plain secure-checksummed packets only */ -#define RXRPC_SECURITY_AUTH 1 /* authenticated packets */ -#define RXRPC_SECURITY_ENCRYPT 2 /* encrypted packets */ - -/* - * RxRPC security indices - */ -#define RXRPC_SECURITY_NONE 0 /* no security protocol */ -#define RXRPC_SECURITY_RXKAD 2 /* kaserver or kerberos 4 */ -#define RXRPC_SECURITY_RXGK 4 /* gssapi-based */ -#define RXRPC_SECURITY_RXK5 5 /* kerberos 5 */ - -#endif /* _LINUX_RXRPC_H */ -- cgit v1.2.3 From bc2fb7ed089ffd16d26e1d95b898a37d2b37d201 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 15 May 2017 09:34:01 -0400 Subject: cgroup: add @flags to css_task_iter_start() and implement CSS_TASK_ITER_PROCS css_task_iter currently always walks all tasks. With the scheduled cgroup v2 thread support, the iterator would need to handle multiple types of iteration. As a preparation, add @flags to css_task_iter_start() and implement CSS_TASK_ITER_PROCS. If the flag is not specified, it walks all tasks as before. When asserted, the iterator only walks the group leaders. For now, the only user of the flag is cgroup v2 "cgroup.procs" file which no longer needs to skip non-leader tasks in cgroup_procs_next(). Note that cgroup v1 "cgroup.procs" can't use the group leader walk as v1 "cgroup.procs" doesn't mean "list all thread group leaders in the cgroup" but "list all thread group id's with any threads in the cgroup". While at it, update cgroup_procs_show() to use task_pid_vnr() instead of task_tgid_vnr(). As the iteration guarantees that the function only sees group leaders, this doesn't change the output and will allow sharing the function for thread iteration. Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 308b10797a54..cae5831ae650 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -36,9 +36,13 @@ #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 +/* walk only threadgroup leaders */ +#define CSS_TASK_ITER_PROCS (1U << 0) + /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { struct cgroup_subsys *ss; + unsigned int flags; struct list_head *cset_pos; struct list_head *cset_head; @@ -129,7 +133,7 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); -void css_task_iter_start(struct cgroup_subsys_state *css, +void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); void css_task_iter_end(struct css_task_iter *it); -- cgit v1.2.3 From 454000adaa2a7420df6e56a42f22726d05872a3f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 15 May 2017 09:34:02 -0400 Subject: cgroup: introduce cgroup->dom_cgrp and threaded css_set handling cgroup v2 is in the process of growing thread granularity support. A threaded subtree is composed of a thread root and threaded cgroups which are proper members of the subtree. The root cgroup of the subtree serves as the domain cgroup to which the processes (as opposed to threads / tasks) of the subtree conceptually belong and domain-level resource consumptions not tied to any specific task are charged. Inside the subtree, threads won't be subject to process granularity or no-internal-task constraint and can be distributed arbitrarily across the subtree. This patch introduces cgroup->dom_cgrp along with threaded css_set handling. * cgroup->dom_cgrp points to self for normal and thread roots. For proper thread subtree members, points to the dom_cgrp (the thread root). * css_set->dom_cset points to self if for normal and thread roots. If threaded, points to the css_set which belongs to the cgrp->dom_cgrp. The dom_cgrp serves as the resource domain and keeps the matching csses available. The dom_cset holds those csses and makes them easily accessible. * All threaded csets are linked on their dom_csets to enable iteration of all threaded tasks. * cgroup->nr_threaded_children keeps track of the number of threaded children. This patch adds the above but doesn't actually use them yet. The following patches will build on top. v4: ->nr_threaded_children added. v3: ->proc_cgrp/cset renamed to ->dom_cgrp/cset. Updated for the new enable-threaded-per-cgroup behavior. v2: Added cgroup_is_threaded() helper. Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 33 +++++++++++++++++++++++++++++---- include/linux/cgroup.h | 3 ++- 2 files changed, 31 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ae7bc1e70085..651c4363c85e 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -172,6 +172,14 @@ struct css_set { /* reference count */ refcount_t refcount; + /* + * For a domain cgroup, the following points to self. If threaded, + * to the matching cset of the nearest domain ancestor. The + * dom_cset provides access to the domain cgroup and its csses to + * which domain level resource consumptions should be charged. + */ + struct css_set *dom_cset; + /* the default cgroup associated with this css_set */ struct cgroup *dfl_cgrp; @@ -200,6 +208,10 @@ struct css_set { */ struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; + /* all threaded csets whose ->dom_cset points to this cset */ + struct list_head threaded_csets; + struct list_head threaded_csets_node; + /* * List running through all cgroup groups in the same hash * slot. Protected by css_set_lock @@ -267,12 +279,16 @@ struct cgroup { * doesn't have any tasks. * * All children which have non-zero nr_populated_csets and/or - * nr_populated_children of their own contribute one to - * nr_populated_children. The counter is zero iff this cgroup's - * subtree proper doesn't have any tasks. + * nr_populated_children of their own contribute one to either + * nr_populated_domain_children or nr_populated_threaded_children + * depending on their type. Each counter is zero iff all cgroups + * of the type in the subtree proper don't have any tasks. */ int nr_populated_csets; - int nr_populated_children; + int nr_populated_domain_children; + int nr_populated_threaded_children; + + int nr_threaded_children; /* # of live threaded child cgroups */ struct kernfs_node *kn; /* cgroup kernfs entry */ struct cgroup_file procs_file; /* handle for "cgroup.procs" */ @@ -310,6 +326,15 @@ struct cgroup { */ struct list_head e_csets[CGROUP_SUBSYS_COUNT]; + /* + * If !threaded, self. If threaded, it points to the nearest + * domain ancestor. Inside a threaded subtree, cgroups are exempt + * from process granularity and no-internal-task constraint. + * Domain level resource consumptions which aren't tied to a + * specific task are charged to the dom_cgrp. + */ + struct cgroup *dom_cgrp; + /* * list of pidlists, up to two for each namespace (one for procs, one * for tasks); created on demand. diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index cae5831ae650..b7dd23040cd5 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -541,7 +541,8 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { - return cgrp->nr_populated_csets + cgrp->nr_populated_children; + return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children + + cgrp->nr_populated_threaded_children; } /* returns ino associated with a cgroup */ -- cgit v1.2.3 From 450ee0c1feed657894e0b4bdd48f3974af9d394c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 15 May 2017 09:34:03 -0400 Subject: cgroup: implement CSS_TASK_ITER_THREADED cgroup v2 is in the process of growing thread granularity support. Once thread mode is enabled, the root cgroup of the subtree serves as the dom_cgrp to which the processes of the subtree conceptually belong and domain-level resource consumptions not tied to any specific task are charged. In the subtree, threads won't be subject to process granularity or no-internal-task constraint and can be distributed arbitrarily across the subtree. This patch implements a new task iterator flag CSS_TASK_ITER_THREADED, which, when used on a dom_cgrp, makes the iteration include the tasks on all the associated threaded css_sets. "cgroup.procs" read path is updated to use it so that reading the file on a proc_cgrp lists all processes. This will also be used by controller implementations which need to walk processes or tasks at the resource domain level. Task iteration is implemented nested in css_set iteration. If CSS_TASK_ITER_THREADED is specified, after walking tasks of each !threaded css_set, all the associated threaded css_sets are visited before moving onto the next !threaded css_set. v2: ->cur_pcset renamed to ->cur_dcset. Updated for the new enable-threaded-per-cgroup behavior. Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b7dd23040cd5..79faa6467f76 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -38,6 +38,8 @@ /* walk only threadgroup leaders */ #define CSS_TASK_ITER_PROCS (1U << 0) +/* walk all threaded css_sets in the domain */ +#define CSS_TASK_ITER_THREADED (1U << 1) /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { @@ -47,11 +49,15 @@ struct css_task_iter { struct list_head *cset_pos; struct list_head *cset_head; + struct list_head *tcset_pos; + struct list_head *tcset_head; + struct list_head *task_pos; struct list_head *tasks_head; struct list_head *mg_tasks_head; struct css_set *cur_cset; + struct css_set *cur_dcset; struct task_struct *cur_task; struct list_head iters_node; /* css_set->task_iters */ }; -- cgit v1.2.3 From 8cfd8147df67e741d93b8783a3ea8f3c74f93a0e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 21 Jul 2017 11:14:51 -0400 Subject: cgroup: implement cgroup v2 thread support This patch implements cgroup v2 thread support. The goal of the thread mode is supporting hierarchical accounting and control at thread granularity while staying inside the resource domain model which allows coordination across different resource controllers and handling of anonymous resource consumptions. A cgroup is always created as a domain and can be made threaded by writing to the "cgroup.type" file. When a cgroup becomes threaded, it becomes a member of a threaded subtree which is anchored at the closest ancestor which isn't threaded. The threads of the processes which are in a threaded subtree can be placed anywhere without being restricted by process granularity or no-internal-process constraint. Note that the threads aren't allowed to escape to a different threaded subtree. To be used inside a threaded subtree, a controller should explicitly support threaded mode and be able to handle internal competition in the way which is appropriate for the resource. The root of a threaded subtree, the nearest ancestor which isn't threaded, is called the threaded domain and serves as the resource domain for the whole subtree. This is the last cgroup where domain controllers are operational and where all the domain-level resource consumptions in the subtree are accounted. This allows threaded controllers to operate at thread granularity when requested while staying inside the scope of system-level resource distribution. As the root cgroup is exempt from the no-internal-process constraint, it can serve as both a threaded domain and a parent to normal cgroups, so, unlike non-root cgroups, the root cgroup can have both domain and threaded children. Internally, in a threaded subtree, each css_set has its ->dom_cset pointing to a matching css_set which belongs to the threaded domain. This ensures that thread root level cgroup_subsys_state for all threaded controllers are readily accessible for domain-level operations. This patch enables threaded mode for the pids and perf_events controllers. Neither has to worry about domain-level resource consumptions and it's enough to simply set the flag. For more details on the interface and behavior of the thread mode, please refer to the section 2-2-2 in Documentation/cgroup-v2.txt added by this patch. v5: - Dropped silly no-op ->dom_cgrp init from cgroup_create(). Spotted by Waiman. - Documentation updated as suggested by Waiman. - cgroup.type content slightly reformatted. - Mark the debug controller threaded. v4: - Updated to the general idea of marking specific cgroups domain/threaded as suggested by PeterZ. v3: - Dropped "join" and always make mixed children join the parent's threaded subtree. v2: - After discussions with Waiman, support for mixed thread mode is added. This should address the issue that Peter pointed out where any nesting should be avoided for thread subtrees while coexisting with other domain cgroups. - Enabling / disabling thread mode now piggy backs on the existing control mask update mechanism. - Bug fixes and cleanup. Signed-off-by: Tejun Heo Cc: Waiman Long Cc: Peter Zijlstra --- include/linux/cgroup-defs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 651c4363c85e..9d741959f218 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -521,6 +521,18 @@ struct cgroup_subsys { */ bool implicit_on_dfl:1; + /* + * If %true, the controller, supports threaded mode on the default + * hierarchy. In a threaded subtree, both process granularity and + * no-internal-process constraint are ignored and a threaded + * controllers should be able to handle that. + * + * Note that as an implicit controller is automatically enabled on + * all cgroups on the default hierarchy, it should also be + * threaded. implicit && !threaded is not supported. + */ + bool threaded:1; + /* * If %false, this subsystem is properly hierarchical - * configuration, resource accounting and restriction on a parent -- cgit v1.2.3 From e8e3edb95ce6a146bc774b6cfad3553f4383edc8 Mon Sep 17 00:00:00 2001 From: Mario Rugiero Date: Mon, 29 May 2017 08:38:41 -0300 Subject: mtd: create per-device and module-scope debugfs entries Several MTD devices are using debugfs entries created in the root. This commit provides the means for a standardized subtree, creating one "mtd" entry at root, and one entry per device inside it, named after the device. The tree is registered in add_mtd_device, and released in del_mtd_device. Devices docg3, mtdswap and nandsim were updated to use this subtree instead of custom ones, and their entries were prefixed with the drivers' names. Signed-off-by: Mario J. Rugiero Acked-by: Boris Brezillon Signed-off-by: Brian Norris --- include/linux/mtd/mtd.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index f8a2ef239c60..6cd0f6b7658b 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -206,6 +206,15 @@ struct mtd_pairing_scheme { struct module; /* only needed for owner field in mtd_info */ +/** + * struct mtd_debug_info - debugging information for an MTD device. + * + * @dfs_dir: direntry object of the MTD device debugfs directory + */ +struct mtd_debug_info { + struct dentry *dfs_dir; +}; + struct mtd_info { u_char type; uint32_t flags; @@ -346,6 +355,7 @@ struct mtd_info { struct module *owner; struct device dev; int usecount; + struct mtd_debug_info dbg; }; int mtd_ooblayout_ecc(struct mtd_info *mtd, int section, -- cgit v1.2.3 From db3e50f3234ba1a477413f56a9e5800a73dca786 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 21 Jul 2017 14:39:31 +0300 Subject: device property: Get rid of struct fwnode_handle type field Instead of relying on the struct fwnode_handle type field, define fwnode_operations structs for all separate types of fwnodes. To find out the type, compare to the ops field to relevant ops structs. This change has two benefits: 1. it avoids adding the type field to each and every instance of struct fwnode_handle, thus saving memory and 2. makes the ops field the single factor that defines both the types of the fwnode as well as defines the implementation of its operations, decreasing the possibility of bugs when developing code dealing with fwnode internals. Suggested-by: Rob Herring Signed-off-by: Sakari Ailus Reviewed-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 8 ++------ include/linux/fwnode.h | 11 ----------- include/linux/irqdomain.h | 4 +++- include/linux/of.h | 3 +-- 4 files changed, 6 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c749eef1daa1..71b763f0bee9 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -57,9 +57,6 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev) acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) - -extern const struct fwnode_operations acpi_fwnode_ops; - static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; @@ -68,15 +65,14 @@ static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) if (!fwnode) return NULL; - fwnode->type = FWNODE_ACPI_STATIC; - fwnode->ops = &acpi_fwnode_ops; + fwnode->ops = &acpi_static_fwnode_ops; return fwnode; } static inline void acpi_free_fwnode_static(struct fwnode_handle *fwnode) { - if (WARN_ON(!fwnode || fwnode->type != FWNODE_ACPI_STATIC)) + if (WARN_ON(!is_acpi_static_node(fwnode))) return; kfree(fwnode); diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 50893a1646cf..c5dbc48b55dd 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -14,20 +14,9 @@ #include -enum fwnode_type { - FWNODE_INVALID = 0, - FWNODE_OF, - FWNODE_ACPI, - FWNODE_ACPI_DATA, - FWNODE_ACPI_STATIC, - FWNODE_PDATA, - FWNODE_IRQCHIP -}; - struct fwnode_operations; struct fwnode_handle { - enum fwnode_type type; struct fwnode_handle *secondary; const struct fwnode_operations *ops; }; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index cac77a5c5555..d24273840b79 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -265,9 +265,11 @@ static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) return node ? &node->fwnode : NULL; } +extern const struct fwnode_operations irqchip_fwnode_ops; + static inline bool is_fwnode_irqchip(struct fwnode_handle *fwnode) { - return fwnode && fwnode->type == FWNODE_IRQCHIP; + return fwnode && fwnode->ops == &irqchip_fwnode_ops; } extern void irq_domain_update_bus_token(struct irq_domain *domain, diff --git a/include/linux/of.h b/include/linux/of.h index 4a8a70916237..cfc34117fc92 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -104,7 +104,6 @@ extern const struct fwnode_operations of_fwnode_ops; static inline void of_node_init(struct device_node *node) { kobject_init(&node->kobj, &of_node_ktype); - node->fwnode.type = FWNODE_OF; node->fwnode.ops = &of_fwnode_ops; } @@ -152,7 +151,7 @@ void of_core_init(void); static inline bool is_of_node(const struct fwnode_handle *fwnode) { - return !IS_ERR_OR_NULL(fwnode) && fwnode->type == FWNODE_OF; + return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &of_fwnode_ops; } #define to_of_node(__fwnode) \ -- cgit v1.2.3 From 99a85464693faa9b6829cb753b328c2e4434d94b Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 21 Jul 2017 14:39:34 +0300 Subject: ACPI: Constify internal fwnode arguments Constify internal ACPI fwnode arguments in preparation for the same in fwnode API. Signed-off-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 40 ++++++++++++++++++++++------------------ 1 file changed, 22 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 71b763f0bee9..4d9fb610f114 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1003,13 +1003,14 @@ struct acpi_reference_args { }; #ifdef CONFIG_ACPI -int acpi_dev_get_property(struct acpi_device *adev, const char *name, +int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); -int __acpi_node_get_property_reference(struct fwnode_handle *fwnode, +int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct acpi_reference_args *args); -static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode, +static inline int acpi_node_get_property_reference( + const struct fwnode_handle *fwnode, const char *name, size_t index, struct acpi_reference_args *args) { @@ -1017,13 +1018,15 @@ static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode, MAX_ACPI_REFERENCE_ARGS, args); } -int acpi_node_prop_get(struct fwnode_handle *fwnode, const char *propname, +int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); -int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname, - enum dev_prop_type proptype, void *val); -int acpi_node_prop_read(struct fwnode_handle *fwnode, const char *propname, - enum dev_prop_type proptype, void *val, size_t nval); -int acpi_dev_prop_read(struct acpi_device *adev, const char *propname, +int acpi_dev_prop_read_single(struct acpi_device *adev, + const char *propname, enum dev_prop_type proptype, + void *val); +int acpi_node_prop_read(const struct fwnode_handle *fwnode, + const char *propname, enum dev_prop_type proptype, + void *val, size_t nval); +int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val, size_t nval); struct fwnode_handle *acpi_get_next_subnode(struct fwnode_handle *fwnode, @@ -1100,35 +1103,36 @@ static inline int acpi_dev_get_property(struct acpi_device *adev, } static inline int -__acpi_node_get_property_reference(struct fwnode_handle *fwnode, +__acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct acpi_reference_args *args) { return -ENXIO; } -static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode, - const char *name, size_t index, - struct acpi_reference_args *args) +static inline int +acpi_node_get_property_reference(const struct fwnode_handle *fwnode, + const char *name, size_t index, + struct acpi_reference_args *args) { return -ENXIO; } -static inline int acpi_node_prop_get(struct fwnode_handle *fwnode, +static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return -ENXIO; } -static inline int acpi_dev_prop_get(struct acpi_device *adev, +static inline int acpi_dev_prop_get(const struct acpi_device *adev, const char *propname, void **valptr) { return -ENXIO; } -static inline int acpi_dev_prop_read_single(struct acpi_device *adev, +static inline int acpi_dev_prop_read_single(const struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val) @@ -1136,7 +1140,7 @@ static inline int acpi_dev_prop_read_single(struct acpi_device *adev, return -ENXIO; } -static inline int acpi_node_prop_read(struct fwnode_handle *fwnode, +static inline int acpi_node_prop_read(const struct fwnode_handle *fwnode, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) @@ -1144,7 +1148,7 @@ static inline int acpi_node_prop_read(struct fwnode_handle *fwnode, return -ENXIO; } -static inline int acpi_dev_prop_read(struct acpi_device *adev, +static inline int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) -- cgit v1.2.3 From 37ba983cfb47cc7b353146422c437468fcb29c61 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 21 Jul 2017 14:39:36 +0300 Subject: device property: Constify fwnode property API Make fwnode arguments to the fwnode property API const. Signed-off-by: Sakari Ailus Reviewed-by: Rob Herring Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 20 ++++++++------- include/linux/fwnode.h | 26 +++++++++++--------- include/linux/property.h | 63 +++++++++++++++++++++++++----------------------- 3 files changed, 58 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 4d9fb610f114..8b9edf87b98d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1029,13 +1029,14 @@ int acpi_node_prop_read(const struct fwnode_handle *fwnode, int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val, size_t nval); -struct fwnode_handle *acpi_get_next_subnode(struct fwnode_handle *fwnode, +struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); -struct fwnode_handle *acpi_node_get_parent(struct fwnode_handle *fwnode); +struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode); -struct fwnode_handle *acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode, - struct fwnode_handle *prev); -int acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode, +struct fwnode_handle * +acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, + struct fwnode_handle *prev); +int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle **remote, struct fwnode_handle **port, struct fwnode_handle **endpoint); @@ -1157,26 +1158,27 @@ static inline int acpi_dev_prop_read(const struct acpi_device *adev, } static inline struct fwnode_handle * -acpi_get_next_subnode(struct fwnode_handle *fwnode, struct fwnode_handle *child) +acpi_get_next_subnode(const struct fwnode_handle *fwnode, + struct fwnode_handle *child) { return NULL; } static inline struct fwnode_handle * -acpi_node_get_parent(struct fwnode_handle *fwnode) +acpi_node_get_parent(const struct fwnode_handle *fwnode) { return NULL; } static inline struct fwnode_handle * -acpi_graph_get_next_endpoint(struct fwnode_handle *fwnode, +acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { return ERR_PTR(-ENXIO); } static inline int -acpi_graph_get_remote_endpoint(struct fwnode_handle *fwnode, +acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle **remote, struct fwnode_handle **port, struct fwnode_handle **endpoint) diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index c5dbc48b55dd..7b50ee4edcfc 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -55,30 +55,32 @@ struct fwnode_endpoint { struct fwnode_operations { void (*get)(struct fwnode_handle *fwnode); void (*put)(struct fwnode_handle *fwnode); - bool (*device_is_available)(struct fwnode_handle *fwnode); - bool (*property_present)(struct fwnode_handle *fwnode, + bool (*device_is_available)(const struct fwnode_handle *fwnode); + bool (*property_present)(const struct fwnode_handle *fwnode, const char *propname); - int (*property_read_int_array)(struct fwnode_handle *fwnode, + int (*property_read_int_array)(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval); - int (*property_read_string_array)(struct fwnode_handle *fwnode_handle, - const char *propname, - const char **val, size_t nval); - struct fwnode_handle *(*get_parent)(struct fwnode_handle *fwnode); + int + (*property_read_string_array)(const struct fwnode_handle *fwnode_handle, + const char *propname, const char **val, + size_t nval); + struct fwnode_handle *(*get_parent)(const struct fwnode_handle *fwnode); struct fwnode_handle * - (*get_next_child_node)(struct fwnode_handle *fwnode, + (*get_next_child_node)(const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle * - (*get_named_child_node)(struct fwnode_handle *fwnode, const char *name); + (*get_named_child_node)(const struct fwnode_handle *fwnode, + const char *name); struct fwnode_handle * - (*graph_get_next_endpoint)(struct fwnode_handle *fwnode, + (*graph_get_next_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_handle *prev); struct fwnode_handle * - (*graph_get_remote_endpoint)(struct fwnode_handle *fwnode); + (*graph_get_remote_endpoint)(const struct fwnode_handle *fwnode); struct fwnode_handle * (*graph_get_port_parent)(struct fwnode_handle *fwnode); - int (*graph_parse_endpoint)(struct fwnode_handle *fwnode, + int (*graph_parse_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); }; diff --git a/include/linux/property.h b/include/linux/property.h index 7e77039e6b81..edff3f89e755 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -51,46 +51,48 @@ int device_property_read_string(struct device *dev, const char *propname, int device_property_match_string(struct device *dev, const char *propname, const char *string); -bool fwnode_device_is_available(struct fwnode_handle *fwnode); -bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname); -int fwnode_property_read_u8_array(struct fwnode_handle *fwnode, +bool fwnode_device_is_available(const struct fwnode_handle *fwnode); +bool fwnode_property_present(const struct fwnode_handle *fwnode, + const char *propname); +int fwnode_property_read_u8_array(const struct fwnode_handle *fwnode, const char *propname, u8 *val, size_t nval); -int fwnode_property_read_u16_array(struct fwnode_handle *fwnode, +int fwnode_property_read_u16_array(const struct fwnode_handle *fwnode, const char *propname, u16 *val, size_t nval); -int fwnode_property_read_u32_array(struct fwnode_handle *fwnode, +int fwnode_property_read_u32_array(const struct fwnode_handle *fwnode, const char *propname, u32 *val, size_t nval); -int fwnode_property_read_u64_array(struct fwnode_handle *fwnode, +int fwnode_property_read_u64_array(const struct fwnode_handle *fwnode, const char *propname, u64 *val, size_t nval); -int fwnode_property_read_string_array(struct fwnode_handle *fwnode, +int fwnode_property_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval); -int fwnode_property_read_string(struct fwnode_handle *fwnode, +int fwnode_property_read_string(const struct fwnode_handle *fwnode, const char *propname, const char **val); -int fwnode_property_match_string(struct fwnode_handle *fwnode, +int fwnode_property_match_string(const struct fwnode_handle *fwnode, const char *propname, const char *string); -struct fwnode_handle *fwnode_get_parent(struct fwnode_handle *fwnode); -struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); -struct fwnode_handle *fwnode_get_next_child_node(struct fwnode_handle *fwnode, - struct fwnode_handle *child); +struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_parent( + struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_next_child_node( + const struct fwnode_handle *fwnode, struct fwnode_handle *child); #define fwnode_for_each_child_node(fwnode, child) \ for (child = fwnode_get_next_child_node(fwnode, NULL); child; \ child = fwnode_get_next_child_node(fwnode, child)) -struct fwnode_handle *device_get_next_child_node(struct device *dev, - struct fwnode_handle *child); +struct fwnode_handle *device_get_next_child_node( + struct device *dev, struct fwnode_handle *child); #define device_for_each_child_node(dev, child) \ for (child = device_get_next_child_node(dev, NULL); child; \ child = device_get_next_child_node(dev, child)) -struct fwnode_handle *fwnode_get_named_child_node(struct fwnode_handle *fwnode, - const char *childname); +struct fwnode_handle *fwnode_get_named_child_node( + const struct fwnode_handle *fwnode, const char *childname); struct fwnode_handle *device_get_named_child_node(struct device *dev, const char *childname); @@ -129,31 +131,31 @@ static inline int device_property_read_u64(struct device *dev, return device_property_read_u64_array(dev, propname, val, 1); } -static inline bool fwnode_property_read_bool(struct fwnode_handle *fwnode, +static inline bool fwnode_property_read_bool(const struct fwnode_handle *fwnode, const char *propname) { return fwnode_property_present(fwnode, propname); } -static inline int fwnode_property_read_u8(struct fwnode_handle *fwnode, +static inline int fwnode_property_read_u8(const struct fwnode_handle *fwnode, const char *propname, u8 *val) { return fwnode_property_read_u8_array(fwnode, propname, val, 1); } -static inline int fwnode_property_read_u16(struct fwnode_handle *fwnode, +static inline int fwnode_property_read_u16(const struct fwnode_handle *fwnode, const char *propname, u16 *val) { return fwnode_property_read_u16_array(fwnode, propname, val, 1); } -static inline int fwnode_property_read_u32(struct fwnode_handle *fwnode, +static inline int fwnode_property_read_u32(const struct fwnode_handle *fwnode, const char *propname, u32 *val) { return fwnode_property_read_u32_array(fwnode, propname, val, 1); } -static inline int fwnode_property_read_u64(struct fwnode_handle *fwnode, +static inline int fwnode_property_read_u64(const struct fwnode_handle *fwnode, const char *propname, u64 *val) { return fwnode_property_read_u64_array(fwnode, propname, val, 1); @@ -274,19 +276,20 @@ int device_get_phy_mode(struct device *dev); void *device_get_mac_address(struct device *dev, char *addr, int alen); struct fwnode_handle *fwnode_graph_get_next_endpoint( - struct fwnode_handle *fwnode, struct fwnode_handle *prev); + const struct fwnode_handle *fwnode, struct fwnode_handle *prev); struct fwnode_handle * -fwnode_graph_get_port_parent(struct fwnode_handle *fwnode); +fwnode_graph_get_port_parent(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_port_parent( - struct fwnode_handle *fwnode); + const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_port( - struct fwnode_handle *fwnode); + const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_endpoint( - struct fwnode_handle *fwnode); -struct fwnode_handle *fwnode_graph_get_remote_node(struct fwnode_handle *fwnode, - u32 port, u32 endpoint); + const struct fwnode_handle *fwnode); +struct fwnode_handle * +fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port, + u32 endpoint); -int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode, +int fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); #endif /* _LINUX_PROPERTY_H_ */ -- cgit v1.2.3 From 3e3119d3088f41106f3581d39e7694a50ca3fc02 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Fri, 21 Jul 2017 15:11:49 +0300 Subject: device property: Introduce fwnode_property_get_reference_args The new fwnode_property_get_reference_args() interface amends the fwnode property API with the functionality of both of_parse_phandle_with_args() and __acpi_node_get_property_reference(). The semantics is slightly different: the cells property is ignored on ACPI as the number of arguments can be explicitly obtained from the firmware interface. Signed-off-by: Sakari Ailus Signed-off-by: Rafael J. Wysocki --- include/linux/fwnode.h | 19 +++++++++++++++++++ include/linux/property.h | 4 ++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 7b50ee4edcfc..0c35b6caf0f6 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -33,6 +33,20 @@ struct fwnode_endpoint { const struct fwnode_handle *local_fwnode; }; +#define NR_FWNODE_REFERENCE_ARGS 8 + +/** + * struct fwnode_reference_args - Fwnode reference with additional arguments + * @fwnode:- A reference to the base fwnode + * @nargs: Number of elements in @args array + * @args: Integer arguments on the fwnode + */ +struct fwnode_reference_args { + struct fwnode_handle *fwnode; + unsigned int nargs; + unsigned int args[NR_FWNODE_REFERENCE_ARGS]; +}; + /** * struct fwnode_operations - Operations for fwnode interface * @get: Get a reference to an fwnode. @@ -46,6 +60,7 @@ struct fwnode_endpoint { * @get_parent: Return the parent of an fwnode. * @get_next_child_node: Return the next child node in an iteration. * @get_named_child_node: Return a child node with a given name. + * @get_reference_args: Return a reference pointed to by a property, with args * @graph_get_next_endpoint: Return an endpoint node in an iteration. * @graph_get_remote_endpoint: Return the remote endpoint node of a local * endpoint node. @@ -73,6 +88,10 @@ struct fwnode_operations { struct fwnode_handle * (*get_named_child_node)(const struct fwnode_handle *fwnode, const char *name); + int (*get_reference_args)(const struct fwnode_handle *fwnode, + const char *prop, const char *nargs_prop, + unsigned int nargs, unsigned int index, + struct fwnode_reference_args *args); struct fwnode_handle * (*graph_get_next_endpoint)(const struct fwnode_handle *fwnode, struct fwnode_handle *prev); diff --git a/include/linux/property.h b/include/linux/property.h index edff3f89e755..6bebee13c5e0 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -73,6 +73,10 @@ int fwnode_property_read_string(const struct fwnode_handle *fwnode, const char *propname, const char **val); int fwnode_property_match_string(const struct fwnode_handle *fwnode, const char *propname, const char *string); +int fwnode_property_get_reference_args(const struct fwnode_handle *fwnode, + const char *prop, const char *nargs_prop, + unsigned int nargs, unsigned int index, + struct fwnode_reference_args *args); struct fwnode_handle *fwnode_get_parent(const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_get_next_parent( -- cgit v1.2.3 From 2d045036322c29b69c22f06530f1130338d06373 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 19 Jul 2017 15:42:41 +0530 Subject: cpufreq: governor: Drop min_sampling_rate The cpufreq core and governors aren't supposed to set a limit on how fast we want to try changing the frequency. This is currently done for the legacy governors with help of min_sampling_rate. At worst, we may end up setting the sampling rate to a value lower than the rate at which frequency can be changed and then one of the CPUs in the policy will be only changing frequency for ever. But that is something for the user to decide and there is no need to have special handling for such cases in the core. Leave it for the user to figure out. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index f10a9b3761cd..02aec384cab9 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -491,9 +491,7 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, * For CPUs with transition latency > 10ms (mostly drivers with CPUFREQ_ETERNAL) * the ondemand governor will not work. All times here are in us (microseconds). */ -#define MIN_SAMPLING_RATE_RATIO (2) #define LATENCY_MULTIPLIER (1000) -#define MIN_LATENCY_MULTIPLIER (20) #define TRANSITION_LATENCY_LIMIT (10 * 1000 * 1000) struct cpufreq_governor { -- cgit v1.2.3 From aa7519af450d3c62a057aece24877c34562fa25a Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 19 Jul 2017 15:42:42 +0530 Subject: cpufreq: Use transition_delay_us for legacy governors as well The policy->transition_delay_us field is used only by the schedutil governor currently, and this field describes how fast the driver wants the cpufreq governor to change CPUs frequency. It should rather be a common thing across all governors, as it doesn't have any schedutil dependency here. Create a new helper cpufreq_policy_transition_delay_us() to get the transition delay across all governors. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 02aec384cab9..aaadfc543f63 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -523,6 +523,7 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, unsigned int relation); unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy, unsigned int target_freq); +unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy); int cpufreq_register_governor(struct cpufreq_governor *governor); void cpufreq_unregister_governor(struct cpufreq_governor *governor); -- cgit v1.2.3 From bd8c9ba3b1e2037af5af4e48aea1087212838179 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 17 Jul 2017 17:19:25 -0700 Subject: PM / suspend: Export pm_suspend_target_state Have the core suspend/resume framework store the system-wide suspend state (suspend_state_t) we are about to enter, and expose it to drivers via pm_suspend_target_state in order to retrieve that. The state is assigned in suspend_devices_and_enter(). This is useful for platform specific drivers that may need to take a slightly different suspend/resume path based on the system's suspend/resume state being entered. Signed-off-by: Florian Fainelli Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 0b1cf32edfd7..2159f6841768 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -427,6 +427,7 @@ extern int unregister_pm_notifier(struct notifier_block *nb); /* drivers/base/power/wakeup.c */ extern bool events_check_enabled; extern unsigned int pm_wakeup_irq; +extern suspend_state_t pm_suspend_target_state; extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); -- cgit v1.2.3 From 8d8b2441db9647890251538f60b75a4e45fdef8d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 19 Jul 2017 02:38:44 +0200 Subject: PM / sleep: Do not print debug messages by default Debug messages from the system suspend/hibernation infrastructure can fill up the entire kernel log buffer in some cases and anyway they are only useful for debugging. They depend on CONFIG_PM_DEBUG, but that is set as a rule as some generally useful diagnostic facilities depend on it too. For this reason, avoid printing those messages by default, but make it possible to turn them on as needed with the help of a new sysfs attribute under /sys/power/. Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 2159f6841768..707e4cdf21c2 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -492,8 +492,14 @@ static inline void unlock_system_sleep(void) {} #ifdef CONFIG_PM_SLEEP_DEBUG extern bool pm_print_times_enabled; +extern __printf(1, 2) void pm_pr_dbg(const char *fmt, ...); #else #define pm_print_times_enabled (false) + +#include + +#define pm_pr_dbg(fmt, ...) \ + no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) #endif #ifdef CONFIG_PM_AUTOSLEEP -- cgit v1.2.3 From 1455cf8dbfd06aa7651dcfccbadb7a093944ca65 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 19 Jul 2017 17:24:30 -0700 Subject: driver core: emit uevents when device is bound to a driver There are certain touch controllers that may come up in either normal (application) or boot mode, depending on whether firmware/configuration is corrupted when they are powered on. In boot mode the kernel does not create input device instance (because it does not necessarily know the characteristics of the input device in question). Another number of controllers does not store firmware in a non-volatile memory, and they similarly need to have firmware loaded before input device instance is created. There are also other types of devices with similar behavior. There is a desire to be able to trigger firmware loading via udev, but it has to happen only when driver is bound to a physical device (i2c or spi). These udev actions can not use ADD events, as those happen too early, so we are introducing BIND and UNBIND events that are emitted at the right moment. Also, many drivers create additional driver-specific device attributes when binding to the device, to provide userspace with additional controls. The new events allow userspace to adjust these driver-specific attributes without worrying that they are not there yet. Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index ca85cb80e99a..12f5ddccb97c 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -57,6 +57,8 @@ enum kobject_action { KOBJ_MOVE, KOBJ_ONLINE, KOBJ_OFFLINE, + KOBJ_BIND, + KOBJ_UNBIND, KOBJ_MAX }; -- cgit v1.2.3 From a7670d425b75f9e44b7d4d0aea04f4a6d5f34291 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 19 Jul 2017 17:24:31 -0700 Subject: driver core: make device_{add|remove}_groups() public Many drivers create additional driver-specific device attributes when binding to the device. To avoid them calling SYSFS API directly, let's export these helpers. Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 9ef518af5515..10cf209a4e82 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1200,6 +1200,11 @@ struct device *device_create_with_groups(struct class *cls, const char *fmt, ...); extern void device_destroy(struct class *cls, dev_t devt); +extern int __must_check device_add_groups(struct device *dev, + const struct attribute_group **groups); +extern void device_remove_groups(struct device *dev, + const struct attribute_group **groups); + /* * Platform "fixup" functions - allow the platform to have their say * about devices and actions that the general device layer doesn't -- cgit v1.2.3 From e323b2dddc1ce7ea7f032c986c012a04d5977dc8 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 19 Jul 2017 17:24:32 -0700 Subject: driver core: add device_{add|remove}_group() helpers We have helpers that work with NULL terminated array of groups, but many drivers only create a single supplemental group, and do not want to declare a group array. Let's provide them with helpers working with a single group. Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 10cf209a4e82..7698a513b35e 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1205,6 +1205,22 @@ extern int __must_check device_add_groups(struct device *dev, extern void device_remove_groups(struct device *dev, const struct attribute_group **groups); +static inline int __must_check device_add_group(struct device *dev, + const struct attribute_group *grp) +{ + const struct attribute_group *groups[] = { grp, NULL }; + + return device_add_groups(dev, groups); +} + +static inline void device_remove_group(struct device *dev, + const struct attribute_group *grp) +{ + const struct attribute_group *groups[] = { grp, NULL }; + + return device_remove_groups(dev, groups); +} + /* * Platform "fixup" functions - allow the platform to have their say * about devices and actions that the general device layer doesn't -- cgit v1.2.3 From 57b8ff070f9897b22e4f80fda775a489fc797008 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Wed, 19 Jul 2017 17:24:33 -0700 Subject: driver core: add devm_device_add_group() and friends Many drivers create additional driver-specific device attributes when binding to the device, and providing managed version of device_create_group() will simplify unbinding and error handling in probe path for such drivers. Without managed version driver writers either have to mix manual and managed resources, which is prone to errors, or open-code this function by providing a wrapper to device_add_group() and use it with devm_add_action() or devm_add_action_or_reset(). Signed-off-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 7698a513b35e..f52288c24734 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1221,6 +1221,15 @@ static inline void device_remove_group(struct device *dev, return device_remove_groups(dev, groups); } +extern int __must_check devm_device_add_groups(struct device *dev, + const struct attribute_group **groups); +extern void devm_device_remove_groups(struct device *dev, + const struct attribute_group **groups); +extern int __must_check devm_device_add_group(struct device *dev, + const struct attribute_group *grp); +extern void devm_device_remove_group(struct device *dev, + const struct attribute_group *grp); + /* * Platform "fixup" functions - allow the platform to have their say * about devices and actions that the general device layer doesn't -- cgit v1.2.3 From cb08e0353c249a27aed10c6f60a13871ae449d33 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 23 Jul 2017 00:03:43 +0200 Subject: PM / timekeeping: Print debug messages when requested The messages printed by tk_debug_account_sleep_time() are basically useful for system sleep debugging, so print them only when the other debug messages from the core suspend/hibernate code are enabled. While at it, make it clear that the messages from tk_debug_account_sleep_time() are about timekeeping suspend duration, because in general timekeeping may be suspeded and resumed for multiple times during one system suspend-resume cycle. Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 707e4cdf21c2..97e394feabdb 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -492,16 +492,22 @@ static inline void unlock_system_sleep(void) {} #ifdef CONFIG_PM_SLEEP_DEBUG extern bool pm_print_times_enabled; -extern __printf(1, 2) void pm_pr_dbg(const char *fmt, ...); +extern __printf(2, 3) void __pm_pr_dbg(bool defer, const char *fmt, ...); #else #define pm_print_times_enabled (false) #include -#define pm_pr_dbg(fmt, ...) \ +#define __pm_pr_dbg(defer, fmt, ...) \ no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) #endif +#define pm_pr_dbg(fmt, ...) \ + __pm_pr_dbg(false, fmt, ##__VA_ARGS__) + +#define pm_deferred_pr_dbg(fmt, ...) \ + __pm_pr_dbg(true, fmt, ##__VA_ARGS__) + #ifdef CONFIG_PM_AUTOSLEEP /* kernel/power/autosleep.c */ -- cgit v1.2.3 From bded747bb432bc5f7ad6d84ea747368b70ed9df2 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Tue, 30 May 2017 09:42:53 +0300 Subject: net/mlx5: Add raw ethernet local loopback firmware command Add support for raw ethernet local loopback firmware command. Signed-off-by: Huy Nguyen Reviewed-by: Daniel Jurgens Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 11 ++++++++--- include/linux/mlx5/vport.h | 3 ++- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 87869c04849a..57c75e8b3c19 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1016,7 +1016,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_wq_sz[0x5]; u8 nic_vport_change_event[0x1]; - u8 reserved_at_3e1[0xa]; + u8 disable_local_lb[0x1]; + u8 reserved_at_3e2[0x9]; u8 log_max_vlan_list[0x5]; u8 reserved_at_3f0[0x3]; u8 log_max_current_mc_list[0x5]; @@ -2562,7 +2563,9 @@ struct mlx5_ifc_rmpc_bits { struct mlx5_ifc_nic_vport_context_bits { u8 reserved_at_0[0x5]; u8 min_wqe_inline_mode[0x3]; - u8 reserved_at_8[0x17]; + u8 reserved_at_8[0x15]; + u8 disable_mc_local_lb[0x1]; + u8 disable_uc_local_lb[0x1]; u8 roce_en[0x1]; u8 arm_change_event[0x1]; @@ -5229,7 +5232,9 @@ struct mlx5_ifc_modify_nic_vport_context_out_bits { }; struct mlx5_ifc_modify_nic_vport_field_select_bits { - u8 reserved_at_0[0x16]; + u8 reserved_at_0[0x14]; + u8 disable_uc_local_lb[0x1]; + u8 disable_mc_local_lb[0x1]; u8 node_guid[0x1]; u8 port_guid[0x1]; u8 min_inline[0x1]; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 656c70b65dd2..aaa0bb9e7655 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -114,5 +114,6 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev, u8 other_vport, u8 port_num, int vf, struct mlx5_hca_vport_context *req); - +int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable); +int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status); #endif /* __MLX5_VPORT_H__ */ -- cgit v1.2.3 From 4a2da0b8c0782816f3ae6846ae7942fcbb0f8172 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 30 May 2017 10:05:15 +0300 Subject: IB/mlx5: Add debug control parameters for congestion control This patch adds debug control parameters for congestion control which can be read or written through debugfs. They are for reaction point and notification point nodes. These control parameters are as below: +------------------------------+-----------------------------------------+ | Name | Description | |------------------------------+-----------------------------------------| |rp_clamp_tgt_rate | When set target rate is updated to | | | current rate | |------------------------------+-----------------------------------------| |rp_clamp_tgt_rate_ati | When set update target rate based on | | | timer as well | |------------------------------+-----------------------------------------| |rp_time_reset | time between rate increase if no | | | CNP is received unit in usec | |------------------------------+-----------------------------------------| |rp_byte_reset | Number of bytes between rate inease if | | | no CNP is received | |------------------------------+-----------------------------------------| |rp_threshold | Threshold for reaction point rate | | | control | |------------------------------+-----------------------------------------| |rp_ai_rate | Rate for target rate, unit in Mbps | |------------------------------+-----------------------------------------| |rp_hai_rate | Rate for hyper increase state | | | unit in Mbps | |------------------------------+-----------------------------------------| |rp_min_dec_fac | Minimum factor by which the current | | | transmit rate can be changed when | | | processing a CNP, unit is percerntage | |------------------------------+-----------------------------------------| |rp_min_rate | Minimum value for rate limit, | | | unit in Mbps | |------------------------------+-----------------------------------------| |rp_rate_to_set_on_first_cnp | Rate that is set when first CNP is | | | received, unit is Mbps | |------------------------------+-----------------------------------------| |rp_dce_tcp_g | Used to calculate alpha | |------------------------------+-----------------------------------------| |rp_dce_tcp_rtt | Time between updates of alpha value, | | | unit is usec | |------------------------------+-----------------------------------------| |rp_rate_reduce_monitor_period | Minimum time between consecutive rate | | | reductions | |------------------------------+-----------------------------------------| |rp_initial_alpha_value | Initial value of alpha | |------------------------------+-----------------------------------------| |rp_gd | When CNP is received, flow rate is | | | reduced based on gd, rp_gd is given as | | | log2(rp_gd) | |------------------------------+-----------------------------------------| |np_cnp_dscp | dscp code point for generated cnp | |------------------------------+-----------------------------------------| |np_cnp_prio_mode | 802.1p priority for generated cnp | |------------------------------+-----------------------------------------| |np_cnp_prio | cnp priority mode | +------------------------------+-----------------------------------------+ Signed-off-by: Parav Pandit Reviewed-by: Daniel Jurgens Reviewed-by: Eli Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 57c75e8b3c19..3e697f672de5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1188,7 +1188,8 @@ struct mlx5_ifc_cong_control_r_roce_ecn_np_bits { u8 reserved_at_c0[0x12]; u8 cnp_dscp[0x6]; - u8 reserved_at_d8[0x5]; + u8 reserved_at_d8[0x4]; + u8 cnp_prio_mode[0x1]; u8 cnp_802p_prio[0x3]; u8 reserved_at_e0[0x720]; -- cgit v1.2.3 From 7ecf6d8ff154e6f7471ee537a400d43a5f3b1c57 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Tue, 30 May 2017 10:18:24 +0300 Subject: IB/mlx5: Restore IB guid/policy for virtual functions When a user sets port_guid, node_guid or policy of an IB virtual function, save this information in "struct mlx5_vf_context". This information will be restored later when pci_resume is called. To make sure this works, one can use aer-inject to generate PCI errors on mlx5 devices and verify if relevant fields are restored after PCI resume. Signed-off-by: Bodong Wang Reviewed-by: Eli Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index df6ce59a1f95..54221be5f69e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -162,6 +162,13 @@ enum dbg_rsc_type { MLX5_DBG_RSC_CQ, }; +enum port_state_policy { + MLX5_POLICY_DOWN = 0, + MLX5_POLICY_UP = 1, + MLX5_POLICY_FOLLOW = 2, + MLX5_POLICY_INVALID = 0xffffffff +}; + struct mlx5_field_desc { struct dentry *dent; int i; @@ -525,6 +532,9 @@ struct mlx5_mkey_table { struct mlx5_vf_context { int enabled; + u64 port_guid; + u64 node_guid; + enum port_state_policy policy; }; struct mlx5_core_sriov { @@ -842,13 +852,6 @@ struct mlx5_pas { u8 log_sz; }; -enum port_state_policy { - MLX5_POLICY_DOWN = 0, - MLX5_POLICY_UP = 1, - MLX5_POLICY_FOLLOW = 2, - MLX5_POLICY_INVALID = 0xffffffff -}; - enum phy_port_state { MLX5_AAA_111 }; -- cgit v1.2.3 From c1e0bfc1312d0e06bdb24e6e4e7e10b0b4313ec6 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 30 May 2017 10:29:11 +0300 Subject: net/mlx5: Introduce set delay drop command Add support to SET_DELAY_DROP command. This command will be used in downstream patches for delay packet drop. The timeout value should be indicated by delay_drop_timeout field. Packet processing will be delayed till timeout value passed or until more WQEs are posted. Setting this value to 0 disables the feature. Signed-off-by: Maor Gottlieb Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 25 ++++++++++++++++++++++++- include/linux/mlx5/qp.h | 3 +++ 2 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3e697f672de5..40c05d29d5bb 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -200,6 +200,7 @@ enum { MLX5_CMD_OP_QUERY_SQ = 0x907, MLX5_CMD_OP_CREATE_RQ = 0x908, MLX5_CMD_OP_MODIFY_RQ = 0x909, + MLX5_CMD_OP_SET_DELAY_DROP_PARAMS = 0x910, MLX5_CMD_OP_DESTROY_RQ = 0x90a, MLX5_CMD_OP_QUERY_RQ = 0x90b, MLX5_CMD_OP_CREATE_RMP = 0x90c, @@ -840,7 +841,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 retransmission_q_counters[0x1]; u8 reserved_at_183[0x1]; u8 modify_rq_counter_set_id[0x1]; - u8 reserved_at_185[0x1]; + u8 rq_delay_drop[0x1]; u8 max_qp_cnt[0xa]; u8 pkey_table_size[0x10]; @@ -5853,6 +5854,28 @@ struct mlx5_ifc_destroy_rq_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_set_delay_drop_params_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x10]; + u8 delay_drop_timeout[0x10]; +}; + +struct mlx5_ifc_set_delay_drop_params_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_destroy_rmp_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index 6f41270d80c0..fff4ec13f620 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -561,6 +561,9 @@ int mlx5_core_destroy_qp(struct mlx5_core_dev *dev, int mlx5_core_qp_query(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp, u32 *out, int outlen); +int mlx5_core_set_delay_drop(struct mlx5_core_dev *dev, + u32 timeout_usec); + int mlx5_core_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn); int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn); void mlx5_init_qp_table(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 246ac9814c5b2c0e9916dca5fbf8d6a40245fad1 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 30 May 2017 10:29:12 +0300 Subject: net/mlx5: Introduce general notification event When delay drop timeout is expired, the firmware raises general notification event of DELAY_DROP_TIMEOUT subtype. In addition the feature is disable so the driver have to reactivate the timeout. Signed-off-by: Maor Gottlieb Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/device.h | 5 +++++ include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 3 ++- 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f31a0b5377e1..a47b9ab9f2c9 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -290,6 +290,7 @@ enum mlx5_event { MLX5_EVENT_TYPE_GPIO_EVENT = 0x15, MLX5_EVENT_TYPE_PORT_MODULE_EVENT = 0x16, MLX5_EVENT_TYPE_REMOTE_CONFIG = 0x19, + MLX5_EVENT_TYPE_GENERAL_EVENT = 0x22, MLX5_EVENT_TYPE_PPS_EVENT = 0x25, MLX5_EVENT_TYPE_DB_BF_CONGESTION = 0x1a, @@ -304,6 +305,10 @@ enum mlx5_event { MLX5_EVENT_TYPE_FPGA_ERROR = 0x20, }; +enum { + MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT = 0x1, +}; + enum { MLX5_PORT_CHANGE_SUBTYPE_DOWN = 1, MLX5_PORT_CHANGE_SUBTYPE_ACTIVE = 4, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 54221be5f69e..758ef40f9316 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -192,6 +192,7 @@ enum mlx5_dev_event { MLX5_DEV_EVENT_GUID_CHANGE, MLX5_DEV_EVENT_CLIENT_REREG, MLX5_DEV_EVENT_PPS, + MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT, }; enum mlx5_port_status { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 40c05d29d5bb..4bc57647fad8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -874,7 +874,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_tc[0x4]; u8 reserved_at_1d0[0x1]; u8 dcbx[0x1]; - u8 reserved_at_1d2[0x3]; + u8 general_notification_event[0x1]; + u8 reserved_at_1d3[0x2]; u8 fpga[0x1]; u8 rol_s[0x1]; u8 rol_g[0x1]; -- cgit v1.2.3 From 03404e8ae652e02a5e3388224836cef53d7a0988 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 30 May 2017 10:29:13 +0300 Subject: IB/mlx5: Add support to dropless RQ RQs that were configured for "delay drop" will prevent packet drops when their WQEs are depleted. Marking an RQ to be drop-less is done by setting delay_drop_en in RQ context using CREATE_RQ command. Since this feature is globally activated/deactivated by using the SET_DELAY_DROP command on all the marked RQs, we activated/deactivated it according to the number of RQs with 'delay_drop' enabled. When timeout is expired, then the feature is deactivated. Therefore the driver handles the delay drop timeout event and reactivate it. Signed-off-by: Maor Gottlieb Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4bc57647fad8..f350688a12fa 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2519,7 +2519,7 @@ enum { struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; - u8 reserved_at_1[0x1]; + u8 delay_drop_en[0x1]; u8 scatter_fcs[0x1]; u8 vsd[0x1]; u8 mem_rq_type[0x4]; -- cgit v1.2.3 From 4ce749bd94f697772ac2be4fb7e7a92726e94bfb Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 8 Jun 2017 16:15:10 +0300 Subject: net/mlx5: Report enhanced capabilities for IPoIB Report 'ipoib_enhanced_offloads' capabilities from the core layer, it will be used in the next patch from this series. Signed-off-by: Yishai Hadas Reviewed-by: Maor Gottlieb Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/device.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index a47b9ab9f2c9..c13d71deaeca 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -973,7 +973,7 @@ enum mlx5_cap_type { MLX5_CAP_ATOMIC, MLX5_CAP_ROCE, MLX5_CAP_IPOIB_OFFLOADS, - MLX5_CAP_EOIB_OFFLOADS, + MLX5_CAP_IPOIB_ENHANCED_OFFLOADS, MLX5_CAP_FLOW_TABLE, MLX5_CAP_ESWITCH_FLOW_TABLE, MLX5_CAP_ESWITCH, @@ -1016,6 +1016,10 @@ enum mlx5_mcam_feature_groups { MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca_max[MLX5_CAP_ETHERNET_OFFLOADS], cap) +#define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \ + MLX5_GET(per_protocol_networking_offload_caps,\ + mdev->caps.hca_cur[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS], cap) + #define MLX5_CAP_ROCE(mdev, cap) \ MLX5_GET(roce_cap, mdev->caps.hca_cur[MLX5_CAP_ROCE], cap) -- cgit v1.2.3 From 3fffc82ad6c78fcc9d5d4eca089f00db14ab0358 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 12 Jun 2017 10:36:16 +0300 Subject: IB/mlx5: Fix existence check for extended address vector The extended address vector is the highest bit in be32 variable, but it was compared with the lowest. This patch fixes the endianness of that check and removes already declared define. Fixes: 17d2f88f92ce ("IB/mlx5: Add ODP atomics support") Reviewed-by: Artemy Kovalyov Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/qp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index fff4ec13f620..66d19b611fe4 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -212,7 +212,6 @@ struct mlx5_wqe_ctrl_seg { #define MLX5_WQE_CTRL_OPCODE_MASK 0xff #define MLX5_WQE_CTRL_WQE_INDEX_MASK 0x00ffff00 #define MLX5_WQE_CTRL_WQE_INDEX_SHIFT 8 -#define MLX5_WQE_AV_EXT 0x80000000 enum { MLX5_ETH_WQE_L3_INNER_CSUM = 1 << 4, -- cgit v1.2.3 From 58dcb60a226ee48cc66c96c27b751f06ec2bc5a9 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Mon, 19 Jun 2017 07:19:37 +0300 Subject: IB/mlx5: Expose extended error counters This patch adds below requester and responder side error counters, which will be exposed by hardware counters interface and are supported as part of query Q counters command extension. +---------------------------+-------------------------------------+ | Name | Description | |---------------------------+-------------------------------------| |resp_local_length_error | Number of times responder detected | | | local length errors | |---------------------------+-------------------------------------| |resp_cqe_error | Number of CQEs completed with error | | | at responder | |---------------------------+-------------------------------------| |req_cqe_error | Number of CQEs completed with error | | | at requester | |---------------------------+-------------------------------------| |req_remote_invalid_request | Number of times requester detected | | | remote invalid request error | |---------------------------+-------------------------------------| |req_remote_access_error | Number of times requester detected | | | remote access error | |---------------------------+-------------------------------------| |resp_remote_access_error | Number of times responder detected | | | remote access error | |---------------------------+-------------------------------------| |resp_cqe_flush_error | Number of CQEs completed with | | | flushed with error at responder | |---------------------------+-------------------------------------| |req_cqe_flush_error | Number of CQEs completed with | | | flushed with error at requester | +---------------------------+-------------------------------------+ Signed-off-by: Parav Pandit Reviewed-by: Daniel Jurgens Reviewed-by: Eli Cohen Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 44 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 42 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f350688a12fa..5bae70eb25af 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -858,7 +858,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 pcam_reg[0x1]; u8 local_ca_ack_delay[0x5]; u8 port_module_event[0x1]; - u8 reserved_at_1b1[0x1]; + u8 enhanced_error_q_counters[0x1]; u8 ports_check[0x1]; u8 reserved_at_1b3[0x1]; u8 disable_link_up[0x1]; @@ -3953,7 +3953,47 @@ struct mlx5_ifc_query_q_counter_out_bits { u8 local_ack_timeout_err[0x20]; - u8 reserved_at_320[0x4e0]; + u8 reserved_at_320[0xa0]; + + u8 resp_local_length_error[0x20]; + + u8 req_local_length_error[0x20]; + + u8 resp_local_qp_error[0x20]; + + u8 local_operation_error[0x20]; + + u8 resp_local_protection[0x20]; + + u8 req_local_protection[0x20]; + + u8 resp_cqe_error[0x20]; + + u8 req_cqe_error[0x20]; + + u8 req_mw_binding[0x20]; + + u8 req_bad_response[0x20]; + + u8 req_remote_invalid_request[0x20]; + + u8 resp_remote_invalid_request[0x20]; + + u8 req_remote_access_errors[0x20]; + + u8 resp_remote_access_errors[0x20]; + + u8 req_remote_operation_errors[0x20]; + + u8 req_transport_retries_exceeded[0x20]; + + u8 cq_overflow[0x20]; + + u8 resp_cqe_flush_error[0x20]; + + u8 req_cqe_flush_error[0x20]; + + u8 reserved_at_620[0x1e0]; }; struct mlx5_ifc_query_q_counter_in_bits { -- cgit v1.2.3 From f3301870161ca293cd14b20a802c5646da02407f Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Wed, 21 Jun 2017 09:29:36 +0300 Subject: (IB, net)/mlx4: Add resource utilization support Adding visibility of resource usage of QPs, CQs and counters used by virtual functions. This feature will be used to give the PF administrator more data while debugging VF status. Usage info was added to ALLOC_RES command, to notify the PF if the resource which is being reserved or allocated for the VF will be used by kernel driver or by user verbs. Updated reservation and allocation functions of QP, CQ and counter with additional usage parameter. Signed-off-by: Moshe Shemesh Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx4/device.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index aad5d81dfb44..3607da001ad3 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -428,6 +428,12 @@ enum mlx4_steer_type { MLX4_NUM_STEERS }; +enum mlx4_resource_usage { + MLX4_RES_USAGE_NONE, + MLX4_RES_USAGE_DRIVER, + MLX4_RES_USAGE_USER_VERBS, +}; + enum { MLX4_NUM_FEXCH = 64 * 1024, }; @@ -748,6 +754,7 @@ struct mlx4_cq { } tasklet_ctx; int reset_notify_added; struct list_head reset_notify; + u8 usage; }; struct mlx4_qp { @@ -757,6 +764,7 @@ struct mlx4_qp { atomic_t refcount; struct completion free; + u8 usage; }; struct mlx4_srq { @@ -1120,7 +1128,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt, unsigned vector, int collapsed, int timestamp_en); void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq); int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, - int *base, u8 flags); + int *base, u8 flags, u8 usage); void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt); int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp); @@ -1417,7 +1425,7 @@ int mlx4_get_phys_port_id(struct mlx4_dev *dev); int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port); int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); -int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx); +int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage); void mlx4_counter_free(struct mlx4_dev *dev, u32 idx); int mlx4_get_default_counter_index(struct mlx4_dev *dev, int port); -- cgit v1.2.3 From d08477aa975e97f1dc64c0ae59cebf98520456ce Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 29 Jun 2017 09:28:50 -0500 Subject: fcntl: Don't use ambiguous SIG_POLL si_codes We have a weird and problematic intersection of features that when they all come together result in ambiguous siginfo values, that we can not support properly. - Supporting fcntl(F_SETSIG,...) with arbitrary valid signals. - Using positive values for POLL_IN, POLL_OUT, POLL_MSG, ..., etc that imply they are signal specific si_codes and using the aforementioned arbitrary signal to deliver them. - Supporting injection of arbitrary siginfo values for debugging and checkpoint/restore. The result is that just looking at siginfo si_codes of 1 to 6 are ambigious. It could either be a signal specific si_code or it could be a generic si_code. For most of the kernel this is a non-issue but for sending signals with siginfo it is impossible to play back the kernel signals and get the same result. Strictly speaking when the si_code was changed from SI_SIGIO to POLL_IN and friends between 2.2 and 2.4 this functionality was not ambiguous, as only real time signals were supported. Before 2.4 was released the kernel began supporting siginfo with non realtime signals so they could give details of why the signal was sent. The result is that if F_SETSIG is set to one of the signals with signal specific si_codes then user space can not know why the signal was sent. I grepped through a bunch of userspace programs using debian code search to get a feel for how often people choose a signal that results in an ambiguous si_code. I only found one program doing so and it was using SIGCHLD to test the F_SETSIG functionality, and did not appear to be a real world usage. Therefore the ambiguity does not appears to be a real world problem in practice. Remove the ambiguity while introducing the smallest chance of breakage by changing the si_code to SI_SIGIO when signals with signal specific si_codes are targeted. Fixes: v2.3.40 -- Added support for queueing non-rt signals Fixes: v2.3.21 -- Changed the si_code from SI_SIGIO Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index e2678b5dbb21..c97cc20369c0 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -380,10 +380,18 @@ int unhandled_signal(struct task_struct *tsk, int sig); rt_sigmask(SIGCONT) | rt_sigmask(SIGCHLD) | \ rt_sigmask(SIGWINCH) | rt_sigmask(SIGURG) ) +#define SIG_SPECIFIC_SICODES_MASK (\ + rt_sigmask(SIGILL) | rt_sigmask(SIGFPE) | \ + rt_sigmask(SIGSEGV) | rt_sigmask(SIGBUS) | \ + rt_sigmask(SIGTRAP) | rt_sigmask(SIGCHLD) | \ + rt_sigmask(SIGPOLL) | rt_sigmask(SIGSYS) | \ + SIGEMT_MASK ) + #define sig_kernel_only(sig) siginmask(sig, SIG_KERNEL_ONLY_MASK) #define sig_kernel_coredump(sig) siginmask(sig, SIG_KERNEL_COREDUMP_MASK) #define sig_kernel_ignore(sig) siginmask(sig, SIG_KERNEL_IGNORE_MASK) #define sig_kernel_stop(sig) siginmask(sig, SIG_KERNEL_STOP_MASK) +#define sig_specific_sicodes(sig) siginmask(sig, SIG_SPECIFIC_SICODES_MASK) #define sig_fatal(t, signr) \ (!siginmask(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \ -- cgit v1.2.3 From cc731525f26af85a1c3537da41e0abd1d35e0bdb Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 16 Jul 2017 22:36:59 -0500 Subject: signal: Remove kernel interal si_code magic struct siginfo is a union and the kernel since 2.4 has been hiding a union tag in the high 16bits of si_code using the values: __SI_KILL __SI_TIMER __SI_POLL __SI_FAULT __SI_CHLD __SI_RT __SI_MESGQ __SI_SYS While this looks plausible on the surface, in practice this situation has not worked well. - Injected positive signals are not copied to user space properly unless they have these magic high bits set. - Injected positive signals are not reported properly by signalfd unless they have these magic high bits set. - These kernel internal values leaked to userspace via ptrace_peek_siginfo - It was possible to inject these kernel internal values and cause the the kernel to misbehave. - Kernel developers got confused and expected these kernel internal values in userspace in kernel self tests. - Kernel developers got confused and set si_code to __SI_FAULT which is SI_USER in userspace which causes userspace to think an ordinary user sent the signal and that it was not kernel generated. - The values make it impossible to reorganize the code to transform siginfo_copy_to_user into a plain copy_to_user. As si_code must be massaged before being passed to userspace. So remove these kernel internal si codes and make the kernel code simpler and more maintainable. To replace these kernel internal magic si_codes introduce the helper function siginfo_layout, that takes a signal number and an si_code and computes which union member of siginfo is being used. Have siginfo_layout return an enumeration so that gcc will have enough information to warn if a switch statement does not handle all of union members. A couple of architectures have a messed up ABI that defines signal specific duplications of SI_USER which causes more special cases in siginfo_layout than I would like. The good news is only problem architectures pay the cost. Update all of the code that used the previous magic __SI_ values to use the new SIL_ values and to call siginfo_layout to get those values. Escept where not all of the cases are handled remove the defaults in the switch statements so that if a new case is missed in the future the lack will show up at compile time. Modify the code that copies siginfo si_code to userspace to just copy the value and not cast si_code to a short first. The high bits are no longer used to hold a magic union member. Fixup the siginfo header files to stop including the __SI_ values in their constants and for the headers that were missing it to properly update the number of si_codes for each signal type. The fixes to copy_siginfo_from_user32 implementations has the interesting property that several of them perviously should never have worked as the __SI_ values they depended up where kernel internal. With that dependency gone those implementations should work much better. The idea of not passing the __SI_ values out to userspace and then not reinserting them has been tested with criu and criu worked without changes. Ref: 2.4.0-test1 Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index c97cc20369c0..38564e3e54c7 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -21,6 +21,20 @@ static inline void copy_siginfo(struct siginfo *to, struct siginfo *from) int copy_siginfo_to_user(struct siginfo __user *to, const struct siginfo *from); +enum siginfo_layout { + SIL_KILL, + SIL_TIMER, + SIL_POLL, + SIL_FAULT, + SIL_CHLD, + SIL_RT, +#ifdef __ARCH_SIGSYS + SIL_SYS, +#endif +}; + +enum siginfo_layout siginfo_layout(int sig, int si_code); + /* * Define some primitives to manipulate sigset_t. */ -- cgit v1.2.3 From 6c9a58e84e59a2fc937798b623f72ae4b436547d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 18 Jul 2017 18:04:17 +0300 Subject: ACPI / boot: Correct address space of __acpi_map_table() Sparse complains about wrong address space used in __acpi_map_table() and in __acpi_unmap_table(). arch/x86/kernel/acpi/boot.c:127:29: warning: incorrect type in return expression (different address spaces) arch/x86/kernel/acpi/boot.c:127:29: expected char * arch/x86/kernel/acpi/boot.c:127:29: got void [noderef] * arch/x86/kernel/acpi/boot.c:135:23: warning: incorrect type in argument 1 (different address spaces) arch/x86/kernel/acpi/boot.c:135:23: expected void [noderef] *addr arch/x86/kernel/acpi/boot.c:135:23: got char *map Correct address space to be in align of type of returned and passed parameter. Reviewed-by: Hanjun Guo Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c749eef1daa1..7443af1d16e7 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -228,8 +228,8 @@ struct acpi_subtable_proc { int count; }; -char * __acpi_map_table (unsigned long phys_addr, unsigned long size); -void __acpi_unmap_table(char *map, unsigned long size); +void __iomem *__acpi_map_table(unsigned long phys, unsigned long size); +void __acpi_unmap_table(void __iomem *map, unsigned long size); int early_acpi_boot_init(void); int acpi_boot_init (void); void acpi_boot_table_init (void); -- cgit v1.2.3 From d764a122cc7af7ab1c40c08745f0fcd33cc2f7db Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 21 Jul 2017 12:49:28 +0200 Subject: net: add new netdevice feature for offload of RX port for UDP tunnels This adds a new netdevice feature, so that the offloading of RX port for UDP tunnels can be disabled by the administrator on some netdevices, using the "rx-udp_tunnel-port-offload" feature in ethtool. This feature is set for all devices that provide ndo_udp_tunnel_add. Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- include/linux/netdev_features.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index ebd273627334..dc8b4896b77b 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -75,6 +75,7 @@ enum { NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */ NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ + NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ /* * Add your fresh new feature above and remember to update @@ -138,6 +139,7 @@ enum { #define NETIF_F_HW_TC __NETIF_F(HW_TC) #define NETIF_F_HW_ESP __NETIF_F(HW_ESP) #define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) +#define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) -- cgit v1.2.3 From 296d8ee37c50f139d934bdefbab85509b2e4a525 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 21 Jul 2017 12:49:30 +0200 Subject: net: add infrastructure to un-offload UDP tunnel port This adds a new NETDEV_UDP_TUNNEL_DROP_INFO event, similar to NETDEV_UDP_TUNNEL_PUSH_INFO, to signal to un-offload ports. This also adds udp_tunnel_drop_rx_port(), which calls ndo_udp_tunnel_del. Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 614642eb7eb7..3a3cdc1b1f31 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2317,6 +2317,7 @@ struct netdev_lag_lower_state_info { #define NETDEV_PRECHANGEUPPER 0x001A #define NETDEV_CHANGELOWERSTATE 0x001B #define NETDEV_UDP_TUNNEL_PUSH_INFO 0x001C +#define NETDEV_UDP_TUNNEL_DROP_INFO 0x001D #define NETDEV_CHANGE_TX_QUEUE_LEN 0x001E int register_netdevice_notifier(struct notifier_block *nb); -- cgit v1.2.3 From afece3ab9a3640f9c1e064f56c8cdd4d783f6144 Mon Sep 17 00:00:00 2001 From: Thara Gopinath Date: Fri, 14 Jul 2017 13:10:15 -0400 Subject: PM / Domains: Add time accounting to various genpd states This patch adds support to calculate the time spent by the generic power domains in on and various idle states. Signed-off-by: Thara Gopinath Acked-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 41004d97cefa..84f423d5633e 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -43,6 +43,7 @@ struct genpd_power_state { s64 power_on_latency_ns; s64 residency_ns; struct fwnode_handle *fwnode; + ktime_t idle_time; }; struct genpd_lock_ops; @@ -78,6 +79,8 @@ struct generic_pm_domain { unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ void *free; /* Free the state that was allocated for default */ + ktime_t on_time; + ktime_t accounting_time; const struct genpd_lock_ops *lock_ops; union { struct mutex mlock; -- cgit v1.2.3 From 786f41fb6b008ea4341355b99083a38853a5311d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 21 Jul 2017 02:09:22 +0200 Subject: PM / core: Split dpm_suspend_noirq() and dpm_resume_noirq() Put the device interrupts disabling and enabling as well as cpuidle_pause() and cpuidle_resume() called during the "noirq" stages of system suspend into separate functions to allow the core suspend-to-idle code to be optimized (later). The only functional difference this makes is that debug facilities and diagnostic tools will not include the above operations into the "noirq" device suspend/resume duration measurements. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index b8b4df09fd8f..47ded8aa8a5d 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -689,6 +689,8 @@ struct dev_pm_domain { extern void device_pm_lock(void); extern void dpm_resume_start(pm_message_t state); extern void dpm_resume_end(pm_message_t state); +extern void dpm_noirq_resume_devices(pm_message_t state); +extern void dpm_noirq_end(void); extern void dpm_resume_noirq(pm_message_t state); extern void dpm_resume_early(pm_message_t state); extern void dpm_resume(pm_message_t state); @@ -697,6 +699,8 @@ extern void dpm_complete(pm_message_t state); extern void device_pm_unlock(void); extern int dpm_suspend_end(pm_message_t state); extern int dpm_suspend_start(pm_message_t state); +extern void dpm_noirq_begin(void); +extern int dpm_noirq_suspend_devices(pm_message_t state); extern int dpm_suspend_noirq(pm_message_t state); extern int dpm_suspend_late(pm_message_t state); extern int dpm_suspend(pm_message_t state); -- cgit v1.2.3 From cb1844c47279fb59129f8a021a0b09bcf2011ad7 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:26 +0800 Subject: sctp: remove the typedef sctp_initack_chunk_t This patch is to remove the typedef sctp_initack_chunk_t, and replace with struct sctp_initack_chunk in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 913474dfc96c..05c2099be537 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -336,7 +336,10 @@ struct sctp_hmac_algo_param { * The INIT ACK chunk is used to acknowledge the initiation of an SCTP * association. */ -typedef struct sctp_init_chunk sctp_initack_chunk_t; +struct sctp_initack_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_inithdr init_hdr; +}; /* Section 3.3.3.1 State Cookie (7) */ typedef struct sctp_cookie_param { -- cgit v1.2.3 From f48ef4c7f7979e8e658b7e038a82f096ab292d70 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:27 +0800 Subject: sctp: remove the typedef sctp_cookie_param_t This patch is to remove the typedef sctp_cookie_param_t, and replace with struct sctp_cookie_param in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 05c2099be537..9e77abda2111 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -342,10 +342,10 @@ struct sctp_initack_chunk { }; /* Section 3.3.3.1 State Cookie (7) */ -typedef struct sctp_cookie_param { +struct sctp_cookie_param { struct sctp_paramhdr p; __u8 body[0]; -} sctp_cookie_param_t; +}; /* Section 3.3.3.1 Unrecognized Parameters (8) */ typedef struct sctp_unrecognized_param { -- cgit v1.2.3 From 62e6b7e4ee244f8043c169c049d3b2c2c798cd60 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:28 +0800 Subject: sctp: remove the typedef sctp_unrecognized_param_t This patch is to remove the typedef sctp_unrecognized_param_t, and replace with struct sctp_unrecognized_param in the places where it's using this typedef. It is also to fix some indents in sctp_sf_do_unexpected_init() and sctp_sf_do_5_1B_init(). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 9e77abda2111..c323b3e3ecdb 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -348,10 +348,10 @@ struct sctp_cookie_param { }; /* Section 3.3.3.1 Unrecognized Parameters (8) */ -typedef struct sctp_unrecognized_param { +struct sctp_unrecognized_param { struct sctp_paramhdr param_hdr; struct sctp_paramhdr unrecognized; -} sctp_unrecognized_param_t; +}; -- cgit v1.2.3 From fe9a0fe7210d803adb3d5817da029fe39b8a4133 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:29 +0800 Subject: sctp: remove the typedef sctp_gap_ack_block_t This patch is to remove the typedef sctp_gap_ack_block_t, and replace with struct sctp_gap_ack_block in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index c323b3e3ecdb..b84b8e8340da 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -363,16 +363,16 @@ struct sctp_unrecognized_param { * subsequences of DATA chunks as represented by their TSNs. */ -typedef struct sctp_gap_ack_block { +struct sctp_gap_ack_block { __be16 start; __be16 end; -} sctp_gap_ack_block_t; +}; typedef __be32 sctp_dup_tsn_t; typedef union { - sctp_gap_ack_block_t gab; - sctp_dup_tsn_t dup; + struct sctp_gap_ack_block gab; + sctp_dup_tsn_t dup; } sctp_sack_variable_t; typedef struct sctp_sackhdr { -- cgit v1.2.3 From 9b41515636563ae76e730dbcb97fd303b94ed7d9 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:30 +0800 Subject: sctp: remove the typedef sctp_dup_tsn_t This patch is to remove the typedef sctp_dup_tsn_t, and replace with __be32 in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index b84b8e8340da..8faf74eff63d 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -368,11 +368,9 @@ struct sctp_gap_ack_block { __be16 end; }; -typedef __be32 sctp_dup_tsn_t; - typedef union { struct sctp_gap_ack_block gab; - sctp_dup_tsn_t dup; + __be32 dup; } sctp_sack_variable_t; typedef struct sctp_sackhdr { -- cgit v1.2.3 From afd93b7be6e24731d82d9fd84b8a5ea73a68214b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:31 +0800 Subject: sctp: remove the typedef sctp_sack_variable_t This patch is to remove the typedef sctp_sack_variable_t, and replace with union sctp_sack_variable in the places where it's using this typedef. It is also to fix some indents in sctp_acked(). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 8faf74eff63d..8df6ac53f05b 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -368,17 +368,17 @@ struct sctp_gap_ack_block { __be16 end; }; -typedef union { +union sctp_sack_variable { struct sctp_gap_ack_block gab; __be32 dup; -} sctp_sack_variable_t; +}; typedef struct sctp_sackhdr { __be32 cum_tsn_ack; __be32 a_rwnd; __be16 num_gap_ack_blocks; __be16 num_dup_tsns; - sctp_sack_variable_t variable[0]; + union sctp_sack_variable variable[0]; } sctp_sackhdr_t; typedef struct sctp_sack_chunk { -- cgit v1.2.3 From 787310859d8d1a72545db2343fb3ac8f765b0f35 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:32 +0800 Subject: sctp: remove the typedef sctp_sackhdr_t This patch is to remove the typedef sctp_sackhdr_t, and replace with struct sctp_sackhdr in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 8df6ac53f05b..a2e43129d11a 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -373,17 +373,17 @@ union sctp_sack_variable { __be32 dup; }; -typedef struct sctp_sackhdr { +struct sctp_sackhdr { __be32 cum_tsn_ack; __be32 a_rwnd; __be16 num_gap_ack_blocks; __be16 num_dup_tsns; union sctp_sack_variable variable[0]; -} sctp_sackhdr_t; +}; typedef struct sctp_sack_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_sackhdr_t sack_hdr; + struct sctp_sackhdr sack_hdr; } sctp_sack_chunk_t; -- cgit v1.2.3 From d4d6c61489e7e4a8944360312e572988889558a8 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:33 +0800 Subject: sctp: remove the typedef sctp_sack_chunk_t This patch is to remove the typedef sctp_sack_chunk_t, and replace with struct sctp_sack_chunk in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index a2e43129d11a..48f6560dd880 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -381,10 +381,10 @@ struct sctp_sackhdr { union sctp_sack_variable variable[0]; }; -typedef struct sctp_sack_chunk { +struct sctp_sack_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_sackhdr sack_hdr; -} sctp_sack_chunk_t; +}; /* RFC 2960. Section 3.3.5 Heartbeat Request (HEARTBEAT) (4): -- cgit v1.2.3 From 4d2dcdf4e04c938b266f06f271000e4b0f3a288f Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:34 +0800 Subject: sctp: remove the typedef sctp_heartbeathdr_t This patch is to remove the typedef sctp_heartbeathdr_t, and replace with struct sctp_heartbeathdr in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 48f6560dd880..6e26b86770f1 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -394,13 +394,13 @@ struct sctp_sack_chunk { * the present association. */ -typedef struct sctp_heartbeathdr { +struct sctp_heartbeathdr { struct sctp_paramhdr info; -} sctp_heartbeathdr_t; +}; typedef struct sctp_heartbeat_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_heartbeathdr_t hb_hdr; + struct sctp_heartbeathdr hb_hdr; } sctp_heartbeat_chunk_t; -- cgit v1.2.3 From 38c00f7482281801d6f7fe410c7a4b61ae25218e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:35 +0800 Subject: sctp: remove the typedef sctp_heartbeat_chunk_t This patch is to remove the typedef sctp_heartbeat_chunk_t, and replace with struct sctp_heartbeat_chunk in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 6e26b86770f1..bfda7c66960c 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -398,10 +398,10 @@ struct sctp_heartbeathdr { struct sctp_paramhdr info; }; -typedef struct sctp_heartbeat_chunk { +struct sctp_heartbeat_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_heartbeathdr hb_hdr; -} sctp_heartbeat_chunk_t; +}; /* For the abort and shutdown ACK we must carry the init tag in the -- cgit v1.2.3 From 441ae65ae000dd325a609306bd0cd850df50cfc4 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 23 Jul 2017 09:34:36 +0800 Subject: sctp: remove the typedef sctp_abort_chunk_t This patch is to remove the typedef sctp_abort_chunk_t, and replace with struct sctp_abort_chunk in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index bfda7c66960c..ba007163acfd 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -408,9 +408,9 @@ struct sctp_heartbeat_chunk { * common header. Just the common header is all that is needed with a * chunk descriptor. */ -typedef struct sctp_abort_chunk { +struct sctp_abort_chunk { struct sctp_chunkhdr uh; -} sctp_abort_chunk_t; +}; /* For the graceful shutdown we must carry the tag (in common header) -- cgit v1.2.3 From 4e3274705324c695f56b3e1c194cd99b76eeea0f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 7 Jun 2017 16:02:24 -0700 Subject: init_task: Remove redundant INIT_TASK_RCU_TREE_PREEMPT() macro Back in the dim distant past, the task_struct structure's RCU-related fields optionally included those needed for CONFIG_RCU_BOOST, even in CONFIG_PREEMPT_RCU builds. The INIT_TASK_RCU_TREE_PREEMPT() macro was used to provide initializers for those optional CONFIG_RCU_BOOST fields. However, the CONFIG_RCU_BOOST fields are now included unconditionally in CONFIG_PREEMPT_RCU builds, so there is no longer any need fro the INIT_TASK_RCU_TREE_PREEMPT() macro. This commit therefore removes it in favor of initializing the ->rcu_blocked_node field directly in the INIT_TASK_RCU_PREEMPT() macro. Signed-off-by: Paul E. McKenney --- include/linux/init_task.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index a2f6707e9fc0..0e849715e5be 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -125,18 +125,12 @@ extern struct group_info init_groups; #define INIT_IDS #endif -#ifdef CONFIG_PREEMPT_RCU -#define INIT_TASK_RCU_TREE_PREEMPT() \ - .rcu_blocked_node = NULL, -#else -#define INIT_TASK_RCU_TREE_PREEMPT(tsk) -#endif #ifdef CONFIG_PREEMPT_RCU #define INIT_TASK_RCU_PREEMPT(tsk) \ .rcu_read_lock_nesting = 0, \ .rcu_read_unlock_special.s = 0, \ .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), \ - INIT_TASK_RCU_TREE_PREEMPT() + .rcu_blocked_node = NULL, #else #define INIT_TASK_RCU_PREEMPT(tsk) #endif -- cgit v1.2.3 From 825c5bd2fd47d30148db15fc121216c483682b01 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 26 May 2017 16:16:40 -0700 Subject: srcu: Move rcu_scheduler_starting() from Tiny RCU to Tiny SRCU Other than lockdep support, Tiny RCU has no need for the scheduler status. However, Tiny SRCU will need this to control boot-time behavior independent of lockdep. Therefore, this commit moves rcu_scheduler_starting() from kernel/rcu/tiny_plugin.h to kernel/rcu/srcutiny.c. This in turn allows the complete removal of kernel/rcu/tiny_plugin.h. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 1 + include/linux/rcutiny.h | 8 +++----- 2 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f816fc72b51e..55c29e1650b9 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -105,6 +105,7 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); +extern int rcu_scheduler_active __read_mostly; void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 5becbbccb998..b3dbf9502fd0 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -116,13 +116,11 @@ static inline void rcu_irq_exit_irqson(void) { } static inline void rcu_irq_enter_irqson(void) { } static inline void rcu_irq_exit(void) { } static inline void exit_rcu(void) { } - -#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) -extern int rcu_scheduler_active __read_mostly; +#ifdef CONFIG_SRCU void rcu_scheduler_starting(void); -#else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ +#else /* #ifndef CONFIG_SRCU */ static inline void rcu_scheduler_starting(void) { } -#endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */ +#endif /* #else #ifndef CONFIG_SRCU */ static inline void rcu_end_inkernel_boot(void) { } static inline bool rcu_is_watching(void) { return true; } -- cgit v1.2.3 From 0d8a1e831e21d955af68f4ae5658b58b7ec25557 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 15 Jun 2017 17:06:38 -0700 Subject: srcu: Make process_srcu() be static The function process_srcu() is not invoked outside of srcutree.c, so this commit makes it static and drops the EXPORT_SYMBOL_GPL(). Signed-off-by: Paul E. McKenney --- include/linux/srcutree.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 42973f787e7e..a026a9493bde 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -104,8 +104,6 @@ struct srcu_struct { #define SRCU_STATE_SCAN1 1 #define SRCU_STATE_SCAN2 2 -void process_srcu(struct work_struct *work); - #define __SRCU_STRUCT_INIT(name) \ { \ .sda = &name##_srcu_data, \ -- cgit v1.2.3 From 115a1a5285664f1931c30457081b4ae1e648f1f9 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 22 May 2017 13:31:03 -0700 Subject: rcutorture: Move SRCU status printing to SRCU implementations This commit gets rid of some ugly #ifdefs in rcutorture.c by moving the SRCU status printing to the SRCU implementations. Signed-off-by: Paul E. McKenney --- include/linux/srcutiny.h | 13 +++++++++++++ include/linux/srcutree.h | 1 + 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index cfbfc540cafc..261471f407a5 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -87,4 +87,17 @@ static inline void srcu_barrier(struct srcu_struct *sp) synchronize_srcu(sp); } +/* Defined here to avoid size increase for non-torture kernels. */ +static inline void srcu_torture_stats_print(struct srcu_struct *sp, + char *tt, char *tf) +{ + int idx; + + idx = READ_ONCE(sp->srcu_idx) & 0x1; + pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n", + tt, tf, idx, + READ_ONCE(sp->srcu_lock_nesting[!idx]), + READ_ONCE(sp->srcu_lock_nesting[idx])); +} + #endif diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index 42973f787e7e..7886356bdc84 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -141,5 +141,6 @@ void process_srcu(struct work_struct *work); void synchronize_srcu_expedited(struct srcu_struct *sp); void srcu_barrier(struct srcu_struct *sp); +void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf); #endif -- cgit v1.2.3 From aa5d1b81500e6059190f18fe25a7617682321910 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 24 Jul 2017 11:35:48 -0700 Subject: x86/asm: Add ASM_UNREACHABLE This creates an unreachable annotation in asm for CONFIG_STACK_VALIDATION=y. While here, adjust earlier uses of \t\n into \n\t. Suggested-by: Josh Poimboeuf Signed-off-by: Kees Cook Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: David S. Miller Cc: Davidlohr Bueso Cc: Elena Reshetova Cc: Eric Biggers Cc: Eric W. Biederman Cc: Greg KH Cc: Hans Liljestrand Cc: James Bottomley Cc: Jann Horn Cc: Linus Torvalds Cc: Manfred Spraul Cc: Peter Zijlstra Cc: Rik van Riel Cc: Serge E. Hallyn Cc: Thomas Gleixner Cc: arozansk@redhat.com Cc: axboe@kernel.dk Cc: kernel-hardening@lists.openwall.com Cc: linux-arch Link: http://lkml.kernel.org/r/1500921349-10803-3-git-send-email-keescook@chromium.org Signed-off-by: Ingo Molnar --- include/linux/compiler-gcc.h | 13 +++++++++---- include/linux/compiler.h | 3 +++ 2 files changed, 12 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cd4bbe8242bd..179375b2d862 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -203,11 +203,16 @@ #ifdef CONFIG_STACK_VALIDATION #define annotate_unreachable() ({ \ - asm("%c0:\t\n" \ - ".pushsection .discard.unreachable\t\n" \ - ".long %c0b - .\t\n" \ - ".popsection\t\n" : : "i" (__LINE__)); \ + asm("%c0:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__LINE__)); \ }) +#define ASM_UNREACHABLE \ + "999:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" #else #define annotate_unreachable() #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 219f82f3ec1a..641f5912d75f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -185,6 +185,9 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* Unreachable code */ +#ifndef ASM_UNREACHABLE +# define ASM_UNREACHABLE +#endif #ifndef unreachable # define unreachable() do { } while (1) #endif -- cgit v1.2.3 From 885dcd709ba9120b9935415b8b0f9d1b94e5826b Mon Sep 17 00:00:00 2001 From: Anju T Sudhakar Date: Wed, 19 Jul 2017 03:06:34 +0530 Subject: powerpc/perf: Add nest IMC PMU support Add support to register Nest In-Memory Collection PMU counters. Patch adds a new device file called "imc-pmu.c" under powerpc/perf folder to contain all the device PMU functions. Device tree parser code added to parse the PMU events information and create sysfs event attributes for the PMU. Cpumask attribute added along with Cpu hotplug online/offline functions specific for nest PMU. A new state "CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE" added for the cpu hotplug callbacks. Error handle path frees the memory and unregisters the CPU hotplug callbacks. Signed-off-by: Anju T Sudhakar Signed-off-by: Hemant Kumar Signed-off-by: Madhavan Srinivasan Signed-off-by: Michael Ellerman --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index b56573bf440d..0853a14b1fa1 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -139,6 +139,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, + CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, -- cgit v1.2.3 From 39a846db1d574a498511ffccd75223a35cdcb059 Mon Sep 17 00:00:00 2001 From: Anju T Sudhakar Date: Wed, 19 Jul 2017 03:06:35 +0530 Subject: powerpc/perf: Add core IMC PMU support Add support to register Core In-Memory Collection PMU counters. Patch adds core IMC specific data structures, along with memory init functions and CPU hotplug support. Signed-off-by: Anju T Sudhakar Signed-off-by: Hemant Kumar Signed-off-by: Madhavan Srinivasan Signed-off-by: Michael Ellerman --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 0853a14b1fa1..1be505db0090 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -140,6 +140,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, + CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, -- cgit v1.2.3 From f74c89bd80fb3f1328fdf4a44eeba793cdce4222 Mon Sep 17 00:00:00 2001 From: Anju T Sudhakar Date: Wed, 19 Jul 2017 03:06:36 +0530 Subject: powerpc/perf: Add thread IMC PMU support Add support to register Thread In-Memory Collection PMU counters. Patch adds thread IMC specific data structures, along with memory init functions and CPU hotplug support. Signed-off-by: Anju T Sudhakar Signed-off-by: Hemant Kumar Signed-off-by: Madhavan Srinivasan Signed-off-by: Michael Ellerman --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 1be505db0090..1bc7dcfbf7b3 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -141,6 +141,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE, CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE, + CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, -- cgit v1.2.3 From 67bd22c09ac1b54b5f42445783d2dc8e011f7a71 Mon Sep 17 00:00:00 2001 From: "Andrew F. Davis" Date: Wed, 19 Jul 2017 12:04:07 -0500 Subject: power: supply: bq27xxx: move platform driver code into bq27xxx_battery_hdq.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the BQ27xxx driver was originally written the w1 subsystem only allowed device drivers for w1 attached devices to live in the w1 subsystem. Kernel driver subsystems expect that the driver for a device live in the directory of the subsystem for which it implements functionality, not in the directory of the bus that it is attached. To work around this, the BQ27xxx driver was implemented as a platform device driver and the interface driver would instantiate this device from within the w1 directory, then pass a w1 read callback as platform data. As we can now have the w1 interface driver in the power/supply directory (like we do already with the i2c interface driver) we can remove this middle-layer platform driver. Signed-off-by: Andrew F. Davis Acked-by: Pali Rohár Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 11e11685dd1d..89890437f9ab 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -20,23 +20,6 @@ enum bq27xxx_chip { BQ27421, /* bq27421, bq27425, bq27441, bq27621 */ }; -/** - * struct bq27xxx_plaform_data - Platform data for bq27xxx devices - * @name: Name of the battery. - * @chip: Chip class number of this device. - * @read: HDQ read callback. - * This function should provide access to the HDQ bus the battery is - * connected to. - * The first parameter is a pointer to the battery device, the second the - * register to be read. The return value should either be the content of - * the passed register or an error value. - */ -struct bq27xxx_platform_data { - const char *name; - enum bq27xxx_chip chip; - int (*read)(struct device *dev, unsigned int); -}; - struct bq27xxx_device_info; struct bq27xxx_access_methods { int (*read)(struct bq27xxx_device_info *di, u8 reg, bool single); -- cgit v1.2.3 From 1ee6f00d1164955b7bdadd36fc0f2736754784d9 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 25 Jul 2017 09:44:51 -0500 Subject: x86/asm: Make objtool unreachable macros independent from GCC version The ASM_UNREACHABLE macro isn't GCC version-specific, so move it outside the GCC 4.5+ check. Otherwise the 0-day robot will report objtool warnings for uses of ASM_UNREACHABLE with GCC 4.4. Also move the annotate_unreachable() macro so the related macros can stay together. Reported-by: kbuild test robot Signed-off-by: Josh Poimboeuf Cc: Kees Cook Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: aa5d1b81500e ("x86/asm: Add ASM_UNREACHABLE") Link: http://lkml.kernel.org/r/fb18337dbf230fd36450d9faf19a2b2533dbcba1.1500993873.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- include/linux/compiler-gcc.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 179375b2d862..17cbe3cffc0e 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -128,6 +128,22 @@ #define __always_unused __attribute__((unused)) #define __mode(x) __attribute__((mode(x))) +#ifdef CONFIG_STACK_VALIDATION +#define annotate_unreachable() ({ \ + asm("%c0:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__LINE__)); \ +}) +#define ASM_UNREACHABLE \ + "999:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" +#else +#define annotate_unreachable() +#endif + /* gcc version specific checks */ #if GCC_VERSION < 30200 @@ -201,22 +217,6 @@ #endif #endif -#ifdef CONFIG_STACK_VALIDATION -#define annotate_unreachable() ({ \ - asm("%c0:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__LINE__)); \ -}) -#define ASM_UNREACHABLE \ - "999:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long 999b - .\n\t" \ - ".popsection\n\t" -#else -#define annotate_unreachable() -#endif - /* * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer -- cgit v1.2.3 From 931ab4a5ce2d93cb434dc7fc067a702117453b13 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 25 Jul 2017 09:59:08 -0700 Subject: atomics: Revert addition of comment header to spin_unlock_wait() There is still considerable confusion as to the semantics of spin_unlock_wait(), but there seems to be universal agreement that it is not that of a lock/unlock pair. This commit therefore removes the comment added by 6016ffc3874d ("atomics: Add header comment so spin_unlock_wait()") in order to prevent at least that flavor of confusion. Signed-off-by: Paul E. McKenney --- include/linux/spinlock.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index d9510e8522d4..59248dcc6ef3 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -369,26 +369,6 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock) raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) -/** - * spin_unlock_wait - Interpose between successive critical sections - * @lock: the spinlock whose critical sections are to be interposed. - * - * Semantically this is equivalent to a spin_lock() immediately - * followed by a spin_unlock(). However, most architectures have - * more efficient implementations in which the spin_unlock_wait() - * cannot block concurrent lock acquisition, and in some cases - * where spin_unlock_wait() does not write to the lock variable. - * Nevertheless, spin_unlock_wait() can have high overhead, so if - * you feel the need to use it, please check to see if there is - * a better way to get your job done. - * - * The ordering guarantees provided by spin_unlock_wait() are: - * - * 1. All accesses preceding the spin_unlock_wait() happen before - * any accesses in later critical sections for this same lock. - * 2. All accesses following the spin_unlock_wait() happen after - * any accesses in earlier critical sections for this same lock. - */ static __always_inline void spin_unlock_wait(spinlock_t *lock) { raw_spin_unlock_wait(&lock->rlock); -- cgit v1.2.3 From a58163d8ca2c8d288ee9f95989712f98473a5ac2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 20 Jun 2017 12:11:34 -0700 Subject: rcu: Migrate callbacks earlier in the CPU-offline timeline RCU callbacks must be migrated away from an outgoing CPU, and this is done near the end of the CPU-hotplug operation, after the outgoing CPU is long gone. Unfortunately, this means that other CPU-hotplug callbacks can execute while the outgoing CPU's callbacks are still immobilized on the long-gone CPU's callback lists. If any of these CPU-hotplug callbacks must wait, either directly or indirectly, for the invocation of any of the immobilized RCU callbacks, the system will hang. This commit avoids such hangs by migrating the callbacks away from the outgoing CPU immediately upon its departure, shortly after the return from __cpu_die() in takedown_cpu(). Thus, RCU is able to advance these callbacks and invoke them, which allows all the after-the-fact CPU-hotplug callbacks to wait on these RCU callbacks without risk of a hang. While in the neighborhood, this commit also moves rcu_send_cbs_to_orphanage() and rcu_adopt_orphan_cbs() under a pre-existing #ifdef to avoid including dead code on the one hand and to avoid define-without-use warnings on the other hand. Reported-by: Jeffrey Hugo Link: http://lkml.kernel.org/r/db9c91f6-1b17-6136-84f0-03c3c2581ab4@codeaurora.org Signed-off-by: Paul E. McKenney Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Cc: Ingo Molnar Cc: Anna-Maria Gleixner Cc: Boris Ostrovsky Cc: Richard Weinberger --- include/linux/rcupdate.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f816fc72b51e..cf307ebf345d 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -110,6 +110,7 @@ void rcu_bh_qs(void); void rcu_check_callbacks(int user); void rcu_report_dead(unsigned int cpu); void rcu_cpu_starting(unsigned int cpu); +void rcutree_migrate_callbacks(int cpu); #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); -- cgit v1.2.3 From ed4676e254630c1f00a4fc8f3821890fff7e3643 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 19 Jul 2017 15:42:46 +0530 Subject: cpufreq: Replace "max_transition_latency" with "dynamic_switching" There is no limitation in the ondemand or conservative governors which disallow the transition_latency to be greater than 10 ms. The max_transition_latency field is rather used to disallow automatic dynamic frequency switching for platforms which didn't wanted these governors to run. Replace max_transition_latency with a boolean (dynamic_switching) and check for transition_latency == CPUFREQ_ETERNAL along with that. This makes it pretty straight forward to read/understand now. Signed-off-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index aaadfc543f63..e141dbbb9d1c 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -487,12 +487,8 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div, * polling frequency is 1000 times the transition latency of the processor. The * ondemand governor will work on any processor with transition latency <= 10ms, * using appropriate sampling rate. - * - * For CPUs with transition latency > 10ms (mostly drivers with CPUFREQ_ETERNAL) - * the ondemand governor will not work. All times here are in us (microseconds). */ #define LATENCY_MULTIPLIER (1000) -#define TRANSITION_LATENCY_LIMIT (10 * 1000 * 1000) struct cpufreq_governor { char name[CPUFREQ_NAME_LEN]; @@ -505,9 +501,8 @@ struct cpufreq_governor { char *buf); int (*store_setspeed) (struct cpufreq_policy *policy, unsigned int freq); - unsigned int max_transition_latency; /* HW must be able to switch to - next freq faster than this value in nano secs or we - will fallback to performance governor */ + /* For governors which change frequency dynamically by themselves */ + bool dynamic_switching; struct list_head governor_list; struct module *owner; }; -- cgit v1.2.3 From fe829ed8ef1f3c7ac22843bd594ef2f6c4044288 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 19 Jul 2017 15:42:48 +0530 Subject: cpufreq: Add CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING cpufreq driver flag The policy->transition_latency field is used for multiple purposes today and its not straight forward at all. This is how it is used: A. Set the correct transition_latency value. B. Set it to CPUFREQ_ETERNAL because: 1. We don't want automatic dynamic switching (with ondemand/conservative) to happen at all. 2. We don't know the transition latency. This patch handles the B.1. case in a more readable way. A new flag for the cpufreq drivers is added to disallow use of cpufreq governors which have dynamic_switching flag set. All the current cpufreq drivers which are setting transition_latency unconditionally to CPUFREQ_ETERNAL are updated to use it. They don't need to set transition_latency anymore. There shouldn't be any functional change after this patch. Signed-off-by: Viresh Kumar Reviewed-by: Dominik Brodowski Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index e141dbbb9d1c..5f40522ec98c 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -370,6 +370,12 @@ struct cpufreq_driver { */ #define CPUFREQ_NEED_INITIAL_FREQ_CHECK (1 << 5) +/* + * Set by drivers to disallow use of governors with "dynamic_switching" flag + * set. + */ +#define CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING (1 << 6) + int cpufreq_register_driver(struct cpufreq_driver *driver_data); int cpufreq_unregister_driver(struct cpufreq_driver *driver_data); -- cgit v1.2.3 From ebae3e830a991116526646f09dd67f68f332b330 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 5 Jul 2017 20:27:53 +0300 Subject: iommu: Correct iommu_map / iommu_unmap prototypes Commit 7d3002cc8c16 ("iommu/core: split mapping to page sizes as supported by the hardware") replaced 'int gfp_order' with a 'size_t size' of iommu_map / iommu_unmap function arguments, but missed the function prototypes for the disabled CONFIG_IOMMU_API case, let's correct them for consistency. Signed-off-by: Dmitry Osipenko Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2cb54adc4a33..f1ce8e517d8d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -425,13 +425,13 @@ static inline struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) } static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, int gfp_order, int prot) + phys_addr_t paddr, size_t size, int prot) { return -ENODEV; } static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova, - int gfp_order) + size_t size) { return -ENODEV; } -- cgit v1.2.3 From f06e8c584fa0d05312c11ea66194f3d2efb93c21 Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Thu, 22 Jun 2017 16:14:17 +0200 Subject: kasan: Allow kasan_check_read/write() to accept pointers to volatiles Currently kasan_check_read/write() accept 'const void*', make them accept 'const volatile void*'. This is required for instrumentation of atomic operations and there is just no reason to not allow that. Signed-off-by: Dmitry Vyukov Reviewed-by: Andrey Ryabinin Acked-by: Mark Rutland Cc: Andrew Morton Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kasan-dev@googlegroups.com Cc: linux-mm@kvack.org Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/33e5ec275c1ee89299245b2ebbccd63709c6021f.1498140838.git.dvyukov@google.com Signed-off-by: Ingo Molnar --- include/linux/kasan-checks.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h index b7f8aced7870..41960fecf783 100644 --- a/include/linux/kasan-checks.h +++ b/include/linux/kasan-checks.h @@ -2,11 +2,13 @@ #define _LINUX_KASAN_CHECKS_H #ifdef CONFIG_KASAN -void kasan_check_read(const void *p, unsigned int size); -void kasan_check_write(const void *p, unsigned int size); +void kasan_check_read(const volatile void *p, unsigned int size); +void kasan_check_write(const volatile void *p, unsigned int size); #else -static inline void kasan_check_read(const void *p, unsigned int size) { } -static inline void kasan_check_write(const void *p, unsigned int size) { } +static inline void kasan_check_read(const volatile void *p, unsigned int size) +{ } +static inline void kasan_check_write(const volatile void *p, unsigned int size) +{ } #endif #endif -- cgit v1.2.3 From d2f3c3849461baefdbb39123abde1054d46bf22e Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Mon, 24 Jul 2017 19:02:09 -0400 Subject: percpu: increase minimum percpu allocation size and align first regions This patch increases the minimum allocation size of percpu memory to 4-bytes. This change will help minimize the metadata overhead associated with the bitmap allocator. The assumption is that most allocations will be of objects or structs greater than 2 bytes with integers or longs being used rather than shorts. The first chunk regions are now aligned with the minimum allocation size. The reserved region is expected to be set as a multiple of the minimum allocation size. The static region is aligned up and the delta is removed from the dynamic size. This works because the dynamic size is increased to be page aligned. If the static size is not minimum allocation size aligned, then there must be a gap that is added to the dynamic size. The dynamic size will never be smaller than the set value. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Signed-off-by: Tejun Heo --- include/linux/percpu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 491b3f5a5f8a..90e0cb0f7802 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -21,6 +21,10 @@ /* minimum unit size, also is the maximum supported allocation size */ #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) +/* minimum allocation size and shift in bytes */ +#define PCPU_MIN_ALLOC_SHIFT 2 +#define PCPU_MIN_ALLOC_SIZE (1 << PCPU_MIN_ALLOC_SHIFT) + /* * Percpu allocator can serve percpu allocations before slab is * initialized which allows slab to depend on the percpu allocator. -- cgit v1.2.3 From 3acdfd280fe7d807237f2cb7a09d6f8f7f1b484f Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 24 Jul 2017 06:22:15 -0400 Subject: errseq: rename __errseq_set to errseq_set Nothing calls this wrapper anymore, so just remove it and rename the old function to get rid of the double underscore prefix. Signed-off-by: Jeff Layton --- include/linux/errseq.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/errseq.h b/include/linux/errseq.h index 9e0d444ac88d..784f0860527b 100644 --- a/include/linux/errseq.h +++ b/include/linux/errseq.h @@ -5,14 +5,7 @@ typedef u32 errseq_t; -errseq_t __errseq_set(errseq_t *eseq, int err); -static inline void errseq_set(errseq_t *eseq, int err) -{ - /* Optimize for the common case of no error */ - if (unlikely(err)) - __errseq_set(eseq, err); -} - +errseq_t errseq_set(errseq_t *eseq, int err); errseq_t errseq_sample(errseq_t *eseq); int errseq_check(errseq_t *eseq, errseq_t since); int errseq_check_and_advance(errseq_t *eseq, errseq_t *since); -- cgit v1.2.3 From 40064aeca35c5c14789e2adcf3a1d7e5d4bd65f2 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Wed, 12 Jul 2017 11:27:32 -0700 Subject: percpu: replace area map allocator with bitmap The percpu memory allocator is experiencing scalability issues when allocating and freeing large numbers of counters as in BPF. Additionally, there is a corner case where iteration is triggered over all chunks if the contig_hint is the right size, but wrong alignment. This patch replaces the area map allocator with a basic bitmap allocator implementation. Each subsequent patch will introduce new features and replace full scanning functions with faster non-scanning options when possible. Implementation: This patchset removes the area map allocator in favor of a bitmap allocator backed by metadata blocks. The primary goal is to provide consistency in performance and memory footprint with a focus on small allocations (< 64 bytes). The bitmap removes the heavy memmove from the freeing critical path and provides a consistent memory footprint. The metadata blocks provide a bound on the amount of scanning required by maintaining a set of hints. In an effort to make freeing fast, the metadata is updated on the free path if the new free area makes a page free, a block free, or spans across blocks. This causes the chunk's contig hint to potentially be smaller than what it could allocate by up to the smaller of a page or a block. If the chunk's contig hint is contained within a block, a check occurs and the hint is kept accurate. Metadata is always kept accurate on allocation, so there will not be a situation where a chunk has a later contig hint than available. Evaluation: I have primarily done testing against a simple workload of allocation of 1 million objects (2^20) of varying size. Deallocation was done by in order, alternating, and in reverse. These numbers were collected after rebasing ontop of a80099a152. I present the worst-case numbers here: Area Map Allocator: Object Size | Alloc Time (ms) | Free Time (ms) ---------------------------------------------- 4B | 310 | 4770 16B | 557 | 1325 64B | 436 | 273 256B | 776 | 131 1024B | 3280 | 122 Bitmap Allocator: Object Size | Alloc Time (ms) | Free Time (ms) ---------------------------------------------- 4B | 490 | 70 16B | 515 | 75 64B | 610 | 80 256B | 950 | 100 1024B | 3520 | 200 This data demonstrates the inability for the area map allocator to handle less than ideal situations. In the best case of reverse deallocation, the area map allocator was able to perform within range of the bitmap allocator. In the worst case situation, freeing took nearly 5 seconds for 1 million 4-byte objects. The bitmap allocator dramatically improves the consistency of the free path. The small allocations performed nearly identical regardless of the freeing pattern. While it does add to the allocation latency, the allocation scenario here is optimal for the area map allocator. The area map allocator runs into trouble when it is allocating in chunks where the latter half is full. It is difficult to replicate this, so I present a variant where the pages are second half filled. Freeing was done sequentially. Below are the numbers for this scenario: Area Map Allocator: Object Size | Alloc Time (ms) | Free Time (ms) ---------------------------------------------- 4B | 4118 | 4892 16B | 1651 | 1163 64B | 598 | 285 256B | 771 | 158 1024B | 3034 | 160 Bitmap Allocator: Object Size | Alloc Time (ms) | Free Time (ms) ---------------------------------------------- 4B | 481 | 67 16B | 506 | 69 64B | 636 | 75 256B | 892 | 90 1024B | 3262 | 147 The data shows a parabolic curve of performance for the area map allocator. This is due to the memmove operation being the dominant cost with the lower object sizes as more objects are packed in a chunk and at higher object sizes, the traversal of the chunk slots is the dominating cost. The bitmap allocator suffers this problem as well. The above data shows the inability to scale for the allocation path with the area map allocator and that the bitmap allocator demonstrates consistent performance in general. The second problem of additional scanning can result in the area map allocator completing in 52 minutes when trying to allocate 1 million 4-byte objects with 8-byte alignment. The same workload takes approximately 16 seconds to complete for the bitmap allocator. V2: Fixed a bug in pcpu_alloc_first_chunk end_offset was setting the bitmap using bytes instead of bits. Added a comment to pcpu_cnt_pop_pages to explain bitmap_weight. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Signed-off-by: Tejun Heo --- include/linux/percpu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 90e0cb0f7802..b7e6c98722d1 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -120,7 +120,6 @@ extern bool is_kernel_percpu_address(unsigned long addr); #if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA) extern void __init setup_per_cpu_areas(void); #endif -extern void __init percpu_init_late(void); extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp); extern void __percpu *__alloc_percpu(size_t size, size_t align); -- cgit v1.2.3 From ca460b3c96274d79f84b31a3fea23a6eed479917 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Mon, 24 Jul 2017 19:02:12 -0400 Subject: percpu: introduce bitmap metadata blocks This patch introduces the bitmap metadata blocks and adds the skeleton of the code that will be used to maintain these blocks. Each chunk's bitmap is made up of full metadata blocks. These blocks maintain basic metadata to help prevent scanning unnecssarily to update hints. Full scanning methods are used for the skeleton and will be replaced in the coming patches. A number of helper functions are added as well to do conversion of pages to blocks and manage offsets. Comments will be updated as the final version of each function is added. There exists a relationship between PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE, the region size, and unit_size. Every chunk's region (including offsets) is page aligned at the beginning to preserve alignment. The end is aligned to LCM(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE) to ensure that the end can fit with the populated page map which is by page and every metadata block is fully accounted for. The unit_size is already page aligned, but must also be aligned with PCPU_BITMAP_BLOCK_SIZE to ensure full metadata blocks. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Signed-off-by: Tejun Heo --- include/linux/percpu.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index b7e6c98722d1..31795e619273 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -25,6 +25,18 @@ #define PCPU_MIN_ALLOC_SHIFT 2 #define PCPU_MIN_ALLOC_SIZE (1 << PCPU_MIN_ALLOC_SHIFT) +/* + * This determines the size of each metadata block. There are several subtle + * constraints around this constant. The reserved region must be a multiple of + * PCPU_BITMAP_BLOCK_SIZE. Additionally, PCPU_BITMAP_BLOCK_SIZE must be a + * multiple of PAGE_SIZE or PAGE_SIZE must be a multiple of + * PCPU_BITMAP_BLOCK_SIZE to align with the populated page map. The unit_size + * also has to be a multiple of PCPU_BITMAP_BLOCK_SIZE to ensure full blocks. + */ +#define PCPU_BITMAP_BLOCK_SIZE PAGE_SIZE +#define PCPU_BITMAP_BLOCK_BITS (PCPU_BITMAP_BLOCK_SIZE >> \ + PCPU_MIN_ALLOC_SHIFT) + /* * Percpu allocator can serve percpu allocations before slab is * initialized which allows slab to depend on the percpu allocator. -- cgit v1.2.3 From b185cd0dc61c14875155e7bcc3f2c139b6feefd2 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Mon, 24 Jul 2017 19:02:17 -0400 Subject: percpu: update free path to take advantage of contig hints The bitmap allocator must keep metadata consistent. The easiest way is to scan after every allocation for each affected block and the entire chunk. This is rather expensive. The free path can take advantage of current contig hints to prevent scanning within the start and end block. If a scan is needed, it can be done by scanning backwards from the start and forwards from the end to identify the entire free area this can be combined with. The blocks can then be updated by some basic checks rather than complete block scans. A chunk scan happens when the freed area makes a page free, a block free, or spans across blocks. This is necessary as the contig hint at this point could span across blocks. The check uses the minimum of page size and the block size to allow for variable sized blocks. There is a tradeoff here with not updating after every free. It is possible a contig hint in one block can be merged with the contig hint in the next block. This means the contig hint can be off by up to a page. However, if the chunk's contig hint is contained in one block, the contig hint will be accurate. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Signed-off-by: Tejun Heo --- include/linux/percpu.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 31795e619273..6a5fb939d3e5 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -25,6 +25,9 @@ #define PCPU_MIN_ALLOC_SHIFT 2 #define PCPU_MIN_ALLOC_SIZE (1 << PCPU_MIN_ALLOC_SHIFT) +/* number of bits per page, used to trigger a scan if blocks are > PAGE_SIZE */ +#define PCPU_BITS_PER_PAGE (PAGE_SIZE >> PCPU_MIN_ALLOC_SHIFT) + /* * This determines the size of each metadata block. There are several subtle * constraints around this constant. The reserved region must be a multiple of -- cgit v1.2.3 From 645874e5807ae5ffa09fba2ccd23f01e4eb16d58 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Wed, 26 Jul 2017 06:07:11 -0700 Subject: qed: Add support for Energy efficient ethernet. The patch adds required driver support for reading/configuring the Energy Efficient Ethernet (EEE) parameters. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index ef39c7f40ae6..9f3276271b02 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -161,6 +161,18 @@ enum qed_nvm_images { QED_NVM_IMAGE_FCOE_CFG, }; +struct qed_link_eee_params { + u32 tx_lpi_timer; +#define QED_EEE_1G_ADV BIT(0) +#define QED_EEE_10G_ADV BIT(1) + + /* Capabilities are represented using QED_EEE_*_ADV values */ + u8 adv_caps; + u8 lp_adv_caps; + bool enable; + bool tx_lpi_enable; +}; + enum qed_led_mode { QED_LED_MODE_OFF, QED_LED_MODE_ON, @@ -408,6 +420,7 @@ struct qed_link_params { #define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) #define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) #define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) +#define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) u32 override_flags; bool autoneg; u32 adv_speeds; @@ -422,6 +435,7 @@ struct qed_link_params { #define QED_LINK_LOOPBACK_EXT BIT(3) #define QED_LINK_LOOPBACK_MAC BIT(4) u32 loopback_mode; + struct qed_link_eee_params eee; }; struct qed_link_output { @@ -437,6 +451,12 @@ struct qed_link_output { u8 port; /* In PORT defs */ bool autoneg; u32 pause_config; + + /* EEE - capability & param */ + bool eee_supported; + bool eee_active; + u8 sup_caps; + struct qed_link_eee_params eee; }; struct qed_probe_params { -- cgit v1.2.3 From 477f2d1460a636abd08f03eafabe0c51366fa5de Mon Sep 17 00:00:00 2001 From: Rahul Verma Date: Wed, 26 Jul 2017 06:07:13 -0700 Subject: qed: Add support for vf coalesce configuration. This patch add the ethtool support to set RX/Tx coalesce value to the VF associated Rx/Tx queues. Signed-off-by: Rahul Verma Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 9f3276271b02..4d59ca16134c 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -694,8 +694,8 @@ struct qed_common_ops { * * @return 0 on success, error otherwise. */ - int (*set_coalesce)(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, - u16 qid, u16 sb_id); + int (*set_coalesce)(struct qed_dev *cdev, + u16 rx_coal, u16 tx_coal, void *handle); /** * @brief set_led - Configure LED mode -- cgit v1.2.3 From bf5a94bfe26a9fcd4af91ae6bccd4f3d600d2262 Mon Sep 17 00:00:00 2001 From: Rahul Verma Date: Wed, 26 Jul 2017 06:07:14 -0700 Subject: qed: Read per queue coalesce from hardware Retrieve the actual coalesce value from hardware for every Rx/Tx queue, instead of Rx/Tx coalesce value cached during set coalesce. Signed-off-by: Rahul Verma Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_eth_if.h | 1 + include/linux/qed/qed_if.h | 11 +---------- 2 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 0eef0a2b1901..d60de4a39810 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -323,6 +323,7 @@ struct qed_eth_ops { int (*configure_arfs_searcher)(struct qed_dev *cdev, bool en_searcher); + int (*get_coalesce)(struct qed_dev *cdev, u16 *coal, void *handle); }; const struct qed_eth_ops *qed_get_eth_ops(void); diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 4d59ca16134c..2b4720bb8b40 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -186,6 +186,7 @@ enum qed_led_mode { #define QED_COALESCE_MAX 0xFF #define QED_DEFAULT_RX_USECS 12 +#define QED_DEFAULT_TX_USECS 48 /* forward */ struct qed_dev; @@ -673,16 +674,6 @@ struct qed_common_ops { int (*nvm_get_image)(struct qed_dev *cdev, enum qed_nvm_images type, u8 *buf, u16 len); -/** - * @brief get_coalesce - Get coalesce parameters in usec - * - * @param cdev - * @param rx_coal - Rx coalesce value in usec - * @param tx_coal - Tx coalesce value in usec - * - */ - void (*get_coalesce)(struct qed_dev *cdev, u16 *rx_coal, u16 *tx_coal); - /** * @brief set_coalesce - Configure Rx coalesce value in usec * -- cgit v1.2.3 From 41822878b2ff40a1f57be81f1a1f0f040847b912 Mon Sep 17 00:00:00 2001 From: Rahul Verma Date: Wed, 26 Jul 2017 06:07:15 -0700 Subject: qed: enhanced per queue max coalesce value. Maximum coalesce per Rx/Tx queue is extended from 255 to 511. Signed-off-by: Rahul Verma Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 2b4720bb8b40..cc646ca97974 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -184,7 +184,7 @@ enum qed_led_mode { #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr)) -#define QED_COALESCE_MAX 0xFF +#define QED_COALESCE_MAX 0x1FF #define QED_DEFAULT_RX_USECS 12 #define QED_DEFAULT_TX_USECS 48 -- cgit v1.2.3 From fc2237a724a9e448599076d7d23497f51e2f7441 Mon Sep 17 00:00:00 2001 From: Jason Gerecke Date: Mon, 24 Jul 2017 09:46:18 -0700 Subject: HID: introduce hid_is_using_ll_driver Although HID itself is transport-agnostic, occasionally a driver may want to interact with the low-level transport that a device is connected through. To do this, we need to know what kind of bus is in use. The first guess may be to look at the 'bus' field of the 'struct hid_device', but this field may be emulated in some cases (e.g. uhid). More ideally, we can check which ll_driver a device is using. This function introduces a 'hid_is_using_ll_driver' function and makes the 'struct hid_ll_driver' of the four most common transports accessible through hid.h. Signed-off-by: Jason Gerecke Acked-By: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 5006f9b5d837..3853408daf7f 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -777,6 +777,17 @@ struct hid_ll_driver { int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); }; +extern struct hid_ll_driver i2c_hid_ll_driver; +extern struct hid_ll_driver hidp_hid_driver; +extern struct hid_ll_driver uhid_hid_driver; +extern struct hid_ll_driver usb_hid_driver; + +static inline bool hid_is_using_ll_driver(struct hid_device *hdev, + struct hid_ll_driver *driver) +{ + return hdev->ll_driver == driver; +} + #define PM_HINT_FULLON 1<<5 #define PM_HINT_NORMAL 1<<1 -- cgit v1.2.3 From 649ea4d5a624f061a111b1f1cb0e47cfdc3ac21b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 27 Jul 2017 15:56:53 -0500 Subject: objtool: Assume unannotated UD2 instructions are dead ends Arnd reported some false positive warnings with GCC 7: drivers/hid/wacom_wac.o: warning: objtool: wacom_bpt3_touch()+0x2a5: stack state mismatch: cfa1=7+8 cfa2=6+16 drivers/iio/adc/vf610_adc.o: warning: objtool: vf610_adc_calculate_rates() falls through to next function vf610_adc_sample_set() drivers/pwm/pwm-hibvt.o: warning: objtool: hibvt_pwm_get_state() falls through to next function hibvt_pwm_remove() drivers/pwm/pwm-mediatek.o: warning: objtool: mtk_pwm_config() falls through to next function mtk_pwm_enable() drivers/spi/spi-bcm2835.o: warning: objtool: .text: unexpected end of section drivers/spi/spi-bcm2835aux.o: warning: objtool: .text: unexpected end of section drivers/watchdog/digicolor_wdt.o: warning: objtool: dc_wdt_get_timeleft() falls through to next function dc_wdt_restart() When GCC 7 detects a potential divide-by-zero condition, it sometimes inserts a UD2 instruction for the case where the divisor is zero, instead of letting the hardware trap on the divide instruction. Objtool doesn't consider UD2 to be fatal unless it's annotated with unreachable(). So it considers the GCC-generated UD2 to be non-fatal, and it tries to follow the control flow past the UD2 and gets confused. Previously, objtool *did* assume UD2 was always a dead end. That changed with the following commit: d1091c7fa3d5 ("objtool: Improve detection of BUG() and other dead ends") The motivation behind that change was that Peter was planning on using UD2 for __WARN(), which is *not* a dead end. However, it turns out that some emulators rely on UD2 being fatal, so he ended up using 'ud0' instead: 9a93848fe787 ("x86/debug: Implement __WARN() using UD0") For GCC 4.5+, it should be safe to go back to the previous assumption that UD2 is fatal, even when it's not annotated with unreachable(). But for pre-4.5 versions of GCC, the unreachable() macro isn't supported, so such cases of UD2 need to be explicitly annotated as reachable. Reported-by: Arnd Bergmann Signed-off-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: d1091c7fa3d5 ("objtool: Improve detection of BUG() and other dead ends") Link: http://lkml.kernel.org/r/e57fa9dfede25f79487da8126ee9cdf7b856db65.1501188854.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- include/linux/compiler-gcc.h | 16 ---------------- include/linux/compiler.h | 25 ++++++++++++++++++++++++- 2 files changed, 24 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 17cbe3cffc0e..dd4b4c59c2f0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -128,22 +128,6 @@ #define __always_unused __attribute__((unused)) #define __mode(x) __attribute__((mode(x))) -#ifdef CONFIG_STACK_VALIDATION -#define annotate_unreachable() ({ \ - asm("%c0:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long %c0b - .\n\t" \ - ".popsection\n\t" : : "i" (__LINE__)); \ -}) -#define ASM_UNREACHABLE \ - "999:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long 999b - .\n\t" \ - ".popsection\n\t" -#else -#define annotate_unreachable() -#endif - /* gcc version specific checks */ #if GCC_VERSION < 30200 diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 641f5912d75f..70f070ddd7c7 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -185,11 +185,34 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* Unreachable code */ +#ifdef CONFIG_STACK_VALIDATION +#define annotate_reachable() ({ \ + asm("%c0:\n\t" \ + ".pushsection .discard.reachable\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__LINE__)); \ +}) +#define annotate_unreachable() ({ \ + asm("%c0:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__LINE__)); \ +}) +#define ASM_UNREACHABLE \ + "999:\n\t" \ + ".pushsection .discard.unreachable\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" +#else +#define annotate_reachable() +#define annotate_unreachable() +#endif + #ifndef ASM_UNREACHABLE # define ASM_UNREACHABLE #endif #ifndef unreachable -# define unreachable() do { } while (1) +# define unreachable() do { annotate_reachable(); do { } while (1); } while (0) #endif /* -- cgit v1.2.3 From 80aafd50b6a4fa6b6bba4b451b553d5d221f59ff Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 24 Jul 2017 06:22:16 -0400 Subject: Documentation: add some docs for errseq_t ...and fix up a few comments in the code. Signed-off-by: Jeff Layton --- include/linux/errseq.h | 5 +++-- include/linux/fs.h | 2 -- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/errseq.h b/include/linux/errseq.h index 784f0860527b..f746bd8fe4d0 100644 --- a/include/linux/errseq.h +++ b/include/linux/errseq.h @@ -1,8 +1,9 @@ +/* + * See Documentation/errseq.rst and lib/errseq.c + */ #ifndef _LINUX_ERRSEQ_H #define _LINUX_ERRSEQ_H -/* See lib/errseq.c for more info */ - typedef u32 errseq_t; errseq_t errseq_set(errseq_t *eseq, int err); diff --git a/include/linux/fs.h b/include/linux/fs.h index 7b5d6816542b..21e7df1ad613 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2571,8 +2571,6 @@ extern int __must_check file_write_and_wait_range(struct file *file, * When a writeback error occurs, most filesystems will want to call * filemap_set_wb_err to record the error in the mapping so that it will be * automatically reported whenever fsync is called on the file. - * - * FIXME: mention FS_* flag here? */ static inline void filemap_set_wb_err(struct address_space *mapping, int err) { -- cgit v1.2.3 From 7d35079f8277b653d6a3075eea9edd4dbf7c2b29 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:46 -0700 Subject: kernfs: use idr instead of ida to manage inode number kernfs uses ida to manage inode number. The problem is we can't get kernfs_node from inode number with ida. Switching to use idr, next patch will add an API to get kernfs_node from inode number. Acked-by: Tejun Heo Acked-by: Greg Kroah-Hartman Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/kernfs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index a9b11b8d06f2..5f5d602eb433 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -163,7 +163,7 @@ struct kernfs_root { unsigned int flags; /* KERNFS_ROOT_* flags */ /* private fields, do not use outside kernfs proper */ - struct ida ino_ida; + struct idr ino_idr; struct kernfs_syscall_ops *syscall_ops; /* list of kernfs_super_info of this root, protected by kernfs_mutex */ -- cgit v1.2.3 From 4a3ef68acacf31570066e69593de5cc49cc91638 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:47 -0700 Subject: kernfs: implement i_generation Set i_generation for kernfs inode. This is required to implement exportfs operations. The generation is 32-bit, so it's possible the generation wraps up and we find stale files. To reduce the posssibility, we don't reuse inode numer immediately. When the inode number allocation wraps, we increase generation number. In this way generation/inode number consist of a 64-bit number which is unlikely duplicated. This does make the idr tree more sparse and waste some memory. Since idr manages 32-bit keys, idr uses a 6-level radix tree, each level covers 6 bits of the key. In a 100k inode kernfs, the worst case will have around 300k radix tree node. Each node is 576bytes, so the tree will use about ~150M memory. Sounds not too bad, if this really is a problem, we should find better data structure. Acked-by: Tejun Heo Acked-by: Greg Kroah-Hartman Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/kernfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 5f5d602eb433..8c00d28f468a 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -135,6 +135,7 @@ struct kernfs_node { umode_t mode; unsigned int ino; struct kernfs_iattrs *iattr; + u32 generation; }; /* @@ -164,6 +165,7 @@ struct kernfs_root { /* private fields, do not use outside kernfs proper */ struct idr ino_idr; + u32 next_generation; struct kernfs_syscall_ops *syscall_ops; /* list of kernfs_super_info of this root, protected by kernfs_mutex */ -- cgit v1.2.3 From c53cd490b1a491ebf1d8e30da97e7231459a4208 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:50 -0700 Subject: kernfs: introduce kernfs_node_id inode number and generation can identify a kernfs node. We are going to export the identification by exportfs operations, so put ino and generation into a separate structure. It's convenient when later patches use the identification. Acked-by: Greg Kroah-Hartman Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/cgroup.h | 2 +- include/linux/kernfs.h | 12 ++++++++++-- 2 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 710a005c6b7a..30c68773fd1e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -543,7 +543,7 @@ static inline bool cgroup_is_populated(struct cgroup *cgrp) /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { - return cgrp->kn->ino; + return cgrp->kn->id.ino; } /* cft/css accessors for cftype->write() operation */ diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 8c00d28f468a..06a0c5913e1d 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -95,6 +95,15 @@ struct kernfs_elem_attr { struct kernfs_node *notify_next; /* for kernfs_notify() */ }; +/* represent a kernfs node */ +union kernfs_node_id { + struct { + u32 ino; + u32 generation; + }; + u64 id; +}; + /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are @@ -131,11 +140,10 @@ struct kernfs_node { void *priv; + union kernfs_node_id id; unsigned short flags; umode_t mode; - unsigned int ino; struct kernfs_iattrs *iattr; - u32 generation; }; /* -- cgit v1.2.3 From aa8188253474b4053bc2900d9fcb545ce68bdf5c Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:51 -0700 Subject: kernfs: add exportfs operations Now we have the facilities to implement exportfs operations. The idea is cgroup can export the fhandle info to userspace, then userspace uses fhandle to find the cgroup name. Another example is userspace can get fhandle for a cgroup and BPF uses the fhandle to filter info for the cgroup. Acked-by: Greg Kroah-Hartman Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/kernfs.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 06a0c5913e1d..d149361e5875 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -69,6 +69,12 @@ enum kernfs_root_flag { * following flag enables that behavior. */ KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK = 0x0002, + + /* + * The filesystem supports exportfs operation, so userspace can use + * fhandle to access nodes of the fs. + */ + KERNFS_ROOT_SUPPORT_EXPORTOP = 0x0004, }; /* type-specific structures for kernfs_node union members */ @@ -98,6 +104,12 @@ struct kernfs_elem_attr { /* represent a kernfs node */ union kernfs_node_id { struct { + /* + * blktrace will export this struct as a simplified 'struct + * fid' (which is a big data struction), so userspace can use + * it to find kernfs node. The layout must match the first two + * fields of 'struct fid' exactly. + */ u32 ino; u32 generation; }; -- cgit v1.2.3 From 121508df44d074245a72eda6b067478218480a40 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:52 -0700 Subject: cgroup: export fhandle info for a cgroup Add an API to export cgroup fhandle info. We don't export a full 'struct file_handle', there are unrequired info. Sepcifically, cgroup is always a directory, so we don't need a 'FILEID_INO32_GEN_PARENT' type fhandle, we only need export the inode number and generation number just like what generic_fh_to_dentry does. And we can avoid the overhead of getting an inode too, since kernfs_node_id (ino and generation) has all the info required. Acked-by: Tejun Heo Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/cgroup.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 30c68773fd1e..52ef9a68ff14 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -609,6 +609,10 @@ static inline void cgroup_kthread_ready(void) current->no_cgroup_migration = 0; } +static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) +{ + return &cgrp->kn->id; +} #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -631,6 +635,10 @@ static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} +static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) +{ + return NULL; +} static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) -- cgit v1.2.3 From 007cc56b7eeca8848021bc43aca2b8607fbe5589 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:54 -0700 Subject: block: always attach cgroup info into bio blkcg_bio_issue_check() already gets blkcg for a BIO. bio_associate_blkcg() uses a percpu refcounter, so it's a very cheap operation. There is no point we don't attach the cgroup info into bio at blkcg_bio_issue_check. This also makes blktrace outputs correct cgroup info. Acked-by: Tejun Heo Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 7104bea8dab1..9d92153dd856 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -691,6 +691,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, rcu_read_lock(); blkcg = bio_blkcg(bio); + /* associate blkcg if bio hasn't attached one */ + bio_associate_blkcg(bio, &blkcg->css); + blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { spin_lock_irq(q->queue_lock); -- cgit v1.2.3 From 69fd5c391763bd94a40dd152bc72a7f230137150 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:55 -0700 Subject: blktrace: add an option to allow displaying cgroup path By default we output cgroup id in blktrace. This adds an option to display cgroup path. Since get cgroup path is a relativly heavy operation, we don't enable it by default. with the option enabled, blktrace will output something like this: dd-1353 [007] d..2 293.015252: 8,0 /test/level D R 24 + 8 [dd] Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/cgroup.h | 6 ++++++ include/linux/kernfs.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 52ef9a68ff14..6144fe923b73 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -613,6 +613,9 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) { return &cgrp->kn->id; } + +void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, + char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; @@ -645,6 +648,9 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, { return true; } + +static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, + char *buf, size_t buflen) {} #endif /* !CONFIG_CGROUPS */ /* diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index d149361e5875..ab25c8b6d9e3 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -358,6 +358,8 @@ struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns); void kernfs_init(void); +struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, + const union kernfs_node_id *id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) -- cgit v1.2.3 From 35fe6d763229e8fc0eb5f9b93a401673cfcb5e1e Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:56 -0700 Subject: block: use standard blktrace API to output cgroup info for debug notes Currently cfq/bfq/blk-throttle output cgroup info in trace in their own way. Now we have standard blktrace API for this, so convert them to use it. Note, this changes the behavior a little bit. cgroup info isn't output by default, we only do this with 'blk_cgroup' option enabled. cgroup info isn't output as a string by default too, we only do this with 'blk_cgname' option enabled. Also cgroup info is output in different position of the note string. I think these behavior changes aren't a big issue (actually we make trace data shorter which is good), since the blktrace note is solely for debugging. Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index d2e908586e3d..67b4d4dfc19c 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -28,10 +28,12 @@ struct blk_trace { atomic_t dropped; }; +struct blkcg; + extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern __printf(2, 3) -void __trace_note_message(struct blk_trace *, const char *fmt, ...); +extern __printf(3, 4) +void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream @@ -46,12 +48,14 @@ void __trace_note_message(struct blk_trace *, const char *fmt, ...); * NOTE: Can not use 'static inline' due to presence of var args... * **/ -#define blk_add_trace_msg(q, fmt, ...) \ +#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ do { \ struct blk_trace *bt = (q)->blk_trace; \ if (unlikely(bt)) \ - __trace_note_message(bt, fmt, ##__VA_ARGS__); \ + __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ } while (0) +#define blk_add_trace_msg(q, fmt, ...) \ + blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__) #define BLK_TN_MAX_MSG 128 static inline bool blk_trace_note_message_enabled(struct request_queue *q) @@ -82,6 +86,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) +# define blk_add_cgroup_trace_msg(q, cg, fmt, ...) do { } while (0) # define blk_trace_remove_sysfs(dev) do { } while (0) # define blk_trace_note_message_enabled(q) (false) static inline int blk_trace_init_sysfs(struct device *dev) -- cgit v1.2.3 From 0bf8bf50eddc7511b52461bae798cbfaa0157a34 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Mon, 24 Jul 2017 18:27:25 -0700 Subject: module: Remove const attribute from alias for MODULE_DEVICE_TABLE MODULE_DEVICE_TABLE(type, name) creates an alias of type 'extern const typeof(name)'. If 'name' is already constant the 'const' attribute is specified twice, which is not allowed in C89 (see discussion at https://lkml.org/lkml/2017/5/23/1440). Since the kernel is built with -std=gnu89 clang generates warnings like this: drivers/thermal/x86_pkg_temp_thermal.c:509:1: warning: duplicate 'const' declaration specifier [-Wduplicate-decl-specifier] MODULE_DEVICE_TABLE(x86cpu, pkg_temp_thermal_ids); ^ ./include/linux/module.h:212:8: note: expanded from macro 'MODULE_DEVICE_TABLE' extern const typeof(name) __mod_##type##__##name##_device_table Remove the const attribute from the alias to avoid the duplicate specifier. After all it is only an alias and the attribute shouldn't have any effect. Signed-off-by: Matthias Kaehlcke Signed-off-by: Jessica Yu --- include/linux/module.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index e7bdd549e527..fe5aa3736707 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -209,7 +209,7 @@ extern void cleanup_module(void); #ifdef MODULE /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ -extern const typeof(name) __mod_##type##__##name##_device_table \ +extern typeof(name) __mod_##type##__##name##_device_table \ __attribute__ ((unused, alias(__stringify(name)))) #else /* !MODULE */ #define MODULE_DEVICE_TABLE(type, name) -- cgit v1.2.3 From 1a5f3da20bd966220931239fbd31e6ac6ff42251 Mon Sep 17 00:00:00 2001 From: Vidya Sagar Ravipati Date: Thu, 27 Jul 2017 16:47:26 -0700 Subject: net: ethtool: add support for forward error correction modes Forward Error Correction (FEC) modes i.e Base-R and Reed-Solomon modes are introduced in 25G/40G/100G standards for providing good BER at high speeds. Various networking devices which support 25G/40G/100G provides ability to manage supported FEC modes and the lack of FEC encoding control and reporting today is a source for interoperability issues for many vendors. FEC capability as well as specific FEC mode i.e. Base-R or RS modes can be requested or advertised through bits D44:47 of base link codeword. This patch set intends to provide option under ethtool to manage and report FEC encoding settings for networking devices as per IEEE 802.3 bj, bm and by specs. set-fec/show-fec option(s) are designed to provide control and report the FEC encoding on the link. SET FEC option: root@tor: ethtool --set-fec swp1 encoding [off | RS | BaseR | auto] Encoding: Types of encoding Off : Turning off any encoding RS : enforcing RS-FEC encoding on supported speeds BaseR : enforcing Base R encoding on supported speeds Auto : IEEE defaults for the speed/medium combination Here are a few examples of what we would expect if encoding=auto: - if autoneg is on, we are expecting FEC to be negotiated as on or off as long as protocol supports it - if the hardware is capable of detecting the FEC encoding on it's receiver it will reconfigure its encoder to match - in absence of the above, the configuration would be set to IEEE defaults. >From our understanding , this is essentially what most hardware/driver combinations are doing today in the absence of a way for users to control the behavior. SHOW FEC option: root@tor: ethtool --show-fec swp1 FEC parameters for swp1: Active FEC encodings: RS Configured FEC encodings: RS | BaseR ETHTOOL DEVNAME output modification: ethtool devname output: root@tor:~# ethtool swp1 Settings for swp1: root@hpe-7712-03:~# ethtool swp18 Settings for swp18: Supported ports: [ FIBRE ] Supported link modes: 40000baseCR4/Full 40000baseSR4/Full 40000baseLR4/Full 100000baseSR4/Full 100000baseCR4/Full 100000baseLR4_ER4/Full Supported pause frame use: No Supports auto-negotiation: Yes Supported FEC modes: [RS | BaseR | None | Not reported] Advertised link modes: Not reported Advertised pause frame use: No Advertised auto-negotiation: No Advertised FEC modes: [RS | BaseR | None | Not reported] <<<< One or more FEC modes Speed: 100000Mb/s Duplex: Full Port: FIBRE PHYAD: 106 Transceiver: internal Auto-negotiation: off Link detected: yes This patch includes following changes a) New ETHTOOL_SFECPARAM/SFECPARAM API, handled by the new get_fecparam/set_fecparam callbacks, provides support for configuration of forward error correction modes. b) Link mode bits for FEC modes i.e. None (No FEC mode), RS, BaseR/FC are defined so that users can configure these fec modes for supported and advertising fields as part of link autonegotiation. Signed-off-by: Vidya Sagar Ravipati Signed-off-by: Dustin Byford Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/ethtool.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 83cc9863444b..afdbb701fdb4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -374,5 +374,9 @@ struct ethtool_ops { struct ethtool_link_ksettings *); int (*set_link_ksettings)(struct net_device *, const struct ethtool_link_ksettings *); + int (*get_fecparam)(struct net_device *, + struct ethtool_fecparam *); + int (*set_fecparam)(struct net_device *, + struct ethtool_fecparam *); }; #endif /* _LINUX_ETHTOOL_H */ -- cgit v1.2.3 From c7ac15ce89242e3c25fcc49fa4d00028285fab05 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 25 Jul 2017 20:39:58 +0300 Subject: serial: core: move UPF_NO_TXEN_TEST to quirks and rename First 16 bits in the flags field are user-visible except UPF_NO_TXEN_TEST. To keep it clean we introduce internal quirks and move UPF_NO_TXEN_TEST to them. Rename the constant to UPQ_NO_TXEN_TEST to distinguish with port flags. Users are converted accordingly. The quirks field might be extended later to hold the additional ones. Signed-off-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 1775500294bb..8dc24c855a70 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -20,7 +20,7 @@ #ifndef LINUX_SERIAL_CORE_H #define LINUX_SERIAL_CORE_H - +#include #include #include #include @@ -144,7 +144,7 @@ struct uart_port { unsigned char x_char; /* xon/xoff char */ unsigned char regshift; /* reg offset shift */ unsigned char iotype; /* io access style */ - unsigned char unused1; + unsigned char quirks; /* internal quirks */ #define UPIO_PORT (SERIAL_IO_PORT) /* 8b I/O port access */ #define UPIO_HUB6 (SERIAL_IO_HUB6) /* Hub6 ISA card */ @@ -155,6 +155,9 @@ struct uart_port { #define UPIO_MEM32BE (SERIAL_IO_MEM32BE) /* 32b big endian */ #define UPIO_MEM16 (SERIAL_IO_MEM16) /* 16b little endian */ + /* quirks must be updated while holding port mutex */ +#define UPQ_NO_TXEN_TEST BIT(0) + unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ struct uart_state *state; /* pointer to parent state */ @@ -175,7 +178,6 @@ struct uart_port { * [for bit definitions in the UPF_CHANGE_MASK] * * Bits [0..UPF_LAST_USER] are userspace defined/visible/changeable - * except bit 15 (UPF_NO_TXEN_TEST) which is masked off. * The remaining bits are serial-core specific and not modifiable by * userspace. */ @@ -192,7 +194,6 @@ struct uart_port { #define UPF_SPD_SHI ((__force upf_t) ASYNC_SPD_SHI /* 12 */ ) #define UPF_LOW_LATENCY ((__force upf_t) ASYNC_LOW_LATENCY /* 13 */ ) #define UPF_BUGGY_UART ((__force upf_t) ASYNC_BUGGY_UART /* 14 */ ) -#define UPF_NO_TXEN_TEST ((__force upf_t) (1 << 15)) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) #define UPF_NO_THRE_TEST ((__force upf_t) (1 << 19)) -- cgit v1.2.3 From 979990c6284814617d8f2179d197f72ff62b5d85 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 20 Jun 2017 23:10:41 +0200 Subject: tty: improve tty_insert_flip_char() fast path kernelci.org reports a crazy stack usage for the VT code when CONFIG_KASAN is enabled: drivers/tty/vt/keyboard.c: In function 'kbd_keycode': drivers/tty/vt/keyboard.c:1452:1: error: the frame size of 2240 bytes is larger than 2048 bytes [-Werror=frame-larger-than=] The problem is that tty_insert_flip_char() gets inlined many times into kbd_keycode(), and also into other functions, and each copy requires 128 bytes for stack redzone to check for a possible out-of-bounds access on the 'ch' and 'flags' arguments that are passed into tty_insert_flip_string_flags as a variable-length string. This introduces a new __tty_insert_flip_char() function for the slow path, which receives the two arguments by value. This completely avoids the problem and the stack usage goes back down to around 100 bytes. Without KASAN, this is also slightly better, as we don't have to spill the arguments to the stack but can simply pass 'ch' and 'flag' in registers, saving a few bytes in .text for each call site. This should be backported to linux-4.0 or later, which first introduced the stack sanitizer in the kernel. Cc: stable@vger.kernel.org Fixes: c420f167db8c ("kasan: enable stack instrumentation") Signed-off-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_flip.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index c28dd523f96e..d43837f2ce3a 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -12,6 +12,7 @@ extern int tty_prepare_flip_string(struct tty_port *port, unsigned char **chars, size_t size); extern void tty_flip_buffer_push(struct tty_port *port); void tty_schedule_flip(struct tty_port *port); +int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag); static inline int tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag) @@ -26,7 +27,7 @@ static inline int tty_insert_flip_char(struct tty_port *port, *char_buf_ptr(tb, tb->used++) = ch; return 1; } - return tty_insert_flip_string_flags(port, &ch, &flag, 1); + return __tty_insert_flip_char(port, ch, flag); } static inline int tty_insert_flip_string(struct tty_port *port, -- cgit v1.2.3 From 87840fb5a9dc934948ef7e067a993423a7a39df9 Mon Sep 17 00:00:00 2001 From: Laurentiu Tudor Date: Wed, 19 Jul 2017 14:42:25 +0300 Subject: staging: fsl-mc: add missing fsl_mc comment in struct msi_desc The mc-bus specific field, fsl_mc in struct msi_desc is missing its comment so add it. Signed-off-by: Laurentiu Tudor Acked-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/msi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index df6d59201d31..80e3b562bef6 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -66,6 +66,7 @@ struct fsl_mc_msi_desc { * @mask_pos: [PCI MSI] Mask register position * @mask_base: [PCI MSI-X] Mask register base address * @platform: [platform] Platform device specific msi descriptor data + * @fsl_mc: [fsl-mc] FSL MC device specific msi descriptor data */ struct msi_desc { /* Shared device/bus type independent data */ -- cgit v1.2.3 From c5dc3c69f17a7e77359f10c342d1816390bc8846 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 19 Jun 2017 20:04:58 +0200 Subject: PCI/portdrv: Move error handler methods to struct pcie_port_service_driver Move the error handler methods to struct pcie_port_service_driver and avoid the detour through the mostly unused pci_error_handlers structure. Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas --- include/linux/pcieport_if.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index afcd130ab3a9..18edc651c070 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -50,8 +50,8 @@ struct pcie_port_service_driver { int (*suspend) (struct pcie_device *dev); int (*resume) (struct pcie_device *dev); - /* Service Error Recovery Handler */ - const struct pci_error_handlers *err_handler; + /* Device driver may resume normal operations */ + void (*error_resume)(struct pci_dev *dev); /* Link Reset Capability - AER service driver specific */ pci_ers_result_t (*reset_link) (struct pci_dev *dev); -- cgit v1.2.3 From 62ce94a7a5a54aac80975f5e6731707225d4077e Mon Sep 17 00:00:00 2001 From: Sinan Kaya Date: Wed, 12 Jul 2017 00:04:14 -0400 Subject: PCI: Mark Broadcom HT2100 Root Port Extended Tags as broken Per PCIe r3.1, sec 2.2.6.2 and 7.8.4, a Requester may not use 8-bit Tags unless its Extended Tag Field Enable is set, but all Receivers/Completers must handle 8-bit Tags correctly regardless of their Extended Tag Field Enable. Some devices do not handle 8-bit Tags as Completers, so add a quirk for them. If we find such a device, we disable Extended Tags for the entire hierarchy to make peer-to-peer DMA possible. The Broadcom HT2100 seems to have issues with handling 8-bit tags. Mark it as broken. The pci_walk_bus() in the quirk handles devices we've enumerated in the past, and pci_configure_device() handles devices we enumerate in the future. Fixes: 60db3a4d8cc9 ("PCI: Enable PCIe Extended Tags if supported") Link: https://bugzilla.redhat.com/show_bug.cgi?id=1467674 Reported-and-tested-by: Wim ten Have Signed-off-by: Sinan Kaya [bhelgaas: changelog, tweak messages, rename bit and quirk] Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659..3b968d435895 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -451,6 +451,7 @@ struct pci_host_bridge { void *release_data; struct msi_controller *msi; unsigned int ignore_reset_delay:1; /* for entire hierarchy */ + unsigned int no_ext_tags:1; /* no Extended Tags */ /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, const struct resource *res, -- cgit v1.2.3 From e7942d0633c47c791ece6afa038be9cf977226de Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 30 Jul 2017 03:57:18 +0200 Subject: tcp: remove prequeue support prequeue is a tcp receive optimization that moves part of rx processing from bh to process context. This only works if the socket being processed belongs to a process that is blocked in recv on that socket. In practice, this doesn't happen anymore that often because nowadays servers tend to use an event driven (epoll) model. Even normal client applications (web browsers) commonly use many tcp connections in parallel. This has measureable impact only in netperf (which uses plain recv and thus allows prequeue use) from host to locally running vm (~4%), however, there were no changes when using netperf between two physical hosts with ixgbe interfaces. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/tcp.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 542ca1ae02c4..32fb37cfb0d1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -192,15 +192,6 @@ struct tcp_sock { struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ - /* Data for direct copy to user */ - struct { - struct sk_buff_head prequeue; - struct task_struct *task; - struct msghdr *msg; - int memory; - int len; - } ucopy; - u32 snd_wl1; /* Sequence for window update */ u32 snd_wnd; /* The window we expect to receive */ u32 max_window; /* Maximal window ever seen from peer */ -- cgit v1.2.3 From 45f119bf936b1f9f546a0b139c5b56f9bb2bdc78 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 30 Jul 2017 03:57:21 +0200 Subject: tcp: remove header prediction Like prequeue, I am not sure this is overly useful nowadays. If we receive a train of packets, GRO will aggregate them if the headers are the same (HP predates GRO by several years) so we don't get a per-packet benefit, only a per-aggregated-packet one. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 32fb37cfb0d1..d7389ea36e10 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -147,12 +147,6 @@ struct tcp_sock { u16 tcp_header_len; /* Bytes of tcp header to send */ u16 gso_segs; /* Max number of segs per GSO packet */ -/* - * Header prediction flags - * 0x5?10 << 16 + snd_wnd in net byte order - */ - __be32 pred_flags; - /* * RFC793 variables by their proper names. This means you can * read the code and the spec side by side (and laugh ...) -- cgit v1.2.3 From f248aff86d1fd6e60b656c2af278f1723c3b84c2 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 31 Jul 2017 12:04:25 -0700 Subject: net: phy: mdio-bcm-unimac: Allow specifying platform data In preparation for having the bcmgenet driver migrate over the mdio-bcm-unimac driver, add a platform data structure which allows passing integrating specific details like bus name, wait function to complete MDIO operations and PHY mask. We also define what the platform device name contract is by defining UNIMAC_MDIO_DRV_NAME and moving it to the platform_data header. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/platform_data/mdio-bcm-unimac.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/platform_data/mdio-bcm-unimac.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mdio-bcm-unimac.h b/include/linux/platform_data/mdio-bcm-unimac.h new file mode 100644 index 000000000000..8a5f9f0b2c52 --- /dev/null +++ b/include/linux/platform_data/mdio-bcm-unimac.h @@ -0,0 +1,13 @@ +#ifndef __MDIO_BCM_UNIMAC_PDATA_H +#define __MDIO_BCM_UNIMAC_PDATA_H + +struct unimac_mdio_pdata { + u32 phy_mask; + int (*wait_func)(void *data); + void *wait_func_data; + const char *bus_name; +}; + +#define UNIMAC_MDIO_DRV_NAME "unimac-mdio" + +#endif /* __MDIO_BCM_UNIMAC_PDATA_H */ -- cgit v1.2.3 From a823e4589e68996436d16db4ede9a43b646332f9 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Fri, 28 Jul 2017 07:24:43 -0400 Subject: mm: add file_fdatawait_range and file_write_and_wait Necessary now for gfs2_fsync and sync_file_range, but there will eventually be other callers. Reviewed-by: Jan Kara Signed-off-by: Jeff Layton --- include/linux/fs.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 21e7df1ad613..af592ca3d509 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2544,6 +2544,8 @@ extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); +extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, + loff_t lend); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); @@ -2552,12 +2554,19 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping, extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); extern int filemap_check_errors(struct address_space *mapping); - extern void __filemap_set_wb_err(struct address_space *mapping, int err); + +extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, + loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); +static inline int file_write_and_wait(struct file *file) +{ + return file_write_and_wait_range(file, 0, LLONG_MAX); +} + /** * filemap_set_wb_err - set a writeback error on an address_space * @mapping: mapping in which to set writeback error -- cgit v1.2.3 From f247037120ecd3dcbbc196b51ded8b57edf4904f Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 19 Jul 2017 00:19:05 +0800 Subject: f2fs: make max inline size changeable This patch tries to make below macros calculating max inline size, inline dentry field size considerring reserving size-changeable space: - MAX_INLINE_DATA - NR_INLINE_DENTRY - INLINE_DENTRY_BITMAP_SIZE - INLINE_RESERVED_SIZE Then, when inline_{data,dentry} options is enabled, it allows us to reserve inline space with different size flexibly for adding newly introduced inode attribute. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 23 +---------------------- 1 file changed, 1 insertion(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index b6feed6547ce..060b1c5b0836 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -206,9 +206,6 @@ struct f2fs_extent { #define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */ #define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */ -#define MAX_INLINE_DATA (sizeof(__le32) * (DEF_ADDRS_PER_INODE - \ - F2FS_INLINE_XATTR_ADDRS - 1)) - struct f2fs_inode { __le16 i_mode; /* file mode */ __u8 i_advise; /* file hints */ @@ -465,7 +462,7 @@ typedef __le32 f2fs_hash_t; #define MAX_DIR_BUCKETS (1 << ((MAX_DIR_HASH_DEPTH / 2) - 1)) /* - * space utilization of regular dentry and inline dentry + * space utilization of regular dentry and inline dentry (w/o extra reservation) * regular dentry inline dentry * bitmap 1 * 27 = 27 1 * 23 = 23 * reserved 1 * 3 = 3 1 * 7 = 7 @@ -501,24 +498,6 @@ struct f2fs_dentry_block { __u8 filename[NR_DENTRY_IN_BLOCK][F2FS_SLOT_LEN]; } __packed; -/* for inline dir */ -#define NR_INLINE_DENTRY (MAX_INLINE_DATA * BITS_PER_BYTE / \ - ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ - BITS_PER_BYTE + 1)) -#define INLINE_DENTRY_BITMAP_SIZE ((NR_INLINE_DENTRY + \ - BITS_PER_BYTE - 1) / BITS_PER_BYTE) -#define INLINE_RESERVED_SIZE (MAX_INLINE_DATA - \ - ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ - NR_INLINE_DENTRY + INLINE_DENTRY_BITMAP_SIZE)) - -/* inline directory entry structure */ -struct f2fs_inline_dentry { - __u8 dentry_bitmap[INLINE_DENTRY_BITMAP_SIZE]; - __u8 reserved[INLINE_RESERVED_SIZE]; - struct f2fs_dir_entry dentry[NR_INLINE_DENTRY]; - __u8 filename[NR_INLINE_DENTRY][F2FS_SLOT_LEN]; -} __packed; - /* file types used in inode_info->flags */ enum { F2FS_FT_UNKNOWN, -- cgit v1.2.3 From 7a2af766af15887754f7f7a0869b4603b390876a Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 19 Jul 2017 00:19:06 +0800 Subject: f2fs: enhance on-disk inode structure scalability This patch add new flag F2FS_EXTRA_ATTR storing in inode.i_inline to indicate that on-disk structure of current inode is extended. In order to extend, we changed the inode structure a bit: Original one: struct f2fs_inode { ... struct f2fs_extent i_ext; __le32 i_addr[DEF_ADDRS_PER_INODE]; __le32 i_nid[DEF_NIDS_PER_INODE]; } Extended one: struct f2fs_inode { ... struct f2fs_extent i_ext; union { struct { __le16 i_extra_isize; __le16 i_padding; __le32 i_extra_end[0]; }; __le32 i_addr[DEF_ADDRS_PER_INODE]; }; __le32 i_nid[DEF_NIDS_PER_INODE]; } Once F2FS_EXTRA_ATTR is set, we will steal four bytes in the head of i_addr field for storing i_extra_isize and i_padding. with i_extra_isize, we can calculate actual size of reserved space in i_addr, available attribute fields included in total extra attribute fields for current inode can be described as below: +--------------------+ | .i_mode | | ... | | .i_ext | +--------------------+ | .i_extra_isize |-----+ | .i_padding | | | .i_prjid | | | .i_atime_extra | | | .i_ctime_extra | | | .i_mtime_extra |<----+ | .i_inode_cs |<----- store blkaddr/inline from here | .i_xattr_cs | | ... | +--------------------+ | | | block address | | | +--------------------+ | .i_nid | +--------------------+ | node_footer | | (nid, ino, offset) | +--------------------+ Hence, with this patch, we would enhance scalability of f2fs inode for storing more newly added attribute. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 060b1c5b0836..0c79ddd40b70 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -186,6 +186,8 @@ struct f2fs_extent { #define F2FS_NAME_LEN 255 #define F2FS_INLINE_XATTR_ADDRS 50 /* 200 bytes for inline xattrs */ #define DEF_ADDRS_PER_INODE 923 /* Address Pointers in an Inode */ +#define CUR_ADDRS_PER_INODE(inode) (DEF_ADDRS_PER_INODE - \ + get_extra_isize(inode)) #define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */ #define ADDRS_PER_INODE(inode) addrs_per_inode(inode) #define ADDRS_PER_BLOCK 1018 /* Address Pointers in a Direct Block */ @@ -205,6 +207,7 @@ struct f2fs_extent { #define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */ #define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */ #define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */ +#define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */ struct f2fs_inode { __le16 i_mode; /* file mode */ @@ -232,8 +235,14 @@ struct f2fs_inode { struct f2fs_extent i_ext; /* caching a largest extent */ - __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ - + union { + struct { + __le16 i_extra_isize; /* extra inode attribute size */ + __le16 i_padding; /* padding */ + __le32 i_extra_end[0]; /* for attribute size calculation */ + }; + __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ + }; __le32 i_nid[DEF_NIDS_PER_INODE]; /* direct(2), indirect(2), double_indirect(1) node id */ } __packed; -- cgit v1.2.3 From 5c57132eaf5265937e46340bfbfb97ffb078c423 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Wed, 26 Jul 2017 00:01:41 +0800 Subject: f2fs: support project quota This patch adds to support plain project quota. Signed-off-by: Chao Yu Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 0c79ddd40b70..50f176683676 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -239,6 +239,7 @@ struct f2fs_inode { struct { __le16 i_extra_isize; /* extra inode attribute size */ __le16 i_padding; /* padding */ + __le32 i_projid; /* project id */ __le32 i_extra_end[0]; /* for attribute size calculation */ }; __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ @@ -522,4 +523,6 @@ enum { #define S_SHIFT 12 +#define F2FS_DEF_PROJID 0 /* default project ID */ + #endif /* _LINUX_F2FS_FS_H */ -- cgit v1.2.3 From 6f68f0ac72087c29a94d1736324902e3ec07a4ec Mon Sep 17 00:00:00 2001 From: Binoy Jayan Date: Wed, 14 Jun 2017 12:59:51 +0530 Subject: HID: Remove the semaphore driver_lock The semaphore 'driver_lock' is used as a simple mutex, and also unnecessary as suggested by Arnd. Hence removing it, as the concurrency between the probe and remove is already handled in the driver core. Suggested-by: Arnd Bergmann Signed-off-by: Binoy Jayan Acked-by: Benjamin Tissoires Reviewed-by: David Herrmann Signed-off-by: Jiri Kosina --- include/linux/hid.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 5006f9b5d837..142409fc1ff3 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -526,7 +526,6 @@ struct hid_device { /* device report descriptor */ struct hid_report_enum report_enum[HID_REPORT_TYPES]; struct work_struct led_work; /* delayed LED worker */ - struct semaphore driver_lock; /* protects the current driver, except during input */ struct semaphore driver_input_lock; /* protects the current driver */ struct device dev; /* device */ struct hid_driver *driver; @@ -551,7 +550,7 @@ struct hid_device { /* device report descriptor */ unsigned int status; /* see STAT flags above */ unsigned claimed; /* Claimed by hidinput, hiddev? */ unsigned quirks; /* Various quirks the device can pull on us */ - bool io_started; /* Protected by driver_lock. If IO has started */ + bool io_started; /* If IO has started */ struct list_head inputs; /* The list of inputs */ void *hiddev; /* The hiddev structure */ -- cgit v1.2.3 From 674e75411fc260b0d4532701228cfe12fc090da8 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 28 Jul 2017 12:16:38 +0530 Subject: sched: cpufreq: Allow remote cpufreq callbacks With Android UI and benchmarks the latency of cpufreq response to certain scheduling events can become very critical. Currently, callbacks into cpufreq governors are only made from the scheduler if the target CPU of the event is the same as the current CPU. This means there are certain situations where a target CPU may not run the cpufreq governor for some time. One testcase to show this behavior is where a task starts running on CPU0, then a new task is also spawned on CPU0 by a task on CPU1. If the system is configured such that the new tasks should receive maximum demand initially, this should result in CPU0 increasing frequency immediately. But because of the above mentioned limitation though, this does not occur. This patch updates the scheduler core to call the cpufreq callbacks for remote CPUs as well. The schedutil, ondemand and conservative governors are updated to process cpufreq utilization update hooks called for remote CPUs where the remote CPU is managed by the cpufreq policy of the local CPU. The intel_pstate driver is updated to always reject remote callbacks. This is tested with couple of usecases (Android: hackbench, recentfling, galleryfling, vellamo, Ubuntu: hackbench) on ARM hikey board (64 bit octa-core, single policy). Only galleryfling showed minor improvements, while others didn't had much deviation. The reason being that this patch only targets a corner case, where following are required to be true to improve performance and that doesn't happen too often with these tests: - Task is migrated to another CPU. - The task has high demand, and should take the target CPU to higher OPPs. - And the target CPU doesn't call into the cpufreq governor until the next tick. Based on initial work from Steve Muckle. Signed-off-by: Viresh Kumar Acked-by: Saravana Kannan Acked-by: Peter Zijlstra (Intel) Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index f10a9b3761cd..c4035964e6b3 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -562,6 +562,15 @@ struct governor_attr { size_t count); }; +static inline bool cpufreq_can_do_remote_dvfs(struct cpufreq_policy *policy) +{ + /* Allow remote callbacks only on the CPUs sharing cpufreq policy */ + if (cpumask_test_cpu(smp_processor_id(), policy->cpus)) + return true; + + return false; +} + /********************************************************************* * FREQUENCY TABLE HELPERS * *********************************************************************/ -- cgit v1.2.3 From 99d14d0e16fadb4de001bacc0ac0786a9ebecf2a Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Fri, 28 Jul 2017 12:16:39 +0530 Subject: cpufreq: Process remote callbacks from any CPU if the platform permits On many platforms, CPUs can do DVFS across cpufreq policies. i.e CPU from policy-A can change frequency of CPUs belonging to policy-B. This is quite common in case of ARM platforms where we don't configure any per-cpu register. Add a flag to identify such platforms and update cpufreq_can_do_remote_dvfs() to allow remote callbacks if this flag is set. Also enable the flag for cpufreq-dt driver which is used only on ARM platforms currently. Signed-off-by: Viresh Kumar Acked-by: Saravana Kannan Acked-by: Peter Zijlstra (Intel) Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c4035964e6b3..1981a4a167ce 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -127,6 +127,15 @@ struct cpufreq_policy { */ unsigned int transition_delay_us; + /* + * Remote DVFS flag (Not added to the driver structure as we don't want + * to access another structure from scheduler hotpath). + * + * Should be set if CPUs can do DVFS on behalf of other CPUs from + * different cpufreq policies. + */ + bool dvfs_possible_from_any_cpu; + /* Cached frequency lookup from cpufreq_driver_resolve_freq. */ unsigned int cached_target_freq; int cached_resolved_idx; @@ -564,8 +573,13 @@ struct governor_attr { static inline bool cpufreq_can_do_remote_dvfs(struct cpufreq_policy *policy) { - /* Allow remote callbacks only on the CPUs sharing cpufreq policy */ - if (cpumask_test_cpu(smp_processor_id(), policy->cpus)) + /* + * Allow remote callbacks if: + * - dvfs_possible_from_any_cpu flag is set + * - the local and remote CPUs share cpufreq policy + */ + if (policy->dvfs_possible_from_any_cpu || + cpumask_test_cpu(smp_processor_id(), policy->cpus)) return true; return false; -- cgit v1.2.3 From bc2eecd7ecce40af43b6eb3d256b6076257df846 Mon Sep 17 00:00:00 2001 From: Nicolas Pitre Date: Tue, 1 Aug 2017 00:31:32 -0400 Subject: futex: Allow for compiling out PI support This makes it possible to preserve basic futex support and compile out the PI support when RT mutexes are not available. Signed-off-by: Nicolas Pitre Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Darren Hart Link: http://lkml.kernel.org/r/alpine.LFD.2.20.1708010024190.5981@knanqh.ubzr --- include/linux/futex.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/futex.h b/include/linux/futex.h index 7c5b694864cd..f36bfd26f998 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -54,7 +54,6 @@ union futex_key { #ifdef CONFIG_FUTEX extern void exit_robust_list(struct task_struct *curr); -extern void exit_pi_state_list(struct task_struct *curr); #ifdef CONFIG_HAVE_FUTEX_CMPXCHG #define futex_cmpxchg_enabled 1 #else @@ -64,8 +63,14 @@ extern int futex_cmpxchg_enabled; static inline void exit_robust_list(struct task_struct *curr) { } +#endif + +#ifdef CONFIG_FUTEX_PI +extern void exit_pi_state_list(struct task_struct *curr); +#else static inline void exit_pi_state_list(struct task_struct *curr) { } #endif + #endif -- cgit v1.2.3 From ffb959bbdf923b4f89a08a04aba2501b1b16d164 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 31 Jul 2017 10:29:38 -0400 Subject: mm: remove optimizations based on i_size in mapping writeback waits Marcelo added this i_size based optimization with a patch in 2004 (commitid is from the linux-history tree): commit 765dad09b4ac101a32d87af2bb793c3060497d3c Author: Marcelo Tosatti Date: Tue Sep 7 17:51:17 2004 -0700 small wait_on_page_writeback_range() optimization filemap_fdatawait() calls wait_on_page_writeback_range() with -1 as "end" parameter. This is not needed since we know the EOF from the inode. Use that instead. There may be races here, particularly with clustered or network filesystems. It also seems like a bit of a layering violation since we're operating on an address_space here, not an inode. Finally, it's also questionable whether this optimization really helps on workloads that we care about. Should we be optimizing for writeback vs. truncate races in a codepath where we expect to wait anyway? It doesn't seem worth the risk. Remove this optimization from the filemap_fdatawait codepaths. This means that filemap_fdatawait becomes a trivial wrapper around filemap_fdatawait_range. Reviewed-by: Jan Kara Signed-off-by: Jeff Layton --- include/linux/fs.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index af592ca3d509..909210bd6366 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2538,10 +2538,15 @@ extern int invalidate_inode_pages2_range(struct address_space *mapping, extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); -extern int filemap_fdatawait(struct address_space *); extern int filemap_fdatawait_keep_errors(struct address_space *mapping); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); + +static inline int filemap_fdatawait(struct address_space *mapping) +{ + return filemap_fdatawait_range(mapping, 0, LLONG_MAX); +} + extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, -- cgit v1.2.3 From 6104c37094e729f3d4ce65797002112735d49cd1 Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 1 Aug 2017 17:32:07 +0200 Subject: fbcon: Make fbcon a built-time depency for fbdev There's a bunch of folks who're trying to make printk less contended and faster, but there's a problem: printk uses the console_lock, and the console lock has become the BKL for all things fbdev/fbcon, which in turn pulled in half the drm subsystem under that lock. That's awkward. There reasons for that is probably just a historical accident: - fbcon is a runtime option of fbdev, i.e. at runtime you can pick whether your fbdev driver instances are used as kernel consoles. Unfortunately this wasn't implemented with some module option, but through some module loading magic: As long as you don't load fbcon.ko, there's no fbdev console support, but loading it (in any order wrt fbdev drivers) will create console instances for all fbdev drivers. - This was implemented through a notifier chain. fbcon.ko enumerates all fbdev instances at load time and also registers itself as listener in the fbdev notifier. The fbdev core tries to register new fbdev instances with fbcon using the notifier. - On top of that the modifier chain is also used at runtime by the fbdev subsystem to e.g. control backlights for panels. - The problem is that the notifier puts a mutex locking context between fbdev and fbcon, which mixes up the locking contexts for both the runtime usage and the register time usage to notify fbcon. And at runtime fbcon (through the fbdev core) might call into the notifier from a printk critical section while console_lock is held. - This means console_lock must be an outer lock for the entire fbdev subsystem, which also means it must be acquired when registering a new framebuffer driver as the outermost lock since we might call into fbcon (through the notifier) which would result in a locking inversion if fbcon would acquire the console_lock from its notifier callback (which it needs to register the console). - console_lock can be held anywhere, since printk can be called anywhere, and through the above story, plus drm/kms being an fbdev driver, we pull in a shocking amount of locking hiercharchy underneath the console_lock. Which makes cleaning up printk really hard (not even splitting console_lock into an rwsem is all that useful due to this). There's various ways to address this, but the cleanest would be to make fbcon a compile-time option, where fbdev directly calls the fbcon register functions from register_framebuffer, or dummy static inline versions if fbcon is disabled. Maybe augmented with a runtime knob to disable fbcon, if that's needed (for debugging perhaps). But this could break some users who rely on the magic "loading fbcon.ko enables/disables fbdev framebuffers at runtime" thing, even if that's unlikely. Hence we must be careful: 1. Create a compile-time dependency between fbcon and fbdev in the least minimal way. This is what this patch does. 2. Wait at least 1 year to give possible users time to scream about how we broke their setup. Unlikely, since all distros make fbcon compile-in, and embedded platforms only compile stuff they know they need anyway. But still. 3. Convert the notifier to direct functions calls, with dummy static inlines if fbcon is disabled. We'll still need the fb notifier for the other uses (like backlights), but we can probably move it into the fb core (atm it must be built-into vmlinux). 4. Push console_lock down the call-chain, until it is down in console_register again. 5. Finally start to clean up and rework the printk/console locking. For context of this saga see commit 50e244cc793d511b86adea24972f3a7264cae114 Author: Alan Cox Date: Fri Jan 25 10:28:15 2013 +1000 fb: rework locking to fix lock ordering on takeover plus the pile of commits on top that tried to make this all work without terminally upsetting lockdep. We've uncovered all this when console_lock lockdep annotations where added in commit daee779718a319ff9f83e1ba3339334ac650bb22 Author: Daniel Vetter Date: Sat Sep 22 19:52:11 2012 +0200 console: implement lockdep support for console_lock On the patch itself: - Switch CONFIG_FRAMEBUFFER_CONSOLE to be a boolean, using the overall CONFIG_FB tristate to decided whether it should be a module or built-in. - At first I thought I could force the build depency with just a dummy symbol that fbcon.ko exports and fb.ko uses. But that leads to a module depency cycle (it works fine when built-in). Since this tight binding is the entire goal the simplest solution is to move all the fbcon modules (and there's a bunch of optinal source-files which are each modules of their own, for no good reason) into the overall fb.ko core module. That's a bit more than what I would have liked to do in this patch, but oh well. Signed-off-by: Daniel Vetter Cc: Alan Cox Cc: Sergey Senozhatsky Cc: Steven Rostedt Reviewed-by: Sean Paul Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/fbcon.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 include/linux/fbcon.h (limited to 'include/linux') diff --git a/include/linux/fbcon.h b/include/linux/fbcon.h new file mode 100644 index 000000000000..0fac6305d51c --- /dev/null +++ b/include/linux/fbcon.h @@ -0,0 +1,12 @@ +#ifndef _LINUX_FBCON_H +#define _LINUX_FBCON_H + +#ifdef CONFIG_FRAMEBUFFER_CONSOLE +void __init fb_console_init(void); +void __exit fb_console_exit(void); +#else +static void fb_console_init(void) {} +static void fb_console_exit(void) {} +#endif + +#endif /* _LINUX_FBCON_H */ -- cgit v1.2.3 From 376b3ff54c9a1cd54d71b1102e061fccf56d535e Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Tue, 1 Aug 2017 17:33:02 +0200 Subject: fbdev: Nuke FBINFO_MODULE Instead check info->ops->owner, which amounts to the same. Spotted because I want to remove the pile of broken and cargo-culted fb_info->flags assignments in drm drivers. Signed-off-by: Daniel Vetter Reviewed-by: Sean Paul Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/fb.h | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index a964d076b4dc..f4386b0ccf40 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -400,7 +400,7 @@ struct fb_tile_ops { #endif /* CONFIG_FB_TILEBLITTING */ /* FBINFO_* = fb_info.flags bit flags */ -#define FBINFO_MODULE 0x0001 /* Low-level driver is a module */ +#define FBINFO_DEFAULT 0 #define FBINFO_HWACCEL_DISABLED 0x0002 /* When FBINFO_HWACCEL_DISABLED is set: * Hardware acceleration is turned off. Software implementations @@ -533,14 +533,6 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) { return a; } -#ifdef MODULE -#define FBINFO_DEFAULT FBINFO_MODULE -#else -#define FBINFO_DEFAULT 0 -#endif - -// This will go away -#define FBINFO_FLAG_MODULE FBINFO_MODULE #define FBINFO_FLAG_DEFAULT FBINFO_DEFAULT /* This will go away -- cgit v1.2.3 From ddb4a1442def2a78b91a85b4251fb712ef23662b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Jul 2017 15:25:23 -0700 Subject: exec: Rename bprm->cred_prepared to called_set_creds The cred_prepared bprm flag has a misleading name. It has nothing to do with the bprm_prepare_cred hook, and actually tracks if bprm_set_creds has been called. Rename this flag and improve its comment. Cc: David Howells Cc: Stephen Smalley Cc: Casey Schaufler Signed-off-by: Kees Cook Acked-by: John Johansen Acked-by: James Morris Acked-by: Paul Moore Acked-by: Serge Hallyn --- include/linux/binfmts.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 3ae9013eeaaa..9023e1d2d5cd 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -25,8 +25,12 @@ struct linux_binprm { struct mm_struct *mm; unsigned long p; /* current top of mem */ unsigned int - cred_prepared:1,/* true if creds already prepared (multiple - * preps happen for interpreters) */ + /* + * True after the bprm_set_creds hook has been called once + * (multiple calls can be made via prepare_binprm() for + * binfmt_script/misc). + */ + called_set_creds:1, cap_effective:1;/* true if has elevated effective capabilities, * false if not; except for init which inherits * its parent's caps anyway */ -- cgit v1.2.3 From c425e189ffd7720c881fe9ccd7143cea577f6d03 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Jul 2017 15:25:22 -0700 Subject: binfmt: Introduce secureexec flag The bprm_secureexec hook can be moved earlier. Right now, it is called during create_elf_tables(), via load_binary(), via search_binary_handler(), via exec_binprm(). Nearly all (see exception below) state used by bprm_secureexec is created during the bprm_set_creds hook, called from prepare_binprm(). For all LSMs (except commoncaps described next), only the first execution of bprm_set_creds takes any effect (they all check bprm->called_set_creds which prepare_binprm() sets after the first call to the bprm_set_creds hook). However, all these LSMs also only do anything with bprm_secureexec when they detected a secure state during their first run of bprm_set_creds. Therefore, it is functionally identical to move the detection into bprm_set_creds, since the results from secureexec here only need to be based on the first call to the LSM's bprm_set_creds hook. The single exception is that the commoncaps secureexec hook also examines euid/uid and egid/gid differences which are controlled by bprm_fill_uid(), via prepare_binprm(), which can be called multiple times (e.g. binfmt_script, binfmt_misc), and may clear the euid/egid for the final load (i.e. the script interpreter). However, while commoncaps specifically ignores bprm->cred_prepared, and runs its bprm_set_creds hook each time prepare_binprm() may get called, it needs to base the secureexec decision on the final call to bprm_set_creds. As a result, it will need special handling. To begin this refactoring, this adds the secureexec flag to the bprm struct, and calls the secureexec hook during setup_new_exec(). This is safe since all the cred work is finished (and past the point of no return). This explicit call will be removed in later patches once the hook has been removed. Cc: David Howells Signed-off-by: Kees Cook Reviewed-by: John Johansen Acked-by: Serge Hallyn Reviewed-by: James Morris --- include/linux/binfmts.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 9023e1d2d5cd..16838ba7ee75 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -31,9 +31,15 @@ struct linux_binprm { * binfmt_script/misc). */ called_set_creds:1, - cap_effective:1;/* true if has elevated effective capabilities, + cap_effective:1,/* true if has elevated effective capabilities, * false if not; except for init which inherits * its parent's caps anyway */ + /* + * Set by bprm_set_creds hook to indicate a privilege-gaining + * exec has happened. Used to sanitize execution environment + * and to set AT_SECURE auxv for glibc. + */ + secureexec:1; #ifdef __alpha__ unsigned int taso:1; #endif -- cgit v1.2.3 From 46d98eb4e1d2bc225f661879e0e157a952107598 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Jul 2017 15:25:27 -0700 Subject: commoncap: Refactor to remove bprm_secureexec hook The commoncap implementation of the bprm_secureexec hook is the only LSM that depends on the final call to its bprm_set_creds hook (since it may be called for multiple files, it ignores bprm->called_set_creds). As a result, it cannot safely _clear_ bprm->secureexec since other LSMs may have set it. Instead, remove the bprm_secureexec hook by introducing a new flag to bprm specific to commoncap: cap_elevated. This is similar to cap_effective, but that is used for a specific subset of elevated privileges, and exists solely to track state from bprm_set_creds to bprm_secureexec. As such, it will be removed in the next patch. Here, set the new bprm->cap_elevated flag when setuid/setgid has happened from bprm_fill_uid() or fscapabilities have been prepared. This temporarily moves the bprm_secureexec hook to a static inline. The helper will be removed in the next patch; this makes the step easier to review and bisect, since this does not introduce any changes to inputs nor outputs to the "elevated privileges" calculation. The new flag is merged with the bprm->secureexec flag in setup_new_exec() since this marks the end of any further prepare_binprm() calls. Cc: Andy Lutomirski Signed-off-by: Kees Cook Reviewed-by: Andy Lutomirski Acked-by: James Morris Acked-by: Serge Hallyn --- include/linux/binfmts.h | 7 +++++++ include/linux/security.h | 3 +-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 16838ba7ee75..213c61fa3780 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -34,6 +34,13 @@ struct linux_binprm { cap_effective:1,/* true if has elevated effective capabilities, * false if not; except for init which inherits * its parent's caps anyway */ + /* + * True if most recent call to the commoncaps bprm_set_creds + * hook (due to multiple prepare_binprm() calls from the + * binfmt_script/misc handlers) resulted in elevated + * privileges. + */ + cap_elevated:1, /* * Set by bprm_set_creds hook to indicate a privilege-gaining * exec has happened. Used to sanitize execution environment diff --git a/include/linux/security.h b/include/linux/security.h index b6ea1dc9cc9d..f89832ccdf55 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -85,7 +85,6 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); extern int cap_bprm_set_creds(struct linux_binprm *bprm); -extern int cap_bprm_secureexec(struct linux_binprm *bprm); extern int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); extern int cap_inode_removexattr(struct dentry *dentry, const char *name); @@ -543,7 +542,7 @@ static inline void security_bprm_committed_creds(struct linux_binprm *bprm) static inline int security_bprm_secureexec(struct linux_binprm *bprm) { - return cap_bprm_secureexec(bprm); + return 0; } static inline int security_sb_alloc(struct super_block *sb) -- cgit v1.2.3 From ee67ae7ef6ff499137292ac8a9dfe86096796283 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Jul 2017 15:25:28 -0700 Subject: commoncap: Move cap_elevated calculation into bprm_set_creds Instead of a separate function, open-code the cap_elevated test, which lets us entirely remove bprm->cap_effective (to use the local "effective" variable instead), and more accurately examine euid/egid changes via the existing local "is_setid". The following LTP tests were run to validate the changes: # ./runltp -f syscalls -s cap # ./runltp -f securebits # ./runltp -f cap_bounds # ./runltp -f filecaps All kernel selftests for capabilities and exec continue to pass as well. Signed-off-by: Kees Cook Reviewed-by: James Morris Acked-by: Serge Hallyn Reviewed-by: Andy Lutomirski --- include/linux/binfmts.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 213c61fa3780..fb44d6180ca0 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -31,9 +31,6 @@ struct linux_binprm { * binfmt_script/misc). */ called_set_creds:1, - cap_effective:1,/* true if has elevated effective capabilities, - * false if not; except for init which inherits - * its parent's caps anyway */ /* * True if most recent call to the commoncaps bprm_set_creds * hook (due to multiple prepare_binprm() calls from the -- cgit v1.2.3 From 2af622802696e1dbe28d81c8ea6355dc30800396 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Jul 2017 15:25:29 -0700 Subject: LSM: drop bprm_secureexec hook This removes the bprm_secureexec hook since the logic has been folded into the bprm_set_creds hook for all LSMs now. Cc: Eric W. Biederman Signed-off-by: Kees Cook Reviewed-by: John Johansen Acked-by: James Morris Acked-by: Serge Hallyn --- include/linux/lsm_hooks.h | 14 +++++--------- include/linux/security.h | 6 ------ 2 files changed, 5 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 3a90febadbe2..d1c7bef25691 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -43,7 +43,11 @@ * interpreters. The hook can tell whether it has already been called by * checking to see if @bprm->security is non-NULL. If so, then the hook * may decide either to retain the security information saved earlier or - * to replace it. + * to replace it. The hook must set @bprm->secureexec to 1 if a "secure + * exec" has happened as a result of this hook call. The flag is used to + * indicate the need for a sanitized execution environment, and is also + * passed in the ELF auxiliary table on the initial stack to indicate + * whether libc should enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_check_security: @@ -71,12 +75,6 @@ * linux_binprm structure. This hook is a good place to perform state * changes on the process such as clearing out non-inheritable signal * state. This is called immediately after commit_creds(). - * @bprm_secureexec: - * Return a boolean value (0 or 1) indicating whether a "secure exec" - * is required. The flag is passed in the auxiliary table - * on the initial stack to the ELF interpreter to indicate whether libc - * should enable secure mode. - * @bprm contains the linux_binprm structure. * * Security hooks for filesystem operations. * @@ -1388,7 +1386,6 @@ union security_list_options { int (*bprm_set_creds)(struct linux_binprm *bprm); int (*bprm_check_security)(struct linux_binprm *bprm); - int (*bprm_secureexec)(struct linux_binprm *bprm); void (*bprm_committing_creds)(struct linux_binprm *bprm); void (*bprm_committed_creds)(struct linux_binprm *bprm); @@ -1710,7 +1707,6 @@ struct security_hook_heads { struct list_head vm_enough_memory; struct list_head bprm_set_creds; struct list_head bprm_check_security; - struct list_head bprm_secureexec; struct list_head bprm_committing_creds; struct list_head bprm_committed_creds; struct list_head sb_alloc_security; diff --git a/include/linux/security.h b/include/linux/security.h index f89832ccdf55..974bb9b0996c 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -231,7 +231,6 @@ int security_bprm_set_creds(struct linux_binprm *bprm); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); void security_bprm_committed_creds(struct linux_binprm *bprm); -int security_bprm_secureexec(struct linux_binprm *bprm); int security_sb_alloc(struct super_block *sb); void security_sb_free(struct super_block *sb); int security_sb_copy_data(char *orig, char *copy); @@ -540,11 +539,6 @@ static inline void security_bprm_committed_creds(struct linux_binprm *bprm) { } -static inline int security_bprm_secureexec(struct linux_binprm *bprm) -{ - return 0; -} - static inline int security_sb_alloc(struct super_block *sb) { return 0; -- cgit v1.2.3 From c4b3eacc1dfef5f36dbdf9a99be37834d3e23ed0 Mon Sep 17 00:00:00 2001 From: Alexander Sverdlin Date: Mon, 17 Jul 2017 17:54:07 +0200 Subject: mtd: spi-nor: Recover from Spansion/Cypress errors S25FL{128|256|512}S datasheets say: "When P_ERR or E_ERR bits are set to one, the WIP bit will remain set to one indicating the device remains busy and unable to receive new operation commands. A Clear Status Register (CLSR) command must be received to return the device to standby mode." Current spi-nor code works until first error occurs, but write/erase errors are not just rare hardware failures, they also occur if user tries to flash write-protected areas. After such attempt no SPI command can be executed any more and even read fails. This patch adds support for P_ERR and E_ERR bits in Status Register 1 (so that operation fails immediately and not after a long timeout) and proper recovery from the error condition. Tested on Spansion S25FS128S, which is supported by S25FL129P entry. Signed-off-by: Alexander Sverdlin Signed-off-by: Cyrille Pitchen --- include/linux/mtd/spi-nor.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 0df3638ff0b8..1f0a7fc7772f 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -105,6 +105,7 @@ /* Used for Spansion flashes only. */ #define SPINOR_OP_BRWR 0x17 /* Bank register write */ +#define SPINOR_OP_CLSR 0x30 /* Clear status register 1 */ /* Used for Micron flashes only. */ #define SPINOR_OP_RD_EVCR 0x65 /* Read EVCR register */ @@ -119,6 +120,9 @@ #define SR_BP2 BIT(4) /* Block protect 2 */ #define SR_TB BIT(5) /* Top/Bottom protect */ #define SR_SRWD BIT(7) /* SR write protect */ +/* Spansion/Cypress specific status bits */ +#define SR_E_ERR BIT(5) +#define SR_P_ERR BIT(6) #define SR_QUAD_EN_MX BIT(6) /* Macronix Quad I/O */ @@ -224,6 +228,7 @@ enum spi_nor_option_flags { SNOR_F_NO_OP_CHIP_ERASE = BIT(2), SNOR_F_S3AN_ADDR_DEFAULT = BIT(3), SNOR_F_READY_XSR_RDY = BIT(4), + SNOR_F_USE_CLSR = BIT(5), }; /** -- cgit v1.2.3 From d31ae2548142b7cd12404929ef3a13ae27c9d961 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Aug 2017 12:00:39 -0400 Subject: sunrpc: Const-ify all instances of struct rpc_xprt_ops After transport instance creation, these function pointers never change. Mark them as constant to prevent their use as an attack vector for code injections. Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xprt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index eab1c749e192..f60c55ca2e2e 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -174,7 +174,7 @@ enum xprt_transports { struct rpc_xprt { struct kref kref; /* Reference count */ - struct rpc_xprt_ops * ops; /* transport methods */ + const struct rpc_xprt_ops *ops; /* transport methods */ const struct rpc_timeout *timeout; /* timeout parms */ struct sockaddr_storage addr; /* server address */ -- cgit v1.2.3 From c39a0e2c8850f08249383f2425dbd8dbe4baad69 Mon Sep 17 00:00:00 2001 From: Vikas Shivappa Date: Tue, 25 Jul 2017 14:14:20 -0700 Subject: x86/perf/cqm: Wipe out perf based cqm 'perf cqm' never worked due to the incompatibility between perf infrastructure and cqm hardware support. The hardware uses RMIDs to track the llc occupancy of tasks and these RMIDs are per package. This makes monitoring a hierarchy like cgroup along with monitoring of tasks separately difficult and several patches sent to lkml to fix them were NACKed. Further more, the following issues in the current perf cqm make it almost unusable: 1. No support to monitor the same group of tasks for which we do allocation using resctrl. 2. It gives random and inaccurate data (mostly 0s) once we run out of RMIDs due to issues in Recycling. 3. Recycling results in inaccuracy of data because we cannot guarantee that the RMID was stolen from a task when it was not pulling data into cache or even when it pulled the least data. Also for monitoring llc_occupancy, if we stop using an RMID_x and then start using an RMID_y after we reclaim an RMID from an other event, we miss accounting all the occupancy that was tagged to RMID_x at a later perf_count. 2. Recycling code makes the monitoring code complex including scheduling because the event can lose RMID any time. Since MBM counters count bandwidth for a period of time by taking snap shot of total bytes at two different times, recycling complicates the way we count MBM in a hierarchy. Also we need a spin lock while we do the processing to account for MBM counter overflow. We also currently use a spin lock in scheduling to prevent the RMID from being taken away. 4. Lack of support when we run different kind of event like task, system-wide and cgroup events together. Data mostly prints 0s. This is also because we can have only one RMID tied to a cpu as defined by the cqm hardware but a perf can at the same time tie multiple events during one sched_in. 5. No support of monitoring a group of tasks. There is partial support for cgroup but it does not work once there is a hierarchy of cgroups or if we want to monitor a task in a cgroup and the cgroup itself. 6. No support for monitoring tasks for the lifetime without perf overhead. 7. It reported the aggregate cache occupancy or memory bandwidth over all sockets. But most cloud and VMM based use cases want to know the individual per-socket usage. Signed-off-by: Vikas Shivappa Signed-off-by: Thomas Gleixner Cc: ravi.v.shankar@intel.com Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: vikas.shivappa@intel.com Cc: ak@linux.intel.com Cc: davidcc@google.com Cc: reinette.chatre@intel.com Link: http://lkml.kernel.org/r/1501017287-28083-2-git-send-email-vikas.shivappa@linux.intel.com --- include/linux/perf_event.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a3b873fc59e4..4572dbabd4e8 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -139,14 +139,6 @@ struct hw_perf_event { /* for tp_event->class */ struct list_head tp_list; }; - struct { /* intel_cqm */ - int cqm_state; - u32 cqm_rmid; - int is_group_event; - struct list_head cqm_events_entry; - struct list_head cqm_groups_entry; - struct list_head cqm_group_entry; - }; struct { /* itrace */ int itrace_started; }; @@ -416,11 +408,6 @@ struct pmu { size_t task_ctx_size; - /* - * Return the count value for a counter. - */ - u64 (*count) (struct perf_event *event); /*optional*/ - /* * Set up pmu-private data structures for an AUX area */ @@ -1111,11 +1098,6 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, __perf_event_task_sched_out(prev, next); } -static inline u64 __perf_event_count(struct perf_event *event) -{ - return local64_read(&event->count) + atomic64_read(&event->child_count); -} - extern void perf_event_mmap(struct vm_area_struct *vma); extern struct perf_guest_info_callbacks *perf_guest_cbs; extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); -- cgit v1.2.3 From f01d7d51f577b5dc0fa5919ab8a9228e2bf49f3e Mon Sep 17 00:00:00 2001 From: Vikas Shivappa Date: Tue, 25 Jul 2017 14:14:22 -0700 Subject: x86/intel_rdt: Introduce a common compile option for RDT We currently have a CONFIG_RDT_A which is for RDT(Resource directory technology) allocation based resctrl filesystem interface. As a preparation to add support for RDT monitoring as well into the same resctrl filesystem, change the config option to be CONFIG_RDT which would include both RDT allocation and monitoring code. No functional change. Signed-off-by: Vikas Shivappa Signed-off-by: Thomas Gleixner Cc: ravi.v.shankar@intel.com Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: vikas.shivappa@intel.com Cc: ak@linux.intel.com Cc: davidcc@google.com Cc: reinette.chatre@intel.com Link: http://lkml.kernel.org/r/1501017287-28083-4-git-send-email-vikas.shivappa@linux.intel.com --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8337e2db0bb2..20b2ff2f4fde 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -898,7 +898,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_INTEL_RDT_A +#ifdef CONFIG_INTEL_RDT int closid; #endif #ifdef CONFIG_FUTEX -- cgit v1.2.3 From 0734ded1abee9439b0c5d7b62af1ead78aab895b Mon Sep 17 00:00:00 2001 From: Vikas Shivappa Date: Tue, 25 Jul 2017 14:14:33 -0700 Subject: x86/intel_rdt: Change closid type from int to u32 OS associates a CLOSid(Class of service id) to a task by writing the high 32 bits of per CPU IA32_PQR_ASSOC MSR when a task is scheduled in. CPUID.(EAX=10H, ECX=1):EDX[15:0] enumerates the max CLOSID supported and it is zero indexed. Hence change the type to u32 from int. Signed-off-by: Vikas Shivappa Signed-off-by: Thomas Gleixner Cc: ravi.v.shankar@intel.com Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: vikas.shivappa@intel.com Cc: ak@linux.intel.com Cc: davidcc@google.com Cc: reinette.chatre@intel.com Link: http://lkml.kernel.org/r/1501017287-28083-15-git-send-email-vikas.shivappa@linux.intel.com --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 20b2ff2f4fde..8839fd09540c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -899,7 +899,7 @@ struct task_struct { struct list_head cg_list; #endif #ifdef CONFIG_INTEL_RDT - int closid; + u32 closid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; -- cgit v1.2.3 From d6aaba615a482ce7d3ec218cf7b8d02d0d5753b8 Mon Sep 17 00:00:00 2001 From: Vikas Shivappa Date: Tue, 25 Jul 2017 14:14:34 -0700 Subject: x86/intel_rdt/cqm: Add tasks file support The root directory, ctrl_mon and monitor groups are populated with a read/write file named "tasks". When read, it shows all the task IDs assigned to the resource group. Tasks can be added to groups by writing the PID to the file. A task can be present in one "ctrl_mon" group "and" one "monitor" group. IOW a PID_x can be seen in a ctrl_mon group and a monitor group at the same time. When a task is added to a ctrl_mon group, it is automatically removed from the previous ctrl_mon group where it belonged. Similarly if a task is moved to a monitor group it is removed from the previous monitor group . Also since the monitor groups can only have subset of tasks of parent ctrl_mon group, a task can be moved to a monitor group only if its already present in the parent ctrl_mon group. Task membership is indicated by a new field in the task_struct "u32 rmid" which holds the RMID for the task. RMID=0 is reserved for the default root group where the tasks belong to at mount. [tony: zero the rmid if rdtgroup was deleted when task was being moved] Signed-off-by: Tony Luck Signed-off-by: Vikas Shivappa Signed-off-by: Thomas Gleixner Cc: ravi.v.shankar@intel.com Cc: tony.luck@intel.com Cc: fenghua.yu@intel.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: vikas.shivappa@intel.com Cc: ak@linux.intel.com Cc: davidcc@google.com Cc: reinette.chatre@intel.com Link: http://lkml.kernel.org/r/1501017287-28083-16-git-send-email-vikas.shivappa@linux.intel.com --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8839fd09540c..067a41ac5fd4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -900,6 +900,7 @@ struct task_struct { #endif #ifdef CONFIG_INTEL_RDT u32 closid; + u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; -- cgit v1.2.3 From 306b13eb3cf9515a8214bbf5d69d811371d05792 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 28 Jul 2017 16:22:41 -0700 Subject: proto_ops: Add locked held versions of sendmsg and sendpage Add new proto_ops sendmsg_locked and sendpage_locked that can be called when the socket lock is already held. Correspondingly, add kernel_sendmsg_locked and kernel_sendpage_locked as front end functions. These functions will be used in zero proxy so that we can take the socket lock in a ULP sendmsg/sendpage and then directly call the backend transport proto_ops functions. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/net.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index dda2cc939a53..b5c15b31709b 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -190,8 +190,16 @@ struct proto_ops { struct pipe_inode_info *pipe, size_t len, unsigned int flags); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); + + /* The following functions are called internally by kernel with + * sock lock already held. + */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); + int (*sendpage_locked)(struct sock *sk, struct page *page, + int offset, size_t size, int flags); + int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, + size_t size); }; #define DECLARE_SOCKADDR(type, dst, src) \ @@ -279,6 +287,8 @@ do { \ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); +int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, + struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); @@ -297,6 +307,8 @@ int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); +int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, + size_t size, int flags); int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); -- cgit v1.2.3 From 20bf50de3028cb15fa81e1d1e63ab6e0c85257fc Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 28 Jul 2017 16:22:42 -0700 Subject: skbuff: Function to send an skbuf on a socket Add skb_send_sock to send an skbuff on a socket within the kernel. Arguments include an offset so that an skbuf might be sent in mulitple calls (e.g. send buffer limit is hit). Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4093552be1de..18e76bf9574e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3113,6 +3113,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); +int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, + int len); +int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, -- cgit v1.2.3 From c613c209c3f351d47158f728271d0c73b6dd24c6 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 31 Jul 2017 08:15:47 -0400 Subject: net: add skb_frag_foreach_page and use with kmap_atomic Skb frags may contain compound pages. Various operations map frags temporarily using kmap_atomic, but this function works on single pages, not whole compound pages. The distinction is only relevant for high mem pages that require temporary mappings. Introduce a looping mechanism that for compound highmem pages maps one page at a time, does not change behavior on other pages. Use the loop in the kmap_atomic callers in net/core/skbuff.c. Verified by triggering skb_copy_bits with tcpdump -n -c 100 -i ${DEV} -w /dev/null & netperf -t TCP_STREAM -H ${HOST} and by triggering __skb_checksum with ethtool -K ${DEV} tx off repeated the tests with looping on a non-highmem platform (x86_64) by making skb_frag_must_loop always return true. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 18e76bf9574e..6f9f1b2715ec 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -345,6 +345,42 @@ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) frag->size -= delta; } +static inline bool skb_frag_must_loop(struct page *p) +{ +#if defined(CONFIG_HIGHMEM) + if (PageHighMem(p)) + return true; +#endif + return false; +} + +/** + * skb_frag_foreach_page - loop over pages in a fragment + * + * @f: skb frag to operate on + * @f_off: offset from start of f->page.p + * @f_len: length from f_off to loop over + * @p: (temp var) current page + * @p_off: (temp var) offset from start of current page, + * non-zero only on first page. + * @p_len: (temp var) length in current page, + * < PAGE_SIZE only on first and last page. + * @copied: (temp var) length so far, excluding current p_len. + * + * A fragment can hold a compound page, in which case per-page + * operations, notably kmap_atomic, must be called for each + * regular page. + */ +#define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ + for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ + p_off = (f_off) & (PAGE_SIZE - 1), \ + p_len = skb_frag_must_loop(p) ? \ + min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ + copied = 0; \ + copied < f_len; \ + copied += p_len, p++, p_off = 0, \ + p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ + #define HAVE_HW_TIME_STAMP /** -- cgit v1.2.3 From 581c4484769e692eade761c17c22549aaefe6749 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Tue, 1 Aug 2017 15:38:01 -0700 Subject: HID: input: map digitizer battery usage We already mapped battery strength reports from the generic device control page, but we did not update capacity from input reports, nor we mapped the battery strength report from the digitizer page, so let's implement this now. Batteries driven by the input reports will now start in "unknown" state, and will get updated once we receive first report containing battery strength from the device. Signed-off-by: Dmitry Torokhov Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 5006f9b5d837..281d1ffcbe02 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -542,10 +542,12 @@ struct hid_device { /* device report descriptor */ * battery is non-NULL. */ struct power_supply *battery; + __s32 battery_capacity; __s32 battery_min; __s32 battery_max; __s32 battery_report_type; __s32 battery_report_id; + bool battery_reported; #endif unsigned int status; /* see STAT flags above */ -- cgit v1.2.3 From b2f9d432deebab5096aad5942c2f2b1ec2865f5a Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Tue, 1 Aug 2017 13:18:09 -0700 Subject: flow_dissector: remove unused functions They are introduced by commit f70ea018da06 ("net: Add functions to get skb->hash based on flow structures") but never gets used in tree. Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/linux/skbuff.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f9f1b2715ec..be76082f48aa 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1158,8 +1158,6 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->hash; } -__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6); - static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { @@ -1172,20 +1170,6 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 return skb->hash; } -__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl); - -static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4) -{ - if (!skb->l4_hash && !skb->sw_hash) { - struct flow_keys keys; - __u32 hash = __get_hash_from_flowi4(fl4, &keys); - - __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); - } - - return skb->hash; -} - __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) -- cgit v1.2.3 From 0679dee03c6d706d57145ea92c23d08fa10a1999 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 2 Aug 2017 17:55:29 +0100 Subject: cgroup: keep track of number of descent cgroups Keep track of the number of online and dying descent cgroups. This data will be used later to add an ability to control cgroup hierarchy (limit the depth and the number of descent cgroups) and display hierarchy stats. Signed-off-by: Roman Gushchin Suggested-by: Tejun Heo Signed-off-by: Tejun Heo Cc: Zefan Li Cc: Waiman Long Cc: Johannes Weiner Cc: kernel-team@fb.com Cc: cgroups@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- include/linux/cgroup-defs.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 9d741959f218..58b4c425a155 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -273,6 +273,14 @@ struct cgroup { */ int level; + /* + * Keep track of total numbers of visible and dying descent cgroups. + * Dying cgroups are cgroups which were deleted by a user, + * but are still existing because someone else is holding a reference. + */ + int nr_descendants; + int nr_dying_descendants; + /* * Each non-empty css_set associated with this cgroup contributes * one to nr_populated_csets. The counter is zero iff this cgroup -- cgit v1.2.3 From 1a926e0bbab83bae8207d05a533173425e0496d1 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Jul 2017 18:28:44 +0100 Subject: cgroup: implement hierarchy limits Creating cgroup hierearchies of unreasonable size can affect overall system performance. A user might want to limit the size of cgroup hierarchy. This is especially important if a user is delegating some cgroup sub-tree. To address this issue, introduce an ability to control the size of cgroup hierarchy. The cgroup.max.descendants control file allows to set the maximum allowed number of descendant cgroups. The cgroup.max.depth file controls the maximum depth of the cgroup tree. Both are single value r/w files, with "max" default value. The control files exist on each hierarchy level (including root). When a new cgroup is created, we check the total descendants and depth limits on each level, and if none of them are exceeded, a new cgroup is created. Only alive cgroups are counted, removed (dying) cgroups are ignored. Signed-off-by: Roman Gushchin Suggested-by: Tejun Heo Signed-off-by: Tejun Heo Cc: Zefan Li Cc: Waiman Long Cc: Johannes Weiner Cc: kernel-team@fb.com Cc: cgroups@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- include/linux/cgroup-defs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 58b4c425a155..59e4ad9e7bac 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -273,13 +273,18 @@ struct cgroup { */ int level; + /* Maximum allowed descent tree depth */ + int max_depth; + /* * Keep track of total numbers of visible and dying descent cgroups. * Dying cgroups are cgroups which were deleted by a user, * but are still existing because someone else is holding a reference. + * max_descendants is a maximum allowed number of descent cgroups. */ int nr_descendants; int nr_dying_descendants; + int max_descendants; /* * Each non-empty css_set associated with this cgroup contributes -- cgit v1.2.3 From 1e140df0496541c473e5d40b0da5d2d626b2e343 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 24 Jul 2017 22:56:43 -0700 Subject: remoteproc: qcom: Add support for SSR notifications This adds the remoteproc part of subsystem restart, which is responsible for emitting notifications to other processors in the system about a dying remoteproc instance. These notifications are propagated to the various communication systems in the various remote processors to shut down communication links that was left in a dangling state as the remoteproc was stopped (or crashed). Signed-off-by: Bjorn Andersson --- include/linux/remoteproc/qcom_rproc.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 include/linux/remoteproc/qcom_rproc.h (limited to 'include/linux') diff --git a/include/linux/remoteproc/qcom_rproc.h b/include/linux/remoteproc/qcom_rproc.h new file mode 100644 index 000000000000..fa8e38681b4b --- /dev/null +++ b/include/linux/remoteproc/qcom_rproc.h @@ -0,0 +1,22 @@ +#ifndef __QCOM_RPROC_H__ +#define __QCOM_RPROC_H__ + +struct notifier_block; + +#if IS_ENABLED(CONFIG_QCOM_RPROC_COMMON) + +int qcom_register_ssr_notifier(struct notifier_block *nb); +void qcom_unregister_ssr_notifier(struct notifier_block *nb); + +#else + +static inline int qcom_register_ssr_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline void qcom_unregister_ssr_notifier(struct notifier_block *nb) {} + +#endif + +#endif -- cgit v1.2.3 From 957b8dffa4e3d191f0f1571d006d0e520790dcb9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jo=C3=A3o=20Paulo=20Rechi=20Vita?= Date: Mon, 24 Jul 2017 14:22:25 -0700 Subject: HID: multitouch: Support Asus T304UA media keys MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Asus T304UA convertible sports a magnetic detachable keyboard with touchpad, which is connected over USB. Most of the keyboard hotkeys are exposed through the same USB interface as the touchpad, defined in the report descriptor as follows: 0x06, 0x31, 0xFF, // Usage Page (Vendor Defined 0xFF31) 0x09, 0x76, // Usage (0x76) 0xA1, 0x01, // Collection (Application) 0x05, 0xFF, // Usage Page (Reserved 0xFF) 0x85, 0x5A, // Report ID (90) 0x19, 0x00, // Usage Minimum (0x00) 0x2A, 0xFF, 0x00, // Usage Maximum (0xFF) 0x15, 0x00, // Logical Minimum (0) 0x26, 0xFF, 0x00, // Logical Maximum (255) 0x75, 0x08, // Report Size (8) 0x95, 0x0F, // Report Count (15) 0xB1, 0x02, // Feature (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position,Non-volatile) 0x05, 0xFF, // Usage Page (Reserved 0xFF) 0x85, 0x5A, // Report ID (90) 0x19, 0x00, // Usage Minimum (0x00) 0x2A, 0xFF, 0x00, // Usage Maximum (0xFF) 0x15, 0x00, // Logical Minimum (0) 0x26, 0xFF, 0x00, // Logical Maximum (255) 0x75, 0x08, // Report Size (8) 0x95, 0x02, // Report Count (2) 0x81, 0x02, // Input (Data,Var,Abs,No Wrap,Linear,Preferred State,No Null Position) 0xC0, // End Collection This UsagePage is declared as a variable, but we need to treat it as an array to be able to map each Usage we care about to its corresponding input key. Signed-off-by: João Paulo Rechi Vita Signed-off-by: Jiri Kosina --- include/linux/hid.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 5006f9b5d837..a08e6b15d98d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -173,6 +173,7 @@ struct hid_item { #define HID_UP_LOGIVENDOR3 0xff430000 #define HID_UP_LNVENDOR 0xffa00000 #define HID_UP_SENSOR 0x00200000 +#define HID_UP_ASUSVENDOR 0xff310000 #define HID_USAGE 0x0000ffff @@ -292,6 +293,7 @@ struct hid_item { #define HID_DG_BARRELSWITCH2 0x000d005a #define HID_DG_TOOLSERIALNUMBER 0x000d005b +#define HID_VD_ASUS_CUSTOM_MEDIA_KEYS 0xff310076 /* * HID report types --- Ouch! HID spec says 1 2 3! */ -- cgit v1.2.3 From d4cb37e71662dac72049bf7c55a9038bd7d2bcb5 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Tue, 16 May 2017 00:17:42 +0200 Subject: mtd: nand: Remove support for block locking/unlocking Commit 7d70f334ad2b ("mtd: nand: add lock/unlock routines") introduced support for the Micron LOCK/UNLOCK commands but no one ever used the nand_lock/unlock() functions. Remove support for these vendor-specific operations from the core. If one ever wants to add them back they should be put in nand_micron.c and mtd->_lock/_unlock should be directly assigned from there instead of exporting the functions. Signed-off-by: Boris Brezillon --- include/linux/mtd/nand.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 892148c448cc..8a6522e82f03 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -44,12 +44,6 @@ void nand_release(struct mtd_info *mtd); /* Internal helper for board drivers which need to override command function */ void nand_wait_ready(struct mtd_info *mtd); -/* locks all blocks present in the device */ -int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len); - -/* unlocks specified locked blocks */ -int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); - /* The maximum number of NAND chips in an array */ #define NAND_MAX_CHIPS 8 @@ -89,10 +83,6 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_CMD_SET_FEATURES 0xef #define NAND_CMD_RESET 0xff -#define NAND_CMD_LOCK 0x2a -#define NAND_CMD_UNLOCK1 0x23 -#define NAND_CMD_UNLOCK2 0x24 - /* Extended commands for large page devices */ #define NAND_CMD_READSTART 0x30 #define NAND_CMD_RNDOUTSTART 0xE0 -- cgit v1.2.3 From e61e4055b165f4c645ce2a85890b313abf841f67 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:09 +0800 Subject: sctp: remove the typedef sctp_shutdownhdr_t This patch is to remove the typedef sctp_shutdownhdr_t, and replace with struct sctp_shutdownhdr in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index ba007163acfd..7a586ba7dcd4 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -416,13 +416,13 @@ struct sctp_abort_chunk { /* For the graceful shutdown we must carry the tag (in common header) * and the highest consecutive acking value. */ -typedef struct sctp_shutdownhdr { +struct sctp_shutdownhdr { __be32 cum_tsn_ack; -} sctp_shutdownhdr_t; +}; struct sctp_shutdown_chunk_t { struct sctp_chunkhdr chunk_hdr; - sctp_shutdownhdr_t shutdown_hdr; + struct sctp_shutdownhdr shutdown_hdr; }; /* RFC 2960. Section 3.3.10 Operation Error (ERROR) (9) */ -- cgit v1.2.3 From ac23e68133f4570f40ec0910286ced08ced2d378 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:10 +0800 Subject: sctp: fix the name of struct sctp_shutdown_chunk_t This patch is to fix the name of struct sctp_shutdown_chunk_t , replace with struct sctp_initack_chunk in the places where it's using it. It is also to fix some indent problem. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 7a586ba7dcd4..553020cbf6f7 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -420,7 +420,7 @@ struct sctp_shutdownhdr { __be32 cum_tsn_ack; }; -struct sctp_shutdown_chunk_t { +struct sctp_shutdown_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_shutdownhdr shutdown_hdr; }; -- cgit v1.2.3 From d8238d9dab8fbea22dd04f4e77639c7f7b83eef7 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:11 +0800 Subject: sctp: remove the typedef sctp_errhdr_t This patch is to remove the typedef sctp_errhdr_t, and replace with struct sctp_errhdr in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 553020cbf6f7..d35bdd30fa0f 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -427,15 +427,15 @@ struct sctp_shutdown_chunk { /* RFC 2960. Section 3.3.10 Operation Error (ERROR) (9) */ -typedef struct sctp_errhdr { +struct sctp_errhdr { __be16 cause; __be16 length; __u8 variable[0]; -} sctp_errhdr_t; +}; typedef struct sctp_operr_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_errhdr_t err_hdr; + struct sctp_errhdr err_hdr; } sctp_operr_chunk_t; /* RFC 2960 3.3.10 - Operation Error -- cgit v1.2.3 From 87caeba7914979ef6a5765dfa3163b51a30133ab Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:12 +0800 Subject: sctp: remove the typedef sctp_operr_chunk_t This patch is to remove the typedef sctp_operr_chunk_t, and replace with struct sctp_operr_chunk in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index d35bdd30fa0f..07c12e98fa85 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -433,10 +433,10 @@ struct sctp_errhdr { __u8 variable[0]; }; -typedef struct sctp_operr_chunk { +struct sctp_operr_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_errhdr err_hdr; -} sctp_operr_chunk_t; +}; /* RFC 2960 3.3.10 - Operation Error * -- cgit v1.2.3 From 2a4932167772874c5bc4b3dfebf61cfadb5554b9 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:13 +0800 Subject: sctp: remove the typedef sctp_error_t This patch is to remove the typedef sctp_error_t, and replace with enum sctp_error in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 07c12e98fa85..c74ea93e36eb 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -457,7 +457,7 @@ struct sctp_operr_chunk { * 9 No User Data * 10 Cookie Received While Shutting Down */ -typedef enum { +enum sctp_error { SCTP_ERROR_NO_ERROR = cpu_to_be16(0x00), SCTP_ERROR_INV_STRM = cpu_to_be16(0x01), @@ -512,7 +512,7 @@ typedef enum { * 0x0105 Unsupported HMAC Identifier */ SCTP_ERROR_UNSUP_HMAC = cpu_to_be16(0x0105) -} sctp_error_t; +}; -- cgit v1.2.3 From 1fb6d83bd37dc7d0949b8a8005f7c24dddc3ee1e Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:14 +0800 Subject: sctp: remove the typedef sctp_ecnehdr_t This patch is to remove the typedef sctp_ecnehdr_t, and replace with struct sctp_ecnehdr in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index c74ea93e36eb..5ea739b99f8d 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -519,13 +519,13 @@ enum sctp_error { /* RFC 2960. Appendix A. Explicit Congestion Notification. * Explicit Congestion Notification Echo (ECNE) (12) */ -typedef struct sctp_ecnehdr { +struct sctp_ecnehdr { __be32 lowest_tsn; -} sctp_ecnehdr_t; +}; typedef struct sctp_ecne_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_ecnehdr_t ence_hdr; + struct sctp_ecnehdr ence_hdr; } sctp_ecne_chunk_t; /* RFC 2960. Appendix A. Explicit Congestion Notification. -- cgit v1.2.3 From b515fd27591dea06bc9f0178fba361b43b76ab6b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:15 +0800 Subject: sctp: remove the typedef sctp_ecne_chunk_t This patch is to remove the typedef sctp_ecne_chunk_t, and replace with struct sctp_ecne_chunk in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 5ea739b99f8d..026bbdfcaf44 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -523,10 +523,10 @@ struct sctp_ecnehdr { __be32 lowest_tsn; }; -typedef struct sctp_ecne_chunk { +struct sctp_ecne_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_ecnehdr ence_hdr; -} sctp_ecne_chunk_t; +}; /* RFC 2960. Appendix A. Explicit Congestion Notification. * Congestion Window Reduced (CWR) (13) -- cgit v1.2.3 From 65f77105438a7793836d7ba2d9a05fa585b8caf9 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:16 +0800 Subject: sctp: remove the typedef sctp_cwrhdr_t This patch is to remove the typedef sctp_cwrhdr_t, and replace with struct sctp_cwrhdr in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 026bbdfcaf44..3c8c418425e6 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -531,13 +531,13 @@ struct sctp_ecne_chunk { /* RFC 2960. Appendix A. Explicit Congestion Notification. * Congestion Window Reduced (CWR) (13) */ -typedef struct sctp_cwrhdr { +struct sctp_cwrhdr { __be32 lowest_tsn; -} sctp_cwrhdr_t; +}; typedef struct sctp_cwr_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_cwrhdr_t cwr_hdr; + struct sctp_cwrhdr cwr_hdr; } sctp_cwr_chunk_t; /* PR-SCTP -- cgit v1.2.3 From 05b25d0ba68d5b6d5d06f7c6cc3fec49ffa2df38 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:17 +0800 Subject: sctp: remove the typedef sctp_cwr_chunk_t Remove this typedef including the struct, there is even no places using it. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 3c8c418425e6..2a97639eb035 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -535,11 +535,6 @@ struct sctp_cwrhdr { __be32 lowest_tsn; }; -typedef struct sctp_cwr_chunk { - struct sctp_chunkhdr chunk_hdr; - struct sctp_cwrhdr cwr_hdr; -} sctp_cwr_chunk_t; - /* PR-SCTP * 3.2 Forward Cumulative TSN Chunk Definition (FORWARD TSN) * -- cgit v1.2.3 From 8b32f2348a0441ef202562618b13d1bb494f3a47 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:18 +0800 Subject: sctp: remove the typedef sctp_addip_param_t This patch is to remove the typedef sctp_addip_param_t, and replace with struct sctp_addip_param in the places where it's using this typedef. It is to use sizeof(variable) instead of sizeof(type), and also fix some indent problems. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 2a97639eb035..5b7d6d9d3fc5 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -629,10 +629,10 @@ struct sctp_fwdtsn_chunk { * The ASCONF Parameter Response is used in the ASCONF-ACK to * report status of ASCONF processing. */ -typedef struct sctp_addip_param { - struct sctp_paramhdr param_hdr; - __be32 crr_id; -} sctp_addip_param_t; +struct sctp_addip_param { + struct sctp_paramhdr param_hdr; + __be32 crr_id; +}; typedef struct sctp_addiphdr { __be32 serial; -- cgit v1.2.3 From 65205cc465e9b37abbdbb3d595c46081b97e35bc Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:19 +0800 Subject: sctp: remove the typedef sctp_addiphdr_t This patch is to remove the typedef sctp_addiphdr_t, and replace with struct sctp_addiphdr in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 5b7d6d9d3fc5..83dac9b0b4bd 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -634,14 +634,14 @@ struct sctp_addip_param { __be32 crr_id; }; -typedef struct sctp_addiphdr { +struct sctp_addiphdr { __be32 serial; __u8 params[0]; -} sctp_addiphdr_t; +}; typedef struct sctp_addip_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_addiphdr_t addip_hdr; + struct sctp_addiphdr addip_hdr; } sctp_addip_chunk_t; /* AUTH -- cgit v1.2.3 From 68d75469468620c37cd58dc352f1dcec8c3896b6 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:20 +0800 Subject: sctp: remove the typedef sctp_addip_chunk_t This patch is to remove the typedef sctp_addip_chunk_t, and replace with struct sctp_addip_chunk in the places where it's using this typedef. Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 83dac9b0b4bd..e7b439ed6371 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -639,10 +639,10 @@ struct sctp_addiphdr { __u8 params[0]; }; -typedef struct sctp_addip_chunk { +struct sctp_addip_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_addiphdr addip_hdr; -} sctp_addip_chunk_t; +}; /* AUTH * Section 4.1 Authentication Chunk (AUTH) -- cgit v1.2.3 From 96f7ef4d58100d7168e0c4d01a59fbd8589f5756 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:21 +0800 Subject: sctp: remove the typedef sctp_authhdr_t This patch is to remove the typedef sctp_authhdr_t, and replace with struct sctp_authhdr in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index e7b439ed6371..b7603f5efebe 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -693,15 +693,15 @@ struct sctp_addip_chunk { * HMAC: n bytes (unsigned integer) This hold the result of the HMAC * calculation. */ -typedef struct sctp_authhdr { +struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; __u8 hmac[0]; -} sctp_authhdr_t; +}; typedef struct sctp_auth_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_authhdr_t auth_hdr; + struct sctp_authhdr auth_hdr; } sctp_auth_chunk_t; struct sctp_infox { -- cgit v1.2.3 From bb96dec74543bb3ceb4ac5caf39341dadb4cb559 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 3 Aug 2017 15:42:22 +0800 Subject: sctp: remove the typedef sctp_auth_chunk_t This patch is to remove the typedef sctp_auth_chunk_t, and replace with struct sctp_auth_chunk in the places where it's using this typedef. It is also to use sizeof(variable) instead of sizeof(type). Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/linux/sctp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index b7603f5efebe..82b171e1aa0b 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -699,10 +699,10 @@ struct sctp_authhdr { __u8 hmac[0]; }; -typedef struct sctp_auth_chunk { +struct sctp_auth_chunk { struct sctp_chunkhdr chunk_hdr; struct sctp_authhdr auth_hdr; -} sctp_auth_chunk_t; +}; struct sctp_infox { struct sctp_info *sctpinfo; -- cgit v1.2.3 From 630b3aff8a51c90ef15b59c9560ac35e40e7ec09 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 1 Aug 2017 14:10:41 +0200 Subject: treewide: Consolidate Apple DMI checks We're about to amend ACPI bus scan with DMI checks whether we're running on a Mac to support Apple device properties in AML. The DMI checks are performed for every single device, adding overhead for everything x86 that isn't Apple, which is the majority. Rafael and Andy therefore request to perform the DMI match only once and cache the result. Outside of ACPI various other Apple DMI checks exist and it seems reasonable to use the cached value there as well. Rafael, Andy and Darren suggest performing the DMI check in arch code and making it available with a header in include/linux/platform_data/x86/. To this end, add early_platform_quirks() to arch/x86/kernel/quirks.c to perform the DMI check and invoke it from setup_arch(). Switch over all existing Apple DMI checks, thereby fixing two deficiencies: * They are now #defined to false on non-x86 arches and can thus be optimized away if they're located in cross-arch code. * Some of them only match "Apple Inc." but not "Apple Computer, Inc.", which is used by BIOSes released between January 2006 (when the first x86 Macs started shipping) and January 2007 (when the company name changed upon introduction of the iPhone). Suggested-by: Andy Shevchenko Suggested-by: Rafael J. Wysocki Suggested-by: Darren Hart Signed-off-by: Lukas Wunner Acked-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- include/linux/platform_data/x86/apple.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 include/linux/platform_data/x86/apple.h (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/apple.h b/include/linux/platform_data/x86/apple.h new file mode 100644 index 000000000000..079e816c3c21 --- /dev/null +++ b/include/linux/platform_data/x86/apple.h @@ -0,0 +1,13 @@ +#ifndef PLATFORM_DATA_X86_APPLE_H +#define PLATFORM_DATA_X86_APPLE_H + +#ifdef CONFIG_X86 +/** + * x86_apple_machine - whether the machine is an x86 Apple Macintosh + */ +extern bool x86_apple_machine; +#else +#define x86_apple_machine false +#endif + +#endif -- cgit v1.2.3 From 004cb784018eaa2a078912180bd9999707c3c483 Mon Sep 17 00:00:00 2001 From: Matthew Minter Date: Mon, 31 Jul 2017 17:37:57 +0100 Subject: PCI: Remove unused pci_fixup_irqs() function Now we have removed all callers of pci_fixup_irqs() and migrated everything to pci_assign_irq(), delete the pci_fixup_irqs() function completely. Signed-off-by: Matthew Minter [lorenzo.pieralisi@arm.com: updated commit log] Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659..69034ab8a68e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1160,8 +1160,6 @@ void pci_assign_unassigned_bus_resources(struct pci_bus *bus); void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus); void pdev_enable_device(struct pci_dev *); int pci_enable_resources(struct pci_dev *, int mask); -void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *), - int (*)(const struct pci_dev *, u8, u8)); void pci_assign_irq(struct pci_dev *dev); struct resource *pci_find_resource(struct pci_dev *dev, struct resource *res); #define HAVE_PCI_REQ_REGIONS 2 -- cgit v1.2.3 From e652399edba99a5497f0d80f240c9075d3b43493 Mon Sep 17 00:00:00 2001 From: Gary R Hook Date: Tue, 25 Jul 2017 14:12:11 -0500 Subject: crypto: ccp - Fix XTS-AES-128 support on v5 CCPs Version 5 CCPs have some new requirements for XTS-AES: the type field must be specified, and the key requires 512 bits, with each part occupying 256 bits and padded with zeroes. cc: # 4.9.x+ Signed-off-by: Gary R Hook Signed-off-by: Herbert Xu --- include/linux/ccp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ccp.h b/include/linux/ccp.h index 3fd9a6dac344..7e9c991c95e0 100644 --- a/include/linux/ccp.h +++ b/include/linux/ccp.h @@ -1,7 +1,7 @@ /* * AMD Cryptographic Coprocessor (CCP) driver * - * Copyright (C) 2013,2016 Advanced Micro Devices, Inc. + * Copyright (C) 2013,2017 Advanced Micro Devices, Inc. * * Author: Tom Lendacky * Author: Gary R Hook @@ -229,6 +229,7 @@ enum ccp_xts_aes_unit_size { * AES operation the new IV overwrites the old IV. */ struct ccp_xts_aes_engine { + enum ccp_aes_type type; enum ccp_aes_action action; enum ccp_xts_aes_unit_size unit_size; -- cgit v1.2.3 From 704956ecf5bcdc14d14650f39f2b545b34c96265 Mon Sep 17 00:00:00 2001 From: Chao Yu Date: Mon, 31 Jul 2017 20:19:09 +0800 Subject: f2fs: support inode checksum This patch adds to support inode checksum in f2fs. Signed-off-by: Chao Yu [Jaegeuk Kim: fix verification flow] Signed-off-by: Jaegeuk Kim --- include/linux/f2fs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 50f176683676..2a0c453d7235 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -240,6 +240,7 @@ struct f2fs_inode { __le16 i_extra_isize; /* extra inode attribute size */ __le16 i_padding; /* padding */ __le32 i_projid; /* project id */ + __le32 i_inode_checksum;/* inode meta checksum */ __le32 i_extra_end[0]; /* for attribute size calculation */ }; __le32 i_addr[DEF_ADDRS_PER_INODE]; /* Pointers to data blocks */ -- cgit v1.2.3 From 3ece782693c4b64d588dd217868558ab9a19bfe7 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 3 Aug 2017 16:29:38 -0400 Subject: sock: skb_copy_ubufs support for compound pages Refine skb_copy_ubufs to support compound pages. With upcoming TCP zerocopy sendmsg, such fragments may appear. The existing code replaces each page one for one. Splitting each compound page into an independent number of regular pages can result in exceeding limit MAX_SKB_FRAGS if data is not exactly page aligned. Instead, fill all destination pages but the last to PAGE_SIZE. Split the existing alloc + copy loop into separate stages: 1. compute bytelength and minimum number of pages to store this. 2. allocate 3. copy, filling each page except the last to PAGE_SIZE bytes 4. update skb frag array Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index be76082f48aa..2f64e2bbb592 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1796,13 +1796,18 @@ static inline unsigned int skb_headlen(const struct sk_buff *skb) return skb->len - skb->data_len; } -static inline unsigned int skb_pagelen(const struct sk_buff *skb) +static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); - return len + skb_headlen(skb); + return len; +} + +static inline unsigned int skb_pagelen(const struct sk_buff *skb) +{ + return skb_headlen(skb) + __skb_pagelen(skb); } /** -- cgit v1.2.3 From 52267790ef52d7513879238ca9fac22c1733e0e3 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 3 Aug 2017 16:29:39 -0400 Subject: sock: add MSG_ZEROCOPY The kernel supports zerocopy sendmsg in virtio and tap. Expand the infrastructure to support other socket types. Introduce a completion notification channel over the socket error queue. Notifications are returned with ee_origin SO_EE_ORIGIN_ZEROCOPY. ee_errno is 0 to avoid blocking the send/recv path on receiving notifications. Add reference counting, to support the skb split, merge, resize and clone operations possible with SOCK_STREAM and other socket types. The patch does not yet modify any datapaths. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/socket.h | 1 + 2 files changed, 61 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2f64e2bbb592..59cff7aa494e 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -429,6 +429,7 @@ enum { SKBTX_SCHED_TSTAMP = 1 << 6, }; +#define SKBTX_ZEROCOPY_FRAG (SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) @@ -445,8 +446,28 @@ struct ubuf_info { void (*callback)(struct ubuf_info *, bool zerocopy_success); void *ctx; unsigned long desc; + u16 zerocopy:1; + atomic_t refcnt; }; +#define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) + +struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); + +static inline void sock_zerocopy_get(struct ubuf_info *uarg) +{ + atomic_inc(&uarg->refcnt); +} + +void sock_zerocopy_put(struct ubuf_info *uarg); +void sock_zerocopy_put_abort(struct ubuf_info *uarg); + +void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg); + /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -1214,6 +1235,45 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) return &skb_shinfo(skb)->hwtstamps; } +static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) +{ + bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY; + + return is_zcopy ? skb_uarg(skb) : NULL; +} + +static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) +{ + if (skb && uarg && !skb_zcopy(skb)) { + sock_zerocopy_get(uarg); + skb_shinfo(skb)->destructor_arg = uarg; + skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; + } +} + +/* Release a reference on a zerocopy structure */ +static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + uarg->zerocopy = uarg->zerocopy && zerocopy; + sock_zerocopy_put(uarg); + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + +/* Abort a zerocopy operation and revert zckey on error in send syscall */ +static inline void skb_zcopy_abort(struct sk_buff *skb) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + sock_zerocopy_put_abort(uarg); + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head diff --git a/include/linux/socket.h b/include/linux/socket.h index 8b13db5163cc..8ad963cdc88c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -287,6 +287,7 @@ struct ucred { #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN +#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file descriptor received through -- cgit v1.2.3 From 1f8b977ab32dc5d148f103326e80d9097f1cefb5 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 3 Aug 2017 16:29:41 -0400 Subject: sock: enable MSG_ZEROCOPY Prepare the datapath for refcounted ubuf_info. Clone ubuf_info with skb_zerocopy_clone() wherever needed due to skb split, merge, resize or clone. Split skb_orphan_frags into two variants. The split, merge, .. paths support reference counted zerocopy buffers, so do not do a deep copy. Add skb_orphan_frags_rx for paths that may loop packets to receive sockets. That is not allowed, as it may cause unbounded latency. Deep copy all zerocopy copy buffers, ref-counted or not, in this path. The exact locations to modify were chosen by exhaustively searching through all code that might modify skb_frag references and/or the the SKBTX_DEV_ZEROCOPY tx_flags bit. The changes err on the safe side, in two ways. (1) legacy ubuf_info paths virtio and tap are not modified. They keep a 1:1 ubuf_info to sk_buff relationship. Calls to skb_orphan_frags still call skb_copy_ubufs and thus copy frags in this case. (2) not all copies deep in the stack are addressed yet. skb_shift, skb_split and skb_try_coalesce can be refined to avoid copying. These are not in the hot path and this patch is hairy enough as is, so that is left for future refinement. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 59cff7aa494e..e5387932c266 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2512,7 +2512,17 @@ static inline void skb_orphan(struct sk_buff *skb) */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { - if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY))) + if (likely(!skb_zcopy(skb))) + return 0; + if (skb_uarg(skb)->callback == sock_zerocopy_callback) + return 0; + return skb_copy_ubufs(skb, gfp_mask); +} + +/* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ +static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) +{ + if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } @@ -2944,6 +2954,8 @@ static inline int skb_add_data(struct sk_buff *skb, static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { + if (skb_zcopy(skb)) + return false; if (i) { const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; -- cgit v1.2.3 From 4ab6c99d99bb1bf0fbba8ff4e52114c66109992f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 3 Aug 2017 16:29:42 -0400 Subject: sock: MSG_ZEROCOPY notification coalescing In the simple case, each sendmsg() call generates data and eventually a zerocopy ready notification N, where N indicates the Nth successful invocation of sendmsg() with the MSG_ZEROCOPY flag on this socket. TCP and corked sockets can cause send() calls to append new data to an existing sk_buff and, thus, ubuf_info. In that case the notification must hold a range. odify ubuf_info to store a inclusive range [N..N+m] and add skb_zerocopy_realloc() to optionally extend an existing range. Also coalesce notifications in this common case: if a notification [1, 1] is about to be queued while [0, 0] is the queue tail, just modify the head of the queue to read [0, 1]. Coalescing is limited to a few TSO frames worth of data to bound notification latency. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e5387932c266..f5bdd93a87da 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -444,15 +444,26 @@ enum { */ struct ubuf_info { void (*callback)(struct ubuf_info *, bool zerocopy_success); - void *ctx; - unsigned long desc; - u16 zerocopy:1; + union { + struct { + unsigned long desc; + void *ctx; + }; + struct { + u32 id; + u16 len; + u16 zerocopy:1; + u32 bytelen; + }; + }; atomic_t refcnt; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); +struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); static inline void sock_zerocopy_get(struct ubuf_info *uarg) { -- cgit v1.2.3 From a91dbff551a6f1865b68fa82b654591490b59901 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 3 Aug 2017 16:29:43 -0400 Subject: sock: ulimit on MSG_ZEROCOPY pages Bound the number of pages that a user may pin. Follow the lead of perf tools to maintain a per-user bound on memory locked pages commit 789f90fcf6b0 ("perf_counter: per user mlock gift") Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/sched/user.h | 3 ++- include/linux/skbuff.h | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 5d5415e129d4..3c07e4135127 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,7 +36,8 @@ struct user_struct { struct hlist_node uidhash_node; kuid_t uid; -#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ + defined(CONFIG_NET) atomic_long_t locked_vm; #endif }; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f5bdd93a87da..8c0708d2e5e6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -457,6 +457,11 @@ struct ubuf_info { }; }; atomic_t refcnt; + + struct mmpin { + struct user_struct *user; + unsigned int num_pg; + } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) -- cgit v1.2.3 From 999616b8536cf3b9a1d0d74d5542ea009df482ff Mon Sep 17 00:00:00 2001 From: Jerome Forissier Date: Wed, 31 May 2017 13:21:05 +0200 Subject: tee: add forward declaration for struct device tee_drv.h references struct device, but does not include device.h nor platform_device.h. Therefore, if tee_drv.h is included by some file that does not pull device.h nor platform_device.h beforehand, we have a compile warning. Fix this by adding a forward declaration. Signed-off-by: Jerome Forissier Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 0f175b8f6456..cb889afe576b 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -28,6 +28,7 @@ #define TEE_SHM_MAPPED 0x1 /* Memory mapped by the kernel */ #define TEE_SHM_DMA_BUF 0x2 /* Memory with dma-buf handle */ +struct device; struct tee_device; struct tee_shm; struct tee_shm_pool; -- cgit v1.2.3 From 8eede5bc4ef04281fbba7ddfe157052d0e76075d Mon Sep 17 00:00:00 2001 From: Nate Watterson Date: Thu, 20 Jul 2017 15:26:24 -0400 Subject: ata: ahci_platform: Add shutdown handler The newly introduced ahci_platform_shutdown() method is called during system shutdown to disable host controller DMA and interrupts in order to avoid potentially corrupting or otherwise interfering with a new kernel being started with kexec. Signed-off-by: Nate Watterson Signed-off-by: Tejun Heo --- include/linux/ahci_platform.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index a270f25ee7c7..1b0a17b22cd3 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -36,6 +36,8 @@ int ahci_platform_init_host(struct platform_device *pdev, const struct ata_port_info *pi_template, struct scsi_host_template *sht); +void ahci_platform_shutdown(struct platform_device *pdev); + int ahci_platform_suspend_host(struct device *dev); int ahci_platform_resume_host(struct device *dev); int ahci_platform_suspend(struct device *dev); -- cgit v1.2.3 From e870c6c87cf9484090d28f2a68aa29e008960c93 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 31 Jul 2017 23:43:18 +0200 Subject: ACPI / PM: Prefer suspend-to-idle over S3 on some systems Modify the ACPI system sleep support setup code to select suspend-to-idle as the default system sleep state if (1) the ACPI_FADT_LOW_POWER_S0 flag is set in the FADT and (2) the Low Power Idle S0 _DSM interface has been discovered and (3) the default sleep state was not selected from the kernel command line. The main motivation for this change is that systems where the (1) and (2) conditions are met typically ship with OSes that don't exercise the S3 path in the platform firmware which remains untested and turns out to be non-functional at least in some cases. Signed-off-by: Rafael J. Wysocki Tested-by: Mario Limonciello --- include/linux/suspend.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 97e394feabdb..8c3b0b1e6786 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -196,6 +196,9 @@ struct platform_freeze_ops { }; #ifdef CONFIG_SUSPEND +extern suspend_state_t mem_sleep_current; +extern suspend_state_t mem_sleep_default; + /** * suspend_set_ops - set platform dependent suspend operations * @ops: The new suspend operations to set. -- cgit v1.2.3 From 401c0a19c6c22efcaff85d5a64a396f9130da2ca Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 4 Aug 2017 17:20:16 -0700 Subject: nfit, libnvdimm, region: export 'position' in mapping info It is useful to be able to know the position of a DIMM in an interleave-set. Consider the case where the order of the DIMMs changes causing a namespace to be invalidated because the interleave-set cookie no longer matches. If the before and after state of each DIMM position is known this state debugged by the system owner. Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index f3d3e6af8838..9b8d81a7b80e 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -87,6 +87,7 @@ struct nd_mapping_desc { struct nvdimm *nvdimm; u64 start; u64 size; + int position; }; struct nd_region_desc { -- cgit v1.2.3 From da4625ac2637e4e5249dc08a10f8dce7643603d2 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 25 Jul 2017 15:02:42 +0100 Subject: net: phy: split out PHY speed and duplex string generation Other code would like to make use of this, so make the speed and duplex string generation visible, and place it in a separate file. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/phy.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 0bb5b212ab42..e8264c78b75b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -667,6 +667,9 @@ struct phy_fixup { int (*run)(struct phy_device *phydev); }; +const char *phy_speed_to_str(int speed); +const char *phy_duplex_to_str(unsigned int duplex); + /** * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. -- cgit v1.2.3 From 0ccb4fc65d2799a315d5ee8732d75f35a114379c Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 25 Jul 2017 15:02:47 +0100 Subject: net: phy: move phy_lookup_setting() and guts of phy_supported_speeds() to phy-core phy_lookup_setting() provides useful functionality in ethtool code outside phylib. Move it to phy-core and allow it to be re-used (eg, in phylink) rather than duplicated elsewhere. Note that this supports the larger linkmode space. As we move the phy settings table, we also need to move the guts of phy_supported_speeds() as well. Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index e8264c78b75b..8a280257778c 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -670,6 +670,21 @@ struct phy_fixup { const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); +/* A structure for mapping a particular speed and duplex + * combination to a particular SUPPORTED and ADVERTISED value + */ +struct phy_setting { + u32 speed; + u8 duplex; + u8 bit; +}; + +const struct phy_setting * +phy_lookup_setting(int speed, int duplex, const unsigned long *mask, + size_t maxbit, bool exact); +size_t phy_speeds(unsigned int *speeds, size_t size, + unsigned long *mask, size_t maxbit); + /** * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. -- cgit v1.2.3 From a81497bee70eb15039594b3116913133aa9c9b29 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 25 Jul 2017 15:02:58 +0100 Subject: net: phy: provide a hook for link up/link down events Sometimes, we need to do additional work between the PHY coming up and marking the carrier present - for example, we may need to wait for the PHY to MAC link to finish negotiation. This changes phylib to provide a notification function pointer which avoids the built-in netif_carrier_on() and netif_carrier_off() functions. Standard ->adjust_link functionality is provided by hooking a helper into the new ->phy_link_change method. Reviewed-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 8a280257778c..0a5e8e62c9e0 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -474,6 +474,7 @@ struct phy_device { u8 mdix; u8 mdix_ctrl; + void (*phy_link_change)(struct phy_device *, bool up, bool do_carrier); void (*adjust_link)(struct net_device *dev); }; #define to_phy_device(d) container_of(to_mdio_device(d), \ -- cgit v1.2.3 From 9525ae83959b60c6061fe2f2caabdc8f69a48bc6 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 25 Jul 2017 15:03:13 +0100 Subject: phylink: add phylink infrastructure The link between the ethernet MAC and its PHY has become more complex as the interface evolves. This is especially true with serdes links, where the part of the PHY is effectively integrated into the MAC. Serdes links can be connected to a variety of devices, including SFF modules soldered down onto the board with the MAC, a SFP cage with a hotpluggable SFP module which may contain a PHY or directly modulate the serdes signals onto optical media with or without a PHY, or even a classical PHY connection. Moreover, the negotiation information on serdes links comes in two varieties - SGMII mode, where the PHY provides its speed/duplex/flow control information to the MAC, and 1000base-X mode where both ends exchange their abilities and each resolve the link capabilities. This means we need a more flexible means to support these arrangements, particularly with the hotpluggable nature of SFP, where the PHY can be attached or detached after the network device has been brought up. Ethtool information can come from multiple sources: - we may have a PHY operating in either SGMII or 1000base-X mode, in which case we take ethtool/mii data directly from the PHY. - we may have a optical SFP module without a PHY, with the MAC operating in 1000base-X mode - the ethtool/mii data needs to come from the MAC. - we may have a copper SFP module with a PHY whic can't be accessed, which means we need to take ethtool/mii data from the MAC. Phylink aims to solve this by providing an intermediary between the MAC and PHY, providing a safe way for PHYs to be hotplugged, and allowing a SFP driver to reconfigure the serdes connection. Phylink also takes over support of fixed link connections, where the speed/duplex/flow control are fixed, but link status may be controlled by a GPIO signal. By avoiding the fixed-phy implementation, phylink can provide a faster response to link events: fixed-phy has to wait for phylib to operate its state machine, which can take several seconds. In comparison, phylink takes milliseconds. Signed-off-by: Russell King - remove sync status - rework supported and advertisment handling - add 1000base-x speed for fixed links - use functionality exported from phy-core, reworking __phylink_ethtool_ksettings_set for it Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/phy.h | 2 + include/linux/phylink.h | 145 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 147 insertions(+) create mode 100644 include/linux/phylink.h (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 0a5e8e62c9e0..d78cd01ea513 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -182,6 +182,7 @@ static inline const char *phy_modes(phy_interface_t interface) #define MII_ADDR_C45 (1<<30) struct device; +struct phylink; struct sk_buff; /* @@ -469,6 +470,7 @@ struct phy_device { struct mutex lock; + struct phylink *phylink; struct net_device *attached_dev; u8 mdix; diff --git a/include/linux/phylink.h b/include/linux/phylink.h new file mode 100644 index 000000000000..76f054f39684 --- /dev/null +++ b/include/linux/phylink.h @@ -0,0 +1,145 @@ +#ifndef NETDEV_PCS_H +#define NETDEV_PCS_H + +#include +#include +#include + +struct device_node; +struct ethtool_cmd; +struct net_device; + +enum { + MLO_PAUSE_NONE, + MLO_PAUSE_ASYM = BIT(0), + MLO_PAUSE_SYM = BIT(1), + MLO_PAUSE_RX = BIT(2), + MLO_PAUSE_TX = BIT(3), + MLO_PAUSE_TXRX_MASK = MLO_PAUSE_TX | MLO_PAUSE_RX, + MLO_PAUSE_AN = BIT(4), + + MLO_AN_PHY = 0, /* Conventional PHY */ + MLO_AN_FIXED, /* Fixed-link mode */ + MLO_AN_SGMII, /* Cisco SGMII protocol */ + MLO_AN_8023Z, /* 1000base-X protocol */ +}; + +static inline bool phylink_autoneg_inband(unsigned int mode) +{ + return mode == MLO_AN_SGMII || mode == MLO_AN_8023Z; +} + +struct phylink_link_state { + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + phy_interface_t interface; /* PHY_INTERFACE_xxx */ + int speed; + int duplex; + int pause; + unsigned int link:1; + unsigned int an_enabled:1; + unsigned int an_complete:1; +}; + +struct phylink_mac_ops { + /** + * validate: validate and update the link configuration + * @ndev: net_device structure associated with MAC + * @config: configuration to validate + * + * Update the %config->supported and %config->advertised masks + * clearing bits that can not be supported. + * + * Note: the PHY may be able to transform from one connection + * technology to another, so, eg, don't clear 1000BaseX just + * because the MAC is unable to support it. This is more about + * clearing unsupported speeds and duplex settings. + * + * If the %config->interface mode is %PHY_INTERFACE_MODE_1000BASEX + * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode + * based on %config->advertised and/or %config->speed. + */ + void (*validate)(struct net_device *ndev, unsigned long *supported, + struct phylink_link_state *state); + + /* Read the current link state from the hardware */ + int (*mac_link_state)(struct net_device *, struct phylink_link_state *); + + /* Configure the MAC */ + /** + * mac_config: configure the MAC for the selected mode and state + * @ndev: net_device structure for the MAC + * @mode: one of MLO_AN_FIXED, MLO_AN_PHY, MLO_AN_8023Z, MLO_AN_SGMII + * @state: state structure + * + * The action performed depends on the currently selected mode: + * + * %MLO_AN_FIXED, %MLO_AN_PHY: + * set the specified speed, duplex, pause mode, and phy interface + * mode in the provided @state. + * %MLO_AN_8023Z: + * place the link in 1000base-X mode, advertising the parameters + * given in advertising in @state. + * %MLO_AN_SGMII: + * place the link in Cisco SGMII mode - there is no advertisment + * to make as the PHY communicates the speed and duplex to the + * MAC over the in-band control word. Configuration of the pause + * mode is as per MLO_AN_PHY since this is not included. + */ + void (*mac_config)(struct net_device *ndev, unsigned int mode, + const struct phylink_link_state *state); + + /** + * mac_an_restart: restart 802.3z BaseX autonegotiation + * @ndev: net_device structure for the MAC + */ + void (*mac_an_restart)(struct net_device *ndev); + + void (*mac_link_down)(struct net_device *, unsigned int mode); + void (*mac_link_up)(struct net_device *, unsigned int mode, + struct phy_device *); +}; + +struct phylink *phylink_create(struct net_device *, struct device_node *, + phy_interface_t iface, const struct phylink_mac_ops *ops); +void phylink_destroy(struct phylink *); + +int phylink_connect_phy(struct phylink *, struct phy_device *); +int phylink_of_phy_connect(struct phylink *, struct device_node *); +void phylink_disconnect_phy(struct phylink *); + +void phylink_mac_change(struct phylink *, bool up); + +void phylink_start(struct phylink *); +void phylink_stop(struct phylink *); + +void phylink_ethtool_get_wol(struct phylink *, struct ethtool_wolinfo *); +int phylink_ethtool_set_wol(struct phylink *, struct ethtool_wolinfo *); + +int phylink_ethtool_ksettings_get(struct phylink *, + struct ethtool_link_ksettings *); +int phylink_ethtool_ksettings_set(struct phylink *, + const struct ethtool_link_ksettings *); +int phylink_ethtool_nway_reset(struct phylink *); +void phylink_ethtool_get_pauseparam(struct phylink *, + struct ethtool_pauseparam *); +int phylink_ethtool_set_pauseparam(struct phylink *, + struct ethtool_pauseparam *); +int phylink_init_eee(struct phylink *, bool); +int phylink_get_eee_err(struct phylink *); +int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *); +int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *); +int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); + +#define phylink_zero(bm) \ + bitmap_zero(bm, __ETHTOOL_LINK_MODE_MASK_NBITS) +#define __phylink_do_bit(op, bm, mode) \ + op(ETHTOOL_LINK_MODE_ ## mode ## _BIT, bm) + +#define phylink_set(bm, mode) __phylink_do_bit(__set_bit, bm, mode) +#define phylink_clear(bm, mode) __phylink_do_bit(__clear_bit, bm, mode) +#define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) + +void phylink_set_port_modes(unsigned long *bits); + +#endif -- cgit v1.2.3 From ce0aa27ff3f68ed4ea1631d33797e573b3508bfa Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 25 Jul 2017 15:03:18 +0100 Subject: sfp: add sfp-bus to bridge between network devices and sfp cages Signed-off-by: Russell King Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/linux/sfp.h | 434 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 434 insertions(+) create mode 100644 include/linux/sfp.h (limited to 'include/linux') diff --git a/include/linux/sfp.h b/include/linux/sfp.h new file mode 100644 index 000000000000..4a906f560817 --- /dev/null +++ b/include/linux/sfp.h @@ -0,0 +1,434 @@ +#ifndef LINUX_SFP_H +#define LINUX_SFP_H + +#include + +struct __packed sfp_eeprom_base { + u8 phys_id; + u8 phys_ext_id; + u8 connector; +#if defined __BIG_ENDIAN_BITFIELD + u8 e10g_base_er:1; + u8 e10g_base_lrm:1; + u8 e10g_base_lr:1; + u8 e10g_base_sr:1; + u8 if_1x_sx:1; + u8 if_1x_lx:1; + u8 if_1x_copper_active:1; + u8 if_1x_copper_passive:1; + + u8 escon_mmf_1310_led:1; + u8 escon_smf_1310_laser:1; + u8 sonet_oc192_short_reach:1; + u8 sonet_reach_bit1:1; + u8 sonet_reach_bit2:1; + u8 sonet_oc48_long_reach:1; + u8 sonet_oc48_intermediate_reach:1; + u8 sonet_oc48_short_reach:1; + + u8 unallocated_5_7:1; + u8 sonet_oc12_smf_long_reach:1; + u8 sonet_oc12_smf_intermediate_reach:1; + u8 sonet_oc12_short_reach:1; + u8 unallocated_5_3:1; + u8 sonet_oc3_smf_long_reach:1; + u8 sonet_oc3_smf_intermediate_reach:1; + u8 sonet_oc3_short_reach:1; + + u8 e_base_px:1; + u8 e_base_bx10:1; + u8 e100_base_fx:1; + u8 e100_base_lx:1; + u8 e1000_base_t:1; + u8 e1000_base_cx:1; + u8 e1000_base_lx:1; + u8 e1000_base_sx:1; + + u8 fc_ll_v:1; + u8 fc_ll_s:1; + u8 fc_ll_i:1; + u8 fc_ll_l:1; + u8 fc_ll_m:1; + u8 fc_tech_sa:1; + u8 fc_tech_lc:1; + u8 fc_tech_electrical_inter_enclosure:1; + + u8 fc_tech_electrical_intra_enclosure:1; + u8 fc_tech_sn:1; + u8 fc_tech_sl:1; + u8 fc_tech_ll:1; + u8 sfp_ct_active:1; + u8 sfp_ct_passive:1; + u8 unallocated_8_1:1; + u8 unallocated_8_0:1; + + u8 fc_media_tw:1; + u8 fc_media_tp:1; + u8 fc_media_mi:1; + u8 fc_media_tv:1; + u8 fc_media_m6:1; + u8 fc_media_m5:1; + u8 unallocated_9_1:1; + u8 fc_media_sm:1; + + u8 fc_speed_1200:1; + u8 fc_speed_800:1; + u8 fc_speed_1600:1; + u8 fc_speed_400:1; + u8 fc_speed_3200:1; + u8 fc_speed_200:1; + u8 unallocated_10_1:1; + u8 fc_speed_100:1; +#elif defined __LITTLE_ENDIAN_BITFIELD + u8 if_1x_copper_passive:1; + u8 if_1x_copper_active:1; + u8 if_1x_lx:1; + u8 if_1x_sx:1; + u8 e10g_base_sr:1; + u8 e10g_base_lr:1; + u8 e10g_base_lrm:1; + u8 e10g_base_er:1; + + u8 sonet_oc3_short_reach:1; + u8 sonet_oc3_smf_intermediate_reach:1; + u8 sonet_oc3_smf_long_reach:1; + u8 unallocated_5_3:1; + u8 sonet_oc12_short_reach:1; + u8 sonet_oc12_smf_intermediate_reach:1; + u8 sonet_oc12_smf_long_reach:1; + u8 unallocated_5_7:1; + + u8 sonet_oc48_short_reach:1; + u8 sonet_oc48_intermediate_reach:1; + u8 sonet_oc48_long_reach:1; + u8 sonet_reach_bit2:1; + u8 sonet_reach_bit1:1; + u8 sonet_oc192_short_reach:1; + u8 escon_smf_1310_laser:1; + u8 escon_mmf_1310_led:1; + + u8 e1000_base_sx:1; + u8 e1000_base_lx:1; + u8 e1000_base_cx:1; + u8 e1000_base_t:1; + u8 e100_base_lx:1; + u8 e100_base_fx:1; + u8 e_base_bx10:1; + u8 e_base_px:1; + + u8 fc_tech_electrical_inter_enclosure:1; + u8 fc_tech_lc:1; + u8 fc_tech_sa:1; + u8 fc_ll_m:1; + u8 fc_ll_l:1; + u8 fc_ll_i:1; + u8 fc_ll_s:1; + u8 fc_ll_v:1; + + u8 unallocated_8_0:1; + u8 unallocated_8_1:1; + u8 sfp_ct_passive:1; + u8 sfp_ct_active:1; + u8 fc_tech_ll:1; + u8 fc_tech_sl:1; + u8 fc_tech_sn:1; + u8 fc_tech_electrical_intra_enclosure:1; + + u8 fc_media_sm:1; + u8 unallocated_9_1:1; + u8 fc_media_m5:1; + u8 fc_media_m6:1; + u8 fc_media_tv:1; + u8 fc_media_mi:1; + u8 fc_media_tp:1; + u8 fc_media_tw:1; + + u8 fc_speed_100:1; + u8 unallocated_10_1:1; + u8 fc_speed_200:1; + u8 fc_speed_3200:1; + u8 fc_speed_400:1; + u8 fc_speed_1600:1; + u8 fc_speed_800:1; + u8 fc_speed_1200:1; +#else +#error Unknown Endian +#endif + u8 encoding; + u8 br_nominal; + u8 rate_id; + u8 link_len[6]; + char vendor_name[16]; + u8 extended_cc; + char vendor_oui[3]; + char vendor_pn[16]; + char vendor_rev[4]; + union { + __be16 optical_wavelength; + u8 cable_spec; + }; + u8 reserved62; + u8 cc_base; +}; + +struct __packed sfp_eeprom_ext { + __be16 options; + u8 br_max; + u8 br_min; + char vendor_sn[16]; + char datecode[8]; + u8 diagmon; + u8 enhopts; + u8 sff8472_compliance; + u8 cc_ext; +}; + +struct __packed sfp_eeprom_id { + struct sfp_eeprom_base base; + struct sfp_eeprom_ext ext; +}; + +/* SFP EEPROM registers */ +enum { + SFP_PHYS_ID = 0x00, + SFP_PHYS_EXT_ID = 0x01, + SFP_CONNECTOR = 0x02, + SFP_COMPLIANCE = 0x03, + SFP_ENCODING = 0x0b, + SFP_BR_NOMINAL = 0x0c, + SFP_RATE_ID = 0x0d, + SFP_LINK_LEN_SM_KM = 0x0e, + SFP_LINK_LEN_SM_100M = 0x0f, + SFP_LINK_LEN_50UM_OM2_10M = 0x10, + SFP_LINK_LEN_62_5UM_OM1_10M = 0x11, + SFP_LINK_LEN_COPPER_1M = 0x12, + SFP_LINK_LEN_50UM_OM4_10M = 0x12, + SFP_LINK_LEN_50UM_OM3_10M = 0x13, + SFP_VENDOR_NAME = 0x14, + SFP_VENDOR_OUI = 0x25, + SFP_VENDOR_PN = 0x28, + SFP_VENDOR_REV = 0x38, + SFP_OPTICAL_WAVELENGTH_MSB = 0x3c, + SFP_OPTICAL_WAVELENGTH_LSB = 0x3d, + SFP_CABLE_SPEC = 0x3c, + SFP_CC_BASE = 0x3f, + SFP_OPTIONS = 0x40, /* 2 bytes, MSB, LSB */ + SFP_BR_MAX = 0x42, + SFP_BR_MIN = 0x43, + SFP_VENDOR_SN = 0x44, + SFP_DATECODE = 0x54, + SFP_DIAGMON = 0x5c, + SFP_ENHOPTS = 0x5d, + SFP_SFF8472_COMPLIANCE = 0x5e, + SFP_CC_EXT = 0x5f, + + SFP_PHYS_ID_SFP = 0x03, + SFP_PHYS_EXT_ID_SFP = 0x04, + SFP_CONNECTOR_UNSPEC = 0x00, + /* codes 01-05 not supportable on SFP, but some modules have single SC */ + SFP_CONNECTOR_SC = 0x01, + SFP_CONNECTOR_FIBERJACK = 0x06, + SFP_CONNECTOR_LC = 0x07, + SFP_CONNECTOR_MT_RJ = 0x08, + SFP_CONNECTOR_MU = 0x09, + SFP_CONNECTOR_SG = 0x0a, + SFP_CONNECTOR_OPTICAL_PIGTAIL = 0x0b, + SFP_CONNECTOR_MPO_1X12 = 0x0c, + SFP_CONNECTOR_MPO_2X16 = 0x0d, + SFP_CONNECTOR_HSSDC_II = 0x20, + SFP_CONNECTOR_COPPER_PIGTAIL = 0x21, + SFP_CONNECTOR_RJ45 = 0x22, + SFP_CONNECTOR_NOSEPARATE = 0x23, + SFP_CONNECTOR_MXC_2X16 = 0x24, + SFP_ENCODING_UNSPEC = 0x00, + SFP_ENCODING_8B10B = 0x01, + SFP_ENCODING_4B5B = 0x02, + SFP_ENCODING_NRZ = 0x03, + SFP_ENCODING_8472_MANCHESTER = 0x04, + SFP_ENCODING_8472_SONET = 0x05, + SFP_ENCODING_8472_64B66B = 0x06, + SFP_ENCODING_256B257B = 0x07, + SFP_ENCODING_PAM4 = 0x08, + SFP_OPTIONS_HIGH_POWER_LEVEL = BIT(13), + SFP_OPTIONS_PAGING_A2 = BIT(12), + SFP_OPTIONS_RETIMER = BIT(11), + SFP_OPTIONS_COOLED_XCVR = BIT(10), + SFP_OPTIONS_POWER_DECL = BIT(9), + SFP_OPTIONS_RX_LINEAR_OUT = BIT(8), + SFP_OPTIONS_RX_DECISION_THRESH = BIT(7), + SFP_OPTIONS_TUNABLE_TX = BIT(6), + SFP_OPTIONS_RATE_SELECT = BIT(5), + SFP_OPTIONS_TX_DISABLE = BIT(4), + SFP_OPTIONS_TX_FAULT = BIT(3), + SFP_OPTIONS_LOS_INVERTED = BIT(2), + SFP_OPTIONS_LOS_NORMAL = BIT(1), + SFP_DIAGMON_DDM = BIT(6), + SFP_DIAGMON_INT_CAL = BIT(5), + SFP_DIAGMON_EXT_CAL = BIT(4), + SFP_DIAGMON_RXPWR_AVG = BIT(3), + SFP_DIAGMON_ADDRMODE = BIT(2), + SFP_ENHOPTS_ALARMWARN = BIT(7), + SFP_ENHOPTS_SOFT_TX_DISABLE = BIT(6), + SFP_ENHOPTS_SOFT_TX_FAULT = BIT(5), + SFP_ENHOPTS_SOFT_RX_LOS = BIT(4), + SFP_ENHOPTS_SOFT_RATE_SELECT = BIT(3), + SFP_ENHOPTS_APP_SELECT_SFF8079 = BIT(2), + SFP_ENHOPTS_SOFT_RATE_SFF8431 = BIT(1), + SFP_SFF8472_COMPLIANCE_NONE = 0x00, + SFP_SFF8472_COMPLIANCE_REV9_3 = 0x01, + SFP_SFF8472_COMPLIANCE_REV9_5 = 0x02, + SFP_SFF8472_COMPLIANCE_REV10_2 = 0x03, + SFP_SFF8472_COMPLIANCE_REV10_4 = 0x04, + SFP_SFF8472_COMPLIANCE_REV11_0 = 0x05, + SFP_SFF8472_COMPLIANCE_REV11_3 = 0x06, + SFP_SFF8472_COMPLIANCE_REV11_4 = 0x07, + SFP_SFF8472_COMPLIANCE_REV12_0 = 0x08, +}; + +/* SFP Diagnostics */ +enum { + /* Alarm and warnings stored MSB at lower address then LSB */ + SFP_TEMP_HIGH_ALARM = 0x00, + SFP_TEMP_LOW_ALARM = 0x02, + SFP_TEMP_HIGH_WARN = 0x04, + SFP_TEMP_LOW_WARN = 0x06, + SFP_VOLT_HIGH_ALARM = 0x08, + SFP_VOLT_LOW_ALARM = 0x0a, + SFP_VOLT_HIGH_WARN = 0x0c, + SFP_VOLT_LOW_WARN = 0x0e, + SFP_BIAS_HIGH_ALARM = 0x10, + SFP_BIAS_LOW_ALARM = 0x12, + SFP_BIAS_HIGH_WARN = 0x14, + SFP_BIAS_LOW_WARN = 0x16, + SFP_TXPWR_HIGH_ALARM = 0x18, + SFP_TXPWR_LOW_ALARM = 0x1a, + SFP_TXPWR_HIGH_WARN = 0x1c, + SFP_TXPWR_LOW_WARN = 0x1e, + SFP_RXPWR_HIGH_ALARM = 0x20, + SFP_RXPWR_LOW_ALARM = 0x22, + SFP_RXPWR_HIGH_WARN = 0x24, + SFP_RXPWR_LOW_WARN = 0x26, + SFP_LASER_TEMP_HIGH_ALARM = 0x28, + SFP_LASER_TEMP_LOW_ALARM = 0x2a, + SFP_LASER_TEMP_HIGH_WARN = 0x2c, + SFP_LASER_TEMP_LOW_WARN = 0x2e, + SFP_TEC_CUR_HIGH_ALARM = 0x30, + SFP_TEC_CUR_LOW_ALARM = 0x32, + SFP_TEC_CUR_HIGH_WARN = 0x34, + SFP_TEC_CUR_LOW_WARN = 0x36, + SFP_CAL_RXPWR4 = 0x38, + SFP_CAL_RXPWR3 = 0x3c, + SFP_CAL_RXPWR2 = 0x40, + SFP_CAL_RXPWR1 = 0x44, + SFP_CAL_RXPWR0 = 0x48, + SFP_CAL_TXI_SLOPE = 0x4c, + SFP_CAL_TXI_OFFSET = 0x4e, + SFP_CAL_TXPWR_SLOPE = 0x50, + SFP_CAL_TXPWR_OFFSET = 0x52, + SFP_CAL_T_SLOPE = 0x54, + SFP_CAL_T_OFFSET = 0x56, + SFP_CAL_V_SLOPE = 0x58, + SFP_CAL_V_OFFSET = 0x5a, + SFP_CHKSUM = 0x5f, + + SFP_TEMP = 0x60, + SFP_VCC = 0x62, + SFP_TX_BIAS = 0x64, + SFP_TX_POWER = 0x66, + SFP_RX_POWER = 0x68, + SFP_LASER_TEMP = 0x6a, + SFP_TEC_CUR = 0x6c, + + SFP_STATUS = 0x6e, + SFP_ALARM = 0x70, + + SFP_EXT_STATUS = 0x76, + SFP_VSL = 0x78, + SFP_PAGE = 0x7f, +}; + +struct device_node; +struct ethtool_eeprom; +struct ethtool_modinfo; +struct net_device; +struct sfp_bus; + +struct sfp_upstream_ops { + int (*module_insert)(void *, const struct sfp_eeprom_id *id); + void (*module_remove)(void *); + void (*link_down)(void *); + void (*link_up)(void *); + int (*connect_phy)(void *, struct phy_device *); + void (*disconnect_phy)(void *); +}; + +#if IS_ENABLED(CONFIG_SFP) +int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, + unsigned long *support); +phy_interface_t sfp_parse_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id); +void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, + unsigned long *support); + +int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); +int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, + u8 *data); +void sfp_upstream_start(struct sfp_bus *bus); +void sfp_upstream_stop(struct sfp_bus *bus); +struct sfp_bus *sfp_register_upstream(struct device_node *np, + struct net_device *ndev, void *upstream, + const struct sfp_upstream_ops *ops); +void sfp_unregister_upstream(struct sfp_bus *bus); +#else +static inline int sfp_parse_port(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *support) +{ + return PORT_OTHER; +} + +static inline phy_interface_t sfp_parse_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id) +{ + return PHY_INTERFACE_MODE_NA; +} + +static inline void sfp_parse_support(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *support) +{ +} + +static inline int sfp_get_module_info(struct sfp_bus *bus, + struct ethtool_modinfo *modinfo) +{ + return -EOPNOTSUPP; +} + +static inline int sfp_get_module_eeprom(struct sfp_bus *bus, + struct ethtool_eeprom *ee, u8 *data) +{ + return -EOPNOTSUPP; +} + +static inline void sfp_upstream_start(struct sfp_bus *bus) +{ +} + +static inline void sfp_upstream_stop(struct sfp_bus *bus) +{ +} + +static inline struct sfp_bus *sfp_register_upstream(struct device_node *np, + struct net_device *ndev, void *upstream, + const struct sfp_upstream_ops *ops) +{ + return (struct sfp_bus *)-1; +} + +static inline void sfp_unregister_upstream(struct sfp_bus *bus) +{ +} +#endif + +#endif -- cgit v1.2.3 From 770a1ad55763a8a783cb71078e0b33a6b91ad92b Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 25 Jul 2017 15:03:23 +0100 Subject: phylink: add module EEPROM support Add support for reading module EEPROMs through phylink. Reviewed-by: Florian Fainelli Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 76f054f39684..af67edd4ae38 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -125,6 +125,9 @@ void phylink_ethtool_get_pauseparam(struct phylink *, struct ethtool_pauseparam *); int phylink_ethtool_set_pauseparam(struct phylink *, struct ethtool_pauseparam *); +int phylink_ethtool_get_module_info(struct phylink *, struct ethtool_modinfo *); +int phylink_ethtool_get_module_eeprom(struct phylink *, + struct ethtool_eeprom *, u8 *); int phylink_init_eee(struct phylink *, bool); int phylink_get_eee_err(struct phylink *); int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *); -- cgit v1.2.3 From 4faf783998b8cb88294e9df89032f473f8771b78 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 3 Aug 2017 20:38:51 -0700 Subject: tcp: fix cwnd undo in Reno and HTCP congestion controls Using ssthresh to revert cwnd is less reliable when ssthresh is bounded to 2 packets. This patch uses an existing variable in TCP "prior_cwnd" that snapshots the cwnd right before entering fast recovery and RTO recovery in Reno. This fixes the issue discussed in netdev thread: "A buggy behavior for Linux TCP Reno and HTCP" https://www.spinics.net/lists/netdev/msg444955.html Suggested-by: Neal Cardwell Reported-by: Wei Sun Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index d7389ea36e10..267164a1d559 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -258,7 +258,7 @@ struct tcp_sock { u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; u32 snd_cwnd_stamp; - u32 prior_cwnd; /* Congestion window at start of Recovery. */ + u32 prior_cwnd; /* cwnd right before starting loss recovery */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ -- cgit v1.2.3 From eeb66cdb682678bfd1f02a4547e3649b38ffea7e Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Sun, 4 Jun 2017 23:11:55 +0300 Subject: net/mlx5: Separate between E-Switch and MPFS Multi-Physical Function Switch (MPFs) is required for when multi-PF configuration is enabled to allow passing user configured unicast MAC addresses to the requesting PF. Before this patch eswitch.c used to manage the HW MPFS l2 table, E-Switch always (regardless of sriov) enabled vport(0) (NIC PF) vport's contexts update on unicast mac address list changes, to populate the PF's MPFS L2 table accordingly. In downstream patch we would like to allow compiling the driver without E-Switch functionalities, for that we move MPFS l2 table logic out of eswitch.c into its own file, and provide Kconfig flag (MLX5_MPFS) to allow compiling out MPFS for those who don't want Multi-PF support. NIC PF netdevice will now directly update MPFS l2 table via the new MPFS API. VF netdevice has no access to MPFS L2 table, so E-Switch will remain responsible of updating its MPFS l2 table on behalf of its VFs. Due to this change we also don't require enabling vport(0) (PF vport) unicast mac changes events anymore, for when SRIOV is not enabled. Which means E-Switch is now activated only on SRIOV activation, and not required otherwise. Signed-off-by: Saeed Mahameed Cc: Jes Sorensen Cc: kernel-team@fb.com --- include/linux/mlx5/driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index df6ce59a1f95..88d6eb5b3a76 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -550,6 +550,7 @@ struct mlx5_fc_stats { unsigned long sampling_interval; /* jiffies */ }; +struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; struct mlx5_pagefault; @@ -647,6 +648,7 @@ struct mlx5_priv { spinlock_t ctx_lock; struct mlx5_flow_steering *steering; + struct mlx5_mpfs *mpfs; struct mlx5_eswitch *eswitch; struct mlx5_core_sriov sriov; struct mlx5_lag *lag; -- cgit v1.2.3 From 97834eba7c194659a72c5bb0f8c19c7055bb69ea Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Wed, 7 Jun 2017 12:14:24 +0300 Subject: net/mlx5: Delay events till ib registration ends When mlx5_ib registers itself to mlx5_core as an interface, it will call mlx5_add_device which will call mlx5_ib interface add callback, in case the latter successfully returns, only then mlx5_core will add it to the interface list and async events will be forwarded to mlx5_ib. Between mlx5_ib interface add callback and mlx5_core adding the mlx5_ib interface to its devices list, arriving mlx5_core events can be missed by the new mlx5_ib registering interface. In other words: thread 1: mlx5_ib: mlx5_register_interface(dev) thread 1: mlx5_core: mlx5_add_device(dev) thread 1: mlx5_core: ctx = dev->add => (mlx5_ib)->mlx5_ib_add thread 2: mlx5_core_event: **new event arrives, forward to dev_list thread 1: mlx5_core: add_ctx_to_dev_list(ctx) /* previous event was missed by the new interface.*/ It is ok to miss events before dev->add (mlx5_ib)->mlx5_ib_add_device but not after. We fix this race by accumulating the events that come between the ib_register_device (inside mlx5_add_device->(dev->add)) till the adding to the list completes and fire them to the new registering interface after that. Fixes: f1ee87fe55c8 ("net/mlx5: Organize device list API in one place") Signed-off-by: Erez Shitrit Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 88d6eb5b3a76..d26f18b39c4a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -647,6 +647,9 @@ struct mlx5_priv { struct list_head ctx_list; spinlock_t ctx_lock; + struct list_head waiting_events_list; + bool is_accum_events; + struct mlx5_flow_steering *steering; struct mlx5_mpfs *mpfs; struct mlx5_eswitch *eswitch; -- cgit v1.2.3 From 61690e09c3b4a40401bdaa89ee11522cc0dc4b11 Mon Sep 17 00:00:00 2001 From: Rabie Loulou Date: Mon, 10 Jul 2017 14:35:10 +0300 Subject: net/mlx5: Fix counter list hardware structure The counter list hardware structure doesn't contain a clear and num_of_counters fields, remove them. These wrong fields were never used by the driver hence no other driver changes. Fixes: a351a1b03bf1 ("net/mlx5: Introduce bulk reading of flow counters") Signed-off-by: Rabie Loulou Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3030121b4746..f847a3a57913 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1071,8 +1071,7 @@ struct mlx5_ifc_dest_format_struct_bits { }; struct mlx5_ifc_flow_counter_list_bits { - u8 clear[0x1]; - u8 num_of_counters[0xf]; + u8 reserved_at_0[0x10]; u8 flow_counter_id[0x10]; u8 reserved_at_20[0x20]; -- cgit v1.2.3 From a8ffcc741acb3c7f3dcf4c7d001209aa0995a5f1 Mon Sep 17 00:00:00 2001 From: Rabie Loulou Date: Sun, 9 Jul 2017 13:39:30 +0300 Subject: net/mlx5: Increase the maximum flow counters supported Read new NIC capability field which represnts 16 MSBs of the max flow counters number supported (max_flow_counter_31_16). Backward compatibility with older firmware is preserved, the modified driver reads max_flow_counter_31_16 as 0 from the older firmware and uses up to 64K counters. Changed flow counter id from 16 bits to 32 bits. Backward compatibility with older firmware is preserved as we kept the 16 LSBs of the counter id in place and added 16 MSBs from reserved field. Changed the background bulk reading of flow counters to work in chunks of at most 32K counters, to make sure we don't attempt to allocate very large buffers. Signed-off-by: Rabie Loulou Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 16 ++++++---------- 1 file changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f847a3a57913..c99daffc3c3c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -963,7 +963,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_2a0[0x10]; u8 max_wqe_sz_rq[0x10]; - u8 reserved_at_2c0[0x10]; + u8 max_flow_counter_31_16[0x10]; u8 max_wqe_sz_sq_dc[0x10]; u8 reserved_at_2e0[0x7]; @@ -981,7 +981,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_340[0x8]; u8 log_max_flow_counter_bulk[0x8]; - u8 max_flow_counter[0x10]; + u8 max_flow_counter_15_0[0x10]; u8 reserved_at_360[0x3]; @@ -1071,8 +1071,7 @@ struct mlx5_ifc_dest_format_struct_bits { }; struct mlx5_ifc_flow_counter_list_bits { - u8 reserved_at_0[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_20[0x20]; }; @@ -4402,8 +4401,7 @@ struct mlx5_ifc_query_flow_counter_in_bits { u8 reserved_at_c1[0xf]; u8 num_of_counters[0x10]; - u8 reserved_at_e0[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; }; struct mlx5_ifc_query_esw_vport_context_out_bits { @@ -6271,8 +6269,7 @@ struct mlx5_ifc_dealloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_60[0x20]; }; @@ -7097,8 +7094,7 @@ struct mlx5_ifc_alloc_flow_counter_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_60[0x20]; }; -- cgit v1.2.3 From c04ac679c6b86e4e36fbb675c6c061b4091f5810 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 7 Aug 2017 11:29:48 +0100 Subject: ACPI: Introduce DMA ranges parsing Some devices have limited addressing capabilities and cannot reference the whole memory address space while carrying out DMA operations (eg some devices with bus address bits range smaller than system bus - which prevents them from using bus addresses that are otherwise valid for the system). The ACPI _DMA object allows bus devices to define the DMA window that is actually addressable by devices that sit upstream the bus, therefore providing a means to parse and initialize the devices DMA masks and addressable DMA range size. By relying on the generic ACPI kernel layer to retrieve and parse resources, introduce ACPI core code to parse the _DMA object. Signed-off-by: Lorenzo Pieralisi Tested-by: Nate Watterson Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c749eef1daa1..a5eaff9f2c6d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -427,6 +427,8 @@ void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); +int acpi_dev_get_dma_resources(struct acpi_device *adev, + struct list_head *list); int acpi_dev_filter_resource_type(struct acpi_resource *ares, unsigned long types); @@ -774,6 +776,12 @@ static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) return DEV_DMA_NOT_SUPPORTED; } +static inline int acpi_dma_get_range(struct device *dev, u64 *dma_addr, + u64 *offset, u64 *size) +{ + return -ENODEV; +} + static inline int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) { -- cgit v1.2.3 From 7ad4263980826e8b02e121af22f4f4c9103fe86d Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Mon, 7 Aug 2017 11:29:49 +0100 Subject: ACPI: Make acpi_dma_configure() DMA regions aware Current ACPI DMA configuration set-up device DMA capabilities through kernel defaults that do not take into account platform specific DMA configurations reported by firmware. By leveraging the ACPI acpi_dev_get_dma_resources() API, add code in acpi_dma_configure() to retrieve the DMA regions to correctly set-up PCI devices DMA parameters. Rework the ACPI IORT kernel API to make sure they can accommodate the DMA set-up required by firmware. By making PCI devices DMA set-up ACPI IORT specific, the kernel is shielded from unwanted regressions that could be triggered by parsing DMA resources on arches that were previously ignoring them (ie x86/ia64), leaving kernel behaviour unchanged on those arches. Signed-off-by: Lorenzo Pieralisi Acked-by: Will Deacon Tested-by: Nate Watterson Signed-off-by: Rafael J. Wysocki --- include/linux/acpi_iort.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 8379d406ad2e..8d3f0bf80379 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -36,7 +36,7 @@ struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id); void acpi_configure_pmsi_domain(struct device *dev); int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ -void iort_set_dma_mask(struct device *dev); +void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size); const struct iommu_ops *iort_iommu_configure(struct device *dev); #else static inline void acpi_iort_init(void) { } @@ -47,7 +47,8 @@ static inline struct irq_domain *iort_get_device_domain(struct device *dev, { return NULL; } static inline void acpi_configure_pmsi_domain(struct device *dev) { } /* IOMMU interface */ -static inline void iort_set_dma_mask(struct device *dev) { } +static inline void iort_dma_setup(struct device *dev, u64 *dma_addr, + u64 *size) { } static inline const struct iommu_ops *iort_iommu_configure(struct device *dev) { return NULL; } -- cgit v1.2.3 From 5e2f30b756a37bd80c5b0471d0e10d769ab2eb9a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 3 Aug 2017 18:11:04 +0200 Subject: KVM: nVMX: get rid of nested_get_page() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit nested_get_page() just sounds confusing. All we want is a page from G1. This is even unrelated to nested. Let's introduce kvm_vcpu_gpa_to_page() so we don't get too lengthy lines. Reviewed-by: Paolo Bonzini Signed-off-by: David Hildenbrand Signed-off-by: Radim Krčmář [Squash pasto fix from Wanpeng Li. - Paolo] Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 21a6fd6c44af..28112d7917c1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -985,6 +985,12 @@ static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) return (hpa_t)pfn << PAGE_SHIFT; } +static inline struct page *kvm_vcpu_gpa_to_page(struct kvm_vcpu *vcpu, + gpa_t gpa) +{ + return kvm_vcpu_gfn_to_page(vcpu, gpa_to_gfn(gpa)); +} + static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa) { unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); -- cgit v1.2.3 From dfc8e9165cfe0b50438f51df5a82ab1dcc08baf4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 7 Aug 2017 17:22:14 +0200 Subject: fbcon: mark dummy functions 'inline' The newly introduced fb_console_init/exit declarations have a dummy alternative that is marked 'static' in the header but not inline, leading to a warning whenever the header gets included: In file included from drivers/video/fbdev/core/fbmem.c:35:0: include/linux/fbcon.h:9:13: error: 'fb_console_exit' defined but not used [-Werror=unused-function] This adds the intended 'inline'. Fixes: 6104c37094e7 ("fbcon: Make fbcon a built-time depency for fbdev") Signed-off-by: Arnd Bergmann Reviewed-by: Daniel Vetter Cc: Sean Paul Signed-off-by: Bartlomiej Zolnierkiewicz --- include/linux/fbcon.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fbcon.h b/include/linux/fbcon.h index 0fac6305d51c..f68a7db14165 100644 --- a/include/linux/fbcon.h +++ b/include/linux/fbcon.h @@ -5,8 +5,8 @@ void __init fb_console_init(void); void __exit fb_console_exit(void); #else -static void fb_console_init(void) {} -static void fb_console_exit(void) {} +static inline void fb_console_init(void) {} +static inline void fb_console_exit(void) {} #endif #endif /* _LINUX_FBCON_H */ -- cgit v1.2.3 From 2606706e4d7b89ebf13f35895a7dfe00e394e782 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 30 May 2017 13:48:22 +0200 Subject: backlight: gpio_backlight: Delete pdata inversion The option to invert the output of the GPIO (active low) is not used by the only platform still using platform data to set up a GPIO backlight (one SH board). Delete the option as we do not expect to expand the use of board files for this driver, and GPIO descriptors intrinsically keep track of any signal inversion. Signed-off-by: Linus Walleij Acked-by: Daniel Thompson Reviewed-by: Laurent Pinchart Signed-off-by: Lee Jones --- include/linux/platform_data/gpio_backlight.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/gpio_backlight.h b/include/linux/platform_data/gpio_backlight.h index 5ae0d9c80d4d..683d90453c41 100644 --- a/include/linux/platform_data/gpio_backlight.h +++ b/include/linux/platform_data/gpio_backlight.h @@ -14,7 +14,6 @@ struct gpio_backlight_platform_data { struct device *fbdev; int gpio; int def_value; - bool active_low; const char *name; }; -- cgit v1.2.3 From 2572ac53c46f58e500b9d8d0f99785666038c590 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 7 Aug 2017 10:15:17 +0200 Subject: net: sched: make type an argument for ndo_setup_tc Since the type is always present, push it to be a separate argument to ndo_setup_tc. On the way, name the type enum and use it for arg type. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3a3cdc1b1f31..e4238e540544 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -774,7 +774,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, /* These structures hold the attributes of qdisc and classifiers * that are being passed to the netdevice through the setup_tc op. */ -enum { +enum tc_setup_type { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, @@ -785,7 +785,6 @@ enum { struct tc_cls_u32_offload; struct tc_to_netdev { - unsigned int type; union { struct tc_cls_u32_offload *cls_u32; struct tc_cls_flower_offload *cls_flower; @@ -978,8 +977,9 @@ struct xfrmdev_ops { * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); - * int (*ndo_setup_tc)(struct net_device *dev, u32 handle, u32 chain_index, - * __be16 protocol, struct tc_to_netdev *tc); + * int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, + * u32 handle, u32 chain_index, __be16 protocol, + * struct tc_to_netdev *tc); * Called to setup any 'tc' scheduler, classifier or action on @dev. * This is always called from the stack with the rtnl lock held and netif * tx queues stopped. This allows the netdevice to perform queue @@ -1227,6 +1227,7 @@ struct net_device_ops { struct net_device *dev, int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, + enum tc_setup_type type, u32 handle, u32 chain_index, __be16 protocol, struct tc_to_netdev *tc); -- cgit v1.2.3 From ade9b6588420b335851951702ab975c975b0c1b2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 7 Aug 2017 10:15:18 +0200 Subject: net: sched: rename TC_SETUP_MATCHALL to TC_SETUP_CLSMATCHALL In order to be aligned with the rest of the types, rename TC_SETUP_MATCHALL to TC_SETUP_CLSMATCHALL. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e4238e540544..f8051a36f900 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -778,7 +778,7 @@ enum tc_setup_type { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, - TC_SETUP_MATCHALL, + TC_SETUP_CLSMATCHALL, TC_SETUP_CLSBPF, }; -- cgit v1.2.3 From 3e0e82664322290a59189f7c2bcb39b0de932505 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 7 Aug 2017 10:15:19 +0200 Subject: net: sched: make egress_dev flag part of flower offload struct Since this is specific to flower now, make it part of the flower offload struct. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f8051a36f900..bd49dbaee84e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -792,7 +792,6 @@ struct tc_to_netdev { struct tc_cls_bpf_offload *cls_bpf; struct tc_mqprio_qopt *mqprio; }; - bool egress_dev; }; /* These structures hold the attributes of xdp state that are being passed -- cgit v1.2.3 From 5fd9fc4e207dba0c05cafe78417952b4c4ca02dc Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 7 Aug 2017 10:15:29 +0200 Subject: net: sched: push cls related args into cls_common structure As ndo_setup_tc is generic offload op for whole tc subsystem, does not really make sense to have cls-specific args. So move them under cls_common structurure which is embedded in all cls structs. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bd49dbaee84e..6e2f7e38cf8e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -977,7 +977,6 @@ struct xfrmdev_ops { * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); * int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, - * u32 handle, u32 chain_index, __be16 protocol, * struct tc_to_netdev *tc); * Called to setup any 'tc' scheduler, classifier or action on @dev. * This is always called from the stack with the rtnl lock held and netif @@ -1227,8 +1226,6 @@ struct net_device_ops { int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, - u32 handle, u32 chain_index, - __be16 protocol, struct tc_to_netdev *tc); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); -- cgit v1.2.3 From de4784ca030fed17d527dbb2bb4e21328b12de94 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Mon, 7 Aug 2017 10:15:32 +0200 Subject: net: sched: get rid of struct tc_to_netdev Get rid of struct tc_to_netdev which is now just unnecessary container and rather pass per-type structures down to drivers directly. Along with that, consolidate the naming of per-type structure variables in cls_*. Signed-off-by: Jiri Pirko Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/netdevice.h | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6e2f7e38cf8e..1d238d54c484 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -771,9 +771,6 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb); -/* These structures hold the attributes of qdisc and classifiers - * that are being passed to the netdevice through the setup_tc op. - */ enum tc_setup_type { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, @@ -782,18 +779,6 @@ enum tc_setup_type { TC_SETUP_CLSBPF, }; -struct tc_cls_u32_offload; - -struct tc_to_netdev { - union { - struct tc_cls_u32_offload *cls_u32; - struct tc_cls_flower_offload *cls_flower; - struct tc_cls_matchall_offload *cls_mall; - struct tc_cls_bpf_offload *cls_bpf; - struct tc_mqprio_qopt *mqprio; - }; -}; - /* These structures hold the attributes of xdp state that are being passed * to the netdevice through the xdp op. */ @@ -977,7 +962,7 @@ struct xfrmdev_ops { * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); * int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, - * struct tc_to_netdev *tc); + * void *type_data); * Called to setup any 'tc' scheduler, classifier or action on @dev. * This is always called from the stack with the rtnl lock held and netif * tx queues stopped. This allows the netdevice to perform queue @@ -1226,7 +1211,7 @@ struct net_device_ops { int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, - struct tc_to_netdev *tc); + void *type_data); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); -- cgit v1.2.3 From 60d9b03141243589dacd3136f3fcb4e6976df954 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 7 Aug 2017 08:44:19 -0700 Subject: net: ipv4: add second dif to multicast source filter Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/igmp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 97caf1821de8..f8231854b5d6 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -118,7 +118,8 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct ip_msfilter __user *optval, int __user *optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen); -extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif); +extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, + int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); -- cgit v1.2.3 From 1801b570dd2ae50b90231f283e79a9a94fbe7875 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 7 Aug 2017 08:44:20 -0700 Subject: net: ipv6: add second dif to udp socket lookups Add a second device index, sdif, to udp socket lookups. sdif is the index for ingress devices enslaved to an l3mdev. It allows the lookups to consider the enslaved device as well as the L3 domain when searching for a socket. Early demux lookups are handled in the next patch as part of INET_MATCH changes. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 474d6bbc158c..ac2da4e11d5e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -158,6 +158,16 @@ static inline bool inet6_is_jumbogram(const struct sk_buff *skb) return !!(IP6CB(skb)->flags & IP6SKB_JUMBOGRAM); } +/* can not be used in TCP layer after tcp_v6_fill_cb */ +static inline int inet6_sdif(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) + return IP6CB(skb)->iif; +#endif + return 0; +} + /* can not be used in TCP layer after tcp_v6_fill_cb */ static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) { -- cgit v1.2.3 From cf5f5cea270655dd49370760576c64b228583b79 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Fri, 4 Aug 2017 16:00:09 -0700 Subject: bpf: add support for sys_enter_* and sys_exit_* tracepoints Currently, bpf programs cannot be attached to sys_enter_* and sys_exit_* style tracepoints. The iovisor/bcc issue #748 (https://github.com/iovisor/bcc/issues/748) documents this issue. For example, if you try to attach a bpf program to tracepoints syscalls/sys_enter_newfstat, you will get the following error: # ./tools/trace.py t:syscalls:sys_enter_newfstat Ioctl(PERF_EVENT_IOC_SET_BPF): Invalid argument Failed to attach BPF to tracepoint The main reason is that syscalls/sys_enter_* and syscalls/sys_exit_* tracepoints are treated differently from other tracepoints and there is no bpf hook to it. This patch adds bpf support for these syscalls tracepoints by . permitting bpf attachment in ioctl PERF_EVENT_IOC_SET_BPF . calling bpf programs in perf_syscall_enter and perf_syscall_exit The legality of bpf program ctx access is also checked. Function trace_event_get_offsets returns correct max offset for each specific syscall tracepoint, which is compared against the maximum offset access in bpf program. Signed-off-by: Yonghong Song Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/syscalls.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3cb15ea48aee..c9170218e9e6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -172,8 +172,20 @@ extern struct trace_event_functions exit_syscall_print_funcs; static struct syscall_metadata __used \ __attribute__((section("__syscalls_metadata"))) \ *__p_syscall_meta_##sname = &__syscall_meta_##sname; + +static inline int is_syscall_trace_event(struct trace_event_call *tp_event) +{ + return tp_event->class == &event_class_syscall_enter || + tp_event->class == &event_class_syscall_exit; +} + #else #define SYSCALL_METADATA(sname, nb, ...) + +static inline int is_syscall_trace_event(struct trace_event_call *tp_event) +{ + return 0; +} #endif #define SYSCALL_DEFINE0(sname) \ -- cgit v1.2.3 From d1df6fd8a1d22d37cffa0075ab8ad423ce656777 Mon Sep 17 00:00:00 2001 From: David Lebrun Date: Sat, 5 Aug 2017 12:38:26 +0200 Subject: ipv6: sr: define core operations for seg6local lightweight tunnel This patch implements a new type of lightweight tunnel named seg6local. A seg6local lwt is defined by a type of action and a set of parameters. The action represents the operation to perform on the packets matching the lwt's route, and is not necessarily an encapsulation. The set of parameters are arguments for the processing function. Each action is defined in a struct seg6_action_desc within seg6_action_table[]. This structure contains the action, mandatory attributes, the processing function, and a static headroom size required by the action. The mandatory attributes are encoded as a bitmask field. The static headroom is set to a non-zero value when the processing function always add a constant number of bytes to the skb (e.g. the header size for encapsulations). To facilitate rtnetlink-related operations such as parsing, fill_encap, and cmp_encap, each type of action parameter is associated to three function pointers, in seg6_action_params[]. All actions defined in seg6_local.h are detailed in [1]. [1] https://tools.ietf.org/html/draft-filsfils-spring-srv6-network-programming-01 Signed-off-by: David Lebrun Signed-off-by: David S. Miller --- include/linux/seg6_local.h | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 include/linux/seg6_local.h (limited to 'include/linux') diff --git a/include/linux/seg6_local.h b/include/linux/seg6_local.h new file mode 100644 index 000000000000..ee63e76fe0c7 --- /dev/null +++ b/include/linux/seg6_local.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_LOCAL_H +#define _LINUX_SEG6_LOCAL_H + +#include + +#endif -- cgit v1.2.3 From 199b5763d329b43c88f6ad539db8a6c6b42f8edb Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Tue, 8 Aug 2017 12:05:32 +0800 Subject: KVM: add spinlock optimization framework If a vcpu exits due to request a user mode spinlock, then the spinlock-holder may be preempted in user mode or kernel mode. (Note that not all architectures trap spin loops in user mode, only AMD x86 and ARM/ARM64 currently do). But if a vcpu exits in kernel mode, then the holder must be preempted in kernel mode, so we should choose a vcpu in kernel mode as a more likely candidate for the lock holder. This introduces kvm_arch_vcpu_in_kernel() to decide whether the vcpu is in kernel-mode when it's preempted. kvm_vcpu_on_spin's new argument says the same of the spinning VCPU. Signed-off-by: Longpeng(Mike) Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 28112d7917c1..6882538eda32 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -720,7 +720,7 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); -void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu); void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); @@ -800,6 +800,7 @@ int kvm_arch_hardware_setup(void); void kvm_arch_hardware_unsetup(void); void kvm_arch_check_processor_compat(void *rtn); int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); +bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); #ifndef __KVM_HAVE_ARCH_VM_ALLOC -- cgit v1.2.3 From 0ec9eb90feec4933637fbde9d5bfbc3b62aea218 Mon Sep 17 00:00:00 2001 From: Chi-Hsien Lin Date: Thu, 3 Aug 2017 17:37:58 +0800 Subject: brcmfmac: Add support for CYW4373 SDIO/USB chipset Add support for CYW4373 SDIO/USB chipset. CYW4373 is a 1x1 dual-band 11ac chipset with 20/40/80Mhz channel support. It's a WiFi/BT combo device. Signed-off-by: Chi-Hsien Lin Reviewed-by: Arend van Spriel Signed-off-by: Kalle Valo --- include/linux/mmc/sdio_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index b733eb404ffc..abacd5484bc0 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -39,6 +39,7 @@ #define SDIO_DEVICE_ID_BROADCOM_43455 0xa9bf #define SDIO_DEVICE_ID_BROADCOM_4354 0x4354 #define SDIO_DEVICE_ID_BROADCOM_4356 0x4356 +#define SDIO_DEVICE_ID_CYPRESS_4373 0x4373 #define SDIO_VENDOR_ID_INTEL 0x0089 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX 0x1402 -- cgit v1.2.3 From 41c8f70f5a3db7e06179186b6525fd9ee1d7d314 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 3 Aug 2017 14:30:11 -0400 Subject: xprtrdma: Harden backchannel call decoding Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- include/linux/sunrpc/xdr.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 261b48a2701d..86b59e3525a5 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -239,6 +239,19 @@ extern unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len); extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); extern int xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len, int (*actor)(struct scatterlist *, void *), void *data); +/** + * xdr_stream_remaining - Return the number of bytes remaining in the stream + * @xdr: pointer to struct xdr_stream + * + * Return value: + * Number of bytes remaining in @xdr before xdr->end + */ +static inline size_t +xdr_stream_remaining(const struct xdr_stream *xdr) +{ + return xdr->nwords << 2; +} + ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, size_t maxlen, gfp_t gfp_flags); /** -- cgit v1.2.3 From d6344d4b5628052ccda104466e5e05b9c43d7b61 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 4 Aug 2017 14:57:39 +0200 Subject: cpufreq: Simplify cpufreq_can_do_remote_dvfs() The if () in cpufreq_can_do_remote_dvfs() is superfluous, so drop it and simply return the value of the expression under it. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1981a4a167ce..d69464139f67 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -578,11 +578,8 @@ static inline bool cpufreq_can_do_remote_dvfs(struct cpufreq_policy *policy) * - dvfs_possible_from_any_cpu flag is set * - the local and remote CPUs share cpufreq policy */ - if (policy->dvfs_possible_from_any_cpu || - cpumask_test_cpu(smp_processor_id(), policy->cpus)) - return true; - - return false; + return policy->dvfs_possible_from_any_cpu || + cpumask_test_cpu(smp_processor_id(), policy->cpus); } /********************************************************************* -- cgit v1.2.3 From ec52e462564b9c5bfdf1f79638c537c7103e1d2b Mon Sep 17 00:00:00 2001 From: Elaine Zhang Date: Tue, 1 Aug 2017 18:21:22 +0200 Subject: clk: fractional-divider: allow overriding of approximation Fractional dividers may have special requirements concerning numerator and denominator selection that differ from just getting the best approximation. For example on Rockchip socs the denominator must be at least 20 times larger than the numerator to generate precise clock frequencies. Therefore add the ability to provide custom approximation functions. Signed-off-by: Elaine Zhang Acked-by: Stephen Boyd Signed-off-by: Heiko Stuebner --- include/linux/clk-provider.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index c59c62571e4f..1fc113fbf955 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -565,6 +565,9 @@ struct clk_fractional_divider { u8 nwidth; u32 nmask; u8 flags; + void (*approximation)(struct clk_hw *hw, + unsigned long rate, unsigned long *parent_rate, + unsigned long *m, unsigned long *n); spinlock_t *lock; }; -- cgit v1.2.3 From 78249c4215840edb95447ec6867b69a7ac1d7a0d Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 13 Jul 2017 11:09:38 +0300 Subject: mlx5: convert to generic pci_alloc_irq_vectors Now that we have a generic code to allocate an array of irq vectors and even correctly spread their affinity, correctly handle cpu hotplug events and more, were much better off using it. Reviewed-by: Christoph Hellwig Acked-by: Leon Romanovsky Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index df6ce59a1f95..5bac7f53b4f9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -597,7 +597,6 @@ struct mlx5_port_module_event_stats { struct mlx5_priv { char name[MLX5_MAX_NAME_LEN]; struct mlx5_eq_table eq_table; - struct msix_entry *msix_arr; struct mlx5_irq_info *irq_info; /* pages stuff */ -- cgit v1.2.3 From a435393acafbf0ecff4deb3e3cb554b34f0d0664 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 13 Jul 2017 11:09:40 +0300 Subject: mlx5: move affinity hints assignments to generic code generic api takes care of spreading affinity similar to what mlx5 open coded (and even handles better asymmetric configurations). Ask the generic API to spread affinity for us, and feed him pre_vectors that do not participate in affinity settings (which is an improvement to what we had before). The affinity assignments should match what mlx5 tried to do earlier but now we do not set affinity to async, cmd and pages dedicated vectors. Also, remove mlx5e_get_cpu and introduce mlx5e_get_node (used for allocation purposes) and mlx5_get_vector_affinity (for indirection table construction) as they provide the needed information. Luckily, we have generic helpers to get cpumask and node given a irq vector. mlx5_get_vector_affinity will be used by mlx5_ib in a subsequent patch. Reviewed-by: Christoph Hellwig Acked-by: Leon Romanovsky Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5bac7f53b4f9..579731842c94 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -534,7 +534,6 @@ struct mlx5_core_sriov { }; struct mlx5_irq_info { - cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; }; @@ -1184,4 +1183,10 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; +static inline const struct cpumask * +mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector) +{ + return pci_irq_get_affinity(dev->pdev, MLX5_EQ_VEC_COMP_BASE + vector); +} + #endif /* MLX5_DRIVER_H */ -- cgit v1.2.3 From 24c5dc6610e8a3764fcb885cc3284c12ff1513de Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 13 Jul 2017 11:09:43 +0300 Subject: block: Add rdma affinity based queue mapping helper Like pci and virtio, we add a rdma helper for affinity spreading. This achieves optimal mq affinity assignments according to the underlying rdma device affinity maps. Reviewed-by: Jens Axboe Reviewed-by: Christoph Hellwig Reviewed-by: Max Gurtovoy Signed-off-by: Sagi Grimberg Signed-off-by: Doug Ledford --- include/linux/blk-mq-rdma.h | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 include/linux/blk-mq-rdma.h (limited to 'include/linux') diff --git a/include/linux/blk-mq-rdma.h b/include/linux/blk-mq-rdma.h new file mode 100644 index 000000000000..b4ade198007d --- /dev/null +++ b/include/linux/blk-mq-rdma.h @@ -0,0 +1,10 @@ +#ifndef _LINUX_BLK_MQ_RDMA_H +#define _LINUX_BLK_MQ_RDMA_H + +struct blk_mq_tag_set; +struct ib_device; + +int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set, + struct ib_device *dev, int first_vec); + +#endif /* _LINUX_BLK_MQ_RDMA_H */ -- cgit v1.2.3 From f1174f77b50c94eecaa658fdc56fa69b421de4b8 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 7 Aug 2017 15:26:19 +0100 Subject: bpf/verifier: rework value tracking Unifies adjusted and unadjusted register value types (e.g. FRAME_POINTER is now just a PTR_TO_STACK with zero offset). Tracks value alignment by means of tracking known & unknown bits. This also replaces the 'reg->imm' (leading zero bits) calculations for (what were) UNKNOWN_VALUEs. If pointer leaks are allowed, and adjust_ptr_min_max_vals returns -EACCES, treat the pointer as an unknown scalar and try again, because we might be able to conclude something about the result (e.g. pointer & 0x40 is either 0 or 0x40). Verifier hooks in the netronome/nfp driver were changed to match the new data structures. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/bpf.h | 34 +++++++------------ include/linux/bpf_verifier.h | 34 +++++++++++-------- include/linux/tnum.h | 79 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 112 insertions(+), 35 deletions(-) create mode 100644 include/linux/tnum.h (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6353c7474dba..39229c455cba 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -117,35 +117,25 @@ enum bpf_access_type { }; /* types of values stored in eBPF registers */ +/* Pointer types represent: + * pointer + * pointer + imm + * pointer + (u16) var + * pointer + (u16) var + imm + * if (range > 0) then [ptr, ptr + range - off) is safe to access + * if (id > 0) means that some 'var' was added + * if (off > 0) means that 'imm' was added + */ enum bpf_reg_type { NOT_INIT = 0, /* nothing was written into register */ - UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ + SCALAR_VALUE, /* reg doesn't contain a valid pointer */ PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ - FRAME_PTR, /* reg == frame_pointer */ - PTR_TO_STACK, /* reg == frame_pointer + imm */ - CONST_IMM, /* constant integer value */ - - /* PTR_TO_PACKET represents: - * skb->data - * skb->data + imm - * skb->data + (u16) var - * skb->data + (u16) var + imm - * if (range > 0) then [ptr, ptr + range - off) is safe to access - * if (id > 0) means that some 'var' was added - * if (off > 0) menas that 'imm' was added - */ - PTR_TO_PACKET, + PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ - - /* PTR_TO_MAP_VALUE_ADJ is used for doing pointer math inside of a map - * elem value. We only allow this if we can statically verify that - * access from this register are going to fall within the size of the - * map element. - */ - PTR_TO_MAP_VALUE_ADJ, }; struct bpf_prog; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 8e5d31f6faef..85936fa92d12 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -9,6 +9,7 @@ #include /* for enum bpf_reg_type */ #include /* for MAX_BPF_STACK */ +#include /* Just some arbitrary values so we can safely do math without overflowing and * are obviously wrong for any sort of memory access. @@ -19,30 +20,37 @@ struct bpf_reg_state { enum bpf_reg_type type; union { - /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ - s64 imm; - - /* valid when type == PTR_TO_PACKET* */ - struct { - u16 off; - u16 range; - }; + /* valid when type == PTR_TO_PACKET */ + u16 range; /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ struct bpf_map *map_ptr; }; + /* Fixed part of pointer offset, pointer types only */ + s32 off; + /* For PTR_TO_PACKET, used to find other pointers with the same variable + * offset, so they can share range knowledge. + * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we + * came from, when one is tested for != NULL. + */ u32 id; + /* These three fields must be last. See states_equal() */ + /* For scalar types (SCALAR_VALUE), this represents our knowledge of + * the actual value. + * For pointer types, this represents the variable part of the offset + * from the pointed-to object, and is shared with all bpf_reg_states + * with the same id as us. + */ + struct tnum var_off; /* Used to determine if any memory access using this register will - * result in a bad access. These two fields must be last. - * See states_equal() + * result in a bad access. + * These refer to the same value as var_off, not necessarily the actual + * contents of the register. */ s64 min_value; u64 max_value; - u32 min_align; - u32 aux_off; - u32 aux_off_align; bool value_from_signed; }; diff --git a/include/linux/tnum.h b/include/linux/tnum.h new file mode 100644 index 000000000000..a0b07bf1842b --- /dev/null +++ b/include/linux/tnum.h @@ -0,0 +1,79 @@ +/* tnum: tracked (or tristate) numbers + * + * A tnum tracks knowledge about the bits of a value. Each bit can be either + * known (0 or 1), or unknown (x). Arithmetic operations on tnums will + * propagate the unknown bits such that the tnum result represents all the + * possible results for possible values of the operands. + */ +#include + +struct tnum { + u64 value; + u64 mask; +}; + +/* Constructors */ +/* Represent a known constant as a tnum. */ +struct tnum tnum_const(u64 value); +/* A completely unknown value */ +extern const struct tnum tnum_unknown; + +/* Arithmetic and logical ops */ +/* Shift a tnum left (by a fixed shift) */ +struct tnum tnum_lshift(struct tnum a, u8 shift); +/* Shift a tnum right (by a fixed shift) */ +struct tnum tnum_rshift(struct tnum a, u8 shift); +/* Add two tnums, return @a + @b */ +struct tnum tnum_add(struct tnum a, struct tnum b); +/* Subtract two tnums, return @a - @b */ +struct tnum tnum_sub(struct tnum a, struct tnum b); +/* Bitwise-AND, return @a & @b */ +struct tnum tnum_and(struct tnum a, struct tnum b); +/* Bitwise-OR, return @a | @b */ +struct tnum tnum_or(struct tnum a, struct tnum b); +/* Bitwise-XOR, return @a ^ @b */ +struct tnum tnum_xor(struct tnum a, struct tnum b); +/* Multiply two tnums, return @a * @b */ +struct tnum tnum_mul(struct tnum a, struct tnum b); + +/* Return a tnum representing numbers satisfying both @a and @b */ +struct tnum tnum_intersect(struct tnum a, struct tnum b); + +/* Return @a with all but the lowest @size bytes cleared */ +struct tnum tnum_cast(struct tnum a, u8 size); + +/* Returns true if @a is a known constant */ +static inline bool tnum_is_const(struct tnum a) +{ + return !a.mask; +} + +/* Returns true if @a == tnum_const(@b) */ +static inline bool tnum_equals_const(struct tnum a, u64 b) +{ + return tnum_is_const(a) && a.value == b; +} + +/* Returns true if @a is completely unknown */ +static inline bool tnum_is_unknown(struct tnum a) +{ + return !~a.mask; +} + +/* Returns true if @a is known to be a multiple of @size. + * @size must be a power of two. + */ +bool tnum_is_aligned(struct tnum a, u64 size); + +/* Returns true if @b represents a subset of @a. */ +bool tnum_in(struct tnum a, struct tnum b); + +/* Formatting functions. These have snprintf-like semantics: they will write + * up to @size bytes (including the terminating NUL byte), and return the number + * of bytes (excluding the terminating NUL) which would have been written had + * sufficient space been available. (Thus tnum_sbin always returns 64.) + */ +/* Format a tnum as a pair of hex numbers (value; mask) */ +int tnum_strn(char *str, size_t size, struct tnum a); +/* Format a tnum as tristate binary expansion */ +int tnum_sbin(char *str, size_t size, struct tnum a); -- cgit v1.2.3 From b03c9f9fdc37dab81ea04d5dacdc5995d4c224c2 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Mon, 7 Aug 2017 15:26:36 +0100 Subject: bpf/verifier: track signed and unsigned min/max values Allows us to, sometimes, combine information from a signed check of one bound and an unsigned check of the other. We now track the full range of possible values, rather than restricting ourselves to [0, 1<<30) and considering anything beyond that as unknown. While this is probably not necessary, it makes the code more straightforward and symmetrical between signed and unsigned bounds. Signed-off-by: Edward Cree Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 23 ++++++++++++++--------- include/linux/tnum.h | 2 ++ 2 files changed, 16 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 85936fa92d12..c61c3033522e 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -11,11 +11,15 @@ #include /* for MAX_BPF_STACK */ #include - /* Just some arbitrary values so we can safely do math without overflowing and - * are obviously wrong for any sort of memory access. - */ -#define BPF_REGISTER_MAX_RANGE (1024 * 1024 * 1024) -#define BPF_REGISTER_MIN_RANGE -1 +/* Maximum variable offset umax_value permitted when resolving memory accesses. + * In practice this is far bigger than any realistic pointer offset; this limit + * ensures that umax_value + (int)off + (int)size cannot overflow a u64. + */ +#define BPF_MAX_VAR_OFF (1ULL << 31) +/* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO]. This ensures + * that converting umax_value to int cannot overflow. + */ +#define BPF_MAX_VAR_SIZ INT_MAX struct bpf_reg_state { enum bpf_reg_type type; @@ -36,7 +40,7 @@ struct bpf_reg_state { * came from, when one is tested for != NULL. */ u32 id; - /* These three fields must be last. See states_equal() */ + /* These five fields must be last. See states_equal() */ /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset @@ -49,9 +53,10 @@ struct bpf_reg_state { * These refer to the same value as var_off, not necessarily the actual * contents of the register. */ - s64 min_value; - u64 max_value; - bool value_from_signed; + s64 smin_value; /* minimum possible (s64)value */ + s64 smax_value; /* maximum possible (s64)value */ + u64 umin_value; /* minimum possible (u64)value */ + u64 umax_value; /* maximum possible (u64)value */ }; enum bpf_stack_slot_type { diff --git a/include/linux/tnum.h b/include/linux/tnum.h index a0b07bf1842b..0d2d3da46139 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -17,6 +17,8 @@ struct tnum { struct tnum tnum_const(u64 value); /* A completely unknown value */ extern const struct tnum tnum_unknown; +/* A value that's unknown except that @min <= value <= @max */ +struct tnum tnum_range(u64 min, u64 max); /* Arithmetic and logical ops */ /* Shift a tnum left (by a fixed shift) */ -- cgit v1.2.3 From 6ec4e2514decd6fb4782a9364fa71d6244d05af4 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Thu, 13 Jul 2017 18:16:01 +0100 Subject: md/raid6: implement recovery using ARM NEON intrinsics Provide a NEON accelerated implementation of the recovery algorithm, which supersedes the default byte-by-byte one. Signed-off-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- include/linux/raid/pq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 30f945329818..583cdd3d49ca 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -121,6 +121,7 @@ extern const struct raid6_recov_calls raid6_recov_ssse3; extern const struct raid6_recov_calls raid6_recov_avx2; extern const struct raid6_recov_calls raid6_recov_avx512; extern const struct raid6_recov_calls raid6_recov_s390xc; +extern const struct raid6_recov_calls raid6_recov_neon; extern const struct raid6_calls raid6_neonx1; extern const struct raid6_calls raid6_neonx2; -- cgit v1.2.3 From d62e26b3ffd28f16ddae85a1babd0303a1a6dfb6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 30 Jun 2017 21:55:08 -0600 Subject: block: pass in queue to inflight accounting No functional change in this patch, just in preparation for basing the inflight mechanism on the queue in question. Reviewed-by: Bart Van Assche Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/bio.h | 9 +++++---- include/linux/genhd.h | 14 +++++++++----- 2 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 7b1cf4ba0902..9276788a9b24 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -463,10 +463,11 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int, extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -void generic_start_io_acct(int rw, unsigned long sectors, - struct hd_struct *part); -void generic_end_io_acct(int rw, struct hd_struct *part, - unsigned long start_time); +void generic_start_io_acct(struct request_queue *q, int rw, + unsigned long sectors, struct hd_struct *part); +void generic_end_io_acct(struct request_queue *q, int rw, + struct hd_struct *part, + unsigned long start_time); #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE # error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e619fae2f037..7f7427e00f9c 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -362,23 +362,27 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(cpu, gendiskp, field, subnd) \ part_stat_add(cpu, gendiskp, field, -subnd) -static inline void part_inc_in_flight(struct hd_struct *part, int rw) +static inline void part_inc_in_flight(struct request_queue *q, + struct hd_struct *part, int rw) { atomic_inc(&part->in_flight[rw]); if (part->partno) atomic_inc(&part_to_disk(part)->part0.in_flight[rw]); } -static inline void part_dec_in_flight(struct hd_struct *part, int rw) +static inline void part_dec_in_flight(struct request_queue *q, + struct hd_struct *part, int rw) { atomic_dec(&part->in_flight[rw]); if (part->partno) atomic_dec(&part_to_disk(part)->part0.in_flight[rw]); } -static inline int part_in_flight(struct hd_struct *part) +static inline int part_in_flight(struct request_queue *q, + struct hd_struct *part) { - return atomic_read(&part->in_flight[0]) + atomic_read(&part->in_flight[1]); + return atomic_read(&part->in_flight[0]) + + atomic_read(&part->in_flight[1]); } static inline struct partition_meta_info *alloc_part_info(struct gendisk *disk) @@ -395,7 +399,7 @@ static inline void free_part_info(struct hd_struct *part) } /* block/blk-core.c */ -extern void part_round_stats(int cpu, struct hd_struct *part); +extern void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part); /* block/genhd.c */ extern void device_add_disk(struct device *parent, struct gendisk *disk); -- cgit v1.2.3 From 0609e0efc5e15195ecf8c6d2f2e890d98760e337 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 8 Aug 2017 17:49:47 -0600 Subject: block: make part_in_flight() take an array of two ints Instead of returning the count that matches the partition, pass in an array of two ints. Index 0 will be filled with the inflight count for the partition in question, and index 1 will filled with the root inflight count, if the partition passed in is not the root. This is in preparation for being able to calculate both in one go. Reviewed-by: Bart Van Assche Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/genhd.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7f7427e00f9c..f2a3a26cdda1 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -378,11 +378,18 @@ static inline void part_dec_in_flight(struct request_queue *q, atomic_dec(&part_to_disk(part)->part0.in_flight[rw]); } -static inline int part_in_flight(struct request_queue *q, - struct hd_struct *part) +static inline void part_in_flight(struct request_queue *q, + struct hd_struct *part, + unsigned int inflight[2]) { - return atomic_read(&part->in_flight[0]) + + inflight[0] = atomic_read(&part->in_flight[0]) + atomic_read(&part->in_flight[1]); + if (part->partno) { + part = &part_to_disk(part)->part0; + inflight[1] = atomic_read(&part->in_flight[0]) + + atomic_read(&part->in_flight[1]); + } else + inflight[1] = 0; } static inline struct partition_meta_info *alloc_part_info(struct gendisk *disk) -- cgit v1.2.3 From f299b7c7a9dee64425e5965bd4f56dc024c1befc Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 8 Aug 2017 17:51:45 -0600 Subject: blk-mq: provide internal in-flight variant We don't have to inc/dec some counter, since we can just iterate the tags. That makes inc/dec a noop, but means we have to iterate busy tags to get an in-flight count. Reviewed-by: Bart Van Assche Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/genhd.h | 35 ++++++----------------------------- 1 file changed, 6 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index f2a3a26cdda1..ea652bfcd675 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -362,35 +362,12 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(cpu, gendiskp, field, subnd) \ part_stat_add(cpu, gendiskp, field, -subnd) -static inline void part_inc_in_flight(struct request_queue *q, - struct hd_struct *part, int rw) -{ - atomic_inc(&part->in_flight[rw]); - if (part->partno) - atomic_inc(&part_to_disk(part)->part0.in_flight[rw]); -} - -static inline void part_dec_in_flight(struct request_queue *q, - struct hd_struct *part, int rw) -{ - atomic_dec(&part->in_flight[rw]); - if (part->partno) - atomic_dec(&part_to_disk(part)->part0.in_flight[rw]); -} - -static inline void part_in_flight(struct request_queue *q, - struct hd_struct *part, - unsigned int inflight[2]) -{ - inflight[0] = atomic_read(&part->in_flight[0]) + - atomic_read(&part->in_flight[1]); - if (part->partno) { - part = &part_to_disk(part)->part0; - inflight[1] = atomic_read(&part->in_flight[0]) + - atomic_read(&part->in_flight[1]); - } else - inflight[1] = 0; -} +void part_in_flight(struct request_queue *q, struct hd_struct *part, + unsigned int inflight[2]); +void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, + int rw); +void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, + int rw); static inline struct partition_meta_info *alloc_part_info(struct gendisk *disk) { -- cgit v1.2.3 From 0a4a060bb204c47825eb4f7c27f66fc7ee85d508 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 9 Aug 2017 19:09:44 -0400 Subject: sock: fix zerocopy_success regression with msg_zerocopy Do not use uarg->zerocopy outside msg_zerocopy. In other paths the field is not explicitly initialized and aliases another field. Those paths have only one reference so do not need this intermediate variable. Call uarg->callback directly. Fixes: 1f8b977ab32d ("sock: enable MSG_ZEROCOPY") Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 8c0708d2e5e6..7594e19bce62 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1273,8 +1273,13 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { - uarg->zerocopy = uarg->zerocopy && zerocopy; - sock_zerocopy_put(uarg); + if (uarg->callback == sock_zerocopy_callback) { + uarg->zerocopy = uarg->zerocopy && zerocopy; + sock_zerocopy_put(uarg); + } else { + uarg->callback(uarg, zerocopy); + } + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; } } -- cgit v1.2.3 From bfe334924ccd9f4a53f30240c03cf2f43f5b2df1 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 2 Aug 2017 19:39:30 +0200 Subject: perf/x86: Fix RDPMC vs. mm_struct tracking Vince reported the following rdpmc() testcase failure: > Failing test case: > > fd=perf_event_open(); > addr=mmap(fd); > exec() // without closing or unmapping the event > fd=perf_event_open(); > addr=mmap(fd); > rdpmc() // GPFs due to rdpmc being disabled The problem is of course that exec() plays tricks with what is current->mm, only destroying the old mappings after having installed the new mm. Fix this confusion by passing along vma->vm_mm instead of relying on current->mm. Reported-by: Vince Weaver Tested-by: Vince Weaver Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: stable@vger.kernel.org Fixes: 1e0fb9ec679c ("perf: Add pmu callbacks to track event mapping and unmapping") Link: http://lkml.kernel.org/r/20170802173930.cstykcqefmqt7jau@hirez.programming.kicks-ass.net [ Minor cleanups. ] Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a3b873fc59e4..b14095bcf4bb 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -310,8 +310,8 @@ struct pmu { * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ - void (*event_mapped) (struct perf_event *event); /*optional*/ - void (*event_unmapped) (struct perf_event *event); /*optional*/ + void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ + void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are -- cgit v1.2.3 From 18f08dae19990f5fffde92e3a63e0d90cda0f1a8 Mon Sep 17 00:00:00 2001 From: Cheng Jian Date: Fri, 4 Aug 2017 17:19:37 +0800 Subject: sched/core: Remove unnecessary initialization init_idle_bootup_task() init_idle_bootup_task( ) is called in rest_init( ) to switch the scheduling class of the boot thread to the idle class. the function only sets: idle->sched_class = &idle_sched_class; which has been set in init_idle() called by sched_init(): /* * The idle tasks have their own, simple scheduling class: */ idle->sched_class = &idle_sched_class; We've already set the boot thread to idle class in start_kernel()->sched_init()->init_idle() so it's unnecessary to set it again in start_kernel()->rest_init()->init_idle_bootup_task() Signed-off-by: Cheng Jian Signed-off-by: Xie XiuQi Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1501838377-109720-1-git-send-email-cj.chengjian@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched/task.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index c97e5f096927..79a2a744648d 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -30,7 +30,6 @@ extern int lockdep_tasklist_lock_is_held(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); -extern void init_idle_bootup_task(struct task_struct *idle); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); extern void sched_dead(struct task_struct *p); -- cgit v1.2.3 From 74dc3384fc7983b78cc46ebb1824968a3db85eb1 Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Sun, 6 Aug 2017 14:41:41 +1000 Subject: sched/debug: Use task_pid_nr_ns in /proc/$pid/sched It appears as though the addition of the PID namespace did not update the output code for /proc/*/sched, which resulted in it providing PIDs that were not self-consistent with the /proc mount. This additionally made it trivial to detect whether a process was inside &init_pid_ns from userspace, making container detection trivial: https://github.com/jessfraz/amicontained This leads to situations such as: % unshare -pmf % mount -t proc proc /proc % head -n1 /proc/1/sched head (10047, #threads: 1) Fix this by just using task_pid_nr_ns for the output of /proc/*/sched. All of the other uses of task_pid_nr in kernel/sched/debug.c are from a sysctl context and thus don't need to be namespaced. Signed-off-by: Aleksa Sarai Signed-off-by: Peter Zijlstra (Intel) Acked-by: Eric W. Biederman Cc: Jess Frazelle Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: cyphar@cyphar.com Link: http://lkml.kernel.org/r/20170806044141.5093-1-asarai@suse.com Signed-off-by: Ingo Molnar --- include/linux/sched/debug.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/debug.h b/include/linux/sched/debug.h index e0eaee54c5a4..5d58d49e9f87 100644 --- a/include/linux/sched/debug.h +++ b/include/linux/sched/debug.h @@ -6,6 +6,7 @@ */ struct task_struct; +struct pid_namespace; extern void dump_cpu_task(int cpu); @@ -34,7 +35,8 @@ extern void sched_show_task(struct task_struct *p); #ifdef CONFIG_SCHED_DEBUG struct seq_file; -extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m); +extern void proc_sched_show_task(struct task_struct *p, + struct pid_namespace *ns, struct seq_file *m); extern void proc_sched_set_task(struct task_struct *p); #endif -- cgit v1.2.3 From 20435d84e5f2041c64c792399ab6f2948a2c2252 Mon Sep 17 00:00:00 2001 From: Xie XiuQi Date: Mon, 7 Aug 2017 16:44:23 +0800 Subject: sched/debug: Intruduce task_state_to_char() helper function Now that we have more than one place to get the task state, intruduce the task_state_to_char() helper function to save some code. No functionality changed. Signed-off-by: Xie XiuQi Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1502095463-160172-3-git-send-email-xiexiuqi@huawei.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8337e2db0bb2..c28b182c9833 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1229,6 +1229,19 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk) return task_pgrp_nr_ns(tsk, &init_pid_ns); } +static inline char task_state_to_char(struct task_struct *task) +{ + const char stat_nam[] = TASK_STATE_TO_CHAR_STR; + unsigned long state = task->state; + + state = state ? __ffs(state) + 1 : 0; + + /* Make sure the string lines up properly with the number of task states: */ + BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1); + + return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'; +} + /** * is_global_init - check if a task structure is init. Since init * is free to have sub-threads we need to check tgid. -- cgit v1.2.3 From 0aa1125fa8bc5e5f98317156728fa4d0293561a5 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Mon, 19 Jun 2017 21:02:12 +0300 Subject: locking/rwsem-spinlock: Add killable versions of __down_read() Rename __down_read() in __down_read_common() and teach it to abort waiting in case of pending signals and killable state argument passed. Note, that we shouldn't wake anybody up in EINTR path, as: We check for signal_pending_state() after (!waiter.task) test and under spinlock. So, current task wasn't able to be woken up. It may be in two cases: a writer is owner of the sem, or a writer is a first waiter of the sem. If a writer is owner of the sem, no one else may work with it in parallel. It will wake somebody, when it call up_write() or downgrade_write(). If a writer is the first waiter, it will be woken up, when the last active reader releases the sem, and sem->count became 0. Also note, that set_current_state() may be moved down to schedule() (after !waiter.task check), as all assignments in this type of semaphore (including wake_up), occur under spinlock, so we can't miss anything. Signed-off-by: Kirill Tkhai Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arnd@arndb.de Cc: avagin@virtuozzo.com Cc: davem@davemloft.net Cc: fenghua.yu@intel.com Cc: gorcunov@virtuozzo.com Cc: heiko.carstens@de.ibm.com Cc: hpa@zytor.com Cc: ink@jurassic.park.msu.ru Cc: mattst88@gmail.com Cc: rth@twiddle.net Cc: schwidefsky@de.ibm.com Cc: tony.luck@intel.com Link: http://lkml.kernel.org/r/149789533283.9059.9829416940494747182.stgit@localhost.localdomain Signed-off-by: Ingo Molnar --- include/linux/rwsem-spinlock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h index ae0528b834cd..e784761a4443 100644 --- a/include/linux/rwsem-spinlock.h +++ b/include/linux/rwsem-spinlock.h @@ -32,6 +32,7 @@ struct rw_semaphore { #define RWSEM_UNLOCKED_VALUE 0x00000000 extern void __down_read(struct rw_semaphore *sem); +extern int __must_check __down_read_killable(struct rw_semaphore *sem); extern int __down_read_trylock(struct rw_semaphore *sem); extern void __down_write(struct rw_semaphore *sem); extern int __must_check __down_write_killable(struct rw_semaphore *sem); -- cgit v1.2.3 From 83ced169d9a01f22eb39f1fcc1f89ad9d223238f Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Mon, 19 Jun 2017 21:02:26 +0300 Subject: locking/rwsem-xadd: Add killable versions of rwsem_down_read_failed() Rename rwsem_down_read_failed() in __rwsem_down_read_failed_common() and teach it to abort waiting in case of pending signals and killable state argument passed. Note, that we shouldn't wake anybody up in EINTR path, as: We check for (waiter.task) under spinlock before we go to out_nolock path. Current task wasn't able to be woken up, so there are a writer, owning the sem, or a writer, which is the first waiter. In the both cases we shouldn't wake anybody. If there is a writer, owning the sem, and we were the only waiter, remove RWSEM_WAITING_BIAS, as there are no waiters anymore. Signed-off-by: Kirill Tkhai Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: arnd@arndb.de Cc: avagin@virtuozzo.com Cc: davem@davemloft.net Cc: fenghua.yu@intel.com Cc: gorcunov@virtuozzo.com Cc: heiko.carstens@de.ibm.com Cc: hpa@zytor.com Cc: ink@jurassic.park.msu.ru Cc: mattst88@gmail.com Cc: rth@twiddle.net Cc: schwidefsky@de.ibm.com Cc: tony.luck@intel.com Link: http://lkml.kernel.org/r/149789534632.9059.2901382369609922565.stgit@localhost.localdomain Signed-off-by: Ingo Molnar --- include/linux/rwsem.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index dd1d14250340..0ad7318ff299 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -44,6 +44,7 @@ struct rw_semaphore { }; extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem); extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); -- cgit v1.2.3 From 1dbb6704de91b169a58d0c8221624afd6a95cfc7 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 1 Aug 2017 17:24:04 +0200 Subject: jump_label: Fix concurrent static_key_enable/disable() static_key_enable/disable are trying to cap the static key count to 0/1. However, their use of key->enabled is outside jump_label_lock so they do not really ensure that. Rewrite them to do a quick check for an already enabled (respectively, already disabled), and then recheck under the jump label lock. Unlike static_key_slow_inc/dec, a failed check under the jump label lock does not modify key->enabled. Signed-off-by: Paolo Bonzini Signed-off-by: Peter Zijlstra (Intel) Cc: Eric Dumazet Cc: Jason Baron Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1501601046-35683-2-git-send-email-pbonzini@redhat.com Signed-off-by: Ingo Molnar --- include/linux/jump_label.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 2afd74b9d844..740a42ea7f7f 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -234,22 +234,24 @@ static inline int jump_label_apply_nops(struct module *mod) static inline void static_key_enable(struct static_key *key) { - int count = static_key_count(key); - - WARN_ON_ONCE(count < 0 || count > 1); + STATIC_KEY_CHECK_USE(); - if (!count) - static_key_slow_inc(key); + if (atomic_read(&key->enabled) != 0) { + WARN_ON_ONCE(atomic_read(&key->enabled) != 1); + return; + } + atomic_set(&key->enabled, 1); } static inline void static_key_disable(struct static_key *key) { - int count = static_key_count(key); - - WARN_ON_ONCE(count < 0 || count > 1); + STATIC_KEY_CHECK_USE(); - if (count) - static_key_slow_dec(key); + if (atomic_read(&key->enabled) != 1) { + WARN_ON_ONCE(atomic_read(&key->enabled) != 0); + return; + } + atomic_set(&key->enabled, 0); } #define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } -- cgit v1.2.3 From be040bea9085a9c2b1700c9e60888777baeb96d5 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 1 Aug 2017 17:24:06 +0200 Subject: cpuset: Make nr_cpusets private Any use of key->enabled (that is static_key_enabled and static_key_count) outside jump_label_lock should handle its own serialization. In the case of cpusets_enabled_key, the key is always incremented/decremented under cpuset_mutex, and hence the same rule applies to nr_cpusets. The rule *is* respected currently, but the mutex is static so nr_cpusets should be static too. Signed-off-by: Paolo Bonzini Signed-off-by: Peter Zijlstra (Intel) Acked-by: Zefan Li Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1501601046-35683-4-git-send-email-pbonzini@redhat.com Signed-off-by: Ingo Molnar --- include/linux/cpuset.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 898cfe2eeb42..e74655d941b7 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -37,12 +37,6 @@ static inline bool cpusets_enabled(void) return static_branch_unlikely(&cpusets_enabled_key); } -static inline int nr_cpusets(void) -{ - /* jump label reference count + the top-level cpuset */ - return static_key_count(&cpusets_enabled_key.key) + 1; -} - static inline void cpuset_inc(void) { static_branch_inc(&cpusets_pre_enable_key); -- cgit v1.2.3 From 5a40527f8f0798553764fc8db4111d7d9c33ea51 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 1 Aug 2017 09:02:56 +0100 Subject: jump_label: Provide hotplug context variants As using the normal static key API under the hotplug lock is pretty much impossible, let's provide a variant of some of them that require the hotplug lock to have already been taken. These function are only meant to be used in CPU hotplug callbacks. Signed-off-by: Marc Zyngier Signed-off-by: Peter Zijlstra (Intel) Cc: Leo Yan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/20170801080257.5056-4-marc.zyngier@arm.com Signed-off-by: Ingo Molnar --- include/linux/jump_label.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 740a42ea7f7f..cd5861651b17 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -163,6 +163,8 @@ extern void jump_label_apply_nops(struct module *mod); extern int static_key_count(struct static_key *key); extern void static_key_enable(struct static_key *key); extern void static_key_disable(struct static_key *key); +extern void static_key_enable_cpuslocked(struct static_key *key); +extern void static_key_disable_cpuslocked(struct static_key *key); /* * We should be using ATOMIC_INIT() for initializing .enabled, but @@ -254,6 +256,9 @@ static inline void static_key_disable(struct static_key *key) atomic_set(&key->enabled, 0); } +#define static_key_enable_cpuslocked(k) static_key_enable((k)) +#define static_key_disable_cpuslocked(k) static_key_disable((k)) + #define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } #define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } @@ -415,8 +420,10 @@ extern bool ____wrong_branch_error(void); * Normal usage; boolean enable/disable. */ -#define static_branch_enable(x) static_key_enable(&(x)->key) -#define static_branch_disable(x) static_key_disable(&(x)->key) +#define static_branch_enable(x) static_key_enable(&(x)->key) +#define static_branch_disable(x) static_key_disable(&(x)->key) +#define static_branch_enable_cpuslocked(x) static_key_enable_cpuslocked(&(x)->key) +#define static_branch_disable_cpuslocked(x) static_key_disable_cpuslocked(&(x)->key) #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From 8b1b436dd1ccc8a1770af6e56eec047ad4920659 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 7 Jun 2017 18:05:07 +0200 Subject: mm, locking: Rework {set,clear,mm}_tlb_flush_pending() Commit: af2c1401e6f9 ("mm: numa: guarantee that tlb_flush_pending updates are visible before page table updates") added smp_mb__before_spinlock() to set_tlb_flush_pending(). I think we can solve the same problem without this barrier. If instead we mandate that mm_tlb_flush_pending() is used while holding the PTL we're guaranteed to observe prior set_tlb_flush_pending() instances. For this to work we need to rework migrate_misplaced_transhuge_page() a little and move the test up into do_huge_pmd_numa_page(). NOTE: this relies on flush_tlb_range() to guarantee: (1) it ensures that prior page table updates are visible to the page table walker and (2) it ensures that subsequent memory accesses are only made visible after the invalidation has completed This is required for architectures that implement TRANSPARENT_HUGEPAGE (arc, arm, arm64, mips, powerpc, s390, sparc, x86) or otherwise use mm_tlb_flush_pending() in their page-table operations (arm, arm64, x86). This appears true for: - arm (DSB ISB before and after), - arm64 (DSB ISHST before, and DSB ISH after), - powerpc (PTESYNC before and after), - s390 and x86 TLB invalidate are serializing instructions But I failed to understand the situation for: - arc, mips, sparc Now SPARC64 is a wee bit special in that flush_tlb_range() is a no-op and it flushes the TLBs using arch_{enter,leave}_lazy_mmu_mode() inside the PTL. It still needs to guarantee the PTL unlock happens _after_ the invalidate completes. Vineet, Ralf and Dave could you guys please have a look? Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Andrew Morton Cc: Benjamin Herrenschmidt Cc: David S. Miller Cc: Heiko Carstens Cc: Linus Torvalds Cc: Mel Gorman Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Rik van Riel Cc: Russell King Cc: Thomas Gleixner Cc: Vineet Gupta Signed-off-by: Ingo Molnar --- include/linux/mm_types.h | 33 +++++++++++++++++++++++++++------ 1 file changed, 27 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f384bb62d8e..36ea3cf7d85e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -531,23 +531,44 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) */ static inline bool mm_tlb_flush_pending(struct mm_struct *mm) { - barrier(); + /* + * Must be called with PTL held; such that our PTL acquire will have + * observed the store from set_tlb_flush_pending(). + */ return mm->tlb_flush_pending; } static inline void set_tlb_flush_pending(struct mm_struct *mm) { mm->tlb_flush_pending = true; - /* - * Guarantee that the tlb_flush_pending store does not leak into the - * critical section updating the page tables + * The only time this value is relevant is when there are indeed pages + * to flush. And we'll only flush pages after changing them, which + * requires the PTL. + * + * So the ordering here is: + * + * mm->tlb_flush_pending = true; + * spin_lock(&ptl); + * ... + * set_pte_at(); + * spin_unlock(&ptl); + * + * spin_lock(&ptl) + * mm_tlb_flush_pending(); + * .... + * spin_unlock(&ptl); + * + * flush_tlb_range(); + * mm->tlb_flush_pending = false; + * + * So the =true store is constrained by the PTL unlock, and the =false + * store is constrained by the TLB invalidate. */ - smp_mb__before_spinlock(); } /* Clearing is done after a TLB flush, which also provides a barrier. */ static inline void clear_tlb_flush_pending(struct mm_struct *mm) { - barrier(); + /* see set_tlb_flush_pending */ mm->tlb_flush_pending = false; } #else -- cgit v1.2.3 From d89e588ca4081615216cc25f2489b0281ac0bfe9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 5 Sep 2016 11:37:53 +0200 Subject: locking: Introduce smp_mb__after_spinlock() Since its inception, our understanding of ACQUIRE, esp. as applied to spinlocks, has changed somewhat. Also, I wonder if, with a simple change, we cannot make it provide more. The problem with the comment is that the STORE done by spin_lock isn't itself ordered by the ACQUIRE, and therefore a later LOAD can pass over it and cross with any prior STORE, rendering the default WMB insufficient (pointed out by Alan). Now, this is only really a problem on PowerPC and ARM64, both of which already defined smp_mb__before_spinlock() as a smp_mb(). At the same time, we can get a much stronger construct if we place that same barrier _inside_ the spin_lock(). In that case we upgrade the RCpc spinlock to an RCsc. That would make all schedule() calls fully transitive against one another. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Will Deacon Cc: Alan Stern Cc: Benjamin Herrenschmidt Cc: Linus Torvalds Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Oleg Nesterov Cc: Paul McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/atomic.h | 3 +++ include/linux/spinlock.h | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/atomic.h b/include/linux/atomic.h index c56be7410130..40d6bfec0e0d 100644 --- a/include/linux/atomic.h +++ b/include/linux/atomic.h @@ -38,6 +38,9 @@ * Besides, if an arch has a special barrier for acquire/release, it could * implement its own __atomic_op_* and use the same framework for building * variants + * + * If an architecture overrides __atomic_op_acquire() it will probably want + * to define smp_mb__after_spinlock(). */ #ifndef __atomic_op_acquire #define __atomic_op_acquire(op, args...) \ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index d9510e8522d4..840281095933 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -130,6 +130,42 @@ do { \ #define smp_mb__before_spinlock() smp_wmb() #endif +/* + * This barrier must provide two things: + * + * - it must guarantee a STORE before the spin_lock() is ordered against a + * LOAD after it, see the comments at its two usage sites. + * + * - it must ensure the critical section is RCsc. + * + * The latter is important for cases where we observe values written by other + * CPUs in spin-loops, without barriers, while being subject to scheduling. + * + * CPU0 CPU1 CPU2 + * + * for (;;) { + * if (READ_ONCE(X)) + * break; + * } + * X=1 + * + * + * r = X; + * + * without transitivity it could be that CPU1 observes X!=0 breaks the loop, + * we get migrated and CPU2 sees X==0. + * + * Since most load-store architectures implement ACQUIRE with an smp_mb() after + * the LL/SC loop, they need no further barriers. Similarly all our TSO + * architectures imply an smp_mb() for each atomic instruction and equally don't + * need more. + * + * Architectures that can implement ACQUIRE better need to take care. + */ +#ifndef smp_mb__after_spinlock +#define smp_mb__after_spinlock() do { } while (0) +#endif + /** * raw_spin_unlock_wait - wait until the spinlock gets unlocked * @lock: the spinlock in question. -- cgit v1.2.3 From a9668cd6ee288c4838bc668880ac085be551cac2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 7 Jun 2017 17:51:27 +0200 Subject: locking: Remove smp_mb__before_spinlock() Now that there are no users of smp_mb__before_spinlock() left, remove it entirely. Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/spinlock.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 840281095933..4e8cce19b507 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -117,19 +117,6 @@ do { \ #endif /*arch_spin_is_contended*/ #endif -/* - * Despite its name it doesn't necessarily has to be a full barrier. - * It should only guarantee that a STORE before the critical section - * can not be reordered with LOADs and STOREs inside this section. - * spin_lock() is the one-way barrier, this LOAD can not escape out - * of the region. So the default implementation simply ensures that - * a STORE can not move into the critical section, smp_wmb() should - * serialize it with another STORE done by spin_lock(). - */ -#ifndef smp_mb__before_spinlock -#define smp_mb__before_spinlock() smp_wmb() -#endif - /* * This barrier must provide two things: * -- cgit v1.2.3 From d92a8cfcb37ecd1315269dab741f073b63b3a8b6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 3 Mar 2017 10:13:38 +0100 Subject: locking/lockdep: Rework FS_RECLAIM annotation A while ago someone, and I cannot find the email just now, asked if we could not implement the RECLAIM_FS inversion stuff with a 'fake' lock like we use for other things like workqueues etc. I think this should be possible which allows reducing the 'irq' states and will reduce the amount of __bfs() lookups we do. Removing the 1 IRQ state results in 4 less __bfs() walks per dependency, improving lockdep performance. And by moving this annotation out of the lockdep code it becomes easier for the mm people to extend. Signed-off-by: Peter Zijlstra (Intel) Cc: Byungchul Park Cc: Linus Torvalds Cc: Mel Gorman Cc: Michal Hocko Cc: Nikolay Borisov Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: boqun.feng@gmail.com Cc: iamjoonsoo.kim@lge.com Cc: kernel-team@lge.com Cc: kirill@shutemov.name Cc: npiggin@gmail.com Cc: walken@google.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 11 ++--------- include/linux/sched.h | 1 - include/linux/sched/mm.h | 8 ++++++++ 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index fffe49f188e6..0a4c02c2d7a2 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -29,7 +29,7 @@ extern int lock_stat; * We'd rather not expose kernel/lockdep_states.h this wide, but we do need * the total number of states... :-( */ -#define XXX_LOCK_USAGE_STATES (1+3*4) +#define XXX_LOCK_USAGE_STATES (1+2*4) /* * NR_LOCKDEP_CACHING_CLASSES ... Number of classes @@ -363,10 +363,6 @@ static inline void lock_set_subclass(struct lockdep_map *lock, extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip); -extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask); -extern void lockdep_clear_current_reclaim_state(void); -extern void lockdep_trace_alloc(gfp_t mask); - struct pin_cookie { unsigned int val; }; #define NIL_COOKIE (struct pin_cookie){ .val = 0U, } @@ -375,7 +371,7 @@ extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock); extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie); extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie); -# define INIT_LOCKDEP .lockdep_recursion = 0, .lockdep_reclaim_gfp = 0, +# define INIT_LOCKDEP .lockdep_recursion = 0, #define lockdep_depth(tsk) (debug_locks ? (tsk)->lockdep_depth : 0) @@ -416,9 +412,6 @@ static inline void lockdep_on(void) # define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) -# define lockdep_set_current_reclaim_state(g) do { } while (0) -# define lockdep_clear_current_reclaim_state() do { } while (0) -# define lockdep_trace_alloc(g) do { } while (0) # define lockdep_info() do { } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) diff --git a/include/linux/sched.h b/include/linux/sched.h index 8337e2db0bb2..57db70ec70d0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -846,7 +846,6 @@ struct task_struct { int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; - gfp_t lockdep_reclaim_gfp; #endif #ifdef CONFIG_UBSAN diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2b24a6974847..2b0a281f9d26 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -167,6 +167,14 @@ static inline gfp_t current_gfp_context(gfp_t flags) return flags; } +#ifdef CONFIG_LOCKDEP +extern void fs_reclaim_acquire(gfp_t gfp_mask); +extern void fs_reclaim_release(gfp_t gfp_mask); +#else +static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } +static inline void fs_reclaim_release(gfp_t gfp_mask) { } +#endif + static inline unsigned int memalloc_noio_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOIO; -- cgit v1.2.3 From b09be676e0ff25bd6d2e7637e26d349f9109ad75 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Mon, 7 Aug 2017 16:12:52 +0900 Subject: locking/lockdep: Implement the 'crossrelease' feature Lockdep is a runtime locking correctness validator that detects and reports a deadlock or its possibility by checking dependencies between locks. It's useful since it does not report just an actual deadlock but also the possibility of a deadlock that has not actually happened yet. That enables problems to be fixed before they affect real systems. However, this facility is only applicable to typical locks, such as spinlocks and mutexes, which are normally released within the context in which they were acquired. However, synchronization primitives like page locks or completions, which are allowed to be released in any context, also create dependencies and can cause a deadlock. So lockdep should track these locks to do a better job. The 'crossrelease' implementation makes these primitives also be tracked. Signed-off-by: Byungchul Park Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: boqun.feng@gmail.com Cc: kernel-team@lge.com Cc: kirill@shutemov.name Cc: npiggin@gmail.com Cc: walken@google.com Cc: willy@infradead.org Link: http://lkml.kernel.org/r/1502089981-21272-6-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/irqflags.h | 24 +++++++++-- include/linux/lockdep.h | 110 ++++++++++++++++++++++++++++++++++++++++++++--- include/linux/sched.h | 8 ++++ 3 files changed, 131 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 5dd1272d1ab2..5fdd93bb9300 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -23,10 +23,26 @@ # define trace_softirq_context(p) ((p)->softirq_context) # define trace_hardirqs_enabled(p) ((p)->hardirqs_enabled) # define trace_softirqs_enabled(p) ((p)->softirqs_enabled) -# define trace_hardirq_enter() do { current->hardirq_context++; } while (0) -# define trace_hardirq_exit() do { current->hardirq_context--; } while (0) -# define lockdep_softirq_enter() do { current->softirq_context++; } while (0) -# define lockdep_softirq_exit() do { current->softirq_context--; } while (0) +# define trace_hardirq_enter() \ +do { \ + current->hardirq_context++; \ + crossrelease_hist_start(XHLOCK_HARD); \ +} while (0) +# define trace_hardirq_exit() \ +do { \ + current->hardirq_context--; \ + crossrelease_hist_end(XHLOCK_HARD); \ +} while (0) +# define lockdep_softirq_enter() \ +do { \ + current->softirq_context++; \ + crossrelease_hist_start(XHLOCK_SOFT); \ +} while (0) +# define lockdep_softirq_exit() \ +do { \ + current->softirq_context--; \ + crossrelease_hist_end(XHLOCK_SOFT); \ +} while (0) # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, #else # define trace_hardirqs_on() do { } while (0) diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 0a4c02c2d7a2..e1e0fcd99613 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -155,6 +155,12 @@ struct lockdep_map { int cpu; unsigned long ip; #endif +#ifdef CONFIG_LOCKDEP_CROSSRELEASE + /* + * Whether it's a crosslock. + */ + int cross; +#endif }; static inline void lockdep_copy_map(struct lockdep_map *to, @@ -258,8 +264,62 @@ struct held_lock { unsigned int hardirqs_off:1; unsigned int references:12; /* 32 bits */ unsigned int pin_count; +#ifdef CONFIG_LOCKDEP_CROSSRELEASE + /* + * Generation id. + * + * A value of cross_gen_id will be stored when holding this, + * which is globally increased whenever each crosslock is held. + */ + unsigned int gen_id; +#endif +}; + +#ifdef CONFIG_LOCKDEP_CROSSRELEASE +#define MAX_XHLOCK_TRACE_ENTRIES 5 + +/* + * This is for keeping locks waiting for commit so that true dependencies + * can be added at commit step. + */ +struct hist_lock { + /* + * Seperate stack_trace data. This will be used at commit step. + */ + struct stack_trace trace; + unsigned long trace_entries[MAX_XHLOCK_TRACE_ENTRIES]; + + /* + * Seperate hlock instance. This will be used at commit step. + * + * TODO: Use a smaller data structure containing only necessary + * data. However, we should make lockdep code able to handle the + * smaller one first. + */ + struct held_lock hlock; +}; + +/* + * To initialize a lock as crosslock, lockdep_init_map_crosslock() should + * be called instead of lockdep_init_map(). + */ +struct cross_lock { + /* + * Seperate hlock instance. This will be used at commit step. + * + * TODO: Use a smaller data structure containing only necessary + * data. However, we should make lockdep code able to handle the + * smaller one first. + */ + struct held_lock hlock; }; +struct lockdep_map_cross { + struct lockdep_map map; + struct cross_lock xlock; +}; +#endif + /* * Initialization, self-test and debugging-output methods: */ @@ -281,13 +341,6 @@ extern void lockdep_on(void); extern void lockdep_init_map(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass); -/* - * To initialize a lockdep_map statically use this macro. - * Note that _name must not be NULL. - */ -#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ - { .name = (_name), .key = (void *)(_key), } - /* * Reinitialize a lock key - for cases where there is special locking or * special initialization of locks so that the validator gets the scope @@ -460,6 +513,49 @@ struct pin_cookie { }; #endif /* !LOCKDEP */ +enum xhlock_context_t { + XHLOCK_HARD, + XHLOCK_SOFT, + XHLOCK_PROC, + XHLOCK_CTX_NR, +}; + +#ifdef CONFIG_LOCKDEP_CROSSRELEASE +extern void lockdep_init_map_crosslock(struct lockdep_map *lock, + const char *name, + struct lock_class_key *key, + int subclass); +extern void lock_commit_crosslock(struct lockdep_map *lock); + +#define STATIC_CROSS_LOCKDEP_MAP_INIT(_name, _key) \ + { .map.name = (_name), .map.key = (void *)(_key), \ + .map.cross = 1, } + +/* + * To initialize a lockdep_map statically use this macro. + * Note that _name must not be NULL. + */ +#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ + { .name = (_name), .key = (void *)(_key), .cross = 0, } + +extern void crossrelease_hist_start(enum xhlock_context_t c); +extern void crossrelease_hist_end(enum xhlock_context_t c); +extern void lockdep_init_task(struct task_struct *task); +extern void lockdep_free_task(struct task_struct *task); +#else +/* + * To initialize a lockdep_map statically use this macro. + * Note that _name must not be NULL. + */ +#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ + { .name = (_name), .key = (void *)(_key), } + +static inline void crossrelease_hist_start(enum xhlock_context_t c) {} +static inline void crossrelease_hist_end(enum xhlock_context_t c) {} +static inline void lockdep_init_task(struct task_struct *task) {} +static inline void lockdep_free_task(struct task_struct *task) {} +#endif + #ifdef CONFIG_LOCK_STAT extern void lock_contended(struct lockdep_map *lock, unsigned long ip); diff --git a/include/linux/sched.h b/include/linux/sched.h index 57db70ec70d0..5235fba537fc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -848,6 +848,14 @@ struct task_struct { struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif +#ifdef CONFIG_LOCKDEP_CROSSRELEASE +#define MAX_XHLOCKS_NR 64UL + struct hist_lock *xhlocks; /* Crossrelease history locks */ + unsigned int xhlock_idx; + /* For restoring at history boundaries */ + unsigned int xhlock_idx_hist[XHLOCK_CTX_NR]; +#endif + #ifdef CONFIG_UBSAN unsigned int in_ubsan; #endif -- cgit v1.2.3 From 23f873d8f9526ed7e49a1a02a45f8afb9ae5fb84 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Mon, 7 Aug 2017 16:12:53 +0900 Subject: locking/lockdep: Detect and handle hist_lock ring buffer overwrite The ring buffer can be overwritten by hardirq/softirq/work contexts. That cases must be considered on rollback or commit. For example, |<------ hist_lock ring buffer size ----->| ppppppppppppiiiiiiiiiiiiiiiiiiiiiiiiiiiiiii wrapped > iiiiiiiiiiiiiiiiiiiiiii.................... where 'p' represents an acquisition in process context, 'i' represents an acquisition in irq context. On irq exit, crossrelease tries to rollback idx to original position, but it should not because the entry already has been invalid by overwriting 'i'. Avoid rollback or commit for entries overwritten. Signed-off-by: Byungchul Park Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: boqun.feng@gmail.com Cc: kernel-team@lge.com Cc: kirill@shutemov.name Cc: npiggin@gmail.com Cc: walken@google.com Cc: willy@infradead.org Link: http://lkml.kernel.org/r/1502089981-21272-7-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 20 ++++++++++++++++++++ include/linux/sched.h | 3 +++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index e1e0fcd99613..c75eedd55af5 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -283,6 +283,26 @@ struct held_lock { * can be added at commit step. */ struct hist_lock { + /* + * Id for each entry in the ring buffer. This is used to + * decide whether the ring buffer was overwritten or not. + * + * For example, + * + * |<----------- hist_lock ring buffer size ------->| + * pppppppppppppppppppppiiiiiiiiiiiiiiiiiiiiiiiiiiiii + * wrapped > iiiiiiiiiiiiiiiiiiiiiiiiiii....................... + * + * where 'p' represents an acquisition in process + * context, 'i' represents an acquisition in irq + * context. + * + * In this example, the ring buffer was overwritten by + * acquisitions in irq context, that should be detected on + * rollback or commit. + */ + unsigned int hist_id; + /* * Seperate stack_trace data. This will be used at commit step. */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 5235fba537fc..772c5f643764 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -854,6 +854,9 @@ struct task_struct { unsigned int xhlock_idx; /* For restoring at history boundaries */ unsigned int xhlock_idx_hist[XHLOCK_CTX_NR]; + unsigned int hist_id; + /* For overwrite check at each context exit */ + unsigned int hist_id_save[XHLOCK_CTX_NR]; #endif #ifdef CONFIG_UBSAN -- cgit v1.2.3 From 28a903f63ec0811ead70ad0f8665e838d207a25e Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Mon, 7 Aug 2017 16:12:54 +0900 Subject: locking/lockdep: Handle non(or multi)-acquisition of a crosslock No acquisition might be in progress on commit of a crosslock. Completion operations enabling crossrelease are the case like: CONTEXT X CONTEXT Y --------- --------- trigger completion context complete AX commit AX wait_for_complete AX acquire AX wait where AX is a crosslock. When no acquisition is in progress, we should not perform commit because the lock does not exist, which might cause incorrect memory access. So we have to track the number of acquisitions of a crosslock to handle it. Moreover, in case that more than one acquisition of a crosslock are overlapped like: CONTEXT W CONTEXT X CONTEXT Y CONTEXT Z --------- --------- --------- --------- acquire AX (gen_id: 1) acquire A acquire AX (gen_id: 10) acquire B commit AX acquire C commit AX where A, B and C are typical locks and AX is a crosslock. Current crossrelease code performs commits in Y and Z with gen_id = 10. However, we can use gen_id = 1 to do it, since not only 'acquire AX in X' but 'acquire AX in W' also depends on each acquisition in Y and Z until their commits. So make it use gen_id = 1 instead of 10 on their commits, which adds an additional dependency 'AX -> A' in the example above. Signed-off-by: Byungchul Park Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: boqun.feng@gmail.com Cc: kernel-team@lge.com Cc: kirill@shutemov.name Cc: npiggin@gmail.com Cc: walken@google.com Cc: willy@infradead.org Link: http://lkml.kernel.org/r/1502089981-21272-8-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index c75eedd55af5..651cc61af041 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -324,6 +324,19 @@ struct hist_lock { * be called instead of lockdep_init_map(). */ struct cross_lock { + /* + * When more than one acquisition of crosslocks are overlapped, + * we have to perform commit for them based on cross_gen_id of + * the first acquisition, which allows us to add more true + * dependencies. + * + * Moreover, when no acquisition of a crosslock is in progress, + * we should not perform commit because the lock might not exist + * any more, which might cause incorrect memory access. So we + * have to track the number of acquisitions of a crosslock. + */ + int nr_acquire; + /* * Seperate hlock instance. This will be used at commit step. * @@ -547,9 +560,16 @@ extern void lockdep_init_map_crosslock(struct lockdep_map *lock, int subclass); extern void lock_commit_crosslock(struct lockdep_map *lock); +/* + * What we essencially have to initialize is 'nr_acquire'. Other members + * will be initialized in add_xlock(). + */ +#define STATIC_CROSS_LOCK_INIT() \ + { .nr_acquire = 0,} + #define STATIC_CROSS_LOCKDEP_MAP_INIT(_name, _key) \ { .map.name = (_name), .map.key = (void *)(_key), \ - .map.cross = 1, } + .map.cross = 1, .xlock = STATIC_CROSS_LOCK_INIT(), } /* * To initialize a lockdep_map statically use this macro. -- cgit v1.2.3 From cd8084f91c02c1afd256a39aa833bff737631304 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Mon, 7 Aug 2017 16:12:56 +0900 Subject: locking/lockdep: Apply crossrelease to completions Although wait_for_completion() and its family can cause deadlock, the lock correctness validator could not be applied to them until now, because things like complete() are usually called in a different context from the waiting context, which violates lockdep's assumption. Thanks to CONFIG_LOCKDEP_CROSSRELEASE, we can now apply the lockdep detector to those completion operations. Applied it. Signed-off-by: Byungchul Park Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: boqun.feng@gmail.com Cc: kernel-team@lge.com Cc: kirill@shutemov.name Cc: npiggin@gmail.com Cc: walken@google.com Cc: willy@infradead.org Link: http://lkml.kernel.org/r/1502089981-21272-10-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/completion.h | 45 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 44 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index 5d5aaae3af43..9bcebf509b4d 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -9,6 +9,9 @@ */ #include +#ifdef CONFIG_LOCKDEP_COMPLETE +#include +#endif /* * struct completion - structure used to maintain state for a "completion" @@ -25,10 +28,50 @@ struct completion { unsigned int done; wait_queue_head_t wait; +#ifdef CONFIG_LOCKDEP_COMPLETE + struct lockdep_map_cross map; +#endif }; +#ifdef CONFIG_LOCKDEP_COMPLETE +static inline void complete_acquire(struct completion *x) +{ + lock_acquire_exclusive((struct lockdep_map *)&x->map, 0, 0, NULL, _RET_IP_); +} + +static inline void complete_release(struct completion *x) +{ + lock_release((struct lockdep_map *)&x->map, 0, _RET_IP_); +} + +static inline void complete_release_commit(struct completion *x) +{ + lock_commit_crosslock((struct lockdep_map *)&x->map); +} + +#define init_completion(x) \ +do { \ + static struct lock_class_key __key; \ + lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map, \ + "(complete)" #x, \ + &__key, 0); \ + __init_completion(x); \ +} while (0) +#else +#define init_completion(x) __init_completion(x) +static inline void complete_acquire(struct completion *x) {} +static inline void complete_release(struct completion *x) {} +static inline void complete_release_commit(struct completion *x) {} +#endif + +#ifdef CONFIG_LOCKDEP_COMPLETE +#define COMPLETION_INITIALIZER(work) \ + { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \ + STATIC_CROSS_LOCKDEP_MAP_INIT("(complete)" #work, &(work)) } +#else #define COMPLETION_INITIALIZER(work) \ { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } +#endif #define COMPLETION_INITIALIZER_ONSTACK(work) \ ({ init_completion(&work); work; }) @@ -70,7 +113,7 @@ struct completion { * This inline function will initialize a dynamically created completion * structure. */ -static inline void init_completion(struct completion *x) +static inline void __init_completion(struct completion *x) { x->done = 0; init_waitqueue_head(&x->wait); -- cgit v1.2.3 From 90001d67be2fa2acbe3510d1f64fa6533efa30ef Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 31 Jul 2017 17:50:05 +0200 Subject: sched/fair: Fix wake_affine() for !NUMA_BALANCING In commit: 3fed382b46ba ("sched/numa: Implement NUMA node level wake_affine()") Rik changed wake_affine to consider NUMA information when balancing between LLC domains. There are a number of problems here which this patch tries to address: - LLC < NODE; in this case we'd use the wrong information to balance - !NUMA_BALANCING: in this case, the new code doesn't do any balancing at all - re-computes the NUMA data for every wakeup, this can mean iterating up to 64 CPUs for every wakeup. - default affine wakeups inside a cache We address these by saving the load/capacity values for each sched_domain during regular load-balance and using these values in wake_affine_llc(). The obvious down-side to using cached values is that they can be too old and poorly reflect reality. But this way we can use LLC wide information and thus not rely on assuming LLC matches NODE. We also don't rely on NUMA_BALANCING nor do we have to aggegate two nodes (or even cache domains) worth of CPUs for each wakeup. Signed-off-by: Peter Zijlstra (Intel) Cc: Josef Bacik Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Fixes: 3fed382b46ba ("sched/numa: Implement NUMA node level wake_affine()") [ Minor readability improvements. ] Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 7d065abc7a47..d7b6dab956ec 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -71,6 +71,14 @@ struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; + + /* + * Some variables from the most recent sd_lb_stats for this domain, + * used by wake_affine(). + */ + unsigned long nr_running; + unsigned long load; + unsigned long capacity; }; struct sched_domain { -- cgit v1.2.3 From e743eb1ecd5564b5ae0a4a76c1566f748a358839 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Aug 2017 08:25:38 -0600 Subject: block: remove unused syncfull/asyncfull queue flags We haven't used these in years, but somehow the definitions still remained. Kill them, and renumber the QUEUE_FLAG_ space. We had a hole in the beginning of the space, too. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 60 ++++++++++++++++++++++++-------------------------- 1 file changed, 29 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 25f6a0cb27d3..f45f157b2910 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -601,38 +601,36 @@ struct request_queue { u64 write_hints[BLK_MAX_WRITE_HINTS]; }; -#define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ -#define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ -#define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ -#define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */ -#define QUEUE_FLAG_DYING 5 /* queue being torn down */ -#define QUEUE_FLAG_BYPASS 6 /* act as dumb FIFO queue */ -#define QUEUE_FLAG_BIDI 7 /* queue supports bidi requests */ -#define QUEUE_FLAG_NOMERGES 8 /* disable merge attempts */ -#define QUEUE_FLAG_SAME_COMP 9 /* complete on same CPU-group */ -#define QUEUE_FLAG_FAIL_IO 10 /* fake timeout */ -#define QUEUE_FLAG_STACKABLE 11 /* supports request stacking */ -#define QUEUE_FLAG_NONROT 12 /* non-rotational device (SSD) */ +#define QUEUE_FLAG_QUEUED 0 /* uses generic tag queueing */ +#define QUEUE_FLAG_STOPPED 1 /* queue is stopped */ +#define QUEUE_FLAG_DYING 2 /* queue being torn down */ +#define QUEUE_FLAG_BYPASS 3 /* act as dumb FIFO queue */ +#define QUEUE_FLAG_BIDI 4 /* queue supports bidi requests */ +#define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ +#define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ +#define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ +#define QUEUE_FLAG_STACKABLE 8 /* supports request stacking */ +#define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 13 /* do IO stats */ -#define QUEUE_FLAG_DISCARD 14 /* supports DISCARD */ -#define QUEUE_FLAG_NOXMERGES 15 /* No extended merges */ -#define QUEUE_FLAG_ADD_RANDOM 16 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 17 /* supports secure erase */ -#define QUEUE_FLAG_SAME_FORCE 18 /* force complete on same CPU */ -#define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */ -#define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */ -#define QUEUE_FLAG_NO_SG_MERGE 21 /* don't attempt to merge SG segments*/ -#define QUEUE_FLAG_POLL 22 /* IO polling enabled if set */ -#define QUEUE_FLAG_WC 23 /* Write back caching */ -#define QUEUE_FLAG_FUA 24 /* device supports FUA writes */ -#define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */ -#define QUEUE_FLAG_DAX 26 /* device supports DAX */ -#define QUEUE_FLAG_STATS 27 /* track rq completion times */ -#define QUEUE_FLAG_POLL_STATS 28 /* collecting stats for hybrid polling */ -#define QUEUE_FLAG_REGISTERED 29 /* queue has been registered to a disk */ -#define QUEUE_FLAG_SCSI_PASSTHROUGH 30 /* queue supports SCSI commands */ -#define QUEUE_FLAG_QUIESCED 31 /* queue has been quiesced */ +#define QUEUE_FLAG_IO_STAT 10 /* do IO stats */ +#define QUEUE_FLAG_DISCARD 11 /* supports DISCARD */ +#define QUEUE_FLAG_NOXMERGES 12 /* No extended merges */ +#define QUEUE_FLAG_ADD_RANDOM 13 /* Contributes to random pool */ +#define QUEUE_FLAG_SECERASE 14 /* supports secure erase */ +#define QUEUE_FLAG_SAME_FORCE 15 /* force complete on same CPU */ +#define QUEUE_FLAG_DEAD 16 /* queue tear-down finished */ +#define QUEUE_FLAG_INIT_DONE 17 /* queue is initialized */ +#define QUEUE_FLAG_NO_SG_MERGE 18 /* don't attempt to merge SG segments*/ +#define QUEUE_FLAG_POLL 19 /* IO polling enabled if set */ +#define QUEUE_FLAG_WC 20 /* Write back caching */ +#define QUEUE_FLAG_FUA 21 /* device supports FUA writes */ +#define QUEUE_FLAG_FLUSH_NQ 22 /* flush not queueuable */ +#define QUEUE_FLAG_DAX 23 /* device supports DAX */ +#define QUEUE_FLAG_STATS 24 /* track rq completion times */ +#define QUEUE_FLAG_POLL_STATS 25 /* collecting stats for hybrid polling */ +#define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ +#define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ +#define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ -- cgit v1.2.3 From 229a71860547ec856b156179a9c6bef2de426f66 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 3 Aug 2017 11:38:21 +0900 Subject: irq: Make the irqentry text section unconditional Generate irqentry and softirqentry text sections without any Kconfig dependencies. This will add extra sections, but there should be no performace impact. Suggested-by: Ingo Molnar Signed-off-by: Masami Hiramatsu Cc: Ananth N Mavinakayanahalli Cc: Anil S Keshavamurthy Cc: Chris Zankel Cc: David S . Miller Cc: Francis Deslauriers Cc: Jesper Nilsson Cc: Linus Torvalds Cc: Max Filippov Cc: Mikael Starvik Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Yoshinori Sato Cc: linux-arch@vger.kernel.org Cc: linux-cris-kernel@axis.com Cc: mathieu.desnoyers@efficios.com Link: http://lkml.kernel.org/r/150172789110.27216.3955739126693102122.stgit@devbox Signed-off-by: Ingo Molnar --- include/linux/interrupt.h | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a2fddddb0d60..59ba11661b6e 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -18,6 +18,7 @@ #include #include #include +#include /* * These correspond to the IORESOURCE_IRQ_* defines in @@ -726,7 +727,6 @@ extern int early_irq_init(void); extern int arch_probe_nr_irqs(void); extern int arch_early_irq_init(void); -#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) /* * We want to know which function is an entrypoint of a hardirq or a softirq. */ @@ -734,16 +734,4 @@ extern int arch_early_irq_init(void); #define __softirq_entry \ __attribute__((__section__(".softirqentry.text"))) -/* Limits of hardirq entrypoints */ -extern char __irqentry_text_start[]; -extern char __irqentry_text_end[]; -/* Limits of softirq entrypoints */ -extern char __softirqentry_text_start[]; -extern char __softirqentry_text_end[]; - -#else -#define __irq_entry -#define __softirq_entry -#endif - #endif -- cgit v1.2.3 From fc53662f13b889a5a1c069e79ee1e3d4534df132 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 2 Aug 2017 18:09:14 +0200 Subject: x86/hyper-v: Make hv_do_hypercall() inline We have only three call sites for hv_do_hypercall() and we're going to change HVCALL_SIGNAL_EVENT to doing fast hypercall so we can inline this function for optimization. Hyper-V top level functional specification states that r9-r11 registers and flags may be clobbered by the hypervisor during hypercall and with inlining this is somewhat important, add the clobbers. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Andy Shevchenko Reviewed-by: Stephen Hemminger Cc: Andy Lutomirski Cc: Haiyang Zhang Cc: Jork Loeser Cc: K. Y. Srinivasan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Simon Xiao Cc: Steven Rostedt Cc: Thomas Gleixner Cc: devel@linuxdriverproject.org Link: http://lkml.kernel.org/r/20170802160921.21791-3-vkuznets@redhat.com Signed-off-by: Ingo Molnar --- include/linux/hyperv.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b7d7bbec74e0..6608a71e7d79 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1187,7 +1187,6 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, bool fb_overlap_ok); void vmbus_free_mmio(resource_size_t start, resource_size_t size); int vmbus_cpu_number_to_vp_number(int cpu_number); -u64 hv_do_hypercall(u64 control, void *input, void *output); /* * GUID definitions of various offer types - services offered to the guest. -- cgit v1.2.3 From 057841713cfff62b4485cdd2b245f05b7ea3ba16 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 2 Aug 2017 18:09:16 +0200 Subject: hyper-v: Use fast hypercall for HVCALL_SIGNAL_EVENT We need to pass only 8 bytes of input for HvSignalEvent which makes it a perfect fit for fast hypercall. hv_input_signal_event_buffer is not needed any more and hv_input_signal_event is converted to union for convenience. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Andy Shevchenko Reviewed-by: Stephen Hemminger Cc: Andy Lutomirski Cc: Haiyang Zhang Cc: Jork Loeser Cc: K. Y. Srinivasan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Simon Xiao Cc: Steven Rostedt Cc: Thomas Gleixner Cc: devel@linuxdriverproject.org Link: http://lkml.kernel.org/r/20170802160921.21791-5-vkuznets@redhat.com Signed-off-by: Ingo Molnar --- include/linux/hyperv.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6608a71e7d79..c472bd43bdd7 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -677,18 +677,6 @@ union hv_connection_id { } u; }; -/* Definition of the hv_signal_event hypercall input structure. */ -struct hv_input_signal_event { - union hv_connection_id connectionid; - u16 flag_number; - u16 rsvdz; -}; - -struct hv_input_signal_event_buffer { - u64 align8; - struct hv_input_signal_event event; -}; - enum hv_numa_policy { HV_BALANCED = 0, HV_LOCALIZED, @@ -770,8 +758,7 @@ struct vmbus_channel { } callback_mode; bool is_dedicated_interrupt; - struct hv_input_signal_event_buffer sig_buf; - struct hv_input_signal_event *sig_event; + u64 sig_event; /* * Starting with win8, this field will be used to specify -- cgit v1.2.3 From 7415aea6072bab15969b6c3c5b2a193d88095326 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 2 Aug 2017 18:09:18 +0200 Subject: hyper-v: Globalize vp_index To support implementing remote TLB flushing on Hyper-V with a hypercall we need to make vp_index available outside of vmbus module. Rename and globalize. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Andy Shevchenko Reviewed-by: Stephen Hemminger Cc: Andy Lutomirski Cc: Haiyang Zhang Cc: Jork Loeser Cc: K. Y. Srinivasan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Simon Xiao Cc: Steven Rostedt Cc: Thomas Gleixner Cc: devel@linuxdriverproject.org Link: http://lkml.kernel.org/r/20170802160921.21791-7-vkuznets@redhat.com Signed-off-by: Ingo Molnar --- include/linux/hyperv.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index c472bd43bdd7..e2a4fa57f110 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1173,7 +1173,6 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, resource_size_t size, resource_size_t align, bool fb_overlap_ok); void vmbus_free_mmio(resource_size_t start, resource_size_t size); -int vmbus_cpu_number_to_vp_number(int cpu_number); /* * GUID definitions of various offer types - services offered to the guest. -- cgit v1.2.3 From fc66ce0b72046318c4c4a66e67a2362193df6de1 Mon Sep 17 00:00:00 2001 From: Sekhar Nori Date: Thu, 10 Aug 2017 09:02:37 -0700 Subject: ARM: OMAP2+: Add pdata-quirks for MMC/SD on DRA74x EVM DRA74x EVM Rev H EVM comes with revision 2.0 silicon. However, earlier versions of EVM can come with either revision 1.1 or revision 1.0 of silicon. The device-tree file is written to support rev 2.0 of silicon. pdata quirks are used to then override the settings needed for PG 1.1 silicon. PG 1.1 silicon has limitations w.r.t frequencies at which MMC1/2/3 can operate as well as different IOdelay numbers. Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Sekhar Nori Signed-off-by: Tony Lindgren --- include/linux/platform_data/hsmmc-omap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/hsmmc-omap.h b/include/linux/platform_data/hsmmc-omap.h index 8e981be2e2c2..67bded22eae4 100644 --- a/include/linux/platform_data/hsmmc-omap.h +++ b/include/linux/platform_data/hsmmc-omap.h @@ -70,6 +70,9 @@ struct omap_hsmmc_platform_data { #define HSMMC_HAS_HSPE_SUPPORT (1 << 2) unsigned features; + /* string specifying a particular variant of hardware */ + char *version; + int gpio_cd; /* gpio (card detect) */ int gpio_cod; /* gpio (cover detect) */ int gpio_wp; /* gpio (write protect) */ -- cgit v1.2.3 From 606799cc5049ae4ccb51ba3242365ca2d411da13 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 10 Aug 2017 12:49:57 -0500 Subject: PCI: Inline and remove pcibios_update_irq() pcibios_update_irq() was a weak function with only one trivial implementation. Inline it and remove the weak function. Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 69034ab8a68e..a9e8d2f3bd91 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -844,7 +844,6 @@ char *pcibios_setup(char *str); resource_size_t pcibios_align_resource(void *, const struct resource *, resource_size_t, resource_size_t); -void pcibios_update_irq(struct pci_dev *, int irq); /* Weak but can be overriden by arch */ void pci_fixup_cardbus(struct pci_bus *); -- cgit v1.2.3 From 690cbb90a709c1b9389c6cb8e1978e77553ce0fb Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 10 Aug 2017 00:13:07 +0200 Subject: PM / s2idle: Rename PM_SUSPEND_FREEZE to PM_SUSPEND_TO_IDLE To make it clear that the symbol in question refers to suspend-to-idle, rename it from PM_SUSPEND_FREEZE to PM_SUSPEND_TO_IDLE. Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 8c3b0b1e6786..d43654be0097 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -33,10 +33,10 @@ static inline void pm_restore_console(void) typedef int __bitwise suspend_state_t; #define PM_SUSPEND_ON ((__force suspend_state_t) 0) -#define PM_SUSPEND_FREEZE ((__force suspend_state_t) 1) +#define PM_SUSPEND_TO_IDLE ((__force suspend_state_t) 1) #define PM_SUSPEND_STANDBY ((__force suspend_state_t) 2) #define PM_SUSPEND_MEM ((__force suspend_state_t) 3) -#define PM_SUSPEND_MIN PM_SUSPEND_FREEZE +#define PM_SUSPEND_MIN PM_SUSPEND_TO_IDLE #define PM_SUSPEND_MAX ((__force suspend_state_t) 4) enum suspend_stat_step { -- cgit v1.2.3 From f02f4f9d826590f1ef1b087374d3e3cfb7949eac Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 10 Aug 2017 00:13:56 +0200 Subject: PM / s2idle: Rename freeze_state enum and related items Rename the freeze_state enum representing the suspend-to-idle state machine states to s2idle_states and rename the related variables and functions accordingly. Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index d43654be0097..feb43dfbf7bc 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -237,22 +237,22 @@ static inline bool pm_resume_via_firmware(void) } /* Suspend-to-idle state machnine. */ -enum freeze_state { - FREEZE_STATE_NONE, /* Not suspended/suspending. */ - FREEZE_STATE_ENTER, /* Enter suspend-to-idle. */ - FREEZE_STATE_WAKE, /* Wake up from suspend-to-idle. */ +enum s2idle_states { + S2IDLE_STATE_NONE, /* Not suspended/suspending. */ + S2IDLE_STATE_ENTER, /* Enter suspend-to-idle. */ + S2IDLE_STATE_WAKE, /* Wake up from suspend-to-idle. */ }; -extern enum freeze_state __read_mostly suspend_freeze_state; +extern enum s2idle_states __read_mostly s2idle_state; -static inline bool idle_should_freeze(void) +static inline bool idle_should_enter_s2idle(void) { - return unlikely(suspend_freeze_state == FREEZE_STATE_ENTER); + return unlikely(s2idle_state == S2IDLE_STATE_ENTER); } extern void __init pm_states_init(void); extern void freeze_set_ops(const struct platform_freeze_ops *ops); -extern void freeze_wake(void); +extern void s2idle_wake(void); /** * arch_suspend_disable_irqs - disable IRQs for suspend @@ -284,10 +284,10 @@ static inline bool pm_resume_via_firmware(void) { return false; } static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } -static inline bool idle_should_freeze(void) { return false; } +static inline bool idle_should_enter_s2idle(void) { return false; } static inline void __init pm_states_init(void) {} static inline void freeze_set_ops(const struct platform_freeze_ops *ops) {} -static inline void freeze_wake(void) {} +static inline void s2idle_wake(void) {} #endif /* !CONFIG_SUSPEND */ /* struct pbe is used for creating lists of pages that should be restored -- cgit v1.2.3 From 28ba086ed30fb3fb714598aa029b894c3754fa7b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 10 Aug 2017 00:14:45 +0200 Subject: PM / s2idle: Rename ->enter_freeze to ->enter_s2idle Rename the ->enter_freeze cpuidle driver callback to ->enter_s2idle to make it clear that it is used for entering suspend-to-idle and rename the related functions, variables and so on accordingly. Signed-off-by: Rafael J. Wysocki --- include/linux/cpuidle.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index fc1e5d7fc1c7..f0e2e9223e66 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -52,11 +52,11 @@ struct cpuidle_state { int (*enter_dead) (struct cpuidle_device *dev, int index); /* - * CPUs execute ->enter_freeze with the local tick or entire timekeeping + * CPUs execute ->enter_s2idle with the local tick or entire timekeeping * suspended, so it must not re-enable interrupts at any point (even * temporarily) or attempt to change states of clock event devices. */ - void (*enter_freeze) (struct cpuidle_device *dev, + void (*enter_s2idle) (struct cpuidle_device *dev, struct cpuidle_driver *drv, int index); }; @@ -197,14 +197,14 @@ static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; } #ifdef CONFIG_CPU_IDLE extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev); -extern int cpuidle_enter_freeze(struct cpuidle_driver *drv, +extern int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern void cpuidle_use_deepest_state(bool enable); #else static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } -static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv, +static inline int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return -ENODEV; } static inline void cpuidle_use_deepest_state(bool enable) -- cgit v1.2.3 From 23d5855f4774f4f7c246a67057ecacc904696d8a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 10 Aug 2017 00:15:30 +0200 Subject: PM / s2idle: Rename platform operations structure Rename struct platform_freeze_ops to platform_s2idle_ops to make it clear that the callbacks in it are used during suspend-to-idle suspend/resume transitions and rename the related functions, variables and so on accordingly. Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index feb43dfbf7bc..0d41daf7e89d 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -186,7 +186,7 @@ struct platform_suspend_ops { void (*recover)(void); }; -struct platform_freeze_ops { +struct platform_s2idle_ops { int (*begin)(void); int (*prepare)(void); void (*wake)(void); @@ -251,7 +251,7 @@ static inline bool idle_should_enter_s2idle(void) } extern void __init pm_states_init(void); -extern void freeze_set_ops(const struct platform_freeze_ops *ops); +extern void s2idle_set_ops(const struct platform_s2idle_ops *ops); extern void s2idle_wake(void); /** @@ -286,7 +286,7 @@ static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } static inline bool idle_should_enter_s2idle(void) { return false; } static inline void __init pm_states_init(void) {} -static inline void freeze_set_ops(const struct platform_freeze_ops *ops) {} +static inline void s2idle_set_ops(const struct platform_s2idle_ops *ops) {} static inline void s2idle_wake(void) {} #endif /* !CONFIG_SUSPEND */ -- cgit v1.2.3 From 38e44da591303d08b0d965a033e11ade284999d0 Mon Sep 17 00:00:00 2001 From: Brian Bian Date: Wed, 9 Aug 2017 11:45:40 -0700 Subject: thermal: int3400_thermal: process "thermal table changed" event Some BIOS implement ACPI notification code 0x83 to indicate active relationship table(ART) and/or thermal relationship table(TRT) changes to INT3400 device. This event needs to be propagated to user space so that it can be handled by the user space thermal daemon. Signed-off-by: Brian Bian Signed-off-by: Zhang Rui --- include/linux/thermal.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index dab11f97e1c6..fd5b959c753c 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -102,6 +102,7 @@ enum thermal_notify_event { THERMAL_DEVICE_DOWN, /* Thermal device is down */ THERMAL_DEVICE_UP, /* Thermal device is up after a down event */ THERMAL_DEVICE_POWER_CAPABILITY_CHANGED, /* power capability changed */ + THERMAL_TABLE_CHANGED, /* Thermal table(s) changed */ }; struct thermal_zone_device_ops { -- cgit v1.2.3 From 3e48930cc74f0c212ee1838f89ad0ca7fcf2fea1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Aug 2017 05:49:01 -0700 Subject: cgroup: misc changes Misc trivial changes to prepare for future changes. No functional difference. * Expose cgroup_get(), cgroup_tryget() and cgroup_parent(). * Implement task_dfl_cgroup() which dereferences css_set->dfl_cgrp. * Rename cgroup_stats_show() to cgroup_stat_show() for consistency with the file name. Signed-off-by: Tejun Heo --- include/linux/cgroup.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 79faa6467f76..085056e562b1 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -398,6 +398,16 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) percpu_ref_put_many(&css->refcnt, n); } +static inline void cgroup_get(struct cgroup *cgrp) +{ + css_get(&cgrp->self); +} + +static inline bool cgroup_tryget(struct cgroup *cgrp) +{ + return css_tryget(&cgrp->self); +} + static inline void cgroup_put(struct cgroup *cgrp) { css_put(&cgrp->self); @@ -510,6 +520,20 @@ static inline struct cgroup *task_cgroup(struct task_struct *task, return task_css(task, subsys_id)->cgroup; } +static inline struct cgroup *task_dfl_cgroup(struct task_struct *task) +{ + return task_css_set(task)->dfl_cgrp; +} + +static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) +{ + struct cgroup_subsys_state *parent_css = cgrp->self.parent; + + if (parent_css) + return container_of(parent_css, struct cgroup, self); + return NULL; +} + /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested -- cgit v1.2.3 From 591b6bb605785c12a21e8b07a08a277065b655a5 Mon Sep 17 00:00:00 2001 From: Andrey Korolyov Date: Thu, 10 Aug 2017 13:21:14 +0300 Subject: cs5536: add support for IDE controller variant Several legacy devices such as Geode-based Cisco ASA appliances and DB800 development board do possess CS5536 IDE controller with different PCI id than existing one. Using pata_generic is not always feasible as at least DB800 requires MSR quirk from pata_cs5536 to be used with vendor firmware. Signed-off-by: Andrey Korolyov CC: stable@vger.kernel.org Signed-off-by: Tejun Heo --- include/linux/pci_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index c71e532da458..4adf6161ec77 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -576,6 +576,7 @@ #define PCI_DEVICE_ID_AMD_CS5536_EHC 0x2095 #define PCI_DEVICE_ID_AMD_CS5536_UDC 0x2096 #define PCI_DEVICE_ID_AMD_CS5536_UOC 0x2097 +#define PCI_DEVICE_ID_AMD_CS5536_DEV_IDE 0x2092 #define PCI_DEVICE_ID_AMD_CS5536_IDE 0x209A #define PCI_DEVICE_ID_AMD_LX_VIDEO 0x2081 #define PCI_DEVICE_ID_AMD_LX_AES 0x2082 -- cgit v1.2.3 From 45fff14bab00eea97e0f60a2a5ba3eca97bd476a Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Thu, 3 Aug 2017 11:14:13 +0200 Subject: iio: trigger: stm32-timer: add support for STM32H7 Add support for STM32H7 timer triggers: - Add new valids_table - Introduce compatible, with configuration data - Extend up to 15 timers, available on STM32H7 Signed-off-by: Fabrice Gasnier Signed-off-by: Jonathan Cameron --- include/linux/iio/timer/stm32-timer-trigger.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/timer/stm32-timer-trigger.h b/include/linux/iio/timer/stm32-timer-trigger.h index fa7d786ed99e..20f465353a7c 100644 --- a/include/linux/iio/timer/stm32-timer-trigger.h +++ b/include/linux/iio/timer/stm32-timer-trigger.h @@ -59,6 +59,8 @@ #define TIM12_CH1 "tim12_ch1" #define TIM12_CH2 "tim12_ch2" +#define TIM15_TRGO "tim15_trgo" + bool is_stm32_timer_trigger(struct iio_trigger *trig); #endif -- cgit v1.2.3 From 25892d6eac9cb752af95bcd539ed5e1158eba760 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Thu, 3 Aug 2017 11:14:14 +0200 Subject: iio: trigger: stm32-timer: add output compare triggers Add output compare trigger sources available on some instances. Signed-off-by: Fabrice Gasnier Signed-off-by: Jonathan Cameron --- include/linux/iio/timer/stm32-timer-trigger.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iio/timer/stm32-timer-trigger.h b/include/linux/iio/timer/stm32-timer-trigger.h index 20f465353a7c..d68add80ab86 100644 --- a/include/linux/iio/timer/stm32-timer-trigger.h +++ b/include/linux/iio/timer/stm32-timer-trigger.h @@ -55,12 +55,24 @@ #define TIM9_CH1 "tim9_ch1" #define TIM9_CH2 "tim9_ch2" +#define TIM10_OC1 "tim10_oc1" + +#define TIM11_OC1 "tim11_oc1" + #define TIM12_TRGO "tim12_trgo" #define TIM12_CH1 "tim12_ch1" #define TIM12_CH2 "tim12_ch2" +#define TIM13_OC1 "tim13_oc1" + +#define TIM14_OC1 "tim14_oc1" + #define TIM15_TRGO "tim15_trgo" +#define TIM16_OC1 "tim16_oc1" + +#define TIM17_OC1 "tim17_oc1" + bool is_stm32_timer_trigger(struct iio_trigger *trig); #endif -- cgit v1.2.3 From d4092d76a4a4e57b65910899948a83cc8646c5a5 Mon Sep 17 00:00:00 2001 From: Boris Brezillon Date: Fri, 4 Aug 2017 17:29:10 +0200 Subject: mtd: nand: Rename nand.h into rawnand.h We are planning to share more code between different NAND based devices (SPI NAND, OneNAND and raw NANDs), but before doing that we need to move the existing include/linux/mtd/nand.h file into include/linux/mtd/rawnand.h so we can later create a nand.h header containing all common structure and function prototypes. Signed-off-by: Boris Brezillon Signed-off-by: Peter Pan Acked-by: Vladimir Zapolskiy Acked-by: Alexander Sverdlin Acked-by: Wenyou Yang Acked-by: Krzysztof Kozlowski Acked-by: Han Xu Acked-by: H Hartley Sweeten Acked-by: Shawn Guo Acked-by: Gregory CLEMENT Acked-by: Neil Armstrong Acked-by: Masahiro Yamada Acked-By: Harvey Hunt Acked-by: Tony Lindgren Acked-by: Krzysztof Halasa --- include/linux/mtd/nand-gpio.h | 2 +- include/linux/mtd/nand.h | 1331 ------------------------ include/linux/mtd/rawnand.h | 1329 +++++++++++++++++++++++ include/linux/mtd/sh_flctl.h | 2 +- include/linux/mtd/sharpsl.h | 2 +- include/linux/platform_data/mtd-davinci.h | 2 +- include/linux/platform_data/mtd-nand-s3c2410.h | 2 +- 7 files changed, 1334 insertions(+), 1336 deletions(-) delete mode 100644 include/linux/mtd/nand.h create mode 100644 include/linux/mtd/rawnand.h (limited to 'include/linux') diff --git a/include/linux/mtd/nand-gpio.h b/include/linux/mtd/nand-gpio.h index 51534e50f7fc..be4f45d89be2 100644 --- a/include/linux/mtd/nand-gpio.h +++ b/include/linux/mtd/nand-gpio.h @@ -1,7 +1,7 @@ #ifndef __LINUX_MTD_NAND_GPIO_H #define __LINUX_MTD_NAND_GPIO_H -#include +#include struct gpio_nand_platdata { int gpio_nce; diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h deleted file mode 100644 index 892148c448cc..000000000000 --- a/include/linux/mtd/nand.h +++ /dev/null @@ -1,1331 +0,0 @@ -/* - * linux/include/linux/mtd/nand.h - * - * Copyright © 2000-2010 David Woodhouse - * Steven J. Hill - * Thomas Gleixner - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Info: - * Contains standard defines and IDs for NAND flash devices - * - * Changelog: - * See git changelog. - */ -#ifndef __LINUX_MTD_NAND_H -#define __LINUX_MTD_NAND_H - -#include -#include -#include -#include -#include - -struct mtd_info; -struct nand_flash_dev; -struct device_node; - -/* Scan and identify a NAND device */ -int nand_scan(struct mtd_info *mtd, int max_chips); -/* - * Separate phases of nand_scan(), allowing board driver to intervene - * and override command or ECC setup according to flash type. - */ -int nand_scan_ident(struct mtd_info *mtd, int max_chips, - struct nand_flash_dev *table); -int nand_scan_tail(struct mtd_info *mtd); - -/* Unregister the MTD device and free resources held by the NAND device */ -void nand_release(struct mtd_info *mtd); - -/* Internal helper for board drivers which need to override command function */ -void nand_wait_ready(struct mtd_info *mtd); - -/* locks all blocks present in the device */ -int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len); - -/* unlocks specified locked blocks */ -int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); - -/* The maximum number of NAND chips in an array */ -#define NAND_MAX_CHIPS 8 - -/* - * Constants for hardware specific CLE/ALE/NCE function - * - * These are bits which can be or'ed to set/clear multiple - * bits in one go. - */ -/* Select the chip by setting nCE to low */ -#define NAND_NCE 0x01 -/* Select the command latch by setting CLE to high */ -#define NAND_CLE 0x02 -/* Select the address latch by setting ALE to high */ -#define NAND_ALE 0x04 - -#define NAND_CTRL_CLE (NAND_NCE | NAND_CLE) -#define NAND_CTRL_ALE (NAND_NCE | NAND_ALE) -#define NAND_CTRL_CHANGE 0x80 - -/* - * Standard NAND flash commands - */ -#define NAND_CMD_READ0 0 -#define NAND_CMD_READ1 1 -#define NAND_CMD_RNDOUT 5 -#define NAND_CMD_PAGEPROG 0x10 -#define NAND_CMD_READOOB 0x50 -#define NAND_CMD_ERASE1 0x60 -#define NAND_CMD_STATUS 0x70 -#define NAND_CMD_SEQIN 0x80 -#define NAND_CMD_RNDIN 0x85 -#define NAND_CMD_READID 0x90 -#define NAND_CMD_ERASE2 0xd0 -#define NAND_CMD_PARAM 0xec -#define NAND_CMD_GET_FEATURES 0xee -#define NAND_CMD_SET_FEATURES 0xef -#define NAND_CMD_RESET 0xff - -#define NAND_CMD_LOCK 0x2a -#define NAND_CMD_UNLOCK1 0x23 -#define NAND_CMD_UNLOCK2 0x24 - -/* Extended commands for large page devices */ -#define NAND_CMD_READSTART 0x30 -#define NAND_CMD_RNDOUTSTART 0xE0 -#define NAND_CMD_CACHEDPROG 0x15 - -#define NAND_CMD_NONE -1 - -/* Status bits */ -#define NAND_STATUS_FAIL 0x01 -#define NAND_STATUS_FAIL_N1 0x02 -#define NAND_STATUS_TRUE_READY 0x20 -#define NAND_STATUS_READY 0x40 -#define NAND_STATUS_WP 0x80 - -#define NAND_DATA_IFACE_CHECK_ONLY -1 - -/* - * Constants for ECC_MODES - */ -typedef enum { - NAND_ECC_NONE, - NAND_ECC_SOFT, - NAND_ECC_HW, - NAND_ECC_HW_SYNDROME, - NAND_ECC_HW_OOB_FIRST, - NAND_ECC_ON_DIE, -} nand_ecc_modes_t; - -enum nand_ecc_algo { - NAND_ECC_UNKNOWN, - NAND_ECC_HAMMING, - NAND_ECC_BCH, -}; - -/* - * Constants for Hardware ECC - */ -/* Reset Hardware ECC for read */ -#define NAND_ECC_READ 0 -/* Reset Hardware ECC for write */ -#define NAND_ECC_WRITE 1 -/* Enable Hardware ECC before syndrome is read back from flash */ -#define NAND_ECC_READSYN 2 - -/* - * Enable generic NAND 'page erased' check. This check is only done when - * ecc.correct() returns -EBADMSG. - * Set this flag if your implementation does not fix bitflips in erased - * pages and you want to rely on the default implementation. - */ -#define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) -#define NAND_ECC_MAXIMIZE BIT(1) -/* - * If your controller already sends the required NAND commands when - * reading or writing a page, then the framework is not supposed to - * send READ0 and SEQIN/PAGEPROG respectively. - */ -#define NAND_ECC_CUSTOM_PAGE_ACCESS BIT(2) - -/* Bit mask for flags passed to do_nand_read_ecc */ -#define NAND_GET_DEVICE 0x80 - - -/* - * Option constants for bizarre disfunctionality and real - * features. - */ -/* Buswidth is 16 bit */ -#define NAND_BUSWIDTH_16 0x00000002 -/* Chip has cache program function */ -#define NAND_CACHEPRG 0x00000008 -/* - * Chip requires ready check on read (for auto-incremented sequential read). - * True only for small page devices; large page devices do not support - * autoincrement. - */ -#define NAND_NEED_READRDY 0x00000100 - -/* Chip does not allow subpage writes */ -#define NAND_NO_SUBPAGE_WRITE 0x00000200 - -/* Device is one of 'new' xD cards that expose fake nand command set */ -#define NAND_BROKEN_XD 0x00000400 - -/* Device behaves just like nand, but is readonly */ -#define NAND_ROM 0x00000800 - -/* Device supports subpage reads */ -#define NAND_SUBPAGE_READ 0x00001000 - -/* - * Some MLC NANDs need data scrambling to limit bitflips caused by repeated - * patterns. - */ -#define NAND_NEED_SCRAMBLING 0x00002000 - -/* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG - -/* Macros to identify the above */ -#define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) -#define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) -#define NAND_HAS_SUBPAGE_WRITE(chip) !((chip)->options & NAND_NO_SUBPAGE_WRITE) - -/* Non chip related options */ -/* This option skips the bbt scan during initialization. */ -#define NAND_SKIP_BBTSCAN 0x00010000 -/* - * This option is defined if the board driver allocates its own buffers - * (e.g. because it needs them DMA-coherent). - */ -#define NAND_OWN_BUFFERS 0x00020000 -/* Chip may not exist, so silence any errors in scan */ -#define NAND_SCAN_SILENT_NODEV 0x00040000 -/* - * Autodetect nand buswidth with readid/onfi. - * This suppose the driver will configure the hardware in 8 bits mode - * when calling nand_scan_ident, and update its configuration - * before calling nand_scan_tail. - */ -#define NAND_BUSWIDTH_AUTO 0x00080000 -/* - * This option could be defined by controller drivers to protect against - * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers - */ -#define NAND_USE_BOUNCE_BUFFER 0x00100000 - -/* - * In case your controller is implementing ->cmd_ctrl() and is relying on the - * default ->cmdfunc() implementation, you may want to let the core handle the - * tCCS delay which is required when a column change (RNDIN or RNDOUT) is - * requested. - * If your controller already takes care of this delay, you don't need to set - * this flag. - */ -#define NAND_WAIT_TCCS 0x00200000 - -/* Options set by nand scan */ -/* Nand scan has allocated controller struct */ -#define NAND_CONTROLLER_ALLOC 0x80000000 - -/* Cell info constants */ -#define NAND_CI_CHIPNR_MSK 0x03 -#define NAND_CI_CELLTYPE_MSK 0x0C -#define NAND_CI_CELLTYPE_SHIFT 2 - -/* Keep gcc happy */ -struct nand_chip; - -/* ONFI features */ -#define ONFI_FEATURE_16_BIT_BUS (1 << 0) -#define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) - -/* ONFI timing mode, used in both asynchronous and synchronous mode */ -#define ONFI_TIMING_MODE_0 (1 << 0) -#define ONFI_TIMING_MODE_1 (1 << 1) -#define ONFI_TIMING_MODE_2 (1 << 2) -#define ONFI_TIMING_MODE_3 (1 << 3) -#define ONFI_TIMING_MODE_4 (1 << 4) -#define ONFI_TIMING_MODE_5 (1 << 5) -#define ONFI_TIMING_MODE_UNKNOWN (1 << 6) - -/* ONFI feature address */ -#define ONFI_FEATURE_ADDR_TIMING_MODE 0x1 - -/* Vendor-specific feature address (Micron) */ -#define ONFI_FEATURE_ADDR_READ_RETRY 0x89 -#define ONFI_FEATURE_ON_DIE_ECC 0x90 -#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) - -/* ONFI subfeature parameters length */ -#define ONFI_SUBFEATURE_PARAM_LEN 4 - -/* ONFI optional commands SET/GET FEATURES supported? */ -#define ONFI_OPT_CMD_SET_GET_FEATURES (1 << 2) - -struct nand_onfi_params { - /* rev info and features block */ - /* 'O' 'N' 'F' 'I' */ - u8 sig[4]; - __le16 revision; - __le16 features; - __le16 opt_cmd; - u8 reserved0[2]; - __le16 ext_param_page_length; /* since ONFI 2.1 */ - u8 num_of_param_pages; /* since ONFI 2.1 */ - u8 reserved1[17]; - - /* manufacturer information block */ - char manufacturer[12]; - char model[20]; - u8 jedec_id; - __le16 date_code; - u8 reserved2[13]; - - /* memory organization block */ - __le32 byte_per_page; - __le16 spare_bytes_per_page; - __le32 data_bytes_per_ppage; - __le16 spare_bytes_per_ppage; - __le32 pages_per_block; - __le32 blocks_per_lun; - u8 lun_count; - u8 addr_cycles; - u8 bits_per_cell; - __le16 bb_per_lun; - __le16 block_endurance; - u8 guaranteed_good_blocks; - __le16 guaranteed_block_endurance; - u8 programs_per_page; - u8 ppage_attr; - u8 ecc_bits; - u8 interleaved_bits; - u8 interleaved_ops; - u8 reserved3[13]; - - /* electrical parameter block */ - u8 io_pin_capacitance_max; - __le16 async_timing_mode; - __le16 program_cache_timing_mode; - __le16 t_prog; - __le16 t_bers; - __le16 t_r; - __le16 t_ccs; - __le16 src_sync_timing_mode; - u8 src_ssync_features; - __le16 clk_pin_capacitance_typ; - __le16 io_pin_capacitance_typ; - __le16 input_pin_capacitance_typ; - u8 input_pin_capacitance_max; - u8 driver_strength_support; - __le16 t_int_r; - __le16 t_adl; - u8 reserved4[8]; - - /* vendor */ - __le16 vendor_revision; - u8 vendor[88]; - - __le16 crc; -} __packed; - -#define ONFI_CRC_BASE 0x4F4E - -/* Extended ECC information Block Definition (since ONFI 2.1) */ -struct onfi_ext_ecc_info { - u8 ecc_bits; - u8 codeword_size; - __le16 bb_per_lun; - __le16 block_endurance; - u8 reserved[2]; -} __packed; - -#define ONFI_SECTION_TYPE_0 0 /* Unused section. */ -#define ONFI_SECTION_TYPE_1 1 /* for additional sections. */ -#define ONFI_SECTION_TYPE_2 2 /* for ECC information. */ -struct onfi_ext_section { - u8 type; - u8 length; -} __packed; - -#define ONFI_EXT_SECTION_MAX 8 - -/* Extended Parameter Page Definition (since ONFI 2.1) */ -struct onfi_ext_param_page { - __le16 crc; - u8 sig[4]; /* 'E' 'P' 'P' 'S' */ - u8 reserved0[10]; - struct onfi_ext_section sections[ONFI_EXT_SECTION_MAX]; - - /* - * The actual size of the Extended Parameter Page is in - * @ext_param_page_length of nand_onfi_params{}. - * The following are the variable length sections. - * So we do not add any fields below. Please see the ONFI spec. - */ -} __packed; - -struct jedec_ecc_info { - u8 ecc_bits; - u8 codeword_size; - __le16 bb_per_lun; - __le16 block_endurance; - u8 reserved[2]; -} __packed; - -/* JEDEC features */ -#define JEDEC_FEATURE_16_BIT_BUS (1 << 0) - -struct nand_jedec_params { - /* rev info and features block */ - /* 'J' 'E' 'S' 'D' */ - u8 sig[4]; - __le16 revision; - __le16 features; - u8 opt_cmd[3]; - __le16 sec_cmd; - u8 num_of_param_pages; - u8 reserved0[18]; - - /* manufacturer information block */ - char manufacturer[12]; - char model[20]; - u8 jedec_id[6]; - u8 reserved1[10]; - - /* memory organization block */ - __le32 byte_per_page; - __le16 spare_bytes_per_page; - u8 reserved2[6]; - __le32 pages_per_block; - __le32 blocks_per_lun; - u8 lun_count; - u8 addr_cycles; - u8 bits_per_cell; - u8 programs_per_page; - u8 multi_plane_addr; - u8 multi_plane_op_attr; - u8 reserved3[38]; - - /* electrical parameter block */ - __le16 async_sdr_speed_grade; - __le16 toggle_ddr_speed_grade; - __le16 sync_ddr_speed_grade; - u8 async_sdr_features; - u8 toggle_ddr_features; - u8 sync_ddr_features; - __le16 t_prog; - __le16 t_bers; - __le16 t_r; - __le16 t_r_multi_plane; - __le16 t_ccs; - __le16 io_pin_capacitance_typ; - __le16 input_pin_capacitance_typ; - __le16 clk_pin_capacitance_typ; - u8 driver_strength_support; - __le16 t_adl; - u8 reserved4[36]; - - /* ECC and endurance block */ - u8 guaranteed_good_blocks; - __le16 guaranteed_block_endurance; - struct jedec_ecc_info ecc_info[4]; - u8 reserved5[29]; - - /* reserved */ - u8 reserved6[148]; - - /* vendor */ - __le16 vendor_rev_num; - u8 reserved7[88]; - - /* CRC for Parameter Page */ - __le16 crc; -} __packed; - -/** - * struct nand_id - NAND id structure - * @data: buffer containing the id bytes. Currently 8 bytes large, but can - * be extended if required. - * @len: ID length. - */ -struct nand_id { - u8 data[8]; - int len; -}; - -/** - * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices - * @lock: protection lock - * @active: the mtd device which holds the controller currently - * @wq: wait queue to sleep on if a NAND operation is in - * progress used instead of the per chip wait queue - * when a hw controller is available. - */ -struct nand_hw_control { - spinlock_t lock; - struct nand_chip *active; - wait_queue_head_t wq; -}; - -static inline void nand_hw_control_init(struct nand_hw_control *nfc) -{ - nfc->active = NULL; - spin_lock_init(&nfc->lock); - init_waitqueue_head(&nfc->wq); -} - -/** - * struct nand_ecc_step_info - ECC step information of ECC engine - * @stepsize: data bytes per ECC step - * @strengths: array of supported strengths - * @nstrengths: number of supported strengths - */ -struct nand_ecc_step_info { - int stepsize; - const int *strengths; - int nstrengths; -}; - -/** - * struct nand_ecc_caps - capability of ECC engine - * @stepinfos: array of ECC step information - * @nstepinfos: number of ECC step information - * @calc_ecc_bytes: driver's hook to calculate ECC bytes per step - */ -struct nand_ecc_caps { - const struct nand_ecc_step_info *stepinfos; - int nstepinfos; - int (*calc_ecc_bytes)(int step_size, int strength); -}; - -/* a shorthand to generate struct nand_ecc_caps with only one ECC stepsize */ -#define NAND_ECC_CAPS_SINGLE(__name, __calc, __step, ...) \ -static const int __name##_strengths[] = { __VA_ARGS__ }; \ -static const struct nand_ecc_step_info __name##_stepinfo = { \ - .stepsize = __step, \ - .strengths = __name##_strengths, \ - .nstrengths = ARRAY_SIZE(__name##_strengths), \ -}; \ -static const struct nand_ecc_caps __name = { \ - .stepinfos = &__name##_stepinfo, \ - .nstepinfos = 1, \ - .calc_ecc_bytes = __calc, \ -} - -/** - * struct nand_ecc_ctrl - Control structure for ECC - * @mode: ECC mode - * @algo: ECC algorithm - * @steps: number of ECC steps per page - * @size: data bytes per ECC step - * @bytes: ECC bytes per step - * @strength: max number of correctible bits per ECC step - * @total: total number of ECC bytes per page - * @prepad: padding information for syndrome based ECC generators - * @postpad: padding information for syndrome based ECC generators - * @options: ECC specific options (see NAND_ECC_XXX flags defined above) - * @priv: pointer to private ECC control data - * @hwctl: function to control hardware ECC generator. Must only - * be provided if an hardware ECC is available - * @calculate: function for ECC calculation or readback from ECC hardware - * @correct: function for ECC correction, matching to ECC generator (sw/hw). - * Should return a positive number representing the number of - * corrected bitflips, -EBADMSG if the number of bitflips exceed - * ECC strength, or any other error code if the error is not - * directly related to correction. - * If -EBADMSG is returned the input buffers should be left - * untouched. - * @read_page_raw: function to read a raw page without ECC. This function - * should hide the specific layout used by the ECC - * controller and always return contiguous in-band and - * out-of-band data even if they're not stored - * contiguously on the NAND chip (e.g. - * NAND_ECC_HW_SYNDROME interleaves in-band and - * out-of-band data). - * @write_page_raw: function to write a raw page without ECC. This function - * should hide the specific layout used by the ECC - * controller and consider the passed data as contiguous - * in-band and out-of-band data. ECC controller is - * responsible for doing the appropriate transformations - * to adapt to its specific layout (e.g. - * NAND_ECC_HW_SYNDROME interleaves in-band and - * out-of-band data). - * @read_page: function to read a page according to the ECC generator - * requirements; returns maximum number of bitflips corrected in - * any single ECC step, -EIO hw error - * @read_subpage: function to read parts of the page covered by ECC; - * returns same as read_page() - * @write_subpage: function to write parts of the page covered by ECC. - * @write_page: function to write a page according to the ECC generator - * requirements. - * @write_oob_raw: function to write chip OOB data without ECC - * @read_oob_raw: function to read chip OOB data without ECC - * @read_oob: function to read chip OOB data - * @write_oob: function to write chip OOB data - */ -struct nand_ecc_ctrl { - nand_ecc_modes_t mode; - enum nand_ecc_algo algo; - int steps; - int size; - int bytes; - int total; - int strength; - int prepad; - int postpad; - unsigned int options; - void *priv; - void (*hwctl)(struct mtd_info *mtd, int mode); - int (*calculate)(struct mtd_info *mtd, const uint8_t *dat, - uint8_t *ecc_code); - int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, - uint8_t *calc_ecc); - int (*read_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page); - int (*write_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page); - int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page); - int (*read_subpage)(struct mtd_info *mtd, struct nand_chip *chip, - uint32_t offs, uint32_t len, uint8_t *buf, int page); - int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, - uint32_t offset, uint32_t data_len, - const uint8_t *data_buf, int oob_required, int page); - int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page); - int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, - int page); - int (*read_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, - int page); - int (*read_oob)(struct mtd_info *mtd, struct nand_chip *chip, int page); - int (*write_oob)(struct mtd_info *mtd, struct nand_chip *chip, - int page); -}; - -static inline int nand_standard_page_accessors(struct nand_ecc_ctrl *ecc) -{ - return !(ecc->options & NAND_ECC_CUSTOM_PAGE_ACCESS); -} - -/** - * struct nand_buffers - buffer structure for read/write - * @ecccalc: buffer pointer for calculated ECC, size is oobsize. - * @ecccode: buffer pointer for ECC read from flash, size is oobsize. - * @databuf: buffer pointer for data, size is (page size + oobsize). - * - * Do not change the order of buffers. databuf and oobrbuf must be in - * consecutive order. - */ -struct nand_buffers { - uint8_t *ecccalc; - uint8_t *ecccode; - uint8_t *databuf; -}; - -/** - * struct nand_sdr_timings - SDR NAND chip timings - * - * This struct defines the timing requirements of a SDR NAND chip. - * These information can be found in every NAND datasheets and the timings - * meaning are described in the ONFI specifications: - * www.onfi.org/~/media/ONFI/specs/onfi_3_1_spec.pdf (chapter 4.15 Timing - * Parameters) - * - * All these timings are expressed in picoseconds. - * - * @tBERS_max: Block erase time - * @tCCS_min: Change column setup time - * @tPROG_max: Page program time - * @tR_max: Page read time - * @tALH_min: ALE hold time - * @tADL_min: ALE to data loading time - * @tALS_min: ALE setup time - * @tAR_min: ALE to RE# delay - * @tCEA_max: CE# access time - * @tCEH_min: CE# high hold time - * @tCH_min: CE# hold time - * @tCHZ_max: CE# high to output hi-Z - * @tCLH_min: CLE hold time - * @tCLR_min: CLE to RE# delay - * @tCLS_min: CLE setup time - * @tCOH_min: CE# high to output hold - * @tCS_min: CE# setup time - * @tDH_min: Data hold time - * @tDS_min: Data setup time - * @tFEAT_max: Busy time for Set Features and Get Features - * @tIR_min: Output hi-Z to RE# low - * @tITC_max: Interface and Timing Mode Change time - * @tRC_min: RE# cycle time - * @tREA_max: RE# access time - * @tREH_min: RE# high hold time - * @tRHOH_min: RE# high to output hold - * @tRHW_min: RE# high to WE# low - * @tRHZ_max: RE# high to output hi-Z - * @tRLOH_min: RE# low to output hold - * @tRP_min: RE# pulse width - * @tRR_min: Ready to RE# low (data only) - * @tRST_max: Device reset time, measured from the falling edge of R/B# to the - * rising edge of R/B#. - * @tWB_max: WE# high to SR[6] low - * @tWC_min: WE# cycle time - * @tWH_min: WE# high hold time - * @tWHR_min: WE# high to RE# low - * @tWP_min: WE# pulse width - * @tWW_min: WP# transition to WE# low - */ -struct nand_sdr_timings { - u32 tBERS_max; - u32 tCCS_min; - u32 tPROG_max; - u32 tR_max; - u32 tALH_min; - u32 tADL_min; - u32 tALS_min; - u32 tAR_min; - u32 tCEA_max; - u32 tCEH_min; - u32 tCH_min; - u32 tCHZ_max; - u32 tCLH_min; - u32 tCLR_min; - u32 tCLS_min; - u32 tCOH_min; - u32 tCS_min; - u32 tDH_min; - u32 tDS_min; - u32 tFEAT_max; - u32 tIR_min; - u32 tITC_max; - u32 tRC_min; - u32 tREA_max; - u32 tREH_min; - u32 tRHOH_min; - u32 tRHW_min; - u32 tRHZ_max; - u32 tRLOH_min; - u32 tRP_min; - u32 tRR_min; - u64 tRST_max; - u32 tWB_max; - u32 tWC_min; - u32 tWH_min; - u32 tWHR_min; - u32 tWP_min; - u32 tWW_min; -}; - -/** - * enum nand_data_interface_type - NAND interface timing type - * @NAND_SDR_IFACE: Single Data Rate interface - */ -enum nand_data_interface_type { - NAND_SDR_IFACE, -}; - -/** - * struct nand_data_interface - NAND interface timing - * @type: type of the timing - * @timings: The timing, type according to @type - */ -struct nand_data_interface { - enum nand_data_interface_type type; - union { - struct nand_sdr_timings sdr; - } timings; -}; - -/** - * nand_get_sdr_timings - get SDR timing from data interface - * @conf: The data interface - */ -static inline const struct nand_sdr_timings * -nand_get_sdr_timings(const struct nand_data_interface *conf) -{ - if (conf->type != NAND_SDR_IFACE) - return ERR_PTR(-EINVAL); - - return &conf->timings.sdr; -} - -/** - * struct nand_manufacturer_ops - NAND Manufacturer operations - * @detect: detect the NAND memory organization and capabilities - * @init: initialize all vendor specific fields (like the ->read_retry() - * implementation) if any. - * @cleanup: the ->init() function may have allocated resources, ->cleanup() - * is here to let vendor specific code release those resources. - */ -struct nand_manufacturer_ops { - void (*detect)(struct nand_chip *chip); - int (*init)(struct nand_chip *chip); - void (*cleanup)(struct nand_chip *chip); -}; - -/** - * struct nand_chip - NAND Private Flash Chip Data - * @mtd: MTD device registered to the MTD framework - * @IO_ADDR_R: [BOARDSPECIFIC] address to read the 8 I/O lines of the - * flash device - * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the - * flash device. - * @read_byte: [REPLACEABLE] read one byte from the chip - * @read_word: [REPLACEABLE] read one word from the chip - * @write_byte: [REPLACEABLE] write a single byte to the chip on the - * low 8 I/O lines - * @write_buf: [REPLACEABLE] write data from the buffer to the chip - * @read_buf: [REPLACEABLE] read data from the chip into the buffer - * @select_chip: [REPLACEABLE] select chip nr - * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers - * @block_markbad: [REPLACEABLE] mark a block bad - * @cmd_ctrl: [BOARDSPECIFIC] hardwarespecific function for controlling - * ALE/CLE/nCE. Also used to write command and address - * @dev_ready: [BOARDSPECIFIC] hardwarespecific function for accessing - * device ready/busy line. If set to NULL no access to - * ready/busy is available and the ready/busy information - * is read from the chip status register. - * @cmdfunc: [REPLACEABLE] hardwarespecific function for writing - * commands to the chip. - * @waitfunc: [REPLACEABLE] hardwarespecific function for wait on - * ready. - * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for - * setting the read-retry mode. Mostly needed for MLC NAND. - * @ecc: [BOARDSPECIFIC] ECC control structure - * @buffers: buffer structure for read/write - * @buf_align: minimum buffer alignment required by a platform - * @hwcontrol: platform-specific hardware control structure - * @erase: [REPLACEABLE] erase function - * @scan_bbt: [REPLACEABLE] function to scan bad block table - * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring - * data from array to read regs (tR). - * @state: [INTERN] the current state of the NAND device - * @oob_poi: "poison value buffer," used for laying out OOB data - * before writing - * @page_shift: [INTERN] number of address bits in a page (column - * address bits). - * @phys_erase_shift: [INTERN] number of address bits in a physical eraseblock - * @bbt_erase_shift: [INTERN] number of address bits in a bbt entry - * @chip_shift: [INTERN] number of address bits in one chip - * @options: [BOARDSPECIFIC] various chip options. They can partly - * be set to inform nand_scan about special functionality. - * See the defines for further explanation. - * @bbt_options: [INTERN] bad block specific options. All options used - * here must come from bbm.h. By default, these options - * will be copied to the appropriate nand_bbt_descr's. - * @badblockpos: [INTERN] position of the bad block marker in the oob - * area. - * @badblockbits: [INTERN] minimum number of set bits in a good block's - * bad block marker position; i.e., BBM == 11110111b is - * not bad when badblockbits == 7 - * @bits_per_cell: [INTERN] number of bits per cell. i.e., 1 means SLC. - * @ecc_strength_ds: [INTERN] ECC correctability from the datasheet. - * Minimum amount of bit errors per @ecc_step_ds guaranteed - * to be correctable. If unknown, set to zero. - * @ecc_step_ds: [INTERN] ECC step required by the @ecc_strength_ds, - * also from the datasheet. It is the recommended ECC step - * size, if known; if unknown, set to zero. - * @onfi_timing_mode_default: [INTERN] default ONFI timing mode. This field is - * set to the actually used ONFI mode if the chip is - * ONFI compliant or deduced from the datasheet if - * the NAND chip is not ONFI compliant. - * @numchips: [INTERN] number of physical chips - * @chipsize: [INTERN] the size of one chip for multichip arrays - * @pagemask: [INTERN] page number mask = number of (pages / chip) - 1 - * @pagebuf: [INTERN] holds the pagenumber which is currently in - * data_buf. - * @pagebuf_bitflips: [INTERN] holds the bitflip count for the page which is - * currently in data_buf. - * @subpagesize: [INTERN] holds the subpagesize - * @id: [INTERN] holds NAND ID - * @onfi_version: [INTERN] holds the chip ONFI version (BCD encoded), - * non 0 if ONFI supported. - * @jedec_version: [INTERN] holds the chip JEDEC version (BCD encoded), - * non 0 if JEDEC supported. - * @onfi_params: [INTERN] holds the ONFI page parameter when ONFI is - * supported, 0 otherwise. - * @jedec_params: [INTERN] holds the JEDEC parameter page when JEDEC is - * supported, 0 otherwise. - * @max_bb_per_die: [INTERN] the max number of bad blocks each die of a - * this nand device will encounter their life times. - * @blocks_per_die: [INTERN] The number of PEBs in a die - * @data_interface: [INTERN] NAND interface timing information - * @read_retries: [INTERN] the number of read retry modes supported - * @onfi_set_features: [REPLACEABLE] set the features for ONFI nand - * @onfi_get_features: [REPLACEABLE] get the features for ONFI nand - * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If - * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this - * means the configuration should not be applied but - * only checked. - * @bbt: [INTERN] bad block table pointer - * @bbt_td: [REPLACEABLE] bad block table descriptor for flash - * lookup. - * @bbt_md: [REPLACEABLE] bad block table mirror descriptor - * @badblock_pattern: [REPLACEABLE] bad block scan pattern used for initial - * bad block scan. - * @controller: [REPLACEABLE] a pointer to a hardware controller - * structure which is shared among multiple independent - * devices. - * @priv: [OPTIONAL] pointer to private chip data - * @manufacturer: [INTERN] Contains manufacturer information - */ - -struct nand_chip { - struct mtd_info mtd; - void __iomem *IO_ADDR_R; - void __iomem *IO_ADDR_W; - - uint8_t (*read_byte)(struct mtd_info *mtd); - u16 (*read_word)(struct mtd_info *mtd); - void (*write_byte)(struct mtd_info *mtd, uint8_t byte); - void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); - void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); - void (*select_chip)(struct mtd_info *mtd, int chip); - int (*block_bad)(struct mtd_info *mtd, loff_t ofs); - int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); - void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); - int (*dev_ready)(struct mtd_info *mtd); - void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, - int page_addr); - int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); - int (*erase)(struct mtd_info *mtd, int page); - int (*scan_bbt)(struct mtd_info *mtd); - int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip, - int feature_addr, uint8_t *subfeature_para); - int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, - int feature_addr, uint8_t *subfeature_para); - int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); - int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, - const struct nand_data_interface *conf); - - - int chip_delay; - unsigned int options; - unsigned int bbt_options; - - int page_shift; - int phys_erase_shift; - int bbt_erase_shift; - int chip_shift; - int numchips; - uint64_t chipsize; - int pagemask; - int pagebuf; - unsigned int pagebuf_bitflips; - int subpagesize; - uint8_t bits_per_cell; - uint16_t ecc_strength_ds; - uint16_t ecc_step_ds; - int onfi_timing_mode_default; - int badblockpos; - int badblockbits; - - struct nand_id id; - int onfi_version; - int jedec_version; - union { - struct nand_onfi_params onfi_params; - struct nand_jedec_params jedec_params; - }; - u16 max_bb_per_die; - u32 blocks_per_die; - - struct nand_data_interface *data_interface; - - int read_retries; - - flstate_t state; - - uint8_t *oob_poi; - struct nand_hw_control *controller; - - struct nand_ecc_ctrl ecc; - struct nand_buffers *buffers; - unsigned long buf_align; - struct nand_hw_control hwcontrol; - - uint8_t *bbt; - struct nand_bbt_descr *bbt_td; - struct nand_bbt_descr *bbt_md; - - struct nand_bbt_descr *badblock_pattern; - - void *priv; - - struct { - const struct nand_manufacturer *desc; - void *priv; - } manufacturer; -}; - -extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops; -extern const struct mtd_ooblayout_ops nand_ooblayout_lp_ops; - -static inline void nand_set_flash_node(struct nand_chip *chip, - struct device_node *np) -{ - mtd_set_of_node(&chip->mtd, np); -} - -static inline struct device_node *nand_get_flash_node(struct nand_chip *chip) -{ - return mtd_get_of_node(&chip->mtd); -} - -static inline struct nand_chip *mtd_to_nand(struct mtd_info *mtd) -{ - return container_of(mtd, struct nand_chip, mtd); -} - -static inline struct mtd_info *nand_to_mtd(struct nand_chip *chip) -{ - return &chip->mtd; -} - -static inline void *nand_get_controller_data(struct nand_chip *chip) -{ - return chip->priv; -} - -static inline void nand_set_controller_data(struct nand_chip *chip, void *priv) -{ - chip->priv = priv; -} - -static inline void nand_set_manufacturer_data(struct nand_chip *chip, - void *priv) -{ - chip->manufacturer.priv = priv; -} - -static inline void *nand_get_manufacturer_data(struct nand_chip *chip) -{ - return chip->manufacturer.priv; -} - -/* - * NAND Flash Manufacturer ID Codes - */ -#define NAND_MFR_TOSHIBA 0x98 -#define NAND_MFR_ESMT 0xc8 -#define NAND_MFR_SAMSUNG 0xec -#define NAND_MFR_FUJITSU 0x04 -#define NAND_MFR_NATIONAL 0x8f -#define NAND_MFR_RENESAS 0x07 -#define NAND_MFR_STMICRO 0x20 -#define NAND_MFR_HYNIX 0xad -#define NAND_MFR_MICRON 0x2c -#define NAND_MFR_AMD 0x01 -#define NAND_MFR_MACRONIX 0xc2 -#define NAND_MFR_EON 0x92 -#define NAND_MFR_SANDISK 0x45 -#define NAND_MFR_INTEL 0x89 -#define NAND_MFR_ATO 0x9b -#define NAND_MFR_WINBOND 0xef - -/* The maximum expected count of bytes in the NAND ID sequence */ -#define NAND_MAX_ID_LEN 8 - -/* - * A helper for defining older NAND chips where the second ID byte fully - * defined the chip, including the geometry (chip size, eraseblock size, page - * size). All these chips have 512 bytes NAND page size. - */ -#define LEGACY_ID_NAND(nm, devid, chipsz, erasesz, opts) \ - { .name = (nm), {{ .dev_id = (devid) }}, .pagesize = 512, \ - .chipsize = (chipsz), .erasesize = (erasesz), .options = (opts) } - -/* - * A helper for defining newer chips which report their page size and - * eraseblock size via the extended ID bytes. - * - * The real difference between LEGACY_ID_NAND and EXTENDED_ID_NAND is that with - * EXTENDED_ID_NAND, manufacturers overloaded the same device ID so that the - * device ID now only represented a particular total chip size (and voltage, - * buswidth), and the page size, eraseblock size, and OOB size could vary while - * using the same device ID. - */ -#define EXTENDED_ID_NAND(nm, devid, chipsz, opts) \ - { .name = (nm), {{ .dev_id = (devid) }}, .chipsize = (chipsz), \ - .options = (opts) } - -#define NAND_ECC_INFO(_strength, _step) \ - { .strength_ds = (_strength), .step_ds = (_step) } -#define NAND_ECC_STRENGTH(type) ((type)->ecc.strength_ds) -#define NAND_ECC_STEP(type) ((type)->ecc.step_ds) - -/** - * struct nand_flash_dev - NAND Flash Device ID Structure - * @name: a human-readable name of the NAND chip - * @dev_id: the device ID (the second byte of the full chip ID array) - * @mfr_id: manufecturer ID part of the full chip ID array (refers the same - * memory address as @id[0]) - * @dev_id: device ID part of the full chip ID array (refers the same memory - * address as @id[1]) - * @id: full device ID array - * @pagesize: size of the NAND page in bytes; if 0, then the real page size (as - * well as the eraseblock size) is determined from the extended NAND - * chip ID array) - * @chipsize: total chip size in MiB - * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) - * @options: stores various chip bit options - * @id_len: The valid length of the @id. - * @oobsize: OOB size - * @ecc: ECC correctability and step information from the datasheet. - * @ecc.strength_ds: The ECC correctability from the datasheet, same as the - * @ecc_strength_ds in nand_chip{}. - * @ecc.step_ds: The ECC step required by the @ecc.strength_ds, same as the - * @ecc_step_ds in nand_chip{}, also from the datasheet. - * For example, the "4bit ECC for each 512Byte" can be set with - * NAND_ECC_INFO(4, 512). - * @onfi_timing_mode_default: the default ONFI timing mode entered after a NAND - * reset. Should be deduced from timings described - * in the datasheet. - * - */ -struct nand_flash_dev { - char *name; - union { - struct { - uint8_t mfr_id; - uint8_t dev_id; - }; - uint8_t id[NAND_MAX_ID_LEN]; - }; - unsigned int pagesize; - unsigned int chipsize; - unsigned int erasesize; - unsigned int options; - uint16_t id_len; - uint16_t oobsize; - struct { - uint16_t strength_ds; - uint16_t step_ds; - } ecc; - int onfi_timing_mode_default; -}; - -/** - * struct nand_manufacturer - NAND Flash Manufacturer structure - * @name: Manufacturer name - * @id: manufacturer ID code of device. - * @ops: manufacturer operations -*/ -struct nand_manufacturer { - int id; - char *name; - const struct nand_manufacturer_ops *ops; -}; - -const struct nand_manufacturer *nand_get_manufacturer(u8 id); - -static inline const char * -nand_manufacturer_name(const struct nand_manufacturer *manufacturer) -{ - return manufacturer ? manufacturer->name : "Unknown"; -} - -extern struct nand_flash_dev nand_flash_ids[]; - -extern const struct nand_manufacturer_ops toshiba_nand_manuf_ops; -extern const struct nand_manufacturer_ops samsung_nand_manuf_ops; -extern const struct nand_manufacturer_ops hynix_nand_manuf_ops; -extern const struct nand_manufacturer_ops micron_nand_manuf_ops; -extern const struct nand_manufacturer_ops amd_nand_manuf_ops; -extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; - -int nand_default_bbt(struct mtd_info *mtd); -int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); -int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); -int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt); -int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, - int allowbbt); -int nand_do_read(struct mtd_info *mtd, loff_t from, size_t len, - size_t *retlen, uint8_t *buf); - -/** - * struct platform_nand_chip - chip level device structure - * @nr_chips: max. number of chips to scan for - * @chip_offset: chip number offset - * @nr_partitions: number of partitions pointed to by partitions (or zero) - * @partitions: mtd partition list - * @chip_delay: R/B delay value in us - * @options: Option flags, e.g. 16bit buswidth - * @bbt_options: BBT option flags, e.g. NAND_BBT_USE_FLASH - * @part_probe_types: NULL-terminated array of probe types - */ -struct platform_nand_chip { - int nr_chips; - int chip_offset; - int nr_partitions; - struct mtd_partition *partitions; - int chip_delay; - unsigned int options; - unsigned int bbt_options; - const char **part_probe_types; -}; - -/* Keep gcc happy */ -struct platform_device; - -/** - * struct platform_nand_ctrl - controller level device structure - * @probe: platform specific function to probe/setup hardware - * @remove: platform specific function to remove/teardown hardware - * @hwcontrol: platform specific hardware control structure - * @dev_ready: platform specific function to read ready/busy pin - * @select_chip: platform specific chip select function - * @cmd_ctrl: platform specific function for controlling - * ALE/CLE/nCE. Also used to write command and address - * @write_buf: platform specific function for write buffer - * @read_buf: platform specific function for read buffer - * @read_byte: platform specific function to read one byte from chip - * @priv: private data to transport driver specific settings - * - * All fields are optional and depend on the hardware driver requirements - */ -struct platform_nand_ctrl { - int (*probe)(struct platform_device *pdev); - void (*remove)(struct platform_device *pdev); - void (*hwcontrol)(struct mtd_info *mtd, int cmd); - int (*dev_ready)(struct mtd_info *mtd); - void (*select_chip)(struct mtd_info *mtd, int chip); - void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); - void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); - void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); - unsigned char (*read_byte)(struct mtd_info *mtd); - void *priv; -}; - -/** - * struct platform_nand_data - container structure for platform-specific data - * @chip: chip level chip structure - * @ctrl: controller level device structure - */ -struct platform_nand_data { - struct platform_nand_chip chip; - struct platform_nand_ctrl ctrl; -}; - -/* return the supported features. */ -static inline int onfi_feature(struct nand_chip *chip) -{ - return chip->onfi_version ? le16_to_cpu(chip->onfi_params.features) : 0; -} - -/* return the supported asynchronous timing mode. */ -static inline int onfi_get_async_timing_mode(struct nand_chip *chip) -{ - if (!chip->onfi_version) - return ONFI_TIMING_MODE_UNKNOWN; - return le16_to_cpu(chip->onfi_params.async_timing_mode); -} - -/* return the supported synchronous timing mode. */ -static inline int onfi_get_sync_timing_mode(struct nand_chip *chip) -{ - if (!chip->onfi_version) - return ONFI_TIMING_MODE_UNKNOWN; - return le16_to_cpu(chip->onfi_params.src_sync_timing_mode); -} - -int onfi_init_data_interface(struct nand_chip *chip, - struct nand_data_interface *iface, - enum nand_data_interface_type type, - int timing_mode); - -/* - * Check if it is a SLC nand. - * The !nand_is_slc() can be used to check the MLC/TLC nand chips. - * We do not distinguish the MLC and TLC now. - */ -static inline bool nand_is_slc(struct nand_chip *chip) -{ - return chip->bits_per_cell == 1; -} - -/** - * Check if the opcode's address should be sent only on the lower 8 bits - * @command: opcode to check - */ -static inline int nand_opcode_8bits(unsigned int command) -{ - switch (command) { - case NAND_CMD_READID: - case NAND_CMD_PARAM: - case NAND_CMD_GET_FEATURES: - case NAND_CMD_SET_FEATURES: - return 1; - default: - break; - } - return 0; -} - -/* return the supported JEDEC features. */ -static inline int jedec_feature(struct nand_chip *chip) -{ - return chip->jedec_version ? le16_to_cpu(chip->jedec_params.features) - : 0; -} - -/* get timing characteristics from ONFI timing mode. */ -const struct nand_sdr_timings *onfi_async_timing_mode_to_sdr_timings(int mode); -/* get data interface from ONFI timing mode 0, used after reset. */ -const struct nand_data_interface *nand_get_default_data_interface(void); - -int nand_check_erased_ecc_chunk(void *data, int datalen, - void *ecc, int ecclen, - void *extraoob, int extraooblen, - int threshold); - -int nand_check_ecc_caps(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail); - -int nand_match_ecc_req(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail); - -int nand_maximize_ecc(struct nand_chip *chip, - const struct nand_ecc_caps *caps, int oobavail); - -/* Default write_oob implementation */ -int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); - -/* Default write_oob syndrome implementation */ -int nand_write_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, - int page); - -/* Default read_oob implementation */ -int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); - -/* Default read_oob syndrome implementation */ -int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, - int page); - -/* Stub used by drivers that do not support GET/SET FEATURES operations */ -int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd, - struct nand_chip *chip, int addr, - u8 *subfeature_param); - -/* Default read_page_raw implementation */ -int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - uint8_t *buf, int oob_required, int page); - -/* Default write_page_raw implementation */ -int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, - const uint8_t *buf, int oob_required, int page); - -/* Reset and initialize a NAND device */ -int nand_reset(struct nand_chip *chip, int chipnr); - -/* Free resources held by the NAND device */ -void nand_cleanup(struct nand_chip *chip); - -/* Default extended ID decoding function */ -void nand_decode_ext_id(struct nand_chip *chip); -#endif /* __LINUX_MTD_NAND_H */ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h new file mode 100644 index 000000000000..b371dc0914a7 --- /dev/null +++ b/include/linux/mtd/rawnand.h @@ -0,0 +1,1329 @@ +/* + * Copyright © 2000-2010 David Woodhouse + * Steven J. Hill + * Thomas Gleixner + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Info: + * Contains standard defines and IDs for NAND flash devices + * + * Changelog: + * See git changelog. + */ +#ifndef __LINUX_MTD_RAWNAND_H +#define __LINUX_MTD_RAWNAND_H + +#include +#include +#include +#include +#include + +struct mtd_info; +struct nand_flash_dev; +struct device_node; + +/* Scan and identify a NAND device */ +int nand_scan(struct mtd_info *mtd, int max_chips); +/* + * Separate phases of nand_scan(), allowing board driver to intervene + * and override command or ECC setup according to flash type. + */ +int nand_scan_ident(struct mtd_info *mtd, int max_chips, + struct nand_flash_dev *table); +int nand_scan_tail(struct mtd_info *mtd); + +/* Unregister the MTD device and free resources held by the NAND device */ +void nand_release(struct mtd_info *mtd); + +/* Internal helper for board drivers which need to override command function */ +void nand_wait_ready(struct mtd_info *mtd); + +/* locks all blocks present in the device */ +int nand_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len); + +/* unlocks specified locked blocks */ +int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); + +/* The maximum number of NAND chips in an array */ +#define NAND_MAX_CHIPS 8 + +/* + * Constants for hardware specific CLE/ALE/NCE function + * + * These are bits which can be or'ed to set/clear multiple + * bits in one go. + */ +/* Select the chip by setting nCE to low */ +#define NAND_NCE 0x01 +/* Select the command latch by setting CLE to high */ +#define NAND_CLE 0x02 +/* Select the address latch by setting ALE to high */ +#define NAND_ALE 0x04 + +#define NAND_CTRL_CLE (NAND_NCE | NAND_CLE) +#define NAND_CTRL_ALE (NAND_NCE | NAND_ALE) +#define NAND_CTRL_CHANGE 0x80 + +/* + * Standard NAND flash commands + */ +#define NAND_CMD_READ0 0 +#define NAND_CMD_READ1 1 +#define NAND_CMD_RNDOUT 5 +#define NAND_CMD_PAGEPROG 0x10 +#define NAND_CMD_READOOB 0x50 +#define NAND_CMD_ERASE1 0x60 +#define NAND_CMD_STATUS 0x70 +#define NAND_CMD_SEQIN 0x80 +#define NAND_CMD_RNDIN 0x85 +#define NAND_CMD_READID 0x90 +#define NAND_CMD_ERASE2 0xd0 +#define NAND_CMD_PARAM 0xec +#define NAND_CMD_GET_FEATURES 0xee +#define NAND_CMD_SET_FEATURES 0xef +#define NAND_CMD_RESET 0xff + +#define NAND_CMD_LOCK 0x2a +#define NAND_CMD_UNLOCK1 0x23 +#define NAND_CMD_UNLOCK2 0x24 + +/* Extended commands for large page devices */ +#define NAND_CMD_READSTART 0x30 +#define NAND_CMD_RNDOUTSTART 0xE0 +#define NAND_CMD_CACHEDPROG 0x15 + +#define NAND_CMD_NONE -1 + +/* Status bits */ +#define NAND_STATUS_FAIL 0x01 +#define NAND_STATUS_FAIL_N1 0x02 +#define NAND_STATUS_TRUE_READY 0x20 +#define NAND_STATUS_READY 0x40 +#define NAND_STATUS_WP 0x80 + +#define NAND_DATA_IFACE_CHECK_ONLY -1 + +/* + * Constants for ECC_MODES + */ +typedef enum { + NAND_ECC_NONE, + NAND_ECC_SOFT, + NAND_ECC_HW, + NAND_ECC_HW_SYNDROME, + NAND_ECC_HW_OOB_FIRST, + NAND_ECC_ON_DIE, +} nand_ecc_modes_t; + +enum nand_ecc_algo { + NAND_ECC_UNKNOWN, + NAND_ECC_HAMMING, + NAND_ECC_BCH, +}; + +/* + * Constants for Hardware ECC + */ +/* Reset Hardware ECC for read */ +#define NAND_ECC_READ 0 +/* Reset Hardware ECC for write */ +#define NAND_ECC_WRITE 1 +/* Enable Hardware ECC before syndrome is read back from flash */ +#define NAND_ECC_READSYN 2 + +/* + * Enable generic NAND 'page erased' check. This check is only done when + * ecc.correct() returns -EBADMSG. + * Set this flag if your implementation does not fix bitflips in erased + * pages and you want to rely on the default implementation. + */ +#define NAND_ECC_GENERIC_ERASED_CHECK BIT(0) +#define NAND_ECC_MAXIMIZE BIT(1) +/* + * If your controller already sends the required NAND commands when + * reading or writing a page, then the framework is not supposed to + * send READ0 and SEQIN/PAGEPROG respectively. + */ +#define NAND_ECC_CUSTOM_PAGE_ACCESS BIT(2) + +/* Bit mask for flags passed to do_nand_read_ecc */ +#define NAND_GET_DEVICE 0x80 + + +/* + * Option constants for bizarre disfunctionality and real + * features. + */ +/* Buswidth is 16 bit */ +#define NAND_BUSWIDTH_16 0x00000002 +/* Chip has cache program function */ +#define NAND_CACHEPRG 0x00000008 +/* + * Chip requires ready check on read (for auto-incremented sequential read). + * True only for small page devices; large page devices do not support + * autoincrement. + */ +#define NAND_NEED_READRDY 0x00000100 + +/* Chip does not allow subpage writes */ +#define NAND_NO_SUBPAGE_WRITE 0x00000200 + +/* Device is one of 'new' xD cards that expose fake nand command set */ +#define NAND_BROKEN_XD 0x00000400 + +/* Device behaves just like nand, but is readonly */ +#define NAND_ROM 0x00000800 + +/* Device supports subpage reads */ +#define NAND_SUBPAGE_READ 0x00001000 + +/* + * Some MLC NANDs need data scrambling to limit bitflips caused by repeated + * patterns. + */ +#define NAND_NEED_SCRAMBLING 0x00002000 + +/* Options valid for Samsung large page devices */ +#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG + +/* Macros to identify the above */ +#define NAND_HAS_CACHEPROG(chip) ((chip->options & NAND_CACHEPRG)) +#define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) +#define NAND_HAS_SUBPAGE_WRITE(chip) !((chip)->options & NAND_NO_SUBPAGE_WRITE) + +/* Non chip related options */ +/* This option skips the bbt scan during initialization. */ +#define NAND_SKIP_BBTSCAN 0x00010000 +/* + * This option is defined if the board driver allocates its own buffers + * (e.g. because it needs them DMA-coherent). + */ +#define NAND_OWN_BUFFERS 0x00020000 +/* Chip may not exist, so silence any errors in scan */ +#define NAND_SCAN_SILENT_NODEV 0x00040000 +/* + * Autodetect nand buswidth with readid/onfi. + * This suppose the driver will configure the hardware in 8 bits mode + * when calling nand_scan_ident, and update its configuration + * before calling nand_scan_tail. + */ +#define NAND_BUSWIDTH_AUTO 0x00080000 +/* + * This option could be defined by controller drivers to protect against + * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers + */ +#define NAND_USE_BOUNCE_BUFFER 0x00100000 + +/* + * In case your controller is implementing ->cmd_ctrl() and is relying on the + * default ->cmdfunc() implementation, you may want to let the core handle the + * tCCS delay which is required when a column change (RNDIN or RNDOUT) is + * requested. + * If your controller already takes care of this delay, you don't need to set + * this flag. + */ +#define NAND_WAIT_TCCS 0x00200000 + +/* Options set by nand scan */ +/* Nand scan has allocated controller struct */ +#define NAND_CONTROLLER_ALLOC 0x80000000 + +/* Cell info constants */ +#define NAND_CI_CHIPNR_MSK 0x03 +#define NAND_CI_CELLTYPE_MSK 0x0C +#define NAND_CI_CELLTYPE_SHIFT 2 + +/* Keep gcc happy */ +struct nand_chip; + +/* ONFI features */ +#define ONFI_FEATURE_16_BIT_BUS (1 << 0) +#define ONFI_FEATURE_EXT_PARAM_PAGE (1 << 7) + +/* ONFI timing mode, used in both asynchronous and synchronous mode */ +#define ONFI_TIMING_MODE_0 (1 << 0) +#define ONFI_TIMING_MODE_1 (1 << 1) +#define ONFI_TIMING_MODE_2 (1 << 2) +#define ONFI_TIMING_MODE_3 (1 << 3) +#define ONFI_TIMING_MODE_4 (1 << 4) +#define ONFI_TIMING_MODE_5 (1 << 5) +#define ONFI_TIMING_MODE_UNKNOWN (1 << 6) + +/* ONFI feature address */ +#define ONFI_FEATURE_ADDR_TIMING_MODE 0x1 + +/* Vendor-specific feature address (Micron) */ +#define ONFI_FEATURE_ADDR_READ_RETRY 0x89 +#define ONFI_FEATURE_ON_DIE_ECC 0x90 +#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) + +/* ONFI subfeature parameters length */ +#define ONFI_SUBFEATURE_PARAM_LEN 4 + +/* ONFI optional commands SET/GET FEATURES supported? */ +#define ONFI_OPT_CMD_SET_GET_FEATURES (1 << 2) + +struct nand_onfi_params { + /* rev info and features block */ + /* 'O' 'N' 'F' 'I' */ + u8 sig[4]; + __le16 revision; + __le16 features; + __le16 opt_cmd; + u8 reserved0[2]; + __le16 ext_param_page_length; /* since ONFI 2.1 */ + u8 num_of_param_pages; /* since ONFI 2.1 */ + u8 reserved1[17]; + + /* manufacturer information block */ + char manufacturer[12]; + char model[20]; + u8 jedec_id; + __le16 date_code; + u8 reserved2[13]; + + /* memory organization block */ + __le32 byte_per_page; + __le16 spare_bytes_per_page; + __le32 data_bytes_per_ppage; + __le16 spare_bytes_per_ppage; + __le32 pages_per_block; + __le32 blocks_per_lun; + u8 lun_count; + u8 addr_cycles; + u8 bits_per_cell; + __le16 bb_per_lun; + __le16 block_endurance; + u8 guaranteed_good_blocks; + __le16 guaranteed_block_endurance; + u8 programs_per_page; + u8 ppage_attr; + u8 ecc_bits; + u8 interleaved_bits; + u8 interleaved_ops; + u8 reserved3[13]; + + /* electrical parameter block */ + u8 io_pin_capacitance_max; + __le16 async_timing_mode; + __le16 program_cache_timing_mode; + __le16 t_prog; + __le16 t_bers; + __le16 t_r; + __le16 t_ccs; + __le16 src_sync_timing_mode; + u8 src_ssync_features; + __le16 clk_pin_capacitance_typ; + __le16 io_pin_capacitance_typ; + __le16 input_pin_capacitance_typ; + u8 input_pin_capacitance_max; + u8 driver_strength_support; + __le16 t_int_r; + __le16 t_adl; + u8 reserved4[8]; + + /* vendor */ + __le16 vendor_revision; + u8 vendor[88]; + + __le16 crc; +} __packed; + +#define ONFI_CRC_BASE 0x4F4E + +/* Extended ECC information Block Definition (since ONFI 2.1) */ +struct onfi_ext_ecc_info { + u8 ecc_bits; + u8 codeword_size; + __le16 bb_per_lun; + __le16 block_endurance; + u8 reserved[2]; +} __packed; + +#define ONFI_SECTION_TYPE_0 0 /* Unused section. */ +#define ONFI_SECTION_TYPE_1 1 /* for additional sections. */ +#define ONFI_SECTION_TYPE_2 2 /* for ECC information. */ +struct onfi_ext_section { + u8 type; + u8 length; +} __packed; + +#define ONFI_EXT_SECTION_MAX 8 + +/* Extended Parameter Page Definition (since ONFI 2.1) */ +struct onfi_ext_param_page { + __le16 crc; + u8 sig[4]; /* 'E' 'P' 'P' 'S' */ + u8 reserved0[10]; + struct onfi_ext_section sections[ONFI_EXT_SECTION_MAX]; + + /* + * The actual size of the Extended Parameter Page is in + * @ext_param_page_length of nand_onfi_params{}. + * The following are the variable length sections. + * So we do not add any fields below. Please see the ONFI spec. + */ +} __packed; + +struct jedec_ecc_info { + u8 ecc_bits; + u8 codeword_size; + __le16 bb_per_lun; + __le16 block_endurance; + u8 reserved[2]; +} __packed; + +/* JEDEC features */ +#define JEDEC_FEATURE_16_BIT_BUS (1 << 0) + +struct nand_jedec_params { + /* rev info and features block */ + /* 'J' 'E' 'S' 'D' */ + u8 sig[4]; + __le16 revision; + __le16 features; + u8 opt_cmd[3]; + __le16 sec_cmd; + u8 num_of_param_pages; + u8 reserved0[18]; + + /* manufacturer information block */ + char manufacturer[12]; + char model[20]; + u8 jedec_id[6]; + u8 reserved1[10]; + + /* memory organization block */ + __le32 byte_per_page; + __le16 spare_bytes_per_page; + u8 reserved2[6]; + __le32 pages_per_block; + __le32 blocks_per_lun; + u8 lun_count; + u8 addr_cycles; + u8 bits_per_cell; + u8 programs_per_page; + u8 multi_plane_addr; + u8 multi_plane_op_attr; + u8 reserved3[38]; + + /* electrical parameter block */ + __le16 async_sdr_speed_grade; + __le16 toggle_ddr_speed_grade; + __le16 sync_ddr_speed_grade; + u8 async_sdr_features; + u8 toggle_ddr_features; + u8 sync_ddr_features; + __le16 t_prog; + __le16 t_bers; + __le16 t_r; + __le16 t_r_multi_plane; + __le16 t_ccs; + __le16 io_pin_capacitance_typ; + __le16 input_pin_capacitance_typ; + __le16 clk_pin_capacitance_typ; + u8 driver_strength_support; + __le16 t_adl; + u8 reserved4[36]; + + /* ECC and endurance block */ + u8 guaranteed_good_blocks; + __le16 guaranteed_block_endurance; + struct jedec_ecc_info ecc_info[4]; + u8 reserved5[29]; + + /* reserved */ + u8 reserved6[148]; + + /* vendor */ + __le16 vendor_rev_num; + u8 reserved7[88]; + + /* CRC for Parameter Page */ + __le16 crc; +} __packed; + +/** + * struct nand_id - NAND id structure + * @data: buffer containing the id bytes. Currently 8 bytes large, but can + * be extended if required. + * @len: ID length. + */ +struct nand_id { + u8 data[8]; + int len; +}; + +/** + * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices + * @lock: protection lock + * @active: the mtd device which holds the controller currently + * @wq: wait queue to sleep on if a NAND operation is in + * progress used instead of the per chip wait queue + * when a hw controller is available. + */ +struct nand_hw_control { + spinlock_t lock; + struct nand_chip *active; + wait_queue_head_t wq; +}; + +static inline void nand_hw_control_init(struct nand_hw_control *nfc) +{ + nfc->active = NULL; + spin_lock_init(&nfc->lock); + init_waitqueue_head(&nfc->wq); +} + +/** + * struct nand_ecc_step_info - ECC step information of ECC engine + * @stepsize: data bytes per ECC step + * @strengths: array of supported strengths + * @nstrengths: number of supported strengths + */ +struct nand_ecc_step_info { + int stepsize; + const int *strengths; + int nstrengths; +}; + +/** + * struct nand_ecc_caps - capability of ECC engine + * @stepinfos: array of ECC step information + * @nstepinfos: number of ECC step information + * @calc_ecc_bytes: driver's hook to calculate ECC bytes per step + */ +struct nand_ecc_caps { + const struct nand_ecc_step_info *stepinfos; + int nstepinfos; + int (*calc_ecc_bytes)(int step_size, int strength); +}; + +/* a shorthand to generate struct nand_ecc_caps with only one ECC stepsize */ +#define NAND_ECC_CAPS_SINGLE(__name, __calc, __step, ...) \ +static const int __name##_strengths[] = { __VA_ARGS__ }; \ +static const struct nand_ecc_step_info __name##_stepinfo = { \ + .stepsize = __step, \ + .strengths = __name##_strengths, \ + .nstrengths = ARRAY_SIZE(__name##_strengths), \ +}; \ +static const struct nand_ecc_caps __name = { \ + .stepinfos = &__name##_stepinfo, \ + .nstepinfos = 1, \ + .calc_ecc_bytes = __calc, \ +} + +/** + * struct nand_ecc_ctrl - Control structure for ECC + * @mode: ECC mode + * @algo: ECC algorithm + * @steps: number of ECC steps per page + * @size: data bytes per ECC step + * @bytes: ECC bytes per step + * @strength: max number of correctible bits per ECC step + * @total: total number of ECC bytes per page + * @prepad: padding information for syndrome based ECC generators + * @postpad: padding information for syndrome based ECC generators + * @options: ECC specific options (see NAND_ECC_XXX flags defined above) + * @priv: pointer to private ECC control data + * @hwctl: function to control hardware ECC generator. Must only + * be provided if an hardware ECC is available + * @calculate: function for ECC calculation or readback from ECC hardware + * @correct: function for ECC correction, matching to ECC generator (sw/hw). + * Should return a positive number representing the number of + * corrected bitflips, -EBADMSG if the number of bitflips exceed + * ECC strength, or any other error code if the error is not + * directly related to correction. + * If -EBADMSG is returned the input buffers should be left + * untouched. + * @read_page_raw: function to read a raw page without ECC. This function + * should hide the specific layout used by the ECC + * controller and always return contiguous in-band and + * out-of-band data even if they're not stored + * contiguously on the NAND chip (e.g. + * NAND_ECC_HW_SYNDROME interleaves in-band and + * out-of-band data). + * @write_page_raw: function to write a raw page without ECC. This function + * should hide the specific layout used by the ECC + * controller and consider the passed data as contiguous + * in-band and out-of-band data. ECC controller is + * responsible for doing the appropriate transformations + * to adapt to its specific layout (e.g. + * NAND_ECC_HW_SYNDROME interleaves in-band and + * out-of-band data). + * @read_page: function to read a page according to the ECC generator + * requirements; returns maximum number of bitflips corrected in + * any single ECC step, -EIO hw error + * @read_subpage: function to read parts of the page covered by ECC; + * returns same as read_page() + * @write_subpage: function to write parts of the page covered by ECC. + * @write_page: function to write a page according to the ECC generator + * requirements. + * @write_oob_raw: function to write chip OOB data without ECC + * @read_oob_raw: function to read chip OOB data without ECC + * @read_oob: function to read chip OOB data + * @write_oob: function to write chip OOB data + */ +struct nand_ecc_ctrl { + nand_ecc_modes_t mode; + enum nand_ecc_algo algo; + int steps; + int size; + int bytes; + int total; + int strength; + int prepad; + int postpad; + unsigned int options; + void *priv; + void (*hwctl)(struct mtd_info *mtd, int mode); + int (*calculate)(struct mtd_info *mtd, const uint8_t *dat, + uint8_t *ecc_code); + int (*correct)(struct mtd_info *mtd, uint8_t *dat, uint8_t *read_ecc, + uint8_t *calc_ecc); + int (*read_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page); + int (*write_page_raw)(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, int page); + int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page); + int (*read_subpage)(struct mtd_info *mtd, struct nand_chip *chip, + uint32_t offs, uint32_t len, uint8_t *buf, int page); + int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip, + uint32_t offset, uint32_t data_len, + const uint8_t *data_buf, int oob_required, int page); + int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, int page); + int (*write_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, + int page); + int (*read_oob_raw)(struct mtd_info *mtd, struct nand_chip *chip, + int page); + int (*read_oob)(struct mtd_info *mtd, struct nand_chip *chip, int page); + int (*write_oob)(struct mtd_info *mtd, struct nand_chip *chip, + int page); +}; + +static inline int nand_standard_page_accessors(struct nand_ecc_ctrl *ecc) +{ + return !(ecc->options & NAND_ECC_CUSTOM_PAGE_ACCESS); +} + +/** + * struct nand_buffers - buffer structure for read/write + * @ecccalc: buffer pointer for calculated ECC, size is oobsize. + * @ecccode: buffer pointer for ECC read from flash, size is oobsize. + * @databuf: buffer pointer for data, size is (page size + oobsize). + * + * Do not change the order of buffers. databuf and oobrbuf must be in + * consecutive order. + */ +struct nand_buffers { + uint8_t *ecccalc; + uint8_t *ecccode; + uint8_t *databuf; +}; + +/** + * struct nand_sdr_timings - SDR NAND chip timings + * + * This struct defines the timing requirements of a SDR NAND chip. + * These information can be found in every NAND datasheets and the timings + * meaning are described in the ONFI specifications: + * www.onfi.org/~/media/ONFI/specs/onfi_3_1_spec.pdf (chapter 4.15 Timing + * Parameters) + * + * All these timings are expressed in picoseconds. + * + * @tBERS_max: Block erase time + * @tCCS_min: Change column setup time + * @tPROG_max: Page program time + * @tR_max: Page read time + * @tALH_min: ALE hold time + * @tADL_min: ALE to data loading time + * @tALS_min: ALE setup time + * @tAR_min: ALE to RE# delay + * @tCEA_max: CE# access time + * @tCEH_min: CE# high hold time + * @tCH_min: CE# hold time + * @tCHZ_max: CE# high to output hi-Z + * @tCLH_min: CLE hold time + * @tCLR_min: CLE to RE# delay + * @tCLS_min: CLE setup time + * @tCOH_min: CE# high to output hold + * @tCS_min: CE# setup time + * @tDH_min: Data hold time + * @tDS_min: Data setup time + * @tFEAT_max: Busy time for Set Features and Get Features + * @tIR_min: Output hi-Z to RE# low + * @tITC_max: Interface and Timing Mode Change time + * @tRC_min: RE# cycle time + * @tREA_max: RE# access time + * @tREH_min: RE# high hold time + * @tRHOH_min: RE# high to output hold + * @tRHW_min: RE# high to WE# low + * @tRHZ_max: RE# high to output hi-Z + * @tRLOH_min: RE# low to output hold + * @tRP_min: RE# pulse width + * @tRR_min: Ready to RE# low (data only) + * @tRST_max: Device reset time, measured from the falling edge of R/B# to the + * rising edge of R/B#. + * @tWB_max: WE# high to SR[6] low + * @tWC_min: WE# cycle time + * @tWH_min: WE# high hold time + * @tWHR_min: WE# high to RE# low + * @tWP_min: WE# pulse width + * @tWW_min: WP# transition to WE# low + */ +struct nand_sdr_timings { + u32 tBERS_max; + u32 tCCS_min; + u32 tPROG_max; + u32 tR_max; + u32 tALH_min; + u32 tADL_min; + u32 tALS_min; + u32 tAR_min; + u32 tCEA_max; + u32 tCEH_min; + u32 tCH_min; + u32 tCHZ_max; + u32 tCLH_min; + u32 tCLR_min; + u32 tCLS_min; + u32 tCOH_min; + u32 tCS_min; + u32 tDH_min; + u32 tDS_min; + u32 tFEAT_max; + u32 tIR_min; + u32 tITC_max; + u32 tRC_min; + u32 tREA_max; + u32 tREH_min; + u32 tRHOH_min; + u32 tRHW_min; + u32 tRHZ_max; + u32 tRLOH_min; + u32 tRP_min; + u32 tRR_min; + u64 tRST_max; + u32 tWB_max; + u32 tWC_min; + u32 tWH_min; + u32 tWHR_min; + u32 tWP_min; + u32 tWW_min; +}; + +/** + * enum nand_data_interface_type - NAND interface timing type + * @NAND_SDR_IFACE: Single Data Rate interface + */ +enum nand_data_interface_type { + NAND_SDR_IFACE, +}; + +/** + * struct nand_data_interface - NAND interface timing + * @type: type of the timing + * @timings: The timing, type according to @type + */ +struct nand_data_interface { + enum nand_data_interface_type type; + union { + struct nand_sdr_timings sdr; + } timings; +}; + +/** + * nand_get_sdr_timings - get SDR timing from data interface + * @conf: The data interface + */ +static inline const struct nand_sdr_timings * +nand_get_sdr_timings(const struct nand_data_interface *conf) +{ + if (conf->type != NAND_SDR_IFACE) + return ERR_PTR(-EINVAL); + + return &conf->timings.sdr; +} + +/** + * struct nand_manufacturer_ops - NAND Manufacturer operations + * @detect: detect the NAND memory organization and capabilities + * @init: initialize all vendor specific fields (like the ->read_retry() + * implementation) if any. + * @cleanup: the ->init() function may have allocated resources, ->cleanup() + * is here to let vendor specific code release those resources. + */ +struct nand_manufacturer_ops { + void (*detect)(struct nand_chip *chip); + int (*init)(struct nand_chip *chip); + void (*cleanup)(struct nand_chip *chip); +}; + +/** + * struct nand_chip - NAND Private Flash Chip Data + * @mtd: MTD device registered to the MTD framework + * @IO_ADDR_R: [BOARDSPECIFIC] address to read the 8 I/O lines of the + * flash device + * @IO_ADDR_W: [BOARDSPECIFIC] address to write the 8 I/O lines of the + * flash device. + * @read_byte: [REPLACEABLE] read one byte from the chip + * @read_word: [REPLACEABLE] read one word from the chip + * @write_byte: [REPLACEABLE] write a single byte to the chip on the + * low 8 I/O lines + * @write_buf: [REPLACEABLE] write data from the buffer to the chip + * @read_buf: [REPLACEABLE] read data from the chip into the buffer + * @select_chip: [REPLACEABLE] select chip nr + * @block_bad: [REPLACEABLE] check if a block is bad, using OOB markers + * @block_markbad: [REPLACEABLE] mark a block bad + * @cmd_ctrl: [BOARDSPECIFIC] hardwarespecific function for controlling + * ALE/CLE/nCE. Also used to write command and address + * @dev_ready: [BOARDSPECIFIC] hardwarespecific function for accessing + * device ready/busy line. If set to NULL no access to + * ready/busy is available and the ready/busy information + * is read from the chip status register. + * @cmdfunc: [REPLACEABLE] hardwarespecific function for writing + * commands to the chip. + * @waitfunc: [REPLACEABLE] hardwarespecific function for wait on + * ready. + * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for + * setting the read-retry mode. Mostly needed for MLC NAND. + * @ecc: [BOARDSPECIFIC] ECC control structure + * @buffers: buffer structure for read/write + * @buf_align: minimum buffer alignment required by a platform + * @hwcontrol: platform-specific hardware control structure + * @erase: [REPLACEABLE] erase function + * @scan_bbt: [REPLACEABLE] function to scan bad block table + * @chip_delay: [BOARDSPECIFIC] chip dependent delay for transferring + * data from array to read regs (tR). + * @state: [INTERN] the current state of the NAND device + * @oob_poi: "poison value buffer," used for laying out OOB data + * before writing + * @page_shift: [INTERN] number of address bits in a page (column + * address bits). + * @phys_erase_shift: [INTERN] number of address bits in a physical eraseblock + * @bbt_erase_shift: [INTERN] number of address bits in a bbt entry + * @chip_shift: [INTERN] number of address bits in one chip + * @options: [BOARDSPECIFIC] various chip options. They can partly + * be set to inform nand_scan about special functionality. + * See the defines for further explanation. + * @bbt_options: [INTERN] bad block specific options. All options used + * here must come from bbm.h. By default, these options + * will be copied to the appropriate nand_bbt_descr's. + * @badblockpos: [INTERN] position of the bad block marker in the oob + * area. + * @badblockbits: [INTERN] minimum number of set bits in a good block's + * bad block marker position; i.e., BBM == 11110111b is + * not bad when badblockbits == 7 + * @bits_per_cell: [INTERN] number of bits per cell. i.e., 1 means SLC. + * @ecc_strength_ds: [INTERN] ECC correctability from the datasheet. + * Minimum amount of bit errors per @ecc_step_ds guaranteed + * to be correctable. If unknown, set to zero. + * @ecc_step_ds: [INTERN] ECC step required by the @ecc_strength_ds, + * also from the datasheet. It is the recommended ECC step + * size, if known; if unknown, set to zero. + * @onfi_timing_mode_default: [INTERN] default ONFI timing mode. This field is + * set to the actually used ONFI mode if the chip is + * ONFI compliant or deduced from the datasheet if + * the NAND chip is not ONFI compliant. + * @numchips: [INTERN] number of physical chips + * @chipsize: [INTERN] the size of one chip for multichip arrays + * @pagemask: [INTERN] page number mask = number of (pages / chip) - 1 + * @pagebuf: [INTERN] holds the pagenumber which is currently in + * data_buf. + * @pagebuf_bitflips: [INTERN] holds the bitflip count for the page which is + * currently in data_buf. + * @subpagesize: [INTERN] holds the subpagesize + * @id: [INTERN] holds NAND ID + * @onfi_version: [INTERN] holds the chip ONFI version (BCD encoded), + * non 0 if ONFI supported. + * @jedec_version: [INTERN] holds the chip JEDEC version (BCD encoded), + * non 0 if JEDEC supported. + * @onfi_params: [INTERN] holds the ONFI page parameter when ONFI is + * supported, 0 otherwise. + * @jedec_params: [INTERN] holds the JEDEC parameter page when JEDEC is + * supported, 0 otherwise. + * @max_bb_per_die: [INTERN] the max number of bad blocks each die of a + * this nand device will encounter their life times. + * @blocks_per_die: [INTERN] The number of PEBs in a die + * @data_interface: [INTERN] NAND interface timing information + * @read_retries: [INTERN] the number of read retry modes supported + * @onfi_set_features: [REPLACEABLE] set the features for ONFI nand + * @onfi_get_features: [REPLACEABLE] get the features for ONFI nand + * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If + * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this + * means the configuration should not be applied but + * only checked. + * @bbt: [INTERN] bad block table pointer + * @bbt_td: [REPLACEABLE] bad block table descriptor for flash + * lookup. + * @bbt_md: [REPLACEABLE] bad block table mirror descriptor + * @badblock_pattern: [REPLACEABLE] bad block scan pattern used for initial + * bad block scan. + * @controller: [REPLACEABLE] a pointer to a hardware controller + * structure which is shared among multiple independent + * devices. + * @priv: [OPTIONAL] pointer to private chip data + * @manufacturer: [INTERN] Contains manufacturer information + */ + +struct nand_chip { + struct mtd_info mtd; + void __iomem *IO_ADDR_R; + void __iomem *IO_ADDR_W; + + uint8_t (*read_byte)(struct mtd_info *mtd); + u16 (*read_word)(struct mtd_info *mtd); + void (*write_byte)(struct mtd_info *mtd, uint8_t byte); + void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); + void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); + void (*select_chip)(struct mtd_info *mtd, int chip); + int (*block_bad)(struct mtd_info *mtd, loff_t ofs); + int (*block_markbad)(struct mtd_info *mtd, loff_t ofs); + void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); + int (*dev_ready)(struct mtd_info *mtd); + void (*cmdfunc)(struct mtd_info *mtd, unsigned command, int column, + int page_addr); + int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); + int (*erase)(struct mtd_info *mtd, int page); + int (*scan_bbt)(struct mtd_info *mtd); + int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip, + int feature_addr, uint8_t *subfeature_para); + int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, + int feature_addr, uint8_t *subfeature_para); + int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); + int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, + const struct nand_data_interface *conf); + + + int chip_delay; + unsigned int options; + unsigned int bbt_options; + + int page_shift; + int phys_erase_shift; + int bbt_erase_shift; + int chip_shift; + int numchips; + uint64_t chipsize; + int pagemask; + int pagebuf; + unsigned int pagebuf_bitflips; + int subpagesize; + uint8_t bits_per_cell; + uint16_t ecc_strength_ds; + uint16_t ecc_step_ds; + int onfi_timing_mode_default; + int badblockpos; + int badblockbits; + + struct nand_id id; + int onfi_version; + int jedec_version; + union { + struct nand_onfi_params onfi_params; + struct nand_jedec_params jedec_params; + }; + u16 max_bb_per_die; + u32 blocks_per_die; + + struct nand_data_interface *data_interface; + + int read_retries; + + flstate_t state; + + uint8_t *oob_poi; + struct nand_hw_control *controller; + + struct nand_ecc_ctrl ecc; + struct nand_buffers *buffers; + unsigned long buf_align; + struct nand_hw_control hwcontrol; + + uint8_t *bbt; + struct nand_bbt_descr *bbt_td; + struct nand_bbt_descr *bbt_md; + + struct nand_bbt_descr *badblock_pattern; + + void *priv; + + struct { + const struct nand_manufacturer *desc; + void *priv; + } manufacturer; +}; + +extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops; +extern const struct mtd_ooblayout_ops nand_ooblayout_lp_ops; + +static inline void nand_set_flash_node(struct nand_chip *chip, + struct device_node *np) +{ + mtd_set_of_node(&chip->mtd, np); +} + +static inline struct device_node *nand_get_flash_node(struct nand_chip *chip) +{ + return mtd_get_of_node(&chip->mtd); +} + +static inline struct nand_chip *mtd_to_nand(struct mtd_info *mtd) +{ + return container_of(mtd, struct nand_chip, mtd); +} + +static inline struct mtd_info *nand_to_mtd(struct nand_chip *chip) +{ + return &chip->mtd; +} + +static inline void *nand_get_controller_data(struct nand_chip *chip) +{ + return chip->priv; +} + +static inline void nand_set_controller_data(struct nand_chip *chip, void *priv) +{ + chip->priv = priv; +} + +static inline void nand_set_manufacturer_data(struct nand_chip *chip, + void *priv) +{ + chip->manufacturer.priv = priv; +} + +static inline void *nand_get_manufacturer_data(struct nand_chip *chip) +{ + return chip->manufacturer.priv; +} + +/* + * NAND Flash Manufacturer ID Codes + */ +#define NAND_MFR_TOSHIBA 0x98 +#define NAND_MFR_ESMT 0xc8 +#define NAND_MFR_SAMSUNG 0xec +#define NAND_MFR_FUJITSU 0x04 +#define NAND_MFR_NATIONAL 0x8f +#define NAND_MFR_RENESAS 0x07 +#define NAND_MFR_STMICRO 0x20 +#define NAND_MFR_HYNIX 0xad +#define NAND_MFR_MICRON 0x2c +#define NAND_MFR_AMD 0x01 +#define NAND_MFR_MACRONIX 0xc2 +#define NAND_MFR_EON 0x92 +#define NAND_MFR_SANDISK 0x45 +#define NAND_MFR_INTEL 0x89 +#define NAND_MFR_ATO 0x9b +#define NAND_MFR_WINBOND 0xef + +/* The maximum expected count of bytes in the NAND ID sequence */ +#define NAND_MAX_ID_LEN 8 + +/* + * A helper for defining older NAND chips where the second ID byte fully + * defined the chip, including the geometry (chip size, eraseblock size, page + * size). All these chips have 512 bytes NAND page size. + */ +#define LEGACY_ID_NAND(nm, devid, chipsz, erasesz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .pagesize = 512, \ + .chipsize = (chipsz), .erasesize = (erasesz), .options = (opts) } + +/* + * A helper for defining newer chips which report their page size and + * eraseblock size via the extended ID bytes. + * + * The real difference between LEGACY_ID_NAND and EXTENDED_ID_NAND is that with + * EXTENDED_ID_NAND, manufacturers overloaded the same device ID so that the + * device ID now only represented a particular total chip size (and voltage, + * buswidth), and the page size, eraseblock size, and OOB size could vary while + * using the same device ID. + */ +#define EXTENDED_ID_NAND(nm, devid, chipsz, opts) \ + { .name = (nm), {{ .dev_id = (devid) }}, .chipsize = (chipsz), \ + .options = (opts) } + +#define NAND_ECC_INFO(_strength, _step) \ + { .strength_ds = (_strength), .step_ds = (_step) } +#define NAND_ECC_STRENGTH(type) ((type)->ecc.strength_ds) +#define NAND_ECC_STEP(type) ((type)->ecc.step_ds) + +/** + * struct nand_flash_dev - NAND Flash Device ID Structure + * @name: a human-readable name of the NAND chip + * @dev_id: the device ID (the second byte of the full chip ID array) + * @mfr_id: manufecturer ID part of the full chip ID array (refers the same + * memory address as @id[0]) + * @dev_id: device ID part of the full chip ID array (refers the same memory + * address as @id[1]) + * @id: full device ID array + * @pagesize: size of the NAND page in bytes; if 0, then the real page size (as + * well as the eraseblock size) is determined from the extended NAND + * chip ID array) + * @chipsize: total chip size in MiB + * @erasesize: eraseblock size in bytes (determined from the extended ID if 0) + * @options: stores various chip bit options + * @id_len: The valid length of the @id. + * @oobsize: OOB size + * @ecc: ECC correctability and step information from the datasheet. + * @ecc.strength_ds: The ECC correctability from the datasheet, same as the + * @ecc_strength_ds in nand_chip{}. + * @ecc.step_ds: The ECC step required by the @ecc.strength_ds, same as the + * @ecc_step_ds in nand_chip{}, also from the datasheet. + * For example, the "4bit ECC for each 512Byte" can be set with + * NAND_ECC_INFO(4, 512). + * @onfi_timing_mode_default: the default ONFI timing mode entered after a NAND + * reset. Should be deduced from timings described + * in the datasheet. + * + */ +struct nand_flash_dev { + char *name; + union { + struct { + uint8_t mfr_id; + uint8_t dev_id; + }; + uint8_t id[NAND_MAX_ID_LEN]; + }; + unsigned int pagesize; + unsigned int chipsize; + unsigned int erasesize; + unsigned int options; + uint16_t id_len; + uint16_t oobsize; + struct { + uint16_t strength_ds; + uint16_t step_ds; + } ecc; + int onfi_timing_mode_default; +}; + +/** + * struct nand_manufacturer - NAND Flash Manufacturer structure + * @name: Manufacturer name + * @id: manufacturer ID code of device. + * @ops: manufacturer operations +*/ +struct nand_manufacturer { + int id; + char *name; + const struct nand_manufacturer_ops *ops; +}; + +const struct nand_manufacturer *nand_get_manufacturer(u8 id); + +static inline const char * +nand_manufacturer_name(const struct nand_manufacturer *manufacturer) +{ + return manufacturer ? manufacturer->name : "Unknown"; +} + +extern struct nand_flash_dev nand_flash_ids[]; + +extern const struct nand_manufacturer_ops toshiba_nand_manuf_ops; +extern const struct nand_manufacturer_ops samsung_nand_manuf_ops; +extern const struct nand_manufacturer_ops hynix_nand_manuf_ops; +extern const struct nand_manufacturer_ops micron_nand_manuf_ops; +extern const struct nand_manufacturer_ops amd_nand_manuf_ops; +extern const struct nand_manufacturer_ops macronix_nand_manuf_ops; + +int nand_default_bbt(struct mtd_info *mtd); +int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs); +int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs); +int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt); +int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr, + int allowbbt); +int nand_do_read(struct mtd_info *mtd, loff_t from, size_t len, + size_t *retlen, uint8_t *buf); + +/** + * struct platform_nand_chip - chip level device structure + * @nr_chips: max. number of chips to scan for + * @chip_offset: chip number offset + * @nr_partitions: number of partitions pointed to by partitions (or zero) + * @partitions: mtd partition list + * @chip_delay: R/B delay value in us + * @options: Option flags, e.g. 16bit buswidth + * @bbt_options: BBT option flags, e.g. NAND_BBT_USE_FLASH + * @part_probe_types: NULL-terminated array of probe types + */ +struct platform_nand_chip { + int nr_chips; + int chip_offset; + int nr_partitions; + struct mtd_partition *partitions; + int chip_delay; + unsigned int options; + unsigned int bbt_options; + const char **part_probe_types; +}; + +/* Keep gcc happy */ +struct platform_device; + +/** + * struct platform_nand_ctrl - controller level device structure + * @probe: platform specific function to probe/setup hardware + * @remove: platform specific function to remove/teardown hardware + * @hwcontrol: platform specific hardware control structure + * @dev_ready: platform specific function to read ready/busy pin + * @select_chip: platform specific chip select function + * @cmd_ctrl: platform specific function for controlling + * ALE/CLE/nCE. Also used to write command and address + * @write_buf: platform specific function for write buffer + * @read_buf: platform specific function for read buffer + * @read_byte: platform specific function to read one byte from chip + * @priv: private data to transport driver specific settings + * + * All fields are optional and depend on the hardware driver requirements + */ +struct platform_nand_ctrl { + int (*probe)(struct platform_device *pdev); + void (*remove)(struct platform_device *pdev); + void (*hwcontrol)(struct mtd_info *mtd, int cmd); + int (*dev_ready)(struct mtd_info *mtd); + void (*select_chip)(struct mtd_info *mtd, int chip); + void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl); + void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); + void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); + unsigned char (*read_byte)(struct mtd_info *mtd); + void *priv; +}; + +/** + * struct platform_nand_data - container structure for platform-specific data + * @chip: chip level chip structure + * @ctrl: controller level device structure + */ +struct platform_nand_data { + struct platform_nand_chip chip; + struct platform_nand_ctrl ctrl; +}; + +/* return the supported features. */ +static inline int onfi_feature(struct nand_chip *chip) +{ + return chip->onfi_version ? le16_to_cpu(chip->onfi_params.features) : 0; +} + +/* return the supported asynchronous timing mode. */ +static inline int onfi_get_async_timing_mode(struct nand_chip *chip) +{ + if (!chip->onfi_version) + return ONFI_TIMING_MODE_UNKNOWN; + return le16_to_cpu(chip->onfi_params.async_timing_mode); +} + +/* return the supported synchronous timing mode. */ +static inline int onfi_get_sync_timing_mode(struct nand_chip *chip) +{ + if (!chip->onfi_version) + return ONFI_TIMING_MODE_UNKNOWN; + return le16_to_cpu(chip->onfi_params.src_sync_timing_mode); +} + +int onfi_init_data_interface(struct nand_chip *chip, + struct nand_data_interface *iface, + enum nand_data_interface_type type, + int timing_mode); + +/* + * Check if it is a SLC nand. + * The !nand_is_slc() can be used to check the MLC/TLC nand chips. + * We do not distinguish the MLC and TLC now. + */ +static inline bool nand_is_slc(struct nand_chip *chip) +{ + return chip->bits_per_cell == 1; +} + +/** + * Check if the opcode's address should be sent only on the lower 8 bits + * @command: opcode to check + */ +static inline int nand_opcode_8bits(unsigned int command) +{ + switch (command) { + case NAND_CMD_READID: + case NAND_CMD_PARAM: + case NAND_CMD_GET_FEATURES: + case NAND_CMD_SET_FEATURES: + return 1; + default: + break; + } + return 0; +} + +/* return the supported JEDEC features. */ +static inline int jedec_feature(struct nand_chip *chip) +{ + return chip->jedec_version ? le16_to_cpu(chip->jedec_params.features) + : 0; +} + +/* get timing characteristics from ONFI timing mode. */ +const struct nand_sdr_timings *onfi_async_timing_mode_to_sdr_timings(int mode); +/* get data interface from ONFI timing mode 0, used after reset. */ +const struct nand_data_interface *nand_get_default_data_interface(void); + +int nand_check_erased_ecc_chunk(void *data, int datalen, + void *ecc, int ecclen, + void *extraoob, int extraooblen, + int threshold); + +int nand_check_ecc_caps(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_match_ecc_req(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_maximize_ecc(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +/* Default write_oob implementation */ +int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); + +/* Default write_oob syndrome implementation */ +int nand_write_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, + int page); + +/* Default read_oob implementation */ +int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); + +/* Default read_oob syndrome implementation */ +int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, + int page); + +/* Stub used by drivers that do not support GET/SET FEATURES operations */ +int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd, + struct nand_chip *chip, int addr, + u8 *subfeature_param); + +/* Default read_page_raw implementation */ +int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page); + +/* Default write_page_raw implementation */ +int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + const uint8_t *buf, int oob_required, int page); + +/* Reset and initialize a NAND device */ +int nand_reset(struct nand_chip *chip, int chipnr); + +/* Free resources held by the NAND device */ +void nand_cleanup(struct nand_chip *chip); + +/* Default extended ID decoding function */ +void nand_decode_ext_id(struct nand_chip *chip); +#endif /* __LINUX_MTD_RAWNAND_H */ diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h index 2251add65fa7..c759d403cbc0 100644 --- a/include/linux/mtd/sh_flctl.h +++ b/include/linux/mtd/sh_flctl.h @@ -22,7 +22,7 @@ #include #include -#include +#include #include #include diff --git a/include/linux/mtd/sharpsl.h b/include/linux/mtd/sharpsl.h index 65e91d0fa981..72a79c7d0e08 100644 --- a/include/linux/mtd/sharpsl.h +++ b/include/linux/mtd/sharpsl.h @@ -8,7 +8,7 @@ * published by the Free Software Foundation. */ -#include +#include #include #include diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h index 1cf555aef896..f1a2cf655bdb 100644 --- a/include/linux/platform_data/mtd-davinci.h +++ b/include/linux/platform_data/mtd-davinci.h @@ -28,7 +28,7 @@ #ifndef __ARCH_ARM_DAVINCI_NAND_H #define __ARCH_ARM_DAVINCI_NAND_H -#include +#include #define NANDFCR_OFFSET 0x60 #define NANDFSR_OFFSET 0x64 diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h index f01659026b26..f8c553f92655 100644 --- a/include/linux/platform_data/mtd-nand-s3c2410.h +++ b/include/linux/platform_data/mtd-nand-s3c2410.h @@ -12,7 +12,7 @@ #ifndef __MTD_NAND_S3C2410_H #define __MTD_NAND_S3C2410_H -#include +#include /** * struct s3c2410_nand_set - define a set of one or more nand chips -- cgit v1.2.3 From 0a1c7959acd9674a0e4e59f911f3e5fbf25fd693 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 17 May 2017 17:22:18 +0200 Subject: gpu: drm: tc35876x: move header file out of I2C realm include/linux/i2c is not for client devices. Move the header file to a more appropriate location. Signed-off-by: Wolfram Sang Acked-by: Patrik Jakobsson --- include/linux/i2c/tc35876x.h | 11 ----------- include/linux/platform_data/tc35876x.h | 11 +++++++++++ 2 files changed, 11 insertions(+), 11 deletions(-) delete mode 100644 include/linux/i2c/tc35876x.h create mode 100644 include/linux/platform_data/tc35876x.h (limited to 'include/linux') diff --git a/include/linux/i2c/tc35876x.h b/include/linux/i2c/tc35876x.h deleted file mode 100644 index cd6a51c71e7e..000000000000 --- a/include/linux/i2c/tc35876x.h +++ /dev/null @@ -1,11 +0,0 @@ - -#ifndef _TC35876X_H -#define _TC35876X_H - -struct tc35876x_platform_data { - int gpio_bridge_reset; - int gpio_panel_bl_en; - int gpio_panel_vadd; -}; - -#endif /* _TC35876X_H */ diff --git a/include/linux/platform_data/tc35876x.h b/include/linux/platform_data/tc35876x.h new file mode 100644 index 000000000000..cd6a51c71e7e --- /dev/null +++ b/include/linux/platform_data/tc35876x.h @@ -0,0 +1,11 @@ + +#ifndef _TC35876X_H +#define _TC35876X_H + +struct tc35876x_platform_data { + int gpio_bridge_reset; + int gpio_panel_bl_en; + int gpio_panel_vadd; +}; + +#endif /* _TC35876X_H */ -- cgit v1.2.3 From 7c4974786f4794178f04e96318fc3b2f2850cbc6 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 11 Aug 2017 19:41:17 +0800 Subject: net: export some generic xdp helpers This patch tries to export some generic xdp helpers to drivers. This can let driver to do XDP for a specific skb. This is useful for the case when the packet is hard to be processed at page level directly (e.g jumbo/GSO frame). With this patch, there's no need for driver to forbid the XDP set when configuration is not suitable. Instead, it can defer the XDP for packets that is hard to be processed directly after skb is created. Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1d238d54c484..0f1c4cb2441e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3243,6 +3243,8 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); } +void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); +int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); -- cgit v1.2.3 From 2be03aedbb6d78929c9e3be0d1850830303744f7 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 14 Aug 2017 10:23:25 +0200 Subject: i2c: mux: pca954x: move header file out of I2C realm include/linux/i2c is not for client devices. Move the header file to a more appropriate location. Signed-off-by: Wolfram Sang Signed-off-by: Peter Rosin --- include/linux/i2c/pca954x.h | 48 ----------------------------------- include/linux/platform_data/pca954x.h | 48 +++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+), 48 deletions(-) delete mode 100644 include/linux/i2c/pca954x.h create mode 100644 include/linux/platform_data/pca954x.h (limited to 'include/linux') diff --git a/include/linux/i2c/pca954x.h b/include/linux/i2c/pca954x.h deleted file mode 100644 index 1712677d5904..000000000000 --- a/include/linux/i2c/pca954x.h +++ /dev/null @@ -1,48 +0,0 @@ -/* - * - * pca954x.h - I2C multiplexer/switch support - * - * Copyright (c) 2008-2009 Rodolfo Giometti - * Copyright (c) 2008-2009 Eurotech S.p.A. - * Michael Lawnick - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - - -#ifndef _LINUX_I2C_PCA954X_H -#define _LINUX_I2C_PCA954X_H - -/* Platform data for the PCA954x I2C multiplexers */ - -/* Per channel initialisation data: - * @adap_id: bus number for the adapter. 0 = don't care - * @deselect_on_exit: set this entry to 1, if your H/W needs deselection - * of this channel after transaction. - * - */ -struct pca954x_platform_mode { - int adap_id; - unsigned int deselect_on_exit:1; - unsigned int class; -}; - -/* Per mux/switch data, used with i2c_register_board_info */ -struct pca954x_platform_data { - struct pca954x_platform_mode *modes; - int num_modes; -}; - -#endif /* _LINUX_I2C_PCA954X_H */ diff --git a/include/linux/platform_data/pca954x.h b/include/linux/platform_data/pca954x.h new file mode 100644 index 000000000000..1712677d5904 --- /dev/null +++ b/include/linux/platform_data/pca954x.h @@ -0,0 +1,48 @@ +/* + * + * pca954x.h - I2C multiplexer/switch support + * + * Copyright (c) 2008-2009 Rodolfo Giometti + * Copyright (c) 2008-2009 Eurotech S.p.A. + * Michael Lawnick + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ + + +#ifndef _LINUX_I2C_PCA954X_H +#define _LINUX_I2C_PCA954X_H + +/* Platform data for the PCA954x I2C multiplexers */ + +/* Per channel initialisation data: + * @adap_id: bus number for the adapter. 0 = don't care + * @deselect_on_exit: set this entry to 1, if your H/W needs deselection + * of this channel after transaction. + * + */ +struct pca954x_platform_mode { + int adap_id; + unsigned int deselect_on_exit:1; + unsigned int class; +}; + +/* Per mux/switch data, used with i2c_register_board_info */ +struct pca954x_platform_data { + struct pca954x_platform_mode *modes; + int num_modes; +}; + +#endif /* _LINUX_I2C_PCA954X_H */ -- cgit v1.2.3 From 26b1083b4545ec08a7dcfe759323a2e142d60d75 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 14 Aug 2017 10:23:26 +0200 Subject: i2c: mux: mlxcpld: move header file out of I2C realm include/linux/i2c is not for client devices. Move the header file to a more appropriate location. Signed-off-by: Wolfram Sang Signed-off-by: Peter Rosin --- include/linux/i2c/mlxcpld.h | 52 ------------------------------- include/linux/platform_data/x86/mlxcpld.h | 52 +++++++++++++++++++++++++++++++ 2 files changed, 52 insertions(+), 52 deletions(-) delete mode 100644 include/linux/i2c/mlxcpld.h create mode 100644 include/linux/platform_data/x86/mlxcpld.h (limited to 'include/linux') diff --git a/include/linux/i2c/mlxcpld.h b/include/linux/i2c/mlxcpld.h deleted file mode 100644 index b08dcb183fca..000000000000 --- a/include/linux/i2c/mlxcpld.h +++ /dev/null @@ -1,52 +0,0 @@ -/* - * mlxcpld.h - Mellanox I2C multiplexer support in CPLD - * - * Copyright (c) 2016 Mellanox Technologies. All rights reserved. - * Copyright (c) 2016 Michael Shych - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the names of the copyright holders nor the names of its - * contributors may be used to endorse or promote products derived from - * this software without specific prior written permission. - * - * Alternatively, this software may be distributed under the terms of the - * GNU General Public License ("GPL") version 2 as published by the Free - * Software Foundation. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE - * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE - * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE - * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS - * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN - * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) - * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE - * POSSIBILITY OF SUCH DAMAGE. - */ - -#ifndef _LINUX_I2C_MLXCPLD_H -#define _LINUX_I2C_MLXCPLD_H - -/* Platform data for the CPLD I2C multiplexers */ - -/* mlxcpld_mux_plat_data - per mux data, used with i2c_register_board_info - * @adap_ids - adapter array - * @num_adaps - number of adapters - * @sel_reg_addr - mux select register offset in CPLD space - */ -struct mlxcpld_mux_plat_data { - int *adap_ids; - int num_adaps; - int sel_reg_addr; -}; - -#endif /* _LINUX_I2C_MLXCPLD_H */ diff --git a/include/linux/platform_data/x86/mlxcpld.h b/include/linux/platform_data/x86/mlxcpld.h new file mode 100644 index 000000000000..b08dcb183fca --- /dev/null +++ b/include/linux/platform_data/x86/mlxcpld.h @@ -0,0 +1,52 @@ +/* + * mlxcpld.h - Mellanox I2C multiplexer support in CPLD + * + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Michael Shych + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _LINUX_I2C_MLXCPLD_H +#define _LINUX_I2C_MLXCPLD_H + +/* Platform data for the CPLD I2C multiplexers */ + +/* mlxcpld_mux_plat_data - per mux data, used with i2c_register_board_info + * @adap_ids - adapter array + * @num_adaps - number of adapters + * @sel_reg_addr - mux select register offset in CPLD space + */ +struct mlxcpld_mux_plat_data { + int *adap_ids; + int num_adaps; + int sel_reg_addr; +}; + +#endif /* _LINUX_I2C_MLXCPLD_H */ -- cgit v1.2.3 From c4aee3e1b0de8e732fafd0d13e75ab7bdbc606ef Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Sun, 21 May 2017 18:48:07 +0200 Subject: i2c: mux: pinctrl: remove platform_data No platform (at least no upstreamed platform) has ever used this platform_data. Just drop it and simplify the code. Reviewed-by: Stephen Warren Acked-by: Wolfram Sang Signed-off-by: Peter Rosin --- include/linux/i2c-mux-pinctrl.h | 41 ----------------------------------------- 1 file changed, 41 deletions(-) delete mode 100644 include/linux/i2c-mux-pinctrl.h (limited to 'include/linux') diff --git a/include/linux/i2c-mux-pinctrl.h b/include/linux/i2c-mux-pinctrl.h deleted file mode 100644 index a65c86429e84..000000000000 --- a/include/linux/i2c-mux-pinctrl.h +++ /dev/null @@ -1,41 +0,0 @@ -/* - * i2c-mux-pinctrl platform data - * - * Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see . - */ - -#ifndef _LINUX_I2C_MUX_PINCTRL_H -#define _LINUX_I2C_MUX_PINCTRL_H - -/** - * struct i2c_mux_pinctrl_platform_data - Platform data for i2c-mux-pinctrl - * @parent_bus_num: Parent I2C bus number - * @base_bus_num: Base I2C bus number for the child busses. 0 for dynamic. - * @bus_count: Number of child busses. Also the number of elements in - * @pinctrl_states - * @pinctrl_states: The names of the pinctrl state to select for each child bus - * @pinctrl_state_idle: The pinctrl state to select when no child bus is being - * accessed. If NULL, the most recently used pinctrl state will be left - * selected. - */ -struct i2c_mux_pinctrl_platform_data { - int parent_bus_num; - int base_bus_num; - int bus_count; - const char **pinctrl_states; - const char *pinctrl_state_idle; -}; - -#endif -- cgit v1.2.3 From 3f713b7c223ebe5094973ce6e0272bd97363b552 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 4 Aug 2017 11:22:31 +0900 Subject: pinctrl: move const qualifier before struct Update subsystem wide for consistency. Signed-off-by: Masahiro Yamada Signed-off-by: Linus Walleij --- include/linux/pinctrl/machine.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/machine.h b/include/linux/pinctrl/machine.h index e5b1716f98cc..7fa5d87190c2 100644 --- a/include/linux/pinctrl/machine.h +++ b/include/linux/pinctrl/machine.h @@ -152,12 +152,12 @@ struct pinctrl_map { #ifdef CONFIG_PINCTRL -extern int pinctrl_register_mappings(struct pinctrl_map const *map, +extern int pinctrl_register_mappings(const struct pinctrl_map *map, unsigned num_maps); extern void pinctrl_provide_dummies(void); #else -static inline int pinctrl_register_mappings(struct pinctrl_map const *map, +static inline int pinctrl_register_mappings(const struct pinctrl_map *map, unsigned num_maps) { return 0; -- cgit v1.2.3 From 950d55f5bf7991222e34428b5f779bd030b6a42a Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 24 Jul 2017 16:57:22 +0200 Subject: gpio: Cleanup kerneldoc Some kerneldoc has become stale or wasn't quite correct from the outset. Fix up the most serious issues to silence warnings when building the documentation. Signed-off-by: Thierry Reding Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index af20369ec8e7..ad4150d075c3 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -327,11 +327,10 @@ int gpiochip_generic_config(struct gpio_chip *chip, unsigned offset, /** * struct gpio_pin_range - pin range controlled by a gpio chip - * @head: list for maintaining set of pin ranges, used internally + * @node: list for maintaining set of pin ranges, used internally * @pctldev: pinctrl device which handles corresponding pins * @range: actual range of pins controlled by a gpio controller */ - struct gpio_pin_range { struct list_head node; struct pinctrl_dev *pctldev; -- cgit v1.2.3 From 67049c505017d7b380e16aa4f4b02344c2be0d55 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 24 Jul 2017 16:57:23 +0200 Subject: gpio: of: Improve kerneldoc Add descriptions for missing fields and fix up some parameter references to match the code. Signed-off-by: Thierry Reding Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index ad4150d075c3..fe66c9306caf 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -180,8 +180,27 @@ struct gpio_chip { * If CONFIG_OF is enabled, then all GPIO controllers described in the * device tree automatically may have an OF translation */ + + /** + * @of_node: + * + * Pointer to a device tree node representing this GPIO controller. + */ struct device_node *of_node; + + /** + * @of_gpio_n_cells: + * + * Number of cells used to form the GPIO specifier. + */ int of_gpio_n_cells; + + /** + * @of_xlate: + * + * Callback to translate a device tree GPIO specifier into a chip- + * relative GPIO number and flags. + */ int (*of_xlate)(struct gpio_chip *gc, const struct of_phandle_args *gpiospec, u32 *flags); #endif -- cgit v1.2.3 From e3b445d77819b8fb41e3ceae9dbd49c8c8427c5d Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 24 Jul 2017 16:57:28 +0200 Subject: gpio: Use unsigned int for of_gpio_n_cells The cell count for GPIO specifiers can never be negative, so make the field unsigned. Signed-off-by: Thierry Reding Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index fe66c9306caf..c97f8325e8bf 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -193,7 +193,7 @@ struct gpio_chip { * * Number of cells used to form the GPIO specifier. */ - int of_gpio_n_cells; + unsigned int of_gpio_n_cells; /** * @of_xlate: -- cgit v1.2.3 From 52510ee934885ec846faaa5d029329c9ba0e6ecc Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Mon, 7 Aug 2017 15:24:37 +0800 Subject: soc: mediatek: add SCPSYS power domain driver for MediaTek MT7622 SoC Add SCPSYS power domain driver for MT7622 SoC having four power domains which are respectively ETHSYS for Ethernet including embedded switch, WBSYS for WIFI and Bluetooth, HIF0SYS for PCI-E and SATA, and HIF1SYS for USB. Those functions could be selectively powered gated when the corresponding function is no longer to use in order to reach more minimal power dissipation. Signed-off-by: Chen Zhong Signed-off-by: Sean Wang Reviewed-by: Ulf Hansson Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/infracfg.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/infracfg.h b/include/linux/soc/mediatek/infracfg.h index a5714e93fb34..a0182ec2a621 100644 --- a/include/linux/soc/mediatek/infracfg.h +++ b/include/linux/soc/mediatek/infracfg.h @@ -20,6 +20,13 @@ #define MT8173_TOP_AXI_PROT_EN_MFG_M1 BIT(22) #define MT8173_TOP_AXI_PROT_EN_MFG_SNOOP_OUT BIT(23) +#define MT7622_TOP_AXI_PROT_EN_ETHSYS (BIT(3) | BIT(17)) +#define MT7622_TOP_AXI_PROT_EN_HIF0 (BIT(24) | BIT(25)) +#define MT7622_TOP_AXI_PROT_EN_HIF1 (BIT(26) | BIT(27) | \ + BIT(28)) +#define MT7622_TOP_AXI_PROT_EN_WB (BIT(2) | BIT(6) | \ + BIT(7) | BIT(8)) + int mtk_infracfg_set_bus_protection(struct regmap *infracfg, u32 mask); int mtk_infracfg_clear_bus_protection(struct regmap *infracfg, u32 mask); -- cgit v1.2.3 From 0ddec0fc8900201c0897b87b762b7c420436662f Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Fri, 11 Aug 2017 04:33:54 +0000 Subject: seccomp: Sysctl to configure actions that are allowed to be logged Adminstrators can write to this sysctl to set the seccomp actions that are allowed to be logged. Any actions not found in this sysctl will not be logged. For example, all SECCOMP_RET_KILL, SECCOMP_RET_TRAP, and SECCOMP_RET_ERRNO actions would be loggable if "kill trap errno" were written to the sysctl. SECCOMP_RET_TRACE actions would not be logged since its string representation ("trace") wasn't present in the sysctl value. The path to the sysctl is: /proc/sys/kernel/seccomp/actions_logged The actions_avail sysctl can be read to discover the valid action names that can be written to the actions_logged sysctl with the exception of "allow". SECCOMP_RET_ALLOW actions cannot be configured for logging. The default setting for the sysctl is to allow all actions to be logged except SECCOMP_RET_ALLOW. While only SECCOMP_RET_KILL actions are currently logged, an upcoming patch will allow applications to request additional actions to be logged. There's one important exception to this sysctl. If a task is specifically being audited, meaning that an audit context has been allocated for the task, seccomp will log all actions other than SECCOMP_RET_ALLOW despite the value of actions_logged. This exception preserves the existing auditing behavior of tasks with an allocated audit context. With this patch, the logic for deciding if an action will be logged is: if action == RET_ALLOW: do not log else if action == RET_KILL && RET_KILL in actions_logged: log else if audit_enabled && task-is-being-audited: log else: do not log Signed-off-by: Tyler Hicks Signed-off-by: Kees Cook --- include/linux/audit.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 2150bdccfbab..8c30f06d639d 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -314,11 +314,7 @@ void audit_core_dumps(long signr); static inline void audit_seccomp(unsigned long syscall, long signr, int code) { - if (!audit_enabled) - return; - - /* Force a record to be reported if a signal was delivered. */ - if (signr || unlikely(!audit_dummy_context())) + if (audit_enabled && unlikely(!audit_dummy_context())) __audit_seccomp(syscall, signr, code); } -- cgit v1.2.3 From e66a39977985b1e69e17c4042cb290768eca9b02 Mon Sep 17 00:00:00 2001 From: Tyler Hicks Date: Fri, 11 Aug 2017 04:33:56 +0000 Subject: seccomp: Filter flag to log all actions except SECCOMP_RET_ALLOW Add a new filter flag, SECCOMP_FILTER_FLAG_LOG, that enables logging for all actions except for SECCOMP_RET_ALLOW for the given filter. SECCOMP_RET_KILL actions are always logged, when "kill" is in the actions_logged sysctl, and SECCOMP_RET_ALLOW actions are never logged, regardless of this flag. This flag can be used to create noisy filters that result in all non-allowed actions to be logged. A process may have one noisy filter, which is loaded with this flag, as well as a quiet filter that's not loaded with this flag. This allows for the actions in a set of filters to be selectively conveyed to the admin. Since a system could have a large number of allocated seccomp_filter structs, struct packing was taken in consideration. On 64 bit x86, the new log member takes up one byte of an existing four byte hole in the struct. On 32 bit x86, the new log member creates a new four byte hole (unavoidable) and consumes one of those bytes. Unfortunately, the tests added for SECCOMP_FILTER_FLAG_LOG are not capable of inspecting the audit log to verify that the actions taken in the filter were logged. With this patch, the logic for deciding if an action will be logged is: if action == RET_ALLOW: do not log else if action == RET_KILL && RET_KILL in actions_logged: log else if filter-requests-logging && action in actions_logged: log else if audit_enabled && process-is-being-audited: log else: do not log Signed-off-by: Tyler Hicks Signed-off-by: Kees Cook --- include/linux/seccomp.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index ecc296c137cd..c8bef436b61d 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -3,7 +3,8 @@ #include -#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC) +#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ + SECCOMP_FILTER_FLAG_LOG) #ifdef CONFIG_SECCOMP -- cgit v1.2.3 From a99b646afa8a02571ea298bedca6592d818229cd Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Tue, 15 Aug 2017 11:23:23 +0800 Subject: PCI: Disable PCIe Relaxed Ordering if unsupported When bit4 is set in the PCIe Device Control register, it indicates whether the device is permitted to use relaxed ordering. On some platforms using relaxed ordering can have performance issues or due to erratum can cause data-corruption. In such cases devices must avoid using relaxed ordering. The patch adds a new flag PCI_DEV_FLAGS_NO_RELAXED_ORDERING to indicate that Relaxed Ordering (RO) attribute should not be used for Transaction Layer Packets (TLP) targeted towards these affected root complexes. This patch checks if there is any node in the hierarchy that indicates that using relaxed ordering is not safe. In such cases the patch turns off the relaxed ordering by clearing the capability for this device. Signed-off-by: Casey Leedom Signed-off-by: Ding Tianhong Acked-by: Ashok Raj Acked-by: Alexander Duyck Acked-by: Casey Leedom Signed-off-by: David S. Miller --- include/linux/pci.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659..29606fb89464 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -188,6 +188,8 @@ enum pci_dev_flags { * the direct_complete optimization. */ PCI_DEV_FLAGS_NEEDS_RESUME = (__force pci_dev_flags_t) (1 << 11), + /* Don't use Relaxed Ordering for TLPs directed at this device */ + PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 12), }; enum pci_irq_reroute_variant { @@ -1125,6 +1127,7 @@ bool pci_check_pme_status(struct pci_dev *dev); void pci_pme_wakeup_bus(struct pci_bus *bus); void pci_d3cold_enable(struct pci_dev *dev); void pci_d3cold_disable(struct pci_dev *dev); +bool pcie_relaxed_ordering_enabled(struct pci_dev *dev); /* PCI Virtual Channel */ int pci_save_vc_state(struct pci_dev *dev); -- cgit v1.2.3 From 0335a9554b4d6acc2d17efe752bff54ce59b57eb Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 14 Aug 2017 18:34:22 +0200 Subject: mfd: dm355evm_msp: Move header file out of I2C realm include/linux/i2c is not for client devices. Move the header file to a more appropriate location. Signed-off-by: Wolfram Sang Acked-by: Alexandre Belloni Acked-by: Dmitry Torokhov Signed-off-by: Lee Jones --- include/linux/i2c/dm355evm_msp.h | 79 ---------------------------------------- include/linux/mfd/dm355evm_msp.h | 79 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+), 79 deletions(-) delete mode 100644 include/linux/i2c/dm355evm_msp.h create mode 100644 include/linux/mfd/dm355evm_msp.h (limited to 'include/linux') diff --git a/include/linux/i2c/dm355evm_msp.h b/include/linux/i2c/dm355evm_msp.h deleted file mode 100644 index 372470350fab..000000000000 --- a/include/linux/i2c/dm355evm_msp.h +++ /dev/null @@ -1,79 +0,0 @@ -/* - * dm355evm_msp.h - support MSP430 microcontroller on DM355EVM board - */ -#ifndef __LINUX_I2C_DM355EVM_MSP -#define __LINUX_I2C_DM355EVM_MSP - -/* - * Written against Spectrum's writeup for the A4 firmware revision, - * and tweaked to match source and rev D2 schematics by removing CPLD - * and NOR flash hooks (which were last appropriate in rev B boards). - * - * Note that the firmware supports a flavor of write posting ... to be - * sure a write completes, issue another read or write. - */ - -/* utilities to access "registers" emulated by msp430 firmware */ -extern int dm355evm_msp_write(u8 value, u8 reg); -extern int dm355evm_msp_read(u8 reg); - - -/* command/control registers */ -#define DM355EVM_MSP_COMMAND 0x00 -# define MSP_COMMAND_NULL 0 -# define MSP_COMMAND_RESET_COLD 1 -# define MSP_COMMAND_RESET_WARM 2 -# define MSP_COMMAND_RESET_WARM_I 3 -# define MSP_COMMAND_POWEROFF 4 -# define MSP_COMMAND_IR_REINIT 5 -#define DM355EVM_MSP_STATUS 0x01 -# define MSP_STATUS_BAD_OFFSET BIT(0) -# define MSP_STATUS_BAD_COMMAND BIT(1) -# define MSP_STATUS_POWER_ERROR BIT(2) -# define MSP_STATUS_RXBUF_OVERRUN BIT(3) -#define DM355EVM_MSP_RESET 0x02 /* 0 bits == in reset */ -# define MSP_RESET_DC5 BIT(0) -# define MSP_RESET_TVP5154 BIT(2) -# define MSP_RESET_IMAGER BIT(3) -# define MSP_RESET_ETHERNET BIT(4) -# define MSP_RESET_SYS BIT(5) -# define MSP_RESET_AIC33 BIT(7) - -/* GPIO registers ... bit patterns mostly match the source MSP ports */ -#define DM355EVM_MSP_LED 0x03 /* active low (MSP P4) */ -#define DM355EVM_MSP_SWITCH1 0x04 /* (MSP P5, masked) */ -# define MSP_SWITCH1_SW6_1 BIT(0) -# define MSP_SWITCH1_SW6_2 BIT(1) -# define MSP_SWITCH1_SW6_3 BIT(2) -# define MSP_SWITCH1_SW6_4 BIT(3) -# define MSP_SWITCH1_J1 BIT(4) /* NTSC/PAL */ -# define MSP_SWITCH1_MSP_INT BIT(5) /* active low */ -#define DM355EVM_MSP_SWITCH2 0x05 /* (MSP P6, masked) */ -# define MSP_SWITCH2_SW10 BIT(3) -# define MSP_SWITCH2_SW11 BIT(4) -# define MSP_SWITCH2_SW12 BIT(5) -# define MSP_SWITCH2_SW13 BIT(6) -# define MSP_SWITCH2_SW14 BIT(7) -#define DM355EVM_MSP_SDMMC 0x06 /* (MSP P2, masked) */ -# define MSP_SDMMC_0_WP BIT(1) -# define MSP_SDMMC_0_CD BIT(2) /* active low */ -# define MSP_SDMMC_1_WP BIT(3) -# define MSP_SDMMC_1_CD BIT(4) /* active low */ -#define DM355EVM_MSP_FIRMREV 0x07 /* not a GPIO (out of order) */ -#define DM355EVM_MSP_VIDEO_IN 0x08 /* (MSP P3, masked) */ -# define MSP_VIDEO_IMAGER BIT(7) /* low == tvp5146 */ - -/* power supply registers are currently omitted */ - -/* RTC registers */ -#define DM355EVM_MSP_RTC_0 0x12 /* LSB */ -#define DM355EVM_MSP_RTC_1 0x13 -#define DM355EVM_MSP_RTC_2 0x14 -#define DM355EVM_MSP_RTC_3 0x15 /* MSB */ - -/* input event queue registers; code == ((HIGH << 8) | LOW) */ -#define DM355EVM_MSP_INPUT_COUNT 0x16 /* decrement by reading LOW */ -#define DM355EVM_MSP_INPUT_HIGH 0x17 -#define DM355EVM_MSP_INPUT_LOW 0x18 - -#endif /* __LINUX_I2C_DM355EVM_MSP */ diff --git a/include/linux/mfd/dm355evm_msp.h b/include/linux/mfd/dm355evm_msp.h new file mode 100644 index 000000000000..372470350fab --- /dev/null +++ b/include/linux/mfd/dm355evm_msp.h @@ -0,0 +1,79 @@ +/* + * dm355evm_msp.h - support MSP430 microcontroller on DM355EVM board + */ +#ifndef __LINUX_I2C_DM355EVM_MSP +#define __LINUX_I2C_DM355EVM_MSP + +/* + * Written against Spectrum's writeup for the A4 firmware revision, + * and tweaked to match source and rev D2 schematics by removing CPLD + * and NOR flash hooks (which were last appropriate in rev B boards). + * + * Note that the firmware supports a flavor of write posting ... to be + * sure a write completes, issue another read or write. + */ + +/* utilities to access "registers" emulated by msp430 firmware */ +extern int dm355evm_msp_write(u8 value, u8 reg); +extern int dm355evm_msp_read(u8 reg); + + +/* command/control registers */ +#define DM355EVM_MSP_COMMAND 0x00 +# define MSP_COMMAND_NULL 0 +# define MSP_COMMAND_RESET_COLD 1 +# define MSP_COMMAND_RESET_WARM 2 +# define MSP_COMMAND_RESET_WARM_I 3 +# define MSP_COMMAND_POWEROFF 4 +# define MSP_COMMAND_IR_REINIT 5 +#define DM355EVM_MSP_STATUS 0x01 +# define MSP_STATUS_BAD_OFFSET BIT(0) +# define MSP_STATUS_BAD_COMMAND BIT(1) +# define MSP_STATUS_POWER_ERROR BIT(2) +# define MSP_STATUS_RXBUF_OVERRUN BIT(3) +#define DM355EVM_MSP_RESET 0x02 /* 0 bits == in reset */ +# define MSP_RESET_DC5 BIT(0) +# define MSP_RESET_TVP5154 BIT(2) +# define MSP_RESET_IMAGER BIT(3) +# define MSP_RESET_ETHERNET BIT(4) +# define MSP_RESET_SYS BIT(5) +# define MSP_RESET_AIC33 BIT(7) + +/* GPIO registers ... bit patterns mostly match the source MSP ports */ +#define DM355EVM_MSP_LED 0x03 /* active low (MSP P4) */ +#define DM355EVM_MSP_SWITCH1 0x04 /* (MSP P5, masked) */ +# define MSP_SWITCH1_SW6_1 BIT(0) +# define MSP_SWITCH1_SW6_2 BIT(1) +# define MSP_SWITCH1_SW6_3 BIT(2) +# define MSP_SWITCH1_SW6_4 BIT(3) +# define MSP_SWITCH1_J1 BIT(4) /* NTSC/PAL */ +# define MSP_SWITCH1_MSP_INT BIT(5) /* active low */ +#define DM355EVM_MSP_SWITCH2 0x05 /* (MSP P6, masked) */ +# define MSP_SWITCH2_SW10 BIT(3) +# define MSP_SWITCH2_SW11 BIT(4) +# define MSP_SWITCH2_SW12 BIT(5) +# define MSP_SWITCH2_SW13 BIT(6) +# define MSP_SWITCH2_SW14 BIT(7) +#define DM355EVM_MSP_SDMMC 0x06 /* (MSP P2, masked) */ +# define MSP_SDMMC_0_WP BIT(1) +# define MSP_SDMMC_0_CD BIT(2) /* active low */ +# define MSP_SDMMC_1_WP BIT(3) +# define MSP_SDMMC_1_CD BIT(4) /* active low */ +#define DM355EVM_MSP_FIRMREV 0x07 /* not a GPIO (out of order) */ +#define DM355EVM_MSP_VIDEO_IN 0x08 /* (MSP P3, masked) */ +# define MSP_VIDEO_IMAGER BIT(7) /* low == tvp5146 */ + +/* power supply registers are currently omitted */ + +/* RTC registers */ +#define DM355EVM_MSP_RTC_0 0x12 /* LSB */ +#define DM355EVM_MSP_RTC_1 0x13 +#define DM355EVM_MSP_RTC_2 0x14 +#define DM355EVM_MSP_RTC_3 0x15 /* MSB */ + +/* input event queue registers; code == ((HIGH << 8) | LOW) */ +#define DM355EVM_MSP_INPUT_COUNT 0x16 /* decrement by reading LOW */ +#define DM355EVM_MSP_INPUT_HIGH 0x17 +#define DM355EVM_MSP_INPUT_LOW 0x18 + +#endif /* __LINUX_I2C_DM355EVM_MSP */ -- cgit v1.2.3 From 9787076c43a86f3465d46aa344cc3e2f607ae72f Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 14 Aug 2017 18:34:23 +0200 Subject: mfd: tps65010: Move header file out of I2C realm include/linux/i2c is not for client devices. Move the header file to a more appropriate location. Signed-off-by: Wolfram Sang Acked-by: Greg Kroah-Hartman Acked-by: Krzysztof Kozlowski Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Tony Lindgren Signed-off-by: Lee Jones --- include/linux/i2c/tps65010.h | 205 ------------------------------------------- include/linux/mfd/tps65010.h | 205 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 205 insertions(+), 205 deletions(-) delete mode 100644 include/linux/i2c/tps65010.h create mode 100644 include/linux/mfd/tps65010.h (limited to 'include/linux') diff --git a/include/linux/i2c/tps65010.h b/include/linux/i2c/tps65010.h deleted file mode 100644 index 08aa92278d71..000000000000 --- a/include/linux/i2c/tps65010.h +++ /dev/null @@ -1,205 +0,0 @@ -/* linux/i2c/tps65010.h - * - * Functions to access TPS65010 power management device. - * - * Copyright (C) 2004 Dirk Behme - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN - * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, - * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT - * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF - * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON - * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF - * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 675 Mass Ave, Cambridge, MA 02139, USA. - */ - -#ifndef __LINUX_I2C_TPS65010_H -#define __LINUX_I2C_TPS65010_H - -/* - * ---------------------------------------------------------------------------- - * Registers, all 8 bits - * ---------------------------------------------------------------------------- - */ - -#define TPS_CHGSTATUS 0x01 -# define TPS_CHG_USB (1 << 7) -# define TPS_CHG_AC (1 << 6) -# define TPS_CHG_THERM (1 << 5) -# define TPS_CHG_TERM (1 << 4) -# define TPS_CHG_TAPER_TMO (1 << 3) -# define TPS_CHG_CHG_TMO (1 << 2) -# define TPS_CHG_PRECHG_TMO (1 << 1) -# define TPS_CHG_TEMP_ERR (1 << 0) -#define TPS_REGSTATUS 0x02 -# define TPS_REG_ONOFF (1 << 7) -# define TPS_REG_COVER (1 << 6) -# define TPS_REG_UVLO (1 << 5) -# define TPS_REG_NO_CHG (1 << 4) /* tps65013 */ -# define TPS_REG_PG_LD02 (1 << 3) -# define TPS_REG_PG_LD01 (1 << 2) -# define TPS_REG_PG_MAIN (1 << 1) -# define TPS_REG_PG_CORE (1 << 0) -#define TPS_MASK1 0x03 -#define TPS_MASK2 0x04 -#define TPS_ACKINT1 0x05 -#define TPS_ACKINT2 0x06 -#define TPS_CHGCONFIG 0x07 -# define TPS_CHARGE_POR (1 << 7) /* 65010/65012 */ -# define TPS65013_AUA (1 << 7) /* 65011/65013 */ -# define TPS_CHARGE_RESET (1 << 6) -# define TPS_CHARGE_FAST (1 << 5) -# define TPS_CHARGE_CURRENT (3 << 3) -# define TPS_VBUS_500MA (1 << 2) -# define TPS_VBUS_CHARGING (1 << 1) -# define TPS_CHARGE_ENABLE (1 << 0) -#define TPS_LED1_ON 0x08 -#define TPS_LED1_PER 0x09 -#define TPS_LED2_ON 0x0a -#define TPS_LED2_PER 0x0b -#define TPS_VDCDC1 0x0c -# define TPS_ENABLE_LP (1 << 3) -#define TPS_VDCDC2 0x0d -# define TPS_LP_COREOFF (1 << 7) -# define TPS_VCORE_1_8V (7<<4) -# define TPS_VCORE_1_5V (6 << 4) -# define TPS_VCORE_1_4V (5 << 4) -# define TPS_VCORE_1_3V (4 << 4) -# define TPS_VCORE_1_2V (3 << 4) -# define TPS_VCORE_1_1V (2 << 4) -# define TPS_VCORE_1_0V (1 << 4) -# define TPS_VCORE_0_85V (0 << 4) -# define TPS_VCORE_LP_1_2V (3 << 2) -# define TPS_VCORE_LP_1_1V (2 << 2) -# define TPS_VCORE_LP_1_0V (1 << 2) -# define TPS_VCORE_LP_0_85V (0 << 2) -# define TPS_VIB (1 << 1) -# define TPS_VCORE_DISCH (1 << 0) -#define TPS_VREGS1 0x0e -# define TPS_LDO2_ENABLE (1 << 7) -# define TPS_LDO2_OFF (1 << 6) -# define TPS_VLDO2_3_0V (3 << 4) -# define TPS_VLDO2_2_75V (2 << 4) -# define TPS_VLDO2_2_5V (1 << 4) -# define TPS_VLDO2_1_8V (0 << 4) -# define TPS_LDO1_ENABLE (1 << 3) -# define TPS_LDO1_OFF (1 << 2) -# define TPS_VLDO1_3_0V (3 << 0) -# define TPS_VLDO1_2_75V (2 << 0) -# define TPS_VLDO1_2_5V (1 << 0) -# define TPS_VLDO1_ADJ (0 << 0) -#define TPS_MASK3 0x0f -#define TPS_DEFGPIO 0x10 - -/* - * ---------------------------------------------------------------------------- - * Macros used by exported functions - * ---------------------------------------------------------------------------- - */ - -#define LED1 1 -#define LED2 2 -#define OFF 0 -#define ON 1 -#define BLINK 2 -#define GPIO1 1 -#define GPIO2 2 -#define GPIO3 3 -#define GPIO4 4 -#define LOW 0 -#define HIGH 1 - -/* - * ---------------------------------------------------------------------------- - * Exported functions - * ---------------------------------------------------------------------------- - */ - -/* Draw from VBUS: - * 0 mA -- DON'T DRAW (might supply power instead) - * 100 mA -- usb unit load (slowest charge rate) - * 500 mA -- usb high power (fast battery charge) - */ -extern int tps65010_set_vbus_draw(unsigned mA); - -/* tps65010_set_gpio_out_value parameter: - * gpio: GPIO1, GPIO2, GPIO3 or GPIO4 - * value: LOW or HIGH - */ -extern int tps65010_set_gpio_out_value(unsigned gpio, unsigned value); - -/* tps65010_set_led parameter: - * led: LED1 or LED2 - * mode: ON, OFF or BLINK - */ -extern int tps65010_set_led(unsigned led, unsigned mode); - -/* tps65010_set_vib parameter: - * value: ON or OFF - */ -extern int tps65010_set_vib(unsigned value); - -/* tps65010_set_low_pwr parameter: - * mode: ON or OFF - */ -extern int tps65010_set_low_pwr(unsigned mode); - -/* tps65010_config_vregs1 parameter: - * value to be written to VREGS1 register - * Note: The complete register is written, set all bits you need - */ -extern int tps65010_config_vregs1(unsigned value); - -/* tps65013_set_low_pwr parameter: - * mode: ON or OFF - */ -extern int tps65013_set_low_pwr(unsigned mode); - -/* tps65010_set_vdcdc2 - * value to be written to VDCDC2 - */ -extern int tps65010_config_vdcdc2(unsigned value); - -struct i2c_client; - -/** - * struct tps65010_board - packages GPIO and LED lines - * @base: the GPIO number to assign to GPIO-1 - * @outmask: bit (N-1) is set to allow GPIO-N to be used as an - * (open drain) output - * @setup: optional callback issued once the GPIOs are valid - * @teardown: optional callback issued before the GPIOs are invalidated - * @context: optional parameter passed to setup() and teardown() - * - * Board data may be used to package the GPIO (and LED) lines for use - * in by the generic GPIO and LED frameworks. The first four GPIOs - * starting at gpio_base are GPIO1..GPIO4. The next two are LED1/nPG - * and LED2 (with hardware blinking capability, not currently exposed). - * - * The @setup callback may be used with the kind of board-specific glue - * which hands the (now-valid) GPIOs to other drivers, or which puts - * devices in their initial states using these GPIOs. - */ -struct tps65010_board { - int base; - unsigned outmask; - - int (*setup)(struct i2c_client *client, void *context); - int (*teardown)(struct i2c_client *client, void *context); - void *context; -}; - -#endif /* __LINUX_I2C_TPS65010_H */ - diff --git a/include/linux/mfd/tps65010.h b/include/linux/mfd/tps65010.h new file mode 100644 index 000000000000..a1fb9bc5311d --- /dev/null +++ b/include/linux/mfd/tps65010.h @@ -0,0 +1,205 @@ +/* linux/mfd/tps65010.h + * + * Functions to access TPS65010 power management device. + * + * Copyright (C) 2004 Dirk Behme + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED + * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN + * NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT + * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON + * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF + * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 675 Mass Ave, Cambridge, MA 02139, USA. + */ + +#ifndef __LINUX_I2C_TPS65010_H +#define __LINUX_I2C_TPS65010_H + +/* + * ---------------------------------------------------------------------------- + * Registers, all 8 bits + * ---------------------------------------------------------------------------- + */ + +#define TPS_CHGSTATUS 0x01 +# define TPS_CHG_USB (1 << 7) +# define TPS_CHG_AC (1 << 6) +# define TPS_CHG_THERM (1 << 5) +# define TPS_CHG_TERM (1 << 4) +# define TPS_CHG_TAPER_TMO (1 << 3) +# define TPS_CHG_CHG_TMO (1 << 2) +# define TPS_CHG_PRECHG_TMO (1 << 1) +# define TPS_CHG_TEMP_ERR (1 << 0) +#define TPS_REGSTATUS 0x02 +# define TPS_REG_ONOFF (1 << 7) +# define TPS_REG_COVER (1 << 6) +# define TPS_REG_UVLO (1 << 5) +# define TPS_REG_NO_CHG (1 << 4) /* tps65013 */ +# define TPS_REG_PG_LD02 (1 << 3) +# define TPS_REG_PG_LD01 (1 << 2) +# define TPS_REG_PG_MAIN (1 << 1) +# define TPS_REG_PG_CORE (1 << 0) +#define TPS_MASK1 0x03 +#define TPS_MASK2 0x04 +#define TPS_ACKINT1 0x05 +#define TPS_ACKINT2 0x06 +#define TPS_CHGCONFIG 0x07 +# define TPS_CHARGE_POR (1 << 7) /* 65010/65012 */ +# define TPS65013_AUA (1 << 7) /* 65011/65013 */ +# define TPS_CHARGE_RESET (1 << 6) +# define TPS_CHARGE_FAST (1 << 5) +# define TPS_CHARGE_CURRENT (3 << 3) +# define TPS_VBUS_500MA (1 << 2) +# define TPS_VBUS_CHARGING (1 << 1) +# define TPS_CHARGE_ENABLE (1 << 0) +#define TPS_LED1_ON 0x08 +#define TPS_LED1_PER 0x09 +#define TPS_LED2_ON 0x0a +#define TPS_LED2_PER 0x0b +#define TPS_VDCDC1 0x0c +# define TPS_ENABLE_LP (1 << 3) +#define TPS_VDCDC2 0x0d +# define TPS_LP_COREOFF (1 << 7) +# define TPS_VCORE_1_8V (7<<4) +# define TPS_VCORE_1_5V (6 << 4) +# define TPS_VCORE_1_4V (5 << 4) +# define TPS_VCORE_1_3V (4 << 4) +# define TPS_VCORE_1_2V (3 << 4) +# define TPS_VCORE_1_1V (2 << 4) +# define TPS_VCORE_1_0V (1 << 4) +# define TPS_VCORE_0_85V (0 << 4) +# define TPS_VCORE_LP_1_2V (3 << 2) +# define TPS_VCORE_LP_1_1V (2 << 2) +# define TPS_VCORE_LP_1_0V (1 << 2) +# define TPS_VCORE_LP_0_85V (0 << 2) +# define TPS_VIB (1 << 1) +# define TPS_VCORE_DISCH (1 << 0) +#define TPS_VREGS1 0x0e +# define TPS_LDO2_ENABLE (1 << 7) +# define TPS_LDO2_OFF (1 << 6) +# define TPS_VLDO2_3_0V (3 << 4) +# define TPS_VLDO2_2_75V (2 << 4) +# define TPS_VLDO2_2_5V (1 << 4) +# define TPS_VLDO2_1_8V (0 << 4) +# define TPS_LDO1_ENABLE (1 << 3) +# define TPS_LDO1_OFF (1 << 2) +# define TPS_VLDO1_3_0V (3 << 0) +# define TPS_VLDO1_2_75V (2 << 0) +# define TPS_VLDO1_2_5V (1 << 0) +# define TPS_VLDO1_ADJ (0 << 0) +#define TPS_MASK3 0x0f +#define TPS_DEFGPIO 0x10 + +/* + * ---------------------------------------------------------------------------- + * Macros used by exported functions + * ---------------------------------------------------------------------------- + */ + +#define LED1 1 +#define LED2 2 +#define OFF 0 +#define ON 1 +#define BLINK 2 +#define GPIO1 1 +#define GPIO2 2 +#define GPIO3 3 +#define GPIO4 4 +#define LOW 0 +#define HIGH 1 + +/* + * ---------------------------------------------------------------------------- + * Exported functions + * ---------------------------------------------------------------------------- + */ + +/* Draw from VBUS: + * 0 mA -- DON'T DRAW (might supply power instead) + * 100 mA -- usb unit load (slowest charge rate) + * 500 mA -- usb high power (fast battery charge) + */ +extern int tps65010_set_vbus_draw(unsigned mA); + +/* tps65010_set_gpio_out_value parameter: + * gpio: GPIO1, GPIO2, GPIO3 or GPIO4 + * value: LOW or HIGH + */ +extern int tps65010_set_gpio_out_value(unsigned gpio, unsigned value); + +/* tps65010_set_led parameter: + * led: LED1 or LED2 + * mode: ON, OFF or BLINK + */ +extern int tps65010_set_led(unsigned led, unsigned mode); + +/* tps65010_set_vib parameter: + * value: ON or OFF + */ +extern int tps65010_set_vib(unsigned value); + +/* tps65010_set_low_pwr parameter: + * mode: ON or OFF + */ +extern int tps65010_set_low_pwr(unsigned mode); + +/* tps65010_config_vregs1 parameter: + * value to be written to VREGS1 register + * Note: The complete register is written, set all bits you need + */ +extern int tps65010_config_vregs1(unsigned value); + +/* tps65013_set_low_pwr parameter: + * mode: ON or OFF + */ +extern int tps65013_set_low_pwr(unsigned mode); + +/* tps65010_set_vdcdc2 + * value to be written to VDCDC2 + */ +extern int tps65010_config_vdcdc2(unsigned value); + +struct i2c_client; + +/** + * struct tps65010_board - packages GPIO and LED lines + * @base: the GPIO number to assign to GPIO-1 + * @outmask: bit (N-1) is set to allow GPIO-N to be used as an + * (open drain) output + * @setup: optional callback issued once the GPIOs are valid + * @teardown: optional callback issued before the GPIOs are invalidated + * @context: optional parameter passed to setup() and teardown() + * + * Board data may be used to package the GPIO (and LED) lines for use + * in by the generic GPIO and LED frameworks. The first four GPIOs + * starting at gpio_base are GPIO1..GPIO4. The next two are LED1/nPG + * and LED2 (with hardware blinking capability, not currently exposed). + * + * The @setup callback may be used with the kind of board-specific glue + * which hands the (now-valid) GPIOs to other drivers, or which puts + * devices in their initial states using these GPIOs. + */ +struct tps65010_board { + int base; + unsigned outmask; + + int (*setup)(struct i2c_client *client, void *context); + int (*teardown)(struct i2c_client *client, void *context); + void *context; +}; + +#endif /* __LINUX_I2C_TPS65010_H */ + -- cgit v1.2.3 From b3c4ec71ec413c2e5bfb028bdf1737af07f1fde0 Mon Sep 17 00:00:00 2001 From: Abdulhadi Mohamed Date: Wed, 19 Jul 2017 16:31:10 +0100 Subject: usb: gadget: f_hid: {GET,SET} PROTOCOL Support The current f_hid driver doesn't handle GET_PROCOTOL and SET_PROCOTOL requests, which are required to operate HID gadgets in BOOT mode. This patch implements this feature for devices that have the same implementation for REPORT and BOOT mode so that these devices are recognized by older BIOSes. Signed-off-by: Abdulhadi Mohamed Signed-off-by: Felipe Balbi --- include/linux/hid.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 5006f9b5d837..6519cdc4c7d3 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -362,6 +362,12 @@ struct hid_item { #define HID_GROUP_WACOM 0x0101 #define HID_GROUP_LOGITECH_DJ_DEVICE 0x0102 +/* + * HID protocol status + */ +#define HID_REPORT_PROTOCOL 1 +#define HID_BOOT_PROTOCOL 0 + /* * This is the global environment of the parser. This information is * persistent for main-items. The global environment can be saved and -- cgit v1.2.3 From 31fe084ffaaf8abece14f8ca28e5e3b4e2bf97b6 Mon Sep 17 00:00:00 2001 From: Jack Pham Date: Tue, 1 Aug 2017 02:00:56 -0700 Subject: usb: gadget: core: unmap request from DMA only if previously mapped In the SG case this is already handled since a non-zero request->num_mapped_sgs is a clear indicator that dma_map_sg() had been called. While it would be nice to do the same for the singly mapped case by simply checking for non-zero request->dma, it's conceivable that 0 is a valid dma_addr_t handle. Hence add a flag 'dma_mapped' to struct usb_request and use this to determine the need to call dma_unmap_single(). Otherwise, if a request is not DMA mapped then the result of calling usb_request_unmap_request() would safely be a no-op. Signed-off-by: Jack Pham Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 1a4a4bacfae6..21468a722c4a 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -48,6 +48,7 @@ struct usb_ep; * by adding a zero length packet as needed; * @short_not_ok: When reading data, makes short packets be * treated as errors (queue stops advancing till cleanup). + * @dma_mapped: Indicates if request has been mapped to DMA (internal) * @complete: Function called when request completes, so this request and * its buffer may be re-used. The function will always be called with * interrupts disabled, and it must not sleep. @@ -103,6 +104,7 @@ struct usb_request { unsigned no_interrupt:1; unsigned zero:1; unsigned short_not_ok:1; + unsigned dma_mapped:1; void (*complete)(struct usb_ep *ep, struct usb_request *req); -- cgit v1.2.3 From a551e27368dea202cbef3e8861c21d965427cfe6 Mon Sep 17 00:00:00 2001 From: Chenglin Xu Date: Tue, 15 Aug 2017 17:09:15 +0800 Subject: regulator: mt6380: Add support for MT6380 The MT6380 is a regulator found those boards with MediaTek MT7622 SoC It is connected as a slave to the SoC using MediaTek PMIC wrapper which is the common interface connecting with Mediatek made various PMICs. Signed-off-by: Chenglin Xu Signed-off-by: Sean Wang Signed-off-by: Mark Brown --- include/linux/regulator/mt6380-regulator.h | 32 ++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 include/linux/regulator/mt6380-regulator.h (limited to 'include/linux') diff --git a/include/linux/regulator/mt6380-regulator.h b/include/linux/regulator/mt6380-regulator.h new file mode 100644 index 000000000000..465182da6315 --- /dev/null +++ b/include/linux/regulator/mt6380-regulator.h @@ -0,0 +1,32 @@ +/* + * Copyright (c) 2017 MediaTek Inc. + * Author: Chenglin Xu + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_REGULATOR_mt6380_H +#define __LINUX_REGULATOR_mt6380_H + +enum { + MT6380_ID_VCPU = 0, + MT6380_ID_VCORE, + MT6380_ID_VRF, + MT6380_ID_VMLDO, + MT6380_ID_VALDO, + MT6380_ID_VPHYLDO, + MT6380_ID_VDDRLDO, + MT6380_ID_VTLDO, + MT6380_ID_RG_MAX, +}; + +#define MT6380_MAX_REGULATOR MT6380_ID_RG_MAX + +#endif /* __LINUX_REGULATOR_mt6380_H */ -- cgit v1.2.3 From 2926a2aa5c14fb2add75e6584845b1c03022235f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 14 Aug 2017 17:19:26 +0200 Subject: iommu: Fix wrong freeing of iommu_device->dev The struct iommu_device has a 'struct device' embedded into it, not as a pointer, but the whole struct. In the conversion of the iommu drivers to use struct iommu_device it was forgotten that the relase function for that struct device simply calls kfree() on the pointer. This frees memory that was never allocated and causes memory corruption. To fix this issue, use a pointer to struct device instead of embedding the whole struct. This needs some updates in the iommu sysfs code as well as the Intel VT-d and AMD IOMMU driver. Reported-by: Sebastian Ott Fixes: 39ab9555c241 ('iommu: Add sysfs bindings for struct iommu_device') Cc: stable@vger.kernel.org # >= v4.11 Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2cb54adc4a33..176f7569d874 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -240,7 +240,7 @@ struct iommu_device { struct list_head list; const struct iommu_ops *ops; struct fwnode_handle *fwnode; - struct device dev; + struct device *dev; }; int iommu_device_register(struct iommu_device *iommu); @@ -265,6 +265,11 @@ static inline void iommu_device_set_fwnode(struct iommu_device *iommu, iommu->fwnode = fwnode; } +static inline struct iommu_device *dev_to_iommu_device(struct device *dev) +{ + return (struct iommu_device *)dev_get_drvdata(dev); +} + #define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ #define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ #define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ @@ -589,6 +594,11 @@ static inline void iommu_device_set_fwnode(struct iommu_device *iommu, { } +static inline struct iommu_device *dev_to_iommu_device(struct device *dev) +{ + return NULL; +} + static inline void iommu_device_unregister(struct iommu_device *iommu) { } -- cgit v1.2.3 From 129f6c4820dd68be26b516ba6d6e471e63855d47 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 21 Jul 2017 22:26:25 +0200 Subject: mtd: only use __xipram annotation when XIP_KERNEL is set When XIP_KERNEL is enabled, some functions are defined in the .data ELF section because we require them to be in RAM whenever we communicate with the flash chip. However this causes problems when FTRACE is enabled and gcc emits calls to __gnu_mcount_nc in the function prolog: drivers/built-in.o: In function `cfi_chip_setup': :(.data+0x272fc): relocation truncated to fit: R_ARM_CALL against symbol `__gnu_mcount_nc' defined in .text section in arch/arm/kernel/built-in.o drivers/built-in.o: In function `cfi_probe_chip': :(.data+0x27de8): relocation truncated to fit: R_ARM_CALL against symbol `__gnu_mcount_nc' defined in .text section in arch/arm/kernel/built-in.o /tmp/ccY172rP.s: Assembler messages: /tmp/ccY172rP.s:70: Warning: ignoring changed section attributes for .data /tmp/ccY172rP.s: Error: 1 warning, treating warnings as errors make[5]: *** [drivers/mtd/chips/cfi_probe.o] Error 1 /tmp/ccK4rjeO.s: Assembler messages: /tmp/ccK4rjeO.s:421: Warning: ignoring changed section attributes for .data /tmp/ccK4rjeO.s: Error: 1 warning, treating warnings as errors make[5]: *** [drivers/mtd/chips/cfi_util.o] Error 1 /tmp/ccUvhCYR.s: Assembler messages: /tmp/ccUvhCYR.s:1895: Warning: ignoring changed section attributes for .data /tmp/ccUvhCYR.s: Error: 1 warning, treating warnings as errors Specifically, this does not work because the .data section is not marked executable, which leads LD to not generate trampolines for long calls. This moves the __xipram functions into their own .xiptext section instead. The section is still placed next to .data and located in RAM but is marked executable, which avoids the build errors. Also, we only need to place the XIP functions into a separate section if both CONFIG_XIP_KERNEL and CONFIG_MTD_XIP are set: When only MTD_XIP is used, the whole kernel is still in RAM and we do not need to worry about pulling out the rug under it. When only XIP_KERNEL but not MTD_XIP is set, the kernel is in some form of ROM, but we never write to it. Note that MTD_XIP has been broken on ARM since around 2011 or 2012. I have sent another patch[2] to fix compilation, which I plan to merge through arm-soc unless there are objections. The obvious alternative to that would be to completely rip out the MTD_XIP support from the kernel, since obviously nobody has been using it in a long while. Link: [1] https://patchwork.kernel.org/patch/8109771/ Link: [2] https://patchwork.kernel.org/patch/9855225/ Signed-off-by: Arnd Bergmann Signed-off-by: Boris Brezillon --- include/linux/mtd/xip.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/xip.h b/include/linux/mtd/xip.h index abed4dec5c2f..e373690cce0a 100644 --- a/include/linux/mtd/xip.h +++ b/include/linux/mtd/xip.h @@ -30,7 +30,9 @@ * obviously not be running from flash. The __xipram is therefore marking * those functions so they get relocated to ram. */ -#define __xipram noinline __attribute__ ((__section__ (".data"))) +#ifdef CONFIG_XIP_KERNEL +#define __xipram noinline __attribute__ ((__section__ (".xiptext"))) +#endif /* * Each architecture has to provide the following macros. They must access @@ -90,10 +92,10 @@ #define xip_cpu_idle() do { } while (0) #endif -#else +#endif /* CONFIG_MTD_XIP */ +#ifndef __xipram #define __xipram - -#endif /* CONFIG_MTD_XIP */ +#endif #endif /* __LINUX_MTD_XIP_H__ */ -- cgit v1.2.3 From a9081a008f84819ab2f3da596bf89afa16beea94 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Tue, 15 Aug 2017 19:07:54 +0800 Subject: usb: phy: Add USB charger support This patch introduces the usb charger support based on usb phy that makes an enhancement to a power driver. The basic conception of the usb charger is that, when one usb charger is added or removed by reporting from the extcon device state change, the usb charger will report to power user to set the current limitation. Power user can register a notifiee on the usb phy by issuing usb_register_notifier() to get notified by charger status changes or charger current changes. we can notify what current to be drawn to power user according to different charger type, and now we have 2 methods to get charger type. One is get charger type from extcon subsystem, which also means the charger state changes. Another is we can get the charger type from USB controller detecting or PMIC detecting, and the charger state changes should be told by issuing usb_phy_set_charger_state(). Signed-off-by: Baolin Wang Signed-off-by: Felipe Balbi --- include/linux/usb/phy.h | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index 299245105610..de881b171ba9 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -12,6 +12,7 @@ #include #include #include +#include enum usb_phy_interface { USBPHY_INTERFACE_MODE_UNKNOWN, @@ -72,6 +73,17 @@ struct usb_phy_io_ops { int (*write)(struct usb_phy *x, u32 val, u32 reg); }; +struct usb_charger_current { + unsigned int sdp_min; + unsigned int sdp_max; + unsigned int dcp_min; + unsigned int dcp_max; + unsigned int cdp_min; + unsigned int cdp_max; + unsigned int aca_min; + unsigned int aca_max; +}; + struct usb_phy { struct device *dev; const char *label; @@ -91,6 +103,13 @@ struct usb_phy { struct extcon_dev *id_edev; struct notifier_block vbus_nb; struct notifier_block id_nb; + struct notifier_block type_nb; + + /* Support USB charger */ + enum usb_charger_type chg_type; + enum usb_charger_state chg_state; + struct usb_charger_current chg_cur; + struct work_struct chg_work; /* for notification of usb_phy_events */ struct atomic_notifier_head notifier; @@ -129,6 +148,12 @@ struct usb_phy { enum usb_device_speed speed); int (*notify_disconnect)(struct usb_phy *x, enum usb_device_speed speed); + + /* + * Charger detection method can be implemented if you need to + * manually detect the charger type. + */ + enum usb_charger_type (*charger_detect)(struct usb_phy *x); }; /** @@ -219,6 +244,12 @@ extern void devm_usb_put_phy(struct device *dev, struct usb_phy *x); extern int usb_bind_phy(const char *dev_name, u8 index, const char *phy_dev_name); extern void usb_phy_set_event(struct usb_phy *x, unsigned long event); +extern void usb_phy_set_charger_current(struct usb_phy *usb_phy, + unsigned int mA); +extern void usb_phy_get_charger_current(struct usb_phy *usb_phy, + unsigned int *min, unsigned int *max); +extern void usb_phy_set_charger_state(struct usb_phy *usb_phy, + enum usb_charger_state state); #else static inline struct usb_phy *usb_get_phy(enum usb_phy_type type) { @@ -270,11 +301,29 @@ static inline int usb_bind_phy(const char *dev_name, u8 index, static inline void usb_phy_set_event(struct usb_phy *x, unsigned long event) { } + +static inline void usb_phy_set_charger_current(struct usb_phy *usb_phy, + unsigned int mA) +{ +} + +static inline void usb_phy_get_charger_current(struct usb_phy *usb_phy, + unsigned int *min, + unsigned int *max) +{ +} + +static inline void usb_phy_set_charger_state(struct usb_phy *usb_phy, + enum usb_charger_state state) +{ +} #endif static inline int usb_phy_set_power(struct usb_phy *x, unsigned mA) { + usb_phy_set_charger_current(x, mA); + if (x && x->set_power) return x->set_power(x, mA); return 0; -- cgit v1.2.3 From e24a1307ba1f99fc62a0bd61d5e87fcfb6d5503d Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 28 Jul 2017 10:31:25 +0530 Subject: mm/hugetlb: Allow arch to override and call the weak function When running in guest mode ppc64 supports a different mechanism for hugetlb allocation/reservation. The LPAR management application called HMC can be used to reserve a set of hugepages and we pass the details of reserved pages via device tree to the guest. (more details in htab_dt_scan_hugepage_blocks()) . We do the memblock_reserve of the range and later in the boot sequence, we add the reserved range to huge_boot_pages. But to enable 16G hugetlb on baremetal config (when we are not running as guest) we want to do memblock reservation during boot. Generic code already does this Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- include/linux/hugetlb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 0ed8e41aaf11..8bbbd37ab105 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -358,6 +358,7 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); /* arch callback */ +int __init __alloc_bootmem_huge_page(struct hstate *h); int __init alloc_bootmem_huge_page(struct hstate *h); void __init hugetlb_bad_size(void); -- cgit v1.2.3 From dee83046e73cb7ebbbae955c1ef0f4f55a0f44f9 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 17 Jul 2017 10:51:02 -0400 Subject: NFS: Remove unuse function nfs_page_group_lock_wait() Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index d67b67ae6c8b..de1d24cedaa2 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -140,7 +140,6 @@ extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_and_release_request(struct nfs_page *); extern int nfs_page_group_lock(struct nfs_page *, bool); -extern void nfs_page_group_lock_wait(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *); -- cgit v1.2.3 From 1344b7ea172b4911a8ee8a6ff26c5bc6b5abb302 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 17 Jul 2017 10:54:14 -0400 Subject: NFS: Remove unused parameter from nfs_page_group_lock() nfs_page_group_lock() is now always called with the 'nonblock' parameter set to 'false'. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index de1d24cedaa2..2f4fdafb6746 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -139,7 +139,7 @@ extern size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_and_release_request(struct nfs_page *); -extern int nfs_page_group_lock(struct nfs_page *, bool); +extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *); -- cgit v1.2.3 From e824f99adaaf1ed0e03eac8574599af6d992163d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 1 Aug 2017 11:53:49 -0400 Subject: NFSv4: Use a mutex to protect the per-inode commit lists The commit lists can get very large, so using the inode->i_lock can end up affecting general metadata performance. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 5cc91d6381a3..121a702888b4 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -163,6 +163,7 @@ struct nfs_inode { /* Readers: in-flight sillydelete RPC calls */ /* Writers: rmdir */ struct rw_semaphore rmdir_sem; + struct mutex commit_mutex; #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; -- cgit v1.2.3 From a6b6d5b85abf4914bbceade5dddd54c345c64136 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 1 Aug 2017 15:39:46 -0400 Subject: NFS: Use an atomic_long_t to count the number of requests Rather than forcing us to take the inode->i_lock just in order to bump the number. Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 121a702888b4..238fdc4c46df 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -154,7 +154,7 @@ struct nfs_inode { */ __be32 cookieverf[2]; - unsigned long nrequests; + atomic_long_t nrequests; struct nfs_mds_commit_info commit_info; /* Open contexts for shared mmap writes */ @@ -511,7 +511,7 @@ extern void nfs_commit_free(struct nfs_commit_data *data); static inline int nfs_have_writebacks(struct inode *inode) { - return NFS_I(inode)->nrequests != 0; + return atomic_long_read(&NFS_I(inode)->nrequests) != 0; } /* -- cgit v1.2.3 From 5cb953d4b1e70a09084f71594c45d47458346bc2 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 1 Aug 2017 17:04:12 -0400 Subject: NFS: Use an atomic_long_t to count the number of commits Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 62cbcb842f99..164d5359d4ab 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1476,7 +1476,7 @@ struct nfs_pgio_header { struct nfs_mds_commit_info { atomic_t rpcs_out; - unsigned long ncommit; + atomic_long_t ncommit; struct list_head list; }; -- cgit v1.2.3 From 5d2405227a9eaea48e8cc95756a06d407b11f141 Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Fri, 4 Aug 2017 13:19:17 -0700 Subject: lib: Add xxhash module Adds xxhash kernel module with xxh32 and xxh64 hashes. xxhash is an extremely fast non-cryptographic hash algorithm for checksumming. The zstd compression and decompression modules added in the next patch require xxhash. I extracted it out from zstd since it is useful on its own. I copied the code from the upstream XXHash source repository and translated it into kernel style. I ran benchmarks and tests in the kernel and tests in userland. I benchmarked xxhash as a special character device. I ran in four modes, no-op, xxh32, xxh64, and crc32. The no-op mode simply copies the data to kernel space and ignores it. The xxh32, xxh64, and crc32 modes compute hashes on the copied data. I also ran it with four different buffer sizes. The benchmark file is located in the upstream zstd source repository under `contrib/linux-kernel/xxhash_test.c` [1]. I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM. The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor, 16 GB of RAM, and a SSD. I benchmarked using the file `filesystem.squashfs` from `ubuntu-16.10-desktop-amd64.iso`, which is 1,536,217,088 B large. Run the following commands for the benchmark: modprobe xxhash_test mknod xxhash_test c 245 0 time cp filesystem.squashfs xxhash_test The time is reported by the time of the userland `cp`. The GB/s is computed with 1,536,217,008 B / time(buffer size, hash) which includes the time to copy from userland. The Normalized GB/s is computed with 1,536,217,088 B / (time(buffer size, hash) - time(buffer size, none)). | Buffer Size (B) | Hash | Time (s) | GB/s | Adjusted GB/s | |-----------------|-------|----------|------|---------------| | 1024 | none | 0.408 | 3.77 | - | | 1024 | xxh32 | 0.649 | 2.37 | 6.37 | | 1024 | xxh64 | 0.542 | 2.83 | 11.46 | | 1024 | crc32 | 1.290 | 1.19 | 1.74 | | 4096 | none | 0.380 | 4.04 | - | | 4096 | xxh32 | 0.645 | 2.38 | 5.79 | | 4096 | xxh64 | 0.500 | 3.07 | 12.80 | | 4096 | crc32 | 1.168 | 1.32 | 1.95 | | 8192 | none | 0.351 | 4.38 | - | | 8192 | xxh32 | 0.614 | 2.50 | 5.84 | | 8192 | xxh64 | 0.464 | 3.31 | 13.60 | | 8192 | crc32 | 1.163 | 1.32 | 1.89 | | 16384 | none | 0.346 | 4.43 | - | | 16384 | xxh32 | 0.590 | 2.60 | 6.30 | | 16384 | xxh64 | 0.466 | 3.30 | 12.80 | | 16384 | crc32 | 1.183 | 1.30 | 1.84 | Tested in userland using the test-suite in the zstd repo under `contrib/linux-kernel/test/XXHashUserlandTest.cpp` [2] by mocking the kernel functions. A line in each branch of every function in `xxhash.c` was commented out to ensure that the test-suite fails. Additionally tested while testing zstd and with SMHasher [3]. [1] https://phabricator.intern.facebook.com/P57526246 [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/XXHashUserlandTest.cpp [3] https://github.com/aappleby/smhasher zstd source repository: https://github.com/facebook/zstd XXHash source repository: https://github.com/cyan4973/xxhash Signed-off-by: Nick Terrell Signed-off-by: Chris Mason --- include/linux/xxhash.h | 236 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 236 insertions(+) create mode 100644 include/linux/xxhash.h (limited to 'include/linux') diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h new file mode 100644 index 000000000000..9e1f42cb57e9 --- /dev/null +++ b/include/linux/xxhash.h @@ -0,0 +1,236 @@ +/* + * xxHash - Extremely Fast Hash algorithm + * Copyright (C) 2012-2016, Yann Collet. + * + * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are + * met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following disclaimer + * in the documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. This program is dual-licensed; you may select + * either version 2 of the GNU General Public License ("GPL") or BSD license + * ("BSD"). + * + * You can contact the author at: + * - xxHash homepage: http://cyan4973.github.io/xxHash/ + * - xxHash source repository: https://github.com/Cyan4973/xxHash + */ + +/* + * Notice extracted from xxHash homepage: + * + * xxHash is an extremely fast Hash algorithm, running at RAM speed limits. + * It also successfully passes all tests from the SMHasher suite. + * + * Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2 + * Duo @3GHz) + * + * Name Speed Q.Score Author + * xxHash 5.4 GB/s 10 + * CrapWow 3.2 GB/s 2 Andrew + * MumurHash 3a 2.7 GB/s 10 Austin Appleby + * SpookyHash 2.0 GB/s 10 Bob Jenkins + * SBox 1.4 GB/s 9 Bret Mulvey + * Lookup3 1.2 GB/s 9 Bob Jenkins + * SuperFastHash 1.2 GB/s 1 Paul Hsieh + * CityHash64 1.05 GB/s 10 Pike & Alakuijala + * FNV 0.55 GB/s 5 Fowler, Noll, Vo + * CRC32 0.43 GB/s 9 + * MD5-32 0.33 GB/s 10 Ronald L. Rivest + * SHA1-32 0.28 GB/s 10 + * + * Q.Score is a measure of quality of the hash function. + * It depends on successfully passing SMHasher test set. + * 10 is a perfect score. + * + * A 64-bits version, named xxh64 offers much better speed, + * but for 64-bits applications only. + * Name Speed on 64 bits Speed on 32 bits + * xxh64 13.8 GB/s 1.9 GB/s + * xxh32 6.8 GB/s 6.0 GB/s + */ + +#ifndef XXHASH_H +#define XXHASH_H + +#include + +/*-**************************** + * Simple Hash Functions + *****************************/ + +/** + * xxh32() - calculate the 32-bit hash of the input with a given seed. + * + * @input: The data to hash. + * @length: The length of the data to hash. + * @seed: The seed can be used to alter the result predictably. + * + * Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s + * + * Return: The 32-bit hash of the data. + */ +uint32_t xxh32(const void *input, size_t length, uint32_t seed); + +/** + * xxh64() - calculate the 64-bit hash of the input with a given seed. + * + * @input: The data to hash. + * @length: The length of the data to hash. + * @seed: The seed can be used to alter the result predictably. + * + * This function runs 2x faster on 64-bit systems, but slower on 32-bit systems. + * + * Return: The 64-bit hash of the data. + */ +uint64_t xxh64(const void *input, size_t length, uint64_t seed); + +/*-**************************** + * Streaming Hash Functions + *****************************/ + +/* + * These definitions are only meant to allow allocation of XXH state + * statically, on stack, or in a struct for example. + * Do not use members directly. + */ + +/** + * struct xxh32_state - private xxh32 state, do not use members directly + */ +struct xxh32_state { + uint32_t total_len_32; + uint32_t large_len; + uint32_t v1; + uint32_t v2; + uint32_t v3; + uint32_t v4; + uint32_t mem32[4]; + uint32_t memsize; +}; + +/** + * struct xxh32_state - private xxh64 state, do not use members directly + */ +struct xxh64_state { + uint64_t total_len; + uint64_t v1; + uint64_t v2; + uint64_t v3; + uint64_t v4; + uint64_t mem64[4]; + uint32_t memsize; +}; + +/** + * xxh32_reset() - reset the xxh32 state to start a new hashing operation + * + * @state: The xxh32 state to reset. + * @seed: Initialize the hash state with this seed. + * + * Call this function on any xxh32_state to prepare for a new hashing operation. + */ +void xxh32_reset(struct xxh32_state *state, uint32_t seed); + +/** + * xxh32_update() - hash the data given and update the xxh32 state + * + * @state: The xxh32 state to update. + * @input: The data to hash. + * @length: The length of the data to hash. + * + * After calling xxh32_reset() call xxh32_update() as many times as necessary. + * + * Return: Zero on success, otherwise an error code. + */ +int xxh32_update(struct xxh32_state *state, const void *input, size_t length); + +/** + * xxh32_digest() - produce the current xxh32 hash + * + * @state: Produce the current xxh32 hash of this state. + * + * A hash value can be produced at any time. It is still possible to continue + * inserting input into the hash state after a call to xxh32_digest(), and + * generate new hashes later on, by calling xxh32_digest() again. + * + * Return: The xxh32 hash stored in the state. + */ +uint32_t xxh32_digest(const struct xxh32_state *state); + +/** + * xxh64_reset() - reset the xxh64 state to start a new hashing operation + * + * @state: The xxh64 state to reset. + * @seed: Initialize the hash state with this seed. + */ +void xxh64_reset(struct xxh64_state *state, uint64_t seed); + +/** + * xxh64_update() - hash the data given and update the xxh64 state + * @state: The xxh64 state to update. + * @input: The data to hash. + * @length: The length of the data to hash. + * + * After calling xxh64_reset() call xxh64_update() as many times as necessary. + * + * Return: Zero on success, otherwise an error code. + */ +int xxh64_update(struct xxh64_state *state, const void *input, size_t length); + +/** + * xxh64_digest() - produce the current xxh64 hash + * + * @state: Produce the current xxh64 hash of this state. + * + * A hash value can be produced at any time. It is still possible to continue + * inserting input into the hash state after a call to xxh64_digest(), and + * generate new hashes later on, by calling xxh64_digest() again. + * + * Return: The xxh64 hash stored in the state. + */ +uint64_t xxh64_digest(const struct xxh64_state *state); + +/*-************************** + * Utils + ***************************/ + +/** + * xxh32_copy_state() - copy the source state into the destination state + * + * @src: The source xxh32 state. + * @dst: The destination xxh32 state. + */ +void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src); + +/** + * xxh64_copy_state() - copy the source state into the destination state + * + * @src: The source xxh64 state. + * @dst: The destination xxh64 state. + */ +void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src); + +#endif /* XXHASH_H */ -- cgit v1.2.3 From 73f3d1b48f5069d46ba48aa28c2898dc93185560 Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Wed, 9 Aug 2017 19:35:53 -0700 Subject: lib: Add zstd modules Add zstd compression and decompression kernel modules. zstd offers a wide varity of compression speed and quality trade-offs. It can compress at speeds approaching lz4, and quality approaching lzma. zstd decompressions at speeds more than twice as fast as zlib, and decompression speed remains roughly the same across all compression levels. The code was ported from the upstream zstd source repository. The `linux/zstd.h` header was modified to match linux kernel style. The cross-platform and allocation code was stripped out. Instead zstd requires the caller to pass a preallocated workspace. The source files were clang-formatted [1] to match the Linux Kernel style as much as possible. Otherwise, the code was unmodified. We would like to avoid as much further manual modification to the source code as possible, so it will be easier to keep the kernel zstd up to date. I benchmarked zstd compression as a special character device. I ran zstd and zlib compression at several levels, as well as performing no compression, which measure the time spent copying the data to kernel space. Data is passed to the compresser 4096 B at a time. The benchmark file is located in the upstream zstd source repository under `contrib/linux-kernel/zstd_compress_test.c` [2]. I ran the benchmarks on a Ubuntu 14.04 VM with 2 cores and 4 GiB of RAM. The VM is running on a MacBook Pro with a 3.1 GHz Intel Core i7 processor, 16 GB of RAM, and a SSD. I benchmarked using `silesia.tar` [3], which is 211,988,480 B large. Run the following commands for the benchmark: sudo modprobe zstd_compress_test sudo mknod zstd_compress_test c 245 0 sudo cp silesia.tar zstd_compress_test The time is reported by the time of the userland `cp`. The MB/s is computed with 1,536,217,008 B / time(buffer size, hash) which includes the time to copy from userland. The Adjusted MB/s is computed with 1,536,217,088 B / (time(buffer size, hash) - time(buffer size, none)). The memory reported is the amount of memory the compressor requests. | Method | Size (B) | Time (s) | Ratio | MB/s | Adj MB/s | Mem (MB) | |----------|----------|----------|-------|---------|----------|----------| | none | 11988480 | 0.100 | 1 | 2119.88 | - | - | | zstd -1 | 73645762 | 1.044 | 2.878 | 203.05 | 224.56 | 1.23 | | zstd -3 | 66988878 | 1.761 | 3.165 | 120.38 | 127.63 | 2.47 | | zstd -5 | 65001259 | 2.563 | 3.261 | 82.71 | 86.07 | 2.86 | | zstd -10 | 60165346 | 13.242 | 3.523 | 16.01 | 16.13 | 13.22 | | zstd -15 | 58009756 | 47.601 | 3.654 | 4.45 | 4.46 | 21.61 | | zstd -19 | 54014593 | 102.835 | 3.925 | 2.06 | 2.06 | 60.15 | | zlib -1 | 77260026 | 2.895 | 2.744 | 73.23 | 75.85 | 0.27 | | zlib -3 | 72972206 | 4.116 | 2.905 | 51.50 | 52.79 | 0.27 | | zlib -6 | 68190360 | 9.633 | 3.109 | 22.01 | 22.24 | 0.27 | | zlib -9 | 67613382 | 22.554 | 3.135 | 9.40 | 9.44 | 0.27 | I benchmarked zstd decompression using the same method on the same machine. The benchmark file is located in the upstream zstd repo under `contrib/linux-kernel/zstd_decompress_test.c` [4]. The memory reported is the amount of memory required to decompress data compressed with the given compression level. If you know the maximum size of your input, you can reduce the memory usage of decompression irrespective of the compression level. | Method | Time (s) | MB/s | Adjusted MB/s | Memory (MB) | |----------|----------|---------|---------------|-------------| | none | 0.025 | 8479.54 | - | - | | zstd -1 | 0.358 | 592.15 | 636.60 | 0.84 | | zstd -3 | 0.396 | 535.32 | 571.40 | 1.46 | | zstd -5 | 0.396 | 535.32 | 571.40 | 1.46 | | zstd -10 | 0.374 | 566.81 | 607.42 | 2.51 | | zstd -15 | 0.379 | 559.34 | 598.84 | 4.61 | | zstd -19 | 0.412 | 514.54 | 547.77 | 8.80 | | zlib -1 | 0.940 | 225.52 | 231.68 | 0.04 | | zlib -3 | 0.883 | 240.08 | 247.07 | 0.04 | | zlib -6 | 0.844 | 251.17 | 258.84 | 0.04 | | zlib -9 | 0.837 | 253.27 | 287.64 | 0.04 | Tested in userland using the test-suite in the zstd repo under `contrib/linux-kernel/test/UserlandTest.cpp` [5] by mocking the kernel functions. Fuzz tested using libfuzzer [6] with the fuzz harnesses under `contrib/linux-kernel/test/{RoundTripCrash.c,DecompressCrash.c}` [7] [8] with ASAN, UBSAN, and MSAN. Additionaly, it was tested while testing the BtrFS and SquashFS patches coming next. [1] https://clang.llvm.org/docs/ClangFormat.html [2] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/zstd_compress_test.c [3] http://sun.aei.polsl.pl/~sdeor/index.php?page=silesia [4] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/zstd_decompress_test.c [5] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/UserlandTest.cpp [6] http://llvm.org/docs/LibFuzzer.html [7] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/RoundTripCrash.c [8] https://github.com/facebook/zstd/blob/dev/contrib/linux-kernel/test/DecompressCrash.c zstd source repository: https://github.com/facebook/zstd Signed-off-by: Nick Terrell Signed-off-by: Chris Mason --- include/linux/zstd.h | 1157 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1157 insertions(+) create mode 100644 include/linux/zstd.h (limited to 'include/linux') diff --git a/include/linux/zstd.h b/include/linux/zstd.h new file mode 100644 index 000000000000..249575e2485f --- /dev/null +++ b/include/linux/zstd.h @@ -0,0 +1,1157 @@ +/* + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of https://github.com/facebook/zstd. + * An additional grant of patent rights can be found in the PATENTS file in the + * same directory. + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. This program is dual-licensed; you may select + * either version 2 of the GNU General Public License ("GPL") or BSD license + * ("BSD"). + */ + +#ifndef ZSTD_H +#define ZSTD_H + +/* ====== Dependency ======*/ +#include /* size_t */ + + +/*-***************************************************************************** + * Introduction + * + * zstd, short for Zstandard, is a fast lossless compression algorithm, + * targeting real-time compression scenarios at zlib-level and better + * compression ratios. The zstd compression library provides in-memory + * compression and decompression functions. The library supports compression + * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled + * ultra, should be used with caution, as they require more memory. + * Compression can be done in: + * - a single step, reusing a context (described as Explicit memory management) + * - unbounded multiple steps (described as Streaming compression) + * The compression ratio achievable on small data can be highly improved using + * compression with a dictionary in: + * - a single step (described as Simple dictionary API) + * - a single step, reusing a dictionary (described as Fast dictionary API) + ******************************************************************************/ + +/*====== Helper functions ======*/ + +/** + * enum ZSTD_ErrorCode - zstd error codes + * + * Functions that return size_t can be checked for errors using ZSTD_isError() + * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode(). + */ +typedef enum { + ZSTD_error_no_error, + ZSTD_error_GENERIC, + ZSTD_error_prefix_unknown, + ZSTD_error_version_unsupported, + ZSTD_error_parameter_unknown, + ZSTD_error_frameParameter_unsupported, + ZSTD_error_frameParameter_unsupportedBy32bits, + ZSTD_error_frameParameter_windowTooLarge, + ZSTD_error_compressionParameter_unsupported, + ZSTD_error_init_missing, + ZSTD_error_memory_allocation, + ZSTD_error_stage_wrong, + ZSTD_error_dstSize_tooSmall, + ZSTD_error_srcSize_wrong, + ZSTD_error_corruption_detected, + ZSTD_error_checksum_wrong, + ZSTD_error_tableLog_tooLarge, + ZSTD_error_maxSymbolValue_tooLarge, + ZSTD_error_maxSymbolValue_tooSmall, + ZSTD_error_dictionary_corrupted, + ZSTD_error_dictionary_wrong, + ZSTD_error_dictionaryCreation_failed, + ZSTD_error_maxCode +} ZSTD_ErrorCode; + +/** + * ZSTD_maxCLevel() - maximum compression level available + * + * Return: Maximum compression level available. + */ +int ZSTD_maxCLevel(void); +/** + * ZSTD_compressBound() - maximum compressed size in worst case scenario + * @srcSize: The size of the data to compress. + * + * Return: The maximum compressed size in the worst case scenario. + */ +size_t ZSTD_compressBound(size_t srcSize); +/** + * ZSTD_isError() - tells if a size_t function result is an error code + * @code: The function result to check for error. + * + * Return: Non-zero iff the code is an error. + */ +static __attribute__((unused)) unsigned int ZSTD_isError(size_t code) +{ + return code > (size_t)-ZSTD_error_maxCode; +} +/** + * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode + * @functionResult: The result of a function for which ZSTD_isError() is true. + * + * Return: The ZSTD_ErrorCode corresponding to the functionResult or 0 + * if the functionResult isn't an error. + */ +static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode( + size_t functionResult) +{ + if (!ZSTD_isError(functionResult)) + return (ZSTD_ErrorCode)0; + return (ZSTD_ErrorCode)(0 - functionResult); +} + +/** + * enum ZSTD_strategy - zstd compression search strategy + * + * From faster to stronger. + */ +typedef enum { + ZSTD_fast, + ZSTD_dfast, + ZSTD_greedy, + ZSTD_lazy, + ZSTD_lazy2, + ZSTD_btlazy2, + ZSTD_btopt, + ZSTD_btopt2 +} ZSTD_strategy; + +/** + * struct ZSTD_compressionParameters - zstd compression parameters + * @windowLog: Log of the largest match distance. Larger means more + * compression, and more memory needed during decompression. + * @chainLog: Fully searched segment. Larger means more compression, slower, + * and more memory (useless for fast). + * @hashLog: Dispatch table. Larger means more compression, + * slower, and more memory. + * @searchLog: Number of searches. Larger means more compression and slower. + * @searchLength: Match length searched. Larger means faster decompression, + * sometimes less compression. + * @targetLength: Acceptable match size for optimal parser (only). Larger means + * more compression, and slower. + * @strategy: The zstd compression strategy. + */ +typedef struct { + unsigned int windowLog; + unsigned int chainLog; + unsigned int hashLog; + unsigned int searchLog; + unsigned int searchLength; + unsigned int targetLength; + ZSTD_strategy strategy; +} ZSTD_compressionParameters; + +/** + * struct ZSTD_frameParameters - zstd frame parameters + * @contentSizeFlag: Controls whether content size will be present in the frame + * header (when known). + * @checksumFlag: Controls whether a 32-bit checksum is generated at the end + * of the frame for error detection. + * @noDictIDFlag: Controls whether dictID will be saved into the frame header + * when using dictionary compression. + * + * The default value is all fields set to 0. + */ +typedef struct { + unsigned int contentSizeFlag; + unsigned int checksumFlag; + unsigned int noDictIDFlag; +} ZSTD_frameParameters; + +/** + * struct ZSTD_parameters - zstd parameters + * @cParams: The compression parameters. + * @fParams: The frame parameters. + */ +typedef struct { + ZSTD_compressionParameters cParams; + ZSTD_frameParameters fParams; +} ZSTD_parameters; + +/** + * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level + * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). + * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. + * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * + * Return: The selected ZSTD_compressionParameters. + */ +ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, + unsigned long long estimatedSrcSize, size_t dictSize); + +/** + * ZSTD_getParams() - returns ZSTD_parameters for selected level + * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). + * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. + * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * + * The same as ZSTD_getCParams() except also selects the default frame + * parameters (all zero). + * + * Return: The selected ZSTD_parameters. + */ +ZSTD_parameters ZSTD_getParams(int compressionLevel, + unsigned long long estimatedSrcSize, size_t dictSize); + +/*-************************************* + * Explicit memory management + **************************************/ + +/** + * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx + * @cParams: The compression parameters to be used for compression. + * + * If multiple compression parameters might be used, the caller must call + * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum + * size. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCCtx(). + */ +size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CCtx - the zstd compression context + * + * When compressing many times it is recommended to allocate a context just once + * and reuse it for each successive compression operation. + */ +typedef struct ZSTD_CCtx_s ZSTD_CCtx; +/** + * ZSTD_initCCtx() - initialize a zstd compression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to + * determine how large the workspace must be. + * + * Return: A compression context emplaced into workspace. + */ +ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize); + +/** + * ZSTD_compressCCtx() - compress src into dst + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, ZSTD_parameters params); + +/** + * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDCtx(). + */ +size_t ZSTD_DCtxWorkspaceBound(void); + +/** + * struct ZSTD_DCtx - the zstd decompression context + * + * When decompressing many times it is recommended to allocate a context just + * once and reuse it for each successive decompression operation. + */ +typedef struct ZSTD_DCtx_s ZSTD_DCtx; +/** + * ZSTD_initDCtx() - initialize a zstd decompression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to + * determine how large the workspace must be. + * + * Return: A decompression context emplaced into workspace. + */ +ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize); + +/** + * ZSTD_decompressDCtx() - decompress zstd compressed src into dst + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); + +/*-************************ + * Simple dictionary API + **************************/ + +/** + * ZSTD_compress_usingDict() - compress src into dst using a dictionary + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @dict: The dictionary to use for compression. + * @dictSize: The size of the dictionary. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Compression using a predefined dictionary. The same dictionary must be used + * during decompression. + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const void *dict, size_t dictSize, + ZSTD_parameters params); + +/** + * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * @dict: The dictionary to use for decompression. The same dictionary + * must've been used to compress the data. + * @dictSize: The size of the dictionary. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const void *dict, size_t dictSize); + +/*-************************** + * Fast dictionary API + ***************************/ + +/** + * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict + * @cParams: The compression parameters to be used for compression. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCDict(). + */ +size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CDict - a digested dictionary to be used for compression + */ +typedef struct ZSTD_CDict_s ZSTD_CDict; + +/** + * ZSTD_initCDict() - initialize a digested dictionary for compression + * @dictBuffer: The dictionary to digest. The buffer is referenced by the + * ZSTD_CDict so it must outlive the returned ZSTD_CDict. + * @dictSize: The size of the dictionary. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * @workspace: The workspace. It must outlive the returned ZSTD_CDict. + * @workspaceSize: The workspace size. Must be at least + * ZSTD_CDictWorkspaceBound(params.cParams). + * + * When compressing multiple messages / blocks with the same dictionary it is + * recommended to load it just once. The ZSTD_CDict merely references the + * dictBuffer, so it must outlive the returned ZSTD_CDict. + * + * Return: The digested dictionary emplaced into workspace. + */ +ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize, + ZSTD_parameters params, void *workspace, size_t workspaceSize); + +/** + * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(cParams) where + * cParams are the compression parameters used to initialize the + * cdict. + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @cdict: The digested dictionary to use for compression. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Compression using a digested dictionary. The same dictionary must be used + * during decompression. + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const ZSTD_CDict *cdict); + + +/** + * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDDict(). + */ +size_t ZSTD_DDictWorkspaceBound(void); + +/** + * struct ZSTD_DDict - a digested dictionary to be used for decompression + */ +typedef struct ZSTD_DDict_s ZSTD_DDict; + +/** + * ZSTD_initDDict() - initialize a digested dictionary for decompression + * @dictBuffer: The dictionary to digest. The buffer is referenced by the + * ZSTD_DDict so it must outlive the returned ZSTD_DDict. + * @dictSize: The size of the dictionary. + * @workspace: The workspace. It must outlive the returned ZSTD_DDict. + * @workspaceSize: The workspace size. Must be at least + * ZSTD_DDictWorkspaceBound(). + * + * When decompressing multiple messages / blocks with the same dictionary it is + * recommended to load it just once. The ZSTD_DDict merely references the + * dictBuffer, so it must outlive the returned ZSTD_DDict. + * + * Return: The digested dictionary emplaced into workspace. + */ +ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize, + void *workspace, size_t workspaceSize); + +/** + * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * @ddict: The digested dictionary to use for decompression. The same + * dictionary must've been used to compress the data. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, + size_t dstCapacity, const void *src, size_t srcSize, + const ZSTD_DDict *ddict); + + +/*-************************** + * Streaming + ***************************/ + +/** + * struct ZSTD_inBuffer - input buffer for streaming + * @src: Start of the input buffer. + * @size: Size of the input buffer. + * @pos: Position where reading stopped. Will be updated. + * Necessarily 0 <= pos <= size. + */ +typedef struct ZSTD_inBuffer_s { + const void *src; + size_t size; + size_t pos; +} ZSTD_inBuffer; + +/** + * struct ZSTD_outBuffer - output buffer for streaming + * @dst: Start of the output buffer. + * @size: Size of the output buffer. + * @pos: Position where writing stopped. Will be updated. + * Necessarily 0 <= pos <= size. + */ +typedef struct ZSTD_outBuffer_s { + void *dst; + size_t size; + size_t pos; +} ZSTD_outBuffer; + + + +/*-***************************************************************************** + * Streaming compression - HowTo + * + * A ZSTD_CStream object is required to track streaming operation. + * Use ZSTD_initCStream() to initialize a ZSTD_CStream object. + * ZSTD_CStream objects can be reused multiple times on consecutive compression + * operations. It is recommended to re-use ZSTD_CStream in situations where many + * streaming operations will be achieved consecutively. Use one separate + * ZSTD_CStream per thread for parallel execution. + * + * Use ZSTD_compressStream() repetitively to consume input stream. + * The function will automatically update both `pos` fields. + * Note that it may not consume the entire input, in which case `pos < size`, + * and it's up to the caller to present again remaining data. + * It returns a hint for the preferred number of bytes to use as an input for + * the next function call. + * + * At any moment, it's possible to flush whatever data remains within internal + * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might + * still be some content left within the internal buffer if `output->size` is + * too small. It returns the number of bytes left in the internal buffer and + * must be called until it returns 0. + * + * ZSTD_endStream() instructs to finish a frame. It will perform a flush and + * write frame epilogue. The epilogue is required for decoders to consider a + * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush + * the full content if `output->size` is too small. In which case, call again + * ZSTD_endStream() to complete the flush. It returns the number of bytes left + * in the internal buffer and must be called until it returns 0. + ******************************************************************************/ + +/** + * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream + * @cParams: The compression parameters to be used for compression. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCStream() and ZSTD_initCStream_usingCDict(). + */ +size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CStream - the zstd streaming compression context + */ +typedef struct ZSTD_CStream_s ZSTD_CStream; + +/*===== ZSTD_CStream management functions =====*/ +/** + * ZSTD_initCStream() - initialize a zstd streaming compression context + * @params: The zstd compression parameters. + * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must + * pass the source size (zero means empty source). Otherwise, + * the caller may optionally pass the source size, or zero if + * unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine + * how large the workspace must be. + * + * Return: The zstd streaming compression context. + */ +ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, + unsigned long long pledgedSrcSize, void *workspace, + size_t workspaceSize); + +/** + * ZSTD_initCStream_usingCDict() - initialize a streaming compression context + * @cdict: The digested dictionary to use for compression. + * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Call ZSTD_CStreamWorkspaceBound() + * with the cParams used to initialize the cdict to determine + * how large the workspace must be. + * + * Return: The zstd streaming compression context. + */ +ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, + unsigned long long pledgedSrcSize, void *workspace, + size_t workspaceSize); + +/*===== Streaming compression functions =====*/ +/** + * ZSTD_resetCStream() - reset the context using parameters from creation + * @zcs: The zstd streaming compression context to reset. + * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * + * Resets the context using the parameters from creation. Skips dictionary + * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame + * content size is always written into the frame header. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize); +/** + * ZSTD_compressStream() - streaming compress some of input into output + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * @input: Source buffer. `input->pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input->pos < input->size`, and it's up to the caller to present + * remaining data again. + * + * The `input` and `output` buffers may be any size. Guaranteed to make some + * forward progress if `input` and `output` are not empty. + * + * Return: A hint for the number of bytes to use as the input for the next + * function call or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, + ZSTD_inBuffer *input); +/** + * ZSTD_flushStream() - flush internal buffers into output + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * + * ZSTD_flushStream() must be called until it returns 0, meaning all the data + * has been flushed. Since ZSTD_flushStream() causes a block to be ended, + * calling it too often will degrade the compression ratio. + * + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); +/** + * ZSTD_endStream() - flush internal buffers into output and end the frame + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * + * ZSTD_endStream() must be called until it returns 0, meaning all the data has + * been flushed and the frame epilogue has been written. + * + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); + +/** + * ZSTD_CStreamInSize() - recommended size for the input buffer + * + * Return: The recommended size for the input buffer. + */ +size_t ZSTD_CStreamInSize(void); +/** + * ZSTD_CStreamOutSize() - recommended size for the output buffer + * + * When the output buffer is at least this large, it is guaranteed to be large + * enough to flush at least one complete compressed block. + * + * Return: The recommended size for the output buffer. + */ +size_t ZSTD_CStreamOutSize(void); + + + +/*-***************************************************************************** + * Streaming decompression - HowTo + * + * A ZSTD_DStream object is required to track streaming operations. + * Use ZSTD_initDStream() to initialize a ZSTD_DStream object. + * ZSTD_DStream objects can be re-used multiple times. + * + * Use ZSTD_decompressStream() repetitively to consume your input. + * The function will update both `pos` fields. + * If `input->pos < input->size`, some input has not been consumed. + * It's up to the caller to present again remaining data. + * If `output->pos < output->size`, decoder has flushed everything it could. + * Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise it returns a suggested next input size that will never load more + * than the current frame. + ******************************************************************************/ + +/** + * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream + * @maxWindowSize: The maximum window size allowed for compressed frames. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDStream() and ZSTD_initDStream_usingDDict(). + */ +size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize); + +/** + * struct ZSTD_DStream - the zstd streaming decompression context + */ +typedef struct ZSTD_DStream_s ZSTD_DStream; +/*===== ZSTD_DStream management functions =====*/ +/** + * ZSTD_initDStream() - initialize a zstd streaming decompression context + * @maxWindowSize: The maximum window size allowed for compressed frames. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine + * how large the workspace must be. + * + * Return: The zstd streaming decompression context. + */ +ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, + size_t workspaceSize); +/** + * ZSTD_initDStream_usingDDict() - initialize streaming decompression context + * @maxWindowSize: The maximum window size allowed for compressed frames. + * @ddict: The digested dictionary to use for decompression. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine + * how large the workspace must be. + * + * Return: The zstd streaming decompression context. + */ +ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, + const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize); + +/*===== Streaming decompression functions =====*/ +/** + * ZSTD_resetDStream() - reset the context using parameters from creation + * @zds: The zstd streaming decompression context to reset. + * + * Resets the context using the parameters from creation. Skips dictionary + * loading, since it can be reused. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_resetDStream(ZSTD_DStream *zds); +/** + * ZSTD_decompressStream() - streaming decompress some of input into output + * @zds: The zstd streaming decompression context. + * @output: Destination buffer. `output.pos` is updated to indicate how much + * decompressed data was written. + * @input: Source buffer. `input.pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input.pos < input.size`, and it's up to the caller to present + * remaining data again. + * + * The `input` and `output` buffers may be any size. Guaranteed to make some + * forward progress if `input` and `output` are not empty. + * ZSTD_decompressStream() will not consume the last byte of the frame until + * the entire frame is flushed. + * + * Return: Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise returns a hint for the number of bytes to use as the input + * for the next function call or an error, which can be checked using + * ZSTD_isError(). The size hint will never load more than the frame. + */ +size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, + ZSTD_inBuffer *input); + +/** + * ZSTD_DStreamInSize() - recommended size for the input buffer + * + * Return: The recommended size for the input buffer. + */ +size_t ZSTD_DStreamInSize(void); +/** + * ZSTD_DStreamOutSize() - recommended size for the output buffer + * + * When the output buffer is at least this large, it is guaranteed to be large + * enough to flush at least one complete decompressed block. + * + * Return: The recommended size for the output buffer. + */ +size_t ZSTD_DStreamOutSize(void); + + +/* --- Constants ---*/ +#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ +#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U + +#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + +#define ZSTD_WINDOWLOG_MAX_32 27 +#define ZSTD_WINDOWLOG_MAX_64 27 +#define ZSTD_WINDOWLOG_MAX \ + ((unsigned int)(sizeof(size_t) == 4 \ + ? ZSTD_WINDOWLOG_MAX_32 \ + : ZSTD_WINDOWLOG_MAX_64)) +#define ZSTD_WINDOWLOG_MIN 10 +#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX +#define ZSTD_HASHLOG_MIN 6 +#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1) +#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN +#define ZSTD_HASHLOG3_MAX 17 +#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) +#define ZSTD_SEARCHLOG_MIN 1 +/* only for ZSTD_fast, other strategies are limited to 6 */ +#define ZSTD_SEARCHLENGTH_MAX 7 +/* only for ZSTD_btopt, other strategies are limited to 4 */ +#define ZSTD_SEARCHLENGTH_MIN 3 +#define ZSTD_TARGETLENGTH_MIN 4 +#define ZSTD_TARGETLENGTH_MAX 999 + +/* for static allocation */ +#define ZSTD_FRAMEHEADERSIZE_MAX 18 +#define ZSTD_FRAMEHEADERSIZE_MIN 6 +static const size_t ZSTD_frameHeaderSize_prefix = 5; +static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN; +static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX; +/* magic number + skippable frame length */ +static const size_t ZSTD_skippableHeaderSize = 8; + + +/*-************************************* + * Compressed size functions + **************************************/ + +/** + * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame + * @src: Source buffer. It should point to the start of a zstd encoded frame + * or a skippable frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * size of the frame. + * + * Return: The compressed size of the frame pointed to by `src` or an error, + * which can be check with ZSTD_isError(). + * Suitable to pass to ZSTD_decompress() or similar functions. + */ +size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize); + +/*-************************************* + * Decompressed size functions + **************************************/ +/** + * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header + * @src: It should point to the start of a zstd encoded frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * + * Return: The frame content size stored in the frame header if known. + * `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the + * frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input. + */ +unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); + +/** + * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames + * @src: It should point to the start of a series of zstd encoded and/or + * skippable frames. + * @srcSize: The exact size of the series of frames. + * + * If any zstd encoded frame in the series doesn't have the frame content size + * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always + * set when using ZSTD_compress(). The decompressed size can be very large. + * If the source is untrusted, the decompressed size could be wrong or + * intentionally modified. Always ensure the result fits within the + * application's authorized limits. ZSTD_findDecompressedSize() handles multiple + * frames, and so it must traverse the input to read each frame header. This is + * efficient as most of the data is skipped, however it does mean that all frame + * data must be present and valid. + * + * Return: Decompressed size of all the data contained in the frames if known. + * `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown. + * `ZSTD_CONTENTSIZE_ERROR` if an error occurred. + */ +unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize); + +/*-************************************* + * Advanced compression functions + **************************************/ +/** + * ZSTD_checkCParams() - ensure parameter values remain within authorized range + * @cParams: The zstd compression parameters. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams); + +/** + * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize + * @srcSize: Optionally the estimated source size, or zero if unknown. + * @dictSize: Optionally the estimated dictionary size, or zero if unknown. + * + * Return: The optimized parameters. + */ +ZSTD_compressionParameters ZSTD_adjustCParams( + ZSTD_compressionParameters cParams, unsigned long long srcSize, + size_t dictSize); + +/*--- Advanced decompression functions ---*/ + +/** + * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame + * @buffer: The source buffer to check. + * @size: The size of the source buffer, must be at least 4 bytes. + * + * Return: True iff the buffer starts with a zstd or skippable frame identifier. + */ +unsigned int ZSTD_isFrame(const void *buffer, size_t size); + +/** + * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary + * @dict: The dictionary buffer. + * @dictSize: The size of the dictionary buffer. + * + * Return: The dictionary id stored within the dictionary or 0 if the + * dictionary is not a zstd dictionary. If it returns 0 the + * dictionary can still be loaded as a content-only dictionary. + */ +unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize); + +/** + * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict + * @ddict: The ddict to find the id of. + * + * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not + * a zstd dictionary. If it returns 0 `ddict` will be loaded as a + * content-only dictionary. + */ +unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict); + +/** + * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame + * @src: Source buffer. It must be a zstd encoded frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * + * Return: The dictionary id required to decompress the frame stored within + * `src` or 0 if the dictionary id could not be decoded. It can return + * 0 if the frame does not require a dictionary, the dictionary id + * wasn't stored in the frame, `src` is not a zstd frame, or `srcSize` + * is too small. + */ +unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize); + +/** + * struct ZSTD_frameParams - zstd frame parameters stored in the frame header + * @frameContentSize: The frame content size, or 0 if not present. + * @windowSize: The window size, or 0 if the frame is a skippable frame. + * @dictID: The dictionary id, or 0 if not present. + * @checksumFlag: Whether a checksum was used. + */ +typedef struct { + unsigned long long frameContentSize; + unsigned int windowSize; + unsigned int dictID; + unsigned int checksumFlag; +} ZSTD_frameParams; + +/** + * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame + * @fparamsPtr: On success the frame parameters are written here. + * @src: The source buffer. It must point to a zstd or skippable frame. + * @srcSize: The size of the source buffer. `ZSTD_frameHeaderSize_max` is + * always large enough to succeed. + * + * Return: 0 on success. If more data is required it returns how many bytes + * must be provided to make forward progress. Otherwise it returns + * an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, + size_t srcSize); + +/*-***************************************************************************** + * Buffer-less and synchronous inner streaming functions + * + * This is an advanced API, giving full control over buffer management, for + * users which need direct control over memory. + * But it's also a complex one, with many restrictions (documented below). + * Prefer using normal streaming API for an easier experience + ******************************************************************************/ + +/*-***************************************************************************** + * Buffer-less streaming compression (synchronous mode) + * + * A ZSTD_CCtx object is required to track streaming operations. + * Use ZSTD_initCCtx() to initialize a context. + * ZSTD_CCtx object can be re-used multiple times within successive compression + * operations. + * + * Start by initializing a context. + * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary + * compression, + * or ZSTD_compressBegin_advanced(), for finer parameter control. + * It's also possible to duplicate a reference context which has already been + * initialized, using ZSTD_copyCCtx() + * + * Then, consume your input using ZSTD_compressContinue(). + * There are some important considerations to keep in mind when using this + * advanced function : + * - ZSTD_compressContinue() has no internal buffer. It uses externally provided + * buffer only. + * - Interface is synchronous : input is consumed entirely and produce 1+ + * (or more) compressed blocks. + * - Caller must ensure there is enough space in `dst` to store compressed data + * under worst case scenario. Worst case evaluation is provided by + * ZSTD_compressBound(). + * ZSTD_compressContinue() doesn't guarantee recover after a failed + * compression. + * - ZSTD_compressContinue() presumes prior input ***is still accessible and + * unmodified*** (up to maximum distance size, see WindowLog). + * It remembers all previous contiguous blocks, plus one separated memory + * segment (which can itself consists of multiple contiguous blocks) + * - ZSTD_compressContinue() detects that prior input has been overwritten when + * `src` buffer overlaps. In which case, it will "discard" the relevant memory + * section from its history. + * + * Finish a frame with ZSTD_compressEnd(), which will write the last block(s) + * and optional checksum. It's possible to use srcSize==0, in which case, it + * will write a final empty block to end the frame. Without last block mark, + * frames will be considered unfinished (corrupted) by decoders. + * + * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new + * frame. + ******************************************************************************/ + +/*===== Buffer-less streaming compression functions =====*/ +size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel); +size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, + size_t dictSize, int compressionLevel); +size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, + size_t dictSize, ZSTD_parameters params, + unsigned long long pledgedSrcSize); +size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx, + unsigned long long pledgedSrcSize); +size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, + unsigned long long pledgedSrcSize); +size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); + + + +/*-***************************************************************************** + * Buffer-less streaming decompression (synchronous mode) + * + * A ZSTD_DCtx object is required to track streaming operations. + * Use ZSTD_initDCtx() to initialize a context. + * A ZSTD_DCtx object can be re-used multiple times. + * + * First typical operation is to retrieve frame parameters, using + * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide + * important information to correctly decode the frame, such as the minimum + * rolling buffer size to allocate to decompress data (`windowSize`), and the + * dictionary ID used. + * Note: content size is optional, it may not be present. 0 means unknown. + * Note that these values could be wrong, either because of data malformation, + * or because an attacker is spoofing deliberate false information. As a + * consequence, check that values remain within valid application range, + * especially `windowSize`, before allocation. Each application can set its own + * limit, depending on local restrictions. For extended interoperability, it is + * recommended to support at least 8 MB. + * Frame parameters are extracted from the beginning of the compressed frame. + * Data fragment must be large enough to ensure successful decoding, typically + * `ZSTD_frameHeaderSize_max` bytes. + * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled. + * >0: `srcSize` is too small, provide at least this many bytes. + * errorCode, which can be tested using ZSTD_isError(). + * + * Start decompression, with ZSTD_decompressBegin() or + * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared + * context, using ZSTD_copyDCtx(). + * + * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() + * alternatively. + * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' + * to ZSTD_decompressContinue(). + * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will + * fail. + * + * The result of ZSTD_decompressContinue() is the number of bytes regenerated + * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an + * error; it just means ZSTD_decompressContinue() has decoded some metadata + * item. It can also be an error code, which can be tested with ZSTD_isError(). + * + * ZSTD_decompressContinue() needs previous data blocks during decompression, up + * to `windowSize`. They should preferably be located contiguously, prior to + * current block. Alternatively, a round buffer of sufficient size is also + * possible. Sufficient size is determined by frame parameters. + * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't + * follow each other, make sure that either the compressor breaks contiguity at + * the same place, or that previous contiguous segment is large enough to + * properly handle maximum back-reference. + * + * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. + * Context can then be reset to start a new decompression. + * + * Note: it's possible to know if next input to present is a header or a block, + * using ZSTD_nextInputType(). This information is not required to properly + * decode a frame. + * + * == Special case: skippable frames == + * + * Skippable frames allow integration of user-defined data into a flow of + * concatenated frames. Skippable frames will be ignored (skipped) by a + * decompressor. The format of skippable frames is as follows: + * a) Skippable frame ID - 4 Bytes, Little endian format, any value from + * 0x184D2A50 to 0x184D2A5F + * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits + * c) Frame Content - any content (User Data) of length equal to Frame Size + * For skippable frames ZSTD_decompressContinue() always returns 0. + * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 + * what means that a frame is skippable. + * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might + * actually be a zstd encoded frame with no content. For purposes of + * decompression, it is valid in both cases to skip the frame using + * ZSTD_findFrameCompressedSize() to find its size in bytes. + * It also returns frame size as fparamsPtr->frameContentSize. + ******************************************************************************/ + +/*===== Buffer-less streaming decompression functions =====*/ +size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx); +size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, + size_t dictSize); +void ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx); +size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx); +size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +typedef enum { + ZSTDnit_frameHeader, + ZSTDnit_blockHeader, + ZSTDnit_block, + ZSTDnit_lastBlock, + ZSTDnit_checksum, + ZSTDnit_skippableFrame +} ZSTD_nextInputType_e; +ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx); + +/*-***************************************************************************** + * Block functions + * + * Block functions produce and decode raw zstd blocks, without frame metadata. + * Frame metadata cost is typically ~18 bytes, which can be non-negligible for + * very small blocks (< 100 bytes). User will have to take in charge required + * information to regenerate data, such as compressed and content sizes. + * + * A few rules to respect: + * - Compressing and decompressing require a context structure + * + Use ZSTD_initCCtx() and ZSTD_initDCtx() + * - It is necessary to init context before starting + * + compression : ZSTD_compressBegin() + * + decompression : ZSTD_decompressBegin() + * + variants _usingDict() are also allowed + * + copyCCtx() and copyDCtx() work too + * - Block size is limited, it must be <= ZSTD_getBlockSizeMax() + * + If you need to compress more, cut data into multiple blocks + * + Consider using the regular ZSTD_compress() instead, as frame metadata + * costs become negligible when source size is large. + * - When a block is considered not compressible enough, ZSTD_compressBlock() + * result will be zero. In which case, nothing is produced into `dst`. + * + User must test for such outcome and deal directly with uncompressed data + * + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!! + * + In case of multiple successive blocks, decoder must be informed of + * uncompressed block existence to follow proper history. Use + * ZSTD_insertBlock() in such a case. + ******************************************************************************/ + +/* Define for static allocation */ +#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) +/*===== Raw zstd block functions =====*/ +size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx); +size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, + size_t blockSize); + +#endif /* ZSTD_H */ -- cgit v1.2.3 From e01d1913b0d0817191418381a6fcebaa01abde2a Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 9 Aug 2017 16:33:40 +0800 Subject: iommu: Add is_attach_deferred call-back to iommu-ops This new call-back will be used to check if the domain attach need be deferred for now. If yes, the domain attach/detach will return directly. Signed-off-by: Baoquan He Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2cb54adc4a33..63983c9e6c3a 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -225,6 +225,7 @@ struct iommu_ops { u32 (*domain_get_windows)(struct iommu_domain *domain); int (*of_xlate)(struct device *dev, struct of_phandle_args *args); + bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev); unsigned long pgsize_bitmap; }; -- cgit v1.2.3 From 42f87e71c3df12d8f29ec1bb7b47772ffaeaf1ee Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 10 Aug 2017 14:44:28 +0200 Subject: iommu/iova: Add flush-queue data structures This patch adds the basic data-structures to implement flush-queues in the generic IOVA code. It also adds the initialization and destroy routines for these data structures. The initialization routine is designed so that the use of this feature is optional for the users of IOVA code. Signed-off-by: Joerg Roedel --- include/linux/iova.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index e0a892ae45c0..8aa10896150e 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -36,6 +36,30 @@ struct iova_rcache { struct iova_cpu_rcache __percpu *cpu_rcaches; }; +struct iova_domain; + +/* Call-Back from IOVA code into IOMMU drivers */ +typedef void (* iova_flush_cb)(struct iova_domain *domain); + +/* Destructor for per-entry data */ +typedef void (* iova_entry_dtor)(unsigned long data); + +/* Number of entries per Flush Queue */ +#define IOVA_FQ_SIZE 256 + +/* Flush Queue entry for defered flushing */ +struct iova_fq_entry { + unsigned long iova_pfn; + unsigned long pages; + unsigned long data; +}; + +/* Per-CPU Flush Queue structure */ +struct iova_fq { + struct iova_fq_entry entries[IOVA_FQ_SIZE]; + unsigned head, tail; +}; + /* holds all the iova translations for a domain */ struct iova_domain { spinlock_t iova_rbtree_lock; /* Lock to protect update of rbtree */ @@ -45,6 +69,14 @@ struct iova_domain { unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ + + iova_flush_cb flush_cb; /* Call-Back function to flush IOMMU + TLBs */ + + iova_entry_dtor entry_dtor; /* IOMMU driver specific destructor for + iova entry */ + + struct iova_fq __percpu *fq; /* Flush Queue */ }; static inline unsigned long iova_size(struct iova *iova) @@ -102,6 +134,8 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn, unsigned long pfn_32bit); +int init_iova_flush_queue(struct iova_domain *iovad, + iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); struct iova *split_and_remove_iova(struct iova_domain *iovad, @@ -174,6 +208,13 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } +static inline int init_iova_flush_queue(struct iova_domain *iovad, + iova_flush_cb flush_cb, + iova_entry_dtor entry_dtor) +{ + return -ENODEV; +} + static inline struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn) { -- cgit v1.2.3 From 1928210107edd4fa786199fef6b875d3af3bef88 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 10 Aug 2017 15:49:44 +0200 Subject: iommu/iova: Implement Flush-Queue ring buffer Add a function to add entries to the Flush-Queue ring buffer. If the buffer is full, call the flush-callback and free the entries. Signed-off-by: Joerg Roedel --- include/linux/iova.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 8aa10896150e..1ae85248ec50 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -127,6 +127,9 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, bool size_aligned); void free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size); +void queue_iova(struct iova_domain *iovad, + unsigned long pfn, unsigned long pages, + unsigned long data); unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn); struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, @@ -182,6 +185,12 @@ static inline void free_iova_fast(struct iova_domain *iovad, { } +static inline void queue_iova(struct iova_domain *iovad, + unsigned long pfn, unsigned long pages, + unsigned long data) +{ +} + static inline unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn) -- cgit v1.2.3 From fb418dab8a4f01dde0c025d15145c589ec02796b Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 10 Aug 2017 16:14:59 +0200 Subject: iommu/iova: Add flush counters to Flush-Queue implementation There are two counters: * fq_flush_start_cnt - Increased when a TLB flush is started. * fq_flush_finish_cnt - Increased when a TLB flush is finished. The fq_flush_start_cnt is assigned to every Flush-Queue entry on its creation. When freeing entries from the Flush-Queue, the value in the entry is compared to the fq_flush_finish_cnt. The entry can only be freed when its value is less than the value of fq_flush_finish_cnt. The reason for these counters it to take advantage of IOMMU TLB flushes that happened on other CPUs. These already flushed the TLB for Flush-Queue entries on other CPUs so that they can already be freed without flushing the TLB again. This makes it less likely that the Flush-Queue is full and saves IOMMU TLB flushes. Signed-off-by: Joerg Roedel --- include/linux/iova.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 1ae85248ec50..985b8008999e 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -14,6 +14,7 @@ #include #include #include +#include #include /* iova structure */ @@ -52,6 +53,7 @@ struct iova_fq_entry { unsigned long iova_pfn; unsigned long pages; unsigned long data; + u64 counter; /* Flush counter when this entrie was added */ }; /* Per-CPU Flush Queue structure */ @@ -77,6 +79,12 @@ struct iova_domain { iova entry */ struct iova_fq __percpu *fq; /* Flush Queue */ + + atomic64_t fq_flush_start_cnt; /* Number of TLB flushes that + have been started */ + + atomic64_t fq_flush_finish_cnt; /* Number of TLB flushes that + have been finished */ }; static inline unsigned long iova_size(struct iova *iova) -- cgit v1.2.3 From 8109c2a2f8463852dddd6a1c3fcf262047c0c124 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 10 Aug 2017 16:31:17 +0200 Subject: iommu/iova: Add locking to Flush-Queues The lock is taken from the same CPU most of the time. But having it allows to flush the queue also from another CPU if necessary. This will be used by a timer to regularily flush any pending IOVAs from the Flush-Queues. Signed-off-by: Joerg Roedel --- include/linux/iova.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 985b8008999e..913a690cd4b0 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -60,6 +60,7 @@ struct iova_fq_entry { struct iova_fq { struct iova_fq_entry entries[IOVA_FQ_SIZE]; unsigned head, tail; + spinlock_t lock; }; /* holds all the iova translations for a domain */ -- cgit v1.2.3 From 9a005a800ae817c2c90ef117d7cd77614d866777 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 10 Aug 2017 16:58:18 +0200 Subject: iommu/iova: Add flush timer Add a timer to flush entries from the Flush-Queues every 10ms. This makes sure that no stale TLB entries remain for too long after an IOVA has been unmapped. Signed-off-by: Joerg Roedel --- include/linux/iova.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 913a690cd4b0..d179b9bf7814 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -48,6 +48,9 @@ typedef void (* iova_entry_dtor)(unsigned long data); /* Number of entries per Flush Queue */ #define IOVA_FQ_SIZE 256 +/* Timeout (in ms) after which entries are flushed from the Flush-Queue */ +#define IOVA_FQ_TIMEOUT 10 + /* Flush Queue entry for defered flushing */ struct iova_fq_entry { unsigned long iova_pfn; @@ -86,6 +89,11 @@ struct iova_domain { atomic64_t fq_flush_finish_cnt; /* Number of TLB flushes that have been finished */ + + struct timer_list fq_timer; /* Timer to regularily empty the + flush-queues */ + atomic_t fq_timer_on; /* 1 when timer is active, 0 + when not */ }; static inline unsigned long iova_size(struct iova *iova) -- cgit v1.2.3 From 48ac3c18cc62d4a23d5dc5c59f8720589d0de14b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 14 Jul 2017 12:23:09 +0100 Subject: fork: allow arch-override of VMAP stack alignment In some cases, an architecture might wish its stacks to be aligned to a boundary larger than THREAD_SIZE. For example, using an alignment of double THREAD_SIZE can allow for stack overflows smaller than THREAD_SIZE to be detected by checking a single bit of the stack pointer. This patch allows architectures to override the alignment of VMAP'd stacks, by defining THREAD_ALIGN. Where not defined, this defaults to THREAD_SIZE, as is the case today. Signed-off-by: Mark Rutland Reviewed-by: Will Deacon Tested-by: Laura Abbott Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Catalin Marinas Cc: James Morse Cc: linux-kernel@vger.kernel.org --- include/linux/thread_info.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 250a27614328..905d769d8ddc 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -38,6 +38,10 @@ enum { #ifdef __KERNEL__ +#ifndef THREAD_ALIGN +#define THREAD_ALIGN THREAD_SIZE +#endif + #ifdef CONFIG_DEBUG_STACK_USAGE # define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \ __GFP_ZERO) -- cgit v1.2.3 From b352baf15b66c5799018104d38f9eb77c7445a34 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Tue, 15 Aug 2017 12:02:16 -0700 Subject: PCI: Move enum pci_interrupt_pin to linux/pci.h We currently have a definition of enum pci_interrupt_pin in a header specific to PCI endpoints - linux/pci-epf.h. In order to allow for use of this enum from PCI host code in a future commit, move its definition to linux/pci.h & include that from linux/pci-epf.h. Additionally we add a PCI_NUM_INTX macro which indicates the number of PCI INTx interrupts, and will be used alongside enum pci_interrupt_pin in further patches. Signed-off-by: Paul Burton [bhelgaas: move enum pci_interrupt_pin outside #ifdef CONFIG_PCI] Signed-off-by: Bjorn Helgaas --- include/linux/pci-epf.h | 9 +-------- include/linux/pci.h | 22 ++++++++++++++++++++++ 2 files changed, 23 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 0d529cb90143..bc8750688348 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -14,17 +14,10 @@ #include #include +#include struct pci_epf; -enum pci_interrupt_pin { - PCI_INTERRUPT_UNKNOWN, - PCI_INTERRUPT_INTA, - PCI_INTERRUPT_INTB, - PCI_INTERRUPT_INTC, - PCI_INTERRUPT_INTD, -}; - enum pci_barno { BAR_0, BAR_1, diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659..bb9c367c85f0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -102,6 +102,28 @@ enum { DEVICE_COUNT_RESOURCE = PCI_NUM_RESOURCES, }; +/** + * enum pci_interrupt_pin - PCI INTx interrupt values + * @PCI_INTERRUPT_UNKNOWN: Unknown or unassigned interrupt + * @PCI_INTERRUPT_INTA: PCI INTA pin + * @PCI_INTERRUPT_INTB: PCI INTB pin + * @PCI_INTERRUPT_INTC: PCI INTC pin + * @PCI_INTERRUPT_INTD: PCI INTD pin + * + * Corresponds to values for legacy PCI INTx interrupts, as can be found in the + * PCI_INTERRUPT_PIN register. + */ +enum pci_interrupt_pin { + PCI_INTERRUPT_UNKNOWN, + PCI_INTERRUPT_INTA, + PCI_INTERRUPT_INTB, + PCI_INTERRUPT_INTC, + PCI_INTERRUPT_INTD, +}; + +/* The number of legacy PCI INTx interrupts */ +#define PCI_NUM_INTX 4 + /* * pci_power_t values must match the bits in the Capabilities PME_Support * and Control/Status PowerState fields in the Power Management capability. -- cgit v1.2.3 From dc503a8ad98474ea0073a1c5c4d9f18cb8dd0dbf Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Tue, 15 Aug 2017 20:34:35 +0100 Subject: bpf/verifier: track liveness for pruning State of a register doesn't matter if it wasn't read in reaching an exit; a write screens off all reads downstream of it from all explored_states upstream of it. This allows us to prune many more branches; here are some processed insn counts for some Cilium programs: Program before after bpf_lb_opt_-DLB_L3.o 6515 3361 bpf_lb_opt_-DLB_L4.o 8976 5176 bpf_lb_opt_-DUNKNOWN.o 2960 1137 bpf_lxc_opt_-DDROP_ALL.o 95412 48537 bpf_lxc_opt_-DUNKNOWN.o 141706 78718 bpf_netdev.o 24251 17995 bpf_overlay.o 10999 9385 The runtime is also improved; here are 'time' results in ms: Program before after bpf_lb_opt_-DLB_L3.o 24 6 bpf_lb_opt_-DLB_L4.o 26 11 bpf_lb_opt_-DUNKNOWN.o 11 2 bpf_lxc_opt_-DDROP_ALL.o 1288 139 bpf_lxc_opt_-DUNKNOWN.o 1768 234 bpf_netdev.o 62 31 bpf_overlay.o 15 13 Signed-off-by: Edward Cree Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c61c3033522e..91d07efed2ba 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -21,6 +21,12 @@ */ #define BPF_MAX_VAR_SIZ INT_MAX +enum bpf_reg_liveness { + REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */ + REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */ + REG_LIVE_WRITTEN, /* reg was written first, screening off later reads */ +}; + struct bpf_reg_state { enum bpf_reg_type type; union { @@ -40,7 +46,7 @@ struct bpf_reg_state { * came from, when one is tested for != NULL. */ u32 id; - /* These five fields must be last. See states_equal() */ + /* Ordering of fields matters. See states_equal() */ /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset @@ -57,6 +63,8 @@ struct bpf_reg_state { s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ + /* This field must be last, for states_equal() reasons. */ + enum bpf_reg_liveness live; }; enum bpf_stack_slot_type { @@ -74,6 +82,7 @@ struct bpf_verifier_state { struct bpf_reg_state regs[MAX_BPF_REG]; u8 stack_slot_type[MAX_BPF_STACK]; struct bpf_reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE]; + struct bpf_verifier_state *parent; }; /* linked list of verifier states used to prune search */ -- cgit v1.2.3 From b3dc8f772fab5b2d284b780830fd56494491e493 Mon Sep 17 00:00:00 2001 From: Tonghao Zhang Date: Tue, 15 Aug 2017 04:28:54 -0700 Subject: net: Fix a typo in comment about sock flags. Signed-off-by: Tonghao Zhang Signed-off-by: David S. Miller --- include/linux/net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index dda2cc939a53..ebeb48c92005 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -37,7 +37,7 @@ struct net; /* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. - * Eventually all flags will be in sk->sk_wq_flags. + * Eventually all flags will be in sk->sk_wq->flags. */ #define SOCKWQ_ASYNC_NOSPACE 0 #define SOCKWQ_ASYNC_WAITDATA 1 -- cgit v1.2.3 From 808ae8f3c7fefef3aece08820c108b68cdb06e1e Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Wed, 22 Mar 2017 19:17:49 +0900 Subject: extcon: Remove deprecated extcon_set/get_cable_state_() The commit 575c2b867ee0 ("extcon: Rename the extcon_set/get_state() to maintain the function naming pattern") renames the extcon function as following: But, the extcon just keeps the old API to prevent the build error. This patch removes the deprecatd extcon API. - extcon_get_cable_state_() -> extcon_get_state() - extcon_set_cable_state_() -> extcon_set_state_sync() Signed-off-by: Chanwoo Choi --- include/linux/extcon.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 7e206a9f88db..3ba02eecba2e 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -422,15 +422,4 @@ static inline int extcon_unregister_interest(struct extcon_specific_cable_nb { return -EINVAL; } - -static inline int extcon_get_cable_state_(struct extcon_dev *edev, unsigned int id) -{ - return extcon_get_state(edev, id); -} - -static inline int extcon_set_cable_state_(struct extcon_dev *edev, unsigned int id, - bool cable_state) -{ - return extcon_set_state_sync(edev, id, cable_state); -} #endif /* __LINUX_EXTCON_H__ */ -- cgit v1.2.3 From 6ab6094f370df082fdf2e117381dd323ce948f68 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Mon, 3 Apr 2017 19:45:48 +0900 Subject: extcon: Correct description to improve the readability The extcon files explains the detailed operation for functions and what is meaning of extcon structure. There are different explanation even if the same argument. So, it modifies the description for both functions and structures in order to improve the readability and guide the role of functions more well. Also, this patch fixes the mismatching license info as a GPL v2 and removes the inactive author information. Signed-off-by: Chanwoo Choi --- include/linux/extcon.h | 72 ++++++++++++++++++++++---------------------------- 1 file changed, 32 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/extcon.h b/include/linux/extcon.h index 3ba02eecba2e..e03204d5a366 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -1,5 +1,5 @@ /* - * External connector (extcon) class driver + * External Connector (extcon) framework * * Copyright (C) 2015 Samsung Electronics * Author: Chanwoo Choi @@ -20,8 +20,7 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * -*/ + */ #ifndef __LINUX_EXTCON_H__ #define __LINUX_EXTCON_H__ @@ -93,7 +92,7 @@ #define EXTCON_NUM 63 /* - * Define the property of supported external connectors. + * Define the properties of supported external connectors. * * When adding the new extcon property, they *must* have * the type/value/default information. Also, you *have to* @@ -176,44 +175,42 @@ struct extcon_dev; #if IS_ENABLED(CONFIG_EXTCON) -/* - * Following APIs are for notifiers or configurations. - * Notifiers are the external port and connection devices. - */ +/* Following APIs register/unregister the extcon device. */ extern int extcon_dev_register(struct extcon_dev *edev); extern void extcon_dev_unregister(struct extcon_dev *edev); extern int devm_extcon_dev_register(struct device *dev, struct extcon_dev *edev); extern void devm_extcon_dev_unregister(struct device *dev, struct extcon_dev *edev); -extern struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name); -/* - * Following APIs control the memory of extcon device. - */ +/* Following APIs allocate/free the memory of the extcon device. */ extern struct extcon_dev *extcon_dev_allocate(const unsigned int *cable); extern void extcon_dev_free(struct extcon_dev *edev); extern struct extcon_dev *devm_extcon_dev_allocate(struct device *dev, const unsigned int *cable); extern void devm_extcon_dev_free(struct device *dev, struct extcon_dev *edev); +/* Synchronize the state and property value for each external connector. */ +extern int extcon_sync(struct extcon_dev *edev, unsigned int id); + /* - * get/set_state access each bit of the 32b encoded state value. - * They are used to access the status of each cable based on the cable id. + * Following APIs get/set the connected state of each external connector. + * The 'id' argument indicates the defined external connector. */ extern int extcon_get_state(struct extcon_dev *edev, unsigned int id); extern int extcon_set_state(struct extcon_dev *edev, unsigned int id, - bool cable_state); + bool state); extern int extcon_set_state_sync(struct extcon_dev *edev, unsigned int id, - bool cable_state); -/* - * Synchronize the state and property data for a specific external connector. - */ -extern int extcon_sync(struct extcon_dev *edev, unsigned int id); + bool state); /* - * get/set_property access the property value of each external connector. - * They are used to access the property of each cable based on the property id. + * Following APIs get/set the property of each external connector. + * The 'id' argument indicates the defined external connector + * and the 'prop' indicates the extcon property. + * + * And extcon_get/set_property_capability() set the capability of the property + * for each external connector. They are used to set the capability of the + * property of each external connector based on the id and property. */ extern int extcon_get_property(struct extcon_dev *edev, unsigned int id, unsigned int prop, @@ -224,19 +221,15 @@ extern int extcon_set_property(struct extcon_dev *edev, unsigned int id, extern int extcon_set_property_sync(struct extcon_dev *edev, unsigned int id, unsigned int prop, union extcon_property_value prop_val); - -/* - * get/set_property_capability set the capability of the property for each - * external connector. They are used to set the capability of the property - * of each external connector based on the id and property. - */ extern int extcon_get_property_capability(struct extcon_dev *edev, unsigned int id, unsigned int prop); extern int extcon_set_property_capability(struct extcon_dev *edev, unsigned int id, unsigned int prop); /* - * Following APIs are to monitor the status change of the external connectors. + * Following APIs register the notifier block in order to detect + * the change of both state and property value for each external connector. + * * extcon_register_notifier(*edev, id, *nb) : Register a notifier block * for specific external connector of the extcon. * extcon_register_notifier_all(*edev, *nb) : Register a notifier block @@ -265,16 +258,15 @@ extern void devm_extcon_unregister_notifier_all(struct device *dev, struct notifier_block *nb); /* - * Following API get the extcon device from devicetree. - * This function use phandle of devicetree to get extcon device directly. + * Following APIs get the extcon_dev from devicetree or by through extcon name. */ +extern struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name); extern struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index); -/* Following API to get information of extcon device */ +/* Following API get the name of extcon device. */ extern const char *extcon_get_edev_name(struct extcon_dev *edev); - #else /* CONFIG_EXTCON */ static inline int extcon_dev_register(struct extcon_dev *edev) { @@ -314,13 +306,13 @@ static inline int extcon_get_state(struct extcon_dev *edev, unsigned int id) } static inline int extcon_set_state(struct extcon_dev *edev, unsigned int id, - bool cable_state) + bool state) { return 0; } static inline int extcon_set_state_sync(struct extcon_dev *edev, unsigned int id, - bool cable_state) + bool state) { return 0; } @@ -362,11 +354,6 @@ static inline int extcon_set_property_capability(struct extcon_dev *edev, return 0; } -static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) -{ - return NULL; -} - static inline int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, struct notifier_block *nb) @@ -392,6 +379,11 @@ static inline void devm_extcon_unregister_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb) { } +static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) +{ + return NULL; +} + static inline struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index) { -- cgit v1.2.3 From ab8a8fbe939de5e2651da6761f83a2b9641b2daa Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Fri, 14 Jul 2017 01:00:55 +0900 Subject: extcon: Use tab instead of space for indentation The extcon header file defines the functions which used the mismatched indentation and used the space on some case. So, this patch clean-up the indentation in order to improve the readbility. And this patch changes the return value of extcon_get_extcon_dev() because of maintaing the same value with extcon_get_edev_by_phandle(). Signed-off-by: Chanwoo Choi --- include/linux/extcon.h | 51 ++++++++++++++++++++++++-------------------------- 1 file changed, 24 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/extcon.h b/include/linux/extcon.h index e03204d5a366..744d60ca80c3 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -179,15 +179,15 @@ struct extcon_dev; extern int extcon_dev_register(struct extcon_dev *edev); extern void extcon_dev_unregister(struct extcon_dev *edev); extern int devm_extcon_dev_register(struct device *dev, - struct extcon_dev *edev); + struct extcon_dev *edev); extern void devm_extcon_dev_unregister(struct device *dev, - struct extcon_dev *edev); + struct extcon_dev *edev); /* Following APIs allocate/free the memory of the extcon device. */ extern struct extcon_dev *extcon_dev_allocate(const unsigned int *cable); extern void extcon_dev_free(struct extcon_dev *edev); extern struct extcon_dev *devm_extcon_dev_allocate(struct device *dev, - const unsigned int *cable); + const unsigned int *cable); extern void devm_extcon_dev_free(struct device *dev, struct extcon_dev *edev); /* Synchronize the state and property value for each external connector. */ @@ -199,7 +199,7 @@ extern int extcon_sync(struct extcon_dev *edev, unsigned int id); */ extern int extcon_get_state(struct extcon_dev *edev, unsigned int id); extern int extcon_set_state(struct extcon_dev *edev, unsigned int id, - bool state); + bool state); extern int extcon_set_state_sync(struct extcon_dev *edev, unsigned int id, bool state); @@ -236,9 +236,9 @@ extern int extcon_set_property_capability(struct extcon_dev *edev, * for all supported external connectors of the extcon. */ extern int extcon_register_notifier(struct extcon_dev *edev, unsigned int id, - struct notifier_block *nb); + struct notifier_block *nb); extern int extcon_unregister_notifier(struct extcon_dev *edev, unsigned int id, - struct notifier_block *nb); + struct notifier_block *nb); extern int devm_extcon_register_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb); @@ -276,13 +276,13 @@ static inline int extcon_dev_register(struct extcon_dev *edev) static inline void extcon_dev_unregister(struct extcon_dev *edev) { } static inline int devm_extcon_dev_register(struct device *dev, - struct extcon_dev *edev) + struct extcon_dev *edev) { return -EINVAL; } static inline void devm_extcon_dev_unregister(struct device *dev, - struct extcon_dev *edev) { } + struct extcon_dev *edev) { } static inline struct extcon_dev *extcon_dev_allocate(const unsigned int *cable) { @@ -292,7 +292,7 @@ static inline struct extcon_dev *extcon_dev_allocate(const unsigned int *cable) static inline void extcon_dev_free(struct extcon_dev *edev) { } static inline struct extcon_dev *devm_extcon_dev_allocate(struct device *dev, - const unsigned int *cable) + const unsigned int *cable) { return ERR_PTR(-ENOSYS); } @@ -323,47 +323,45 @@ static inline int extcon_sync(struct extcon_dev *edev, unsigned int id) } static inline int extcon_get_property(struct extcon_dev *edev, unsigned int id, - unsigned int prop, - union extcon_property_value *prop_val) + unsigned int prop, + union extcon_property_value *prop_val) { return 0; } static inline int extcon_set_property(struct extcon_dev *edev, unsigned int id, - unsigned int prop, - union extcon_property_value prop_val) + unsigned int prop, + union extcon_property_value prop_val) { return 0; } static inline int extcon_set_property_sync(struct extcon_dev *edev, - unsigned int id, unsigned int prop, - union extcon_property_value prop_val) + unsigned int id, unsigned int prop, + union extcon_property_value prop_val) { return 0; } static inline int extcon_get_property_capability(struct extcon_dev *edev, - unsigned int id, unsigned int prop) + unsigned int id, unsigned int prop) { return 0; } static inline int extcon_set_property_capability(struct extcon_dev *edev, - unsigned int id, unsigned int prop) + unsigned int id, unsigned int prop) { return 0; } static inline int extcon_register_notifier(struct extcon_dev *edev, - unsigned int id, - struct notifier_block *nb) + unsigned int id, struct notifier_block *nb) { return 0; } static inline int extcon_unregister_notifier(struct extcon_dev *edev, - unsigned int id, - struct notifier_block *nb) + unsigned int id, struct notifier_block *nb) { return 0; } @@ -381,11 +379,11 @@ static inline void devm_extcon_unregister_notifier(struct device *dev, static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) { - return NULL; + return ERR_PTR(-ENODEV); } static inline struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, - int index) + int index) { return ERR_PTR(-ENODEV); } @@ -403,14 +401,13 @@ struct extcon_specific_cable_nb { }; static inline int extcon_register_interest(struct extcon_specific_cable_nb *obj, - const char *extcon_name, const char *cable_name, - struct notifier_block *nb) + const char *extcon_name, const char *cable_name, + struct notifier_block *nb) { return -EINVAL; } -static inline int extcon_unregister_interest(struct extcon_specific_cable_nb - *obj) +static inline int extcon_unregister_interest(struct extcon_specific_cable_nb *obj) { return -EINVAL; } -- cgit v1.2.3 From b19af510e67e6ca696b8721f45c148119437307c Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 14 Aug 2017 16:53:16 +0200 Subject: genirq/irq_sim: Add a simple interrupt simulator framework Implement a simple, irq_work-based framework for simulating interrupts. Currently the API exposes routines for initializing and deinitializing the simulator object, enqueueing the interrupts and retrieving the allocated interrupt numbers based on the offset of the dummy interrupt in the simulator struct. Signed-off-by: Bartosz Golaszewski Reviewed-by: Jonathan Cameron Cc: Lars-Peter Clausen Cc: Jonathan Corbet Cc: Marc Zyngier Cc: Linus Walleij Cc: linux-doc@vger.kernel.org Cc: linux-gpio@vger.kernel.org Cc: Bamvor Jian Zhang Cc: Jonathan Cameron Link: http://lkml.kernel.org/r/20170814145318.6495-2-brgl@bgdev.pl Signed-off-by: Thomas Gleixner --- include/linux/irq_sim.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/linux/irq_sim.h (limited to 'include/linux') diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h new file mode 100644 index 000000000000..39ce57bfa995 --- /dev/null +++ b/include/linux/irq_sim.h @@ -0,0 +1,41 @@ +#ifndef _LINUX_IRQ_SIM_H +#define _LINUX_IRQ_SIM_H +/* + * Copyright (C) 2017 Bartosz Golaszewski + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include + +/* + * Provides a framework for allocating simulated interrupts which can be + * requested like normal irqs and enqueued from process context. + */ + +struct irq_sim_work_ctx { + struct irq_work work; + int irq; +}; + +struct irq_sim_irq_ctx { + int irqnum; + bool enabled; +}; + +struct irq_sim { + struct irq_sim_work_ctx work_ctx; + int irq_base; + unsigned int irq_count; + struct irq_sim_irq_ctx *irqs; +}; + +int irq_sim_init(struct irq_sim *sim, unsigned int num_irqs); +void irq_sim_fini(struct irq_sim *sim); +void irq_sim_fire(struct irq_sim *sim, unsigned int offset); +int irq_sim_irqnum(struct irq_sim *sim, unsigned int offset); + +#endif /* _LINUX_IRQ_SIM_H */ -- cgit v1.2.3 From 44e72c7ebf294043cfe276f7328b8c0e6a3e50e9 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 14 Aug 2017 16:53:17 +0200 Subject: genirq/irq_sim: Add a devres variant of irq_sim_init() Add a resource managed version of irq_sim_init(). This can be conveniently used in device drivers. Signed-off-by: Bartosz Golaszewski Acked-by: Jonathan Cameron Cc: Lars-Peter Clausen Cc: Jonathan Corbet Cc: Marc Zyngier Cc: Linus Walleij Cc: linux-doc@vger.kernel.org Cc: linux-gpio@vger.kernel.org Cc: Bamvor Jian Zhang Cc: Jonathan Cameron Link: http://lkml.kernel.org/r/20170814145318.6495-3-brgl@bgdev.pl Signed-off-by: Thomas Gleixner --- include/linux/irq_sim.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h index 39ce57bfa995..0380d899b955 100644 --- a/include/linux/irq_sim.h +++ b/include/linux/irq_sim.h @@ -10,6 +10,7 @@ */ #include +#include /* * Provides a framework for allocating simulated interrupts which can be @@ -34,6 +35,8 @@ struct irq_sim { }; int irq_sim_init(struct irq_sim *sim, unsigned int num_irqs); +int devm_irq_sim_init(struct device *dev, struct irq_sim *sim, + unsigned int num_irqs); void irq_sim_fini(struct irq_sim *sim); void irq_sim_fire(struct irq_sim *sim, unsigned int offset); int irq_sim_irqnum(struct irq_sim *sim, unsigned int offset); -- cgit v1.2.3 From 6f3d791f300618caf82a2be0c27456edd76d5164 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Fri, 11 Aug 2017 10:03:59 -0700 Subject: Drivers: hv: vmbus: Fix rescind handling issues This patch handles the following issues that were observed when we are handling racing channel offer message and rescind message for the same offer: 1. Since the host does not respond to messages on a rescinded channel, in the current code, we could be indefinitely blocked on the vmbus_open() call. 2. When a rescinded channel is being closed, if there is a pending interrupt on the channel, we could end up freeing the channel that the interrupt handler would run on. Signed-off-by: K. Y. Srinivasan Reviewed-by: Dexuan Cui Tested-by: Dexuan Cui Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 27db4e650b8c..07650d0232cc 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -879,6 +879,8 @@ struct vmbus_channel { */ enum hv_numa_policy affinity_policy; + bool probe_done; + }; static inline bool is_hvsock_channel(const struct vmbus_channel *c) -- cgit v1.2.3 From 0d58e6c1b19b30623b5f0a053818bd2c32d61166 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Tue, 15 Aug 2017 12:02:17 -0700 Subject: PCI: Add pci_irqd_intx_xlate() Legacy PCI INTx interrupts are represented in the PCI_INTERRUPT_PIN register using the range 1-4, which matches our enum pci_interrupt_pin. This is however not ideal for an IRQ domain, where with 4 interrupts we would ideally have a domain of size 4 & hwirq numbers in the range 0-3. Different PCI host controller drivers have handled this in different ways. Of those under drivers/pci/ which register an INTx IRQ domain, we have: - pcie-altera uses the range 1-4 in device trees and an IRQ domain of size 5 to cover that range, with entry 0 wasted. - pcie-xilinx & pcie-xilinx-nwl use the range 1-4 in device trees but register an IRQ domain of size 4, which doesn't cover the hwirq=4/INTD case leading to that interrupt being broken. - pci-ftpci100 & pci-aardvark use the range 0-3 in both device trees & as hwirq numbering in the driver & IRQ domain. In order to introduce some level of consistency in at least the hwirq numbering used by the drivers & IRQ domains, this patch introduces a new pci_irqd_intx_xlate() helper function which drivers using the 1-4 range in device trees can assign as the xlate callback for their INTx IRQ domain. This translates the 1-4 range into a 0-3 range, allowing us to use an IRQ domain of size 4 & avoid a wasted entry. Further patches will make use of this in drivers to allow them to use an IRQ domain of size 4 for legacy INTx interrupts without breaking INTD. Signed-off-by: Paul Burton Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index bb9c367c85f0..bbc2a991b63f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1416,6 +1416,38 @@ pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, NULL); } +/** + * pci_irqd_intx_xlate() - Translate PCI INTx value to an IRQ domain hwirq + * @d: the INTx IRQ domain + * @node: the DT node for the device whose interrupt we're translating + * @intspec: the interrupt specifier data from the DT + * @intsize: the number of entries in @intspec + * @out_hwirq: pointer at which to write the hwirq number + * @out_type: pointer at which to write the interrupt type + * + * Translate a PCI INTx interrupt number from device tree in the range 1-4, as + * stored in the standard PCI_INTERRUPT_PIN register, to a value in the range + * 0-3 suitable for use in a 4 entry IRQ domain. That is, subtract one from the + * INTx value to obtain the hwirq number. + * + * Returns 0 on success, or -EINVAL if the interrupt specifier is out of range. + */ +static inline int pci_irqd_intx_xlate(struct irq_domain *d, + struct device_node *node, + const u32 *intspec, + unsigned int intsize, + unsigned long *out_hwirq, + unsigned int *out_type) +{ + const u32 intx = intspec[0]; + + if (intx < PCI_INTERRUPT_INTA || intx > PCI_INTERRUPT_INTD) + return -EINVAL; + + *out_hwirq = intx - PCI_INTERRUPT_INTA; + return 0; +} + #ifdef CONFIG_PCIEPORTBUS extern bool pcie_ports_disabled; extern bool pcie_ports_auto; -- cgit v1.2.3 From b005fd189cec9407b700599e1e80e0552446ee79 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 15 Aug 2017 22:31:58 -0700 Subject: bpf: introduce new program type for skbs on sockets A class of programs, run from strparser and soon from a new map type called sock map, are used with skb as the context but on established sockets. By creating a specific program type for these we can use bpf helpers that expect full sockets and get the verifier to ensure these helpers are not used out of context. The new type is BPF_PROG_TYPE_SK_SKB. This patch introduces the infrastructure and type. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/bpf_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index b1e1035ca24b..4b72db30dacf 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -11,6 +11,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops) #endif #ifdef CONFIG_BPF_EVENTS BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) -- cgit v1.2.3 From a6f6df69c48b86cd84f36c70593eb4968fceb34a Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 15 Aug 2017 22:32:22 -0700 Subject: bpf: export bpf_prog_inc_not_zero bpf_prog_inc_not_zero will be used by upcoming sockmap patches this patch simply exports it so we can pull it in. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 39229c455cba..d6e1de8ce0fc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -252,6 +252,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); +struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages); @@ -344,6 +345,12 @@ static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) return ERR_PTR(-EOPNOTSUPP); } +static inline struct bpf_prog *__must_check +bpf_prog_inc_not_zero(struct bpf_prog *prog) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) { return 0; -- cgit v1.2.3 From 174a79ff9515f400b9a6115643dafd62a635b7e6 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 15 Aug 2017 22:32:47 -0700 Subject: bpf: sockmap with sk redirect support Recently we added a new map type called dev map used to forward XDP packets between ports (6093ec2dc313). This patches introduces a similar notion for sockets. A sockmap allows users to add participating sockets to a map. When sockets are added to the map enough context is stored with the map entry to use the entry with a new helper bpf_sk_redirect_map(map, key, flags) This helper (analogous to bpf_redirect_map in XDP) is given the map and an entry in the map. When called from a sockmap program, discussed below, the skb will be sent on the socket using skb_send_sock(). With the above we need a bpf program to call the helper from that will then implement the send logic. The initial site implemented in this series is the recv_sock hook. For this to work we implemented a map attach command to add attributes to a map. In sockmap we add two programs a parse program and a verdict program. The parse program uses strparser to build messages and pass them to the verdict program. The parse programs use the normal strparser semantics. The verdict program is of type SK_SKB. The verdict program returns a verdict SK_DROP, or SK_REDIRECT for now. Additional actions may be added later. When SK_REDIRECT is returned, expected when bpf program uses bpf_sk_redirect_map(), the sockmap logic will consult per cpu variables set by the helper routine and pull the sock entry out of the sock map. This pattern follows the existing redirect logic in cls and xdp programs. This gives the flow, recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock \ -> kfree_skb As an example use case a message based load balancer may use specific logic in the verdict program to select the sock to send on. Sample programs are provided in future patches that hopefully illustrate the user interfaces. Also selftests are in follow-on patches. Signed-off-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/bpf.h | 7 +++++-- include/linux/bpf_types.h | 1 + include/linux/filter.h | 2 ++ 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d6e1de8ce0fc..a4145e9c74b5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -16,6 +16,7 @@ #include struct perf_event; +struct bpf_prog; struct bpf_map; /* map is generic key/value storage optionally accesible by eBPF programs */ @@ -37,6 +38,8 @@ struct bpf_map_ops { void (*map_fd_put_ptr)(void *ptr); u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); + int (*map_attach)(struct bpf_map *map, + struct bpf_prog *p1, struct bpf_prog *p2); }; struct bpf_map { @@ -138,8 +141,6 @@ enum bpf_reg_type { PTR_TO_PACKET_END, /* skb->data + headlen */ }; -struct bpf_prog; - /* The information passed from prog-specific *_is_valid_access * back to the verifier. */ @@ -312,6 +313,7 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); /* Map specifics */ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); @@ -391,6 +393,7 @@ extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_skb_vlan_push_proto; extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; +extern const struct bpf_func_proto bpf_sock_map_update_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 4b72db30dacf..fa805074d168 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -38,4 +38,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif diff --git a/include/linux/filter.h b/include/linux/filter.h index d19ed3c15e1e..7015116331af 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -727,6 +727,8 @@ void xdp_do_flush_map(void); void bpf_warn_invalid_xdp_action(u32 act); void bpf_warn_invalid_xdp_redirect(u32 ifindex); +struct sock *do_sk_redirect_map(void); + #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; -- cgit v1.2.3 From 729749bb8da186e68d97d1b0439f0b1e0059c41d Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 13 Aug 2017 10:03:59 -0400 Subject: SUNRPC: Don't hold the transport lock across socket copy operations Instead add a mechanism to ensure that the request doesn't disappear from underneath us while copying from the socket. We do this by preventing xprt_release() from freeing the XDR buffers until the flag RPC_TASK_MSG_RECV has been cleared from the request. Signed-off-by: Trond Myklebust Reviewed-by: Chuck Lever --- include/linux/sunrpc/sched.h | 2 ++ include/linux/sunrpc/xprt.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 50a99a117da7..c1768f9d993b 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -139,6 +139,8 @@ struct rpc_task_setup { #define RPC_TASK_RUNNING 0 #define RPC_TASK_QUEUED 1 #define RPC_TASK_ACTIVE 2 +#define RPC_TASK_MSG_RECV 3 +#define RPC_TASK_MSG_RECV_WAIT 4 #define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index eab1c749e192..65b9e0224753 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -372,6 +372,8 @@ void xprt_write_space(struct rpc_xprt *xprt); void xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); void xprt_complete_rqst(struct rpc_task *task, int copied); +void xprt_pin_rqst(struct rpc_rqst *req); +void xprt_unpin_rqst(struct rpc_rqst *req); void xprt_release_rqst_cong(struct rpc_task *task); void xprt_disconnect_done(struct rpc_xprt *xprt); void xprt_force_disconnect(struct rpc_xprt *xprt); -- cgit v1.2.3 From 6bdc9c4c31c81688e19cb186d49be01bbb6a1618 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 16 Aug 2017 15:02:32 -0700 Subject: bpf: sock_map fixes for !CONFIG_BPF_SYSCALL and !STREAM_PARSER MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Resolve issues with !CONFIG_BPF_SYSCALL and !STREAM_PARSER net/core/filter.c: In function ‘do_sk_redirect_map’: net/core/filter.c:1881:3: error: implicit declaration of function ‘__sock_map_lookup_elem’ [-Werror=implicit-function-declaration] sk = __sock_map_lookup_elem(ri->map, ri->ifindex); ^ net/core/filter.c:1881:6: warning: assignment makes pointer from integer without a cast [enabled by default] sk = __sock_map_lookup_elem(ri->map, ri->ifindex); Fixes: 174a79ff9515 ("bpf: sockmap with sk redirect support") Reported-by: Eric Dumazet Signed-off-by: John Fastabend Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 10 +++++++++- include/linux/bpf_types.h | 2 ++ 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a4145e9c74b5..1cc6c5ff61ec 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -313,7 +313,6 @@ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); /* Map specifics */ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); -struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); @@ -377,6 +376,15 @@ static inline void __dev_map_flush(struct bpf_map *map) } #endif /* CONFIG_BPF_SYSCALL */ +#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) +struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); +#else +static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) +{ + return NULL; +} +#endif + /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fa805074d168..6f1a567667b8 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -38,5 +38,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) #ifdef CONFIG_NET BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +#ifdef CONFIG_STREAM_PARSER BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif +#endif -- cgit v1.2.3 From 9a603b8e1136f2b55f780fefbcbf84d31844ff2b Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 16 Aug 2017 08:56:24 -0700 Subject: vmbus: remove unused vmbus_sendpacket_multipagebuffer This function is not used anywhere in current code. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/hyperv.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b7d7bbec74e0..39a080ce17da 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1052,12 +1052,6 @@ extern int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, u64 requestid, u32 flags); -extern int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, - struct hv_multipage_buffer *mpb, - void *buffer, - u32 bufferlen, - u64 requestid); - extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *mpb, u32 desc_size, -- cgit v1.2.3 From 5a668d8cddbe8bf14379ce110c49ca088a1e9fae Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 16 Aug 2017 08:56:25 -0700 Subject: vmbus: remove unused vmubs_sendpacket_pagebuffer_ctl The function vmbus_sendpacket_pagebuffer_ctl was never used directly. Just have vmbus_send_pagebuffer Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/hyperv.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 39a080ce17da..9692592d43a3 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1044,14 +1044,6 @@ extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, u32 bufferlen, u64 requestid); -extern int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, - struct hv_page_buffer pagebuffers[], - u32 pagecount, - void *buffer, - u32 bufferlen, - u64 requestid, - u32 flags); - extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, struct vmbus_packet_mpb_array *mpb, u32 desc_size, -- cgit v1.2.3 From 5dd0fb9b9ffc0ef9b312d05604f4ad0fffc50505 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 16 Aug 2017 08:56:26 -0700 Subject: vmbus: remove unused vmbus_sendpacket_ctl The only usage of vmbus_sendpacket_ctl was by vmbus_sendpacket. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/hyperv.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 9692592d43a3..a5f961c4149e 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1030,13 +1030,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel, enum vmbus_packet_type type, u32 flags); -extern int vmbus_sendpacket_ctl(struct vmbus_channel *channel, - void *buffer, - u32 bufferLen, - u64 requestid, - enum vmbus_packet_type type, - u32 flags); - extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel, struct hv_page_buffer pagebuffers[], u32 pagecount, -- cgit v1.2.3 From 81fbfe8adaf38d4f5a98c19bebfd41c5d6acaee8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Aug 2017 10:36:47 -0700 Subject: ptr_ring: use kmalloc_array() As found by syzkaller, malicious users can set whatever tx_queue_len on a tun device and eventually crash the kernel. Lets remove the ALIGN(XXX, SMP_CACHE_BYTES) thing since a small ring buffer is not fast anyway. Fixes: 2e0ab8ca83c1 ("ptr_ring: array based FIFO for pointers") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Cc: Michael S. Tsirkin Cc: Jason Wang Signed-off-by: David S. Miller --- include/linux/ptr_ring.h | 9 +++++---- include/linux/skb_array.h | 3 ++- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index d8c97ec8a8e6..37b4bb2545b3 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -436,9 +436,9 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, __PTR_RING_PEEK_CALL_v; \ }) -static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp) +static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp) { - return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp); + return kcalloc(size, sizeof(void *), gfp); } static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) @@ -582,7 +582,8 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ -static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings, +static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, + unsigned int nrings, int size, gfp_t gfp, void (*destroy)(void *)) { @@ -590,7 +591,7 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings, void ***queues; int i; - queues = kmalloc(nrings * sizeof *queues, gfp); + queues = kmalloc_array(nrings, sizeof(*queues), gfp); if (!queues) goto noqueues; diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index 35226cd4efb0..8621ffdeecbf 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -193,7 +193,8 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) } static inline int skb_array_resize_multiple(struct skb_array **rings, - int nrings, int size, gfp_t gfp) + int nrings, unsigned int size, + gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); return ptr_ring_resize_multiple((struct ptr_ring **)rings, -- cgit v1.2.3 From ce0fa3e56ad20f04d8252353dcd24e924abdafca Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Wed, 16 Aug 2017 10:18:03 -0700 Subject: x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages Speculative processor accesses may reference any memory that has a valid page table entry. While a speculative access won't generate a machine check, it will log the error in a machine check bank. That could cause escalation of a subsequent error since the overflow bit will be then set in the machine check bank status register. Code has to be double-plus-tricky to avoid mentioning the 1:1 virtual address of the page we want to map out otherwise we may trigger the very problem we are trying to avoid. We use a non-canonical address that passes through the usual Linux table walking code to get to the same "pte". Thanks to Dave Hansen for reviewing several iterations of this. Also see: http://marc.info/?l=linux-mm&m=149860136413338&w=2 Signed-off-by: Tony Luck Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: Elliott, Robert (Persistent Memory) Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Naoya Horiguchi Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-mm@kvack.org Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20170816171803.28342-1-tony.luck@intel.com Signed-off-by: Ingo Molnar --- include/linux/mm_inline.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index e030a68ead7e..25438b2b6f22 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -126,4 +126,10 @@ static __always_inline enum lru_list page_lru(struct page *page) #define lru_to_page(head) (list_entry((head)->prev, struct page, lru)) +#ifdef arch_unmap_kpfn +extern void arch_unmap_kpfn(unsigned long pfn); +#else +static __always_inline void arch_unmap_kpfn(unsigned long pfn) { } +#endif + #endif -- cgit v1.2.3 From 7a46ec0e2f4850407de5e1d19a44edee6efa58ec Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 15 Aug 2017 09:19:24 -0700 Subject: locking/refcounts, x86/asm: Implement fast refcount overflow protection This implements refcount_t overflow protection on x86 without a noticeable performance impact, though without the fuller checking of REFCOUNT_FULL. This is done by duplicating the existing atomic_t refcount implementation but with normally a single instruction added to detect if the refcount has gone negative (e.g. wrapped past INT_MAX or below zero). When detected, the handler saturates the refcount_t to INT_MIN / 2. With this overflow protection, the erroneous reference release that would follow a wrap back to zero is blocked from happening, avoiding the class of refcount-overflow use-after-free vulnerabilities entirely. Only the overflow case of refcounting can be perfectly protected, since it can be detected and stopped before the reference is freed and left to be abused by an attacker. There isn't a way to block early decrements, and while REFCOUNT_FULL stops increment-from-zero cases (which would be the state _after_ an early decrement and stops potential double-free conditions), this fast implementation does not, since it would require the more expensive cmpxchg loops. Since the overflow case is much more common (e.g. missing a "put" during an error path), this protection provides real-world protection. For example, the two public refcount overflow use-after-free exploits published in 2016 would have been rendered unexploitable: http://perception-point.io/2016/01/14/analysis-and-exploitation-of-a-linux-kernel-vulnerability-cve-2016-0728/ http://cyseclabs.com/page?n=02012016 This implementation does, however, notice an unchecked decrement to zero (i.e. caller used refcount_dec() instead of refcount_dec_and_test() and it resulted in a zero). Decrements under zero are noticed (since they will have resulted in a negative value), though this only indicates that a use-after-free may have already happened. Such notifications are likely avoidable by an attacker that has already exploited a use-after-free vulnerability, but it's better to have them reported than allow such conditions to remain universally silent. On first overflow detection, the refcount value is reset to INT_MIN / 2 (which serves as a saturation value) and a report and stack trace are produced. When operations detect only negative value results (such as changing an already saturated value), saturation still happens but no notification is performed (since the value was already saturated). On the matter of races, since the entire range beyond INT_MAX but before 0 is negative, every operation at INT_MIN / 2 will trap, leaving no overflow-only race condition. As for performance, this implementation adds a single "js" instruction to the regular execution flow of a copy of the standard atomic_t refcount operations. (The non-"and_test" refcount_dec() function, which is uncommon in regular refcount design patterns, has an additional "jz" instruction to detect reaching exactly zero.) Since this is a forward jump, it is by default the non-predicted path, which will be reinforced by dynamic branch prediction. The result is this protection having virtually no measurable change in performance over standard atomic_t operations. The error path, located in .text.unlikely, saves the refcount location and then uses UD0 to fire a refcount exception handler, which resets the refcount, handles reporting, and returns to regular execution. This keeps the changes to .text size minimal, avoiding return jumps and open-coded calls to the error reporting routine. Example assembly comparison: refcount_inc() before: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) refcount_inc() after: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) ffffffff8154614d: 0f 88 80 d5 17 00 js ffffffff816c36d3 ... .text.unlikely: ffffffff816c36d3: 48 8d 4d f4 lea -0xc(%rbp),%rcx ffffffff816c36d7: 0f ff (bad) These are the cycle counts comparing a loop of refcount_inc() from 1 to INT_MAX and back down to 0 (via refcount_dec_and_test()), between unprotected refcount_t (atomic_t), fully protected REFCOUNT_FULL (refcount_t-full), and this overflow-protected refcount (refcount_t-fast): 2147483646 refcount_inc()s and 2147483647 refcount_dec_and_test()s: cycles protections atomic_t 82249267387 none refcount_t-fast 82211446892 overflow, untested dec-to-zero refcount_t-full 144814735193 overflow, untested dec-to-zero, inc-from-zero This code is a modified version of the x86 PAX_REFCOUNT atomic_t overflow defense from the last public patch of PaX/grsecurity, based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Thanks to PaX Team for various suggestions for improvement for repurposing this code to be a refcount-only protection. Signed-off-by: Kees Cook Reviewed-by: Josh Poimboeuf Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: David S. Miller Cc: Davidlohr Bueso Cc: Elena Reshetova Cc: Eric Biggers Cc: Eric W. Biederman Cc: Greg KH Cc: Hans Liljestrand Cc: James Bottomley Cc: Jann Horn Cc: Linus Torvalds Cc: Manfred Spraul Cc: Peter Zijlstra Cc: Rik van Riel Cc: Serge E. Hallyn Cc: Thomas Gleixner Cc: arozansk@redhat.com Cc: axboe@kernel.dk Cc: kernel-hardening@lists.openwall.com Cc: linux-arch Link: http://lkml.kernel.org/r/20170815161924.GA133115@beast Signed-off-by: Ingo Molnar --- include/linux/kernel.h | 7 +++++++ include/linux/refcount.h | 4 ++++ 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bd6d96cf80b1..6607225d0ea4 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -277,6 +277,13 @@ extern int oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; +#ifdef CONFIG_ARCH_HAS_REFCOUNT +void refcount_error_report(struct pt_regs *regs, const char *err); +#else +static inline void refcount_error_report(struct pt_regs *regs, const char *err) +{ } +#endif + /* Internal, do not use. */ int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); int __must_check _kstrtol(const char *s, unsigned int base, long *res); diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 591792c8e5b0..48b7c9c68c4d 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -53,6 +53,9 @@ extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r); extern __must_check bool refcount_dec_and_test(refcount_t *r); extern void refcount_dec(refcount_t *r); #else +# ifdef CONFIG_ARCH_HAS_REFCOUNT +# include +# else static inline __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r) { return atomic_add_unless(&r->refs, i, 0); @@ -87,6 +90,7 @@ static inline void refcount_dec(refcount_t *r) { atomic_dec(&r->refs); } +# endif /* !CONFIG_ARCH_HAS_REFCOUNT */ #endif /* CONFIG_REFCOUNT_FULL */ extern __must_check bool refcount_dec_if_one(refcount_t *r); -- cgit v1.2.3 From 02e43c2dcd3b3cf7244f6dda65a07e8dacadaf8d Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 16 Aug 2017 21:46:51 +0800 Subject: efi: Introduce efi_early_memdesc_ptr to get pointer to memmap descriptor The existing map iteration helper for_each_efi_memory_desc_in_map can only be used after the kernel initializes the EFI subsystem to set up struct efi_memory_map. Before that we also need iterate map descriptors which are stored in several intermediate structures, like struct efi_boot_memmap for arch independent usage and struct efi_info for x86 arch only. Introduce efi_early_memdesc_ptr() to get pointer to a map descriptor, and replace several places where that primitive is open coded. Signed-off-by: Baoquan He [ Various improvements to the text. ] Acked-by: Matt Fleming Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: ard.biesheuvel@linaro.org Cc: fanc.fnst@cn.fujitsu.com Cc: izumi.taku@jp.fujitsu.com Cc: keescook@chromium.org Cc: linux-efi@vger.kernel.org Cc: n-horiguchi@ah.jp.nec.com Cc: thgarnie@google.com Link: http://lkml.kernel.org/r/20170816134651.GF21273@x1 Signed-off-by: Ingo Molnar --- include/linux/efi.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 8269bcb8ccf7..a686ca9a7e5c 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1020,6 +1020,28 @@ extern int efi_memattr_init(void); extern int efi_memattr_apply_permissions(struct mm_struct *mm, efi_memattr_perm_setter fn); +/* + * efi_early_memdesc_ptr - get the n-th EFI memmap descriptor + * @map: the start of efi memmap + * @desc_size: the size of space for each EFI memmap descriptor + * @n: the index of efi memmap descriptor + * + * EFI boot service provides the GetMemoryMap() function to get a copy of the + * current memory map which is an array of memory descriptors, each of + * which describes a contiguous block of memory. It also gets the size of the + * map, and the size of each descriptor, etc. + * + * Note that per section 6.2 of UEFI Spec 2.6 Errata A, the returned size of + * each descriptor might not be equal to sizeof(efi_memory_memdesc_t), + * since efi_memory_memdesc_t may be extended in the future. Thus the OS + * MUST use the returned size of the descriptor to find the start of each + * efi_memory_memdesc_t in the memory map array. This should only be used + * during bootup since for_each_efi_memory_desc_xxx() is available after the + * kernel initializes the EFI subsystem to set up struct efi_memory_map. + */ +#define efi_early_memdesc_ptr(map, desc_size, n) \ + (efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size))) + /* Iterate through an efi_memory_map */ #define for_each_efi_memory_desc_in_map(m, md) \ for ((md) = (m)->map; \ -- cgit v1.2.3 From ea3f2c0fdfbb180f142cdbc0d1f055c7b9a5e63e Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Thu, 17 Aug 2017 17:57:41 +0900 Subject: locking/lockdep: Rename CONFIG_LOCKDEP_COMPLETE to CONFIG_LOCKDEP_COMPLETIONS 'complete' is an adjective and LOCKDEP_COMPLETE sounds like 'lockdep is complete', so pick a better name that uses a noun. Signed-off-by: Byungchul Park Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-team@lge.com Link: http://lkml.kernel.org/r/1502960261-16206-3-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- include/linux/completion.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index 9bcebf509b4d..791f053f28b7 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -9,7 +9,7 @@ */ #include -#ifdef CONFIG_LOCKDEP_COMPLETE +#ifdef CONFIG_LOCKDEP_COMPLETIONS #include #endif @@ -28,12 +28,12 @@ struct completion { unsigned int done; wait_queue_head_t wait; -#ifdef CONFIG_LOCKDEP_COMPLETE +#ifdef CONFIG_LOCKDEP_COMPLETIONS struct lockdep_map_cross map; #endif }; -#ifdef CONFIG_LOCKDEP_COMPLETE +#ifdef CONFIG_LOCKDEP_COMPLETIONS static inline void complete_acquire(struct completion *x) { lock_acquire_exclusive((struct lockdep_map *)&x->map, 0, 0, NULL, _RET_IP_); @@ -64,7 +64,7 @@ static inline void complete_release(struct completion *x) {} static inline void complete_release_commit(struct completion *x) {} #endif -#ifdef CONFIG_LOCKDEP_COMPLETE +#ifdef CONFIG_LOCKDEP_COMPLETIONS #define COMPLETION_INITIALIZER(work) \ { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \ STATIC_CROSS_LOCKDEP_MAP_INIT("(complete)" #work, &(work)) } -- cgit v1.2.3 From 52fa5bc5cbba089f09bc2c372e3432f3f3e48051 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Thu, 17 Aug 2017 17:46:12 +0800 Subject: locking/lockdep: Explicitly initialize wq_barrier::done::map With the new lockdep crossrelease feature, which checks completions usage, a false positive is reported in the workqueue code: > Worker A : acquired of wfc.work -> wait for cpu_hotplug_lock to be released > Task B : acquired of cpu_hotplug_lock -> wait for lock#3 to be released > Task C : acquired of lock#3 -> wait for completion of barr->done > (Task C is in lru_add_drain_all_cpuslocked()) > Worker D : wait for wfc.work to be released -> will complete barr->done Such a dead lock can not happen because Task C's barr->done and Worker D's barr->done can not be the same instance. The reason of this false positive is we initialize all wq_barrier::done at insert_wq_barrier() via init_completion(), which makes them belong to the same lock class, therefore, impossible circles are reported. To fix this, explicitly initialize the lockdep map for wq_barrier::done in insert_wq_barrier(), so that the lock class key of wq_barrier::done is a subkey of the corresponding work_struct, as a result we won't build a dependency between a wq_barrier with a unrelated work, and we can differ wq barriers based on the related works, so the false positive above is avoided. Also define the empty lockdep_init_map_crosslock() for !CROSSRELEASE to make the code simple and away from unnecessary #ifdefs. Reported-by: Ingo Molnar Signed-off-by: Boqun Feng Cc: Byungchul Park Cc: Lai Jiangshan Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Tejun Heo Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170817094622.12915-1-boqun.feng@gmail.com Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 651cc61af041..fc827cab6d6e 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -583,6 +583,7 @@ extern void crossrelease_hist_end(enum xhlock_context_t c); extern void lockdep_init_task(struct task_struct *task); extern void lockdep_free_task(struct task_struct *task); #else +#define lockdep_init_map_crosslock(m, n, k, s) do {} while (0) /* * To initialize a lockdep_map statically use this macro. * Note that _name must not be NULL. -- cgit v1.2.3 From 7e42776d5ed1fe9a941ed8876c5d15cd7cf5d89f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 May 2017 08:05:00 -0700 Subject: rcu: Drive TASKS_RCU directly off of PREEMPT The actual use of TASKS_RCU is only when PREEMPT, otherwise RCU-sched is used instead. This commit therefore makes synchronize_rcu_tasks() and call_rcu_tasks() available always, but mapped to synchronize_sched() and call_rcu_sched(), respectively, when !PREEMPT. This approach also allows some #ifdefs to be removed from rcutorture. Reported-by: Ingo Molnar Signed-off-by: Paul E. McKenney Reviewed-by: Masami Hiramatsu Acked-by: Ingo Molnar --- include/linux/rcupdate.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f816fc72b51e..c3f380befdd7 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -58,8 +58,6 @@ void call_rcu(struct rcu_head *head, rcu_callback_t func); void call_rcu_bh(struct rcu_head *head, rcu_callback_t func); void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); void synchronize_sched(void); -void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); -void synchronize_rcu_tasks(void); void rcu_barrier_tasks(void); #ifdef CONFIG_PREEMPT_RCU @@ -176,10 +174,14 @@ extern struct srcu_struct tasks_rcu_exit_srcu; rcu_all_qs(); \ rcu_note_voluntary_context_switch_lite(t); \ } while (0) +void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); +void synchronize_rcu_tasks(void); #else /* #ifdef CONFIG_TASKS_RCU */ #define TASKS_RCU(x) do { } while (0) #define rcu_note_voluntary_context_switch_lite(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() +#define call_rcu_tasks call_rcu_sched +#define synchronize_rcu_tasks synchronize_sched #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** -- cgit v1.2.3 From ccdd29ffffa7246cb359b9408772858a15fc4ea5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 25 May 2017 08:51:48 -0700 Subject: rcu: Create reasonable API for do_exit() TASKS_RCU processing Currently, the exit-time support for TASKS_RCU is open-coded in do_exit(). This commit creates exit_tasks_rcu_start() and exit_tasks_rcu_finish() APIs for do_exit() use. This has the benefit of confining the use of the tasks_rcu_exit_srcu variable to one file, allowing it to become static. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 7 ++++--- include/linux/sched.h | 5 +++-- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c3f380befdd7..ce9d21923d75 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -162,8 +162,6 @@ static inline void rcu_init_nohz(void) { } * macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU -#define TASKS_RCU(x) x -extern struct srcu_struct tasks_rcu_exit_srcu; #define rcu_note_voluntary_context_switch_lite(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ @@ -176,12 +174,15 @@ extern struct srcu_struct tasks_rcu_exit_srcu; } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); +void exit_tasks_rcu_start(void); +void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ -#define TASKS_RCU(x) do { } while (0) #define rcu_note_voluntary_context_switch_lite(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) rcu_all_qs() #define call_rcu_tasks call_rcu_sched #define synchronize_rcu_tasks synchronize_sched +static inline void exit_tasks_rcu_start(void) { } +static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 8337e2db0bb2..e4c38809a09e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -589,9 +589,10 @@ struct task_struct { #ifdef CONFIG_TASKS_RCU unsigned long rcu_tasks_nvcsw; - bool rcu_tasks_holdout; - struct list_head rcu_tasks_holdout_list; + u8 rcu_tasks_holdout; + u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; + struct list_head rcu_tasks_holdout_list; #endif /* #ifdef CONFIG_TASKS_RCU */ struct sched_info sched_info; -- cgit v1.2.3 From 352eee1242ef62e18a475ef9278697dbd865969b Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Tue, 20 Jun 2017 14:45:46 -0700 Subject: swait: Add idle variants which don't contribute to load average There are cases where folks are using an interruptible swait when using kthreads. This is rather confusing given you'd expect interruptible waits to be -- interruptible, but kthreads are not interruptible ! The reason for such practice though is to avoid having these kthreads contribute to the system load average. When systems are idle some kthreads may spend a lot of time blocking if using swait_event_timeout(). This would contribute to the system load average. On systems without preemption this would mean the load average of an idle system is bumped to 2 instead of 0. On systems with PREEMPT=y this would mean the load average of an idle system is bumped to 3 instead of 0. This adds proper API using TASK_IDLE to make such goals explicit and avoid confusion. Suggested-by: "Eric W. Biederman" Acked-by: "Eric W. Biederman" Tested-by: Paul E. McKenney Signed-off-by: Luis R. Rodriguez Signed-off-by: Paul E. McKenney --- include/linux/swait.h | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swait.h b/include/linux/swait.h index c1f9c62a8a50..4a4e180d0a35 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -169,4 +169,59 @@ do { \ __ret; \ }) +#define __swait_event_idle(wq, condition) \ + (void)___swait_event(wq, condition, TASK_IDLE, 0, schedule()) + +/** + * swait_event_idle - wait without system load contribution + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * + * The process is put to sleep (TASK_IDLE) until the @condition evaluates to + * true. The @condition is checked each time the waitqueue @wq is woken up. + * + * This function is mostly used when a kthread or workqueue waits for some + * condition and doesn't want to contribute to system load. Signals are + * ignored. + */ +#define swait_event_idle(wq, condition) \ +do { \ + if (condition) \ + break; \ + __swait_event_idle(wq, condition); \ +} while (0) + +#define __swait_event_idle_timeout(wq, condition, timeout) \ + ___swait_event(wq, ___wait_cond_timeout(condition), \ + TASK_IDLE, timeout, \ + __ret = schedule_timeout(__ret)) + +/** + * swait_event_idle_timeout - wait up to timeout without load contribution + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout at which we'll give up in jiffies + * + * The process is put to sleep (TASK_IDLE) until the @condition evaluates to + * true. The @condition is checked each time the waitqueue @wq is woken up. + * + * This function is mostly used when a kthread or workqueue waits for some + * condition and doesn't want to contribute to system load. Signals are + * ignored. + * + * Returns: + * 0 if the @condition evaluated to %false after the @timeout elapsed, + * 1 if the @condition evaluated to %true after the @timeout elapsed, + * or the remaining jiffies (at least 1) if the @condition evaluated + * to %true before the @timeout elapsed. + */ +#define swait_event_idle_timeout(wq, condition, timeout) \ +({ \ + long __ret = timeout; \ + if (!___wait_cond_timeout(condition)) \ + __ret = __swait_event_idle_timeout(wq, \ + condition, timeout); \ + __ret; \ +}) + #endif /* _LINUX_SWAIT_H */ -- cgit v1.2.3 From d3a024abbc438277851c510b51ec9b158821488b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 29 Jun 2017 15:47:44 -0700 Subject: locking: Remove spin_unlock_wait() generic definitions There is no agreed-upon definition of spin_unlock_wait()'s semantics, and it appears that all callers could do just as well with a lock/unlock pair. This commit therefore removes spin_unlock_wait() and related definitions from core code. Signed-off-by: Paul E. McKenney Cc: Arnd Bergmann Cc: Ingo Molnar Cc: Will Deacon Cc: Peter Zijlstra Cc: Alan Stern Cc: Andrea Parri Cc: Linus Torvalds --- include/linux/spinlock.h | 11 ----------- include/linux/spinlock_up.h | 6 ------ 2 files changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 59248dcc6ef3..ef018a6e4985 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -130,12 +130,6 @@ do { \ #define smp_mb__before_spinlock() smp_wmb() #endif -/** - * raw_spin_unlock_wait - wait until the spinlock gets unlocked - * @lock: the spinlock in question. - */ -#define raw_spin_unlock_wait(lock) arch_spin_unlock_wait(&(lock)->raw_lock) - #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); #define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock) @@ -369,11 +363,6 @@ static __always_inline int spin_trylock_irq(spinlock_t *lock) raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) -static __always_inline void spin_unlock_wait(spinlock_t *lock) -{ - raw_spin_unlock_wait(&lock->rlock); -} - static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 0d9848de677d..612fb530af41 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -26,11 +26,6 @@ #ifdef CONFIG_DEBUG_SPINLOCK #define arch_spin_is_locked(x) ((x)->slock == 0) -static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) -{ - smp_cond_load_acquire(&lock->slock, VAL); -} - static inline void arch_spin_lock(arch_spinlock_t *lock) { lock->slock = 0; @@ -73,7 +68,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #else /* DEBUG_SPINLOCK */ #define arch_spin_is_locked(lock) ((void)(lock), 0) -#define arch_spin_unlock_wait(lock) do { barrier(); (void)(lock); } while (0) /* for sched/core.c and kernel_lock.c: */ # define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0) # define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0) -- cgit v1.2.3 From c8c03f1858331e85d397bacccd34ef409aae993c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 16 Aug 2017 17:08:07 -0700 Subject: pty: fix the cached path of the pty slave file descriptor in the master Christian Brauner reported that if you use the TIOCGPTPEER ioctl() to get a slave pty file descriptor, the resulting file descriptor doesn't look right in /proc//fd/. In particular, he wanted to use readlink() on /proc/self/fd/ to get the pathname of the slave pty (basically implementing "ptsname{_r}()"). The reason for that was that we had generated the wrong 'struct path' when we create the pty in ptmx_open(). In particular, the dentry was correct, but the vfsmount pointed to the mount of the ptmx node. That _can_ be correct - in case you use "/dev/pts/ptmx" to open the master - but usually is not. The normal case is to use /dev/ptmx, which then looks up the pts/ directory, and then the vfsmount of the ptmx node is obviously the /dev directory, not the /dev/pts/ directory. We actually did have the right vfsmount available, but in the wrong place (it gets looked up in 'devpts_acquire()' when we get a reference to the pts filesystem), and so ptmx_open() used the wrong mnt pointer. The end result of this confusion was that the pty worked fine, but when if you did TIOCGPTPEER to get the slave side of the pty, end end result would also work, but have that dodgy 'struct path'. And then when doing "d_path()" on to get the pathname, the vfsmount would not match the root of the pts directory, and d_path() would return an empty pathname thinking that the entry had escaped a bind mount into another mount. This fixes the problem by making devpts_acquire() return the vfsmount for the pts filesystem, allowing ptmx_open() to trivially just use the right mount for the pts dentry, and create the proper 'struct path'. Reported-by: Christian Brauner Cc: Al Viro Acked-by: Eric Biederman Signed-off-by: Linus Torvalds --- include/linux/devpts_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 277ab9af9ac2..7883e901f65c 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,7 +19,7 @@ struct pts_fs_info; -struct pts_fs_info *devpts_acquire(struct file *); +struct pts_fs_info *devpts_acquire(struct file *, struct vfsmount **ptsmnt); void devpts_release(struct pts_fs_info *); int devpts_new_index(struct pts_fs_info *); -- cgit v1.2.3 From bc8230ee8e2ba967af780cdaf2dcc0f8e5eb45ca Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 8 Jun 2017 14:39:48 +0200 Subject: quota: Convert dqio_mutex to rwsem Convert dqio_mutex to rwsem and call it dqio_sem. No functional changes yet. Signed-off-by: Jan Kara --- include/linux/quota.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index bfd077ca6ac3..3a6df7461642 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -521,7 +521,7 @@ static inline void quota_send_warning(struct kqid qid, dev_t dev, struct quota_info { unsigned int flags; /* Flags for diskquotas on this device */ - struct mutex dqio_mutex; /* lock device while I/O in progress */ + struct rw_semaphore dqio_sem; /* Lock quota file while I/O in progress */ struct inode *files[MAXQUOTAS]; /* inodes of quotafiles */ struct mem_dqinfo info[MAXQUOTAS]; /* Information for each quota type */ const struct quota_format_ops *ops[MAXQUOTAS]; /* Operations for each type */ -- cgit v1.2.3 From 5d72801538eb59cfd9ca25d00aa439cfbc02ac9a Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Thu, 17 Aug 2017 13:32:37 -0400 Subject: lsm_audit: update my email address Update my email address since epoch.ncsc.mil no longer exists. MAINTAINERS and CREDITS are already correct. Signed-off-by: Stephen Smalley Signed-off-by: Paul Moore --- include/linux/lsm_audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 22b5d4e687ce..d1c2901f1542 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -4,7 +4,7 @@ * * Author : Etienne BASSET * - * All credits to : Stephen Smalley, + * All credits to : Stephen Smalley, * All BUGS to : Etienne BASSET */ #ifndef _LSM_COMMON_LOGGING_ -- cgit v1.2.3 From 503330f3820fab13aa2a7b1f9e7633686acc7c79 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 2 Aug 2017 17:18:50 +0200 Subject: quota: Remove dq_wait_unused from dquot Currently every dquot carries a wait_queue_head_t used only when we are turning quotas off to wait for last users to drop dquot references. Since such rare case is not performance sensitive in any means, just use a global waitqueue for this and save space in struct dquot. Also convert the logic to use wait_event() instead of open-coding it. Signed-off-by: Jan Kara --- include/linux/quota.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 3a6df7461642..ad6809f099ac 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -299,7 +299,6 @@ struct dquot { struct list_head dq_dirty; /* List of dirty dquots */ struct mutex dq_lock; /* dquot IO lock */ atomic_t dq_count; /* Use count */ - wait_queue_head_t dq_wait_unused; /* Wait queue for dquot to become unused */ struct super_block *dq_sb; /* superblock this applies to */ struct kqid dq_id; /* ID this applies to (uid, gid, projid) */ loff_t dq_off; /* Offset of dquot on disk */ -- cgit v1.2.3 From 834057bf846691552a8906f7ed3f67546e5f897c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 3 Aug 2017 11:18:23 +0200 Subject: quota: Allow disabling tracking of dirty dquots in a list Filesystems that are journalling quotas generally don't need tracking of dirty dquots in a list since forcing a transaction commit flushes all quotas anyway. Allow filesystem to say it doesn't want dquots to be tracked as it reduces contention on the dq_list_lock. Signed-off-by: Jan Kara --- include/linux/quota.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index ad6809f099ac..eccc1cb6274e 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -490,6 +490,9 @@ enum { */ #define DQUOT_NEGATIVE_USAGE (1 << (DQUOT_STATE_LAST + 1)) /* Allow negative quota usage */ +/* Do not track dirty dquots in a list */ +#define DQUOT_NOLIST_DIRTY (1 << (DQUOT_STATE_LAST + 2)) + static inline unsigned int dquot_state_flag(unsigned int flags, int type) { return flags << type; -- cgit v1.2.3 From 0ed60de34a975804a256fb3fe233b1466c603be6 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Aug 2017 17:07:28 +0200 Subject: quota: Inline functions into their callsites inode_add_rsv_space() and inode_sub_rsv_space() had only one callsite. Inline them there directly. inode_claim_rsv_space() and inode_reclaim_rsv_space() had two callsites so inline them there as well. This will simplify further locking changes. Signed-off-by: Jan Kara --- include/linux/quotaops.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h index dda22f45fc1b..0ce6fc49962e 100644 --- a/include/linux/quotaops.h +++ b/include/linux/quotaops.h @@ -38,11 +38,6 @@ void __quota_error(struct super_block *sb, const char *func, /* * declaration of quota_function calls in kernel. */ -void inode_add_rsv_space(struct inode *inode, qsize_t number); -void inode_claim_rsv_space(struct inode *inode, qsize_t number); -void inode_sub_rsv_space(struct inode *inode, qsize_t number); -void inode_reclaim_rsv_space(struct inode *inode, qsize_t number); - int dquot_initialize(struct inode *inode); bool dquot_initialize_needed(struct inode *inode); void dquot_drop(struct inode *inode); -- cgit v1.2.3 From f4a8116a4c8c8f754d0ec1498a2ba4b63d114e6a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 8 Aug 2017 09:54:36 +0200 Subject: fs: Provide __inode_get_bytes() Provide helper __inode_get_bytes() which assumes i_lock is already acquired. Quota code will need this to be able to use i_lock to protect consistency of quota accounting information and inode usage. Signed-off-by: Jan Kara --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e1fd5d21248..d6e9ab7f184f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2998,6 +2998,10 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); +static inline loff_t __inode_get_bytes(struct inode *inode) +{ + return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; +} loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, -- cgit v1.2.3 From 7b9ca4c61bc278b771fb57d6290a31ab1fc7fdac Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 7 Aug 2017 13:19:50 +0200 Subject: quota: Reduce contention on dq_data_lock dq_data_lock is currently used to protect all modifications of quota accounting information, consistency of quota accounting on the inode, and dquot pointers from inode. As a result contention on the lock can be pretty heavy. Reduce the contention on the lock by protecting quota accounting information by a new dquot->dq_dqb_lock and consistency of quota accounting with inode usage by inode->i_lock. This change reduces time to create 500000 files on ext4 on ramdisk by 50 different processes in separate directories by 6% when user quota is turned on. When those 50 processes belong to 50 different users, the improvement is about 9%. Signed-off-by: Jan Kara --- include/linux/quota.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index eccc1cb6274e..074123975595 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -298,12 +298,13 @@ struct dquot { struct list_head dq_free; /* Free list element */ struct list_head dq_dirty; /* List of dirty dquots */ struct mutex dq_lock; /* dquot IO lock */ + spinlock_t dq_dqb_lock; /* Lock protecting dq_dqb changes */ atomic_t dq_count; /* Use count */ struct super_block *dq_sb; /* superblock this applies to */ struct kqid dq_id; /* ID this applies to (uid, gid, projid) */ loff_t dq_off; /* Offset of dquot on disk */ unsigned long dq_flags; /* See DQ_* */ - struct mem_dqblk dq_dqb; /* Diskquota usage */ + struct mem_dqblk dq_dqb; /* Diskquota usage [dq_dqb_lock] */ }; /* Operations which must be implemented by each quota format */ -- cgit v1.2.3 From c71b02e4d207cbcf097f9746d5f7967b22905e70 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 9 Aug 2017 21:11:00 -0700 Subject: Revert "pstore: Honor dmesg_restrict sysctl on dmesg dumps" This reverts commit 68c4a4f8abc60c9440ede9cd123d48b78325f7a3, with various conflict clean-ups. The capability check required too much privilege compared to simple DAC controls. A system builder was forced to have crash handler processes run with CAP_SYSLOG which would give it the ability to read (and wipe) the _current_ dmesg, which is much more access than being given access only to the historical log stored in pstorefs. With the prior commit to make the root directory 0750, the files are protected by default but a system builder can now opt to give access to a specific group (via chgrp on the pstorefs root directory) without being forced to also give away CAP_SYSLOG. Suggested-by: Nick Kralevich Signed-off-by: Kees Cook Reviewed-by: Petr Mladek Reviewed-by: Sergey Senozhatsky --- include/linux/syslog.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syslog.h b/include/linux/syslog.h index c3a7f0cc3a27..e1c3632f4e81 100644 --- a/include/linux/syslog.h +++ b/include/linux/syslog.h @@ -49,13 +49,4 @@ int do_syslog(int type, char __user *buf, int count, int source); -#ifdef CONFIG_PRINTK -int check_syslog_permissions(int type, int source); -#else -static inline int check_syslog_permissions(int type, int source) -{ - return 0; -} -#endif - #endif /* _LINUX_SYSLOG_H */ -- cgit v1.2.3 From 726fb6b4f2a82a14a906f39bdabac4863b87c01a Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Tue, 15 Aug 2017 18:16:59 -0700 Subject: ACPI / PM: Check low power idle constraints for debug only For SoC to achieve its lowest power platform idle state a set of hardware preconditions must be met. These preconditions or constraints can be obtained by issuing a device specific method (_DSM) with function "1". Refer to the document provided in the link below. Here during initialization (from attach() callback of LPS0 device), invoke function 1 to get the device constraints. Each enabled constraint is stored in a table. The devices in this table are used to check whether they were in required minimum state, while entering suspend. This check is done from platform freeze wake() callback, only when /sys/power/pm_debug_messages attribute is non zero. If any constraint is not met and device is ACPI power managed then it prints the device information to kernel logs. Also if debug is enabled in acpi/sleep.c, the constraint table and state of each device on wake is dumped in kernel logs. Since pm_debug_messages_on setting is used as condition to check constraints outside kernel/power/main.c, pm_debug_messages_on is changed to a global variable. Link: http://www.uefi.org/sites/default/files/resources/Intel_ACPI_Low_Power_S0_Idle.pdf Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 0d41daf7e89d..d10b7980799d 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -495,9 +495,11 @@ static inline void unlock_system_sleep(void) {} #ifdef CONFIG_PM_SLEEP_DEBUG extern bool pm_print_times_enabled; +extern bool pm_debug_messages_on; extern __printf(2, 3) void __pm_pr_dbg(bool defer, const char *fmt, ...); #else #define pm_print_times_enabled (false) +#define pm_debug_messages_on (false) #include -- cgit v1.2.3 From 74def747bcd09692bdbf8c6a15350795b0f11ca8 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 18 Aug 2017 09:39:14 +0100 Subject: genirq: Restrict effective affinity to interrupts actually using it Just because CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK is selected doesn't mean that all the interrupts are using the effective affinity mask. For a number of them, this mask is likely to be empty. In order to deal with this, let's restrict the use of the effective affinity mask to these interrupts that have a non empty effective affinity. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Cc: Andrew Lunn Cc: James Hogan Cc: Jason Cooper Cc: Paul Burton Cc: Chris Zankel Cc: Kevin Cernekee Cc: Wei Xu Cc: Max Filippov Cc: Florian Fainelli Cc: Gregory Clement Cc: Matt Redfearn Cc: Sebastian Hesselbarth Link: http://lkml.kernel.org/r/20170818083925.10108-2-marc.zyngier@arm.com --- include/linux/irq.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index d2d543794093..dcfac6c8ba18 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -781,7 +781,10 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) static inline struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) { - return d->common->effective_affinity; + if (!cpumask_empty(d->common->effective_affinity)) + return d->common->effective_affinity; + + return d->common->affinity; } static inline void irq_data_update_effective_affinity(struct irq_data *d, const struct cpumask *m) -- cgit v1.2.3 From 7703b08cc93b3586f9eb733f3a2b10bed634a5cf Mon Sep 17 00:00:00 2001 From: David Daney Date: Thu, 17 Aug 2017 17:53:31 -0700 Subject: genirq: Add handle_fasteoi_{level,edge}_irq flow handlers Follow-on patch for gpio-thunderx uses a irqdomain hierarchy which requires slightly different flow handlers, add them to chip.c which contains most of the other flow handlers. Make these conditionally compiled based on CONFIG_IRQ_FASTEOI_HIERARCHY_HANDLERS. Signed-off-by: David Daney Signed-off-by: Thomas Gleixner Cc: Mark Rutland Cc: Alexandre Courbot Cc: Marc Zyngier Cc: Linus Walleij Cc: linux-gpio@vger.kernel.org Link: http://lkml.kernel.org/r/1503017616-3252-3-git-send-email-david.daney@cavium.com --- include/linux/irq.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index d2d543794093..d4728bf6a537 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -568,6 +568,8 @@ extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); extern int irq_chip_pm_get(struct irq_data *data); extern int irq_chip_pm_put(struct irq_data *data); #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +extern void handle_fasteoi_ack_irq(struct irq_desc *desc); +extern void handle_fasteoi_mask_irq(struct irq_desc *desc); extern void irq_chip_enable_parent(struct irq_data *data); extern void irq_chip_disable_parent(struct irq_data *data); extern void irq_chip_ack_parent(struct irq_data *data); -- cgit v1.2.3 From 495c38d3001fd226cf91df1d031320f349bcaf35 Mon Sep 17 00:00:00 2001 From: David Daney Date: Thu, 17 Aug 2017 17:53:34 -0700 Subject: irqdomain: Add irq_domain_{push,pop}_irq() functions For an already existing irqdomain hierarchy, as might be obtained via a call to pci_enable_msix_range(), a PCI driver wishing to add an additional irqdomain to the hierarchy needs to be able to insert the irqdomain to that already initialized hierarchy. Calling irq_domain_create_hierarchy() allows the new irqdomain to be created, but no existing code allows for initializing the associated irq_data. Add a couple of helper functions (irq_domain_push_irq() and irq_domain_pop_irq()) to initialize the irq_data for the new irqdomain added to an existing hierarchy. Signed-off-by: David Daney Signed-off-by: Thomas Gleixner Reviewed-by: Marc Zyngier Cc: Mark Rutland Cc: Alexandre Courbot Cc: Linus Walleij Cc: linux-gpio@vger.kernel.org Link: http://lkml.kernel.org/r/1503017616-3252-6-git-send-email-david.daney@cavium.com --- include/linux/irqdomain.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index cac77a5c5555..2318f29054af 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -460,6 +460,9 @@ extern void irq_domain_free_irqs_common(struct irq_domain *domain, extern void irq_domain_free_irqs_top(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); +extern int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg); +extern int irq_domain_pop_irq(struct irq_domain *domain, int virq); + extern int irq_domain_alloc_irqs_parent(struct irq_domain *domain, unsigned int irq_base, unsigned int nr_irqs, void *arg); -- cgit v1.2.3 From 7edaeb6841dfb27e362288ab8466ebdc4972e867 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Aug 2017 09:50:13 +0200 Subject: kernel/watchdog: Prevent false positives with turbo modes The hardlockup detector on x86 uses a performance counter based on unhalted CPU cycles and a periodic hrtimer. The hrtimer period is about 2/5 of the performance counter period, so the hrtimer should fire 2-3 times before the performance counter NMI fires. The NMI code checks whether the hrtimer fired since the last invocation. If not, it assumess a hard lockup. The calculation of those periods is based on the nominal CPU frequency. Turbo modes increase the CPU clock frequency and therefore shorten the period of the perf/NMI watchdog. With extreme Turbo-modes (3x nominal frequency) the perf/NMI period is shorter than the hrtimer period which leads to false positives. A simple fix would be to shorten the hrtimer period, but that comes with the side effect of more frequent hrtimer and softlockup thread wakeups, which is not desired. Implement a low pass filter, which checks the perf/NMI period against kernel time. If the perf/NMI fires before 4/5 of the watchdog period has elapsed then the event is ignored and postponed to the next perf/NMI. That solves the problem and avoids the overhead of shorter hrtimer periods and more frequent softlockup thread wakeups. Fixes: 58687acba592 ("lockup_detector: Combine nmi_watchdog and softlockup detector") Reported-and-tested-by: Kan Liang Signed-off-by: Thomas Gleixner Cc: dzickus@redhat.com Cc: prarit@redhat.com Cc: ak@linux.intel.com Cc: babu.moger@oracle.com Cc: peterz@infradead.org Cc: eranian@google.com Cc: acme@redhat.com Cc: stable@vger.kernel.org Cc: atomlin@redhat.com Cc: akpm@linux-foundation.org Cc: torvalds@linux-foundation.org Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1708150931310.1886@nanos --- include/linux/nmi.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 8aa01fd859fb..a36abe2da13e 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -168,6 +168,14 @@ extern int sysctl_hardlockup_all_cpu_backtrace; #define sysctl_softlockup_all_cpu_backtrace 0 #define sysctl_hardlockup_all_cpu_backtrace 0 #endif + +#if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ + defined(CONFIG_HARDLOCKUP_DETECTOR) +void watchdog_update_hrtimer_threshold(u64 period); +#else +static inline void watchdog_update_hrtimer_threshold(u64 period) { } +#endif + extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , -- cgit v1.2.3 From d352ae205d8b05f3f7558d10f474d8436581b3e2 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Thu, 17 Aug 2017 16:23:03 -0700 Subject: blk-mq: Make blk_mq_reinit_tagset() calls easier to read Since blk_mq_ops.reinit_request is only called from inside blk_mq_reinit_tagset(), make this function pointer an argument of blk_mq_reinit_tagset() instead of a member of struct blk_mq_ops. This patch does not change any functionality but makes blk_mq_reinit_tagset() calls easier to read and to analyze. Signed-off-by: Bart Van Assche Reviewed-by: Hannes Reinecke Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: James Smart Cc: Johannes Thumshirn Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 14542308d25b..50c6485cb04f 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -97,7 +97,6 @@ typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *, unsigned int, unsigned int); typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *, unsigned int); -typedef int (reinit_request_fn)(void *, struct request *); typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); @@ -143,7 +142,6 @@ struct blk_mq_ops { */ init_request_fn *init_request; exit_request_fn *exit_request; - reinit_request_fn *reinit_request; /* Called from inside blk_get_request() */ void (*initialize_rq_fn)(struct request *rq); @@ -261,7 +259,8 @@ void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); -int blk_mq_reinit_tagset(struct blk_mq_tag_set *set); +int blk_mq_reinit_tagset(struct blk_mq_tag_set *set, + int (reinit_request)(void *, struct request *)); int blk_mq_map_queues(struct blk_mq_tag_set *set); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); -- cgit v1.2.3 From e1cba4b85daa71b710384d451ff6238d5e4d1ff6 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 17 Aug 2017 15:33:09 -0400 Subject: cgroup: Add mount flag to enable cpuset to use v2 behavior in v1 cgroup A new mount option "cpuset_v2_mode" is added to the v1 cgroupfs filesystem to enable cpuset controller to use v2 behavior in a v1 cgroup. This mount option applies only to cpuset controller and have no effect on other controllers. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 59e4ad9e7bac..ade4a78a54c2 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -74,6 +74,11 @@ enum { * aren't writeable from inside the namespace. */ CGRP_ROOT_NS_DELEGATE = (1 << 3), + + /* + * Enable cpuset controller in v1 cgroup to use v2 behavior. + */ + CGRP_ROOT_CPUSET_V2_MODE = (1 << 4), }; /* cftype->flags */ -- cgit v1.2.3 From f01f969e25ecc6f88844bcdd63f1f27610418bbc Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Fri, 18 Aug 2017 20:27:54 +0530 Subject: PCI: endpoint: Add an API to get matching "pci_epf_device_id" Add an API to get "pci_epf_device_id" matching the EPF name. This can be used by the EPF driver to get the driver data corresponding to the EPF device name. Signed-off-by: Kishon Vijay Abraham I [bhelgaas: folded in "while" loop termination fix from Colin Ian King ] Signed-off-by: Bjorn Helgaas --- include/linux/pci-epf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index 0d529cb90143..6ed63b5e106b 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -149,6 +149,8 @@ static inline void *epf_get_drvdata(struct pci_epf *epf) return dev_get_drvdata(&epf->dev); } +const struct pci_epf_device_id * +pci_epf_match_device(const struct pci_epf_device_id *id, struct pci_epf *epf); struct pci_epf *pci_epf_create(const char *name); void pci_epf_destroy(struct pci_epf *epf); int __pci_epf_register_driver(struct pci_epf_driver *driver, -- cgit v1.2.3 From 300238cecede382fbd9084499e57f3b30acc75fa Mon Sep 17 00:00:00 2001 From: Gustavo Padovan Date: Mon, 31 Jul 2017 16:36:55 -0300 Subject: dma-buf/sync_file: document flags field Documentation for it was missing. Signed-off-by: Gustavo Padovan Acked-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20170731193655.6176-1-gustavo@padovan.org --- include/linux/sync_file.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sync_file.h b/include/linux/sync_file.h index 0ad87c434ae6..790ca021203a 100644 --- a/include/linux/sync_file.h +++ b/include/linux/sync_file.h @@ -25,8 +25,12 @@ * @file: file representing this fence * @sync_file_list: membership in global file list * @wq: wait queue for fence signaling + * @flags: flags for the sync_file * @fence: fence with the fences in the sync_file * @cb: fence callback information + * + * flags: + * POLL_ENABLED: whether userspace is currently poll()'ing or not */ struct sync_file { struct file *file; -- cgit v1.2.3 From 92d50fc1602ecef44babe411c475344e55e1cdd9 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 19 Jul 2017 15:01:06 +0200 Subject: PCI/IB: add support for pci driver attribute groups Some drivers (specifically the nes IB driver), want to create a lot of sysfs driver attributes. Instead of open-coding the creation and removal of these files (and getting it wrong btw), it's a better idea to let the driver core handle all of this logic for us. So add a new field to the pci driver structure, **groups, that allows pci drivers to specify an attribute group list it wishes to have created when it is registered with the driver core. Big bonus is now the driver doesn't race with userspace when the sysfs files are created vs. when the kobject is announced, so any script/tool that actually wanted to use these files will not have to poll waiting for them to show up. Cc: Faisal Latif Cc: Doug Ledford Cc: Sean Hefty Cc: Hal Rosenstock Cc: Bjorn Helgaas Signed-off-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas Signed-off-by: Doug Ledford --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659..c421af60f2df 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -729,6 +729,7 @@ struct pci_driver { void (*shutdown) (struct pci_dev *dev); int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* PF pdev */ const struct pci_error_handlers *err_handler; + const struct attribute_group **groups; struct device_driver driver; struct pci_dynids dynids; }; -- cgit v1.2.3 From ce7c252a8c741aba7c38f817b86e34361f561e42 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 16 Aug 2017 15:30:35 -0400 Subject: SUNRPC: Add a separate spinlock to protect the RPC request receive list This further reduces contention with the transport_lock, and allows us to convert to using a non-bh-safe spinlock, since the list is now never accessed from a bh context. Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 65b9e0224753..a97e6de5f9f2 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -232,6 +232,7 @@ struct rpc_xprt { */ spinlock_t transport_lock; /* lock transport info */ spinlock_t reserve_lock; /* lock slot table */ + spinlock_t recv_lock; /* lock receive list */ u32 xid; /* Next XID value to use */ struct rpc_task * snd_task; /* Task blocked in send */ struct svc_xprt *bc_xprt; /* NFSv4.1 backchannel */ -- cgit v1.2.3 From 739f79fc9db1b38f96b5a5109b247a650fbebf6d Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 18 Aug 2017 15:15:48 -0700 Subject: mm: memcontrol: fix NULL pointer crash in test_clear_page_writeback() Jaegeuk and Brad report a NULL pointer crash when writeback ending tries to update the memcg stats: BUG: unable to handle kernel NULL pointer dereference at 00000000000003b0 IP: test_clear_page_writeback+0x12e/0x2c0 [...] RIP: 0010:test_clear_page_writeback+0x12e/0x2c0 Call Trace: end_page_writeback+0x47/0x70 f2fs_write_end_io+0x76/0x180 [f2fs] bio_endio+0x9f/0x120 blk_update_request+0xa8/0x2f0 scsi_end_request+0x39/0x1d0 scsi_io_completion+0x211/0x690 scsi_finish_command+0xd9/0x120 scsi_softirq_done+0x127/0x150 __blk_mq_complete_request_remote+0x13/0x20 flush_smp_call_function_queue+0x56/0x110 generic_smp_call_function_single_interrupt+0x13/0x30 smp_call_function_single_interrupt+0x27/0x40 call_function_single_interrupt+0x89/0x90 RIP: 0010:native_safe_halt+0x6/0x10 (gdb) l *(test_clear_page_writeback+0x12e) 0xffffffff811bae3e is in test_clear_page_writeback (./include/linux/memcontrol.h:619). 614 mod_node_page_state(page_pgdat(page), idx, val); 615 if (mem_cgroup_disabled() || !page->mem_cgroup) 616 return; 617 mod_memcg_state(page->mem_cgroup, idx, val); 618 pn = page->mem_cgroup->nodeinfo[page_to_nid(page)]; 619 this_cpu_add(pn->lruvec_stat->count[idx], val); 620 } 621 622 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, 623 gfp_t gfp_mask, The issue is that writeback doesn't hold a page reference and the page might get freed after PG_writeback is cleared (and the mapping is unlocked) in test_clear_page_writeback(). The stat functions looking up the page's node or zone are safe, as those attributes are static across allocation and free cycles. But page->mem_cgroup is not, and it will get cleared if we race with truncation or migration. It appears this race window has been around for a while, but less likely to trigger when the memcg stats were updated first thing after PG_writeback is cleared. Recent changes reshuffled this code to update the global node stats before the memcg ones, though, stretching the race window out to an extent where people can reproduce the problem. Update test_clear_page_writeback() to look up and pin page->mem_cgroup before clearing PG_writeback, then not use that pointer afterward. It is a partial revert of 62cccb8c8e7a ("mm: simplify lock_page_memcg()") but leaves the pageref-holding callsites that aren't affected alone. Link: http://lkml.kernel.org/r/20170809183825.GA26387@cmpxchg.org Fixes: 62cccb8c8e7a ("mm: simplify lock_page_memcg()") Signed-off-by: Johannes Weiner Reported-by: Jaegeuk Kim Tested-by: Jaegeuk Kim Reported-by: Bradley Bolen Tested-by: Brad Bolen Cc: Vladimir Davydov Cc: Michal Hocko Cc: [4.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3914e3dd6168..9b15a4bcfa77 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -484,7 +484,8 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -void lock_page_memcg(struct page *page); +struct mem_cgroup *lock_page_memcg(struct page *page); +void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, @@ -809,7 +810,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline void lock_page_memcg(struct page *page) +static inline struct mem_cgroup *lock_page_memcg(struct page *page) +{ + return NULL; +} + +static inline void __unlock_page_memcg(struct mem_cgroup *memcg) { } -- cgit v1.2.3 From 8ada92799ec4de00f4bc0f10b1ededa256c1ab22 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Fri, 18 Aug 2017 15:15:55 -0700 Subject: wait: add wait_event_killable_timeout() These are the few pending fixes I have queued up for v4.13-final. One is a a generic regression fix for recursive loops on kmod and the other one is a trivial print out correction. During the v4.13 development we assumed that recursive kmod loops were no longer possible. Clearly that is not true. The regression fix makes use of a new killable wait. We use a killable wait to be paranoid in how signals might be sent to modprobe and only accept a proper SIGKILL. The signal will only be available to userspace to issue *iff* a thread has already entered a wait state, and that happens only if we've already throttled after 50 kmod threads have been hit. Note that although it may seem excessive to trigger a failure afer 5 seconds if all kmod thread remain busy, prior to the series of changes that went into v4.13 we would actually *always* fatally fail any request which came in if the limit was already reached. The new waiting implemented in v4.13 actually gives us *more* breathing room -- the wait for 5 seconds is a wait for *any* kmod thread to finish. We give up and fail *iff* no kmod thread has finished and they're *all* running straight for 5 consecutive seconds. If 50 kmod threads are running consecutively for 5 seconds something else must be really bad. Recursive loops with kmod are bad but they're also hard to implement properly as a selftest without currently fooling current userspace tools like kmod [1]. For instance kmod will complain when you run depmod if it finds a recursive loop with symbol dependency between modules as such this type of recursive loop cannot go upstream as the modules_install target will fail after running depmod. These tests already exist on userspace kmod upstream though (refer to the testsuite/module-playground/mod-loop-*.c files). The same is not true if request_module() is used though, or worst if aliases are used. Likewise the issue with 64-bit kernels booting 32-bit userspace without a binfmt handler built-in is also currently not detected and proactively avoided by userspace kmod tools, or kconfig for all architectures. Although we could complain in the kernel when some of these individual recursive issues creep up, proactively avoiding these situations in userspace at build time is what we should keep striving for. Lastly, since recursive loops could happen with kmod it may mean recursive loops may also be possible with other kernel usermode helpers, this should be investigated and long term if we can come up with a more sensible generic solution even better! [0] https://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux.git/log/?h=20170809-kmod-for-v4.13-final [1] https://git.kernel.org/pub/scm/utils/kernel/kmod/kmod.git This patch (of 3): This wait is similar to wait_event_interruptible_timeout() but only accepts SIGKILL interrupt signal. Other signals are ignored. Link: http://lkml.kernel.org/r/20170809234635.13443-2-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Acked-by: Peter Zijlstra (Intel) Cc: Ingo Molnar Cc: Kees Cook Cc: Dmitry Torokhov Cc: Jessica Yu Cc: Rusty Russell Cc: Michal Marek Cc: Petr Mladek Cc: Miroslav Benes Cc: Josh Poimboeuf Cc: "Eric W. Biederman" Cc: Shuah Khan Cc: Matt Redfearn Cc: Dan Carpenter Cc: Colin Ian King Cc: Daniel Mentz Cc: David Binderman Cc: Matt Redfearn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/wait.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 5b74e36c0ca8..dc19880c02f5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -757,6 +757,43 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); __ret; \ }) +#define __wait_event_killable_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_KILLABLE, 0, timeout, \ + __ret = schedule_timeout(__ret)) + +/** + * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses + * @wq_head: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, in jiffies + * + * The process is put to sleep (TASK_KILLABLE) until the + * @condition evaluates to true or a kill signal is received. + * The @condition is checked each time the waitqueue @wq_head is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * Returns: + * 0 if the @condition evaluated to %false after the @timeout elapsed, + * 1 if the @condition evaluated to %true after the @timeout elapsed, + * the remaining jiffies (at least 1) if the @condition evaluated + * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was + * interrupted by a kill signal. + * + * Only kill signals interrupt this process. + */ +#define wait_event_killable_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_killable_timeout(wq_head, \ + condition, timeout); \ + __ret; \ +}) + #define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ -- cgit v1.2.3 From 3010f876500f9ba921afaeccec30c45ca6584dc8 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 18 Aug 2017 15:16:05 -0700 Subject: mm: discard memblock data later There is existing use after free bug when deferred struct pages are enabled: The memblock_add() allocates memory for the memory array if more than 128 entries are needed. See comment in e820__memblock_setup(): * The bootstrap memblock region count maximum is 128 entries * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries * than that - so allow memblock resizing. This memblock memory is freed here: free_low_memory_core_early() We access the freed memblock.memory later in boot when deferred pages are initialized in this path: deferred_init_memmap() for_each_mem_pfn_range() __next_mem_pfn_range() type = &memblock.memory; One possible explanation for why this use-after-free hasn't been hit before is that the limit of INIT_MEMBLOCK_REGIONS has never been exceeded at least on systems where deferred struct pages were enabled. Tested by reducing INIT_MEMBLOCK_REGIONS down to 4 from the current 128, and verifying in qemu that this code is getting excuted and that the freed pages are sane. Link: http://lkml.kernel.org/r/1502485554-318703-2-git-send-email-pasha.tatashin@oracle.com Fixes: 7e18adb4f80b ("mm: meminit: initialise remaining struct pages in parallel with kswapd") Signed-off-by: Pavel Tatashin Reviewed-by: Steven Sistare Reviewed-by: Daniel Jordan Reviewed-by: Bob Picco Acked-by: Michal Hocko Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 77d427974f57..bae11c7e7bf3 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -61,6 +61,7 @@ extern int memblock_debug; #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK #define __init_memblock __meminit #define __initdata_memblock __meminitdata +void memblock_discard(void); #else #define __init_memblock #define __initdata_memblock @@ -74,8 +75,6 @@ phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, int nid, ulong flags); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); -phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr); -phys_addr_t get_allocated_memblock_memory_regions_info(phys_addr_t *addr); void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); @@ -110,6 +109,9 @@ void __next_mem_range_rev(u64 *idx, int nid, ulong flags, void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, phys_addr_t *out_end); +void __memblock_free_early(phys_addr_t base, phys_addr_t size); +void __memblock_free_late(phys_addr_t base, phys_addr_t size); + /** * for_each_mem_range - iterate through memblock areas from type_a and not * included in type_b. Or just type_a if type_b is NULL. -- cgit v1.2.3 From 6b31d5955cb29a51c5baffee382f213d75e98fb8 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 18 Aug 2017 15:16:15 -0700 Subject: mm, oom: fix potential data corruption when oom_reaper races with writer Wenwei Tao has noticed that our current assumption that the oom victim is dying and never doing any visible changes after it dies, and so the oom_reaper can tear it down, is not entirely true. __task_will_free_mem consider a task dying when SIGNAL_GROUP_EXIT is set but do_group_exit sends SIGKILL to all threads _after_ the flag is set. So there is a race window when some threads won't have fatal_signal_pending while the oom_reaper could start unmapping the address space. Moreover some paths might not check for fatal signals before each PF/g-u-p/copy_from_user. We already have a protection for oom_reaper vs. PF races by checking MMF_UNSTABLE. This has been, however, checked only for kernel threads (use_mm users) which can outlive the oom victim. A simple fix would be to extend the current check in handle_mm_fault for all tasks but that wouldn't be sufficient because the current check assumes that a kernel thread would bail out after EFAULT from get_user*/copy_from_user and never re-read the same address which would succeed because the PF path has established page tables already. This seems to be the case for the only existing use_mm user currently (virtio driver) but it is rather fragile in general. This is even more fragile in general for more complex paths such as generic_perform_write which can re-read the same address more times (e.g. iov_iter_copy_from_user_atomic to fail and then iov_iter_fault_in_readable on retry). Therefore we have to implement MMF_UNSTABLE protection in a robust way and never make a potentially corrupted content visible. That requires to hook deeper into the PF path and check for the flag _every time_ before a pte for anonymous memory is established (that means all !VM_SHARED mappings). The corruption can be triggered artificially (http://lkml.kernel.org/r/201708040646.v746kkhC024636@www262.sakura.ne.jp) but there doesn't seem to be any real life bug report. The race window should be quite tight to trigger most of the time. Link: http://lkml.kernel.org/r/20170807113839.16695-3-mhocko@kernel.org Fixes: aac453635549 ("mm, oom: introduce oom reaper") Signed-off-by: Michal Hocko Reported-by: Wenwei Tao Tested-by: Tetsuo Handa Cc: "Kirill A. Shutemov" Cc: Andrea Argangeli Cc: David Rientjes Cc: Oleg Nesterov Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/oom.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/oom.h b/include/linux/oom.h index 8a266e2be5a6..76aac4ce39bc 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -6,6 +6,8 @@ #include #include #include +#include /* MMF_* */ +#include /* VM_FAULT* */ struct zonelist; struct notifier_block; @@ -63,6 +65,26 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk) return tsk->signal->oom_mm; } +/* + * Checks whether a page fault on the given mm is still reliable. + * This is no longer true if the oom reaper started to reap the + * address space which is reflected by MMF_UNSTABLE flag set in + * the mm. At that moment any !shared mapping would lose the content + * and could cause a memory corruption (zero pages instead of the + * original content). + * + * User should call this before establishing a page table entry for + * a !shared mapping and under the proper page table lock. + * + * Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise. + */ +static inline int check_stable_address_space(struct mm_struct *mm) +{ + if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags))) + return VM_FAULT_SIGBUS; + return 0; +} + extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); -- cgit v1.2.3 From 606c07f3086017a8c2d7ce0843807e81b541edcc Mon Sep 17 00:00:00 2001 From: "Lendacky, Thomas" Date: Fri, 18 Aug 2017 09:03:44 -0500 Subject: net: ethtool: Add macro to clear a link mode setting There are currently macros to set and test an ETHTOOL_LINK_MODE_ setting, but not to clear one. Add a macro to clear an ETHTOOL_LINK_MODE_ setting. Signed-off-by: Tom Lendacky Signed-off-by: David S. Miller --- include/linux/ethtool.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index afdbb701fdb4..4587a4c36923 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -136,6 +136,17 @@ struct ethtool_link_ksettings { #define ethtool_link_ksettings_add_link_mode(ptr, name, mode) \ __set_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) +/** + * ethtool_link_ksettings_del_link_mode - clear bit in link_ksettings + * link mode mask + * @ptr : pointer to struct ethtool_link_ksettings + * @name : one of supported/advertising/lp_advertising + * @mode : one of the ETHTOOL_LINK_MODE_*_BIT + * (not atomic, no bound checking) + */ +#define ethtool_link_ksettings_del_link_mode(ptr, name, mode) \ + __clear_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) + /** * ethtool_link_ksettings_test_link_mode - test bit in ksettings link mode mask * @ptr : pointer to struct ethtool_link_ksettings -- cgit v1.2.3 From b793dc5c6edfb106fd57d12ad6aca64bf160b403 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 18 Aug 2017 13:46:20 -0700 Subject: net: constify netdev_class_file These functions are wrapper arount class_create_file which can take a const attribute. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0f1c4cb2441e..eaa77bd9cb80 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4013,17 +4013,17 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi return rc; } -int netdev_class_create_file_ns(struct class_attribute *class_attr, +int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns); -void netdev_class_remove_file_ns(struct class_attribute *class_attr, +void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns); -static inline int netdev_class_create_file(struct class_attribute *class_attr) +static inline int netdev_class_create_file(const struct class_attribute *class_attr) { return netdev_class_create_file_ns(class_attr, NULL); } -static inline void netdev_class_remove_file(struct class_attribute *class_attr) +static inline void netdev_class_remove_file(const struct class_attribute *class_attr) { netdev_class_remove_file_ns(class_attr, NULL); } -- cgit v1.2.3 From 737aec57c672c1308d602afecd841455c39561e5 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 18 Aug 2017 13:46:22 -0700 Subject: net: constify net_ns_type_operations This can be const. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eaa77bd9cb80..b0c928598dab 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4028,7 +4028,7 @@ static inline void netdev_class_remove_file(const struct class_attribute *class_ netdev_class_remove_file_ns(class_attr, NULL); } -extern struct kobj_ns_type_operations net_ns_type_operations; +extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); -- cgit v1.2.3 From 718ad681eff47d3d04879ff5f5290bdab0b8bad6 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 18 Aug 2017 13:46:24 -0700 Subject: net: drop unused attribute argument from sysfs queue funcs The show and store functions don't need/use the attribute. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0c928598dab..c5475b37a631 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -694,10 +694,9 @@ struct netdev_rx_queue { */ struct rx_queue_attribute { struct attribute attr; - ssize_t (*show)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, char *buf); + ssize_t (*show)(struct netdev_rx_queue *queue, char *buf); ssize_t (*store)(struct netdev_rx_queue *queue, - struct rx_queue_attribute *attr, const char *buf, size_t len); + const char *buf, size_t len); }; #ifdef CONFIG_XPS -- cgit v1.2.3 From 96eabe7a40aa17e613cf3db2c742ee8b1fc764d0 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 18 Aug 2017 11:28:00 -0700 Subject: bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1cc6c5ff61ec..55b88e329804 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -51,6 +51,7 @@ struct bpf_map { u32 map_flags; u32 pages; u32 id; + int numa_node; struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; @@ -264,7 +265,7 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_precharge_memlock(u32 pages); -void *bpf_map_area_alloc(size_t size); +void *bpf_map_area_alloc(size_t size, int numa_node); void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; @@ -316,6 +317,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); void __dev_map_insert_ctx(struct bpf_map *map, u32 index); void __dev_map_flush(struct bpf_map *map); +/* Return map's numa specified by userspace */ +static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) +{ + return (attr->map_flags & BPF_F_NUMA_NODE) ? + attr->numa_node : NUMA_NO_NODE; +} + #else static inline struct bpf_prog *bpf_prog_get(u32 ufd) { -- cgit v1.2.3 From d6e1e46f69fbe956e877cdd00dbfb002baddf577 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 19 Aug 2017 23:34:03 -0700 Subject: bpf: linux/bpf.h needs linux/numa.h Reported-by: kbuild test robot Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 55b88e329804..830f472d8df5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -14,6 +14,7 @@ #include #include #include +#include struct perf_event; struct bpf_prog; -- cgit v1.2.3 From 5405fa26c25e18ab735daddc46c8a7a78f138f70 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Thu, 15 Jun 2017 18:29:23 +0300 Subject: net/mlx5: Add PCIe outbound stalls counters infrastructure Add capability bit in MCAM register and counters to MPCNT register. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c99daffc3c3c..ba533b39c885 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1854,7 +1854,17 @@ struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits { u8 crc_error_tlp[0x20]; - u8 reserved_at_140[0x680]; + u8 reserved_at_140[0x40]; + + u8 outbound_stalled_reads[0x20]; + + u8 outbound_stalled_writes[0x20]; + + u8 outbound_stalled_reads_events[0x20]; + + u8 outbound_stalled_writes_events[0x20]; + + u8 reserved_at_200[0x5c0]; }; struct mlx5_ifc_cmd_inter_comp_event_bits { @@ -7744,8 +7754,9 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x7d]; - + u8 reserved_at_0[0x7b]; + u8 pcie_outbound_stalled[0x1]; + u8 reserved_at_7c[0x1]; u8 mtpps_enh_out_per_adj[0x1]; u8 mtpps_fs[0x1]; u8 pcie_performance_group[0x1]; -- cgit v1.2.3 From 2dba07975acbc30c77a22d38030ee5a86ab8a748 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 18 Jun 2017 14:56:45 +0300 Subject: net/mlx5: Add RX buffer fullness counters infrastructure Add capability bit in PCAM register and counters to PPCNT register. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ba533b39c885..cf7ff52c594e 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1538,7 +1538,17 @@ struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { u8 port_transmit_wait_low[0x20]; - u8 reserved_at_40[0x780]; + u8 reserved_at_40[0x100]; + + u8 rx_buffer_almost_full_high[0x20]; + + u8 rx_buffer_almost_full_low[0x20]; + + u8 rx_buffer_full_high[0x20]; + + u8 rx_buffer_full_low[0x20]; + + u8 reserved_at_1c0[0x600]; }; struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { @@ -7723,8 +7733,9 @@ struct mlx5_ifc_peir_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x7c]; + u8 reserved_at_0[0x7b]; + u8 rx_buffer_fullness_counters[0x1]; u8 ptys_connector_type[0x1]; u8 reserved_at_7d[0x1]; u8 ppcnt_discard_group[0x1]; -- cgit v1.2.3 From efae7f78c45ba37bdc23a95d219b59ac85bdd0a7 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Fri, 12 May 2017 02:47:02 +0300 Subject: net/mlx5e: Add outbound PCI buffer overflow counter Add outbound_pci_buffer_overflow to ethtool output for monitoring the number of packets that were dropped due to lack of PCIe buffers on receive path from NIC port toward the host(s). This counter is valid only in case that tx_overflow_buffer_pkt is supported in MCAM enhanced features. Signed-off-by: Eran Ben Elisha Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cf7ff52c594e..ae7d09b9c52f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1864,7 +1864,9 @@ struct mlx5_ifc_pcie_perf_cntrs_grp_data_layout_bits { u8 crc_error_tlp[0x20]; - u8 reserved_at_140[0x40]; + u8 tx_overflow_buffer_pkt_high[0x20]; + + u8 tx_overflow_buffer_pkt_low[0x20]; u8 outbound_stalled_reads[0x20]; @@ -7767,7 +7769,7 @@ struct mlx5_ifc_pcam_reg_bits { struct mlx5_ifc_mcam_enhanced_features_bits { u8 reserved_at_0[0x7b]; u8 pcie_outbound_stalled[0x1]; - u8 reserved_at_7c[0x1]; + u8 tx_overflow_buffer_pkt[0x1]; u8 mtpps_enh_out_per_adj[0x1]; u8 mtpps_fs[0x1]; u8 pcie_performance_group[0x1]; -- cgit v1.2.3 From f00fd7ae4f409abb7b2e5d099248832548199f0c Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Sun, 30 Jul 2017 16:14:42 -0600 Subject: PATCH] iio: Fix some documentation warnings The kerneldoc description for the trig_readonly field of struct iio_dev lacked a colon, leading to this doc build warning: ./include/linux/iio/iio.h:603: warning: No description found for parameter 'trig_readonly' A similar issue for iio_trigger_set_immutable() in trigger.h yielded: ./include/linux/iio/trigger.h:151: warning: No description found for parameter 'indio_dev' ./include/linux/iio/trigger.h:151: warning: No description found for parameter 'trig' Fix the formatting and silence the warnings. Signed-off-by: Jonathan Corbet Signed-off-by: Jonathan Cameron --- include/linux/iio/iio.h | 2 +- include/linux/iio/trigger.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index d68bec297a45..c380daa40c0e 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -535,7 +535,7 @@ struct iio_buffer_setup_ops { * @scan_timestamp: [INTERN] set if any buffers have requested timestamp * @scan_index_timestamp:[INTERN] cache of the index to the timestamp * @trig: [INTERN] current device trigger (buffer modes) - * @trig_readonly [INTERN] mark the current trigger immutable + * @trig_readonly: [INTERN] mark the current trigger immutable * @pollfunc: [DRIVER] function run on trigger being received * @pollfunc_event: [DRIVER] function run on events trigger being received * @channels: [DRIVER] channel specification structure table diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index ea08302f2d7b..7142d8d6e470 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -144,8 +144,8 @@ void devm_iio_trigger_unregister(struct device *dev, /** * iio_trigger_set_immutable() - set an immutable trigger on destination * - * @indio_dev - IIO device structure containing the device - * @trig - trigger to assign to device + * @indio_dev: IIO device structure containing the device + * @trig: trigger to assign to device * **/ int iio_trigger_set_immutable(struct iio_dev *indio_dev, struct iio_trigger *trig); -- cgit v1.2.3 From 3bde7afdabe9f37974af806abe646c2ca43c67c7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sun, 20 Aug 2017 11:33:25 -0400 Subject: NFS: Remove unused parameter gfp_flags from nfs_pageio_init() Now that the mirror allocation has been moved, the parameter can go. Also remove the redundant symbol export. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index d67b67ae6c8b..8b1a35aad0c3 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -125,8 +125,7 @@ extern void nfs_pageio_init(struct nfs_pageio_descriptor *desc, const struct nfs_pgio_completion_ops *compl_ops, const struct nfs_rw_ops *rw_ops, size_t bsize, - int how, - gfp_t gfp_flags); + int how); extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *, struct nfs_page *); extern int nfs_pageio_resend(struct nfs_pageio_descriptor *, -- cgit v1.2.3 From 9d6105e19f617406aea46dd19281080c7c5ae0d8 Mon Sep 17 00:00:00 2001 From: Elaine Zhang Date: Mon, 21 Aug 2017 03:28:34 +0200 Subject: mfd: rk808: Fix up the chip id get failed the rk8xx chip id is: ((MSB << 8) | LSB) & 0xfff0 Signed-off-by: Elaine Zhang Signed-off-by: Joseph Chen Signed-off-by: Heiko Stuebner Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 83701ef7d3c7..54feb140c210 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -298,6 +298,7 @@ enum rk818_reg { #define VOUT_LO_INT BIT(0) #define CLK32KOUT2_EN BIT(0) +#define RK8XX_ID_MSK 0xfff0 enum { BUCK_ILMIN_50MA, BUCK_ILMIN_100MA, -- cgit v1.2.3 From a5247ca6708ff7dc089d2774c131455774153eb6 Mon Sep 17 00:00:00 2001 From: Elaine Zhang Date: Mon, 21 Aug 2017 03:28:35 +0200 Subject: mfd: rk808: Add rk805 regs addr and ID Signed-off-by: Elaine Zhang Signed-off-by: Joseph Chen Signed-off-by: Heiko Stuebner Signed-off-by: Lee Jones --- include/linux/mfd/rk808.h | 120 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 120 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 54feb140c210..d3156594674c 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -206,6 +206,97 @@ enum rk818_reg { #define RK818_USB_ILMIN_2000MA 0x7 #define RK818_USB_CHG_SD_VSEL_MASK 0x70 +/* RK805 */ +enum rk805_reg { + RK805_ID_DCDC1, + RK805_ID_DCDC2, + RK805_ID_DCDC3, + RK805_ID_DCDC4, + RK805_ID_LDO1, + RK805_ID_LDO2, + RK805_ID_LDO3, +}; + +/* CONFIG REGISTER */ +#define RK805_VB_MON_REG 0x21 +#define RK805_THERMAL_REG 0x22 + +/* POWER CHANNELS ENABLE REGISTER */ +#define RK805_DCDC_EN_REG 0x23 +#define RK805_SLP_DCDC_EN_REG 0x25 +#define RK805_SLP_LDO_EN_REG 0x26 +#define RK805_LDO_EN_REG 0x27 + +/* BUCK AND LDO CONFIG REGISTER */ +#define RK805_BUCK_LDO_SLP_LP_EN_REG 0x2A +#define RK805_BUCK1_CONFIG_REG 0x2E +#define RK805_BUCK1_ON_VSEL_REG 0x2F +#define RK805_BUCK1_SLP_VSEL_REG 0x30 +#define RK805_BUCK2_CONFIG_REG 0x32 +#define RK805_BUCK2_ON_VSEL_REG 0x33 +#define RK805_BUCK2_SLP_VSEL_REG 0x34 +#define RK805_BUCK3_CONFIG_REG 0x36 +#define RK805_BUCK4_CONFIG_REG 0x37 +#define RK805_BUCK4_ON_VSEL_REG 0x38 +#define RK805_BUCK4_SLP_VSEL_REG 0x39 +#define RK805_LDO1_ON_VSEL_REG 0x3B +#define RK805_LDO1_SLP_VSEL_REG 0x3C +#define RK805_LDO2_ON_VSEL_REG 0x3D +#define RK805_LDO2_SLP_VSEL_REG 0x3E +#define RK805_LDO3_ON_VSEL_REG 0x3F +#define RK805_LDO3_SLP_VSEL_REG 0x40 + +/* INTERRUPT REGISTER */ +#define RK805_PWRON_LP_INT_TIME_REG 0x47 +#define RK805_PWRON_DB_REG 0x48 +#define RK805_DEV_CTRL_REG 0x4B +#define RK805_INT_STS_REG 0x4C +#define RK805_INT_STS_MSK_REG 0x4D +#define RK805_GPIO_IO_POL_REG 0x50 +#define RK805_OUT_REG 0x52 +#define RK805_ON_SOURCE_REG 0xAE +#define RK805_OFF_SOURCE_REG 0xAF + +#define RK805_NUM_REGULATORS 7 + +#define RK805_PWRON_FALL_RISE_INT_EN 0x0 +#define RK805_PWRON_FALL_RISE_INT_MSK 0x81 + +/* RK805 IRQ Definitions */ +#define RK805_IRQ_PWRON_RISE 0 +#define RK805_IRQ_VB_LOW 1 +#define RK805_IRQ_PWRON 2 +#define RK805_IRQ_PWRON_LP 3 +#define RK805_IRQ_HOTDIE 4 +#define RK805_IRQ_RTC_ALARM 5 +#define RK805_IRQ_RTC_PERIOD 6 +#define RK805_IRQ_PWRON_FALL 7 + +#define RK805_IRQ_PWRON_RISE_MSK BIT(0) +#define RK805_IRQ_VB_LOW_MSK BIT(1) +#define RK805_IRQ_PWRON_MSK BIT(2) +#define RK805_IRQ_PWRON_LP_MSK BIT(3) +#define RK805_IRQ_HOTDIE_MSK BIT(4) +#define RK805_IRQ_RTC_ALARM_MSK BIT(5) +#define RK805_IRQ_RTC_PERIOD_MSK BIT(6) +#define RK805_IRQ_PWRON_FALL_MSK BIT(7) + +#define RK805_PWR_RISE_INT_STATUS BIT(0) +#define RK805_VB_LOW_INT_STATUS BIT(1) +#define RK805_PWRON_INT_STATUS BIT(2) +#define RK805_PWRON_LP_INT_STATUS BIT(3) +#define RK805_HOTDIE_INT_STATUS BIT(4) +#define RK805_ALARM_INT_STATUS BIT(5) +#define RK805_PERIOD_INT_STATUS BIT(6) +#define RK805_PWR_FALL_INT_STATUS BIT(7) + +#define RK805_BUCK1_2_ILMAX_MASK (3 << 6) +#define RK805_BUCK3_4_ILMAX_MASK (3 << 3) +#define RK805_RTC_PERIOD_INT_MASK (1 << 6) +#define RK805_RTC_ALARM_INT_MASK (1 << 5) +#define RK805_INT_ALARM_EN (1 << 3) +#define RK805_INT_TIMER_EN (1 << 2) + /* RK808 IRQ Definitions */ #define RK808_IRQ_VOUT_LO 0 #define RK808_IRQ_VB_LO 1 @@ -298,7 +389,14 @@ enum rk818_reg { #define VOUT_LO_INT BIT(0) #define CLK32KOUT2_EN BIT(0) +#define TEMP115C 0x0c +#define TEMP_HOTDIE_MSK 0x0c +#define SLP_SD_MSK (0x3 << 2) +#define SHUTDOWN_FUN (0x2 << 2) +#define SLEEP_FUN (0x1 << 2) #define RK8XX_ID_MSK 0xfff0 +#define FPWM_MODE BIT(7) + enum { BUCK_ILMIN_50MA, BUCK_ILMIN_100MA, @@ -322,6 +420,28 @@ enum { }; enum { + RK805_BUCK1_2_ILMAX_2500MA, + RK805_BUCK1_2_ILMAX_3000MA, + RK805_BUCK1_2_ILMAX_3500MA, + RK805_BUCK1_2_ILMAX_4000MA, +}; + +enum { + RK805_BUCK3_ILMAX_1500MA, + RK805_BUCK3_ILMAX_2000MA, + RK805_BUCK3_ILMAX_2500MA, + RK805_BUCK3_ILMAX_3000MA, +}; + +enum { + RK805_BUCK4_ILMAX_2000MA, + RK805_BUCK4_ILMAX_2500MA, + RK805_BUCK4_ILMAX_3000MA, + RK805_BUCK4_ILMAX_3500MA, +}; + +enum { + RK805_ID = 0x8050, RK808_ID = 0x0000, RK818_ID = 0x8181, }; -- cgit v1.2.3 From 6c83fd5142c68294acb0e857b7bac2ce8a5077f7 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 21 Aug 2017 14:06:46 +0200 Subject: quota: Add lock annotations to struct members Add annotation which lock protects which struct members to struct dquot and struct mem_dqinfo. Signed-off-by: Jan Kara --- include/linux/quota.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 074123975595..5ac9de4fcd6f 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -223,12 +223,12 @@ struct mem_dqinfo { struct quota_format_type *dqi_format; int dqi_fmt_id; /* Id of the dqi_format - used when turning * quotas on after remount RW */ - struct list_head dqi_dirty_list; /* List of dirty dquots */ - unsigned long dqi_flags; - unsigned int dqi_bgrace; - unsigned int dqi_igrace; - qsize_t dqi_max_spc_limit; - qsize_t dqi_max_ino_limit; + struct list_head dqi_dirty_list; /* List of dirty dquots [dq_list_lock] */ + unsigned long dqi_flags; /* DFQ_ flags [dq_data_lock] */ + unsigned int dqi_bgrace; /* Space grace time [dq_data_lock] */ + unsigned int dqi_igrace; /* Inode grace time [dq_data_lock] */ + qsize_t dqi_max_spc_limit; /* Maximum space limit [static] */ + qsize_t dqi_max_ino_limit; /* Maximum inode limit [static] */ void *dqi_priv; }; @@ -293,16 +293,16 @@ static inline void dqstats_dec(unsigned int type) * clear them when it sees fit. */ struct dquot { - struct hlist_node dq_hash; /* Hash list in memory */ - struct list_head dq_inuse; /* List of all quotas */ - struct list_head dq_free; /* Free list element */ - struct list_head dq_dirty; /* List of dirty dquots */ + struct hlist_node dq_hash; /* Hash list in memory [dq_list_lock] */ + struct list_head dq_inuse; /* List of all quotas [dq_list_lock] */ + struct list_head dq_free; /* Free list element [dq_list_lock] */ + struct list_head dq_dirty; /* List of dirty dquots [dq_list_lock] */ struct mutex dq_lock; /* dquot IO lock */ spinlock_t dq_dqb_lock; /* Lock protecting dq_dqb changes */ atomic_t dq_count; /* Use count */ struct super_block *dq_sb; /* superblock this applies to */ struct kqid dq_id; /* ID this applies to (uid, gid, projid) */ - loff_t dq_off; /* Offset of dquot on disk */ + loff_t dq_off; /* Offset of dquot on disk [dq_lock, stable once set] */ unsigned long dq_flags; /* See DQ_* */ struct mem_dqblk dq_dqb; /* Diskquota usage [dq_dqb_lock] */ }; -- cgit v1.2.3 From 7467c9d9598993d8531b2f76c090a5743000612b Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 24 Jul 2017 14:55:13 +0100 Subject: of: return of_get_cpu_node from of_cpu_device_node_get if CPUs are not registered Instead of the callsites choosing between of_cpu_device_node_get if the CPUs are registered as of_node is populated by then and of_get_cpu_node when the CPUs are not yet registered as CPU of_nodes are not yet stashed thereby needing to parse the device tree, we can call of_get_cpu_node in case the CPUs are not yet registered. This will allow to use of_cpu_device_node_get anywhere hiding the details from the caller. Cc: Rob Herring Cc: Frank Rowand Signed-off-by: Sudeep Holla Signed-off-by: Rob Herring --- include/linux/of_device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_device.h b/include/linux/of_device.h index b4ad8b4f8506..611502524425 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -50,7 +50,7 @@ static inline struct device_node *of_cpu_device_node_get(int cpu) struct device *cpu_dev; cpu_dev = get_cpu_device(cpu); if (!cpu_dev) - return NULL; + return of_get_cpu_node(cpu, NULL); return of_node_get(cpu_dev->of_node); } -- cgit v1.2.3 From dd1c1f2f2028a7b851f701fc6a8ebe39dcb95e7c Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 21 Aug 2017 17:35:02 +0200 Subject: pids: make task_tgid_nr_ns() safe This was reported many times, and this was even mentioned in commit 52ee2dfdd4f5 ("pids: refactor vnr/nr_ns helpers to make them safe") but somehow nobody bothered to fix the obvious problem: task_tgid_nr_ns() is not safe because task->group_leader points to nowhere after the exiting task passes exit_notify(), rcu_read_lock() can not help. We really need to change __unhash_process() to nullify group_leader, parent, and real_parent, but this needs some cleanups. Until then we can turn task_tgid_nr_ns() into another user of __task_pid_nr_ns() and fix the problem. Reported-by: Troy Kensinger Signed-off-by: Oleg Nesterov Signed-off-by: Linus Torvalds --- include/linux/pid.h | 4 +++- include/linux/sched.h | 51 +++++++++++++++++++++++++++------------------------ 2 files changed, 30 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index 4d179316e431..719582744a2e 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -8,7 +8,9 @@ enum pid_type PIDTYPE_PID, PIDTYPE_PGID, PIDTYPE_SID, - PIDTYPE_MAX + PIDTYPE_MAX, + /* only valid to __task_pid_nr_ns() */ + __PIDTYPE_TGID }; /* diff --git a/include/linux/sched.h b/include/linux/sched.h index 8337e2db0bb2..c05ac5f5aa03 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1163,13 +1163,6 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk) return tsk->tgid; } -extern pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); - -static inline pid_t task_tgid_vnr(struct task_struct *tsk) -{ - return pid_vnr(task_tgid(tsk)); -} - /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. @@ -1185,23 +1178,6 @@ static inline int pid_alive(const struct task_struct *p) return p->pids[PIDTYPE_PID].pid != NULL; } -static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) -{ - pid_t pid = 0; - - rcu_read_lock(); - if (pid_alive(tsk)) - pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); - rcu_read_unlock(); - - return pid; -} - -static inline pid_t task_ppid_nr(const struct task_struct *tsk) -{ - return task_ppid_nr_ns(tsk, &init_pid_ns); -} - static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); @@ -1223,6 +1199,33 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } +static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns); +} + +static inline pid_t task_tgid_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL); +} + +static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) +{ + pid_t pid = 0; + + rcu_read_lock(); + if (pid_alive(tsk)) + pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); + rcu_read_unlock(); + + return pid; +} + +static inline pid_t task_ppid_nr(const struct task_struct *tsk) +{ + return task_ppid_nr_ns(tsk, &init_pid_ns); +} + /* Obsolete, do not use: */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { -- cgit v1.2.3 From c678fa66341c7b82a57cfed0ba3656162e970f99 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Mon, 21 Aug 2017 10:23:13 -0700 Subject: dmaengine: remove DMA_SG as it is dead code in kernel There are no in kernel consumers for DMA_SG op. Removing operation, dead code, and test code in dmatest. Signed-off-by: Dave Jiang Reviewed-by: Linus Walleij Cc: Gary Hook Cc: Ludovic Desroches Cc: Kedareswara rao Appana Cc: Li Yang Cc: Michal Simek Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 533680860865..64fbd380c430 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -68,7 +68,6 @@ enum dma_transaction_type { DMA_MEMSET, DMA_MEMSET_SG, DMA_INTERRUPT, - DMA_SG, DMA_PRIVATE, DMA_ASYNC_TX, DMA_SLAVE, @@ -771,11 +770,6 @@ struct dma_device { unsigned int nents, int value, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)( struct dma_chan *chan, unsigned long flags); - struct dma_async_tx_descriptor *(*device_prep_dma_sg)( - struct dma_chan *chan, - struct scatterlist *dst_sg, unsigned int dst_nents, - struct scatterlist *src_sg, unsigned int src_nents, - unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_slave_sg)( struct dma_chan *chan, struct scatterlist *sgl, @@ -905,19 +899,6 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy( len, flags); } -static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_sg( - struct dma_chan *chan, - struct scatterlist *dst_sg, unsigned int dst_nents, - struct scatterlist *src_sg, unsigned int src_nents, - unsigned long flags) -{ - if (!chan || !chan->device || !chan->device->device_prep_dma_sg) - return NULL; - - return chan->device->device_prep_dma_sg(chan, dst_sg, dst_nents, - src_sg, src_nents, flags); -} - /** * dmaengine_terminate_all() - Terminate all active DMA transfers * @chan: The channel for which to terminate the transfers -- cgit v1.2.3 From 67dfabe3a01be6b0cc4c0056aa546f0279ed6279 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Mon, 21 Aug 2017 16:54:01 +0200 Subject: mfd: da9052: Add register details for TSI Add register details an channels definition for using the TSI registers in the hwmon driver. Signed-off-by: Sebastian Reichel Signed-off-by: Lee Jones --- include/linux/mfd/da9052/da9052.h | 6 ++++++ include/linux/mfd/da9052/reg.h | 11 ++++++++++- 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h index ce9230af09c2..ae5b663836d0 100644 --- a/include/linux/mfd/da9052/da9052.h +++ b/include/linux/mfd/da9052/da9052.h @@ -45,6 +45,12 @@ #define DA9052_ADC_TJUNC 8 #define DA9052_ADC_VBBAT 9 +/* TSI channel has its own 4 channel mux */ +#define DA9052_ADC_TSI_XP 70 +#define DA9052_ADC_TSI_XN 71 +#define DA9052_ADC_TSI_YP 72 +#define DA9052_ADC_TSI_YN 73 + #define DA9052_IRQ_DCIN 0 #define DA9052_IRQ_VBUS 1 #define DA9052_IRQ_DCINREM 2 diff --git a/include/linux/mfd/da9052/reg.h b/include/linux/mfd/da9052/reg.h index 5010f978725c..76780ea8849c 100644 --- a/include/linux/mfd/da9052/reg.h +++ b/include/linux/mfd/da9052/reg.h @@ -690,7 +690,10 @@ /* TSI CONTROL REGISTER B BITS */ #define DA9052_TSICONTB_ADCREF 0X80 #define DA9052_TSICONTB_TSIMAN 0X40 -#define DA9052_TSICONTB_TSIMUX 0X30 +#define DA9052_TSICONTB_TSIMUX_XP 0X00 +#define DA9052_TSICONTB_TSIMUX_YP 0X10 +#define DA9052_TSICONTB_TSIMUX_XN 0X20 +#define DA9052_TSICONTB_TSIMUX_YN 0X30 #define DA9052_TSICONTB_TSISEL3 0X08 #define DA9052_TSICONTB_TSISEL2 0X04 #define DA9052_TSICONTB_TSISEL1 0X02 @@ -705,8 +708,14 @@ /* TSI CO-ORDINATE LSB RESULT REGISTER BITS */ #define DA9052_TSILSB_PENDOWN 0X40 #define DA9052_TSILSB_TSIZL 0X30 +#define DA9052_TSILSB_TSIZL_SHIFT 4 +#define DA9052_TSILSB_TSIZL_BITS 2 #define DA9052_TSILSB_TSIYL 0X0C +#define DA9052_TSILSB_TSIYL_SHIFT 2 +#define DA9052_TSILSB_TSIYL_BITS 2 #define DA9052_TSILSB_TSIXL 0X03 +#define DA9052_TSILSB_TSIXL_SHIFT 0 +#define DA9052_TSILSB_TSIXL_BITS 2 /* TSI Z MEASUREMENT MSB RESULT REGISTER BIT */ #define DA9052_TSIZMSB_TSIZM 0XFF -- cgit v1.2.3 From 18c90df9f2c00cb35ab8ba747aa0f742ee6bbf6a Mon Sep 17 00:00:00 2001 From: Romain Perier Date: Tue, 22 Aug 2017 13:46:59 +0200 Subject: mlx5: Replace PCI pool old API The PCI pool API is deprecated. This commit replaces the PCI pool old API by the appropriate function with the DMA pool API. Signed-off-by: Romain Perier Reviewed-by: Peter Senna Tschudin Acked-by: Doug Ledford Tested-by: Doug Ledford Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 099fe311f272..db40bc4055c7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -299,7 +299,7 @@ struct mlx5_cmd { struct semaphore pages_sem; int mode; struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS]; - struct pci_pool *pool; + struct dma_pool *pool; struct mlx5_cmd_debug dbg; struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; -- cgit v1.2.3 From 3946d18765be0b0fe278bea4f87a54cf13858019 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Mon, 14 Aug 2017 21:59:55 -0700 Subject: gpio: add gpio_add_lookup_tables() to add several tables at once When converting legacy board to use gpiod API() there might be several lookup tables in board file, let's provide a way to register them all at once. Reviewed-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Dmitry Torokhov Signed-off-by: Linus Walleij --- include/linux/gpio/machine.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index 6e76b16fcade..ba4ccfd900f9 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -60,11 +60,14 @@ struct gpiod_lookup_table { #ifdef CONFIG_GPIOLIB void gpiod_add_lookup_table(struct gpiod_lookup_table *table); +void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n); void gpiod_remove_lookup_table(struct gpiod_lookup_table *table); #else static inline void gpiod_add_lookup_table(struct gpiod_lookup_table *table) {} static inline +void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n) {} +static inline void gpiod_remove_lookup_table(struct gpiod_lookup_table *table) {} #endif -- cgit v1.2.3 From 0edc23ea2692fe75e941ec00867e661eb15f67fa Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 19 Dec 2016 17:01:52 +0000 Subject: irqchip/gic-v3: Add VLPI/DirectLPI discovery Add helper functions that probe for VLPI and DirectLPI properties. Reviewed-by: Eric Auger Reviewed-by: Thomas Gleixner Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 6a1f87ff94e2..20a553423ac7 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -204,6 +204,7 @@ #define GICR_TYPER_PLPIS (1U << 0) #define GICR_TYPER_VLPIS (1U << 1) +#define GICR_TYPER_DirectLPIS (1U << 3) #define GICR_TYPER_LAST (1U << 4) #define GIC_V3_REDIST_SIZE 0x20000 @@ -487,6 +488,8 @@ struct rdists { struct page *prop_page; int id_bits; u64 flags; + bool has_vlpis; + bool has_direct_lpi; }; struct irq_domain; -- cgit v1.2.3 From 3dfa576bfb453482314b596931a59a4951428058 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 19 Dec 2016 17:25:54 +0000 Subject: irqchip/gic-v3-its: Add probing for VLPI properties Add the probing code for the ITS VLPI support. This includes configuring the ITS number if not supporting the single VMOVP command feature. Reviewed-by: Eric Auger Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 20a553423ac7..af8c55105fc2 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -235,15 +235,20 @@ #define GITS_TRANSLATER 0x10040 #define GITS_CTLR_ENABLE (1U << 0) +#define GITS_CTLR_ITS_NUMBER_SHIFT 4 +#define GITS_CTLR_ITS_NUMBER (0xFU << GITS_CTLR_ITS_NUMBER_SHIFT) #define GITS_CTLR_QUIESCENT (1U << 31) #define GITS_TYPER_PLPIS (1UL << 0) +#define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 +#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) #define GITS_TYPER_PTA (1UL << 19) #define GITS_TYPER_HWCOLLCNT_SHIFT 24 +#define GITS_TYPER_VMOVP (1ULL << 37) #define GITS_IIDR_REV_SHIFT 12 #define GITS_IIDR_REV_MASK (0xf << GITS_IIDR_REV_SHIFT) -- cgit v1.2.3 From 5158bd5597e4c0939db3ecefbcbf492c425e611c Mon Sep 17 00:00:00 2001 From: Jean-Louis Thekekara Date: Thu, 29 Jun 2017 19:08:30 +0200 Subject: mtd: nand: remove hard-coded NAND ids length This commit removes hard-coded '8' used for looping into struct nand_chip.id.data array. NAND_MAX_ID_LEN has been introduced by Artem Bityutskiy in 53552d22bfe1f for defining ids length in nand_flash_ids[] list. This commit unifies ids length in nand base driver. Signed-off-by: Jean-Louis Thekekara Signed-off-by: Boris Brezillon --- include/linux/mtd/nand.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 8a6522e82f03..297684013977 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -439,14 +439,16 @@ struct nand_jedec_params { __le16 crc; } __packed; +/* The maximum expected count of bytes in the NAND ID sequence */ +#define NAND_MAX_ID_LEN 8 + /** * struct nand_id - NAND id structure - * @data: buffer containing the id bytes. Currently 8 bytes large, but can - * be extended if required. + * @data: buffer containing the id bytes. * @len: ID length. */ struct nand_id { - u8 data[8]; + u8 data[NAND_MAX_ID_LEN]; int len; }; @@ -1018,8 +1020,6 @@ static inline void *nand_get_manufacturer_data(struct nand_chip *chip) #define NAND_MFR_ATO 0x9b #define NAND_MFR_WINBOND 0xef -/* The maximum expected count of bytes in the NAND ID sequence */ -#define NAND_MAX_ID_LEN 8 /* * A helper for defining older NAND chips where the second ID byte fully -- cgit v1.2.3 From e59ad6ff83b444517067046bd837595a1ab84900 Mon Sep 17 00:00:00 2001 From: Andrea Adami Date: Mon, 14 Aug 2017 22:48:33 +0200 Subject: mtd: nand: sharpsl: Add partition parsers platform data With the introduction of sharpslpart partition parser we can now read the offsets from NAND: we specify the list of the parsers as platform data, with cmdlinepart and ofpart parsers first allowing to override the part. table written in NAND. This is done in the board files using this driver. Thus, we need to extend sharpsl_nand_platform_data to consider the partition parsers. Signed-off-by: Andrea Adami Signed-off-by: Boris Brezillon --- include/linux/mtd/sharpsl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/sharpsl.h b/include/linux/mtd/sharpsl.h index 65e91d0fa981..6381a7d6c289 100644 --- a/include/linux/mtd/sharpsl.h +++ b/include/linux/mtd/sharpsl.h @@ -17,4 +17,5 @@ struct sharpsl_nand_platform_data { const struct mtd_ooblayout_ops *ecc_layout; struct mtd_partition *partitions; unsigned int nr_partitions; + const char *const *part_parsers; }; -- cgit v1.2.3 From 827dba9d626325a65727c4074913b2d3c7e7ea4d Mon Sep 17 00:00:00 2001 From: Andrea Adami Date: Mon, 14 Aug 2017 22:48:34 +0200 Subject: mfd: tmio: Add partition parsers platform data With the introduction of sharpslpart partition parser we can now read the offsets from NAND: we specify the list of the parsers as platform data, with cmdlinepart and ofpart parsers first allowing to override the part. table written in NAND. This is done in the board files using this driver. Thus, we need to extend tmio_nand_data to consider the partition parsers. Signed-off-by: Andrea Adami Acked-by: Lee Jones Acked-by: Wolfram Sang Signed-off-by: Boris Brezillon --- include/linux/mfd/tmio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 26e8f8c0a6db..357b6cfdf34a 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -139,6 +139,7 @@ struct tmio_nand_data { struct nand_bbt_descr *badblock_pattern; struct mtd_partition *partition; unsigned int num_partitions; + const char *const *part_parsers; }; #define FBIO_TMIO_ACC_WRITE 0x7C639300 -- cgit v1.2.3 From c2ee070fb00365d7841f6661dcdc7fbe6620bdf8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 23 Aug 2017 19:10:31 +0200 Subject: block: cache the partition index in struct block_device Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e1fd5d21248..706dd3a972d2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -427,6 +427,7 @@ struct block_device { #endif struct block_device * bd_contains; unsigned bd_block_size; + u8 bd_partno; struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ unsigned bd_part_count; -- cgit v1.2.3 From 74d46992e0d9dee7f1f376de0d56d31614c8a17a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 23 Aug 2017 19:10:32 +0200 Subject: block: replace bi_bdev with a gendisk pointer and partitions index This way we don't need a block_device structure to submit I/O. The block_device has different life time rules from the gendisk and request_queue and is usually only available when the block device node is open. Other callers need to explicitly create one (e.g. the lightnvm passthrough code, or the new nvme multipathing code). For the actual I/O path all that we need is the gendisk, which exists once per block device. But given that the block layer also does partition remapping we additionally need a partition index, which is used for said remapping in generic_make_request. Note that all the block drivers generally want request_queue or sometimes the gendisk, so this removes a layer of indirection all over the stack. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 18 ++++++++++++++++++ include/linux/blk_types.h | 3 ++- 2 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9276788a9b24..a8fe7935332f 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -494,6 +494,24 @@ extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); +#define bio_set_dev(bio, bdev) \ +do { \ + (bio)->bi_disk = (bdev)->bd_disk; \ + (bio)->bi_partno = (bdev)->bd_partno; \ +} while (0) + +#define bio_copy_dev(dst, src) \ +do { \ + (dst)->bi_disk = (src)->bi_disk; \ + (dst)->bi_partno = (src)->bi_partno; \ +} while (0) + +#define bio_dev(bio) \ + disk_devt((bio)->bi_disk) + +#define bio_devname(bio, buf) \ + __bdevname(bio_dev(bio), (buf)) + #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_current(struct bio *bio); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d2eb87c84d82..a2d2aa709cef 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -48,7 +48,8 @@ struct blk_issue_stat { */ struct bio { struct bio *bi_next; /* request queue link */ - struct block_device *bi_bdev; + struct gendisk *bi_disk; + u8 bi_partno; blk_status_t bi_status; unsigned int bi_opf; /* bottom bits req flags, * top bits REQ_OP. Use -- cgit v1.2.3 From 143c97cc652949893c8056c679012f0aeccb80e5 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 23 Aug 2017 18:16:11 -0700 Subject: Revert "pty: fix the cached path of the pty slave file descriptor in the master" This reverts commit c8c03f1858331e85d397bacccd34ef409aae993c. It turns out that while fixing the ptmx file descriptor to have the correct 'struct path' to the associated slave pty is a really good thing, it breaks some user space tools for a very annoying reason. The problem is that /dev/ptmx and its associated slave pty (/dev/pts/X) are on different mounts. That was what caused us to have the wrong path in the first place (we would mix up the vfsmount of the 'ptmx' node, with the dentry of the pty slave node), but it also means that now while we use the right vfsmount, having the pty master open also keeps the pts mount busy. And it turn sout that that makes 'pbuilder' very unhappy, as noted by Stefan Lippers-Hollmann: "This patch introduces a regression for me when using pbuilder 0.228.7[2] (a helper to build Debian packages in a chroot and to create and update its chroots) when trying to umount /dev/ptmx (inside the chroot) on Debian/ unstable (full log and pbuilder configuration file[3] attached). [...] Setting up build-essential (12.3) ... Processing triggers for libc-bin (2.24-15) ... I: unmounting dev/ptmx filesystem W: Could not unmount dev/ptmx: umount: /var/cache/pbuilder/build/1340/dev/ptmx: target is busy (In some cases useful info about processes that use the device is found by lsof(8) or fuser(1).)" apparently pbuilder tries to unmount the /dev/pts filesystem while still holding at least one master node open, which is arguably not very nice, but we don't break user space even when fixing other bugs. So this commit has to be reverted. I'll try to figure out a way to avoid caching the path to the slave pty in the master pty. The only thing that actually wants that slave pty path is the "TIOCGPTPEER" ioctl, and I think we could just recreate the path at that time. Reported-by: Stefan Lippers-Hollmann Cc: Eric W Biederman Cc: Christian Brauner Cc: Al Viro Signed-off-by: Linus Torvalds --- include/linux/devpts_fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 7883e901f65c..277ab9af9ac2 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,7 +19,7 @@ struct pts_fs_info; -struct pts_fs_info *devpts_acquire(struct file *, struct vfsmount **ptsmnt); +struct pts_fs_info *devpts_acquire(struct file *); void devpts_release(struct pts_fs_info *); int devpts_new_index(struct pts_fs_info *); -- cgit v1.2.3 From cd0a137acbb66208368353723f5f1480995cf1c4 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 22 Aug 2017 15:12:14 -0700 Subject: net: core: Specify skb_pad()/skb_put_padto() SKB freeing Rename skb_pad() into __skb_pad() and make it take a third argument: free_on_error which controls whether kfree_skb() should be called or not, skb_pad() directly makes use of it and passes true to preserve its existing behavior. Do exactly the same thing with __skb_put_padto() and skb_put_padto(). Suggested-by: David Miller Signed-off-by: Florian Fainelli Reviewed-by: Woojung Huh Signed-off-by: David S. Miller --- include/linux/skbuff.h | 41 +++++++++++++++++++++++++++++++++++++---- 1 file changed, 37 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbe29b6c9bd6..d67a8182e5eb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -973,7 +973,23 @@ int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); -int skb_pad(struct sk_buff *skb, int pad); +int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); + +/** + * skb_pad - zero pad the tail of an skb + * @skb: buffer to pad + * @pad: space to pad + * + * Ensure that a buffer is followed by a padding area that is zero + * filled. Used by network drivers which may DMA or transfer data + * beyond the buffer end onto the wire. + * + * May return error in out of memory cases. The skb is freed on error. + */ +static inline int skb_pad(struct sk_buff *skb, int pad) +{ + return __skb_pad(skb, pad, true); +} #define dev_kfree_skb(a) consume_skb(a) int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, @@ -2825,25 +2841,42 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length + * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on - * success. The skb is freed on error. + * success. The skb is freed on error if @free_on_error is true. */ -static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, + bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; - if (skb_pad(skb, len)) + if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } +/** + * skb_put_padto - increase size and pad an skbuff up to a minimal size + * @skb: buffer to pad + * @len: minimal length + * + * Pads up a buffer to ensure the trailing bytes exist and are + * blanked. If the buffer already contains sufficient data it + * is untouched. Otherwise it is extended. Returns zero on + * success. The skb is freed on error. + */ +static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +{ + return __skb_put_padto(skb, len, true); +} + static inline int skb_add_data(struct sk_buff *skb, struct iov_iter *from, int copy) { -- cgit v1.2.3 From 1b688a19a92223cf2d1892c9d05d64dc397b33e3 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Wed, 23 Aug 2017 15:10:50 +0100 Subject: bpf/verifier: remove varlen_map_value_access flag The optimisation it does is broken when the 'new' register value has a variable offset and the 'old' was constant. I broke it with my pointer types unification (see Fixes tag below), before which the 'new' value would have type PTR_TO_MAP_VALUE_ADJ and would thus not compare equal; other changes in that patch mean that its original behaviour (ignore min/max values) cannot be restored. Tests on a sample set of cilium programs show no change in count of processed instructions. Fixes: f1174f77b50c ("bpf/verifier: rework value tracking") Signed-off-by: Edward Cree Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 91d07efed2ba..d8f131a36fd0 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -125,7 +125,6 @@ struct bpf_verifier_env { u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; bool seen_direct_write; - bool varlen_map_value_access; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ }; -- cgit v1.2.3 From 8e9cd9ce90d48369b2c5ddd79fe3d4a4cb1ccb56 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Wed, 23 Aug 2017 15:11:21 +0100 Subject: bpf/verifier: document liveness analysis The liveness tracking algorithm is quite subtle; add comments to explain it. Signed-off-by: Edward Cree Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf_verifier.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index d8f131a36fd0..b8d200f60a40 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -21,6 +21,19 @@ */ #define BPF_MAX_VAR_SIZ INT_MAX +/* Liveness marks, used for registers and spilled-regs (in stack slots). + * Read marks propagate upwards until they find a write mark; they record that + * "one of this state's descendants read this reg" (and therefore the reg is + * relevant for states_equal() checks). + * Write marks collect downwards and do not propagate; they record that "the + * straight-line code that reached this state (from its parent) wrote this reg" + * (and therefore that reads propagated from this state or its descendants + * should not propagate to its parent). + * A state with a write mark can receive read marks; it just won't propagate + * them to its parent, since the write mark is a property, not of the state, + * but of the link between it and its parent. See mark_reg_read() and + * mark_stack_slot_read() in kernel/bpf/verifier.c. + */ enum bpf_reg_liveness { REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */ REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */ -- cgit v1.2.3 From ecda85e70277ef24e44a1f6bc00243cebd19f985 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 16 Aug 2017 19:31:57 +0200 Subject: x86/lguest: Remove lguest support Lguest seems to be rather unused these days. It has seen only patches ensuring it still builds the last two years and its official state is "Odd Fixes". Remove it in order to be able to clean up the paravirt code. Signed-off-by: Juergen Gross Acked-by: Rusty Russell Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: boris.ostrovsky@oracle.com Cc: lguest@lists.ozlabs.org Cc: rusty@rustcorp.com.au Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/20170816173157.8633-3-jgross@suse.com Signed-off-by: Ingo Molnar --- include/linux/lguest.h | 73 ----------------------------------------- include/linux/lguest_launcher.h | 44 ------------------------- 2 files changed, 117 deletions(-) delete mode 100644 include/linux/lguest.h delete mode 100644 include/linux/lguest_launcher.h (limited to 'include/linux') diff --git a/include/linux/lguest.h b/include/linux/lguest.h deleted file mode 100644 index 6db19f35f7c5..000000000000 --- a/include/linux/lguest.h +++ /dev/null @@ -1,73 +0,0 @@ -/* - * Things the lguest guest needs to know. Note: like all lguest interfaces, - * this is subject to wild and random change between versions. - */ -#ifndef _LINUX_LGUEST_H -#define _LINUX_LGUEST_H - -#ifndef __ASSEMBLY__ -#include -#include -#include - -#define LG_CLOCK_MIN_DELTA 100UL -#define LG_CLOCK_MAX_DELTA ULONG_MAX - -/*G:031 - * The second method of communicating with the Host is to via "struct - * lguest_data". Once the Guest's initialization hypercall tells the Host where - * this is, the Guest and Host both publish information in it. -:*/ -struct lguest_data { - /* - * 512 == enabled (same as eflags in normal hardware). The Guest - * changes interrupts so often that a hypercall is too slow. - */ - unsigned int irq_enabled; - /* Fine-grained interrupt disabling by the Guest */ - DECLARE_BITMAP(blocked_interrupts, LGUEST_IRQS); - - /* - * The Host writes the virtual address of the last page fault here, - * which saves the Guest a hypercall. CR2 is the native register where - * this address would normally be found. - */ - unsigned long cr2; - - /* Wallclock time set by the Host. */ - struct timespec time; - - /* - * Interrupt pending set by the Host. The Guest should do a hypercall - * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF). - */ - int irq_pending; - - /* - * Async hypercall ring. Instead of directly making hypercalls, we can - * place them in here for processing the next time the Host wants. - * This batching can be quite efficient. - */ - - /* 0xFF == done (set by Host), 0 == pending (set by Guest). */ - u8 hcall_status[LHCALL_RING_SIZE]; - /* The actual registers for the hypercalls. */ - struct hcall_args hcalls[LHCALL_RING_SIZE]; - -/* Fields initialized by the Host at boot: */ - /* Memory not to try to access */ - unsigned long reserve_mem; - /* KHz for the TSC clock. */ - u32 tsc_khz; - -/* Fields initialized by the Guest at boot: */ - /* Instruction to suppress interrupts even if enabled */ - unsigned long noirq_iret; - /* Address above which page tables are all identical. */ - unsigned long kernel_address; - /* The vector to try to use for system calls (0x40 or 0x80). */ - unsigned int syscall_vec; -}; -extern struct lguest_data lguest_data; -#endif /* __ASSEMBLY__ */ -#endif /* _LINUX_LGUEST_H */ diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h deleted file mode 100644 index acd5b12565cc..000000000000 --- a/include/linux/lguest_launcher.h +++ /dev/null @@ -1,44 +0,0 @@ -#ifndef _LINUX_LGUEST_LAUNCHER -#define _LINUX_LGUEST_LAUNCHER -/* Everything the "lguest" userspace program needs to know. */ -#include - -/*D:010 - * Drivers - * - * The Guest needs devices to do anything useful. Since we don't let it touch - * real devices (think of the damage it could do!) we provide virtual devices. - * We emulate a PCI bus with virtio devices on it; we used to have our own - * lguest bus which was far simpler, but this tests the virtio 1.0 standard. - * - * Virtio devices are also used by kvm, so we can simply reuse their optimized - * device drivers. And one day when everyone uses virtio, my plan will be - * complete. Bwahahahah! - */ - -/* Write command first word is a request. */ -enum lguest_req -{ - LHREQ_INITIALIZE, /* + base, pfnlimit, start */ - LHREQ_GETDMA, /* No longer used */ - LHREQ_IRQ, /* + irq */ - LHREQ_BREAK, /* No longer used */ - LHREQ_EVENTFD, /* No longer used. */ - LHREQ_GETREG, /* + offset within struct pt_regs (then read value). */ - LHREQ_SETREG, /* + offset within struct pt_regs, value. */ - LHREQ_TRAP, /* + trap number to deliver to guest. */ -}; - -/* - * This is what read() of the lguest fd populates. trap == - * LGUEST_TRAP_ENTRY for an LHCALL_NOTIFY (addr is the - * argument), 14 for a page fault in the MMIO region (addr is - * the trap address, insn is the instruction), or 13 for a GPF - * (insn is the instruction). - */ -struct lguest_pending { - __u8 trap; - __u8 insn[7]; - __u32 addr; -}; -#endif /* _LINUX_LGUEST_LAUNCHER */ -- cgit v1.2.3 From 581821ae7f7e2c4547945c65f1bcd357f5915aa5 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 16 Aug 2017 13:32:39 +0300 Subject: usb: chipidea: udc: Support SKB alignment quirk NVIDIA Tegra20 UDC can't cope with unaligned DMA and require a USB gadget quirk that avoids SKB buffer alignment to be set in order to make Ethernet Gadget working. Later Tegra generations do not require that quirk. Let's add a new platform data flag that allows to enable USB gadget quirk for platforms that require it. Signed-off-by: Dmitry Osipenko Acked-by: Peter Chen Signed-off-by: Peter Chen --- include/linux/usb/chipidea.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h index c5fdfcf99828..d725cff7268d 100644 --- a/include/linux/usb/chipidea.h +++ b/include/linux/usb/chipidea.h @@ -58,6 +58,7 @@ struct ci_hdrc_platform_data { #define CI_HDRC_OVERRIDE_TX_BURST BIT(10) #define CI_HDRC_OVERRIDE_RX_BURST BIT(11) #define CI_HDRC_OVERRIDE_PHY_CONTROL BIT(12) /* Glue layer manages phy */ +#define CI_HDRC_REQUIRES_ALIGNED_DMA BIT(13) enum usb_dr_mode dr_mode; #define CI_HDRC_CONTROLLER_RESET_EVENT 0 #define CI_HDRC_CONTROLLER_STOPPED_EVENT 1 -- cgit v1.2.3 From 07533c6765de05199417ec73f9c2a495ddd29473 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 21 Aug 2017 17:54:21 +0300 Subject: net/mlx5: Remove a leftover unused variable mlx5_core_wq is no longer being used and should be removed from the code. Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d26f18b39c4a..d5b6f6a9fcc5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -890,8 +890,6 @@ static inline void *mlx5_buf_offset(struct mlx5_buf *buf, int offset) return buf->direct.buf + offset; } -extern struct workqueue_struct *mlx5_core_wq; - #define STRUCT_FIELD(header, field) \ .struct_offset_bytes = offsetof(struct ib_unpacked_ ## header, field), \ .struct_size_bytes = sizeof((struct ib_unpacked_ ## header *)0)->field -- cgit v1.2.3 From 667cb65ae5ad01523505d48d6cfd92bd1d3c9785 Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Mon, 7 Aug 2017 11:14:11 +0300 Subject: net/mlx5: Don't store reserved part in FTEs and FGs The current code stores fte_match_param in the software representation of FTEs and FGs. fte_match_param contains a large reserved area at the bottom of the struct. Since downstream patches are going to hash this part, we would like to avoid doing so on a reserved part. Signed-off-by: Matan Barak Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f31a0b5377e1..3c7442b56460 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -48,7 +48,7 @@ /* helper macros */ #define __mlx5_nullp(typ) ((struct mlx5_ifc_##typ##_bits *)0) #define __mlx5_bit_sz(typ, fld) sizeof(__mlx5_nullp(typ)->fld) -#define __mlx5_bit_off(typ, fld) ((unsigned)(unsigned long)(&(__mlx5_nullp(typ)->fld))) +#define __mlx5_bit_off(typ, fld) (offsetof(struct mlx5_ifc_##typ##_bits, fld)) #define __mlx5_dw_off(typ, fld) (__mlx5_bit_off(typ, fld) / 32) #define __mlx5_64_off(typ, fld) (__mlx5_bit_off(typ, fld) / 64) #define __mlx5_dw_bit_off(typ, fld) (32 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0x1f)) -- cgit v1.2.3 From 50b4d485528d1dbe0bd249f2073140e3444f4a7b Mon Sep 17 00:00:00 2001 From: Benjamin Block Date: Thu, 24 Aug 2017 01:57:56 +0200 Subject: bsg-lib: fix kernel panic resulting from missing allocation of reply-buffer Since we split the scsi_request out of struct request bsg fails to provide a reply-buffer for the drivers. This was done via the pointer for sense-data, that is not preallocated anymore. Failing to allocate/assign it results in illegal dereferences because LLDs use this pointer unquestioned. An example panic on s390x, using the zFCP driver, looks like this (I had debugging on, otherwise NULL-pointer dereferences wouldn't even panic on s390x): Unable to handle kernel pointer dereference in virtual kernel address space Failing address: 6b6b6b6b6b6b6000 TEID: 6b6b6b6b6b6b6403 Fault in home space mode while using kernel ASCE. AS:0000000001590007 R3:0000000000000024 Oops: 0038 ilc:2 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.12.0-bsg-regression+ #3 Hardware name: IBM 2964 N96 702 (z/VM 6.4.0) task: 0000000065cb0100 task.stack: 0000000065cb4000 Krnl PSW : 0704e00180000000 000003ff801e4156 (zfcp_fc_ct_els_job_handler+0x16/0x58 [zfcp]) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:2 PM:0 RI:0 EA:3 Krnl GPRS: 0000000000000001 000000005fa9d0d0 000000005fa9d078 0000000000e16866 000003ff00000290 6b6b6b6b6b6b6b6b 0000000059f78f00 000000000000000f 00000000593a0958 00000000593a0958 0000000060d88800 000000005ddd4c38 0000000058b50100 07000000659cba08 000003ff801e8556 00000000659cb9a8 Krnl Code: 000003ff801e4146: e31020500004 lg %r1,80(%r2) 000003ff801e414c: 58402040 l %r4,64(%r2) #000003ff801e4150: e35020200004 lg %r5,32(%r2) >000003ff801e4156: 50405004 st %r4,4(%r5) 000003ff801e415a: e54c50080000 mvhi 8(%r5),0 000003ff801e4160: e33010280012 lt %r3,40(%r1) 000003ff801e4166: a718fffb lhi %r1,-5 000003ff801e416a: 1803 lr %r0,%r3 Call Trace: ([<000003ff801e8556>] zfcp_fsf_req_complete+0x726/0x768 [zfcp]) [<000003ff801ea82a>] zfcp_fsf_reqid_check+0x102/0x180 [zfcp] [<000003ff801eb980>] zfcp_qdio_int_resp+0x230/0x278 [zfcp] [<00000000009b91b6>] qdio_kick_handler+0x2ae/0x2c8 [<00000000009b9e3e>] __tiqdio_inbound_processing+0x406/0xc10 [<00000000001684c2>] tasklet_action+0x15a/0x1d8 [<0000000000bd28ec>] __do_softirq+0x3ec/0x848 [<00000000001675a4>] irq_exit+0x74/0xf8 [<000000000010dd6a>] do_IRQ+0xba/0xf0 [<0000000000bd19e8>] io_int_handler+0x104/0x2d4 [<00000000001033b6>] enabled_wait+0xb6/0x188 ([<000000000010339e>] enabled_wait+0x9e/0x188) [<000000000010396a>] arch_cpu_idle+0x32/0x50 [<0000000000bd0112>] default_idle_call+0x52/0x68 [<00000000001cd0fa>] do_idle+0x102/0x188 [<00000000001cd41e>] cpu_startup_entry+0x3e/0x48 [<0000000000118c64>] smp_start_secondary+0x11c/0x130 [<0000000000bd2016>] restart_int_handler+0x62/0x78 [<0000000000000000>] (null) INFO: lockdep is turned off. Last Breaking-Event-Address: [<000003ff801e41d6>] zfcp_fc_ct_job_handler+0x3e/0x48 [zfcp] Kernel panic - not syncing: Fatal exception in interrupt This patch moves bsg-lib to allocate and setup struct bsg_job ahead of time, including the allocation of a buffer for the reply-data. This means, struct bsg_job is not allocated separately anymore, but as part of struct request allocation - similar to struct scsi_cmd. Reflect this in the function names that used to handle creation/destruction of struct bsg_job. Reported-by: Steffen Maier Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Signed-off-by: Benjamin Block Fixes: 82ed4db499b8 ("block: split scsi_request out of struct request") Cc: #4.11+ Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - include/linux/bsg-lib.h | 2 ++ 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 25f6a0cb27d3..2a5d52fa90f5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -568,7 +568,6 @@ struct request_queue { #if defined(CONFIG_BLK_DEV_BSG) bsg_job_fn *bsg_job_fn; - int bsg_job_size; struct bsg_class_device bsg_dev; #endif diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index e34dde2da0ef..637a20cfb237 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -24,6 +24,7 @@ #define _BLK_BSG_ #include +#include struct request; struct device; @@ -37,6 +38,7 @@ struct bsg_buffer { }; struct bsg_job { + struct scsi_request sreq; struct device *dev; struct request *req; -- cgit v1.2.3 From ea369ea6d828930c0cf0cacf81f6fd9dff61992d Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Wed, 23 Aug 2017 02:33:04 +0200 Subject: rtc: remove .open() and .release() There are no driver left using .open and .release. There is no good use case for them as there is nothing the character device interface does that should not be done in the sysfs interface or in-kernel interface. Remove those callbacks now to avoid future confusion. Signed-off-by: Alexandre Belloni --- include/linux/rtc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 0a0f0d14a5fb..e6d0f9c1cafd 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -72,8 +72,6 @@ extern struct class *rtc_class; * issued through ioctl() ... */ struct rtc_class_ops { - int (*open)(struct device *); - void (*release)(struct device *); int (*ioctl)(struct device *, unsigned int, unsigned long); int (*read_time)(struct device *, struct rtc_time *); int (*set_time)(struct device *, struct rtc_time *); -- cgit v1.2.3 From 2facaad6000f2322eb40ca379aced31c957f0a41 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Thu, 24 Aug 2017 12:33:08 +0200 Subject: xdp: make generic xdp redirect use tracepoint trace_xdp_redirect If the xdp_do_generic_redirect() call fails, it trigger the trace_xdp_exception tracepoint. It seems better to use the same tracepoint trace_xdp_redirect, as the native xdp_do_redirect{,_map} does. Signed-off-by: Jesper Dangaard Brouer Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/filter.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 7015116331af..d29e58fde364 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -718,7 +718,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, * because we only track one map and force a flush when the map changes. * This does not appear to be a real limitation for existing software. */ -int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb); +int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); -- cgit v1.2.3 From 311fc65c9fb9c966bca8e6f3ff8132ce57344ab9 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 24 Aug 2017 15:13:29 -0500 Subject: pty: Repair TIOCGPTPEER The implementation of TIOCGPTPEER has two issues. When /dev/ptmx (as opposed to /dev/pts/ptmx) is opened the wrong vfsmount is passed to dentry_open. Which results in the kernel displaying the wrong pathname for the peer. The second is simply by caching the vfsmount and dentry of the peer it leaves them open, in a way they were not previously Which because of the inreased reference counts can cause unnecessary behaviour differences resulting in regressions. To fix these move the ioctl into tty_io.c at a generic level allowing the ioctl to have access to the struct file on which the ioctl is being called. This allows the path of the slave to be derived when opening the slave through TIOCGPTPEER instead of requiring the path to the slave be cached. Thus removing the need for caching the path. A new function devpts_ptmx_path is factored out of devpts_acquire and used to implement a function devpts_mntget. The new function devpts_mntget takes a filp to perform the lookup on and fsi so that it can confirm that the superblock that is found by devpts_ptmx_path is the proper superblock. v2: Lots of fixes to make the code actually work v3: Suggestions by Linus - Removed the unnecessary initialization of filp in ptm_open_peer - Simplified devpts_ptmx_path as gotos are no longer required [ This is the fix for the issue that was reverted in commit 143c97cc6529, but this time without breaking 'pbuilder' due to increased reference counts - Linus ] Fixes: 54ebbfb16034 ("tty: add TIOCGPTPEER ioctl") Reported-by: Christian Brauner Reported-and-tested-by: Stefan Lippers-Hollmann Signed-off-by: "Eric W. Biederman" Signed-off-by: Linus Torvalds --- include/linux/devpts_fs.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 277ab9af9ac2..100cb4343763 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,6 +19,7 @@ struct pts_fs_info; +struct vfsmount *devpts_mntget(struct file *, struct pts_fs_info *); struct pts_fs_info *devpts_acquire(struct file *); void devpts_release(struct pts_fs_info *); @@ -32,6 +33,15 @@ void *devpts_get_priv(struct dentry *); /* unlink */ void devpts_pty_kill(struct dentry *); +/* in pty.c */ +int ptm_open_peer(struct file *master, struct tty_struct *tty, int flags); + +#else +static inline int +ptm_open_peer(struct file *master, struct tty_struct *tty, int flags) +{ + return -EIO; +} #endif -- cgit v1.2.3 From 8b7ff7f3b301de52924cb2cf3fed47b181893116 Mon Sep 17 00:00:00 2001 From: Ilya Lesokhin Date: Thu, 17 Aug 2017 15:52:29 +0300 Subject: IB/mlx5: Enable UMR for MRs created with reg_create This patch is the first step in decoupling UMR usage and allocation from the MR cache. The only functional change in this patch is to enables UMR for MRs created with reg_create. This change fixes a bug where ODP memory regions that were not allocated from the MR cache did not have UMR enabled. Signed-off-by: Ilya Lesokhin Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index db40bc4055c7..99d88624ad07 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1093,7 +1093,7 @@ enum { }; enum { - MAX_UMR_CACHE_ENTRY = 20, + MR_CACHE_LAST_STD_ENTRY = 20, MLX5_IMR_MTT_CACHE_ENTRY, MLX5_IMR_KSM_CACHE_ENTRY, MAX_MR_CACHE_ENTRIES -- cgit v1.2.3 From a550ddfc543e250798048cf4eabe721cd85ac724 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 17 Aug 2017 15:52:33 +0300 Subject: IB/mlx5: Add support for multi underlay QP Set underlay QPN as part of flow rule when it's applicable. There is one root flow table in the NIC RX namespace and all the underlay QPs steer the traffic to this flow table. In order to prevent QP to get traffic which is not target to its underlay QP, we need to set the underlay QP number as part of the steering matching. Note: When multicast traffic is sent the QPN filtering is done by the firmware as some early step. Adding the QPN match on the flow table entry is wrong as by that time the target QPN holds the multicast address (e.g. FF(s)) and it won't match. Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 5bae70eb25af..6563500c85de 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -295,8 +295,10 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 inner_tcp_dport[0x1]; u8 inner_tcp_flags[0x1]; u8 reserved_at_37[0x9]; + u8 reserved_at_40[0x1a]; + u8 bth_dst_qp[0x1]; - u8 reserved_at_40[0x40]; + u8 reserved_at_5b[0x25]; }; struct mlx5_ifc_flow_table_prop_layout_bits { @@ -432,7 +434,9 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_100[0xc]; u8 inner_ipv6_flow_label[0x14]; - u8 reserved_at_120[0xe0]; + u8 reserved_at_120[0x28]; + u8 bth_dst_qp[0x18]; + u8 reserved_at_160[0xa0]; }; struct mlx5_ifc_cmd_pas_bits { -- cgit v1.2.3 From 795b609c8b59f8f20fa9d72bf8b4ae3b8aa5582c Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Thu, 17 Aug 2017 15:52:34 +0300 Subject: IB/mlx5: Allow posting multi packet send WQEs if hardware supports Set the field to allow posting multi packet send WQEs if hardware supports this feature. This doesn't mean the send WQEs will be for multi packet unless the send WQE was prepared according to multi packet send WQE format. User space shall use flag MLX5_IB_ALLOW_MPW to check if hardware supports MPW and allows MPW in SQ context. Signed-off-by: Bodong Wang Reviewed-by: Daniel Jurgens Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6563500c85de..6865e60ba473 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2445,7 +2445,7 @@ struct mlx5_ifc_sqc_bits { u8 cd_master[0x1]; u8 fre[0x1]; u8 flush_in_error_en[0x1]; - u8 reserved_at_4[0x1]; + u8 allow_multi_pkt_send_wqe[0x1]; u8 min_wqe_inline_mode[0x3]; u8 state[0x4]; u8 reg_umr[0x1]; -- cgit v1.2.3 From 050da902adde8faf6b1bef15ac4876ae145358f4 Mon Sep 17 00:00:00 2001 From: Bodong Wang Date: Thu, 17 Aug 2017 15:52:35 +0300 Subject: IB/mlx5: Report mlx5 enhanced multi packet WQE capability Expose enhanced multi packet WQE capability to user space through query_device by uhw. Signed-off-by: Bodong Wang Reviewed-by: Daniel Jurgens Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6865e60ba473..4eff0b8a1482 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -604,7 +604,7 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 rss_ind_tbl_cap[0x4]; u8 reg_umr_sq[0x1]; u8 scatter_fcs[0x1]; - u8 reserved_at_1a[0x1]; + u8 enhanced_multi_pkt_send_wqe[0x1]; u8 tunnel_lso_const_out_ip_id[0x1]; u8 reserved_at_1c[0x2]; u8 tunnel_statless_gre[0x1]; -- cgit v1.2.3 From 2412e927604e0af7e17ae4b688b85a1e87e378fe Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Aug 2017 11:59:49 -0400 Subject: sunrpc: Const-ify instances of struct svc_xprt_ops Close an attack vector by moving the arrays of server-side transport methods to read-only memory. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc_xprt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index ddb7f94a9d06..6a2ad38f5458 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -31,7 +31,7 @@ struct svc_xprt_ops { struct svc_xprt_class { const char *xcl_name; struct module *xcl_owner; - struct svc_xprt_ops *xcl_ops; + const struct svc_xprt_ops *xcl_ops; struct list_head xcl_list; u32 xcl_max_payload; int xcl_ident; @@ -49,7 +49,7 @@ struct svc_xpt_user { struct svc_xprt { struct svc_xprt_class *xpt_class; - struct svc_xprt_ops *xpt_ops; + const struct svc_xprt_ops *xpt_ops; struct kref xpt_ref; struct list_head xpt_list; struct list_head xpt_ready; -- cgit v1.2.3 From afea5657c20b11ec9f895ac5cc33b560fb1e0276 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 1 Aug 2017 12:00:06 -0400 Subject: sunrpc: Const-ify struct sv_serv_ops Close an attack vector by moving the arrays of per-server methods to read-only memory. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index a3f8af9bd543..38f561b2dda3 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -99,7 +99,7 @@ struct svc_serv { unsigned int sv_nrpools; /* number of thread pools */ struct svc_pool * sv_pools; /* array of thread pools */ - struct svc_serv_ops *sv_ops; /* server operations */ + const struct svc_serv_ops *sv_ops; /* server operations */ #if defined(CONFIG_SUNRPC_BACKCHANNEL) struct list_head sv_cb_list; /* queue for callback requests * that arrive over the same @@ -465,7 +465,7 @@ int svc_rpcb_setup(struct svc_serv *serv, struct net *net); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); struct svc_serv *svc_create(struct svc_program *, unsigned int, - struct svc_serv_ops *); + const struct svc_serv_ops *); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, @@ -475,7 +475,7 @@ void svc_exit_thread(struct svc_rqst *); unsigned int svc_pool_map_get(void); void svc_pool_map_put(void); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, - struct svc_serv_ops *); + const struct svc_serv_ops *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -- cgit v1.2.3 From 0e709703af5bbc9ea6e75e1f99c2dd0dae261869 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 11 Aug 2017 16:04:50 +0200 Subject: mm, locking/barriers: Clarify tlb_flush_pending() barriers Better document the ordering around tlb_flush_pending(). Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/mm_types.h | 78 ++++++++++++++++++++++++++++-------------------- 1 file changed, 45 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index dc1edec05a3f..57378c7cb5f8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -526,30 +526,6 @@ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, extern void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end); -/* - * Memory barriers to keep this state in sync are graciously provided by - * the page table locks, outside of which no page table modifications happen. - * The barriers are used to ensure the order between tlb_flush_pending updates, - * which happen while the lock is not taken, and the PTE updates, which happen - * while the lock is taken, are serialized. - */ -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) -{ - /* - * Must be called with PTL held; such that our PTL acquire will have - * observed the store from set_tlb_flush_pending(). - */ - return atomic_read(&mm->tlb_flush_pending) > 0; -} - -/* - * Returns true if there are two above TLB batching threads in parallel. - */ -static inline bool mm_tlb_flush_nested(struct mm_struct *mm) -{ - return atomic_read(&mm->tlb_flush_pending) > 1; -} - static inline void init_tlb_flush_pending(struct mm_struct *mm) { atomic_set(&mm->tlb_flush_pending, 0); @@ -558,7 +534,6 @@ static inline void init_tlb_flush_pending(struct mm_struct *mm) static inline void inc_tlb_flush_pending(struct mm_struct *mm) { atomic_inc(&mm->tlb_flush_pending); - /* * The only time this value is relevant is when there are indeed pages * to flush. And we'll only flush pages after changing them, which @@ -580,24 +555,61 @@ static inline void inc_tlb_flush_pending(struct mm_struct *mm) * flush_tlb_range(); * atomic_dec(&mm->tlb_flush_pending); * - * So the =true store is constrained by the PTL unlock, and the =false - * store is constrained by the TLB invalidate. + * Where the increment if constrained by the PTL unlock, it thus + * ensures that the increment is visible if the PTE modification is + * visible. After all, if there is no PTE modification, nobody cares + * about TLB flushes either. + * + * This very much relies on users (mm_tlb_flush_pending() and + * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and + * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc + * locks (PPC) the unlock of one doesn't order against the lock of + * another PTL. + * + * The decrement is ordered by the flush_tlb_range(), such that + * mm_tlb_flush_pending() will not return false unless all flushes have + * completed. */ } -/* Clearing is done after a TLB flush, which also provides a barrier. */ static inline void dec_tlb_flush_pending(struct mm_struct *mm) { /* - * Guarantee that the tlb_flush_pending does not not leak into the - * critical section, since we must order the PTE change and changes to - * the pending TLB flush indication. We could have relied on TLB flush - * as a memory barrier, but this behavior is not clearly documented. + * See inc_tlb_flush_pending(). + * + * This cannot be smp_mb__before_atomic() because smp_mb() simply does + * not order against TLB invalidate completion, which is what we need. + * + * Therefore we must rely on tlb_flush_*() to guarantee order. */ - smp_mb__before_atomic(); atomic_dec(&mm->tlb_flush_pending); } +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * Must be called after having acquired the PTL; orders against that + * PTLs release and therefore ensures that if we observe the modified + * PTE we must also observe the increment from inc_tlb_flush_pending(). + * + * That is, it only guarantees to return true if there is a flush + * pending for _this_ PTL. + */ + return atomic_read(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +{ + /* + * Similar to mm_tlb_flush_pending(), we must have acquired the PTL + * for which there is a TLB flush pending in order to guarantee + * we've seen both that PTE modification and the increment. + * + * (no requirement on actually still holding the PTL, that is irrelevant) + */ + return atomic_read(&mm->tlb_flush_pending) > 1; +} + struct vm_fault; struct vm_special_mapping { -- cgit v1.2.3 From e6f3faa734a00c606b7b06c6b9f15e5627d3245b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 23 Aug 2017 13:23:30 +0200 Subject: locking/lockdep: Fix workqueue crossrelease annotation The new completion/crossrelease annotations interact unfavourable with the extant flush_work()/flush_workqueue() annotations. The problem is that when a single work class does: wait_for_completion(&C) and complete(&C) in different executions, we'll build dependencies like: lock_map_acquire(W) complete_acquire(C) and lock_map_acquire(W) complete_release(C) which results in the dependency chain: W->C->W, which lockdep thinks spells deadlock, even though there is no deadlock potential since works are ran concurrently. One possibility would be to change the work 'lock' to recursive-read, but that would mean hitting a lockdep limitation on recursive locks. Also, unconditinoally switching to recursive-read here would fail to detect the actual deadlock on single-threaded workqueues, which do have a problem with this. For now, forcefully disregard these locks for crossrelease. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: boqun.feng@gmail.com Cc: byungchul.park@lge.com Cc: david@fromorbit.com Cc: johannes@sipsolutions.net Cc: oleg@redhat.com Signed-off-by: Ingo Molnar --- include/linux/irqflags.h | 4 ++-- include/linux/lockdep.h | 10 ++++++---- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 5fdd93bb9300..9bc050bc81b2 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -26,7 +26,7 @@ # define trace_hardirq_enter() \ do { \ current->hardirq_context++; \ - crossrelease_hist_start(XHLOCK_HARD); \ + crossrelease_hist_start(XHLOCK_HARD, 0);\ } while (0) # define trace_hardirq_exit() \ do { \ @@ -36,7 +36,7 @@ do { \ # define lockdep_softirq_enter() \ do { \ current->softirq_context++; \ - crossrelease_hist_start(XHLOCK_SOFT); \ + crossrelease_hist_start(XHLOCK_SOFT, 0);\ } while (0) # define lockdep_softirq_exit() \ do { \ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index fc827cab6d6e..78bb7133abed 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -18,6 +18,8 @@ extern int lock_stat; #define MAX_LOCKDEP_SUBCLASSES 8UL +#include + #ifdef CONFIG_LOCKDEP #include @@ -578,11 +580,11 @@ extern void lock_commit_crosslock(struct lockdep_map *lock); #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), .cross = 0, } -extern void crossrelease_hist_start(enum xhlock_context_t c); +extern void crossrelease_hist_start(enum xhlock_context_t c, bool force); extern void crossrelease_hist_end(enum xhlock_context_t c); extern void lockdep_init_task(struct task_struct *task); extern void lockdep_free_task(struct task_struct *task); -#else +#else /* !CROSSRELEASE */ #define lockdep_init_map_crosslock(m, n, k, s) do {} while (0) /* * To initialize a lockdep_map statically use this macro. @@ -591,11 +593,11 @@ extern void lockdep_free_task(struct task_struct *task); #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), } -static inline void crossrelease_hist_start(enum xhlock_context_t c) {} +static inline void crossrelease_hist_start(enum xhlock_context_t c, bool force) {} static inline void crossrelease_hist_end(enum xhlock_context_t c) {} static inline void lockdep_init_task(struct task_struct *task) {} static inline void lockdep_free_task(struct task_struct *task) {} -#endif +#endif /* CROSSRELEASE */ #ifdef CONFIG_LOCK_STAT -- cgit v1.2.3 From 5237e95f63761477b7ea45499d08b89383a77eab Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Mon, 24 Jul 2017 18:29:27 +0100 Subject: dma-mapping: reduce dma_mapping_error inline bloat Thanks to the nested inlining, all drivers correctly calling dma_mapping_error() after a mapping a page or single buffer generate two calls to get_arch_dma_ops() per callsite, which all adds up to a fair old chunk of useless code, e.g. ~3KB for an arm64 defconfig plus extras: text data bss dec hex filename 13051391 1503898 327768 14883057 e318f1 vmlinux.o.old 13050751 1503898 327768 14882417 e31671 vmlinux.o.new Give the compiler a hand by making it clear we want the same ops. Signed-off-by: Robin Murphy Reviewed-by: Marek Szyprowski Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 03c0196a6f24..66d8ea68f40b 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -565,10 +565,11 @@ static inline void dma_free_noncoherent(struct device *dev, size_t size, static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - debug_dma_mapping_error(dev, dma_addr); + const struct dma_map_ops *ops = get_dma_ops(dev); - if (get_dma_ops(dev)->mapping_error) - return get_dma_ops(dev)->mapping_error(dev, dma_addr); + debug_dma_mapping_error(dev, dma_addr); + if (ops->mapping_error) + return ops->mapping_error(dev, dma_addr); return 0; } -- cgit v1.2.3 From fbb113f773482496d601e0bd934e680b35876016 Mon Sep 17 00:00:00 2001 From: Stefan Assmann Date: Thu, 29 Jun 2017 15:12:24 +0200 Subject: i40e/i40evf: rename vf_offload_flags to vf_cap_flags in struct virtchnl_vf_resource The current name of vf_offload_flags indicates that the bitmap is limited to offload related features. Make this more generic by renaming it to vf_cap_flags, which allows for other capabilities besides offloading to be added. Signed-off-by: Stefan Assmann Tested-by: Andrew Bowers Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index c893b9520a67..becfca2ae94e 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -223,7 +223,7 @@ struct virtchnl_vsi_resource { VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); -/* VF offload flags +/* VF capability flags * VIRTCHNL_VF_OFFLOAD_L2 flag is inclusive of base mode L2 offloads including * TX/RX Checksum offloading and TSO for non-tunnelled packets. */ @@ -251,7 +251,7 @@ struct virtchnl_vf_resource { u16 max_vectors; u16 max_mtu; - u32 vf_offload_flags; + u32 vf_cap_flags; u32 rss_key_size; u32 rss_lut_size; -- cgit v1.2.3 From ccc829ba3624beb9a703fc995d016b836d9eead8 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Fri, 25 Aug 2017 16:50:15 +0100 Subject: efi/libstub: Enable reset attack mitigation If a machine is reset while secrets are present in RAM, it may be possible for code executed after the reboot to extract those secrets from untouched memory. The Trusted Computing Group specified a mechanism for requesting that the firmware clear all RAM on reset before booting another OS. This is done by setting the MemoryOverwriteRequestControl variable at startup. If userspace can ensure that all secrets are removed as part of a controlled shutdown, it can reset this variable to 0 before triggering a hardware reboot. Signed-off-by: Matthew Garrett Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20170825155019.6740-2-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 4e47f78430be..c241acca0b15 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1504,6 +1504,13 @@ enum efi_secureboot_mode { }; enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table); +#ifdef CONFIG_RESET_ATTACK_MITIGATION +void efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg); +#else +static inline void +efi_enable_reset_attack_mitigation(efi_system_table_t *sys_table_arg) { } +#endif + /* * Arch code can implement the following three template macros, avoiding * reptition for the void/non-void return cases of {__,}efi_call_virt(): -- cgit v1.2.3 From c2ceb5fd4e921506e86208b82fca716a2c3aad59 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 25 Aug 2017 16:50:16 +0100 Subject: efi/random: Increase size of firmware supplied randomness The crng code requires at least 64 bytes (2 * CHACHA20_BLOCK_SIZE) to complete the fast boot-time init, so provide that many bytes when invoking UEFI protocols to seed the entropy pool. Also, add a notice so we can tell from the boot log when the seeding actually took place. Signed-off-by: Ard Biesheuvel Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20170825155019.6740-3-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- include/linux/efi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index c241acca0b15..33d41df062bc 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1571,6 +1571,8 @@ efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table, void *priv, efi_exit_boot_map_processing priv_func); +#define EFI_RANDOM_SEED_SIZE 64U + struct linux_efi_random_seed { u32 size; u8 bits[]; -- cgit v1.2.3 From a1cc5a57e49e871ce5e610597af1bd6bea06cb5c Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Sun, 13 Aug 2017 16:21:17 +0200 Subject: blackfin: merge the two TWI header files There seems to be no need for separate ones since all users include both files anyhow. Merge them because include/linux/i2c is to be deprecated. Signed-off-by: Wolfram Sang --- include/linux/i2c/bfin_twi.h | 145 ------------------------------------------- 1 file changed, 145 deletions(-) delete mode 100644 include/linux/i2c/bfin_twi.h (limited to 'include/linux') diff --git a/include/linux/i2c/bfin_twi.h b/include/linux/i2c/bfin_twi.h deleted file mode 100644 index 135a4e0876ae..000000000000 --- a/include/linux/i2c/bfin_twi.h +++ /dev/null @@ -1,145 +0,0 @@ -/* - * i2c-bfin-twi.h - interface to ADI TWI controller - * - * Copyright 2005-2014 Analog Devices Inc. - * - * Licensed under the GPL-2 or later. - */ - -#ifndef __I2C_BFIN_TWI_H__ -#define __I2C_BFIN_TWI_H__ - -#include -#include - -/* - * ADI twi registers layout - */ -struct bfin_twi_regs { - u16 clkdiv; - u16 dummy1; - u16 control; - u16 dummy2; - u16 slave_ctl; - u16 dummy3; - u16 slave_stat; - u16 dummy4; - u16 slave_addr; - u16 dummy5; - u16 master_ctl; - u16 dummy6; - u16 master_stat; - u16 dummy7; - u16 master_addr; - u16 dummy8; - u16 int_stat; - u16 dummy9; - u16 int_mask; - u16 dummy10; - u16 fifo_ctl; - u16 dummy11; - u16 fifo_stat; - u16 dummy12; - u32 __pad[20]; - u16 xmt_data8; - u16 dummy13; - u16 xmt_data16; - u16 dummy14; - u16 rcv_data8; - u16 dummy15; - u16 rcv_data16; - u16 dummy16; -}; - -struct bfin_twi_iface { - int irq; - spinlock_t lock; - char read_write; - u8 command; - u8 *transPtr; - int readNum; - int writeNum; - int cur_mode; - int manual_stop; - int result; - struct i2c_adapter adap; - struct completion complete; - struct i2c_msg *pmsg; - int msg_num; - int cur_msg; - u16 saved_clkdiv; - u16 saved_control; - struct bfin_twi_regs __iomem *regs_base; -}; - -/* ******************** TWO-WIRE INTERFACE (TWI) MASKS ********************/ -/* TWI_CLKDIV Macros (Use: *pTWI_CLKDIV = CLKLOW(x)|CLKHI(y); ) */ -#define CLKLOW(x) ((x) & 0xFF) /* Periods Clock Is Held Low */ -#define CLKHI(y) (((y)&0xFF)<<0x8) /* Periods Before New Clock Low */ - -/* TWI_PRESCALE Masks */ -#define PRESCALE 0x007F /* SCLKs Per Internal Time Reference (10MHz) */ -#define TWI_ENA 0x0080 /* TWI Enable */ -#define SCCB 0x0200 /* SCCB Compatibility Enable */ - -/* TWI_SLAVE_CTL Masks */ -#define SEN 0x0001 /* Slave Enable */ -#define SADD_LEN 0x0002 /* Slave Address Length */ -#define STDVAL 0x0004 /* Slave Transmit Data Valid */ -#define NAK 0x0008 /* NAK Generated At Conclusion Of Transfer */ -#define GEN 0x0010 /* General Call Address Matching Enabled */ - -/* TWI_SLAVE_STAT Masks */ -#define SDIR 0x0001 /* Slave Transfer Direction (RX/TX*) */ -#define GCALL 0x0002 /* General Call Indicator */ - -/* TWI_MASTER_CTL Masks */ -#define MEN 0x0001 /* Master Mode Enable */ -#define MADD_LEN 0x0002 /* Master Address Length */ -#define MDIR 0x0004 /* Master Transmit Direction (RX/TX*) */ -#define FAST 0x0008 /* Use Fast Mode Timing Specs */ -#define STOP 0x0010 /* Issue Stop Condition */ -#define RSTART 0x0020 /* Repeat Start or Stop* At End Of Transfer */ -#define DCNT 0x3FC0 /* Data Bytes To Transfer */ -#define SDAOVR 0x4000 /* Serial Data Override */ -#define SCLOVR 0x8000 /* Serial Clock Override */ - -/* TWI_MASTER_STAT Masks */ -#define MPROG 0x0001 /* Master Transfer In Progress */ -#define LOSTARB 0x0002 /* Lost Arbitration Indicator (Xfer Aborted) */ -#define ANAK 0x0004 /* Address Not Acknowledged */ -#define DNAK 0x0008 /* Data Not Acknowledged */ -#define BUFRDERR 0x0010 /* Buffer Read Error */ -#define BUFWRERR 0x0020 /* Buffer Write Error */ -#define SDASEN 0x0040 /* Serial Data Sense */ -#define SCLSEN 0x0080 /* Serial Clock Sense */ -#define BUSBUSY 0x0100 /* Bus Busy Indicator */ - -/* TWI_INT_SRC and TWI_INT_ENABLE Masks */ -#define SINIT 0x0001 /* Slave Transfer Initiated */ -#define SCOMP 0x0002 /* Slave Transfer Complete */ -#define SERR 0x0004 /* Slave Transfer Error */ -#define SOVF 0x0008 /* Slave Overflow */ -#define MCOMP 0x0010 /* Master Transfer Complete */ -#define MERR 0x0020 /* Master Transfer Error */ -#define XMTSERV 0x0040 /* Transmit FIFO Service */ -#define RCVSERV 0x0080 /* Receive FIFO Service */ - -/* TWI_FIFO_CTRL Masks */ -#define XMTFLUSH 0x0001 /* Transmit Buffer Flush */ -#define RCVFLUSH 0x0002 /* Receive Buffer Flush */ -#define XMTINTLEN 0x0004 /* Transmit Buffer Interrupt Length */ -#define RCVINTLEN 0x0008 /* Receive Buffer Interrupt Length */ - -/* TWI_FIFO_STAT Masks */ -#define XMTSTAT 0x0003 /* Transmit FIFO Status */ -#define XMT_EMPTY 0x0000 /* Transmit FIFO Empty */ -#define XMT_HALF 0x0001 /* Transmit FIFO Has 1 Byte To Write */ -#define XMT_FULL 0x0003 /* Transmit FIFO Full (2 Bytes To Write) */ - -#define RCVSTAT 0x000C /* Receive FIFO Status */ -#define RCV_EMPTY 0x0000 /* Receive FIFO Empty */ -#define RCV_HALF 0x0004 /* Receive FIFO Has 1 Byte To Read */ -#define RCV_FULL 0x000C /* Receive FIFO Full (2 Bytes To Read) */ - -#endif -- cgit v1.2.3 From 83b2a3c2ab24561cb6de45e6b155e3a7c4c1c91b Mon Sep 17 00:00:00 2001 From: Pierre-Hugues Husson Date: Sun, 27 Aug 2017 15:58:31 +0200 Subject: regulator: rn5t618: add RC5T619 PMIC support Extend the driver to support Ricoh RC5T619. Support the additional regulators and slightly different voltage ranges. Signed-off-by: Pierre-Hugues Husson Signed-off-by: Mark Brown --- include/linux/mfd/rn5t618.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/rn5t618.h b/include/linux/mfd/rn5t618.h index e5a6cdeb77db..d61bc58aba8a 100644 --- a/include/linux/mfd/rn5t618.h +++ b/include/linux/mfd/rn5t618.h @@ -226,11 +226,17 @@ enum { RN5T618_DCDC2, RN5T618_DCDC3, RN5T618_DCDC4, + RN5T618_DCDC5, RN5T618_LDO1, RN5T618_LDO2, RN5T618_LDO3, RN5T618_LDO4, RN5T618_LDO5, + RN5T618_LDO6, + RN5T618_LDO7, + RN5T618_LDO8, + RN5T618_LDO9, + RN5T618_LDO10, RN5T618_LDORTC1, RN5T618_LDORTC2, RN5T618_REG_NUM, -- cgit v1.2.3 From 0cc3b0ec23ce4c69e1e890ed2b8d2fa932b14aad Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 27 Aug 2017 12:12:25 -0700 Subject: Clarify (and fix) MAX_LFS_FILESIZE macros We have a MAX_LFS_FILESIZE macro that is meant to be filled in by filesystems (and other IO targets) that know they are 64-bit clean and don't have any 32-bit limits in their IO path. It turns out that our 32-bit value for that limit was bogus. On 32-bit, the VM layer is limited by the page cache to only 32-bit index values, but our logic for that was confusing and actually wrong. We used to define that value to (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1) which is actually odd in several ways: it limits the index to 31 bits, and then it limits files so that they can't have data in that last byte of a page that has the highest 31-bit index (ie page index 0x7fffffff). Neither of those limitations make sense. The index is actually the full 32 bit unsigned value, and we can use that whole full page. So the maximum size of the file would logically be "PAGE_SIZE << BITS_PER_LONG". However, we do wan tto avoid the maximum index, because we have code that iterates over the page indexes, and we don't want that code to overflow. So the maximum size of a file on a 32-bit host should actually be one page less than the full 32-bit index. So the actual limit is ULONG_MAX << PAGE_SHIFT. That means that we will not actually be using the page of that last index (ULONG_MAX), but we can grow a file up to that limit. The wrong value of MAX_LFS_FILESIZE actually caused problems for Doug Nazar, who was still using a 32-bit host, but with a 9.7TB 2 x RAID5 volume. It turns out that our old MAX_LFS_FILESIZE was 8TiB (well, one byte less), but the actual true VM limit is one page less than 16TiB. This was invisible until commit c2a9737f45e2 ("vfs,mm: fix a dead loop in truncate_inode_pages_range()"), which started applying that MAX_LFS_FILESIZE limit to block devices too. NOTE! On 64-bit, the page index isn't a limiter at all, and the limit is actually just the offset type itself (loff_t), which is signed. But for clarity, on 64-bit, just use the maximum signed value, and don't make people have to count the number of 'f' characters in the hex constant. So just use LLONG_MAX for the 64-bit case. That was what the value had been before too, just written out as a hex constant. Fixes: c2a9737f45e2 ("vfs,mm: fix a dead loop in truncate_inode_pages_range()") Reported-and-tested-by: Doug Nazar Cc: Andreas Dilger Cc: Mark Fasheh Cc: Joel Becker Cc: Dave Kleikamp Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e1fd5d21248..cbfe127bccf8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -907,9 +907,9 @@ static inline struct file *get_file(struct file *f) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 -#define MAX_LFS_FILESIZE (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1) +#define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 -#define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL) +#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif #define FL_POSIX 1 -- cgit v1.2.3 From 8774370d268f2f43d8487d230e0d4fa1647759b3 Mon Sep 17 00:00:00 2001 From: Mariusz Stachura Date: Mon, 17 Jul 2017 22:09:45 -0700 Subject: i40e/i40evf: support for VF VLAN tag stripping control This patch gives VF capability to control VLAN tag stripping via ethtool. As rx-vlan-offload was fixed before, now the VF is able to change it using "ethtool --offload rxvlan on/off" settings. Signed-off-by: Mariusz Stachura Signed-off-by: Jeff Kirsher --- include/linux/avf/virtchnl.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index becfca2ae94e..2b038442c352 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -133,6 +133,8 @@ enum virtchnl_ops { VIRTCHNL_OP_CONFIG_RSS_LUT = 24, VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25, VIRTCHNL_OP_SET_RSS_HENA = 26, + VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27, + VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28, }; /* This macro is used to generate a compilation error if a structure @@ -686,6 +688,9 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_SET_RSS_HENA: valid_len = sizeof(struct virtchnl_rss_hena); break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: -- cgit v1.2.3 From f75b0afa190d041c142bdc3f0c6022f61340b8a3 Mon Sep 17 00:00:00 2001 From: Chanwoo Choi Date: Thu, 24 Aug 2017 10:42:50 +0900 Subject: PM / devfreq: Move private devfreq_update_stats() into devfreq THe devfreq_update_stats() updates the 'struct devfreq_dev_status' in order to get current status of devfreq device. It is only used for the governors. This patch moves the devfreq_update_stats() into devfreq directory. Signed-off-by: Chanwoo Choi Signed-off-by: MyungJoo Ham --- include/linux/devfreq.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index 6c220e4ebb6b..597294e0cc40 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -214,19 +214,6 @@ extern void devm_devfreq_unregister_notifier(struct device *dev, extern struct devfreq *devfreq_get_devfreq_by_phandle(struct device *dev, int index); -/** - * devfreq_update_stats() - update the last_status pointer in struct devfreq - * @df: the devfreq instance whose status needs updating - * - * Governors are recommended to use this function along with last_status, - * which allows other entities to reuse the last_status without affecting - * the values fetched later by governors. - */ -static inline int devfreq_update_stats(struct devfreq *df) -{ - return df->profile->get_dev_status(df->dev.parent, &df->last_status); -} - #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq -- cgit v1.2.3 From 3e00ab4ac51c2ed47c28fd5000c47399f1a11cf5 Mon Sep 17 00:00:00 2001 From: Abhishek Sahu Date: Tue, 1 Aug 2017 19:41:42 +0530 Subject: dmaengine: add DMA_PREP_CMD for non-Data descriptors. Some of the DMA controllers are capable of issuing the commands to peripheral by the DMA. These commands can be list of register reads/writes and its different from normal data reads/writes. This patch adds new flag DMA_PREP_CMD in DMA API which tells the driver that the data passed to DMA API is command data and DMA controller driver will form descriptor in the required format. This flag can be used by any DMA controller driver which requires the descriptor in different format for non-Data descriptors. Signed-off-by: Abhishek Sahu Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 533680860865..dd4de1d40166 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -186,6 +186,9 @@ struct dma_interleaved_template { * on the result of this operation * @DMA_CTRL_REUSE: client can reuse the descriptor and submit again till * cleared or freed + * @DMA_PREP_CMD: tell the driver that the data passed to DMA API is command + * data and the descriptor should be in different format from normal + * data descriptors. */ enum dma_ctrl_flags { DMA_PREP_INTERRUPT = (1 << 0), @@ -195,6 +198,7 @@ enum dma_ctrl_flags { DMA_PREP_CONTINUE = (1 << 4), DMA_PREP_FENCE = (1 << 5), DMA_CTRL_REUSE = (1 << 6), + DMA_PREP_CMD = (1 << 7), }; /** -- cgit v1.2.3 From dfebb055f73a24e2c8756b837d9ce1a06457f5d7 Mon Sep 17 00:00:00 2001 From: Abhishek Sahu Date: Tue, 1 Aug 2017 19:41:43 +0530 Subject: dmaengine: qcom: bam_dma: wrapper functions for command descriptor QCOM BAM also supports command descriptor which allows the SW to create descriptors of type command which does not generate any data transmissions but configures registers in the peripheral. In command descriptor the 32bit address point to the start of the command block which holds the command elements and the 16bit size define the size of the command block. Each Command Element is structured by 4 words: Write command: address + cmd register data register mask reserved Read command: address + cmd read data result address, reserved reserved This patch creates a new header file for BAM driver which contains the structures and wrapper functions for command descriptor. This file will be used by different QCOM peripheral drivers for forming the command descriptor Signed-off-by: Abhishek Sahu Signed-off-by: Vinod Koul --- include/linux/dma/qcom_bam_dma.h | 79 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 79 insertions(+) create mode 100644 include/linux/dma/qcom_bam_dma.h (limited to 'include/linux') diff --git a/include/linux/dma/qcom_bam_dma.h b/include/linux/dma/qcom_bam_dma.h new file mode 100644 index 000000000000..077d43a358e5 --- /dev/null +++ b/include/linux/dma/qcom_bam_dma.h @@ -0,0 +1,79 @@ +/* + * Copyright (c) 2016-2017, The Linux Foundation. All rights reserved. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _QCOM_BAM_DMA_H +#define _QCOM_BAM_DMA_H + +#include + +/* + * This data type corresponds to the native Command Element + * supported by BAM DMA Engine. + * + * @cmd_and_addr - upper 8 bits command and lower 24 bits register address. + * @data - for write command: content to be written into peripheral register. + * for read command: dest addr to write peripheral register value. + * @mask - register mask. + * @reserved - for future usage. + * + */ +struct bam_cmd_element { + __le32 cmd_and_addr; + __le32 data; + __le32 mask; + __le32 reserved; +}; + +/* + * This enum indicates the command type in a command element + */ +enum bam_command_type { + BAM_WRITE_COMMAND = 0, + BAM_READ_COMMAND, +}; + +/* + * prep_bam_ce_le32 - Wrapper function to prepare a single BAM command + * element with the data already in le32 format. + * + * @bam_ce: bam command element + * @addr: target address + * @cmd: BAM command + * @data: actual data for write and dest addr for read in le32 + */ +static inline void +bam_prep_ce_le32(struct bam_cmd_element *bam_ce, u32 addr, + enum bam_command_type cmd, __le32 data) +{ + bam_ce->cmd_and_addr = + cpu_to_le32((addr & 0xffffff) | ((cmd & 0xff) << 24)); + bam_ce->data = data; + bam_ce->mask = cpu_to_le32(0xffffffff); +} + +/* + * bam_prep_ce - Wrapper function to prepare a single BAM command element + * with the data. + * + * @bam_ce: BAM command element + * @addr: target address + * @cmd: BAM command + * @data: actual data for write and dest addr for read + */ +static inline void +bam_prep_ce(struct bam_cmd_element *bam_ce, u32 addr, + enum bam_command_type cmd, u32 data) +{ + bam_prep_ce_le32(bam_ce, addr, cmd, cpu_to_le32(data)); +} +#endif -- cgit v1.2.3 From 604407890ecf624c2fb41013c82b22aade59b455 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 9 Aug 2017 11:32:11 -0700 Subject: dm: fix printk() rate limiting code Using the same rate limiting state for different kinds of messages is wrong because this can cause a high frequency message to suppress a report of a low frequency message. Hence use a unique rate limiting state per message type. Fixes: 71a16736a15e ("dm: use local printk ratelimit") Cc: stable@vger.kernel.org Signed-off-by: Bart Van Assche Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 41 ++++++++++++----------------------------- 1 file changed, 12 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 1473455d0341..4f2b3b2076c4 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -549,46 +549,29 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); *---------------------------------------------------------------*/ #define DM_NAME "device-mapper" -#ifdef CONFIG_PRINTK -extern struct ratelimit_state dm_ratelimit_state; - -#define dm_ratelimit() __ratelimit(&dm_ratelimit_state) -#else -#define dm_ratelimit() 0 -#endif +#define DM_RATELIMIT(pr_func, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + \ + if (__ratelimit(&rs)) \ + pr_func(DM_FMT(fmt), ##__VA_ARGS__); \ +} while (0) #define DM_FMT(fmt) DM_NAME ": " DM_MSG_PREFIX ": " fmt "\n" #define DMCRIT(fmt, ...) pr_crit(DM_FMT(fmt), ##__VA_ARGS__) #define DMERR(fmt, ...) pr_err(DM_FMT(fmt), ##__VA_ARGS__) -#define DMERR_LIMIT(fmt, ...) \ -do { \ - if (dm_ratelimit()) \ - DMERR(fmt, ##__VA_ARGS__); \ -} while (0) - +#define DMERR_LIMIT(fmt, ...) DM_RATELIMIT(pr_err, fmt, ##__VA_ARGS__) #define DMWARN(fmt, ...) pr_warn(DM_FMT(fmt), ##__VA_ARGS__) -#define DMWARN_LIMIT(fmt, ...) \ -do { \ - if (dm_ratelimit()) \ - DMWARN(fmt, ##__VA_ARGS__); \ -} while (0) - +#define DMWARN_LIMIT(fmt, ...) DM_RATELIMIT(pr_warn, fmt, ##__VA_ARGS__) #define DMINFO(fmt, ...) pr_info(DM_FMT(fmt), ##__VA_ARGS__) -#define DMINFO_LIMIT(fmt, ...) \ -do { \ - if (dm_ratelimit()) \ - DMINFO(fmt, ##__VA_ARGS__); \ -} while (0) +#define DMINFO_LIMIT(fmt, ...) DM_RATELIMIT(pr_info, fmt, ##__VA_ARGS__) #ifdef CONFIG_DM_DEBUG #define DMDEBUG(fmt, ...) printk(KERN_DEBUG DM_FMT(fmt), ##__VA_ARGS__) -#define DMDEBUG_LIMIT(fmt, ...) \ -do { \ - if (dm_ratelimit()) \ - DMDEBUG(fmt, ##__VA_ARGS__); \ -} while (0) +#define DMDEBUG_LIMIT(fmt, ...) DM_RATELIMIT(pr_debug, fmt, ##__VA_ARGS__) #else #define DMDEBUG(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #define DMDEBUG_LIMIT(fmt, ...) no_printk(fmt, ##__VA_ARGS__) -- cgit v1.2.3 From b97971bee55dc45420e0fe352d0b4df6e74716d4 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Wed, 2 Aug 2017 10:22:01 -0600 Subject: coresight: pmu: Adds return stack option to perf coresight pmu Return stack is a programmable option on some ETM and PTM hardware. Adds the option flags to enable this from the perf event command line. Signed-off-by: Mike Leach Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight-pmu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 7d410260661b..45852c2cd096 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -24,6 +24,7 @@ /* ETMv3.5/PTM's ETMCR config bit */ #define ETM_OPT_CYCACC 12 #define ETM_OPT_TS 28 +#define ETM_OPT_RETSTK 29 static inline int coresight_get_trace_id(int cpu) { -- cgit v1.2.3 From a09ac3974d0c0b25dfa70f8076546bc4876dd7a8 Mon Sep 17 00:00:00 2001 From: Okash Khawaja Date: Thu, 20 Jul 2017 08:22:36 +0100 Subject: tty: resolve tty contention between kernel and user space The commit 12e84c71b7d4 ("tty: export tty_open_by_driver") exports tty_open_by_device to allow tty to be opened from inside kernel which works fine except that it doesn't handle contention with user space or another kernel-space open of the same tty. For example, opening a tty from user space while it is kernel opened results in failure and a kernel log message about mismatch between tty->count and tty's file open count. This patch makes kernel access to tty exclusive, so that if a user process or kernel opens a kernel opened tty, it gets -EBUSY. It does this by adding TTY_KOPENED flag to tty->flags. When this flag is set, tty_open_by_driver returns -EBUSY. Instead of overloading tty_open_by_driver for both kernel and user space, this patch creates a separate function tty_kopen which closely follows tty_open_by_driver. tty_kclose closes the tty opened by tty_kopen. To address the mismatch between tty->count and #fd's, this patch adds #kopen's to the count before comparing it with tty->count. That way check_tty_count reflects correct usage count. Returning -EBUSY on tty open is a change in the interface. I have tested this with minicom, picocom and commands like "echo foo > /dev/ttyS0". They all correctly report "Device or resource busy" when the tty is already kernel opened. Signed-off-by: Okash Khawaja Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 79c30daf46a9..236d52b8be8c 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -261,6 +261,8 @@ struct tty_port { */ #define TTY_PORT_CTS_FLOW 3 /* h/w flow control enabled */ #define TTY_PORT_CHECK_CD 4 /* carrier detect enabled */ +#define TTY_PORT_KOPENED 5 /* device exclusively opened by + kernel */ /* * Where all of the state associated with a tty is kept while the tty @@ -401,6 +403,8 @@ extern int __init tty_init(void); extern const char *tty_name(const struct tty_struct *tty); extern struct tty_struct *tty_open_by_driver(dev_t device, struct inode *inode, struct file *filp); +extern struct tty_struct *tty_kopen(dev_t device); +extern void tty_kclose(struct tty_struct *tty); extern int tty_dev_name_to_number(const char *name, dev_t *number); #else static inline void tty_kref_put(struct tty_struct *tty) @@ -425,6 +429,10 @@ static inline const char *tty_name(const struct tty_struct *tty) static inline struct tty_struct *tty_open_by_driver(dev_t device, struct inode *inode, struct file *filp) { return NULL; } +static inline struct tty_struct *tty_kopen(dev_t device) +{ return ERR_PTR(-ENODEV); } +static inline void tty_kclose(struct tty_struct *tty) +{ } static inline int tty_dev_name_to_number(const char *name, dev_t *number) { return -ENOTSUPP; } #endif @@ -652,6 +660,19 @@ static inline void tty_port_set_initialized(struct tty_port *port, bool val) clear_bit(TTY_PORT_INITIALIZED, &port->iflags); } +static inline bool tty_port_kopened(struct tty_port *port) +{ + return test_bit(TTY_PORT_KOPENED, &port->iflags); +} + +static inline void tty_port_set_kopened(struct tty_port *port, bool val) +{ + if (val) + set_bit(TTY_PORT_KOPENED, &port->iflags); + else + clear_bit(TTY_PORT_KOPENED, &port->iflags); +} + extern struct tty_struct *tty_port_tty_get(struct tty_port *port); extern void tty_port_tty_set(struct tty_port *port, struct tty_struct *tty); extern int tty_port_carrier_raised(struct tty_port *port); -- cgit v1.2.3 From a033c3b10a2bec387ccd9e39fadd94eef6519626 Mon Sep 17 00:00:00 2001 From: Okash Khawaja Date: Thu, 20 Jul 2017 08:22:38 +0100 Subject: tty: undo export of tty_open_by_driver Since we have tty_kopen, we no longer need to export tty_open_by_driver. This patch makes this function static. Signed-off-by: Okash Khawaja Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 236d52b8be8c..cf53eb539f6e 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -401,8 +401,6 @@ extern struct tty_struct *get_current_tty(void); /* tty_io.c */ extern int __init tty_init(void); extern const char *tty_name(const struct tty_struct *tty); -extern struct tty_struct *tty_open_by_driver(dev_t device, struct inode *inode, - struct file *filp); extern struct tty_struct *tty_kopen(dev_t device); extern void tty_kclose(struct tty_struct *tty); extern int tty_dev_name_to_number(const char *name, dev_t *number); @@ -426,9 +424,6 @@ static inline int __init tty_init(void) { return 0; } static inline const char *tty_name(const struct tty_struct *tty) { return "(none)"; } -static inline struct tty_struct *tty_open_by_driver(dev_t device, - struct inode *inode, struct file *filp) -{ return NULL; } static inline struct tty_struct *tty_kopen(dev_t device) { return ERR_PTR(-ENODEV); } static inline void tty_kclose(struct tty_struct *tty) -- cgit v1.2.3 From 00ee84159020728cbdbfc569b42c036ef20c6e55 Mon Sep 17 00:00:00 2001 From: sayli karnik Date: Fri, 16 Jun 2017 15:39:38 +0530 Subject: mod_devicetable: Remove excess description from structured comment Remove excess member description to fix following warnings in sphinx build: Excess struct/union/enum/typedef member 'ver_major' description in 'fsl_mc_device_id' Excess struct/union/enum/typedef member 'ver_minor' description in 'fsl_mc_device_id' Signed-off-by: sayli karnik CC: Stuart Yoder Signed-off-by: Jonathan Corbet Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 3f74ef2281e8..694cebb50f72 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -674,8 +674,6 @@ struct ulpi_device_id { * struct fsl_mc_device_id - MC object device identifier * @vendor: vendor ID * @obj_type: MC object type - * @ver_major: MC object version major number - * @ver_minor: MC object version minor number * * Type of entries in the "device Id" table for MC object devices supported by * a MC object device driver. The last entry of the table has vendor set to 0x0 -- cgit v1.2.3 From 9f757f415210a7c85e2784e4a1733ea78b2e4e88 Mon Sep 17 00:00:00 2001 From: Federico Vaga Date: Tue, 18 Jul 2017 08:32:53 +0200 Subject: drivers/fmc: hide fmc operations behind helpers This gave us more freedom to change/add/remove operations without recompiling all device driver. Typically, Carrier board implement the fmc operations, so they will not use these helpers. Signed-off-by: Federico Vaga Tested-by: Pat Riehecky Acked-by: Alessandro Rubini Signed-off-by: Greg Kroah-Hartman --- include/linux/fmc.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fmc.h b/include/linux/fmc.h index a5f0aa5c2a8d..8bb4a154bbdc 100644 --- a/include/linux/fmc.h +++ b/include/linux/fmc.h @@ -234,4 +234,22 @@ extern void fmc_free_id_info(struct fmc_device *fmc); extern void fmc_dump_eeprom(const struct fmc_device *fmc); extern void fmc_dump_sdb(const struct fmc_device *fmc); +/* helpers for FMC operations */ +extern int fmc_irq_request(struct fmc_device *fmc, irq_handler_t h, + char *name, int flags); +extern void fmc_irq_free(struct fmc_device *fmc); +extern void fmc_irq_ack(struct fmc_device *fmc); +extern int fmc_validate(struct fmc_device *fmc, struct fmc_driver *drv); +extern int fmc_gpio_config(struct fmc_device *fmc, struct fmc_gpio *gpio, + int ngpio); +extern int fmc_read_ee(struct fmc_device *fmc, int pos, void *d, int l); +extern int fmc_write_ee(struct fmc_device *fmc, int pos, const void *d, int l); + +/* helpers for FMC operations */ +extern int fmc_irq_request(struct fmc_device *fmc, irq_handler_t h, + char *name, int flags); +extern void fmc_irq_free(struct fmc_device *fmc); +extern void fmc_irq_ack(struct fmc_device *fmc); +extern int fmc_validate(struct fmc_device *fmc, struct fmc_driver *drv); + #endif /* __LINUX_FMC_H__ */ -- cgit v1.2.3 From 2071a3e94abd34d65bd40f1ff845f9cea300dfa6 Mon Sep 17 00:00:00 2001 From: Federico Vaga Date: Tue, 18 Jul 2017 08:33:03 +0200 Subject: drivers/fmc: The only way to dump the SDB is from debugfs Driver should not call fmc_sdb_dump() anymore. (actually they can but the operation is not supported, so it will print an error message) Signed-off-by: Federico Vaga Tested-by: Pat Riehecky Acked-by: Alessandro Rubini Signed-off-by: Greg Kroah-Hartman --- include/linux/fmc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fmc.h b/include/linux/fmc.h index 8bb4a154bbdc..5c8df0c49fc3 100644 --- a/include/linux/fmc.h +++ b/include/linux/fmc.h @@ -180,6 +180,9 @@ struct fmc_device { uint32_t device_id; /* Filled by the device */ char *mezzanine_name; /* Defaults to ``fmc'' */ void *mezzanine_data; + + struct dentry *dbg_dir; + struct dentry *dbg_sdb_dump; }; #define to_fmc_device(x) container_of((x), struct fmc_device, dev) @@ -232,7 +235,6 @@ extern int fmc_match(struct device *dev, struct device_driver *drv); extern int fmc_fill_id_info(struct fmc_device *fmc); extern void fmc_free_id_info(struct fmc_device *fmc); extern void fmc_dump_eeprom(const struct fmc_device *fmc); -extern void fmc_dump_sdb(const struct fmc_device *fmc); /* helpers for FMC operations */ extern int fmc_irq_request(struct fmc_device *fmc, irq_handler_t h, -- cgit v1.2.3 From 15b1b0f0d87e34a87172d9b83bd260543a991c2e Mon Sep 17 00:00:00 2001 From: Federico Vaga Date: Tue, 18 Jul 2017 08:33:13 +0200 Subject: drivers/fmc: change registration prototype Permit use of either fmc_device_register_n or fmc_device_register_n_gw depending on the type of device in use. Signed-off-by: Federico Vaga Tested-by: Pat Riehecky Acked-by: Alessandro Rubini Signed-off-by: Greg Kroah-Hartman --- include/linux/fmc.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fmc.h b/include/linux/fmc.h index 5c8df0c49fc3..b6c73d54ca46 100644 --- a/include/linux/fmc.h +++ b/include/linux/fmc.h @@ -220,14 +220,23 @@ static inline void fmc_set_drvdata(struct fmc_device *fmc, void *data) dev_set_drvdata(&fmc->dev, data); } -/* The 4 access points */ +struct fmc_gateware { + void *bitstream; + unsigned long len; +}; + +/* The 5 access points */ extern int fmc_driver_register(struct fmc_driver *drv); extern void fmc_driver_unregister(struct fmc_driver *drv); extern int fmc_device_register(struct fmc_device *tdev); +extern int fmc_device_register_gw(struct fmc_device *tdev, + struct fmc_gateware *gw); extern void fmc_device_unregister(struct fmc_device *tdev); -/* Two more for device sets, all driven by the same FPGA */ +/* Three more for device sets, all driven by the same FPGA */ extern int fmc_device_register_n(struct fmc_device **devs, int n); +extern int fmc_device_register_n_gw(struct fmc_device **devs, int n, + struct fmc_gateware *gw); extern void fmc_device_unregister_n(struct fmc_device **devs, int n); /* Internal cross-calls between files; not exported to other modules */ -- cgit v1.2.3 From 9c0dda14951e9ed30b6f04e14bf64a3c69686c5b Mon Sep 17 00:00:00 2001 From: Federico Vaga Date: Tue, 18 Jul 2017 08:33:24 +0200 Subject: drivers/fmc: carrier can program FPGA on registration The initial FPGA may require programming before it is useful. Signed-off-by: Federico Vaga Tested-by: Pat Riehecky Acked-by: Alessandro Rubini Signed-off-by: Greg Kroah-Hartman --- include/linux/fmc.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fmc.h b/include/linux/fmc.h index b6c73d54ca46..3dc8a1b2db7b 100644 --- a/include/linux/fmc.h +++ b/include/linux/fmc.h @@ -132,6 +132,8 @@ struct fmc_operations { uint32_t (*read32)(struct fmc_device *fmc, int offset); void (*write32)(struct fmc_device *fmc, uint32_t value, int offset); int (*validate)(struct fmc_device *fmc, struct fmc_driver *drv); + int (*reprogram_raw)(struct fmc_device *f, struct fmc_driver *d, + void *gw, unsigned long len); int (*reprogram)(struct fmc_device *f, struct fmc_driver *d, char *gw); int (*irq_request)(struct fmc_device *fmc, irq_handler_t h, char *name, int flags); @@ -144,6 +146,8 @@ struct fmc_operations { }; /* Prefer this helper rather than calling of fmc->reprogram directly */ +int fmc_reprogram_raw(struct fmc_device *fmc, struct fmc_driver *d, + void *gw, unsigned long len, int sdb_entry); extern int fmc_reprogram(struct fmc_device *f, struct fmc_driver *d, char *gw, int sdb_entry); -- cgit v1.2.3 From 6a7a81761bee2a6694c0a5fb1a16b263c96241c1 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Thu, 24 Aug 2017 16:09:10 -0600 Subject: driver core: Document struct device:dma_ops Commit 5657933dbb6e (treewide: Move dma_ops from struct dev_archdata into struct device) added the dma_ops field to struct device, but did not update the kerneldoc comment, yielding this warning: ./include/linux/device.h:969: warning: No description found for parameter 'dma_ops' Add a description and bring a little peace to the world. Signed-off-by: Jonathan Corbet Reviewed-by: Bart Van Assche Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index 5db26b9c0fcc..d5bcc5f109eb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -847,6 +847,7 @@ struct dev_links_info { * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. + * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations -- cgit v1.2.3 From e0552573575ef43daaee5b1a139952d6127f088c Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Wed, 19 Jul 2017 23:35:29 -0300 Subject: misc: eeprom_93xx46: Include eeprom_93xx46_platform_data struct has a 'struct gpio_desc' type member, so it is better to include , which provides 'struct gpio_desc' type. Signed-off-by: Fabio Estevam Signed-off-by: Greg Kroah-Hartman --- include/linux/eeprom_93xx46.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h index 885f587a3555..915898759280 100644 --- a/include/linux/eeprom_93xx46.h +++ b/include/linux/eeprom_93xx46.h @@ -2,8 +2,7 @@ * Module: eeprom_93xx46 * platform description for 93xx46 EEPROMs. */ - -struct gpio_desc; +#include struct eeprom_93xx46_platform_data { unsigned char flags; -- cgit v1.2.3 From d3cc8ca3ab6c1d78c26102870313fa36c48ea247 Mon Sep 17 00:00:00 2001 From: Ulrich Hecht Date: Tue, 22 Aug 2017 08:27:07 +0200 Subject: mux: include compiler.h from mux/consumer.h Required for __must_check. Signed-off-by: Ulrich Hecht Signed-off-by: Peter Rosin Signed-off-by: Greg Kroah-Hartman --- include/linux/mux/consumer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mux/consumer.h b/include/linux/mux/consumer.h index 5577e1b773c4..ea96d4c82be7 100644 --- a/include/linux/mux/consumer.h +++ b/include/linux/mux/consumer.h @@ -13,6 +13,8 @@ #ifndef _LINUX_MUX_CONSUMER_H #define _LINUX_MUX_CONSUMER_H +#include + struct device; struct mux_control; -- cgit v1.2.3 From 242b476f821b055ed0fb70a8eb6defa85baada9c Mon Sep 17 00:00:00 2001 From: Johannes Poehlmann Date: Tue, 25 Jul 2017 13:27:11 +0200 Subject: w1: ds1wm: fix register offset (bus shift) calculation Replace incorrect register offsett calculation by direct configuration of bus_shift in mfd-cell. Indirect definition of address-shift by resource size was unobvious and was wrong (should have used a binary log). Signed-off-by: Johannes Poehlmann Acked-by: Evgeniy Polyakov Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/ds1wm.h | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h index 38a372a0e285..79a01e8dc83f 100644 --- a/include/linux/mfd/ds1wm.h +++ b/include/linux/mfd/ds1wm.h @@ -1,13 +1,23 @@ -/* MFD cell driver data for the DS1WM driver */ +/* MFD cell driver data for the DS1WM driver + * + * to be defined in the MFD device that is + * using this driver for one of his sub devices + */ struct ds1wm_driver_data { int active_high; int clock_rate; - /* in milliseconds, the amount of time to */ - /* sleep following a reset pulse. Zero */ - /* should work if your bus devices recover*/ - /* time respects the 1-wire spec since the*/ - /* ds1wm implements the precise timings of*/ - /* a reset pulse/presence detect sequence.*/ + /* in milliseconds, the amount of time to + * sleep following a reset pulse. Zero + * should work if your bus devices recover + * time respects the 1-wire spec since the + * ds1wm implements the precise timings of + * a reset pulse/presence detect sequence. + */ unsigned int reset_recover_delay; + + /* left shift of register number to get register address offsett. + * Only 0,1,2 allowed for 8,16 or 32 bit bus width respectively + */ + unsigned int bus_shift; }; -- cgit v1.2.3 From baa8055de0293a91f87bef5f32296d9ddcba9c56 Mon Sep 17 00:00:00 2001 From: Johannes Poehlmann Date: Tue, 25 Jul 2017 13:27:12 +0200 Subject: w1: ds1wm: make endian clean and use standard io memory accessors o Make endian clean, make HW-endianness configurable. o Use ioread*, iowrite* instead of __raw_readb,__raw_writeb to also use memory-barriers when accessing HW-registers. We do not want reordering to happen here. Both changes are tightly coupled, so I do them in one patch Signed-off-by: Johannes Poehlmann Acked-by: Evgeniy Polyakov Signed-off-by: Greg Kroah-Hartman --- include/linux/mfd/ds1wm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h index 79a01e8dc83f..2227c6a75d84 100644 --- a/include/linux/mfd/ds1wm.h +++ b/include/linux/mfd/ds1wm.h @@ -16,6 +16,11 @@ struct ds1wm_driver_data { */ unsigned int reset_recover_delay; + /* Say 1 here for big endian Hardware + * (only relevant with bus-shift > 0 + */ + bool is_hw_big_endian; + /* left shift of register number to get register address offsett. * Only 0,1,2 allowed for 8,16 or 32 bit bus width respectively */ -- cgit v1.2.3 From d026d70a2e9460dc701d20b48672b80a2656006d Mon Sep 17 00:00:00 2001 From: Leonard Crestez Date: Wed, 26 Jul 2017 11:34:46 +0200 Subject: nvmem: core: Add nvmem_cell_read_u32 This function does a quick and easy read of an u32 value without any kind of resource management code on the consumer side. Signed-off-by: Leonard Crestez Reviewed-by: Shawn Guo Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index c2256d746543..efafccffaee8 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -35,6 +35,7 @@ void nvmem_cell_put(struct nvmem_cell *cell); void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell); void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len); int nvmem_cell_write(struct nvmem_cell *cell, void *buf, size_t len); +int nvmem_cell_read_u32(struct device *dev, const char *cell_id, u32 *val); /* direct nvmem device read/write interface */ struct nvmem_device *nvmem_device_get(struct device *dev, const char *name); @@ -85,6 +86,12 @@ static inline int nvmem_cell_write(struct nvmem_cell *cell, return -ENOSYS; } +static inline int nvmem_cell_read_u32(struct device *dev, + const char *cell_id, u32 *val) +{ + return -ENOSYS; +} + static inline struct nvmem_device *nvmem_device_get(struct device *dev, const char *name) { -- cgit v1.2.3 From 4da69f49e73e3c79f079de62ea940cabbbf15ae7 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Wed, 26 Jul 2017 11:34:48 +0200 Subject: nvmem: include linux/err.h from header missing err.h header file can cause simillar errors like below in some configurations. "error: implicit declaration of function 'ERR_PTR' [-Werror=implicit-function-declaration]" This adds the missing include to ensure we can always include the header. Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index efafccffaee8..4e85447f7860 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -12,6 +12,9 @@ #ifndef _LINUX_NVMEM_CONSUMER_H #define _LINUX_NVMEM_CONSUMER_H +#include +#include + struct device; struct device_node; /* consumer cookie */ -- cgit v1.2.3 From df770ff0586a494fabe68ffbe2898d7df5666663 Mon Sep 17 00:00:00 2001 From: Mike Leach Date: Wed, 2 Aug 2017 10:22:19 -0600 Subject: perf: cs-etm: Fix ETMv4 CONFIGR entry in perf.data file The value passed into the perf.data file for the CONFIGR register in ETMv4 was incorrectly being set to the command line options/ETMv3 value. Adds bit definitions and function to remap this value to the correct ETMv4 CONFIGR bit values for all selected options. Signed-off-by: Mike Leach Signed-off-by: Greg Kroah-Hartman --- include/linux/coresight-pmu.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 45852c2cd096..edfeaba95429 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -26,6 +26,11 @@ #define ETM_OPT_TS 28 #define ETM_OPT_RETSTK 29 +/* ETMv4 CONFIGR programming bits for the ETM OPTs */ +#define ETM4_CFG_BIT_CYCACC 4 +#define ETM4_CFG_BIT_TS 11 +#define ETM4_CFG_BIT_RETSTK 12 + static inline int coresight_get_trace_id(int cpu) { /* -- cgit v1.2.3 From 960632ece6949be1ab6f7a911faa4fa6e8305f4a Mon Sep 17 00:00:00 2001 From: Aaron Conole Date: Thu, 24 Aug 2017 00:08:32 +0200 Subject: netfilter: convert hook list to an array This converts the storage and layout of netfilter hook entries from a linked list to an array. After this commit, hook entries will be stored adjacent in memory. The next pointer is no longer required. The ops pointers are stored at the end of the array as they are only used in the register/unregister path and in the legacy br_netfilter code. nf_unregister_net_hooks() is slower than needed as it just calls nf_unregister_net_hook in a loop (i.e. at least n synchronize_net() calls), this will be addressed in followup patch. Test setup: - ixgbe 10gbit - netperf UDP_STREAM, 64 byte packets - 5 hooks: (raw + mangle prerouting, mangle+filter input, inet filter): empty mangle and raw prerouting, mangle and filter input hooks: 353.9 this patch: 364.2 Signed-off-by: Aaron Conole Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netdevice.h | 2 +- include/linux/netfilter.h | 45 ++++++++++++++++++++------------------- include/linux/netfilter_ingress.h | 4 ++-- 3 files changed, 26 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 614642eb7eb7..ca0a30127300 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1811,7 +1811,7 @@ struct net_device { #endif struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS - struct nf_hook_entry __rcu *nf_hooks_ingress; + struct nf_hook_entries __rcu *nf_hooks_ingress; #endif unsigned char broadcast[MAX_ADDR_LEN]; diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 22f081065d49..f84bca1703cd 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -72,25 +72,32 @@ struct nf_hook_ops { }; struct nf_hook_entry { - struct nf_hook_entry __rcu *next; nf_hookfn *hook; void *priv; - const struct nf_hook_ops *orig_ops; }; -static inline void -nf_hook_entry_init(struct nf_hook_entry *entry, const struct nf_hook_ops *ops) -{ - entry->next = NULL; - entry->hook = ops->hook; - entry->priv = ops->priv; - entry->orig_ops = ops; -} +struct nf_hook_entries { + u16 num_hook_entries; + /* padding */ + struct nf_hook_entry hooks[]; + + /* trailer: pointers to original orig_ops of each hook. + * + * This is not part of struct nf_hook_entry since its only + * needed in slow path (hook register/unregister). + * + * const struct nf_hook_ops *orig_ops[] + */ +}; -static inline int -nf_hook_entry_priority(const struct nf_hook_entry *entry) +static inline struct nf_hook_ops **nf_hook_entries_get_hook_ops(const struct nf_hook_entries *e) { - return entry->orig_ops->priority; + unsigned int n = e->num_hook_entries; + const void *hook_end; + + hook_end = &e->hooks[n]; /* this is *past* ->hooks[]! */ + + return (struct nf_hook_ops **)hook_end; } static inline int @@ -100,12 +107,6 @@ nf_hook_entry_hookfn(const struct nf_hook_entry *entry, struct sk_buff *skb, return entry->hook(entry->priv, skb, state); } -static inline const struct nf_hook_ops * -nf_hook_entry_ops(const struct nf_hook_entry *entry) -{ - return entry->orig_ops; -} - static inline void nf_hook_state_init(struct nf_hook_state *p, unsigned int hook, u_int8_t pf, @@ -168,7 +169,7 @@ extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; #endif int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, - struct nf_hook_entry *entry); + const struct nf_hook_entries *e, unsigned int i); /** * nf_hook - call a netfilter hook @@ -182,7 +183,7 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - struct nf_hook_entry *hook_head; + struct nf_hook_entries *hook_head; int ret = 1; #ifdef HAVE_JUMP_LABEL @@ -200,7 +201,7 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, nf_hook_state_init(&state, hook, pf, indev, outdev, sk, net, okfn); - ret = nf_hook_slow(skb, &state, hook_head); + ret = nf_hook_slow(skb, &state, hook_head, 0); } rcu_read_unlock(); diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index 59476061de86..8d5dae1e2ff8 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -17,7 +17,7 @@ static inline bool nf_hook_ingress_active(const struct sk_buff *skb) /* caller must hold rcu_read_lock */ static inline int nf_hook_ingress(struct sk_buff *skb) { - struct nf_hook_entry *e = rcu_dereference(skb->dev->nf_hooks_ingress); + struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); struct nf_hook_state state; int ret; @@ -30,7 +30,7 @@ static inline int nf_hook_ingress(struct sk_buff *skb) nf_hook_state_init(&state, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); - ret = nf_hook_slow(skb, &state, e); + ret = nf_hook_slow(skb, &state, e, 0); if (ret == 0) return -1; -- cgit v1.2.3 From 5916a22b83041b07d63191fe06206ae0fff6ec7a Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 22 Jun 2017 11:32:45 -0700 Subject: dm: constify argument arrays The arrays of 'struct dm_arg' are never modified by the device-mapper core, so constify them so that they are placed in .rodata. (Exception: the args array in dm-raid cannot be constified because it is allocated on the stack and modified.) Signed-off-by: Eric Biggers Signed-off-by: Mike Snitzer --- include/linux/device-mapper.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 4f2b3b2076c4..3b5fdf308148 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -387,7 +387,7 @@ struct dm_arg { * Validate the next argument, either returning it as *value or, if invalid, * returning -EINVAL and setting *error. */ -int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, +int dm_read_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set, unsigned *value, char **error); /* @@ -395,7 +395,7 @@ int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, * arg->min and arg->max further arguments. Either return the size as * *num_args or, if invalid, return -EINVAL and set *error. */ -int dm_read_arg_group(struct dm_arg *arg, struct dm_arg_set *arg_set, +int dm_read_arg_group(const struct dm_arg *arg, struct dm_arg_set *arg_set, unsigned *num_args, char **error); /* -- cgit v1.2.3 From 7521621e600aeefe5ffcc1f90ae26a42fc20c452 Mon Sep 17 00:00:00 2001 From: Michal Suchanek Date: Fri, 11 Aug 2017 15:44:43 +0200 Subject: Do not disable driver and bus shutdown hook when class shutdown hook is set. As seen from the implementation of the single class shutdown hook this is not very sound design. Rename the class shutdown hook to shutdown_pre to make it clear it runs before the driver shutdown hook. Signed-off-by: Michal Suchanek Reviewed-by: Jarkko Sakkinen Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index d5bcc5f109eb..c6f27207dbe8 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -375,7 +375,7 @@ int subsys_virtual_register(struct bus_type *subsys, * @suspend: Used to put the device to sleep mode, usually to a low power * state. * @resume: Used to bring the device from the sleep mode. - * @shutdown: Called at shut-down time to quiesce the device. + * @shutdown_pre: Called at shut-down time before driver shutdown. * @ns_type: Callbacks so sysfs can detemine namespaces. * @namespace: Namespace of the device belongs to this class. * @pm: The default device power management operations of this class. @@ -404,7 +404,7 @@ struct class { int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); - int (*shutdown)(struct device *dev); + int (*shutdown_pre)(struct device *dev); const struct kobj_ns_type_operations *ns_type; const void *(*namespace)(struct device *dev); -- cgit v1.2.3 From 35f0b6a779b8b7a98faefd7c1c660b4dac9a5c26 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 28 Aug 2017 08:28:08 +0200 Subject: libata: quirk read log on no-name M.2 SSD Ido reported that reading the log page on his systems fails, so quirk it as it won't support ZBC or security protocols. Signed-off-by: Christoph Hellwig Reported-by: Ido Schimmel Tested-by: Ido Schimmel Signed-off-by: Tejun Heo --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 931c32f1f18d..9e927ae7fced 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -438,6 +438,7 @@ enum { ATA_HORKAGE_NO_DMA_LOG = (1 << 23), /* don't use DMA for log read */ ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ + ATA_HORKAGE_NO_LOG_PAGE = (1 << 26), /* Doesn't like Get Log Page */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 464bc0fd6273d518aee79fbd37211dd9bc35d863 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Mon, 28 Aug 2017 07:10:04 -0700 Subject: bpf: convert sockmap field attach_bpf_fd2 to type In the initial sockmap API we provided strparser and verdict programs using a single attach command by extending the attach API with a the attach_bpf_fd2 field. However, if we add other programs in the future we will be adding a field for every new possible type, attach_bpf_fd(3,4,..). This seems a bit clumsy for an API. So lets push the programs using two new type fields. BPF_SK_SKB_STREAM_PARSER BPF_SK_SKB_STREAM_VERDICT This has the advantage of having a readable name and can easily be extended in the future. Updates to samples and sockmap included here also generalize tests slightly to support upcoming patch for multiple map support. Signed-off-by: John Fastabend Fixes: 174a79ff9515 ("bpf: sockmap with sk redirect support") Suggested-by: Alexei Starovoitov Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 830f472d8df5..c2cb1b5c094e 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -39,8 +39,6 @@ struct bpf_map_ops { void (*map_fd_put_ptr)(void *ptr); u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); - int (*map_attach)(struct bpf_map *map, - struct bpf_prog *p1, struct bpf_prog *p2); }; struct bpf_map { @@ -387,11 +385,19 @@ static inline void __dev_map_flush(struct bpf_map *map) #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); +int sock_map_attach_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); #else static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) { return NULL; } + +static inline int sock_map_attach_prog(struct bpf_map *map, + struct bpf_prog *prog, + u32 type) +{ + return -EOPNOTSUPP; +} #endif /* verifier prototypes for helper functions called from eBPF programs */ -- cgit v1.2.3 From aef3ad103a686f21b746977d4ed21cc1af36f589 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Sun, 13 Aug 2017 17:47:42 +0300 Subject: serial: core: remove unneeded irq_wake flag There is no need to duplicate a flag which IRQ core takes care of. Replace custom flag by IRQ core API that retrieves its state. Signed-off-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 8dc24c855a70..5553e04e59c9 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -247,7 +247,6 @@ struct uart_port { struct device *dev; /* parent device */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; - unsigned char irq_wake; unsigned char unused[2]; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ -- cgit v1.2.3 From 6e0a5de2136b26bd0b3501f2f362abfffeb47d1e Mon Sep 17 00:00:00 2001 From: Rafael Gago Date: Mon, 31 Jul 2017 10:46:43 +0200 Subject: serial: 8250: Use hrtimers for rs485 delays Previously the timers where based on the classic timers, giving a too coarse resolution on systems with configs of less than 1000 HZ. This patch changes the rs485 timers to hrtimers. Signed-off-by: Rafael Gago Castano Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 61fbb440449c..a27ef5f56431 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -80,9 +80,10 @@ struct uart_8250_ops { }; struct uart_8250_em485 { - struct timer_list start_tx_timer; /* "rs485 start tx" timer */ - struct timer_list stop_tx_timer; /* "rs485 stop tx" timer */ - struct timer_list *active_timer; /* pointer to active timer */ + struct hrtimer start_tx_timer; /* "rs485 start tx" timer */ + struct hrtimer stop_tx_timer; /* "rs485 stop tx" timer */ + struct hrtimer *active_timer; /* pointer to active timer */ + struct uart_8250_port *port; /* for hrtimer callbacks */ }; /* -- cgit v1.2.3 From 2ce8008711e4837c11e99a94df55406085d0d098 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 2 Aug 2017 09:58:52 +0200 Subject: mcb: introduce mcb_get_resource() Introduce mcb_get_resource() as a common accessor to a mcb device's memory or IRQ resources. Signed-off-by: Johannes Thumshirn Signed-off-by: Greg Kroah-Hartman --- include/linux/mcb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mcb.h b/include/linux/mcb.h index 4097ac9ea13a..b1a0ad9d23b3 100644 --- a/include/linux/mcb.h +++ b/include/linux/mcb.h @@ -136,5 +136,7 @@ extern struct resource *mcb_request_mem(struct mcb_device *dev, const char *name); extern void mcb_release_mem(struct resource *mem); extern int mcb_get_irq(struct mcb_device *dev); +extern struct resource *mcb_get_resource(struct mcb_device *dev, + unsigned int type); #endif /* _LINUX_MCB_H */ -- cgit v1.2.3 From d01c3289e7d68162e32bc08c2b65dd1a216a7ef8 Mon Sep 17 00:00:00 2001 From: Masatake YAMATO Date: Tue, 18 Jul 2017 06:27:59 +0900 Subject: pty: show associative slave of ptmx in fdinfo This patch adds "tty-index" field to /proc/PID/fdinfo/N if N specifies /dev/ptmx. The field shows the index of associative slave pts. Though a minor number is given for each pts instance, ptmx is not. It means there is no way in user-space to know the association between file descriptors for pts/n and ptmx. (n = 0, 1, ...) This is different from pipe. About pipe such association can be solved by inode of pipefs. Providing the way to know the association between pts/n and ptmx helps users understand the status of running system. lsof can utilize this field. Signed-off-by: Masatake YAMATO Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_driver.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 00b2213f6a35..fcdc0f5d9098 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -243,6 +243,7 @@ #include #include #include +#include struct tty_struct; struct tty_driver; @@ -285,6 +286,7 @@ struct tty_operations { int (*set_termiox)(struct tty_struct *tty, struct termiox *tnew); int (*get_icount)(struct tty_struct *tty, struct serial_icounter_struct *icount); + void (*show_fdinfo)(struct tty_struct *tty, struct seq_file *m); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct tty_driver *driver, int line, char *options); int (*poll_get_char)(struct tty_driver *driver, int line); -- cgit v1.2.3 From b6dccf7fae4331b0ea41cf087e3f02d5db9161dc Mon Sep 17 00:00:00 2001 From: Arnav Dawn Date: Wed, 12 Jul 2017 16:10:40 +0530 Subject: nvme: add support for FW activation without reset This patch adds support for handling Fw activation without reset On completion of FW-activation-starting AER, all queues are paused till CSTS.PP is cleared or timed out (exceeds max time for fw activtion MTFA). If device fails to clear CSTS.PP within MTFA, driver issues reset controller. Signed-off-by: Arnav Dawn Reviewed-by: Keith Busch Reviewed-by: Christoph Hellwig Signed-off-by: Sagi Grimberg --- include/linux/nvme.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 25d8225dbd04..5d0f2f4fc3b8 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -146,6 +146,7 @@ enum { NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, + NVME_CSTS_PP = 1 << 5, NVME_CSTS_SHST_NORMAL = 0 << 2, NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, @@ -376,6 +377,13 @@ struct nvme_smart_log { __u8 rsvd216[296]; }; +struct nvme_fw_slot_info_log { + __u8 afi; + __u8 rsvd1[7]; + __le64 frs[7]; + __u8 rsvd64[448]; +}; + enum { NVME_SMART_CRIT_SPARE = 1 << 0, NVME_SMART_CRIT_TEMPERATURE = 1 << 1, @@ -386,6 +394,7 @@ enum { enum { NVME_AER_NOTICE_NS_CHANGED = 0x0002, + NVME_AER_NOTICE_FW_ACT_STARTING = 0x0102, }; struct nvme_lba_range_type { -- cgit v1.2.3 From 62346eaeb2f1a0524b35eaa2f479596f40491165 Mon Sep 17 00:00:00 2001 From: Arnav Dawn Date: Wed, 12 Jul 2017 16:11:53 +0530 Subject: nvme: define NVME_NSID_ALL Define the constant "0xffffffff" (used as nsid for all namespaces) as NVME_NSID_ALL. Signed-off-by: Arnav Dawn Signed-off-by: Sagi Grimberg --- include/linux/nvme.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 5d0f2f4fc3b8..1d79046bf9d4 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -32,6 +32,8 @@ #define NVME_RDMA_IP_PORT 4420 +#define NVME_NSID_ALL 0xffffffff + enum nvme_subsys_type { NVME_NQN_DISC = 1, /* Discovery type target subsystem */ NVME_NQN_NVME = 2, /* NVME type target subsystem */ -- cgit v1.2.3 From dbf86b39005d26b21c52a23720e15fb850d71cdc Mon Sep 17 00:00:00 2001 From: Jon Derrick Date: Wed, 16 Aug 2017 09:51:29 +0200 Subject: nvme: add support for NVMe 1.3 Timestamp Feature NVME's Timestamp feature allows controllers to be aware of the epoch time in milliseconds. This patch adds the set features hook for various transports through the identify path, so that resets and resumes can update the controller as necessary. Signed-off-by: Jon Derrick [hch: rebased on top of nvme-4.13 error handling changes, changed nvme_configure_timestamp to return the status] Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 1d79046bf9d4..a12b47073273 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -254,6 +254,7 @@ enum { NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, NVME_CTRL_ONCS_DSM = 1 << 2, NVME_CTRL_ONCS_WRITE_ZEROES = 1 << 3, + NVME_CTRL_ONCS_TIMESTAMP = 1 << 6, NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, NVME_CTRL_OACS_DIRECTIVES = 1 << 5, @@ -688,6 +689,7 @@ enum { NVME_FEAT_ASYNC_EVENT = 0x0b, NVME_FEAT_AUTO_PST = 0x0c, NVME_FEAT_HOST_MEM_BUF = 0x0d, + NVME_FEAT_TIMESTAMP = 0x0e, NVME_FEAT_KATO = 0x0f, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, -- cgit v1.2.3 From ad4e05b24c428d6125f6f10bd300600cae5079d4 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Sun, 13 Aug 2017 19:21:06 +0300 Subject: nvme: add symbolic constants for CC identifiers Signed-off-by: Max Gurtovoy Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index a12b47073273..7b4322dc2975 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -135,16 +135,22 @@ enum { enum { NVME_CC_ENABLE = 1 << 0, NVME_CC_CSS_NVM = 0 << 4, + NVME_CC_EN_SHIFT = 0, + NVME_CC_CSS_SHIFT = 4, NVME_CC_MPS_SHIFT = 7, - NVME_CC_ARB_RR = 0 << 11, - NVME_CC_ARB_WRRU = 1 << 11, - NVME_CC_ARB_VS = 7 << 11, - NVME_CC_SHN_NONE = 0 << 14, - NVME_CC_SHN_NORMAL = 1 << 14, - NVME_CC_SHN_ABRUPT = 2 << 14, - NVME_CC_SHN_MASK = 3 << 14, - NVME_CC_IOSQES = NVME_NVM_IOSQES << 16, - NVME_CC_IOCQES = NVME_NVM_IOCQES << 20, + NVME_CC_AMS_SHIFT = 11, + NVME_CC_SHN_SHIFT = 14, + NVME_CC_IOSQES_SHIFT = 16, + NVME_CC_IOCQES_SHIFT = 20, + NVME_CC_ARB_RR = 0 << NVME_CC_AMS_SHIFT, + NVME_CC_ARB_WRRU = 1 << NVME_CC_AMS_SHIFT, + NVME_CC_ARB_VS = 7 << NVME_CC_AMS_SHIFT, + NVME_CC_SHN_NONE = 0 << NVME_CC_SHN_SHIFT, + NVME_CC_SHN_NORMAL = 1 << NVME_CC_SHN_SHIFT, + NVME_CC_SHN_ABRUPT = 2 << NVME_CC_SHN_SHIFT, + NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, + NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, + NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, -- cgit v1.2.3 From 60b43f627a71aaf233ef5af90f72e207c29781b4 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Sun, 13 Aug 2017 19:21:07 +0300 Subject: nvme: rename AMS symbolic constants to fit specification Signed-off-by: Max Gurtovoy Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7b4322dc2975..05560c2ecc83 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -142,9 +142,9 @@ enum { NVME_CC_SHN_SHIFT = 14, NVME_CC_IOSQES_SHIFT = 16, NVME_CC_IOCQES_SHIFT = 20, - NVME_CC_ARB_RR = 0 << NVME_CC_AMS_SHIFT, - NVME_CC_ARB_WRRU = 1 << NVME_CC_AMS_SHIFT, - NVME_CC_ARB_VS = 7 << NVME_CC_AMS_SHIFT, + NVME_CC_AMS_RR = 0 << NVME_CC_AMS_SHIFT, + NVME_CC_AMS_WRRU = 1 << NVME_CC_AMS_SHIFT, + NVME_CC_AMS_VS = 7 << NVME_CC_AMS_SHIFT, NVME_CC_SHN_NONE = 0 << NVME_CC_SHN_SHIFT, NVME_CC_SHN_NORMAL = 1 << NVME_CC_SHN_SHIFT, NVME_CC_SHN_ABRUPT = 2 << NVME_CC_SHN_SHIFT, -- cgit v1.2.3 From 48fa362b6c3f4d69bdb6310b46626049092475e0 Mon Sep 17 00:00:00 2001 From: James Smart Date: Mon, 31 Jul 2017 13:21:14 -0700 Subject: nvmet-fc: simplify sg list handling The existing nvmet_fc sg list handling has 2 faults: a) the request between LLDD and transport has too large of an sg list (256 elements), which is normally 256k (64 elements). b) sglist handling doesn't optimize on the fact that each element is a page. This patch removes the static sg list in the request and uses the dynamic list already present in the nvmet_fc transport. It also simplies the handling of the sg list on multiple sequences to take advantage of the per-page divisions. Signed-off-by: James Smart Signed-off-by: Christoph Hellwig --- include/linux/nvme-fc-driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 2591878c1d48..9c5cb4480806 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -624,7 +624,7 @@ struct nvmefc_tgt_fcp_req { u32 timeout; u32 transfer_length; struct fc_ba_rjt ba_rjt; - struct scatterlist sg[NVME_FC_MAX_SEGMENTS]; + struct scatterlist *sg; int sg_cnt; void *rspaddr; dma_addr_t rspdma; -- cgit v1.2.3 From 01f33c336e2d298ea5d4ce5d6e5bcd12865cc30f Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Mon, 14 Aug 2017 22:12:38 +0200 Subject: string.h: add memcpy_and_pad() This helper function is useful for the nvme subsystem, and maybe others. Note: the warnings reported by the kbuild test robot for this patch are actually generated by the use of CONFIG_PROFILE_ALL_BRANCHES together with __FORTIFY_INLINE. Signed-off-by: Martin Wilck Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/string.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index a467e617eeb0..0bec4151b0eb 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -200,6 +200,7 @@ static inline const char *kbasename(const char *path) void fortify_panic(const char *name) __noreturn __cold; void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); +void __read_overflow3(void) __compiletime_error("detected read beyond size of object passed as 3rd parameter"); void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) @@ -395,4 +396,33 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) #endif +/** + * memcpy_and_pad - Copy one buffer to another with padding + * @dest: Where to copy to + * @dest_len: The destination buffer size + * @src: Where to copy from + * @count: The number of bytes to copy + * @pad: Character to use for padding if space is left in destination. + */ +__FORTIFY_INLINE void memcpy_and_pad(void *dest, size_t dest_len, + const void *src, size_t count, int pad) +{ + size_t dest_size = __builtin_object_size(dest, 0); + size_t src_size = __builtin_object_size(src, 0); + + if (__builtin_constant_p(dest_len) && __builtin_constant_p(count)) { + if (dest_size < dest_len && dest_size < count) + __write_overflow(); + else if (src_size < dest_len && src_size < count) + __read_overflow3(); + } + if (dest_size < dest_len) + fortify_panic(__func__); + if (dest_len > count) { + memcpy(dest, src, count); + memset(dest + count, pad, dest_len - count); + } else + memcpy(dest, src, dest_len); +} + #endif /* _LINUX_STRING_H_ */ -- cgit v1.2.3 From 5aa5911a0ed9355ebb02f83de4be9ba435a45a2c Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 23 Aug 2017 16:54:43 -0600 Subject: ACPI / blacklist: add acpi_match_platform_list() ACPI OEM ID / OEM Table ID / Revision can be used to identify a platform based on ACPI firmware info. acpi_blacklisted(), intel_pstate_platform_pwr_mgmt_exists(), and some other funcs, have been using similar check to detect a list of platforms that require special handlings. Move the platform check in acpi_blacklisted() to a new common utility function, acpi_match_platform_list(), so that other drivers do not have to implement their own version. There is no change in functionality. Signed-off-by: Toshi Kani Reviewed-by: Borislav Petkov Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 27b4b6615263..1c8a97d8b09b 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -556,6 +556,25 @@ extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, #define ACPI_OST_SC_DRIVER_LOAD_FAILURE 0x81 #define ACPI_OST_SC_INSERT_NOT_SUPPORTED 0x82 +enum acpi_predicate { + all_versions, + less_than_or_equal, + equal, + greater_than_or_equal, +}; + +/* Table must be terminted by a NULL entry */ +struct acpi_platform_list { + char oem_id[ACPI_OEM_ID_SIZE+1]; + char oem_table_id[ACPI_OEM_TABLE_ID_SIZE+1]; + u32 oem_revision; + char *table; + enum acpi_predicate pred; + char *reason; + u32 data; +}; +int acpi_match_platform_list(const struct acpi_platform_list *plat); + extern void acpi_early_init(void); extern void acpi_subsystem_init(void); -- cgit v1.2.3 From 2fd523c57e520899e05ec663d04743005bcef5b2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Aug 2017 17:06:13 +0200 Subject: dma-mapping: remove dma_alloc_noncoherent and dma_free_noncoherent No users left, everyone switched to the _attrs versions. Signed-off-by: Christoph Hellwig --- include/linux/dma-mapping.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 66d8ea68f40b..4c98cc96971f 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -549,20 +549,6 @@ static inline void dma_free_coherent(struct device *dev, size_t size, return dma_free_attrs(dev, size, cpu_addr, dma_handle, 0); } -static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp) -{ - return dma_alloc_attrs(dev, size, dma_handle, gfp, - DMA_ATTR_NON_CONSISTENT); -} - -static inline void dma_free_noncoherent(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t dma_handle) -{ - dma_free_attrs(dev, size, cpu_addr, dma_handle, - DMA_ATTR_NON_CONSISTENT); -} - static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { const struct dma_map_ops *ops = get_dma_ops(dev); -- cgit v1.2.3 From c3142dd8bedb8b78ee13c885dd92093fc8a50277 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 15 Aug 2017 22:04:56 +0200 Subject: power: supply: Add power_supply_set_input_current_limit_from_supplier helper On some devices the USB Type-C port power (USB PD 2.0) negotiation is done by a separate port-controller IC, while the current limit is controlled through another (charger) IC. It has been decided to model this by modelling the external Type-C power brick (adapter/charger) as a power-supply class device which supplies the charger-IC, with its voltage-now and current-max representing the negotiated voltage and max current draw. This commit adds a power_supply_set_input_current_limit_from_supplier helper function which charger power-supply drivers can call to get the max-current from their supplier and have this applied through their set_property call-back to their input-current-limit. Signed-off-by: Hans de Goede Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index de89066b72b1..79e90b3d3288 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -332,6 +332,8 @@ extern int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info *info); extern void power_supply_changed(struct power_supply *psy); extern int power_supply_am_i_supplied(struct power_supply *psy); +extern int power_supply_set_input_current_limit_from_supplier( + struct power_supply *psy); extern int power_supply_set_battery_charged(struct power_supply *psy); #ifdef CONFIG_POWER_SUPPLY -- cgit v1.2.3 From 3a731c6414c94012328f485b4b1bb88ed841f9eb Mon Sep 17 00:00:00 2001 From: Liam Breck Date: Wed, 23 Aug 2017 20:36:14 -0700 Subject: power: supply: bq27xxx: Add chip IDs for previously shadowed chips For the existing features, these chips act like others already ID'd, so they had false but functional IDs. We will be adding features which require correct IDs, so the following IDs are added: BQ2752X, 531, 542, 546, 742, 425, 441, 621 Chip-specific features are now tracked by BQ27XXX_O_* flags in di->opts. No functional changes to the driver. Signed-off-by: Liam Breck Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 89890437f9ab..e48e7a4e9cd6 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -6,6 +6,7 @@ enum bq27xxx_chip { BQ27010, /* bq27010, bq27210 */ BQ2750X, /* bq27500 deprecated alias */ BQ2751X, /* bq27510, bq27520 deprecated alias */ + BQ2752X, BQ27500, /* bq27500/1 */ BQ27510G1, /* bq27510G1 */ BQ27510G2, /* bq27510G2 */ @@ -15,9 +16,16 @@ enum bq27xxx_chip { BQ27520G3, /* bq27520G3 */ BQ27520G4, /* bq27520G4 */ BQ27530, /* bq27530, bq27531 */ + BQ27531, BQ27541, /* bq27541, bq27542, bq27546, bq27742 */ + BQ27542, + BQ27546, + BQ27742, BQ27545, /* bq27545 */ BQ27421, /* bq27421, bq27425, bq27441, bq27621 */ + BQ27425, + BQ27441, + BQ27621, }; struct bq27xxx_device_info; @@ -47,6 +55,7 @@ struct bq27xxx_device_info { int id; enum bq27xxx_chip chip; bool ram_chip; + u32 opts; const char *name; struct bq27xxx_dm_reg *dm_regs; u32 unseal_key; -- cgit v1.2.3 From 05045379b2740686020618c8cfd4b517cff9f918 Mon Sep 17 00:00:00 2001 From: Liam Breck Date: Wed, 23 Aug 2017 20:36:15 -0700 Subject: power: supply: bq27xxx: Enable data memory update for certain chips Support data memory update on BQ27425. Parameters from TI datasheets are also provided for BQ27500, 545, 421, 441, 621; however these are commented out, as they are not tested. Add BQ27XXX_O_CFGUP & _O_RAM for use in bq27xxx_chip_data[n].opts and by data memory update functions. Signed-off-by: Liam Breck Signed-off-by: Sebastian Reichel --- include/linux/power/bq27xxx_battery.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index e48e7a4e9cd6..43194e02c1ee 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -54,7 +54,6 @@ struct bq27xxx_device_info { struct device *dev; int id; enum bq27xxx_chip chip; - bool ram_chip; u32 opts; const char *name; struct bq27xxx_dm_reg *dm_regs; -- cgit v1.2.3 From 75e8387685f6c65feb195a4556110b58f852b848 Mon Sep 17 00:00:00 2001 From: Zhou Chengming Date: Fri, 25 Aug 2017 21:49:37 +0800 Subject: perf/ftrace: Fix double traces of perf on ftrace:function When running perf on the ftrace:function tracepoint, there is a bug which can be reproduced by: perf record -e ftrace:function -a sleep 20 & perf record -e ftrace:function ls perf script ls 10304 [005] 171.853235: ftrace:function: perf_output_begin ls 10304 [005] 171.853237: ftrace:function: perf_output_begin ls 10304 [005] 171.853239: ftrace:function: task_tgid_nr_ns ls 10304 [005] 171.853240: ftrace:function: task_tgid_nr_ns ls 10304 [005] 171.853242: ftrace:function: __task_pid_nr_ns ls 10304 [005] 171.853244: ftrace:function: __task_pid_nr_ns We can see that all the function traces are doubled. The problem is caused by the inconsistency of the register function perf_ftrace_event_register() with the probe function perf_ftrace_function_call(). The former registers one probe for every perf_event. And the latter handles all perf_events on the current cpu. So when two perf_events on the current cpu, the traces of them will be doubled. So this patch adds an extra parameter "event" for perf_tp_event, only send sample data to this event when it's not NULL. Signed-off-by: Zhou Chengming Reviewed-by: Jiri Olsa Acked-by: Steven Rostedt (VMware) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: acme@kernel.org Cc: alexander.shishkin@linux.intel.com Cc: huawei.libin@huawei.com Link: http://lkml.kernel.org/r/1503668977-12526-1-git-send-email-zhouchengming1@huawei.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- include/linux/trace_events.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b14095bcf4bb..c00cd4b02f32 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1201,7 +1201,7 @@ extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, - struct task_struct *task); + struct task_struct *task, struct perf_event *event); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 536c80ff7ad9..5012b524283d 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -508,9 +508,9 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, u64 count, struct pt_regs *regs, void *head, - struct task_struct *task) + struct task_struct *task, struct perf_event *event) { - perf_tp_event(type, count, raw_data, size, regs, head, rctx, task); + perf_tp_event(type, count, raw_data, size, regs, head, rctx, task, event); } #endif -- cgit v1.2.3 From 6e44636aeab19259f804c8abca57a95ddc01df66 Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Tue, 15 Aug 2017 11:59:02 +0300 Subject: net/mlx5: Update HW layout definitions * add offload_type field to mlx5_ifc_qpc_bits * update mlx5_ifc_xrqc_bits layout Signed-off-by: Artemy Kovalyov Reviewed-by: Yossi Itigin Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/mlx5_ifc.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 4eff0b8a1482..e27283ab3667 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2022,6 +2022,10 @@ enum { MLX5_QPC_PM_STATE_MIGRATED = 0x3, }; +enum { + MLX5_QPC_OFFLOAD_TYPE_RNDV = 0x1, +}; + enum { MLX5_QPC_END_PADDING_MODE_SCATTER_AS_IS = 0x0, MLX5_QPC_END_PADDING_MODE_PAD_TO_CACHE_LINE_ALIGNMENT = 0x1, @@ -2065,7 +2069,8 @@ struct mlx5_ifc_qpc_bits { u8 st[0x8]; u8 reserved_at_10[0x3]; u8 pm_state[0x2]; - u8 reserved_at_15[0x7]; + u8 reserved_at_15[0x3]; + u8 offload_type[0x4]; u8 end_padding_mode[0x2]; u8 reserved_at_1e[0x2]; @@ -3010,7 +3015,7 @@ struct mlx5_ifc_xrqc_bits { struct mlx5_ifc_tag_matching_topology_context_bits tag_matching_topology_context; - u8 reserved_at_180[0x880]; + u8 reserved_at_180[0x280]; struct mlx5_ifc_wq_bits wq; }; -- cgit v1.2.3 From 5b3ec3fcb6bbe081279c73fb574af8c72f14cea0 Mon Sep 17 00:00:00 2001 From: Artemy Kovalyov Date: Thu, 17 Aug 2017 15:52:10 +0300 Subject: net/mlx5: Add XRQ support Add support to new XRQ(eXtended shared Receive Queue) hardware object. It supports SRQ semantics with addition of extended receive buffers topologies and offloads. Currently supports tag matching topology and rendezvouz offload. Signed-off-by: Artemy Kovalyov Reviewed-by: Yossi Itigin Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford --- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/srq.h | 5 +++++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 99d88624ad07..c33e6f7a1afb 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -418,6 +418,7 @@ enum mlx5_res_type { MLX5_RES_SQ = MLX5_EVENT_QUEUE_TYPE_SQ, MLX5_RES_SRQ = 3, MLX5_RES_XSRQ = 4, + MLX5_RES_XRQ = 5, }; struct mlx5_core_rsc_common { diff --git a/include/linux/mlx5/srq.h b/include/linux/mlx5/srq.h index 1cde0fd53f90..24ff23e27c8a 100644 --- a/include/linux/mlx5/srq.h +++ b/include/linux/mlx5/srq.h @@ -38,6 +38,7 @@ enum { MLX5_SRQ_FLAG_ERR = (1 << 0), MLX5_SRQ_FLAG_WQ_SIG = (1 << 1), + MLX5_SRQ_FLAG_RNDV = (1 << 2), }; struct mlx5_srq_attr { @@ -56,6 +57,10 @@ struct mlx5_srq_attr { u32 user_index; u64 db_record; __be64 *pas; + u32 tm_log_list_size; + u32 tm_next_tag; + u32 tm_hw_phase_cnt; + u32 tm_sw_phase_cnt; }; struct mlx5_core_dev; -- cgit v1.2.3 From 8d4e6c4caa12dafbcba138e5450b7af17b0b2194 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Thu, 30 Mar 2017 18:39:56 +0300 Subject: perf/core, pt, bts: Get rid of itrace_started I just noticed that hw.itrace_started and hw.config are aliased to the same location. Now, the PT driver happens to use both, which works out fine by sheer luck: - STORE(hw.itrace_start) is ordered before STORE(hw.config), in the program order, although there are no compiler barriers to ensure that, - to the perf_log_itrace_start() hw.itrace_start looks set at the same time as when it is intended to be set because both stores happen in the same path, - hw.config is never reset to zero in the PT driver. Now, the use of hw.config by the PT driver makes more sense (it being a HW PMU) than messing around with itrace_started, which is an awkward API to begin with. This patch replaces hw.itrace_started with an attach_state bit and an API call for the PMU drivers to use to communicate the condition. Signed-off-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: vince@deater.net Link: http://lkml.kernel.org/r/20170330153956.25994-1-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c00cd4b02f32..adda0aaae6c8 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -147,9 +147,6 @@ struct hw_perf_event { struct list_head cqm_groups_entry; struct list_head cqm_group_entry; }; - struct { /* itrace */ - int itrace_started; - }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; @@ -541,6 +538,7 @@ struct swevent_hlist { #define PERF_ATTACH_GROUP 0x02 #define PERF_ATTACH_TASK 0x04 #define PERF_ATTACH_TASK_DATA 0x08 +#define PERF_ATTACH_ITRACE 0x10 struct perf_cgroup; struct ring_buffer; @@ -864,6 +862,7 @@ extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); +extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern void perf_pmu_unregister(struct pmu *pmu); -- cgit v1.2.3 From fc7ce9c74c3ad232b084d80148654f926d01ece7 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Mon, 28 Aug 2017 20:52:49 -0400 Subject: perf/core, x86: Add PERF_SAMPLE_PHYS_ADDR For understanding how the workload maps to memory channels and hardware behavior, it's very important to collect address maps with physical addresses. For example, 3D XPoint access can only be found by filtering the physical address. Add a new sample type for physical address. perf already has a facility to collect data virtual address. This patch introduces a function to convert the virtual address to physical address. The function is quite generic and can be extended to any architecture as long as a virtual address is provided. - For kernel direct mapping addresses, virt_to_phys is used to convert the virtual addresses to physical address. - For user virtual addresses, __get_user_pages_fast is used to walk the pages tables for user physical address. - This does not work for vmalloc addresses right now. These are not resolved, but code to do that could be added. The new sample type requires collecting the virtual address. The virtual address will not be output unless SAMPLE_ADDR is applied. For security, the physical address can only be exposed to root or privileged user. Tested-by: Madhavan Srinivasan Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: acme@kernel.org Cc: mpe@ellerman.id.au Link: http://lkml.kernel.org/r/1503967969-48278-1-git-send-email-kan.liang@intel.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index adda0aaae6c8..718ba163c1b9 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -943,6 +943,8 @@ struct perf_sample_data { struct perf_regs regs_intr; u64 stack_user_size; + + u64 phys_addr; } ____cacheline_aligned; /* default value for data source */ -- cgit v1.2.3 From f52be5708076b75a045ac52c6fef3fffb8300525 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 29 Aug 2017 10:59:39 +0200 Subject: locking/lockdep: Untangle xhlock history save/restore from task independence Where XHLOCK_{SOFT,HARD} are save/restore points in the xhlocks[] to ensure the temporal IRQ events don't interact with task state, the XHLOCK_PROC is a fundament different beast that just happens to share the interface. The purpose of XHLOCK_PROC is to annotate independent execution inside one task. For example workqueues, each work should appear to run in its own 'pristine' 'task'. Remove XHLOCK_PROC in favour of its own interface to avoid confusion. Signed-off-by: Peter Zijlstra (Intel) Cc: Byungchul Park Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: boqun.feng@gmail.com Cc: david@fromorbit.com Cc: johannes@sipsolutions.net Cc: kernel-team@lge.com Cc: oleg@redhat.com Cc: tj@kernel.org Link: http://lkml.kernel.org/r/20170829085939.ggmb6xiohw67micb@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/irqflags.h | 4 ++-- include/linux/lockdep.h | 7 ++++--- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 9bc050bc81b2..5fdd93bb9300 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -26,7 +26,7 @@ # define trace_hardirq_enter() \ do { \ current->hardirq_context++; \ - crossrelease_hist_start(XHLOCK_HARD, 0);\ + crossrelease_hist_start(XHLOCK_HARD); \ } while (0) # define trace_hardirq_exit() \ do { \ @@ -36,7 +36,7 @@ do { \ # define lockdep_softirq_enter() \ do { \ current->softirq_context++; \ - crossrelease_hist_start(XHLOCK_SOFT, 0);\ + crossrelease_hist_start(XHLOCK_SOFT); \ } while (0) # define lockdep_softirq_exit() \ do { \ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 78bb7133abed..bfa8e0b0d6f1 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -551,7 +551,6 @@ struct pin_cookie { }; enum xhlock_context_t { XHLOCK_HARD, XHLOCK_SOFT, - XHLOCK_PROC, XHLOCK_CTX_NR, }; @@ -580,8 +579,9 @@ extern void lock_commit_crosslock(struct lockdep_map *lock); #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), .cross = 0, } -extern void crossrelease_hist_start(enum xhlock_context_t c, bool force); +extern void crossrelease_hist_start(enum xhlock_context_t c); extern void crossrelease_hist_end(enum xhlock_context_t c); +extern void lockdep_invariant_state(bool force); extern void lockdep_init_task(struct task_struct *task); extern void lockdep_free_task(struct task_struct *task); #else /* !CROSSRELEASE */ @@ -593,8 +593,9 @@ extern void lockdep_free_task(struct task_struct *task); #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), } -static inline void crossrelease_hist_start(enum xhlock_context_t c, bool force) {} +static inline void crossrelease_hist_start(enum xhlock_context_t c) {} static inline void crossrelease_hist_end(enum xhlock_context_t c) {} +static inline void lockdep_invariant_state(bool force) {} static inline void lockdep_init_task(struct task_struct *task) {} static inline void lockdep_free_task(struct task_struct *task) {} #endif /* CROSSRELEASE */ -- cgit v1.2.3 From 966a967116e699762dbf4af7f9e0d1955c25aa37 Mon Sep 17 00:00:00 2001 From: Ying Huang Date: Tue, 8 Aug 2017 12:30:00 +0800 Subject: smp: Avoid using two cache lines for struct call_single_data struct call_single_data is used in IPIs to transfer information between CPUs. Its size is bigger than sizeof(unsigned long) and less than cache line size. Currently it is not allocated with any explicit alignment requirements. This makes it possible for allocated call_single_data to cross two cache lines, which results in double the number of the cache lines that need to be transferred among CPUs. This can be fixed by requiring call_single_data to be aligned with the size of call_single_data. Currently the size of call_single_data is the power of 2. If we add new fields to call_single_data, we may need to add padding to make sure the size of new definition is the power of 2 as well. Fortunately, this is enforced by GCC, which will report bad sizes. To set alignment requirements of call_single_data to the size of call_single_data, a struct definition and a typedef is used. To test the effect of the patch, I used the vm-scalability multiple thread swap test case (swap-w-seq-mt). The test will create multiple threads and each thread will eat memory until all RAM and part of swap is used, so that huge number of IPIs are triggered when unmapping memory. In the test, the throughput of memory writing improves ~5% compared with misaligned call_single_data, because of faster IPIs. Suggested-by: Peter Zijlstra Signed-off-by: Huang, Ying [ Add call_single_data_t and align with size of call_single_data. ] Signed-off-by: Peter Zijlstra (Intel) Cc: Aaron Lu Cc: Borislav Petkov Cc: Eric Dumazet Cc: Juergen Gross Cc: Linus Torvalds Cc: Michael Ellerman Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/87bmnqd6lz.fsf@yhuang-mobile.sh.intel.com Signed-off-by: Ingo Molnar --- include/linux/blkdev.h | 2 +- include/linux/netdevice.h | 2 +- include/linux/smp.h | 8 ++++++-- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 25f6a0cb27d3..006fa09a641e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -134,7 +134,7 @@ typedef __u32 __bitwise req_flags_t; struct request { struct list_head queuelist; union { - struct call_single_data csd; + call_single_data_t csd; u64 fifo_time; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 779b23595596..6557f320b66e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2774,7 +2774,7 @@ struct softnet_data { unsigned int input_queue_head ____cacheline_aligned_in_smp; /* Elements below can be accessed between CPUs for RPS/RFS */ - struct call_single_data csd ____cacheline_aligned_in_smp; + call_single_data_t csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; unsigned int cpu; unsigned int input_queue_tail; diff --git a/include/linux/smp.h b/include/linux/smp.h index 68123c1fe549..98b1fe027fc9 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -14,13 +14,17 @@ #include typedef void (*smp_call_func_t)(void *info); -struct call_single_data { +struct __call_single_data { struct llist_node llist; smp_call_func_t func; void *info; unsigned int flags; }; +/* Use __aligned() to avoid to use 2 cache lines for 1 csd */ +typedef struct __call_single_data call_single_data_t + __aligned(sizeof(struct __call_single_data)); + /* total number of cpus in this system (may exceed NR_CPUS) */ extern unsigned int total_cpus; @@ -48,7 +52,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), smp_call_func_t func, void *info, bool wait, gfp_t gfp_flags); -int smp_call_function_single_async(int cpu, struct call_single_data *csd); +int smp_call_function_single_async(int cpu, call_single_data_t *csd); #ifdef CONFIG_SMP -- cgit v1.2.3 From ec81048cc340bb03334e6ca62661ecc0a684897a Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Wed, 23 Aug 2017 23:25:38 +0800 Subject: sched/completion: Avoid unnecessary stack allocation for COMPLETION_INITIALIZER_ONSTACK() In theory, COMPLETION_INITIALIZER_ONSTACK() should never affect the stack allocation of the caller. However, on some compilers, a temporary structure was allocated for the return value of COMPLETION_INITIALIZER_ONSTACK(). For example in write_journal() with LOCKDEP_COMPLETIONS=y (GCC is 7.1.1): io_comp.comp = COMPLETION_INITIALIZER_ONSTACK(io_comp.comp); 2462: e8 00 00 00 00 callq 2467 2467: 48 8d 85 80 fd ff ff lea -0x280(%rbp),%rax 246e: 48 c7 c6 00 00 00 00 mov $0x0,%rsi 2475: 48 c7 c2 00 00 00 00 mov $0x0,%rdx x->done = 0; 247c: c7 85 90 fd ff ff 00 movl $0x0,-0x270(%rbp) 2483: 00 00 00 init_waitqueue_head(&x->wait); 2486: 48 8d 78 18 lea 0x18(%rax),%rdi 248a: e8 00 00 00 00 callq 248f if (commit_start + commit_sections <= ic->journal_sections) { 248f: 41 8b 87 a8 00 00 00 mov 0xa8(%r15),%eax io_comp.comp = COMPLETION_INITIALIZER_ONSTACK(io_comp.comp); 2496: 48 8d bd e8 f9 ff ff lea -0x618(%rbp),%rdi 249d: 48 8d b5 90 fd ff ff lea -0x270(%rbp),%rsi 24a4: b9 17 00 00 00 mov $0x17,%ecx 24a9: f3 48 a5 rep movsq %ds:(%rsi),%es:(%rdi) if (commit_start + commit_sections <= ic->journal_sections) { 24ac: 41 39 c6 cmp %eax,%r14d io_comp.comp = COMPLETION_INITIALIZER_ONSTACK(io_comp.comp); 24af: 48 8d bd 90 fd ff ff lea -0x270(%rbp),%rdi 24b6: 48 8d b5 e8 f9 ff ff lea -0x618(%rbp),%rsi 24bd: b9 17 00 00 00 mov $0x17,%ecx 24c2: f3 48 a5 rep movsq %ds:(%rsi),%es:(%rdi) We can obviously see the temporary structure allocated, and the compiler also does two meaningless memcpy with "rep movsq". And according to: https://gcc.gnu.org/onlinedocs/gcc/Statement-Exprs.html#Statement-Exprs The return value of a statement expression is returned by value, so the temporary variable is created in COMPLETION_INITIALIZER_ONSTACK(), and that's why the temporary structures are allocted. To fix this, make the brace block in COMPLETION_INITIALIZER_ONSTACK() return a pointer and dereference it outside the block rather than return the whole structure, in this way, we are able to teach the compiler not to do the unnecessary stack allocation. This could also reduce the stack size even if !LOCKDEP, for example in write_journal(), compiled with gcc 7.1.1, the result of command: objdump -d drivers/md/dm-integrity.o | ./scripts/checkstack.pl x86 before: 0x0000246a write_journal [dm-integrity.o]: 696 after: 0x00002b7a write_journal [dm-integrity.o]: 296 Reported-by: Arnd Bergmann Signed-off-by: Boqun Feng Signed-off-by: Peter Zijlstra (Intel) Acked-by: Arnd Bergmann Cc: Andrew Morton Cc: Byungchul Park Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: walken@google.com Cc: willy@infradead.org Link: http://lkml.kernel.org/r/20170823152542.5150-3-boqun.feng@gmail.com Signed-off-by: Ingo Molnar --- include/linux/completion.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/completion.h b/include/linux/completion.h index 791f053f28b7..cae5400022a3 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -74,7 +74,7 @@ static inline void complete_release_commit(struct completion *x) {} #endif #define COMPLETION_INITIALIZER_ONSTACK(work) \ - ({ init_completion(&work); work; }) + (*({ init_completion(&work); &work; })) /** * DECLARE_COMPLETION - declare and initialize a completion structure -- cgit v1.2.3 From e8f11db956aa09c1618051a7aaf367d6810d8d8c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Aug 2017 14:42:06 +0200 Subject: libata: check for trusted computing in IDENTIFY DEVICE data ATA-8 and later mirrors the TRUSTED COMPUTING SUPPORTED bit in word 48 of the IDENTIFY DEVICE data. Check this before issuing a READ LOG PAGE command to avoid issues with buggy devices. The only downside is that we can't support Security Send / Receive for a device with an older revision due to the conflicting use of this field in earlier specifications. tj: The reason we need this is because some devices which don't support READ LOG PAGE lock up after getting issued that command. Signed-off-by: Christoph Hellwig Tested-by: David Ahern Signed-off-by: Tejun Heo --- include/linux/ata.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ata.h b/include/linux/ata.h index e65ae4b2ed48..c7a353825450 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -60,7 +60,8 @@ enum { ATA_ID_FW_REV = 23, ATA_ID_PROD = 27, ATA_ID_MAX_MULTSECT = 47, - ATA_ID_DWORD_IO = 48, + ATA_ID_DWORD_IO = 48, /* before ATA-8 */ + ATA_ID_TRUSTED = 48, /* ATA-8 and later */ ATA_ID_CAPABILITY = 49, ATA_ID_OLD_PIO_MODES = 51, ATA_ID_OLD_DMA_MODES = 52, @@ -889,6 +890,13 @@ static inline bool ata_id_has_dword_io(const u16 *id) return id[ATA_ID_DWORD_IO] & (1 << 0); } +static inline bool ata_id_has_trusted(const u16 *id) +{ + if (ata_id_major_version(id) <= 7) + return false; + return id[ATA_ID_TRUSTED] & (1 << 0); +} + static inline bool ata_id_has_unload(const u16 *id) { if (ata_id_major_version(id) >= 7 && -- cgit v1.2.3 From 2aca392398384f8a2f339f4c661a1699f4f2e2eb Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Aug 2017 08:36:58 -0700 Subject: Revert "libata: quirk read log on no-name M.2 SSD" This reverts commit 35f0b6a779b8b7a98faefd7c1c660b4dac9a5c26. We now conditionalize issuing of READ LOG PAGE on the TRUSTED COMPUTING SUPPORTED bit in the identity data and this shouldn't be necessary. Signed-off-by: Tejun Heo --- include/linux/libata.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 9e927ae7fced..931c32f1f18d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -438,7 +438,6 @@ enum { ATA_HORKAGE_NO_DMA_LOG = (1 << 23), /* don't use DMA for log read */ ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ - ATA_HORKAGE_NO_LOG_PAGE = (1 << 26), /* Doesn't like Get Log Page */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 2d2a2b8c080ad8feab7ca87769dedb3c7a83a375 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lothar=20Wa=C3=9Fmann?= Date: Tue, 29 Aug 2017 12:17:13 +0200 Subject: mtd: nand: complain loudly when chip->bits_per_cell is not correctly initialized MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit chip->bits_per_cell which is used to determine the NAND cell type (SLC/MLC) should always have a value != 0. Complain loudly if the value is 0 in nand_is_slc() to catch use before correct initialization. Signed-off-by: Lothar Waßmann Signed-off-by: Boris Brezillon --- include/linux/mtd/rawnand.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 8fb488d586d6..c433f093766a 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1234,6 +1234,8 @@ int onfi_init_data_interface(struct nand_chip *chip, */ static inline bool nand_is_slc(struct nand_chip *chip) { + WARN(chip->bits_per_cell == 0, + "chip->bits_per_cell is used uninitialized\n"); return chip->bits_per_cell == 1; } -- cgit v1.2.3 From f5808ac158f2b16b686a3d3c0879c5d6048aba14 Mon Sep 17 00:00:00 2001 From: Andrew Jeffery Date: Mon, 28 Aug 2017 09:47:11 +0930 Subject: leds: gpio: Allow LED to retain state at shutdown In some systems, such as Baseboard Management Controllers (BMCs), we want to retain the state of LEDs across a reboot of the BMC (whilst the host remains up). Implement support for the retain-state-shutdown devicetree property in leds-gpio. Signed-off-by: Andrew Jeffery Acked-by: Pavel Machek Tested-by: Brandon Wyman Signed-off-by: Jacek Anaszewski --- include/linux/leds.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/leds.h b/include/linux/leds.h index 64c56d454f7d..bf6db4fe895b 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -49,6 +49,7 @@ struct led_classdev { #define LED_HW_PLUGGABLE (1 << 19) #define LED_PANIC_INDICATOR (1 << 20) #define LED_BRIGHT_HW_CHANGED (1 << 21) +#define LED_RETAIN_AT_SHUTDOWN (1 << 22) /* set_brightness_work / blink_timer flags, atomic, private. */ unsigned long work_flags; @@ -392,6 +393,7 @@ struct gpio_led { unsigned retain_state_suspended : 1; unsigned panic_indicator : 1; unsigned default_state : 2; + unsigned retain_state_shutdown : 1; /* default_state should be one of LEDS_GPIO_DEFSTATE_(ON|OFF|KEEP) */ struct gpio_desc *gpiod; }; -- cgit v1.2.3 From 52c9285d47459cf241e144c7d8ef15941ba1b181 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Fri, 18 Aug 2017 20:27:56 +0530 Subject: PCI: endpoint: Add support for configurable page size MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit pci-epc-mem uses a page size equal to *PAGE_SIZE* (usually 4KB) to manage the address space. However certain platforms like TI's K2G have a restriction that this address space should be either divided into 1MB/2MB/4MB or 8MB sizes (Ref: 11.14.4.9.1 Outbound Address Translation in K2G TRM SPRUHY8F January 2016 – Revised May 2017). Add support to handle different page sizes here. Signed-off-by: Kishon Vijay Abraham I Signed-off-by: Bjorn Helgaas --- include/linux/pci-epc.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index af5edbf3eea3..f7a04e1af112 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -62,11 +62,13 @@ struct pci_epc_ops { * @size: the size of the PCI address space * @bitmap: bitmap to manage the PCI address space * @pages: number of bits representing the address region + * @page_size: size of each page */ struct pci_epc_mem { phys_addr_t phys_base; size_t size; unsigned long *bitmap; + size_t page_size; int pages; }; @@ -98,6 +100,9 @@ struct pci_epc { #define devm_pci_epc_create(dev, ops) \ __devm_pci_epc_create((dev), (ops), THIS_MODULE) +#define pci_epc_mem_init(epc, phys_addr, size) \ + __pci_epc_mem_init((epc), (phys_addr), (size), PAGE_SIZE) + static inline void epc_set_drvdata(struct pci_epc *epc, void *data) { dev_set_drvdata(&epc->dev, data); @@ -135,7 +140,8 @@ void pci_epc_stop(struct pci_epc *epc); struct pci_epc *pci_epc_get(const char *epc_name); void pci_epc_put(struct pci_epc *epc); -int pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_addr, size_t size); +int __pci_epc_mem_init(struct pci_epc *epc, phys_addr_t phys_addr, size_t size, + size_t page_size); void pci_epc_mem_exit(struct pci_epc *epc); void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc, phys_addr_t *phys_addr, size_t size); -- cgit v1.2.3 From 9de7e14a1a9c6bc4f9be6ccd9b951341a80dbd52 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 29 Aug 2017 10:20:38 +0200 Subject: drbd: new disk-option disable-write-same Some backend devices claim to support write-same, but would fail actual write-same requests. Allow to set (or toggle) whether or not DRBD tries to support write-same. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd_genl.h | 3 ++- include/linux/drbd_limits.h | 8 +++++++- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h index 2896f93808ae..4e6d4d4c7056 100644 --- a/include/linux/drbd_genl.h +++ b/include/linux/drbd_genl.h @@ -132,7 +132,8 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf, __flg_field_def(18, DRBD_GENLA_F_MANDATORY, disk_drain, DRBD_DISK_DRAIN_DEF) __flg_field_def(19, DRBD_GENLA_F_MANDATORY, md_flushes, DRBD_MD_FLUSHES_DEF) __flg_field_def(23, 0 /* OPTIONAL */, al_updates, DRBD_AL_UPDATES_DEF) - __flg_field_def(24, 0 /* OPTIONAL */, discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED) + __flg_field_def(24, 0 /* OPTIONAL */, discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF) + __flg_field_def(26, 0 /* OPTIONAL */, disable_write_same, DRBD_DISABLE_WRITE_SAME_DEF) ) GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts, diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index ddac68422a96..24ae1b9b76c7 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -209,12 +209,18 @@ #define DRBD_MD_FLUSHES_DEF 1 #define DRBD_TCP_CORK_DEF 1 #define DRBD_AL_UPDATES_DEF 1 + /* We used to ignore the discard_zeroes_data setting. * To not change established (and expected) behaviour, * by default assume that, for discard_zeroes_data=0, * we can make that an effective discard_zeroes_data=1, * if we only explicitly zero-out unaligned partial chunks. */ -#define DRBD_DISCARD_ZEROES_IF_ALIGNED 1 +#define DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF 1 + +/* Some backends pretend to support WRITE SAME, + * but fail such requests when they are actually submitted. + * This is to tell DRBD to not even try. */ +#define DRBD_DISABLE_WRITE_SAME_DEF 0 #define DRBD_ALLOW_TWO_PRIMARIES_DEF 0 #define DRBD_ALWAYS_ASBP_DEF 0 -- cgit v1.2.3 From 365cf663b64791e341f425385c7ae152327c7009 Mon Sep 17 00:00:00 2001 From: Roland Kammerer Date: Tue, 29 Aug 2017 10:20:48 +0200 Subject: drbd: switch from kmalloc() to kmalloc_array() We had one call to kmalloc that actually allocates an array. Switch that one to the kmalloc_array() function. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- include/linux/drbd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 002611c85318..2d0259327721 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -51,7 +51,7 @@ #endif extern const char *drbd_buildtag(void); -#define REL_VERSION "8.4.7" +#define REL_VERSION "8.4.10" #define API_VERSION 1 #define PRO_VERSION_MIN 86 #define PRO_VERSION_MAX 101 -- cgit v1.2.3 From c73c8b1e47ca275388f774fd36560ab7e994e99e Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Mon, 28 Aug 2017 16:38:20 +0300 Subject: net/mlx4_core: Dynamically allocate structs at mlx4_slave_cap In order to avoid temporary large structs on the stack, allocate them dynamically. Signed-off-by: Eran Ben Elisha Signed-off-by: Tal Alon Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b54517c05e9a..9844606f9491 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -518,6 +518,14 @@ struct mlx4_phys_caps { u32 base_tunnel_sqpn; }; +struct mlx4_spec_qps { + u32 qp0_qkey; + u32 qp0_proxy; + u32 qp0_tunnel; + u32 qp1_proxy; + u32 qp1_tunnel; +}; + struct mlx4_caps { u64 fw_ver; u32 function; @@ -547,11 +555,7 @@ struct mlx4_caps { int max_qp_init_rdma; int max_qp_dest_rdma; int max_tc_eth; - u32 *qp0_qkey; - u32 *qp0_proxy; - u32 *qp1_proxy; - u32 *qp0_tunnel; - u32 *qp1_tunnel; + struct mlx4_spec_qps *spec_qps; int num_srqs; int max_srq_wqes; int max_srq_sge; -- cgit v1.2.3 From be59960395f86991c6599c41d8c421fe4bf7a210 Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Mon, 28 Aug 2017 16:38:23 +0300 Subject: net/mlx4: Add user mac FW update support Adding support for updating the FW on new port mac, when port mac change is requested by the user. This info is required by the FW as OEM management tools require this info directly from the NIC FW. Check device capability bit to verify the FW supports user mac. If the FW does support it, use set_port command to notify the FW on the new mac. The feature is relevant only to PF port mac. Signed-off-by: Moshe Shemesh Signed-off-by: Tariq Toukan Signed-off-by: David S. Miller --- include/linux/mlx4/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 9844606f9491..89c0e7f7cd9b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -224,6 +224,7 @@ enum { MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT = 1ULL << 35, MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP = 1ULL << 36, MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT = 1ULL << 37, + MLX4_DEV_CAP_FLAG2_USER_MAC_EN = 1ULL << 38, }; enum { @@ -1377,6 +1378,7 @@ int mlx4_get_base_qpn(struct mlx4_dev *dev, u8 port); int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac); int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu, u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx); +int mlx4_SET_PORT_user_mac(struct mlx4_dev *dev, u8 port, u8 *user_mac); int mlx4_SET_PORT_user_mtu(struct mlx4_dev *dev, u8 port, u16 user_mtu); int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn, u8 promisc); -- cgit v1.2.3 From 0dd5759dbb1c9a862e7d90c09d6cf398c45f1100 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 29 Aug 2017 13:17:51 -0700 Subject: net: remove dmaengine.h inclusion from netdevice.h Since the removal of NET_DMA, dmaengine.h header file shouldn't be needed by netdevice.h anymore. Signed-off-by: Dave Jiang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c5475b37a631..29bf06ff157c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -35,7 +35,6 @@ #include #include -#include #include #include -- cgit v1.2.3 From dc2251bf98c66db3f4e055b751968f0871037ae4 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 23 Aug 2017 23:19:57 +0200 Subject: cpuidle: Eliminate the CPUIDLE_DRIVER_STATE_START symbol On some architectures the first (index 0) idle state is a polling one and it doesn't really save energy, so there is the CPUIDLE_DRIVER_STATE_START symbol allowing some pieces of cpuidle code to avoid using that state. However, this makes the code rather hard to follow. It is better to explicitly avoid the polling state, so add a new cpuidle state flag CPUIDLE_FLAG_POLLING to mark it and make the relevant code check that flag for the first state instead of using the CPUIDLE_DRIVER_STATE_START symbol. In the ACPI processor driver that cannot always rely on the state flags (like before the states table has been set up) define a new internal symbol ACPI_IDLE_STATE_START equivalent to the CPUIDLE_DRIVER_STATE_START one and drop the latter. Signed-off-by: Rafael J. Wysocki Tested-by: Sudeep Holla Acked-by: Daniel Lezcano --- include/linux/cpuidle.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index fc1e5d7fc1c7..b58d952a00e2 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -63,6 +63,7 @@ struct cpuidle_state { /* Idle State Flags */ #define CPUIDLE_FLAG_NONE (0x00) +#define CPUIDLE_FLAG_POLLING (0x01) /* polling state */ #define CPUIDLE_FLAG_COUPLED (0x02) /* state applies to multiple cpus */ #define CPUIDLE_FLAG_TIMER_STOP (0x04) /* timer is stopped on this state */ @@ -250,12 +251,6 @@ static inline int cpuidle_register_governor(struct cpuidle_governor *gov) {return 0;} #endif -#ifdef CONFIG_ARCH_HAS_CPU_RELAX -#define CPUIDLE_DRIVER_STATE_START 1 -#else -#define CPUIDLE_DRIVER_STATE_START 0 -#endif - #define CPU_PM_CPU_IDLE_ENTER(low_level_idle_enter, idx) \ ({ \ int __ret; \ -- cgit v1.2.3 From 34c2f65b718d44ea7d7b3cc10777f410677455ce Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 23 Aug 2017 23:21:07 +0200 Subject: cpuidle: Move polling state initialization code to separate file Move the polling state initialization code to a separate file built conditionally on CONFIG_ARCH_HAS_CPU_RELAX to get rid of the #ifdef in driver.c. Signed-off-by: Rafael J. Wysocki Tested-by: Sudeep Holla Acked-by: Daniel Lezcano --- include/linux/cpuidle.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index b58d952a00e2..561bc5365067 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -225,6 +225,12 @@ static inline void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, } #endif +#ifdef CONFIG_ARCH_HAS_CPU_RELAX +void poll_idle_init(struct cpuidle_driver *drv); +#else +static void poll_idle_init(struct cpuidle_driver *drv) {} +#endif + /****************************** * CPUIDLE GOVERNOR INTERFACE * ******************************/ -- cgit v1.2.3 From 1b39e3f813b4685c7a30ae964d5529a1b0e3a286 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 29 Aug 2017 03:14:37 +0200 Subject: cpuidle: Make drivers initialize polling state Make the drivers that want to include the polling state into their states table initialize it explicitly and drop the initialization of it (which in fact is conditional, but that is not obvious from the code) from the core. Signed-off-by: Rafael J. Wysocki Tested-by: Sudeep Holla Acked-by: Daniel Lezcano --- include/linux/cpuidle.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 561bc5365067..5baacd3a0559 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -226,9 +226,9 @@ static inline void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, #endif #ifdef CONFIG_ARCH_HAS_CPU_RELAX -void poll_idle_init(struct cpuidle_driver *drv); +void cpuidle_poll_state_init(struct cpuidle_driver *drv); #else -static void poll_idle_init(struct cpuidle_driver *drv) {} +static inline void cpuidle_poll_state_init(struct cpuidle_driver *drv) {} #endif /****************************** -- cgit v1.2.3 From 26e3e3cb05604073f2e9969fb0f06f35eb3b3313 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 29 Aug 2017 08:50:11 -0700 Subject: scsi: rcu: Introduce rcu_swap_protected() A common pattern in RCU code is to assign a new value to an RCU pointer after having read and stored the old value. Introduce a macro for this pattern. Signed-off-by: Bart Van Assche Acked-by: Paul E. McKenney Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Johannes Thumshirn Cc: Shane M Seymour Signed-off-by: Martin K. Petersen --- include/linux/rcupdate.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f816fc72b51e..8e920f0ecb07 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -407,6 +407,22 @@ static inline void rcu_preempt_sleep_check(void) { } _r_a_p__v; \ }) +/** + * rcu_swap_protected() - swap an RCU and a regular pointer + * @rcu_ptr: RCU pointer + * @ptr: regular pointer + * @c: the conditions under which the dereference will take place + * + * Perform swap(@rcu_ptr, @ptr) where @rcu_ptr is an RCU-annotated pointer and + * @c is the argument that is passed to the rcu_dereference_protected() call + * used to read that pointer. + */ +#define rcu_swap_protected(rcu_ptr, ptr, c) do { \ + typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ + rcu_assign_pointer((rcu_ptr), (ptr)); \ + (ptr) = __tmp; \ +} while (0) + /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read -- cgit v1.2.3 From c1225f01af085aea9c9d094febf157de9d07d861 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Aug 2017 17:37:38 +0200 Subject: scsi: bsg-lib: pass the release callback through bsg_setup_queue The SAS code will need it. Also mark the name argument const to match bsg_register_queue. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Signed-off-by: Martin K. Petersen --- include/linux/bsg-lib.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index e34dde2da0ef..1062f08e1a55 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -66,8 +66,9 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); -struct request_queue *bsg_setup_queue(struct device *dev, char *name, - bsg_job_fn *job_fn, int dd_job_size); +struct request_queue *bsg_setup_queue(struct device *dev, const char *name, + bsg_job_fn *job_fn, int dd_job_size, + void (*release)(struct device *)); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); -- cgit v1.2.3 From caf989c350e8e0b9584744b9005fc2c45ca30883 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Thu, 24 Aug 2017 12:51:30 +0530 Subject: rpmsg: glink: Introduce glink smem based transport The glink protocol supports different types of transports (shared memory). With the core protocol remaining the same, the way the transport's memory is probed and accessed is different. So add support for glink's smem based transports. Adding a new smem transport register function and the fifo accessors for the same. Acked-by: Arun Kumar Neelakantam Signed-off-by: Sricharan R Signed-off-by: Bjorn Andersson --- include/linux/rpmsg/qcom_glink.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 include/linux/rpmsg/qcom_glink.h (limited to 'include/linux') diff --git a/include/linux/rpmsg/qcom_glink.h b/include/linux/rpmsg/qcom_glink.h new file mode 100644 index 000000000000..a622f029836e --- /dev/null +++ b/include/linux/rpmsg/qcom_glink.h @@ -0,0 +1,27 @@ +#ifndef _LINUX_RPMSG_QCOM_GLINK_H +#define _LINUX_RPMSG_QCOM_GLINK_H + +#include + +struct qcom_glink; + +#if IS_ENABLED(CONFIG_RPMSG_QCOM_GLINK_SMEM) + +struct qcom_glink *qcom_glink_smem_register(struct device *parent, + struct device_node *node); +void qcom_glink_smem_unregister(struct qcom_glink *glink); + +#else + +static inline struct qcom_glink * +qcom_glink_smem_register(struct device *parent, + struct device_node *node) +{ + return NULL; +} + +static inline void qcom_glink_smem_unregister(struct qcom_glink *glink) {} + +#endif + +#endif -- cgit v1.2.3 From 603aa14d3daaa7073bab4c472025c4963030e0cc Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Wed, 21 Jun 2017 16:00:27 +0200 Subject: mmc: tmio, renesas-sdhi: add max_{segs, blk_count} to tmio_mmc_data Allow TMIO and SDHI driver implementations to provide values for max_segs and max_blk_count. A follow-up patch will set these values for Renesas Gen3 SoCs the using an SDHI driver. Signed-off-by: Yoshihiro Shimoda Signed-off-by: Ai Kyuse Signed-off-by: Simon Horman Reviewed-by: Wolfram Sang Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 26e8f8c0a6db..18b17a39d465 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -128,6 +128,8 @@ struct tmio_mmc_data { unsigned int cd_gpio; int alignment_shift; dma_addr_t dma_rx_offset; + unsigned int max_blk_count; + unsigned short max_segs; void (*set_pwr)(struct platform_device *host, int state); void (*set_clk_div)(struct platform_device *host, int state); }; -- cgit v1.2.3 From 1896f14006b28a7ed6881666d18a244827af0a5b Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Wed, 19 Jul 2017 15:50:56 +0800 Subject: mmc: core: remove check of host->removed for rescan routine The intention of this check was to prevent the conflict between hotplug and removing driver for whatever reason. Currently it doesn't improve anything and the following rescan process could still saftly perform the scan flow. So these code seems pointless now and let's remove them. Signed-off-by: Shawn Lin Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index ebd1cebbef0c..4617c21f97f7 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -328,9 +328,6 @@ struct mmc_host { unsigned int use_spi_crc:1; unsigned int claimed:1; /* host exclusively claimed */ unsigned int bus_dead:1; /* bus has been released */ -#ifdef CONFIG_MMC_DEBUG - unsigned int removed:1; /* host is being removed */ -#endif unsigned int can_retune:1; /* re-tuning can be used */ unsigned int doing_retune:1; /* re-tuning in progress */ unsigned int retune_now:1; /* do re-tuning at next req */ -- cgit v1.2.3 From 4406ae215b5a1dd59d941c1323b9f40d241357ac Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Wed, 2 Aug 2017 11:12:42 +0800 Subject: mmc: core: correct taac parameter according to the specification Per the spec of JESD84-B51, section 7.3, replace tacc with taac to fix the obvious typo. Signed-off-by: Shawn Lin Signed-off-by: Ulf Hansson --- include/linux/mmc/card.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 46c73e97e61f..279b39008a33 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -29,8 +29,8 @@ struct mmc_csd { unsigned char structure; unsigned char mmca_vsn; unsigned short cmdclass; - unsigned short tacc_clks; - unsigned int tacc_ns; + unsigned short taac_clks; + unsigned int taac_ns; unsigned int c_size; unsigned int r2w_factor; unsigned int max_dtr; -- cgit v1.2.3 From f6f64ed868d32a121f1535da9f42791c91562e4a Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Mon, 24 Jul 2017 21:58:56 +0800 Subject: clk: sunxi-ng: Add interface to query or configure MMC timing modes. Starting with the A83T SoC, Allwinner introduced a new timing mode for its MMC clocks. The new mode changes how the MMC controller sample and output clocks are delayed to match chip and board specifics. There are two controls for this, one on the CCU side controlling how the clocks behave, and one in the MMC controller controlling what inputs to take and how to route them. In the old mode, the MMC clock had 2 child clocks providing the output and sample clocks, which could be delayed by a number of clock cycles measured from the MMC clock's parent. With the new mode, the 2 delay clocks are no longer active. Instead, the delays and associated controls are moved into the MMC controller. The output of the MMC clock is also halved. The difference in how things are wired between the modes means that the clock controls and the MMC controls must match. To achieve this in a clear, explicit way, we introduce two functions for the MMC driver to use: one queries the hardware for the current mode set, and the other allows the MMC driver to request a mode. Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Ulf Hansson --- include/linux/clk/sunxi-ng.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/clk/sunxi-ng.h (limited to 'include/linux') diff --git a/include/linux/clk/sunxi-ng.h b/include/linux/clk/sunxi-ng.h new file mode 100644 index 000000000000..990f760f70e5 --- /dev/null +++ b/include/linux/clk/sunxi-ng.h @@ -0,0 +1,35 @@ +/* + * Copyright (c) 2017 Chen-Yu Tsai. All rights reserved. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _LINUX_CLK_SUNXI_NG_H_ +#define _LINUX_CLK_SUNXI_NG_H_ + +#include + +#ifdef CONFIG_SUNXI_CCU +int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, bool new_mode); +int sunxi_ccu_get_mmc_timing_mode(struct clk *clk); +#else +static inline int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, + bool new_mode) +{ + return -ENOTSUPP; +} + +static inline int sunxi_ccu_get_mmc_timing_mode(struct clk *clk) +{ + return -ENOTSUPP; +} +#endif + +#endif -- cgit v1.2.3 From 5124b59202eb3118eba5ac2222dc00f3390549a8 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 9 Aug 2017 21:00:41 +0200 Subject: mmc: renesas_sdhi: use extra flag for CBSY usage There is one SDHI instance on Gen2 which does not have the CBSY bit. So, turn CBSY usage into an extra flag and set it accordingly. This has the additional advantage that we can also set it for other incarnations later. Signed-off-by: Wolfram Sang Tested-by: Chris Brandt Reviewed-by: Simon Horman Signed-off-by: Ulf Hansson --- include/linux/mfd/tmio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h index 18b17a39d465..b572955e6de6 100644 --- a/include/linux/mfd/tmio.h +++ b/include/linux/mfd/tmio.h @@ -107,6 +107,9 @@ */ #define TMIO_MMC_CLK_ACTUAL BIT(10) +/* Some controllers have a CBSY bit */ +#define TMIO_MMC_HAVE_CBSY BIT(11) + int tmio_core_mmc_enable(void __iomem *cnf, int shift, unsigned long base); int tmio_core_mmc_resume(void __iomem *cnf, int shift, unsigned long base); void tmio_core_mmc_pwr(void __iomem *cnf, int shift, int state); -- cgit v1.2.3 From dc8d68bb6c6f7d7fb1aeb3450c0654598e4f4e52 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 10 Aug 2017 15:08:11 +0300 Subject: mmc: core: Remove unused MMC_CAP2_PACKED_CMD Packed commands support was removed but some bits got left behind. Remove them. Signed-off-by: Adrian Hunter Reviewed-by: Linus Walleij Signed-off-by: Ulf Hansson --- include/linux/mmc/host.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 4617c21f97f7..e92629518f68 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -291,10 +291,6 @@ struct mmc_host { MMC_CAP2_HS200_1_2V_SDR) #define MMC_CAP2_CD_ACTIVE_HIGH (1 << 10) /* Card-detect signal active high */ #define MMC_CAP2_RO_ACTIVE_HIGH (1 << 11) /* Write-protect signal active high */ -#define MMC_CAP2_PACKED_RD (1 << 12) /* Allow packed read */ -#define MMC_CAP2_PACKED_WR (1 << 13) /* Allow packed write */ -#define MMC_CAP2_PACKED_CMD (MMC_CAP2_PACKED_RD | \ - MMC_CAP2_PACKED_WR) #define MMC_CAP2_NO_PRESCAN_POWERUP (1 << 14) /* Don't power up before scan */ #define MMC_CAP2_HS400_1_8V (1 << 15) /* Can support HS400 1.8V */ #define MMC_CAP2_HS400_1_2V (1 << 16) /* Can support HS400 1.2V */ -- cgit v1.2.3 From d2f82254e4e862662e7820953b049b7d4d660ec7 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 10 Aug 2017 15:08:07 +0300 Subject: mmc: core: Add members to mmc_request and mmc_data for CQE's Most of the information needed to issue requests to a CQE is already in struct mmc_request and struct mmc_data. Add data block address, some flags, and the task id (tag), and allow for cmd being NULL which it is for CQE tasks. Signed-off-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index a0c63ea28796..bf1788a224e6 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -122,11 +122,18 @@ struct mmc_data { unsigned int timeout_clks; /* data timeout (in clocks) */ unsigned int blksz; /* data block size */ unsigned int blocks; /* number of blocks */ + unsigned int blk_addr; /* block address */ int error; /* data error */ unsigned int flags; -#define MMC_DATA_WRITE (1 << 8) -#define MMC_DATA_READ (1 << 9) +#define MMC_DATA_WRITE BIT(8) +#define MMC_DATA_READ BIT(9) +/* Extra flags used by CQE */ +#define MMC_DATA_QBR BIT(10) /* CQE queue barrier*/ +#define MMC_DATA_PRIO BIT(11) /* CQE high priority */ +#define MMC_DATA_REL_WR BIT(12) /* Reliable write */ +#define MMC_DATA_DAT_TAG BIT(13) /* Tag request */ +#define MMC_DATA_FORCED_PRG BIT(14) /* Forced programming */ unsigned int bytes_xfered; @@ -153,6 +160,8 @@ struct mmc_request { /* Allow other commands during this ongoing data transfer or busy wait */ bool cap_cmd_during_tfr; + + int tag; }; struct mmc_card; -- cgit v1.2.3 From c0020756315eebec58310aca42cf9fb73e1322eb Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 19 Jul 2017 21:28:52 +0300 Subject: efi: switch to use new generic UUID API There are new types and helpers that are supposed to be used in new code. As a preparation to get rid of legacy types and API functions do the conversion here. Signed-off-by: Andy Shevchenko Acked-by: Ard Biesheuvel Signed-off-by: Christoph Hellwig --- include/linux/cper.h | 94 ++++++++++++++++++++++++++-------------------------- include/linux/efi.h | 4 +-- 2 files changed, 49 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cper.h b/include/linux/cper.h index 4c671fc2081e..723e952fde0d 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -74,36 +74,36 @@ enum { * Corrected Machine Check */ #define CPER_NOTIFY_CMC \ - UUID_LE(0x2DCE8BB1, 0xBDD7, 0x450e, 0xB9, 0xAD, 0x9C, 0xF4, \ - 0xEB, 0xD4, 0xF8, 0x90) + GUID_INIT(0x2DCE8BB1, 0xBDD7, 0x450e, 0xB9, 0xAD, 0x9C, 0xF4, \ + 0xEB, 0xD4, 0xF8, 0x90) /* Corrected Platform Error */ #define CPER_NOTIFY_CPE \ - UUID_LE(0x4E292F96, 0xD843, 0x4a55, 0xA8, 0xC2, 0xD4, 0x81, \ - 0xF2, 0x7E, 0xBE, 0xEE) + GUID_INIT(0x4E292F96, 0xD843, 0x4a55, 0xA8, 0xC2, 0xD4, 0x81, \ + 0xF2, 0x7E, 0xBE, 0xEE) /* Machine Check Exception */ #define CPER_NOTIFY_MCE \ - UUID_LE(0xE8F56FFE, 0x919C, 0x4cc5, 0xBA, 0x88, 0x65, 0xAB, \ - 0xE1, 0x49, 0x13, 0xBB) + GUID_INIT(0xE8F56FFE, 0x919C, 0x4cc5, 0xBA, 0x88, 0x65, 0xAB, \ + 0xE1, 0x49, 0x13, 0xBB) /* PCI Express Error */ #define CPER_NOTIFY_PCIE \ - UUID_LE(0xCF93C01F, 0x1A16, 0x4dfc, 0xB8, 0xBC, 0x9C, 0x4D, \ - 0xAF, 0x67, 0xC1, 0x04) + GUID_INIT(0xCF93C01F, 0x1A16, 0x4dfc, 0xB8, 0xBC, 0x9C, 0x4D, \ + 0xAF, 0x67, 0xC1, 0x04) /* INIT Record (for IPF) */ #define CPER_NOTIFY_INIT \ - UUID_LE(0xCC5263E8, 0x9308, 0x454a, 0x89, 0xD0, 0x34, 0x0B, \ - 0xD3, 0x9B, 0xC9, 0x8E) + GUID_INIT(0xCC5263E8, 0x9308, 0x454a, 0x89, 0xD0, 0x34, 0x0B, \ + 0xD3, 0x9B, 0xC9, 0x8E) /* Non-Maskable Interrupt */ #define CPER_NOTIFY_NMI \ - UUID_LE(0x5BAD89FF, 0xB7E6, 0x42c9, 0x81, 0x4A, 0xCF, 0x24, \ - 0x85, 0xD6, 0xE9, 0x8A) + GUID_INIT(0x5BAD89FF, 0xB7E6, 0x42c9, 0x81, 0x4A, 0xCF, 0x24, \ + 0x85, 0xD6, 0xE9, 0x8A) /* BOOT Error Record */ #define CPER_NOTIFY_BOOT \ - UUID_LE(0x3D61A466, 0xAB40, 0x409a, 0xA6, 0x98, 0xF3, 0x62, \ - 0xD4, 0x64, 0xB3, 0x8F) + GUID_INIT(0x3D61A466, 0xAB40, 0x409a, 0xA6, 0x98, 0xF3, 0x62, \ + 0xD4, 0x64, 0xB3, 0x8F) /* DMA Remapping Error */ #define CPER_NOTIFY_DMAR \ - UUID_LE(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \ - 0x72, 0x2D, 0xEB, 0x41) + GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E, \ + 0x72, 0x2D, 0xEB, 0x41) /* * Flags bits definitions for flags in struct cper_record_header @@ -170,50 +170,50 @@ enum { * Processor Generic */ #define CPER_SEC_PROC_GENERIC \ - UUID_LE(0x9876CCAD, 0x47B4, 0x4bdb, 0xB6, 0x5E, 0x16, 0xF1, \ - 0x93, 0xC4, 0xF3, 0xDB) + GUID_INIT(0x9876CCAD, 0x47B4, 0x4bdb, 0xB6, 0x5E, 0x16, 0xF1, \ + 0x93, 0xC4, 0xF3, 0xDB) /* Processor Specific: X86/X86_64 */ #define CPER_SEC_PROC_IA \ - UUID_LE(0xDC3EA0B0, 0xA144, 0x4797, 0xB9, 0x5B, 0x53, 0xFA, \ - 0x24, 0x2B, 0x6E, 0x1D) + GUID_INIT(0xDC3EA0B0, 0xA144, 0x4797, 0xB9, 0x5B, 0x53, 0xFA, \ + 0x24, 0x2B, 0x6E, 0x1D) /* Processor Specific: IA64 */ #define CPER_SEC_PROC_IPF \ - UUID_LE(0xE429FAF1, 0x3CB7, 0x11D4, 0x0B, 0xCA, 0x07, 0x00, \ - 0x80, 0xC7, 0x3C, 0x88, 0x81) + GUID_INIT(0xE429FAF1, 0x3CB7, 0x11D4, 0x0B, 0xCA, 0x07, 0x00, \ + 0x80, 0xC7, 0x3C, 0x88, 0x81) /* Processor Specific: ARM */ #define CPER_SEC_PROC_ARM \ - UUID_LE(0xE19E3D16, 0xBC11, 0x11E4, 0x9C, 0xAA, 0xC2, 0x05, \ - 0x1D, 0x5D, 0x46, 0xB0) + GUID_INIT(0xE19E3D16, 0xBC11, 0x11E4, 0x9C, 0xAA, 0xC2, 0x05, \ + 0x1D, 0x5D, 0x46, 0xB0) /* Platform Memory */ #define CPER_SEC_PLATFORM_MEM \ - UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ - 0xED, 0x7C, 0x83, 0xB1) + GUID_INIT(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ + 0xED, 0x7C, 0x83, 0xB1) #define CPER_SEC_PCIE \ - UUID_LE(0xD995E954, 0xBBC1, 0x430F, 0xAD, 0x91, 0xB4, 0x4D, \ - 0xCB, 0x3C, 0x6F, 0x35) + GUID_INIT(0xD995E954, 0xBBC1, 0x430F, 0xAD, 0x91, 0xB4, 0x4D, \ + 0xCB, 0x3C, 0x6F, 0x35) /* Firmware Error Record Reference */ #define CPER_SEC_FW_ERR_REC_REF \ - UUID_LE(0x81212A96, 0x09ED, 0x4996, 0x94, 0x71, 0x8D, 0x72, \ - 0x9C, 0x8E, 0x69, 0xED) + GUID_INIT(0x81212A96, 0x09ED, 0x4996, 0x94, 0x71, 0x8D, 0x72, \ + 0x9C, 0x8E, 0x69, 0xED) /* PCI/PCI-X Bus */ #define CPER_SEC_PCI_X_BUS \ - UUID_LE(0xC5753963, 0x3B84, 0x4095, 0xBF, 0x78, 0xED, 0xDA, \ - 0xD3, 0xF9, 0xC9, 0xDD) + GUID_INIT(0xC5753963, 0x3B84, 0x4095, 0xBF, 0x78, 0xED, 0xDA, \ + 0xD3, 0xF9, 0xC9, 0xDD) /* PCI Component/Device */ #define CPER_SEC_PCI_DEV \ - UUID_LE(0xEB5E4685, 0xCA66, 0x4769, 0xB6, 0xA2, 0x26, 0x06, \ - 0x8B, 0x00, 0x13, 0x26) + GUID_INIT(0xEB5E4685, 0xCA66, 0x4769, 0xB6, 0xA2, 0x26, 0x06, \ + 0x8B, 0x00, 0x13, 0x26) #define CPER_SEC_DMAR_GENERIC \ - UUID_LE(0x5B51FEF7, 0xC79D, 0x4434, 0x8F, 0x1B, 0xAA, 0x62, \ - 0xDE, 0x3E, 0x2C, 0x64) + GUID_INIT(0x5B51FEF7, 0xC79D, 0x4434, 0x8F, 0x1B, 0xAA, 0x62, \ + 0xDE, 0x3E, 0x2C, 0x64) /* Intel VT for Directed I/O specific DMAr */ #define CPER_SEC_DMAR_VT \ - UUID_LE(0x71761D37, 0x32B2, 0x45cd, 0xA7, 0xD0, 0xB0, 0xFE, \ - 0xDD, 0x93, 0xE8, 0xCF) + GUID_INIT(0x71761D37, 0x32B2, 0x45cd, 0xA7, 0xD0, 0xB0, 0xFE, \ + 0xDD, 0x93, 0xE8, 0xCF) /* IOMMU specific DMAr */ #define CPER_SEC_DMAR_IOMMU \ - UUID_LE(0x036F84E1, 0x7F37, 0x428c, 0xA7, 0x9E, 0x57, 0x5F, \ - 0xDF, 0xAA, 0x84, 0xEC) + GUID_INIT(0x036F84E1, 0x7F37, 0x428c, 0xA7, 0x9E, 0x57, 0x5F, \ + 0xDF, 0xAA, 0x84, 0xEC) #define CPER_PROC_VALID_TYPE 0x0001 #define CPER_PROC_VALID_ISA 0x0002 @@ -290,10 +290,10 @@ struct cper_record_header { __u32 validation_bits; __u32 record_length; __u64 timestamp; - uuid_le platform_id; - uuid_le partition_id; - uuid_le creator_id; - uuid_le notification_type; + guid_t platform_id; + guid_t partition_id; + guid_t creator_id; + guid_t notification_type; __u64 record_id; __u32 flags; __u64 persistence_information; @@ -309,8 +309,8 @@ struct cper_section_descriptor { __u8 validation_bits; __u8 reserved; /* must be zero */ __u32 flags; - uuid_le section_type; - uuid_le fru_id; + guid_t section_type; + guid_t fru_id; __u32 section_severity; __u8 fru_text[20]; }; @@ -343,7 +343,7 @@ struct cper_sec_proc_ia { /* IA32/X64 Processor Error Information Structure */ struct cper_ia_err_info { - uuid_le err_type; + guid_t err_type; __u64 validation_bits; __u64 check_info; __u64 target_id; diff --git a/include/linux/efi.h b/include/linux/efi.h index 8269bcb8ccf7..7a322aed979f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -47,10 +47,10 @@ typedef u16 efi_char16_t; /* UNICODE character */ typedef u64 efi_physical_addr_t; typedef void *efi_handle_t; -typedef uuid_le efi_guid_t; +typedef guid_t efi_guid_t; #define EFI_GUID(a,b,c,d0,d1,d2,d3,d4,d5,d6,d7) \ - UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) + GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) /* * Generic EFI table header -- cgit v1.2.3 From 223694b9ae8bfba99f3528d49d07a740af6ff95a Mon Sep 17 00:00:00 2001 From: Changpeng Liu Date: Thu, 31 Aug 2017 11:22:49 +0800 Subject: nvme: fix the definition of the doorbell buffer config support bit NVMe 1.3 specification defines the Optional Admin Command Support feature flags, bit 8 set to '1' then the controller supports the Doorbell Buffer Config command. Bit 7 is used for Virtualization Mangement command. Signed-off-by: Changpeng Liu Reviewed-by: Sagi Grimberg Reviewed-by: Max Gurtovoy Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Fixes: f9f38e33 ("nvme: improve performance for virtual NVMe devices") Cc: stable@vger.kernel.org --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 25d8225dbd04..8efff888bd9b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -254,7 +254,7 @@ enum { NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, NVME_CTRL_OACS_DIRECTIVES = 1 << 5, - NVME_CTRL_OACS_DBBUF_SUPP = 1 << 7, + NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, }; struct nvme_lbaf { -- cgit v1.2.3 From d3bf68ae04c7e29ed3c30b7f4b1f0c6a4a11c7f1 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 25 Aug 2017 15:43:46 +0300 Subject: mmc: host: Add CQE interface Add CQE host operations, capabilities, and host members. Signed-off-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 6 ++++++ include/linux/mmc/host.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index bf1788a224e6..c6d17f626234 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -156,6 +156,12 @@ struct mmc_request { struct completion completion; struct completion cmd_completion; void (*done)(struct mmc_request *);/* completion function */ + /* + * Notify uppers layers (e.g. mmc block driver) that recovery is needed + * due to an error associated with the mmc_request. Currently used only + * by CQE. + */ + void (*recovery_notifier)(struct mmc_request *); struct mmc_host *host; /* Allow other commands during this ongoing data transfer or busy wait */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index e92629518f68..f3f2d07feb2a 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -162,6 +162,50 @@ struct mmc_host_ops { unsigned int direction, int blk_size); }; +struct mmc_cqe_ops { + /* Allocate resources, and make the CQE operational */ + int (*cqe_enable)(struct mmc_host *host, struct mmc_card *card); + /* Free resources, and make the CQE non-operational */ + void (*cqe_disable)(struct mmc_host *host); + /* + * Issue a read, write or DCMD request to the CQE. Also deal with the + * effect of ->cqe_off(). + */ + int (*cqe_request)(struct mmc_host *host, struct mmc_request *mrq); + /* Free resources (e.g. DMA mapping) associated with the request */ + void (*cqe_post_req)(struct mmc_host *host, struct mmc_request *mrq); + /* + * Prepare the CQE and host controller to accept non-CQ commands. There + * is no corresponding ->cqe_on(), instead ->cqe_request() is required + * to deal with that. + */ + void (*cqe_off)(struct mmc_host *host); + /* + * Wait for all CQE tasks to complete. Return an error if recovery + * becomes necessary. + */ + int (*cqe_wait_for_idle)(struct mmc_host *host); + /* + * Notify CQE that a request has timed out. Return false if the request + * completed or true if a timeout happened in which case indicate if + * recovery is needed. + */ + bool (*cqe_timeout)(struct mmc_host *host, struct mmc_request *mrq, + bool *recovery_needed); + /* + * Stop all CQE activity and prepare the CQE and host controller to + * accept recovery commands. + */ + void (*cqe_recovery_start)(struct mmc_host *host); + /* + * Clear the queue and call mmc_cqe_request_done() on all requests. + * Requests that errored will have the error set on the mmc_request + * (data->error or cmd->error for DCMD). Requests that did not error + * will have zero data bytes transferred. + */ + void (*cqe_recovery_finish)(struct mmc_host *host); +}; + struct mmc_async_req { /* active mmc request */ struct mmc_request *mrq; @@ -303,6 +347,8 @@ struct mmc_host { #define MMC_CAP2_HS400_ES (1 << 20) /* Host supports enhanced strobe */ #define MMC_CAP2_NO_SD (1 << 21) /* Do not send SD commands during initialization */ #define MMC_CAP2_NO_MMC (1 << 22) /* Do not send (e)MMC commands during initialization */ +#define MMC_CAP2_CQE (1 << 23) /* Has eMMC command queue engine */ +#define MMC_CAP2_CQE_DCMD (1 << 24) /* CQE can issue a direct command */ mmc_pm_flag_t pm_caps; /* supported pm features */ @@ -386,6 +432,13 @@ struct mmc_host { int dsr_req; /* DSR value is valid */ u32 dsr; /* optional driver stage (DSR) value */ + /* Command Queue Engine (CQE) support */ + const struct mmc_cqe_ops *cqe_ops; + void *cqe_private; + int cqe_qdepth; + bool cqe_enabled; + bool cqe_on; + unsigned long private[0] ____cacheline_aligned; }; -- cgit v1.2.3 From 906d5ff6188953f4981df39e9999f858542df9ce Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 25 Aug 2017 15:43:44 +0300 Subject: mmc: core: Move mmc_start_areq() declaration mmc_start_areq() is an internal mmc core API. Move the declaration accordingly. Signed-off-by: Adrian Hunter Signed-off-by: Ulf Hansson --- include/linux/mmc/core.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index c6d17f626234..927519385482 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -171,11 +171,7 @@ struct mmc_request { }; struct mmc_card; -struct mmc_async_req; -struct mmc_async_req *mmc_start_areq(struct mmc_host *host, - struct mmc_async_req *areq, - enum mmc_blk_status *ret_stat); void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); -- cgit v1.2.3 From 66b6bef2c4e06f8c7a0030445766bf868110c5a1 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 30 Aug 2017 11:48:11 +0200 Subject: power: supply: bq24190_charger: Export 5V boost converter as regulator Register the 5V boost converter as a regulator named "usb_otg_vbus". This commit also adds support for bq24190_platform_data, through which non device-tree platforms can pass the regulator_init_data (containing mappings for the consumer amongst other things). Signed-off-by: Hans de Goede Acked-by: Tony Lindgren Signed-off-by: Sebastian Reichel --- include/linux/power/bq24190_charger.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 include/linux/power/bq24190_charger.h (limited to 'include/linux') diff --git a/include/linux/power/bq24190_charger.h b/include/linux/power/bq24190_charger.h new file mode 100644 index 000000000000..45ce7f116a91 --- /dev/null +++ b/include/linux/power/bq24190_charger.h @@ -0,0 +1,18 @@ +/* + * Platform data for the TI bq24190 battery charger driver. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _BQ24190_CHARGER_H_ +#define _BQ24190_CHARGER_H_ + +#include + +struct bq24190_platform_data { + const struct regulator_init_data *regulator_init_data; +}; + +#endif -- cgit v1.2.3 From add02cfdc9bc2987b0121861d5bb0c7392865be9 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 23 Aug 2017 15:50:04 +0200 Subject: iommu: Introduce Interface for IOMMU TLB Flushing With the current IOMMU-API the hardware TLBs have to be flushed in every iommu_ops->unmap() call-back. For unmapping large amounts of address space, like it happens when a KVM domain with assigned devices is destroyed, this causes thousands of unnecessary TLB flushes in the IOMMU hardware because the unmap call-back runs for every unmapped physical page. With the TLB Flush Interface and the new iommu_unmap_fast() function introduced here the need to clean the hardware TLBs is removed from the unmapping code-path. Users of iommu_unmap_fast() have to explicitly call the TLB-Flush functions to sync the page-table changes to the hardware. Three functions for TLB-Flushes are introduced: * iommu_flush_tlb_all() - Flushes all TLB entries associated with that domain. TLBs entries are flushed when this function returns. * iommu_tlb_range_add() - This will add a given range to the flush queue for this domain. * iommu_tlb_sync() - Flushes all queued ranges from the hardware TLBs. Returns when the flush is finished. The semantic of this interface is intentionally similar to the iommu_gather_ops from the io-pgtable code. Cc: Alex Williamson Cc: Will Deacon Cc: Robin Murphy Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 49 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index f1ce8e517d8d..50be4fd338e4 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -167,6 +167,10 @@ struct iommu_resv_region { * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain * @map_sg: map a scatter-gather list of physically contiguous memory chunks + * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain + * @tlb_range_add: Add a given iova range to the flush queue for this domain + * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush + * queue * to an iommu domain * @iova_to_phys: translate iova to physical address * @add_device: add device to iommu grouping @@ -199,6 +203,10 @@ struct iommu_ops { size_t size); size_t (*map_sg)(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot); + void (*flush_iotlb_all)(struct iommu_domain *domain); + void (*iotlb_range_add)(struct iommu_domain *domain, + unsigned long iova, size_t size); + void (*iotlb_sync)(struct iommu_domain *domain); phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova); int (*add_device)(struct device *dev); void (*remove_device)(struct device *dev); @@ -286,7 +294,9 @@ extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot); extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size); + size_t size); +extern size_t iommu_unmap_fast(struct iommu_domain *domain, + unsigned long iova, size_t size); extern size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg,unsigned int nents, int prot); @@ -343,6 +353,25 @@ extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr) extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags); +static inline void iommu_flush_tlb_all(struct iommu_domain *domain) +{ + if (domain->ops->flush_iotlb_all) + domain->ops->flush_iotlb_all(domain); +} + +static inline void iommu_tlb_range_add(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + if (domain->ops->iotlb_range_add) + domain->ops->iotlb_range_add(domain, iova, size); +} + +static inline void iommu_tlb_sync(struct iommu_domain *domain) +{ + if (domain->ops->iotlb_sync) + domain->ops->iotlb_sync(domain); +} + static inline size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) @@ -436,6 +465,12 @@ static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova, return -ENODEV; } +static inline int iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, + int gfp_order) +{ + return -ENODEV; +} + static inline size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) @@ -443,6 +478,19 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain, return -ENODEV; } +static inline void iommu_flush_tlb_all(struct iommu_domain *domain) +{ +} + +static inline void iommu_tlb_range_add(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ +} + +static inline void iommu_tlb_sync(struct iommu_domain *domain) +{ +} + static inline int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) -- cgit v1.2.3 From 78f35473508118df5ea04b9515ac3f1aaec0a980 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 30 Aug 2017 09:16:38 -0700 Subject: dax: introduce a fs_dax_get_by_bdev() helper Add a helper that can replace the following common pattern: if (blk_queue_dax(bdev->bd_queue)) fs_dax_get_by_host(bdev->bd_disk->disk_name); This will be used to move dax_device lookup from iomap-operation time to fs-mount time. Reviewed-by: Jan Kara Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Dan Williams --- include/linux/dax.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index df97b7af7e2c..ac8afa18f707 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -57,6 +57,7 @@ static inline void fs_put_dax(struct dax_device *dax_dev) put_dax(dax_dev); } +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); #else static inline int bdev_dax_supported(struct super_block *sb, int blocksize) { @@ -71,6 +72,11 @@ static inline struct dax_device *fs_dax_get_by_host(const char *host) static inline void fs_put_dax(struct dax_device *dax_dev) { } + +static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) +{ + return NULL; +} #endif int dax_read_lock(void); -- cgit v1.2.3 From 31770e34e43d6c8dee129bfee77e56c34e61f0e5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 30 Aug 2017 19:24:58 +0200 Subject: tcp: Revert "tcp: remove header prediction" This reverts commit 45f119bf936b1f9f546a0b139c5b56f9bb2bdc78. Eric Dumazet says: We found at Google a significant regression caused by 45f119bf936b1f9f546a0b139c5b56f9bb2bdc78 tcp: remove header prediction In typical RPC (TCP_RR), when a TCP socket receives data, we now call tcp_ack() while we used to not call it. This touches enough cache lines to cause a slowdown. so problem does not seem to be HP removal itself but the tcp_ack() call. Therefore, it might be possible to remove HP after all, provided one finds a way to elide tcp_ack for most cases. Reported-by: Eric Dumazet Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 267164a1d559..4aa40ef02d32 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -147,6 +147,12 @@ struct tcp_sock { u16 tcp_header_len; /* Bytes of tcp header to send */ u16 gso_segs; /* Max number of segs per GSO packet */ +/* + * Header prediction flags + * 0x5?10 << 16 + snd_wnd in net byte order + */ + __be32 pred_flags; + /* * RFC793 variables by their proper names. This means you can * read the code and the spec side by side (and laugh ...) -- cgit v1.2.3 From b3cb5388499c5e219324bfe7da2e46cbad82bfcf Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Tue, 8 Aug 2017 13:17:00 -0500 Subject: net/mlx5: Skip mlx5_unload_one if mlx5_load_one fails There is an issue where the firmware fails during mlx5_load_one, the health_care timer detects the issue and schedules a health_care call. Then the mlx5_load_one detects the issue, cleans up and quits. Then the health_care starts and calls mlx5_unload_one to clean up the resources that no longer exist and causes kernel panic. The root cause is that the bit MLX5_INTERFACE_STATE_DOWN is not set after mlx5_load_one fails. The solution is removing the bit MLX5_INTERFACE_STATE_DOWN and quit mlx5_unload_one if the bit MLX5_INTERFACE_STATE_UP is not set. The bit MLX5_INTERFACE_STATE_DOWN is redundant and we can use MLX5_INTERFACE_STATE_UP instead. Fixes: 5fc7197d3a25 ("net/mlx5: Add pci shutdown callback") Signed-off-by: Huy Nguyen Reviewed-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index df6ce59a1f95..918f5e644506 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -673,9 +673,8 @@ enum mlx5_device_state { }; enum mlx5_interface_state { - MLX5_INTERFACE_STATE_DOWN = BIT(0), - MLX5_INTERFACE_STATE_UP = BIT(1), - MLX5_INTERFACE_STATE_SHUTDOWN = BIT(2), + MLX5_INTERFACE_STATE_UP = BIT(0), + MLX5_INTERFACE_STATE_SHUTDOWN = BIT(1), }; enum mlx5_pci_status { -- cgit v1.2.3 From 10a8d00707082955b177164d4b4e758ffcbd4017 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Wed, 9 Aug 2017 10:03:40 -0500 Subject: net/mlx5: Remove the flag MLX5_INTERFACE_STATE_SHUTDOWN MLX5_INTERFACE_STATE_SHUTDOWN is not used in the code. Fixes: 5fc7197d3a25 ("net/mlx5: Add pci shutdown callback") Signed-off-by: Huy Nguyen Reviewed-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 918f5e644506..205d82d4c468 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -674,7 +674,6 @@ enum mlx5_device_state { enum mlx5_interface_state { MLX5_INTERFACE_STATE_UP = BIT(0), - MLX5_INTERFACE_STATE_SHUTDOWN = BIT(1), }; enum mlx5_pci_status { -- cgit v1.2.3 From 388f79fda74fd3d8700ed5d899573ec58c2e0253 Mon Sep 17 00:00:00 2001 From: Chris Mi Date: Wed, 30 Aug 2017 02:31:57 -0400 Subject: idr: Add new APIs to support unsigned long The following new APIs are added: int idr_alloc_ext(struct idr *idr, void *ptr, unsigned long *index, unsigned long start, unsigned long end, gfp_t gfp); void *idr_remove_ext(struct idr *idr, unsigned long id); void *idr_find_ext(const struct idr *idr, unsigned long id); void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id); void *idr_get_next_ext(struct idr *idr, unsigned long *nextid); Signed-off-by: Chris Mi Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/idr.h | 69 ++++++++++++++++++++++++++++++++++++++++++++-- include/linux/radix-tree.h | 21 ++++++++++++-- 2 files changed, 85 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/idr.h b/include/linux/idr.h index bf70b3ef0a07..7c3a365f7e12 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -80,19 +80,75 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val) */ void idr_preload(gfp_t gfp_mask); -int idr_alloc(struct idr *, void *entry, int start, int end, gfp_t); + +int idr_alloc_cmn(struct idr *idr, void *ptr, unsigned long *index, + unsigned long start, unsigned long end, gfp_t gfp, + bool ext); + +/** + * idr_alloc - allocate an id + * @idr: idr handle + * @ptr: pointer to be associated with the new id + * @start: the minimum id (inclusive) + * @end: the maximum id (exclusive) + * @gfp: memory allocation flags + * + * Allocates an unused ID in the range [start, end). Returns -ENOSPC + * if there are no unused IDs in that range. + * + * Note that @end is treated as max when <= 0. This is to always allow + * using @start + N as @end as long as N is inside integer range. + * + * Simultaneous modifications to the @idr are not allowed and should be + * prevented by the user, usually with a lock. idr_alloc() may be called + * concurrently with read-only accesses to the @idr, such as idr_find() and + * idr_for_each_entry(). + */ +static inline int idr_alloc(struct idr *idr, void *ptr, + int start, int end, gfp_t gfp) +{ + unsigned long id; + int ret; + + if (WARN_ON_ONCE(start < 0)) + return -EINVAL; + + ret = idr_alloc_cmn(idr, ptr, &id, start, end, gfp, false); + + if (ret) + return ret; + + return id; +} + +static inline int idr_alloc_ext(struct idr *idr, void *ptr, + unsigned long *index, + unsigned long start, + unsigned long end, + gfp_t gfp) +{ + return idr_alloc_cmn(idr, ptr, index, start, end, gfp, true); +} + int idr_alloc_cyclic(struct idr *, void *entry, int start, int end, gfp_t); int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *, int *nextid); +void *idr_get_next_ext(struct idr *idr, unsigned long *nextid); void *idr_replace(struct idr *, void *, int id); +void *idr_replace_ext(struct idr *idr, void *ptr, unsigned long id); void idr_destroy(struct idr *); -static inline void *idr_remove(struct idr *idr, int id) +static inline void *idr_remove_ext(struct idr *idr, unsigned long id) { return radix_tree_delete_item(&idr->idr_rt, id, NULL); } +static inline void *idr_remove(struct idr *idr, int id) +{ + return idr_remove_ext(idr, id); +} + static inline void idr_init(struct idr *idr) { INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); @@ -128,11 +184,16 @@ static inline void idr_preload_end(void) * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. */ -static inline void *idr_find(const struct idr *idr, int id) +static inline void *idr_find_ext(const struct idr *idr, unsigned long id) { return radix_tree_lookup(&idr->idr_rt, id); } +static inline void *idr_find(const struct idr *idr, int id) +{ + return idr_find_ext(idr, id); +} + /** * idr_for_each_entry - iterate over an idr's elements of a given type * @idr: idr handle @@ -145,6 +206,8 @@ static inline void *idr_find(const struct idr *idr, int id) */ #define idr_for_each_entry(idr, entry, id) \ for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) +#define idr_for_each_entry_ext(idr, entry, id) \ + for (id = 0; ((entry) = idr_get_next_ext(idr, &(id))) != NULL; ++id) /** * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 3e5735064b71..567ebb5eaab0 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -357,8 +357,25 @@ int radix_tree_split(struct radix_tree_root *, unsigned long index, unsigned new_order); int radix_tree_join(struct radix_tree_root *, unsigned long index, unsigned new_order, void *); -void __rcu **idr_get_free(struct radix_tree_root *, struct radix_tree_iter *, - gfp_t, int end); + +void __rcu **idr_get_free_cmn(struct radix_tree_root *root, + struct radix_tree_iter *iter, gfp_t gfp, + unsigned long max); +static inline void __rcu **idr_get_free(struct radix_tree_root *root, + struct radix_tree_iter *iter, + gfp_t gfp, + int end) +{ + return idr_get_free_cmn(root, iter, gfp, end > 0 ? end - 1 : INT_MAX); +} + +static inline void __rcu **idr_get_free_ext(struct radix_tree_root *root, + struct radix_tree_iter *iter, + gfp_t gfp, + unsigned long end) +{ + return idr_get_free_cmn(root, iter, gfp, end - 1); +} enum { RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ -- cgit v1.2.3 From 5c23f2dc8eeb5a6010cb66119d942361bc8ec833 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Wed, 30 Aug 2017 10:29:12 +0200 Subject: phy: add sgmii and 10gkr modes to the phy_mode enum This patch adds more generic PHY modes to the phy_mode enum, to allow configuring generic PHYs to the SGMII and/or the 10GKR mode by using the set_mode callback. Signed-off-by: Antoine Tenart Acked-by: Kishon Vijay Abraham I Signed-off-by: David S. Miller --- include/linux/phy/phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 78bb0d7f6b11..e694d4008c4a 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -27,6 +27,8 @@ enum phy_mode { PHY_MODE_USB_HOST, PHY_MODE_USB_DEVICE, PHY_MODE_USB_OTG, + PHY_MODE_SGMII, + PHY_MODE_10GKR, }; /** -- cgit v1.2.3 From 2729984149e6a23e849a40e16fc3efdc07dd3668 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 13 Aug 2017 13:34:42 +0300 Subject: net/mlx5e: Support TSO and TX checksum offloads for GRE tunnels Add TX offloads support for GRE tunneled packets by reporting the needed netdev features. Signed-off-by: Gal Pressman Reviewed-by: Or Gerlitz Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ae7d09b9c52f..3d5d32e5446c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -602,7 +602,7 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 reserved_at_1a[0x1]; u8 tunnel_lso_const_out_ip_id[0x1]; u8 reserved_at_1c[0x2]; - u8 tunnel_statless_gre[0x1]; + u8 tunnel_stateless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; u8 swp[0x1]; -- cgit v1.2.3 From 6606bc9dee63ad8cda2cc310d2ad5992673a785a Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Thu, 17 Aug 2017 14:50:36 +0800 Subject: pinctrl: Add sleep related state to indicate sleep related configs In some scenarios, we should set some pins as input/output/pullup/pulldown when the specified system goes into deep sleep mode, then when the system goes into deep sleep mode, these pins will be set automatically by hardware. That means some pins are not controlled by any specific driver in the OS, but need to be controlled when entering sleep mode. Thus we introduce one sleep state config into pinconf-generic for users to configure. Signed-off-by: Baolin Wang Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinconf-generic.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index e91d1b6a260d..5d8bc7f21c2a 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -86,6 +86,7 @@ * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells * the driver which alternative power source to use. + * @PIN_CONFIG_SLEEP_HARDWARE_STATE: indicate this is sleep related state. * @PIN_CONFIG_SLEW_RATE: if the pin can select slew rate, the argument to * this parameter (on a custom format) tells the driver which alternative * slew rate to use. @@ -114,6 +115,7 @@ enum pin_config_param { PIN_CONFIG_OUTPUT_ENABLE, PIN_CONFIG_OUTPUT, PIN_CONFIG_POWER_SOURCE, + PIN_CONFIG_SLEEP_HARDWARE_STATE, PIN_CONFIG_SLEW_RATE, PIN_CONFIG_END = 0x7F, PIN_CONFIG_MAX = 0xFF, -- cgit v1.2.3 From de29faa0d8ac925534749bc56d539bf936ce122b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 19 Dec 2016 19:25:00 +0000 Subject: irqchip/gic-v4: Add management structure definitions Add a bunch of GICv4-specific data structures that will get used in subsequent patches. Reviewed-by: Thomas Gleixner Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v4.h | 92 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 92 insertions(+) create mode 100644 include/linux/irqchip/arm-gic-v4.h (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h new file mode 100644 index 000000000000..d499538dd86f --- /dev/null +++ b/include/linux/irqchip/arm-gic-v4.h @@ -0,0 +1,92 @@ +/* + * Copyright (C) 2016,2017 ARM Limited, All Rights Reserved. + * Author: Marc Zyngier + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __LINUX_IRQCHIP_ARM_GIC_V4_H +#define __LINUX_IRQCHIP_ARM_GIC_V4_H + +struct its_vpe; + +/* Embedded in kvm.arch */ +struct its_vm { + struct fwnode_handle *fwnode; + struct irq_domain *domain; + struct page *vprop_page; + struct its_vpe **vpes; + int nr_vpes; + irq_hw_number_t db_lpi_base; + unsigned long *db_bitmap; + int nr_db_lpis; +}; + +/* Embedded in kvm_vcpu.arch */ +struct its_vpe { + struct page *vpt_page; + struct its_vm *its_vm; + /* Doorbell interrupt */ + int irq; + irq_hw_number_t vpe_db_lpi; + /* + * This collection ID is used to indirect the target + * redistributor for this VPE. The ID itself isn't involved in + * programming of the ITS. + */ + u16 col_idx; + /* Unique (system-wide) VPE identifier */ + u16 vpe_id; + /* Implementation Defined Area Invalid */ + bool idai; + /* Pending VLPIs on schedule out? */ + bool pending_last; +}; + +/* + * struct its_vlpi_map: structure describing the mapping of a + * VLPI. Only to be interpreted in the context of a physical interrupt + * it complements. To be used as the vcpu_info passed to + * irq_set_vcpu_affinity(). + * + * @vm: Pointer to the GICv4 notion of a VM + * @vpe: Pointer to the GICv4 notion of a virtual CPU (VPE) + * @vintid: Virtual LPI number + * @db_enabled: Is the VPE doorbell to be generated? + */ +struct its_vlpi_map { + struct its_vm *vm; + struct its_vpe *vpe; + u32 vintid; + bool db_enabled; +}; + +enum its_vcpu_info_cmd_type { + MAP_VLPI, + GET_VLPI, + PROP_UPDATE_VLPI, + PROP_UPDATE_AND_INV_VLPI, + SCHEDULE_VPE, + DESCHEDULE_VPE, + INVALL_VPE, +}; + +struct its_cmd_info { + enum its_vcpu_info_cmd_type cmd_type; + union { + struct its_vlpi_map *map; + u8 config; + }; +}; + +#endif -- cgit v1.2.3 From d7276b80e752acaaf30f04e62d0e986b5bced2df Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 20 Dec 2016 15:11:47 +0000 Subject: irqchip/gic-v3-its: Add GICv4 ITS command definitions Add the new GICv4 ITS command definitions, most of them, being defined in terms of their physical counterparts. Reviewed-by: Eric Auger Reviewed-by: Thomas Gleixner Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index af8c55105fc2..7c6fd8f3e36c 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -347,6 +347,18 @@ #define GITS_CMD_CLEAR 0x04 #define GITS_CMD_SYNC 0x05 +/* + * GICv4 ITS specific commands + */ +#define GITS_CMD_GICv4(x) ((x) | 0x20) +#define GITS_CMD_VINVALL GITS_CMD_GICv4(GITS_CMD_INVALL) +#define GITS_CMD_VMAPP GITS_CMD_GICv4(GITS_CMD_MAPC) +#define GITS_CMD_VMAPTI GITS_CMD_GICv4(GITS_CMD_MAPTI) +#define GITS_CMD_VMOVI GITS_CMD_GICv4(GITS_CMD_MOVI) +#define GITS_CMD_VSYNC GITS_CMD_GICv4(GITS_CMD_SYNC) +/* VMOVP is the odd one, as it doesn't have a physical counterpart */ +#define GITS_CMD_VMOVP GITS_CMD_GICv4(2) + /* * ITS error numbers */ -- cgit v1.2.3 From 3ca63f363f3f8fe457482c53d5c86d83bff21e64 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 3 Jan 2017 13:39:52 +0000 Subject: irqchip/gic-v3-its: Add VPENDBASER/VPROPBASER accessors V{PEND,PROP}BASER being 64bit registers, they need some ad-hoc accessors on 32bit, specially given that VPENDBASER contains a Valid bit, making the access a bit convoluted. Reviewed-by: Thomas Gleixner Reviewed-by: Eric Auger Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 7c6fd8f3e36c..17ba0d732f12 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -212,6 +212,11 @@ #define LPI_PROP_GROUP1 (1 << 1) #define LPI_PROP_ENABLED (1 << 0) +#define GICR_VPENDBASER_Dirty (1ULL << 60) +#define GICR_VPENDBASER_PendingLast (1ULL << 61) +#define GICR_VPENDBASER_IDAI (1ULL << 62) +#define GICR_VPENDBASER_Valid (1ULL << 63) + /* * ITS registers, offsets from ITS_base */ -- cgit v1.2.3 From e643d80340363c9d172abfbe437537196cfc1643 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 20 Dec 2016 15:09:31 +0000 Subject: irqchip/gic-v3-its: Add VPE scheduling When a VPE is scheduled to run, the corresponding redistributor must be told so, by setting VPROPBASER to the VM's property table, and VPENDBASER to the vcpu's pending table. When scheduled out, we preserve the IDAI and PendingLast bits. The latter is specially important, as it tells the hypervisor that there are pending interrupts for this vcpu. Reviewed-by: Eric Auger Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 58 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 17ba0d732f12..6bc142cfa616 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -212,6 +212,64 @@ #define LPI_PROP_GROUP1 (1 << 1) #define LPI_PROP_ENABLED (1 << 0) +/* + * Re-Distributor registers, offsets from VLPI_base + */ +#define GICR_VPROPBASER 0x0070 + +#define GICR_VPROPBASER_IDBITS_MASK 0x1f + +#define GICR_VPROPBASER_SHAREABILITY_SHIFT (10) +#define GICR_VPROPBASER_INNER_CACHEABILITY_SHIFT (7) +#define GICR_VPROPBASER_OUTER_CACHEABILITY_SHIFT (56) + +#define GICR_VPROPBASER_SHAREABILITY_MASK \ + GIC_BASER_SHAREABILITY(GICR_VPROPBASER, SHAREABILITY_MASK) +#define GICR_VPROPBASER_INNER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, MASK) +#define GICR_VPROPBASER_OUTER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_VPROPBASER, OUTER, MASK) +#define GICR_VPROPBASER_CACHEABILITY_MASK \ + GICR_VPROPBASER_INNER_CACHEABILITY_MASK + +#define GICR_VPROPBASER_InnerShareable \ + GIC_BASER_SHAREABILITY(GICR_VPROPBASER, InnerShareable) + +#define GICR_VPROPBASER_nCnB GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, nCnB) +#define GICR_VPROPBASER_nC GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, nC) +#define GICR_VPROPBASER_RaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWt) +#define GICR_VPROPBASER_RaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWt) +#define GICR_VPROPBASER_WaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, WaWt) +#define GICR_VPROPBASER_WaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, WaWb) +#define GICR_VPROPBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWt) +#define GICR_VPROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_VPROPBASER, INNER, RaWaWb) + +#define GICR_VPENDBASER 0x0078 + +#define GICR_VPENDBASER_SHAREABILITY_SHIFT (10) +#define GICR_VPENDBASER_INNER_CACHEABILITY_SHIFT (7) +#define GICR_VPENDBASER_OUTER_CACHEABILITY_SHIFT (56) +#define GICR_VPENDBASER_SHAREABILITY_MASK \ + GIC_BASER_SHAREABILITY(GICR_VPENDBASER, SHAREABILITY_MASK) +#define GICR_VPENDBASER_INNER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, MASK) +#define GICR_VPENDBASER_OUTER_CACHEABILITY_MASK \ + GIC_BASER_CACHEABILITY(GICR_VPENDBASER, OUTER, MASK) +#define GICR_VPENDBASER_CACHEABILITY_MASK \ + GICR_VPENDBASER_INNER_CACHEABILITY_MASK + +#define GICR_VPENDBASER_NonShareable \ + GIC_BASER_SHAREABILITY(GICR_VPENDBASER, NonShareable) + +#define GICR_VPENDBASER_nCnB GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nCnB) +#define GICR_VPENDBASER_nC GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, nC) +#define GICR_VPENDBASER_RaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWt) +#define GICR_VPENDBASER_RaWb GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWt) +#define GICR_VPENDBASER_WaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, WaWt) +#define GICR_VPENDBASER_WaWb GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, WaWb) +#define GICR_VPENDBASER_RaWaWt GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWaWt) +#define GICR_VPENDBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_VPENDBASER, INNER, RaWaWb) + #define GICR_VPENDBASER_Dirty (1ULL << 60) #define GICR_VPENDBASER_PendingLast (1ULL << 61) #define GICR_VPENDBASER_IDAI (1ULL << 62) -- cgit v1.2.3 From 20b3d54ecba51c5fe476eea94ffdc463559c5c85 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 20 Dec 2016 15:23:22 +0000 Subject: irqchip/gic-v3-its: Add device proxy for VPE management if !DirectLpi When we don't have the DirectLPI feature, we must work around the architecture shortcomings to be able to perform the required maintenance (interrupt masking, clearing and injection). For this, we create a fake device whose sole purpose is to provide a way to issue commands as if we were dealing with LPIs coming from that device (while they actually originate from the ITS). This fake device doesn't have LPIs allocated to it, but instead uses the VPE LPIs. Of course, this could be a real bottleneck, and a naive implementation would require 6 commands to issue an invalidation. Instead, let's allocate at least one event per physical CPU (rounded up to the next power of 2), and opportunistically map the VPE doorbell to an event. This doorbell will be mapped until we roll over and need to reallocate this slot. This ensures that most of the time, we only need 2 commands to issue an INV, INT or CLEAR, making the performance a lot better, given that we always issue a CLEAR on entry, and an INV on each side of a trapped WFI. Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v4.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index d499538dd86f..e7a93ad4fe97 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -39,6 +39,8 @@ struct its_vpe { /* Doorbell interrupt */ int irq; irq_hw_number_t vpe_db_lpi; + /* VPE proxy mapping */ + int vpe_proxy_event; /* * This collection ID is used to indirect the target * redistributor for this VPE. The ID itself isn't involved in -- cgit v1.2.3 From d51c4b4da7f8fae8c884e3b89fdab906f66da28a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 27 Jun 2017 21:24:25 +0100 Subject: irqchip/gic-v3-its: Set implementation defined bit to enable VLPIs A long time ago, GITS_CTLR[1] used to be called GITC_CTLR.EnableVLPI. It has been subsequently deprecated and is now an "Implementation Defined" bit that may ot may not be set for GICv4. Brilliant. And the current crop of the FastModel requires that bit for VLPIs to be enabled. Oh well... Let's set it and find out what breaks. Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 6bc142cfa616..1ea576c8126f 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -298,6 +298,7 @@ #define GITS_TRANSLATER 0x10040 #define GITS_CTLR_ENABLE (1U << 0) +#define GITS_CTLR_ImDe (1U << 1) #define GITS_CTLR_ITS_NUMBER_SHIFT 4 #define GITS_CTLR_ITS_NUMBER (0xFU << GITS_CTLR_ITS_NUMBER_SHIFT) #define GITS_CTLR_QUIESCENT (1U << 31) -- cgit v1.2.3 From 7de5c0af9c7c717f9052e6d75b24f90050e6a56e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 20 Dec 2016 15:27:52 +0000 Subject: irqchip/gic-v4: Add per-VM VPE domain creation When creating a VM, it is very convenient to have an irq domain containing all the doorbell interrupts associated with that VM (each interrupt representing a VPE). Reviewed-by: Thomas Gleixner Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v4.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index e7a93ad4fe97..3dc811dc53da 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -91,4 +91,7 @@ struct its_cmd_info { }; }; +int its_alloc_vcpu_irqs(struct its_vm *vm); +void its_free_vcpu_irqs(struct its_vm *vm); + #endif -- cgit v1.2.3 From eab84318c2811e3f38c080efcc7f709f51bb8370 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 20 Dec 2016 15:31:02 +0000 Subject: irqchip/gic-v4: Add VPE command interface Add the required interfaces to schedule a VPE and perform a VINVALL command. Reviewed-by: Thomas Gleixner Reviewed-by: Eric Auger Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v4.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index 3dc811dc53da..6450f3ed101f 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -93,5 +93,7 @@ struct its_cmd_info { int its_alloc_vcpu_irqs(struct its_vm *vm); void its_free_vcpu_irqs(struct its_vm *vm); +int its_schedule_vpe(struct its_vpe *vpe, bool on); +int its_invall_vpe(struct its_vpe *vpe); #endif -- cgit v1.2.3 From f2eac75de435871d5a497f8b557874a2a8a7b264 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 21 Dec 2016 21:50:32 +0000 Subject: irqchip/gic-v4: Add VLPI configuration interface Add the required interfaces to map, unmap and update a VLPI. Reviewed-by: Eric Auger Reviewed-by: Thomas Gleixner Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v4.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index 6450f3ed101f..e22f878ad017 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -95,5 +95,9 @@ int its_alloc_vcpu_irqs(struct its_vm *vm); void its_free_vcpu_irqs(struct its_vm *vm); int its_schedule_vpe(struct its_vpe *vpe, bool on); int its_invall_vpe(struct its_vpe *vpe); +int its_map_vlpi(int irq, struct its_vlpi_map *map); +int its_get_vlpi(int irq, struct its_vlpi_map *map); +int its_unmap_vlpi(int irq); +int its_prop_update_vlpi(int irq, u8 config, bool inv); #endif -- cgit v1.2.3 From 3d63cb53e221d8ab347e94aeac0b5511857beb7f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 20 Dec 2016 15:31:54 +0000 Subject: irqchip/gic-v4: Enable low-level GICv4 operations Get the show on the road... Reviewed-by: Thomas Gleixner Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v4.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index e22f878ad017..58a4d89aa82c 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -100,4 +100,6 @@ int its_get_vlpi(int irq, struct its_vlpi_map *map); int its_unmap_vlpi(int irq); int its_prop_update_vlpi(int irq, u8 config, bool inv); +int its_init_v4(struct irq_domain *domain, const struct irq_domain_ops *ops); + #endif -- cgit v1.2.3 From 4bdf502517288662d883fbaa915874790f51a2cd Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 25 Jun 2017 14:10:46 +0100 Subject: irqchip/gic-v3: Advertise GICv4 support to KVM As KVM needs to know about the availability of GICv4 to enable direct injection of interrupts, let's advertise the feature in the gic_kvm_info structure. Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-common.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index c647b0547bcd..0a83b4379f34 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -27,6 +27,8 @@ struct gic_kvm_info { unsigned int maint_irq; /* Virtual control interface */ struct resource vctrl; + /* vlpi support */ + bool has_v4; }; const struct gic_kvm_info *gic_get_kvm_info(void); -- cgit v1.2.3 From b5f515735bea4ae71c248aea3e049073f8852889 Mon Sep 17 00:00:00 2001 From: Andreas Dilger Date: Thu, 31 Aug 2017 11:09:45 -0400 Subject: ext4: avoid Y2038 overflow in recently_deleted() Avoid a 32-bit time overflow in recently_deleted() since i_dtime (inode deletion time) is stored only as a 32-bit value on disk. Since i_dtime isn't used for much beyond a boolean value in e2fsck and is otherwise only used in this function in the kernel, there is no benefit to use more space in the inode for this field on disk. Instead, compare only the relative deletion time with the low 32 bits of the time using the newly-added time_before32() helper, which is similar to time_before() and time_after() for jiffies. Increase RECENTCY_DIRTY to 300s based on Ted's comments about usage experience at Google. Signed-off-by: Andreas Dilger Signed-off-by: Theodore Ts'o Reviewed-by: Arnd Bergmann --- include/linux/time.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 4abb32d4c6b8..3877136bbdf8 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -285,4 +285,19 @@ static inline bool itimerspec64_valid(const struct itimerspec64 *its) return true; } +/** + * time_after32 - compare two 32-bit relative times + * @a: the time which may be after @b + * @b: the time which may be before @a + * + * time_after32(a, b) returns true if the time @a is after time @b. + * time_before32(b, a) returns true if the time @b is before time @a. + * + * Similar to time_after(), compare two 32-bit timestamps for relative + * times. This is useful for comparing 32-bit seconds values that can't + * be converted to 64-bit values (e.g. due to disk format or wire protocol + * issues) when it is known that the times are less than 68 years apart. + */ +#define time_after32(a, b) ((s32)((u32)(b) - (u32)(a)) < 0) +#define time_before32(b, a) time_after32(a, b) #endif -- cgit v1.2.3 From a27bfcab5c1c3a0df61b68e85fc5e4cade83559f Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Thu, 31 Aug 2017 09:47:22 -0600 Subject: genalloc: Fix an incorrect kerneldoc comment The kerneldoc comment for the genpool_algo_t typedef was incomplete and incorrectly formatted, leading to a raft of warnings during the docs build. Fix it appropriately. Signed-off-by: Jonathan Corbet --- include/linux/genalloc.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 29d4385903d4..6dfec4d638df 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -38,12 +38,13 @@ struct device_node; struct gen_pool; /** - * Allocation callback function type definition + * typedef genpool_algo_t: Allocation callback function type definition * @map: Pointer to bitmap * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for - * @data: optional additional data used by @genpool_algo_t + * @data: optional additional data used by the callback + * @pool: the pool being allocated from */ typedef unsigned long (*genpool_algo_t)(unsigned long *map, unsigned long size, -- cgit v1.2.3 From eb3c74de28b24f5a36d12d6c84f1fceb25d12c4f Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Mon, 28 Aug 2017 19:02:41 +0800 Subject: usb: phy: Avoid unchecked dereference warning Move the USB phy NULL checking before issuing usb_phy_set_charger_current() to avoid unchecked dereference warning. Signed-off-by: Baolin Wang Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/phy.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index de881b171ba9..8c6914873a16 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -322,9 +322,12 @@ static inline void usb_phy_set_charger_state(struct usb_phy *usb_phy, static inline int usb_phy_set_power(struct usb_phy *x, unsigned mA) { + if (!x) + return 0; + usb_phy_set_charger_current(x, mA); - if (x && x->set_power) + if (x->set_power) return x->set_power(x, mA); return 0; } -- cgit v1.2.3 From 2eb7954809bf26de27bc3a2fea4eef606bbf4482 Mon Sep 17 00:00:00 2001 From: Jaghathiswari Rankappagounder Natarajan Date: Wed, 30 Aug 2017 16:34:33 -0700 Subject: drivers: w1: add hwmon support structures This patch has changes to w1.h/w1.c generic files to add (optional) hwmon support structures. Signed-off-by: Jaghathiswari Rankappagounder Natarajan Acked-by: Evgeniy Polyakov Acked-by: Guenter Roeck Signed-off-by: Greg Kroah-Hartman --- include/linux/w1.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/w1.h b/include/linux/w1.h index 90cbe7e65059..5b2972946dda 100644 --- a/include/linux/w1.h +++ b/include/linux/w1.h @@ -68,6 +68,7 @@ struct w1_reg_num { * @family: module for device family type * @family_data: pointer for use by the family module * @dev: kernel device identifier + * @hwmon: pointer to hwmon device * */ struct w1_slave { @@ -83,6 +84,7 @@ struct w1_slave { struct w1_family *family; void *family_data; struct device dev; + struct device *hwmon; }; typedef void (*w1_slave_found_callback)(struct w1_master *, u64); @@ -250,11 +252,13 @@ void w1_remove_master_device(struct w1_bus_master *master); * @add_slave: add_slave * @remove_slave: remove_slave * @groups: sysfs group + * @chip_info: pointer to struct hwmon_chip_info */ struct w1_family_ops { int (*add_slave)(struct w1_slave *sl); void (*remove_slave)(struct w1_slave *sl); const struct attribute_group **groups; + const struct hwmon_chip_info *chip_info; }; /** -- cgit v1.2.3 From f16ded5948a5e6a399161bd71e866b198952ea5f Mon Sep 17 00:00:00 2001 From: Rami Rosen Date: Thu, 31 Aug 2017 13:41:40 +0300 Subject: net: fix two typos in net_device_ops documentation. This patch fixes two trivial typos in net_device_ops documentation, related to ndo_xdp_flush callback. Signed-off-by: Rami Rosen Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 29bf06ff157c..35de8312e0b5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1124,8 +1124,8 @@ struct xfrmdev_ops { * This function is used to submit a XDP packet for transmit on a * netdevice. * void (*ndo_xdp_flush)(struct net_device *dev); - * This function is used to inform the driver to flush a paticular - * xpd tx queue. Must be called on same CPU as xdp_xmit. + * This function is used to inform the driver to flush a particular + * xdp tx queue. Must be called on same CPU as xdp_xmit. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); -- cgit v1.2.3 From 60361e12d01676e23a8de89a5ef4a349ae97f616 Mon Sep 17 00:00:00 2001 From: Zev Weiss Date: Wed, 30 Aug 2017 05:36:38 -0500 Subject: ftrace: Fix debug preempt config name in stack_tracer_{en,dis}able stack_tracer_disable()/stack_tracer_enable() had been using the wrong name for the config symbol to enable their preempt-debugging checks -- fix with a word swap. Link: http://lkml.kernel.org/r/20170831154036.4xldyakmmhuts5x7@hatter.bewilderbeest.net Cc: stable@vger.kernel.org Fixes: 8aaf1ee70e ("tracing: Rename trace_active to disable_stack_tracer and inline its modification") Signed-off-by: Zev Weiss Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 6383115e9d2c..2e028854bac7 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -307,7 +307,7 @@ DECLARE_PER_CPU(int, disable_stack_tracer); static inline void stack_tracer_disable(void) { /* Preemption or interupts must be disabled */ - if (IS_ENABLED(CONFIG_PREEMPT_DEBUG)) + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) WARN_ON_ONCE(!preempt_count() || !irqs_disabled()); this_cpu_inc(disable_stack_tracer); } @@ -320,7 +320,7 @@ static inline void stack_tracer_disable(void) */ static inline void stack_tracer_enable(void) { - if (IS_ENABLED(CONFIG_PREEMPT_DEBUG)) + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) WARN_ON_ONCE(!preempt_count() || !irqs_disabled()); this_cpu_dec(disable_stack_tracer); } -- cgit v1.2.3 From 4f59c718521a0f00b6589da6b8fcea2dc296026d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 8 Jul 2017 11:40:39 -0400 Subject: teach SYSCALL_DEFINE/COMPAT_SYSCALL_DEFINE to handle __bitwise arguments Signed-off-by: Al Viro --- include/linux/compat.h | 2 +- include/linux/syscalls.h | 9 +++++---- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index 5a6a109b4a50..e5d3fbe24f7d 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -27,7 +27,7 @@ #endif #ifndef __SC_DELOUSE -#define __SC_DELOUSE(t,v) ((t)(unsigned long)(v)) +#define __SC_DELOUSE(t,v) ((__force t)(unsigned long)(v)) #endif #define COMPAT_SYSCALL_DEFINE0(name) \ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3cb15ea48aee..0bc1d2e8cc17 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -100,11 +100,12 @@ union bpf_attr; #define __MAP(n,...) __MAP##n(__VA_ARGS__) #define __SC_DECL(t, a) t a -#define __TYPE_IS_L(t) (__same_type((t)0, 0L)) -#define __TYPE_IS_UL(t) (__same_type((t)0, 0UL)) -#define __TYPE_IS_LL(t) (__same_type((t)0, 0LL) || __same_type((t)0, 0ULL)) +#define __TYPE_AS(t, v) __same_type((__force t)0, v) +#define __TYPE_IS_L(t) (__TYPE_AS(t, 0L)) +#define __TYPE_IS_UL(t) (__TYPE_AS(t, 0UL)) +#define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL)) #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a -#define __SC_CAST(t, a) (t) a +#define __SC_CAST(t, a) (__force t) a #define __SC_ARGS(t, a) a #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long)) -- cgit v1.2.3 From ddef7ed2b5cbafae692d1d580bb5a07808926a9c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Jul 2017 18:58:37 +0200 Subject: annotate RWF_... flags [AV: added missing annotations in syscalls.h/compat.h] Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/compat.h | 16 ++++++++++++++-- include/linux/fs.h | 12 +++++++----- include/linux/syscalls.h | 4 ++-- 3 files changed, 23 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index e5d3fbe24f7d..3fc433303d7a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -365,10 +365,10 @@ asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, compat_ulong_t vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, @@ -382,6 +382,18 @@ asmlinkage long compat_sys_pwritev64(unsigned long fd, unsigned long vlen, loff_t pos); #endif +#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 +asmlinkage long compat_sys_readv64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif + +#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 +asmlinkage long compat_sys_pwritev64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif + asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, diff --git a/include/linux/fs.h b/include/linux/fs.h index cbfe127bccf8..2625fc47c7e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -72,6 +72,8 @@ extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; +typedef __kernel_rwf_t rwf_t; + struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); @@ -1758,9 +1760,9 @@ extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *) extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); + unsigned long, loff_t *, rwf_t); extern ssize_t vfs_writev(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); + unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, @@ -2874,9 +2876,9 @@ extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags); + rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags); + rwf_t flags); /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); @@ -3143,7 +3145,7 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) { if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0bc1d2e8cc17..138c94535864 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -579,12 +579,12 @@ asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - int flags); + rwf_t flags); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - int flags); + rwf_t flags); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); asmlinkage long sys_chdir(const char __user *filename); -- cgit v1.2.3 From f58e76c1c551c7577b25a6fe493d82f5214331b7 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 23 Aug 2017 15:29:10 -0700 Subject: : Fix copy_in_user() declaration copy_in_user() copies data from user-space address @from to user- space address @to. Hence declare both @from and @to as user-space pointers. Fixes: commit d597580d3737 ("generic ...copy_..._user primitives") Signed-off-by: Bart Van Assche Cc: Signed-off-by: Al Viro --- include/linux/uaccess.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index acdd6f915a8d..20ef8e6ec2db 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -156,7 +156,7 @@ copy_to_user(void __user *to, const void *from, unsigned long n) } #ifdef CONFIG_COMPAT static __always_inline unsigned long __must_check -copy_in_user(void __user *to, const void *from, unsigned long n) +copy_in_user(void __user *to, const void __user *from, unsigned long n) { might_fault(); if (access_ok(VERIFY_WRITE, to, n) && access_ok(VERIFY_READ, from, n)) -- cgit v1.2.3 From 065e63f951432068ba89a844fcbff68ea16ee186 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 31 Aug 2017 17:03:47 -0400 Subject: tracing: Only have rmmod clear buffers that its events were active in Currently, when a module event is enabled, when that module is removed, it clears all ring buffers. This is to prevent another module from being loaded and having one of its trace event IDs from reusing a trace event ID of the removed module. This could cause undesirable effects as the trace event of the new module would be using its own processing algorithms to process raw data of another event. To prevent this, when a module is loaded, if any of its events have been used (signified by the WAS_ENABLED event call flag, which is never cleared), all ring buffers are cleared, just in case any one of them contains event data of the removed event. The problem is, there's no reason to clear all ring buffers if only one (or less than all of them) uses one of the events. Instead, only clear the ring buffers that recorded the events of a module that is being removed. To do this, instead of keeping the WAS_ENABLED flag with the trace event call, move it to the per instance (per ring buffer) event file descriptor. The event file descriptor maps each event to a separate ring buffer instance. Then when the module is removed, only the ring buffers that activated one of the module's events get cleared. The rest are not touched. Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 536c80ff7ad9..3702b9cb5dc8 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -217,7 +217,6 @@ enum { TRACE_EVENT_FL_CAP_ANY_BIT, TRACE_EVENT_FL_NO_SET_FILTER_BIT, TRACE_EVENT_FL_IGNORE_ENABLE_BIT, - TRACE_EVENT_FL_WAS_ENABLED_BIT, TRACE_EVENT_FL_TRACEPOINT_BIT, TRACE_EVENT_FL_KPROBE_BIT, TRACE_EVENT_FL_UPROBE_BIT, @@ -229,9 +228,6 @@ enum { * CAP_ANY - Any user can enable for perf * NO_SET_FILTER - Set when filter has error and is to be ignored * IGNORE_ENABLE - For trace internal events, do not enable with debugfs file - * WAS_ENABLED - Set and stays set when an event was ever enabled - * (used for module unloading, if a module event is enabled, - * it is best to clear the buffers that used it). * TRACEPOINT - Event is a tracepoint * KPROBE - Event is a kprobe * UPROBE - Event is a uprobe @@ -241,7 +237,6 @@ enum { TRACE_EVENT_FL_CAP_ANY = (1 << TRACE_EVENT_FL_CAP_ANY_BIT), TRACE_EVENT_FL_NO_SET_FILTER = (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT), TRACE_EVENT_FL_IGNORE_ENABLE = (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT), - TRACE_EVENT_FL_WAS_ENABLED = (1 << TRACE_EVENT_FL_WAS_ENABLED_BIT), TRACE_EVENT_FL_TRACEPOINT = (1 << TRACE_EVENT_FL_TRACEPOINT_BIT), TRACE_EVENT_FL_KPROBE = (1 << TRACE_EVENT_FL_KPROBE_BIT), TRACE_EVENT_FL_UPROBE = (1 << TRACE_EVENT_FL_UPROBE_BIT), @@ -306,6 +301,7 @@ enum { EVENT_FILE_FL_TRIGGER_MODE_BIT, EVENT_FILE_FL_TRIGGER_COND_BIT, EVENT_FILE_FL_PID_FILTER_BIT, + EVENT_FILE_FL_WAS_ENABLED_BIT, }; /* @@ -321,6 +317,7 @@ enum { * TRIGGER_MODE - When set, invoke the triggers associated with the event * TRIGGER_COND - When set, one or more triggers has an associated filter * PID_FILTER - When set, the event is filtered based on pid + * WAS_ENABLED - Set when enabled to know to clear trace on module removal */ enum { EVENT_FILE_FL_ENABLED = (1 << EVENT_FILE_FL_ENABLED_BIT), @@ -333,6 +330,7 @@ enum { EVENT_FILE_FL_TRIGGER_MODE = (1 << EVENT_FILE_FL_TRIGGER_MODE_BIT), EVENT_FILE_FL_TRIGGER_COND = (1 << EVENT_FILE_FL_TRIGGER_COND_BIT), EVENT_FILE_FL_PID_FILTER = (1 << EVENT_FILE_FL_PID_FILTER_BIT), + EVENT_FILE_FL_WAS_ENABLED = (1 << EVENT_FILE_FL_WAS_ENABLED_BIT), }; struct trace_event_file { -- cgit v1.2.3 From 5deb67f77a266010e2c10fb124b7516d0d258ce8 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Thu, 31 Aug 2017 12:27:09 +0100 Subject: libnvdimm, nd_blk: remove mmio_flush_range() mmio_flush_range() suffers from a lack of clearly-defined semantics, and is somewhat ambiguous to port to other architectures where the scope of the writeback implied by "flush" and ordering might matter, but MMIO would tend to imply non-cacheable anyway. Per the rationale in 67a3e8fe9015 ("nd_blk: change aperture mapping from WC to WB"), the only existing use is actually to invalidate clean cache lines for ARCH_MEMREMAP_PMEM type mappings *without* writeback. Since the recent cleanup of the pmem API, that also now happens to be the exact purpose of arch_invalidate_pmem(), which would be a far more well-defined tool for the job. Rather than risk potentially inconsistent implementations of mmio_flush_range() for the sake of one callsite, streamline things by removing it entirely and instead move the ARCH_MEMREMAP_PMEM related definitions up to the libnvdimm level, so they can be shared by NFIT as well. This allows NFIT to be enabled for arm64. Signed-off-by: Robin Murphy Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 9b8d81a7b80e..3eaad2fbf284 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -174,4 +174,19 @@ u64 nd_fletcher64(void *addr, size_t len, bool le); void nvdimm_flush(struct nd_region *nd_region); int nvdimm_has_flush(struct nd_region *nd_region); int nvdimm_has_cache(struct nd_region *nd_region); + +#ifdef CONFIG_ARCH_HAS_PMEM_API +#define ARCH_MEMREMAP_PMEM MEMREMAP_WB +void arch_wb_cache_pmem(void *addr, size_t size); +void arch_invalidate_pmem(void *addr, size_t size); +#else +#define ARCH_MEMREMAP_PMEM MEMREMAP_WT +static inline void arch_wb_cache_pmem(void *addr, size_t size) +{ +} +static inline void arch_invalidate_pmem(void *addr, size_t size) +{ +} +#endif + #endif /* __LIBNVDIMM_H__ */ -- cgit v1.2.3 From a4d1a885251382250ec315482bdd8ca52dd61e6a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Thu, 31 Aug 2017 17:17:26 -0400 Subject: dax: update to new mmu_notifier semantic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Replace all mmu_notifier_invalidate_page() calls by *_invalidate_range() and make sure it is bracketed by calls to *_invalidate_range_start()/end(). Note that because we can not presume the pmd value or pte value we have to assume the worst and unconditionaly report an invalidation as happening. Signed-off-by: Jérôme Glisse Cc: Dan Williams Cc: Ross Zwisler Cc: Bernhard Held Cc: Adam Borowski Cc: Andrea Arcangeli Cc: Radim Krčmář Cc: Wanpeng Li Cc: Paolo Bonzini Cc: Takashi Iwai Cc: Nadav Amit Cc: Mike Galbraith Cc: Kirill A. Shutemov Cc: axie Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 46b9ac5e8569..c1f6c95f3496 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1260,6 +1260,7 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, + unsigned long *start, unsigned long *end, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); -- cgit v1.2.3 From 5f32b265400de723ab0db23101a75ac073bdd980 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Thu, 31 Aug 2017 17:17:38 -0400 Subject: mm/mmu_notifier: kill invalidate_page MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The invalidate_page callback suffered from two pitfalls. First it used to happen after the page table lock was release and thus a new page might have setup before the call to invalidate_page() happened. This is in a weird way fixed by commit c7ab0d2fdc84 ("mm: convert try_to_unmap_one() to use page_vma_mapped_walk()") that moved the callback under the page table lock but this also broke several existing users of the mmu_notifier API that assumed they could sleep inside this callback. The second pitfall was invalidate_page() being the only callback not taking a range of address in respect to invalidation but was giving an address and a page. Lots of the callback implementers assumed this could never be THP and thus failed to invalidate the appropriate range for THP. By killing this callback we unify the mmu_notifier callback API to always take a virtual address range as input. Finally this also simplifies the end user life as there is now two clear choices: - invalidate_range_start()/end() callback (which allow you to sleep) - invalidate_range() where you can not sleep but happen right after page table update under page table lock Signed-off-by: Jérôme Glisse Cc: Bernhard Held Cc: Adam Borowski Cc: Andrea Arcangeli Cc: Radim Krčmář Cc: Wanpeng Li Cc: Paolo Bonzini Cc: Takashi Iwai Cc: Nadav Amit Cc: Mike Galbraith Cc: Kirill A. Shutemov Cc: axie Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmu_notifier.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index c91b3bcd158f..7b2e31b1745a 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -94,17 +94,6 @@ struct mmu_notifier_ops { unsigned long address, pte_t pte); - /* - * Before this is invoked any secondary MMU is still ok to - * read/write to the page previously pointed to by the Linux - * pte because the page hasn't been freed yet and it won't be - * freed until this returns. If required set_page_dirty has to - * be called internally to this method. - */ - void (*invalidate_page)(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address); - /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_sem and/or the @@ -220,8 +209,6 @@ extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); -extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address); extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end); extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, @@ -268,13 +255,6 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm, __mmu_notifier_change_pte(mm, address, pte); } -static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address) -{ - if (mm_has_notifiers(mm)) - __mmu_notifier_invalidate_page(mm, address); -} - static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { @@ -442,11 +422,6 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm, { } -static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address) -{ -} - static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { -- cgit v1.2.3 From c03567a8e8d5cf2aaca40e605c48f319dc2ead57 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Thu, 31 Aug 2017 16:15:33 -0700 Subject: include/linux/compiler.h: don't perform compiletime_assert with -O0 Commit c7acec713d14 ("kernel.h: handle pointers to arrays better in container_of()") made use of __compiletime_assert() from container_of() thus increasing the usage of this macro, allowing developers to notice type conflicts in usage of container_of() at compile time. However, the implementation of __compiletime_assert relies on compiler optimizations to report an error. This means that if a developer uses "-O0" with any code that performs container_of(), the compiler will always report an error regardless of whether there is an actual problem in the code. This patch disables compile_time_assert when optimizations are disabled to allow such code to compile with CFLAGS="-O0". Example compilation failure: ./include/linux/compiler.h:547:38: error: call to `__compiletime_assert_94' declared with attribute error: pointer type mismatch in container_of() _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__) ^ ./include/linux/compiler.h:530:4: note: in definition of macro `__compiletime_assert' prefix ## suffix(); \ ^~~~~~ ./include/linux/compiler.h:547:2: note: in expansion of macro `_compiletime_assert' _compiletime_assert(condition, msg, __compiletime_assert_, __LINE__) ^~~~~~~~~~~~~~~~~~~ ./include/linux/build_bug.h:46:37: note: in expansion of macro `compiletime_assert' #define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) ^~~~~~~~~~~~~~~~~~ ./include/linux/kernel.h:860:2: note: in expansion of macro `BUILD_BUG_ON_MSG' BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ ^~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: use do{}while(0), per Michal] Link: http://lkml.kernel.org/r/20170829230114.11662-1-joe@ovn.org Fixes: c7acec713d14c6c ("kernel.h: handle pointers to arrays better in container_of()") Signed-off-by: Joe Stringer Cc: Ian Abbott Cc: Arnd Bergmann Cc: Michal Nazarewicz Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index eca8ad75e28b..043b60de041e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -517,7 +517,8 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s # define __compiletime_error_fallback(condition) do { } while (0) #endif -#define __compiletime_assert(condition, msg, prefix, suffix) \ +#ifdef __OPTIMIZE__ +# define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ bool __cond = !(condition); \ extern void prefix ## suffix(void) __compiletime_error(msg); \ @@ -525,6 +526,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s prefix ## suffix(); \ __compiletime_error_fallback(__cond); \ } while (0) +#else +# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) +#endif #define _compiletime_assert(condition, msg, prefix, suffix) \ __compiletime_assert(condition, msg, prefix, suffix) -- cgit v1.2.3 From 0a9c869d5c568054a828a38357f30d77659e5b1e Mon Sep 17 00:00:00 2001 From: Gabriel Fernandez Date: Mon, 21 Aug 2017 13:59:01 +0200 Subject: clk: gate: expose clk_gate_ops::is_enabled This patch exposes clk_gate_ops::is_enabled as functions that can be directly called and assigned in places like this so we don't need wrapper functions that do nothing besides forward the call. Signed-off-by: Gabriel Fernandez Suggested-by: Stephen Boyd Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 1fc113fbf955..5100ec1b5d55 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -343,6 +343,7 @@ struct clk_hw *clk_hw_register_gate(struct device *dev, const char *name, u8 clk_gate_flags, spinlock_t *lock); void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); +int clk_gate_is_enabled(struct clk_hw *hw); struct clk_div_table { unsigned int val; -- cgit v1.2.3 From b32dbc1e0bf0eaa8bdd725491b361d5fc2f57a85 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Aug 2017 17:12:18 +0200 Subject: dma-coherent: remove the DMA_MEMORY_INCLUDES_CHILDREN flag This flag was never implemented or used. Signed-off-by: Christoph Hellwig Reviewed-by: Robin Murphy --- include/linux/dma-mapping.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4c98cc96971f..abf369b11f54 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -696,8 +696,7 @@ static inline int dma_get_cache_alignment(void) /* flags for the coherent memory api */ #define DMA_MEMORY_MAP 0x01 #define DMA_MEMORY_IO 0x02 -#define DMA_MEMORY_INCLUDES_CHILDREN 0x04 -#define DMA_MEMORY_EXCLUSIVE 0x08 +#define DMA_MEMORY_EXCLUSIVE 0x04 #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, -- cgit v1.2.3 From 2436bdcda53ff4abb7897c87fa29ef3de8055344 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 25 Aug 2017 17:13:09 +0200 Subject: dma-coherent: remove the DMA_MEMORY_MAP and DMA_MEMORY_IO flags DMA_MEMORY_IO was never used in the tree, so remove it. That means there is no need for the DMA_MEMORY_MAP flag either now, so remove it as well and change dma_declare_coherent_memory to return a normal errno value. Signed-off-by: Christoph Hellwig Reviewed-by: Marek Szyprowski --- include/linux/dma-mapping.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index abf369b11f54..b7dd11c02a45 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -694,9 +694,7 @@ static inline int dma_get_cache_alignment(void) #endif /* flags for the coherent memory api */ -#define DMA_MEMORY_MAP 0x01 -#define DMA_MEMORY_IO 0x02 -#define DMA_MEMORY_EXCLUSIVE 0x04 +#define DMA_MEMORY_EXCLUSIVE 0x01 #ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, @@ -709,7 +707,7 @@ static inline int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags) { - return 0; + return -ENOSYS; } static inline void -- cgit v1.2.3 From 25cc72a33835ed8a6f53180a822cadab855852ac Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 1 Sep 2017 10:52:31 +0200 Subject: mlxsw: spectrum: Forbid linking to devices that have uppers The mlxsw driver relies on NETDEV_CHANGEUPPER events to configure the device in case a port is enslaved to a master netdev such as bridge or bond. Since the driver ignores events unrelated to its ports and their uppers, it's possible to engineer situations in which the device's data path differs from the kernel's. One example to such a situation is when a port is enslaved to a bond that is already enslaved to a bridge. When the bond was enslaved the driver ignored the event - as the bond wasn't one of its uppers - and therefore a bridge port instance isn't created in the device. Until such configurations are supported forbid them by checking that the upper device doesn't have uppers of its own. Fixes: 0d65fc13042f ("mlxsw: spectrum: Implement LAG port join/leave") Signed-off-by: Ido Schimmel Reported-by: Nogah Frankel Tested-by: Nogah Frankel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 779b23595596..c99ba7914c0a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3866,6 +3866,8 @@ int netdev_walk_all_upper_dev_rcu(struct net_device *dev, bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); +bool netdev_has_any_upper_dev(struct net_device *dev); + void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter); void *netdev_lower_get_next_private_rcu(struct net_device *dev, -- cgit v1.2.3 From 799ea9e9c59949008770aab4e1da87f10e99dbe4 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Fri, 18 Aug 2017 18:08:25 -0700 Subject: xfs: evict all inodes involved with log redo item When we introduced the bmap redo log items, we set MS_ACTIVE on the mountpoint and XFS_IRECOVERY on the inode to prevent unlinked inodes from being truncated prematurely during log recovery. This also had the effect of putting linked inodes on the lru instead of evicting them. Unfortunately, we neglected to find all those unreferenced lru inodes and evict them after finishing log recovery, which means that we leak them if anything goes wrong in the rest of xfs_mountfs, because the lru is only cleaned out on unmount. Therefore, evict unreferenced inodes in the lru list immediately after clearing MS_ACTIVE. Fixes: 17c12bcd30 ("xfs: when replaying bmap operations, don't let unlinked inodes get reaped") Signed-off-by: Darrick J. Wong Cc: viro@ZenIV.linux.org.uk Reviewed-by: Brian Foster --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e1fd5d21248..00f46e018370 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2831,6 +2831,7 @@ static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern unsigned int get_next_ino(void); +extern void evict_inodes(struct super_block *sb); extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); -- cgit v1.2.3 From 8db6c34f1dbc8e06aa016a9b829b06902c3e1340 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 8 May 2017 13:11:56 -0500 Subject: Introduce v3 namespaced file capabilities Root in a non-initial user ns cannot be trusted to write a traditional security.capability xattr. If it were allowed to do so, then any unprivileged user on the host could map his own uid to root in a private namespace, write the xattr, and execute the file with privilege on the host. However supporting file capabilities in a user namespace is very desirable. Not doing so means that any programs designed to run with limited privilege must continue to support other methods of gaining and dropping privilege. For instance a program installer must detect whether file capabilities can be assigned, and assign them if so but set setuid-root otherwise. The program in turn must know how to drop partial capabilities, and do so only if setuid-root. This patch introduces v3 of the security.capability xattr. It builds a vfs_ns_cap_data struct by appending a uid_t rootid to struct vfs_cap_data. This is the absolute uid_t (that is, the uid_t in user namespace which mounted the filesystem, usually init_user_ns) of the root id in whose namespaces the file capabilities may take effect. When a task asks to write a v2 security.capability xattr, if it is privileged with respect to the userns which mounted the filesystem, then nothing should change. Otherwise, the kernel will transparently rewrite the xattr as a v3 with the appropriate rootid. This is done during the execution of setxattr() to catch user-space-initiated capability writes. Subsequently, any task executing the file which has the noted kuid as its root uid, or which is in a descendent user_ns of such a user_ns, will run the file with capabilities. Similarly when asking to read file capabilities, a v3 capability will be presented as v2 if it applies to the caller's namespace. If a task writes a v3 security.capability, then it can provide a uid for the xattr so long as the uid is valid in its own user namespace, and it is privileged with CAP_SETFCAP over its namespace. The kernel will translate that rootid to an absolute uid, and write that to disk. After this, a task in the writer's namespace will not be able to use those capabilities (unless rootid was 0), but a task in a namespace where the given uid is root will. Only a single security.capability xattr may exist at a time for a given file. A task may overwrite an existing xattr so long as it is privileged over the inode. Note this is a departure from previous semantics, which required privilege to remove a security.capability xattr. This check can be re-added if deemed useful. This allows a simple setxattr to work, allows tar/untar to work, and allows us to tar in one namespace and untar in another while preserving the capability, without risking leaking privilege into a parent namespace. Example using tar: $ cp /bin/sleep sleepx $ mkdir b1 b2 $ lxc-usernsexec -m b:0:100000:1 -m b:1:$(id -u):1 -- chown 0:0 b1 $ lxc-usernsexec -m b:0:100001:1 -m b:1:$(id -u):1 -- chown 0:0 b2 $ lxc-usernsexec -m b:0:100000:1000 -- tar --xattrs-include=security.capability --xattrs -cf b1/sleepx.tar sleepx $ lxc-usernsexec -m b:0:100001:1000 -- tar --xattrs-include=security.capability --xattrs -C b2 -xf b1/sleepx.tar $ lxc-usernsexec -m b:0:100001:1000 -- getcap b2/sleepx b2/sleepx = cap_sys_admin+ep # /opt/ltp/testcases/bin/getv3xattr b2/sleepx v3 xattr, rootid is 100001 A patch to linux-test-project adding a new set of tests for this functionality is in the nsfscaps branch at github.com/hallyn/ltp Changelog: Nov 02 2016: fix invalid check at refuse_fcap_overwrite() Nov 07 2016: convert rootid from and to fs user_ns (From ebiederm: mar 28 2017) commoncap.c: fix typos - s/v4/v3 get_vfs_caps_from_disk: clarify the fs_ns root access check nsfscaps: change the code split for cap_inode_setxattr() Apr 09 2017: don't return v3 cap for caps owned by current root. return a v2 cap for a true v2 cap in non-init ns Apr 18 2017: . Change the flow of fscap writing to support s_user_ns writing. . Remove refuse_fcap_overwrite(). The value of the previous xattr doesn't matter. Apr 24 2017: . incorporate Eric's incremental diff . move cap_convert_nscap to setxattr and simplify its usage May 8, 2017: . fix leaking dentry refcount in cap_inode_getsecurity Signed-off-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- include/linux/capability.h | 2 ++ include/linux/security.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/capability.h b/include/linux/capability.h index 6ffb67e10c06..b52e278e4744 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -248,4 +248,6 @@ extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); +extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size); + #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/security.h b/include/linux/security.h index b6ea1dc9cc9d..6fff8c924718 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -91,6 +91,8 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name, extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); +extern int cap_inode_getsecurity(struct inode *inode, const char *name, + void **buffer, bool alloc); extern int cap_mmap_addr(unsigned long addr); extern int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags); -- cgit v1.2.3 From 0142626d08223b0f6ad04859301b53178f11c317 Mon Sep 17 00:00:00 2001 From: Shawn Lin Date: Fri, 1 Sep 2017 16:35:20 -0500 Subject: PCI: Correct kernel-doc of pci_vpd_srdt_size(), pci_vpd_srdt_tag() The kernel-doc comments don't match the arguments, so fix the comments. Signed-off-by: Shawn Lin Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 4869e66dd659..7950fc697394 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2059,7 +2059,7 @@ static inline u16 pci_vpd_lrdt_tag(const u8 *lrdt) /** * pci_vpd_srdt_size - Extracts the Small Resource Data Type length - * @lrdt: Pointer to the beginning of the Small Resource Data Type tag + * @srdt: Pointer to the beginning of the Small Resource Data Type tag * * Returns the extracted Small Resource Data Type length. */ @@ -2070,7 +2070,7 @@ static inline u8 pci_vpd_srdt_size(const u8 *srdt) /** * pci_vpd_srdt_tag - Extracts the Small Resource Data Type Tag Item - * @lrdt: Pointer to the beginning of the Small Resource Data Type tag + * @srdt: Pointer to the beginning of the Small Resource Data Type tag * * Returns the extracted Small Resource Data Type Tag Item. */ -- cgit v1.2.3 From 96291d565550c1fd363e488cc17cb3189d2e4cc2 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 1 Sep 2017 16:35:50 -0500 Subject: PCI: Fix typos and whitespace errors Fix various typos and whitespace errors: s/Synopsis/Synopsys/ s/Designware/DesignWare/ s/Keystine/Keystone/ s/gpio/GPIO/ s/pcie/PCIe/ s/phy/PHY/ s/confgiruation/configuration/ No functional change intended. Signed-off-by: Bjorn Helgaas --- include/linux/aer.h | 5 ++--- include/linux/pcieport_if.h | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/aer.h b/include/linux/aer.h index 04602cbe85dc..43799bd17a02 100644 --- a/include/linux/aer.h +++ b/include/linux/aer.h @@ -39,7 +39,7 @@ struct aer_capability_regs { }; #if defined(CONFIG_PCIEAER) -/* pci-e port driver needs this function to enable aer */ +/* PCIe port driver needs this function to enable AER */ int pci_enable_pcie_error_reporting(struct pci_dev *dev); int pci_disable_pcie_error_reporting(struct pci_dev *dev); int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev); @@ -67,7 +67,6 @@ void cper_print_aer(struct pci_dev *dev, int aer_severity, struct aer_capability_regs *aer); int cper_severity_to_aer(int cper_severity); void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn, - int severity, - struct aer_capability_regs *aer_regs); + int severity, struct aer_capability_regs *aer_regs); #endif //_AER_H_ diff --git a/include/linux/pcieport_if.h b/include/linux/pcieport_if.h index afcd130ab3a9..12542f5ac83d 100644 --- a/include/linux/pcieport_if.h +++ b/include/linux/pcieport_if.h @@ -38,7 +38,7 @@ static inline void set_service_data(struct pcie_device *dev, void *data) dev->priv_data = data; } -static inline void* get_service_data(struct pcie_device *dev) +static inline void *get_service_data(struct pcie_device *dev) { return dev->priv_data; } -- cgit v1.2.3 From 0865805d82d4c822647ee35ab2629c48cc40706b Mon Sep 17 00:00:00 2001 From: Quentin Schulz Date: Thu, 10 Aug 2017 08:34:03 +0200 Subject: clk: at91: add audio pll clock drivers This new clock driver set allows to have a fractional divided clock that would generate a precise clock particularly suitable for audio applications. The main audio pll clock has two children clocks: one that is connected to the PMC, the other that can directly drive a pad. As these two routes have different enable bits and different dividers and divider formulas, they are handled by two different drivers. Each of them could modify the rate of the main audio pll parent. The main audio pll clock can output 620MHz to 700MHz. Signed-off-by: Nicolas Ferre Signed-off-by: Quentin Schulz Acked-by: Boris Brezillon Signed-off-by: Stephen Boyd --- include/linux/clk/at91_pmc.h | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h index 17f413bbbedf..6aca5ce8a99a 100644 --- a/include/linux/clk/at91_pmc.h +++ b/include/linux/clk/at91_pmc.h @@ -185,4 +185,29 @@ #define AT91_PMC_PCR_EN (0x1 << 28) /* Enable */ #define AT91_PMC_PCR_GCKEN (0x1 << 29) /* GCK Enable */ +#define AT91_PMC_AUDIO_PLL0 0x14c +#define AT91_PMC_AUDIO_PLL_PLLEN (1 << 0) +#define AT91_PMC_AUDIO_PLL_PADEN (1 << 1) +#define AT91_PMC_AUDIO_PLL_PMCEN (1 << 2) +#define AT91_PMC_AUDIO_PLL_RESETN (1 << 3) +#define AT91_PMC_AUDIO_PLL_ND_OFFSET 8 +#define AT91_PMC_AUDIO_PLL_ND_MASK (0x7f << AT91_PMC_AUDIO_PLL_ND_OFFSET) +#define AT91_PMC_AUDIO_PLL_ND(n) ((n) << AT91_PMC_AUDIO_PLL_ND_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPMC_OFFSET 16 +#define AT91_PMC_AUDIO_PLL_QDPMC_MASK (0x7f << AT91_PMC_AUDIO_PLL_QDPMC_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPMC(n) ((n) << AT91_PMC_AUDIO_PLL_QDPMC_OFFSET) + +#define AT91_PMC_AUDIO_PLL1 0x150 +#define AT91_PMC_AUDIO_PLL_FRACR_MASK 0x3fffff +#define AT91_PMC_AUDIO_PLL_QDPAD_OFFSET 24 +#define AT91_PMC_AUDIO_PLL_QDPAD_MASK (0x7f << AT91_PMC_AUDIO_PLL_QDPAD_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD(n) ((n) << AT91_PMC_AUDIO_PLL_QDPAD_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD_DIV_OFFSET AT91_PMC_AUDIO_PLL_QDPAD_OFFSET +#define AT91_PMC_AUDIO_PLL_QDPAD_DIV_MASK (0x3 << AT91_PMC_AUDIO_PLL_QDPAD_DIV_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD_DIV(n) ((n) << AT91_PMC_AUDIO_PLL_QDPAD_DIV_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_OFFSET 26 +#define AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_MAX 0x1f +#define AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_MASK (AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_MAX << AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_OFFSET) +#define AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV(n) ((n) << AT91_PMC_AUDIO_PLL_QDPAD_EXTDIV_OFFSET) + #endif -- cgit v1.2.3 From 7c89717f82bd305e3102963485f3da160d11bcf6 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Sun, 27 Aug 2017 22:34:53 -0700 Subject: remoteproc: Introduce rproc handle accessor for children In certain circumstances rpmsg devices needs to acquire a handle to the ancestor remoteproc instance, e.g. to invoke rproc_report_crash() when a fatal error is detected. Introduce an interface that walks the device tree in search for a remoteproc instance and return this. Tested-by: Suman Anna Signed-off-by: Bjorn Andersson --- include/linux/remoteproc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 81da49564ff4..44e630eb3d94 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -510,6 +510,8 @@ struct rproc_vdev { }; struct rproc *rproc_get_by_phandle(phandle phandle); +struct rproc *rproc_get_by_child(struct device *dev); + struct rproc *rproc_alloc(struct device *dev, const char *name, const struct rproc_ops *ops, const char *firmware, int len); -- cgit v1.2.3 From b37e88407c1d78f157778d73427cd7e9e1d6369d Mon Sep 17 00:00:00 2001 From: Ivan Delalande Date: Thu, 31 Aug 2017 09:59:38 -0700 Subject: inet_diag: allow protocols to provide additional data Extend inet_diag_handler to allow individual protocols to report additional data on INET_DIAG_INFO through idiag_get_aux. The size can be dynamic and is computed by idiag_get_aux_size. Signed-off-by: Ivan Delalande Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/inet_diag.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h index 65da430e260f..ee251c585854 100644 --- a/include/linux/inet_diag.h +++ b/include/linux/inet_diag.h @@ -25,6 +25,13 @@ struct inet_diag_handler { struct inet_diag_msg *r, void *info); + int (*idiag_get_aux)(struct sock *sk, + bool net_admin, + struct sk_buff *skb); + + size_t (*idiag_get_aux_size)(struct sock *sk, + bool net_admin); + int (*destroy)(struct sk_buff *in_skb, const struct inet_diag_req_v2 *req); -- cgit v1.2.3 From c1d1b437816f0afa99202be3cb650c9d174667bc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 31 Aug 2017 16:48:22 -0700 Subject: net: convert (struct ubuf_info)->refcnt to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. v2: added the change in drivers/vhost/net.c as spotted by Willem. Signed-off-by: Eric Dumazet Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f93cc01064cb..f751f3b93039 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -22,6 +22,7 @@ #include #include #include +#include #include #include @@ -456,7 +457,7 @@ struct ubuf_info { u32 bytelen; }; }; - atomic_t refcnt; + refcount_t refcnt; struct mmpin { struct user_struct *user; @@ -472,7 +473,7 @@ struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, static inline void sock_zerocopy_get(struct ubuf_info *uarg) { - atomic_inc(&uarg->refcnt); + refcount_inc(&uarg->refcnt); } void sock_zerocopy_put(struct ubuf_info *uarg); -- cgit v1.2.3 From 604acb193b8383a3774673c324e576e4c6b4ffcd Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Mon, 5 Jun 2017 11:17:20 +0300 Subject: net/mlx5e: Refactor data-path lro header function Refactor function mlx5e_lro_update_hdr() to reduce number of branches. Signed-off-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 3c7442b56460..7031d655ec32 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -709,7 +709,7 @@ static inline int mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) return (cqe->op_own >> 2) & 0x3; } -static inline int get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) +static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { return (cqe->lro_tcppsh_abort_dupack >> 6) & 1; } -- cgit v1.2.3 From b9047726386bb538cf5e4f52a9f04eb556eebc67 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 2 Aug 2017 19:51:11 -0700 Subject: ipc: mqueue: Replace timespec with timespec64 struct timespec is not y2038 safe. Replace all uses of timespec by y2038 safe struct timespec64. Even though timespec is used here to represent timeouts, replace these with timespec64 so that it facilitates in verification by creating a y2038 safe kernel image that is free of timespec. The syscall interfaces themselves are not changed as part of the patch. They will be part of a different series. Signed-off-by: Deepa Dinamani Cc: Paul Moore Cc: Richard Guy Briggs Reviewed-by: Richard Guy Briggs Reviewed-by: Arnd Bergmann Acked-by: Paul Moore Signed-off-by: Al Viro --- include/linux/audit.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 2150bdccfbab..74d4d4e8e3db 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -351,7 +351,7 @@ extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); -extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout); +extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, @@ -412,7 +412,7 @@ static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } -static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec *abs_timeout) +static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); @@ -549,7 +549,7 @@ static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, - const struct timespec *abs_timeout) + const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) -- cgit v1.2.3 From 50578ea97a2a352c109bd1657e667b212faf2cbb Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 2 Aug 2017 19:51:12 -0700 Subject: ipc: msg: Make msg_queue timestamps y2038 safe time_t is not y2038 safe. Replace all uses of time_t by y2038 safe time64_t. Similarly, replace the calls to get_seconds() with y2038 safe ktime_get_real_seconds(). Note that this preserves fast access on 64 bit systems, but 32 bit systems need sequence counters. The syscall interfaces themselves are not changed as part of the patch. They will be part of a different series. Signed-off-by: Deepa Dinamani Reviewed-by: Arnd Bergmann Signed-off-by: Al Viro --- include/linux/msg.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msg.h b/include/linux/msg.h index 4e5ec3cbf464..05115342daa3 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -2,6 +2,7 @@ #define _LINUX_MSG_H #include +#include #include /* one msg_msg structure for each message */ @@ -17,9 +18,9 @@ struct msg_msg { /* one msq_queue structure for each present queue on the system */ struct msg_queue { struct kern_ipc_perm q_perm; - time_t q_stime; /* last msgsnd time */ - time_t q_rtime; /* last msgrcv time */ - time_t q_ctime; /* last change time */ + time64_t q_stime; /* last msgsnd time */ + time64_t q_rtime; /* last msgrcv time */ + time64_t q_ctime; /* last change time */ unsigned long q_cbytes; /* current number of bytes on queue */ unsigned long q_qnum; /* number of messages in queue */ unsigned long q_qbytes; /* max number of bytes on queue */ -- cgit v1.2.3 From e54d02b23c5eed3aa0ffe54e659dfe1c9084c262 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 2 Aug 2017 19:51:13 -0700 Subject: ipc: sem: Make sem_array timestamps y2038 safe time_t is not y2038 safe. Replace all uses of time_t by y2038 safe time64_t. Similarly, replace the calls to get_seconds() with y2038 safe ktime_get_real_seconds(). Note that this preserves fast access on 64 bit systems, but 32 bit systems need sequence counters. The syscall interface themselves are not changed as part of the patch. They will be part of a different series. Signed-off-by: Deepa Dinamani Reviewed-by: Arnd Bergmann Signed-off-by: Al Viro --- include/linux/sem.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sem.h b/include/linux/sem.h index be5cf2ea14ad..867f86f1a20b 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -4,6 +4,7 @@ #include #include #include +#include #include struct task_struct; @@ -30,7 +31,7 @@ struct sem { /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ - time_t sem_ctime; /* create/last semctl() time */ + time64_t sem_ctime; /* create/last semctl() time */ struct list_head pending_alter; /* pending operations */ /* that alter the array */ struct list_head pending_const; /* pending complex operations */ -- cgit v1.2.3 From 7ff2819e8dd5b528887dfbe4ff395f5d2142edff Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 2 Aug 2017 19:51:14 -0700 Subject: ipc: shm: Make shmid_kernel timestamps y2038 safe time_t is not y2038 safe. Replace all uses of time_t by y2038 safe time64_t. Similarly, replace the calls to get_seconds() with y2038 safe ktime_get_real_seconds(). Note that this preserves fast access on 64 bit systems, but 32 bit systems need sequence counters. The syscall interfaces themselves are not changed as part of the patch. They will be part of a different series. Signed-off-by: Deepa Dinamani Reviewed-by: Arnd Bergmann Signed-off-by: Al Viro --- include/linux/shm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shm.h b/include/linux/shm.h index 04e881829625..7bb897b25309 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -12,9 +12,9 @@ struct shmid_kernel /* private to the kernel */ struct file *shm_file; unsigned long shm_nattch; unsigned long shm_segsz; - time_t shm_atim; - time_t shm_dtim; - time_t shm_ctim; + time64_t shm_atim; + time64_t shm_dtim; + time64_t shm_ctim; pid_t shm_cprid; pid_t shm_lprid; struct user_struct *mlock_user; -- cgit v1.2.3 From aaed2dd8a31359e5767ee099ecbb078d55be4d29 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Wed, 2 Aug 2017 19:51:15 -0700 Subject: utimes: Make utimes y2038 safe struct timespec is not y2038 safe on 32 bit machines. Replace timespec with y2038 safe struct timespec64. Note that the patch only changes the internals without modifying the syscall interfaces. This will be part of a separate series. Signed-off-by: Deepa Dinamani Reviewed-by: Arnd Bergmann Signed-off-by: Al Viro --- include/linux/time.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/time.h b/include/linux/time.h index 4abb32d4c6b8..3d0cd017f0d7 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -178,7 +178,7 @@ extern int do_setitimer(int which, struct itimerval *value, struct itimerval *ovalue); extern int do_getitimer(int which, struct itimerval *value); -extern long do_utimes(int dfd, const char __user *filename, struct timespec *times, int flags); +extern long do_utimes(int dfd, const char __user *filename, struct timespec64 *times, int flags); /* * Similar to the struct tm in userspace , but it needs to be here so -- cgit v1.2.3 From bea74641e3786d51dcf1175527cc1781420961c9 Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Fri, 18 Aug 2017 20:58:59 +0200 Subject: netfilter: xt_hashlimit: add rate match mode This patch adds a new feature to hashlimit that allows matching on the current packet/byte rate without rate limiting. This can be enabled with a new flag --hashlimit-rate-match. The match returns true if the current rate of packets is above/below the user specified value. The main difference between the existing algorithm and the new one is that the existing algorithm rate-limits the flow whereas the new algorithm does not. Instead it *classifies* the flow based on whether it is above or below a certain rate. I will demonstrate this with an example below. Let us assume this rule: iptables -A INPUT -m hashlimit --hashlimit-above 10/s -j new_chain If the packet rate is 15/s, the existing algorithm would ACCEPT 10 packets every second and send 5 packets to "new_chain". But with the new algorithm, as long as the rate of 15/s is sustained, all packets will continue to match and every packet is sent to new_chain. This new functionality will let us classify different flows based on their current rate, so that further decisions can be made on them based on what the current rate is. This is how the new algorithm works: We divide time into intervals of 1 (sec/min/hour) as specified by the user. We keep track of the number of packets/bytes processed in the current interval. After each interval we reset the counter to 0. When we receive a packet for match, we look at the packet rate during the current interval and the previous interval to make a decision: if [ prev_rate < user and cur_rate < user ] return Below else return Above Where cur_rate is the number of packets/bytes seen in the current interval, prev is the number of packets/bytes seen in the previous interval and 'user' is the rate specified by the user. We also provide flexibility to the user for choosing the time interval using the option --hashilmit-interval. For example the user can keep a low rate like x/hour but still keep the interval as small as 1 second. To preserve backwards compatibility we have to add this feature in a new revision, so I've created revision 3 for hashlimit. The two new options we add are: --hashlimit-rate-match --hashlimit-rate-interval I have updated the help text to add these new options. Also added a few tests for the new options. Suggested-by: Igor Lubashev Reviewed-by: Josh Hunt Signed-off-by: Vishwanath Pai Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/xt_hashlimit.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/xt_hashlimit.h b/include/linux/netfilter/xt_hashlimit.h index 074790c0cf74..0fc458bde80b 100644 --- a/include/linux/netfilter/xt_hashlimit.h +++ b/include/linux/netfilter/xt_hashlimit.h @@ -5,5 +5,6 @@ #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ XT_HASHLIMIT_HASH_SIP | XT_HASHLIMIT_HASH_SPT | \ - XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES) + XT_HASHLIMIT_INVERT | XT_HASHLIMIT_BYTES |\ + XT_HASHLIMIT_RATE_MATCH) #endif /*_XT_HASHLIMIT_H*/ -- cgit v1.2.3 From 095a7e388b5fbf8958686a90a04fe9387f6aa50b Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:12 -0700 Subject: irqchip: mips-gic: Remove counter access functions The MIPS GIC clocksource driver is no longer using the accessor functions provided by the irqchip driver, so remove them. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17022/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 2b0e56619e53..c9e1c993cf5b 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -40,11 +40,6 @@ #define GIC_SH_CONFIG_OFS 0x0000 -/* Shared Global Counter */ -#define GIC_SH_COUNTER_31_00_OFS 0x0010 -/* 64-bit counter register for CM3 */ -#define GIC_SH_COUNTER_OFS GIC_SH_COUNTER_31_00_OFS -#define GIC_SH_COUNTER_63_32_OFS 0x0014 #define GIC_SH_REVISIONID_OFS 0x0020 /* Convert an interrupt number to a byte offset/bit for multi-word registers */ @@ -107,10 +102,6 @@ #define GIC_VPE_WD_CONFIG0_OFS 0x0090 #define GIC_VPE_WD_COUNT0_OFS 0x0094 #define GIC_VPE_WD_INITIAL0_OFS 0x0098 -#define GIC_VPE_COMPARE_LO_OFS 0x00a0 -/* 64-bit Compare register on CM3 */ -#define GIC_VPE_COMPARE_OFS GIC_VPE_COMPARE_LO_OFS -#define GIC_VPE_COMPARE_HI_OFS 0x00a4 #define GIC_VPE_EIC_SHADOW_SET_BASE_OFS 0x0100 #define GIC_VPE_EIC_SS(intr) (4 * (intr)) @@ -128,12 +119,6 @@ #define GIC_UMV_SH_COUNTER_63_32_OFS 0x0004 /* Masks */ -#define GIC_SH_CONFIG_COUNTSTOP_SHF 28 -#define GIC_SH_CONFIG_COUNTSTOP_MSK (MSK(1) << GIC_SH_CONFIG_COUNTSTOP_SHF) - -#define GIC_SH_CONFIG_COUNTBITS_SHF 24 -#define GIC_SH_CONFIG_COUNTBITS_MSK (MSK(4) << GIC_SH_CONFIG_COUNTBITS_SHF) - #define GIC_SH_CONFIG_NUMINTRS_SHF 16 #define GIC_SH_CONFIG_NUMINTRS_MSK (MSK(8) << GIC_SH_CONFIG_NUMINTRS_SHF) @@ -258,13 +243,6 @@ extern unsigned int gic_present; extern void gic_init(unsigned long gic_base_addr, unsigned long gic_addrspace_size, unsigned int cpu_vec, unsigned int irqbase); -extern u64 gic_read_count(void); -extern unsigned int gic_get_count_width(void); -extern u64 gic_read_compare(void); -extern void gic_write_compare(u64 cnt); -extern void gic_write_cpu_compare(u64 cnt, int cpu); -extern void gic_start_count(void); -extern void gic_stop_count(void); extern int gic_get_c0_compare_int(void); extern int gic_get_c0_perfcount_int(void); extern int gic_get_c0_fdc_int(void); -- cgit v1.2.3 From 9762d2e6d329a500dc6c07156e3c56aab3992471 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:14 -0700 Subject: irqchip: mips-gic: Remove gic_read_local_vp_id() Nothing needs gic_read_local_vp_id() any longer, so remove the dead code. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17024/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index c9e1c993cf5b..29453bdc06e2 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -98,7 +98,6 @@ #define GIC_VPE_SWINT0_MAP_OFS 0x0054 #define GIC_VPE_SWINT1_MAP_OFS 0x0058 #define GIC_VPE_OTHER_ADDR_OFS 0x0080 -#define GIC_VP_IDENT_OFS 0x0088 #define GIC_VPE_WD_CONFIG0_OFS 0x0090 #define GIC_VPE_WD_COUNT0_OFS 0x0094 #define GIC_VPE_WD_INITIAL0_OFS 0x0098 @@ -197,10 +196,6 @@ #define GIC_VPE_SMASK_FDC_SHF 6 #define GIC_VPE_SMASK_FDC_MSK (MSK(1) << GIC_VPE_SMASK_FDC_SHF) -/* GIC_VP_IDENT fields */ -#define GIC_VP_IDENT_VCNUM_SHF 0 -#define GIC_VP_IDENT_VCNUM_MSK (MSK(6) << GIC_VP_IDENT_VCNUM_SHF) - /* GIC nomenclature for Core Interrupt Pins. */ #define GIC_CPU_INT0 0 /* Core Interrupt 2 */ #define GIC_CPU_INT1 1 /* . */ @@ -260,16 +255,4 @@ static inline int gic_get_usm_range(struct resource *gic_usm_res) #endif /* CONFIG_MIPS_GIC */ -/** - * gic_read_local_vp_id() - read the local VPs VCNUM - * - * Read the VCNUM of the local VP from the GIC_VP_IDENT register and - * return it to the caller. This ID should be used to refer to the VP - * via the GICs VP-other region, or when calculating an offset to a - * bit representing the VP in interrupt masks. - * - * Return: The VCNUM value for the local VP. - */ -extern unsigned gic_read_local_vp_id(void); - #endif /* __LINUX_IRQCHIP_MIPS_GIC_H */ -- cgit v1.2.3 From e98fcb2a8cc003c37c24713d2303667a8f624a30 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:16 -0700 Subject: irqchip: mips-gic: Simplify shared interrupt pending/mask reads Simplify the reads of the bitmaps indicating pending & masked interrupts in gic_handle_shared_int() using the __ioread32_copy() & __ioread64_copy() helper functions. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17026/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 29453bdc06e2..835e25506660 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -68,12 +68,6 @@ #define GIC_SH_RMASK_OFS 0x0300 #define GIC_SH_SMASK_OFS 0x0380 -/* Global Interrupt Mask Register (RO) - Bit Set == Interrupt enabled */ -#define GIC_SH_MASK_OFS 0x0400 - -/* Pending Global Interrupts (RO) */ -#define GIC_SH_PEND_OFS 0x0480 - /* Maps Interrupt X to a Pin */ #define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS 0x0500 #define GIC_SH_MAP_TO_PIN(intr) (4 * (intr)) -- cgit v1.2.3 From a0dc5cb5e31bdbcf1f1dddf62a62d06d6b82d53a Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:17 -0700 Subject: irqchip: mips-gic: Simplify gic_local_irq_domain_map() Simplify gic_local_irq_domain_map() by: - Moving the check for invalid IRQs outside of the loop. - Moving the decision about whether to use gic_cpu_pin or timer_cpu_pin outside of the loop. - Using the new write_gic_vo_map() accessor function to avoid the need to handle each map register separately. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17027/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 835e25506660..1342b17b6812 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -84,13 +84,7 @@ #define GIC_VPE_MASK_OFS 0x0008 #define GIC_VPE_RMASK_OFS 0x000c #define GIC_VPE_SMASK_OFS 0x0010 -#define GIC_VPE_WD_MAP_OFS 0x0040 -#define GIC_VPE_COMPARE_MAP_OFS 0x0044 #define GIC_VPE_TIMER_MAP_OFS 0x0048 -#define GIC_VPE_FDC_MAP_OFS 0x004c -#define GIC_VPE_PERFCTR_MAP_OFS 0x0050 -#define GIC_VPE_SWINT0_MAP_OFS 0x0054 -#define GIC_VPE_SWINT1_MAP_OFS 0x0058 #define GIC_VPE_OTHER_ADDR_OFS 0x0080 #define GIC_VPE_WD_CONFIG0_OFS 0x0090 #define GIC_VPE_WD_COUNT0_OFS 0x0094 -- cgit v1.2.3 From 87554b0ef3884143563e090375269730780c6617 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:18 -0700 Subject: irqchip: mips-gic: Drop gic_(re)set_mask() functions The gic_set_mask() & gic_reset_mask() functions are now no more convenient to call than the write_gic_smask() or write_gic_rmask() accessor functions. Remove the layer of abstraction. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17028/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 1342b17b6812..8160cc8b677d 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -64,10 +64,6 @@ /* Set/Clear corresponding bit in Edge Detect Register */ #define GIC_SH_WEDGE_OFS 0x0280 -/* Mask manipulation */ -#define GIC_SH_RMASK_OFS 0x0300 -#define GIC_SH_SMASK_OFS 0x0380 - /* Maps Interrupt X to a Pin */ #define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS 0x0500 #define GIC_SH_MAP_TO_PIN(intr) (4 * (intr)) -- cgit v1.2.3 From 80e5f9c9e295b08c5c588083a4ad35e1e5f78731 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:19 -0700 Subject: irqchip: mips-gic: Remove gic_set_polarity() Remove the gic_set_polarity() function in favour of using the new change_gic_pol() accessor function which provides equivalent functionality. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17029/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 8160cc8b677d..960e49a64e7a 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -14,8 +14,6 @@ #define GIC_MAX_INTRS 256 /* Constants */ -#define GIC_POL_POS 1 -#define GIC_POL_NEG 0 #define GIC_TRIG_EDGE 1 #define GIC_TRIG_LEVEL 0 #define GIC_TRIG_DUAL_ENABLE 1 @@ -52,9 +50,6 @@ }) #define GIC_INTR_BIT(intr) ((intr) % (mips_cm_is64 ? 64 : 32)) -/* Polarity : Reset Value is always 0 */ -#define GIC_SH_SET_POLARITY_OFS 0x0100 - /* Triggering : Reset Value is always 0 */ #define GIC_SH_SET_TRIGGER_OFS 0x0180 -- cgit v1.2.3 From 471aa962a6acc19a990e20fa3846db40e62120cc Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:20 -0700 Subject: irqchip: mips-gic: Remove gic_set_trigger() Remove the gic_set_trigger() function in favour of using the new change_gic_trig() accessor function which provides equivalent functionality. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17030/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 960e49a64e7a..2e9f0c43d425 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -14,8 +14,6 @@ #define GIC_MAX_INTRS 256 /* Constants */ -#define GIC_TRIG_EDGE 1 -#define GIC_TRIG_LEVEL 0 #define GIC_TRIG_DUAL_ENABLE 1 #define GIC_TRIG_DUAL_DISABLE 0 @@ -50,9 +48,6 @@ }) #define GIC_INTR_BIT(intr) ((intr) % (mips_cm_is64 ? 64 : 32)) -/* Triggering : Reset Value is always 0 */ -#define GIC_SH_SET_TRIGGER_OFS 0x0180 - /* Dual edge triggering : Reset Value is always 0 */ #define GIC_SH_SET_DUAL_OFS 0x0200 -- cgit v1.2.3 From c26ba670cdb84e0556436be7bf68a75a1d4f4d76 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:21 -0700 Subject: irqchip: mips-gic: Remove gic_set_dual_edge() Remove the gic_set_dual_edge() function in favour of using the new change_gic_dual() accessor function which provides equivalent functionality. This also allows us to remove the gic_update_bits() function which gic_set_dual_edge() was the last user of, along with the GIC_INTR_OFS() & GIC_INTR_BIT() macros. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17031/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 2e9f0c43d425..bd348fc9db18 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -13,10 +13,6 @@ #define GIC_MAX_INTRS 256 -/* Constants */ -#define GIC_TRIG_DUAL_ENABLE 1 -#define GIC_TRIG_DUAL_DISABLE 0 - #define MSK(n) ((1 << (n)) - 1) /* Accessors */ @@ -38,19 +34,6 @@ #define GIC_SH_REVISIONID_OFS 0x0020 -/* Convert an interrupt number to a byte offset/bit for multi-word registers */ -#define GIC_INTR_OFS(intr) ({ \ - unsigned bits = mips_cm_is64 ? 64 : 32; \ - unsigned reg_idx = (intr) / bits; \ - unsigned reg_width = bits / 8; \ - \ - reg_idx * reg_width; \ -}) -#define GIC_INTR_BIT(intr) ((intr) % (mips_cm_is64 ? 64 : 32)) - -/* Dual edge triggering : Reset Value is always 0 */ -#define GIC_SH_SET_DUAL_OFS 0x0200 - /* Set/Clear corresponding bit in Edge Detect Register */ #define GIC_SH_WEDGE_OFS 0x0280 -- cgit v1.2.3 From d3e8cf44792d60047ba45036abfc38ab414e49e5 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:22 -0700 Subject: irqchip: mips-gic: Remove gic_map_to_pin() Remove the gic_map_to_pin() function in favour of using the new write_gic_map_pin() accessor function which isn't any more complex to use & allows us to drop a level of abstraction. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17032/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index bd348fc9db18..dea79a7a54cc 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -37,10 +37,6 @@ /* Set/Clear corresponding bit in Edge Detect Register */ #define GIC_SH_WEDGE_OFS 0x0280 -/* Maps Interrupt X to a Pin */ -#define GIC_SH_INTR_MAP_TO_PIN_BASE_OFS 0x0500 -#define GIC_SH_MAP_TO_PIN(intr) (4 * (intr)) - /* Maps Interrupt X to a VPE */ #define GIC_SH_INTR_MAP_TO_VPE_BASE_OFS 0x2000 #define GIC_SH_MAP_TO_VPE_REG_OFF(intr, vpe) \ @@ -84,12 +80,6 @@ #define GIC_SH_WEDGE_SET(intr) ((intr) | (0x1 << 31)) #define GIC_SH_WEDGE_CLR(intr) ((intr) & ~(0x1 << 31)) -#define GIC_MAP_TO_PIN_SHF 31 -#define GIC_MAP_TO_PIN_MSK (MSK(1) << GIC_MAP_TO_PIN_SHF) -#define GIC_MAP_TO_NMI_SHF 30 -#define GIC_MAP_TO_NMI_MSK (MSK(1) << GIC_MAP_TO_NMI_SHF) -#define GIC_MAP_TO_YQ_SHF 29 -#define GIC_MAP_TO_YQ_MSK (MSK(1) << GIC_MAP_TO_YQ_SHF) #define GIC_MAP_SHF 0 #define GIC_MAP_MSK (MSK(6) << GIC_MAP_SHF) -- cgit v1.2.3 From 0efe3cbf1504309bf088f74eb627d0987f67e934 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:23 -0700 Subject: irqchip: mips-gic: Remove gic_map_to_vpe() Remove the gic_map_to_vpe() function in favour of using the new write_gic_map_vp() accessor function which isn't any more complex to use & allows us to drop a level of abstraction. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17033/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index dea79a7a54cc..ad8b216b6056 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -37,12 +37,6 @@ /* Set/Clear corresponding bit in Edge Detect Register */ #define GIC_SH_WEDGE_OFS 0x0280 -/* Maps Interrupt X to a VPE */ -#define GIC_SH_INTR_MAP_TO_VPE_BASE_OFS 0x2000 -#define GIC_SH_MAP_TO_VPE_REG_OFF(intr, vpe) \ - ((32 * (intr)) + (((vpe) / 32) * 4)) -#define GIC_SH_MAP_TO_VPE_REG_BIT(vpe) (1 << ((vpe) % 32)) - /* Register Map for Local Section */ #define GIC_VPE_CTL_OFS 0x0000 #define GIC_VPE_PEND_OFS 0x0004 -- cgit v1.2.3 From 3680746abd87e733ec836025115580562b3dcb47 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:24 -0700 Subject: irqchip: mips-gic: Convert remaining shared reg access to new accessors Convert the remaining accesses to registers in the GIC shared register block to use the new accessor functions provided by asm/mips-gic.h, resulting in code which is often shorter & easier to read. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17034/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index ad8b216b6056..f0a60770d775 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -19,8 +19,6 @@ #define GIC_REG(segment, offset) (segment##_##SECTION_OFS + offset##_##OFS) /* GIC Address Space */ -#define SHARED_SECTION_OFS 0x0000 -#define SHARED_SECTION_SIZE 0x8000 #define VPE_LOCAL_SECTION_OFS 0x8000 #define VPE_LOCAL_SECTION_SIZE 0x4000 #define VPE_OTHER_SECTION_OFS 0xc000 @@ -28,15 +26,6 @@ #define USM_VISIBLE_SECTION_OFS 0x10000 #define USM_VISIBLE_SECTION_SIZE 0x10000 -/* Register Map for Shared Section */ - -#define GIC_SH_CONFIG_OFS 0x0000 - -#define GIC_SH_REVISIONID_OFS 0x0020 - -/* Set/Clear corresponding bit in Edge Detect Register */ -#define GIC_SH_WEDGE_OFS 0x0280 - /* Register Map for Local Section */ #define GIC_VPE_CTL_OFS 0x0000 #define GIC_VPE_PEND_OFS 0x0004 @@ -65,15 +54,6 @@ #define GIC_UMV_SH_COUNTER_63_32_OFS 0x0004 /* Masks */ -#define GIC_SH_CONFIG_NUMINTRS_SHF 16 -#define GIC_SH_CONFIG_NUMINTRS_MSK (MSK(8) << GIC_SH_CONFIG_NUMINTRS_SHF) - -#define GIC_SH_CONFIG_NUMVPES_SHF 0 -#define GIC_SH_CONFIG_NUMVPES_MSK (MSK(8) << GIC_SH_CONFIG_NUMVPES_SHF) - -#define GIC_SH_WEDGE_SET(intr) ((intr) | (0x1 << 31)) -#define GIC_SH_WEDGE_CLR(intr) ((intr) & ~(0x1 << 31)) - #define GIC_MAP_SHF 0 #define GIC_MAP_MSK (MSK(6) << GIC_MAP_SHF) -- cgit v1.2.3 From 9da3c64589e4eae68631b1b5ed31c586be6ad923 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:25 -0700 Subject: irqchip: mips-gic: Convert local int mask access to new accessors Use the new accessor functions provided by asm/mips-gic.h to access masks controlling local interrupts, resulting in code which is often shorter & easier to read. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17035/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 52 ---------------------------------------- 1 file changed, 52 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index f0a60770d775..011698962a8d 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -28,10 +28,6 @@ /* Register Map for Local Section */ #define GIC_VPE_CTL_OFS 0x0000 -#define GIC_VPE_PEND_OFS 0x0004 -#define GIC_VPE_MASK_OFS 0x0008 -#define GIC_VPE_RMASK_OFS 0x000c -#define GIC_VPE_SMASK_OFS 0x0010 #define GIC_VPE_TIMER_MAP_OFS 0x0048 #define GIC_VPE_OTHER_ADDR_OFS 0x0080 #define GIC_VPE_WD_CONFIG0_OFS 0x0090 @@ -69,54 +65,6 @@ #define GIC_VPE_CTL_EIC_MODE_SHF 0 #define GIC_VPE_CTL_EIC_MODE_MSK (MSK(1) << GIC_VPE_CTL_EIC_MODE_SHF) -/* GIC_VPE_PEND Masks */ -#define GIC_VPE_PEND_WD_SHF 0 -#define GIC_VPE_PEND_WD_MSK (MSK(1) << GIC_VPE_PEND_WD_SHF) -#define GIC_VPE_PEND_CMP_SHF 1 -#define GIC_VPE_PEND_CMP_MSK (MSK(1) << GIC_VPE_PEND_CMP_SHF) -#define GIC_VPE_PEND_TIMER_SHF 2 -#define GIC_VPE_PEND_TIMER_MSK (MSK(1) << GIC_VPE_PEND_TIMER_SHF) -#define GIC_VPE_PEND_PERFCOUNT_SHF 3 -#define GIC_VPE_PEND_PERFCOUNT_MSK (MSK(1) << GIC_VPE_PEND_PERFCOUNT_SHF) -#define GIC_VPE_PEND_SWINT0_SHF 4 -#define GIC_VPE_PEND_SWINT0_MSK (MSK(1) << GIC_VPE_PEND_SWINT0_SHF) -#define GIC_VPE_PEND_SWINT1_SHF 5 -#define GIC_VPE_PEND_SWINT1_MSK (MSK(1) << GIC_VPE_PEND_SWINT1_SHF) -#define GIC_VPE_PEND_FDC_SHF 6 -#define GIC_VPE_PEND_FDC_MSK (MSK(1) << GIC_VPE_PEND_FDC_SHF) - -/* GIC_VPE_RMASK Masks */ -#define GIC_VPE_RMASK_WD_SHF 0 -#define GIC_VPE_RMASK_WD_MSK (MSK(1) << GIC_VPE_RMASK_WD_SHF) -#define GIC_VPE_RMASK_CMP_SHF 1 -#define GIC_VPE_RMASK_CMP_MSK (MSK(1) << GIC_VPE_RMASK_CMP_SHF) -#define GIC_VPE_RMASK_TIMER_SHF 2 -#define GIC_VPE_RMASK_TIMER_MSK (MSK(1) << GIC_VPE_RMASK_TIMER_SHF) -#define GIC_VPE_RMASK_PERFCNT_SHF 3 -#define GIC_VPE_RMASK_PERFCNT_MSK (MSK(1) << GIC_VPE_RMASK_PERFCNT_SHF) -#define GIC_VPE_RMASK_SWINT0_SHF 4 -#define GIC_VPE_RMASK_SWINT0_MSK (MSK(1) << GIC_VPE_RMASK_SWINT0_SHF) -#define GIC_VPE_RMASK_SWINT1_SHF 5 -#define GIC_VPE_RMASK_SWINT1_MSK (MSK(1) << GIC_VPE_RMASK_SWINT1_SHF) -#define GIC_VPE_RMASK_FDC_SHF 6 -#define GIC_VPE_RMASK_FDC_MSK (MSK(1) << GIC_VPE_RMASK_FDC_SHF) - -/* GIC_VPE_SMASK Masks */ -#define GIC_VPE_SMASK_WD_SHF 0 -#define GIC_VPE_SMASK_WD_MSK (MSK(1) << GIC_VPE_SMASK_WD_SHF) -#define GIC_VPE_SMASK_CMP_SHF 1 -#define GIC_VPE_SMASK_CMP_MSK (MSK(1) << GIC_VPE_SMASK_CMP_SHF) -#define GIC_VPE_SMASK_TIMER_SHF 2 -#define GIC_VPE_SMASK_TIMER_MSK (MSK(1) << GIC_VPE_SMASK_TIMER_SHF) -#define GIC_VPE_SMASK_PERFCNT_SHF 3 -#define GIC_VPE_SMASK_PERFCNT_MSK (MSK(1) << GIC_VPE_SMASK_PERFCNT_SHF) -#define GIC_VPE_SMASK_SWINT0_SHF 4 -#define GIC_VPE_SMASK_SWINT0_MSK (MSK(1) << GIC_VPE_SMASK_SWINT0_SHF) -#define GIC_VPE_SMASK_SWINT1_SHF 5 -#define GIC_VPE_SMASK_SWINT1_MSK (MSK(1) << GIC_VPE_SMASK_SWINT1_SHF) -#define GIC_VPE_SMASK_FDC_SHF 6 -#define GIC_VPE_SMASK_FDC_MSK (MSK(1) << GIC_VPE_SMASK_FDC_SHF) - /* GIC nomenclature for Core Interrupt Pins. */ #define GIC_CPU_INT0 0 /* Core Interrupt 2 */ #define GIC_CPU_INT1 1 /* . */ -- cgit v1.2.3 From 0d0cf58cd6814ed63deb67fc5f4c27ad725075b1 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:26 -0700 Subject: irqchip: mips-gic: Convert remaining local reg access to new accessors Convert the remaining accesses to registers in the GIC VP-local & VP-other register blocks to use the new accessor functions provided by asm/mips-gic.h, resulting in code which is often shorter & easier to read. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17036/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 44 ---------------------------------------- 1 file changed, 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 011698962a8d..b7a3ce1da9a7 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -13,58 +13,14 @@ #define GIC_MAX_INTRS 256 -#define MSK(n) ((1 << (n)) - 1) - -/* Accessors */ -#define GIC_REG(segment, offset) (segment##_##SECTION_OFS + offset##_##OFS) - /* GIC Address Space */ -#define VPE_LOCAL_SECTION_OFS 0x8000 -#define VPE_LOCAL_SECTION_SIZE 0x4000 -#define VPE_OTHER_SECTION_OFS 0xc000 -#define VPE_OTHER_SECTION_SIZE 0x4000 #define USM_VISIBLE_SECTION_OFS 0x10000 #define USM_VISIBLE_SECTION_SIZE 0x10000 -/* Register Map for Local Section */ -#define GIC_VPE_CTL_OFS 0x0000 -#define GIC_VPE_TIMER_MAP_OFS 0x0048 -#define GIC_VPE_OTHER_ADDR_OFS 0x0080 -#define GIC_VPE_WD_CONFIG0_OFS 0x0090 -#define GIC_VPE_WD_COUNT0_OFS 0x0094 -#define GIC_VPE_WD_INITIAL0_OFS 0x0098 - -#define GIC_VPE_EIC_SHADOW_SET_BASE_OFS 0x0100 -#define GIC_VPE_EIC_SS(intr) (4 * (intr)) - -#define GIC_VPE_EIC_VEC_BASE_OFS 0x0800 -#define GIC_VPE_EIC_VEC(intr) (4 * (intr)) - -#define GIC_VPE_TENABLE_NMI_OFS 0x1000 -#define GIC_VPE_TENABLE_YQ_OFS 0x1004 -#define GIC_VPE_TENABLE_INT_31_0_OFS 0x1080 -#define GIC_VPE_TENABLE_INT_63_32_OFS 0x1084 - /* User Mode Visible Section Register Map */ #define GIC_UMV_SH_COUNTER_31_00_OFS 0x0000 #define GIC_UMV_SH_COUNTER_63_32_OFS 0x0004 -/* Masks */ -#define GIC_MAP_SHF 0 -#define GIC_MAP_MSK (MSK(6) << GIC_MAP_SHF) - -/* GIC_VPE_CTL Masks */ -#define GIC_VPE_CTL_FDC_RTBL_SHF 4 -#define GIC_VPE_CTL_FDC_RTBL_MSK (MSK(1) << GIC_VPE_CTL_FDC_RTBL_SHF) -#define GIC_VPE_CTL_SWINT_RTBL_SHF 3 -#define GIC_VPE_CTL_SWINT_RTBL_MSK (MSK(1) << GIC_VPE_CTL_SWINT_RTBL_SHF) -#define GIC_VPE_CTL_PERFCNT_RTBL_SHF 2 -#define GIC_VPE_CTL_PERFCNT_RTBL_MSK (MSK(1) << GIC_VPE_CTL_PERFCNT_RTBL_SHF) -#define GIC_VPE_CTL_TIMER_RTBL_SHF 1 -#define GIC_VPE_CTL_TIMER_RTBL_MSK (MSK(1) << GIC_VPE_CTL_TIMER_RTBL_SHF) -#define GIC_VPE_CTL_EIC_MODE_SHF 0 -#define GIC_VPE_CTL_EIC_MODE_MSK (MSK(1) << GIC_VPE_CTL_EIC_MODE_SHF) - /* GIC nomenclature for Core Interrupt Pins. */ #define GIC_CPU_INT0 0 /* Core Interrupt 2 */ #define GIC_CPU_INT1 1 /* . */ -- cgit v1.2.3 From ba9cc4352e9c40ab3b158620a1bd9cd53295ea17 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:27 -0700 Subject: MIPS: GIC: Move GIC_LOCAL_INT_* to asm/mips-gic.h Move the definition of VP-local interrupts provided by the MIPS Global Interrupt Controller to the new asm/mips-gic.h header to be alongside the new accessor functions. Whilst at it, convert to an enum which lends itself more easily to expansion & documentation. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17037/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index b7a3ce1da9a7..9546947d1842 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -38,16 +38,6 @@ /* Mapped interrupt to pin X, then GIC will generate the vector (X+1). */ #define GIC_PIN_TO_VEC_OFFSET 1 -/* Local GIC interrupts. */ -#define GIC_LOCAL_INT_WD 0 /* GIC watchdog */ -#define GIC_LOCAL_INT_COMPARE 1 /* GIC count and compare timer */ -#define GIC_LOCAL_INT_TIMER 2 /* CPU timer interrupt */ -#define GIC_LOCAL_INT_PERFCTR 3 /* CPU performance counter */ -#define GIC_LOCAL_INT_SWINT0 4 /* CPU software interrupt 0 */ -#define GIC_LOCAL_INT_SWINT1 5 /* CPU software interrupt 1 */ -#define GIC_LOCAL_INT_FDC 6 /* CPU fast debug channel */ -#define GIC_NUM_LOCAL_INTRS 7 - /* Convert between local/shared IRQ number and GIC HW IRQ number. */ #define GIC_LOCAL_HWIRQ_BASE 0 #define GIC_LOCAL_TO_HWIRQ(x) (GIC_LOCAL_HWIRQ_BASE + (x)) -- cgit v1.2.3 From 3ee50dcbef374651056ea42d5eb543bbacb3ff41 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:28 -0700 Subject: irqchip: mips-gic: Remove GIC_CPU_INT* macros The GIC_CPU_INT* macros are never used. Remove the dead code. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17038/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 9546947d1842..e93aaf529baa 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -21,14 +21,6 @@ #define GIC_UMV_SH_COUNTER_31_00_OFS 0x0000 #define GIC_UMV_SH_COUNTER_63_32_OFS 0x0004 -/* GIC nomenclature for Core Interrupt Pins. */ -#define GIC_CPU_INT0 0 /* Core Interrupt 2 */ -#define GIC_CPU_INT1 1 /* . */ -#define GIC_CPU_INT2 2 /* . */ -#define GIC_CPU_INT3 3 /* . */ -#define GIC_CPU_INT4 4 /* . */ -#define GIC_CPU_INT5 5 /* Core Interrupt 7 */ - /* Add 2 to convert GIC CPU pin to core interrupt */ #define GIC_CPU_PIN_OFFSET 2 -- cgit v1.2.3 From b11d4c1f5a3ac68fa163b0daeca1f98ba328c9de Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:29 -0700 Subject: irqchip: mips-gic: Move various definitions to the driver Move the definitions of macros used to convert between hardware IRQ numbers & shared or local interrupt numbers into the irqchip driver, which is all that should ever need to care about them. Remove GIC_CPU_TO_VEC_OFFSET() in the process since it's never used. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17039/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index e93aaf529baa..da02a146b292 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -11,8 +11,6 @@ #include #include -#define GIC_MAX_INTRS 256 - /* GIC Address Space */ #define USM_VISIBLE_SECTION_OFS 0x10000 #define USM_VISIBLE_SECTION_SIZE 0x10000 @@ -21,23 +19,6 @@ #define GIC_UMV_SH_COUNTER_31_00_OFS 0x0000 #define GIC_UMV_SH_COUNTER_63_32_OFS 0x0004 -/* Add 2 to convert GIC CPU pin to core interrupt */ -#define GIC_CPU_PIN_OFFSET 2 - -/* Add 2 to convert non-EIC hardware interrupt to EIC vector number. */ -#define GIC_CPU_TO_VEC_OFFSET 2 - -/* Mapped interrupt to pin X, then GIC will generate the vector (X+1). */ -#define GIC_PIN_TO_VEC_OFFSET 1 - -/* Convert between local/shared IRQ number and GIC HW IRQ number. */ -#define GIC_LOCAL_HWIRQ_BASE 0 -#define GIC_LOCAL_TO_HWIRQ(x) (GIC_LOCAL_HWIRQ_BASE + (x)) -#define GIC_HWIRQ_TO_LOCAL(x) ((x) - GIC_LOCAL_HWIRQ_BASE) -#define GIC_SHARED_HWIRQ_BASE GIC_NUM_LOCAL_INTRS -#define GIC_SHARED_TO_HWIRQ(x) (GIC_SHARED_HWIRQ_BASE + (x)) -#define GIC_HWIRQ_TO_SHARED(x) ((x) - GIC_SHARED_HWIRQ_BASE) - #ifdef CONFIG_MIPS_GIC extern unsigned int gic_present; -- cgit v1.2.3 From 84103814a2cfd3561ff00bd7317c22f40f9e0dad Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:31 -0700 Subject: irqchip: mips-gic: Remove gic_get_usm_range() The MIPS VDSO code is no longer reliant upon the irqchip driver to provide the address of the GIC's user-visible section via gic_get_usm_range(). Remove the now-dead code. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17041/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index da02a146b292..843e1bb49767 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -11,10 +11,6 @@ #include #include -/* GIC Address Space */ -#define USM_VISIBLE_SECTION_OFS 0x10000 -#define USM_VISIBLE_SECTION_SIZE 0x10000 - /* User Mode Visible Section Register Map */ #define GIC_UMV_SH_COUNTER_31_00_OFS 0x0000 #define GIC_UMV_SH_COUNTER_63_32_OFS 0x0004 @@ -29,18 +25,11 @@ extern void gic_init(unsigned long gic_base_addr, extern int gic_get_c0_compare_int(void); extern int gic_get_c0_perfcount_int(void); extern int gic_get_c0_fdc_int(void); -extern int gic_get_usm_range(struct resource *gic_usm_res); #else /* CONFIG_MIPS_GIC */ #define gic_present 0 -static inline int gic_get_usm_range(struct resource *gic_usm_res) -{ - /* Shouldn't be called. */ - return -1; -} - #endif /* CONFIG_MIPS_GIC */ #endif /* __LINUX_IRQCHIP_MIPS_GIC_H */ -- cgit v1.2.3 From 85eec73ce4c4322b3b442b9582f6656abb5d125f Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:33 -0700 Subject: irqchip: mips-gic: Remove gic_init() All in-tree platforms now probe the GIC driver using device tree, and as such nothing calls gic_init() any longer. Remove the dead code. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17043/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 843e1bb49767..63c5f87034c9 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -19,9 +19,6 @@ extern unsigned int gic_present; -extern void gic_init(unsigned long gic_base_addr, - unsigned long gic_addrspace_size, unsigned int cpu_vec, - unsigned int irqbase); extern int gic_get_c0_compare_int(void); extern int gic_get_c0_perfcount_int(void); extern int gic_get_c0_fdc_int(void); -- cgit v1.2.3 From 56d7b61dc6d4e13cef786c8e4a2bfe43e4db932d Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:35 -0700 Subject: irqchip: mips-gic: Remove gic_present Nothing uses the global gic_present variable anymore; mips_gic_present() should be used instead. Remove the dead code. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17045/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 63c5f87034c9..113010c8dd8b 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -17,16 +17,10 @@ #ifdef CONFIG_MIPS_GIC -extern unsigned int gic_present; - extern int gic_get_c0_compare_int(void); extern int gic_get_c0_perfcount_int(void); extern int gic_get_c0_fdc_int(void); -#else /* CONFIG_MIPS_GIC */ - -#define gic_present 0 - #endif /* CONFIG_MIPS_GIC */ #endif /* __LINUX_IRQCHIP_MIPS_GIC_H */ -- cgit v1.2.3 From dd0163508c07a67b28befe5af23d7ab9941ae8ca Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:36 -0700 Subject: irqchip: mips-gic: Move gic_get_c0_*_int() to asm/mips-gic.h The linux/irqchip/mips-gic.h header is now almost empty. Move the declarations of gic_get_c0_compare_int(), gic_get_c0_perfcount_int() & gic_get_c0_fdc_int() to asm/mips-gic.h in order to close in on being able to delete the former header. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17046/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 113010c8dd8b..277d5be03a57 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -15,12 +15,4 @@ #define GIC_UMV_SH_COUNTER_31_00_OFS 0x0000 #define GIC_UMV_SH_COUNTER_63_32_OFS 0x0004 -#ifdef CONFIG_MIPS_GIC - -extern int gic_get_c0_compare_int(void); -extern int gic_get_c0_perfcount_int(void); -extern int gic_get_c0_fdc_int(void); - -#endif /* CONFIG_MIPS_GIC */ - #endif /* __LINUX_IRQCHIP_MIPS_GIC_H */ -- cgit v1.2.3 From 16ae123e89d603a69d980bd76c4bb686f219ba0e Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:37 -0700 Subject: MIPS: VDSO: Avoid use of linux/irqchip/mips-gic.h Our VDSO code makes use of macros from linux/irqchip/mips-gic.h to provide offsets to register values, but these are trivial offsets to the two 32 bit halves of a 64 bit value. Replace use of the macros with zero (ie. omit adding an offset) and the size of the low 32 bit of the value. This removes our need for linux/irqchip/mips-gic.h & prepares us for it to be removed. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17047/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h index 277d5be03a57..6e6c9adea049 100644 --- a/include/linux/irqchip/mips-gic.h +++ b/include/linux/irqchip/mips-gic.h @@ -11,8 +11,4 @@ #include #include -/* User Mode Visible Section Register Map */ -#define GIC_UMV_SH_COUNTER_31_00_OFS 0x0000 -#define GIC_UMV_SH_COUNTER_63_32_OFS 0x0004 - #endif /* __LINUX_IRQCHIP_MIPS_GIC_H */ -- cgit v1.2.3 From 1fad12cd5ef43755d028f760fa089c87f5533451 Mon Sep 17 00:00:00 2001 From: Paul Burton Date: Sat, 12 Aug 2017 21:36:39 -0700 Subject: irqchip: mips-gic: Remove linux/irqchip/mips-gic.h The linux/irqchip/mips-gic.h header is no longer used. Remove it. Signed-off-by: Paul Burton Acked-by: Marc Zyngier Cc: Jason Cooper Cc: Thomas Gleixner Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/17049/ Signed-off-by: Ralf Baechle --- include/linux/irqchip/mips-gic.h | 14 -------------- 1 file changed, 14 deletions(-) delete mode 100644 include/linux/irqchip/mips-gic.h (limited to 'include/linux') diff --git a/include/linux/irqchip/mips-gic.h b/include/linux/irqchip/mips-gic.h deleted file mode 100644 index 6e6c9adea049..000000000000 --- a/include/linux/irqchip/mips-gic.h +++ /dev/null @@ -1,14 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2000, 07 MIPS Technologies, Inc. - */ -#ifndef __LINUX_IRQCHIP_MIPS_GIC_H -#define __LINUX_IRQCHIP_MIPS_GIC_H - -#include -#include - -#endif /* __LINUX_IRQCHIP_MIPS_GIC_H */ -- cgit v1.2.3 From a205425658dead19bb1b8ac00584aed98e60dde2 Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Mon, 14 Aug 2017 18:34:24 +0200 Subject: mfd: twl: Move header file out of I2C realm include/linux/i2c is not for client devices. Move the header file to a more appropriate location. Signed-off-by: Wolfram Sang Acked-by: Greg Kroah-Hartman Acked-by: Alexandre Belloni Acked-by: Mark Brown Acked-by: Sebastian Reichel Acked-by: Jonathan Cameron Acked-by: Dmitry Torokhov Acked-by: Kishon Vijay Abraham I Acked-by: Bartlomiej Zolnierkiewicz Acked-by: Thierry Reding Acked-by: Tony Lindgren Acked-by: Daniel Thompson Acked-by: Linus Walleij Acked-by: Guenter Roeck Signed-off-by: Lee Jones --- include/linux/i2c/twl.h | 876 ------------------------------------------------ include/linux/mfd/twl.h | 876 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 876 insertions(+), 876 deletions(-) delete mode 100644 include/linux/i2c/twl.h create mode 100644 include/linux/mfd/twl.h (limited to 'include/linux') diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h deleted file mode 100644 index 9ad7828d9d34..000000000000 --- a/include/linux/i2c/twl.h +++ /dev/null @@ -1,876 +0,0 @@ -/* - * twl4030.h - header for TWL4030 PM and audio CODEC device - * - * Copyright (C) 2005-2006 Texas Instruments, Inc. - * - * Based on tlv320aic23.c: - * Copyright (c) by Kai Svahn - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - */ - -#ifndef __TWL_H_ -#define __TWL_H_ - -#include -#include - -/* - * Using the twl4030 core we address registers using a pair - * { module id, relative register offset } - * which that core then maps to the relevant - * { i2c slave, absolute register address } - * - * The module IDs are meaningful only to the twl4030 core code, - * which uses them as array indices to look up the first register - * address each module uses within a given i2c slave. - */ - -/* Module IDs for similar functionalities found in twl4030/twl6030 */ -enum twl_module_ids { - TWL_MODULE_USB, - TWL_MODULE_PIH, - TWL_MODULE_MAIN_CHARGE, - TWL_MODULE_PM_MASTER, - TWL_MODULE_PM_RECEIVER, - - TWL_MODULE_RTC, - TWL_MODULE_PWM, - TWL_MODULE_LED, - TWL_MODULE_SECURED_REG, - - TWL_MODULE_LAST, -}; - -/* Modules only available in twl4030 series */ -enum twl4030_module_ids { - TWL4030_MODULE_AUDIO_VOICE = TWL_MODULE_LAST, - TWL4030_MODULE_GPIO, - TWL4030_MODULE_INTBR, - TWL4030_MODULE_TEST, - TWL4030_MODULE_KEYPAD, - - TWL4030_MODULE_MADC, - TWL4030_MODULE_INTERRUPTS, - TWL4030_MODULE_PRECHARGE, - TWL4030_MODULE_BACKUP, - TWL4030_MODULE_INT, - - TWL5031_MODULE_ACCESSORY, - TWL5031_MODULE_INTERRUPTS, - - TWL4030_MODULE_LAST, -}; - -/* Modules only available in twl6030 series */ -enum twl6030_module_ids { - TWL6030_MODULE_ID0 = TWL_MODULE_LAST, - TWL6030_MODULE_ID1, - TWL6030_MODULE_ID2, - TWL6030_MODULE_GPADC, - TWL6030_MODULE_GASGAUGE, - - TWL6030_MODULE_LAST, -}; - -/* Until the clients has been converted to use TWL_MODULE_LED */ -#define TWL4030_MODULE_LED TWL_MODULE_LED - -#define GPIO_INTR_OFFSET 0 -#define KEYPAD_INTR_OFFSET 1 -#define BCI_INTR_OFFSET 2 -#define MADC_INTR_OFFSET 3 -#define USB_INTR_OFFSET 4 -#define CHARGERFAULT_INTR_OFFSET 5 -#define BCI_PRES_INTR_OFFSET 9 -#define USB_PRES_INTR_OFFSET 10 -#define RTC_INTR_OFFSET 11 - -/* - * Offset from TWL6030_IRQ_BASE / pdata->irq_base - */ -#define PWR_INTR_OFFSET 0 -#define HOTDIE_INTR_OFFSET 12 -#define SMPSLDO_INTR_OFFSET 13 -#define BATDETECT_INTR_OFFSET 14 -#define SIMDETECT_INTR_OFFSET 15 -#define MMCDETECT_INTR_OFFSET 16 -#define GASGAUGE_INTR_OFFSET 17 -#define USBOTG_INTR_OFFSET 4 -#define CHARGER_INTR_OFFSET 2 -#define RSV_INTR_OFFSET 0 - -/* INT register offsets */ -#define REG_INT_STS_A 0x00 -#define REG_INT_STS_B 0x01 -#define REG_INT_STS_C 0x02 - -#define REG_INT_MSK_LINE_A 0x03 -#define REG_INT_MSK_LINE_B 0x04 -#define REG_INT_MSK_LINE_C 0x05 - -#define REG_INT_MSK_STS_A 0x06 -#define REG_INT_MSK_STS_B 0x07 -#define REG_INT_MSK_STS_C 0x08 - -/* MASK INT REG GROUP A */ -#define TWL6030_PWR_INT_MASK 0x07 -#define TWL6030_RTC_INT_MASK 0x18 -#define TWL6030_HOTDIE_INT_MASK 0x20 -#define TWL6030_SMPSLDOA_INT_MASK 0xC0 - -/* MASK INT REG GROUP B */ -#define TWL6030_SMPSLDOB_INT_MASK 0x01 -#define TWL6030_BATDETECT_INT_MASK 0x02 -#define TWL6030_SIMDETECT_INT_MASK 0x04 -#define TWL6030_MMCDETECT_INT_MASK 0x08 -#define TWL6030_GPADC_INT_MASK 0x60 -#define TWL6030_GASGAUGE_INT_MASK 0x80 - -/* MASK INT REG GROUP C */ -#define TWL6030_USBOTG_INT_MASK 0x0F -#define TWL6030_CHARGER_CTRL_INT_MASK 0x10 -#define TWL6030_CHARGER_FAULT_INT_MASK 0x60 - -#define TWL6030_MMCCTRL 0xEE -#define VMMC_AUTO_OFF (0x1 << 3) -#define SW_FC (0x1 << 2) -#define STS_MMC 0x1 - -#define TWL6030_CFG_INPUT_PUPD3 0xF2 -#define MMC_PU (0x1 << 3) -#define MMC_PD (0x1 << 2) - -#define TWL_SIL_TYPE(rev) ((rev) & 0x00FFFFFF) -#define TWL_SIL_REV(rev) ((rev) >> 24) -#define TWL_SIL_5030 0x09002F -#define TWL5030_REV_1_0 0x00 -#define TWL5030_REV_1_1 0x10 -#define TWL5030_REV_1_2 0x30 - -#define TWL4030_CLASS_ID 0x4030 -#define TWL6030_CLASS_ID 0x6030 -unsigned int twl_rev(void); -#define GET_TWL_REV (twl_rev()) -#define TWL_CLASS_IS(class, id) \ -static inline int twl_class_is_ ##class(void) \ -{ \ - return ((id) == (GET_TWL_REV)) ? 1 : 0; \ -} - -TWL_CLASS_IS(4030, TWL4030_CLASS_ID) -TWL_CLASS_IS(6030, TWL6030_CLASS_ID) - -/* Set the regcache bypass for the regmap associated with the nodule */ -int twl_set_regcache_bypass(u8 mod_no, bool enable); - -/* - * Read and write several 8-bit registers at once. - */ -int twl_i2c_write(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes); -int twl_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes); - -/* - * Read and write single 8-bit registers - */ -static inline int twl_i2c_write_u8(u8 mod_no, u8 val, u8 reg) { - return twl_i2c_write(mod_no, &val, reg, 1); -} - -static inline int twl_i2c_read_u8(u8 mod_no, u8 *val, u8 reg) { - return twl_i2c_read(mod_no, val, reg, 1); -} - -static inline int twl_i2c_write_u16(u8 mod_no, u16 val, u8 reg) { - val = cpu_to_le16(val); - return twl_i2c_write(mod_no, (u8*) &val, reg, 2); -} - -static inline int twl_i2c_read_u16(u8 mod_no, u16 *val, u8 reg) { - int ret; - ret = twl_i2c_read(mod_no, (u8*) val, reg, 2); - *val = le16_to_cpu(*val); - return ret; -} - -int twl_get_type(void); -int twl_get_version(void); -int twl_get_hfclk_rate(void); - -int twl6030_interrupt_unmask(u8 bit_mask, u8 offset); -int twl6030_interrupt_mask(u8 bit_mask, u8 offset); - -/* Card detect Configuration for MMC1 Controller on OMAP4 */ -#ifdef CONFIG_TWL4030_CORE -int twl6030_mmc_card_detect_config(void); -#else -static inline int twl6030_mmc_card_detect_config(void) -{ - pr_debug("twl6030_mmc_card_detect_config not supported\n"); - return 0; -} -#endif - -/* MMC1 Controller on OMAP4 uses Phoenix irq for Card detect */ -#ifdef CONFIG_TWL4030_CORE -int twl6030_mmc_card_detect(struct device *dev, int slot); -#else -static inline int twl6030_mmc_card_detect(struct device *dev, int slot) -{ - pr_debug("Call back twl6030_mmc_card_detect not supported\n"); - return -EIO; -} -#endif -/*----------------------------------------------------------------------*/ - -/* - * NOTE: at up to 1024 registers, this is a big chip. - * - * Avoid putting register declarations in this file, instead of into - * a driver-private file, unless some of the registers in a block - * need to be shared with other drivers. One example is blocks that - * have Secondary IRQ Handler (SIH) registers. - */ - -#define TWL4030_SIH_CTRL_EXCLEN_MASK BIT(0) -#define TWL4030_SIH_CTRL_PENDDIS_MASK BIT(1) -#define TWL4030_SIH_CTRL_COR_MASK BIT(2) - -/*----------------------------------------------------------------------*/ - -/* - * GPIO Block Register offsets (use TWL4030_MODULE_GPIO) - */ - -#define REG_GPIODATAIN1 0x0 -#define REG_GPIODATAIN2 0x1 -#define REG_GPIODATAIN3 0x2 -#define REG_GPIODATADIR1 0x3 -#define REG_GPIODATADIR2 0x4 -#define REG_GPIODATADIR3 0x5 -#define REG_GPIODATAOUT1 0x6 -#define REG_GPIODATAOUT2 0x7 -#define REG_GPIODATAOUT3 0x8 -#define REG_CLEARGPIODATAOUT1 0x9 -#define REG_CLEARGPIODATAOUT2 0xA -#define REG_CLEARGPIODATAOUT3 0xB -#define REG_SETGPIODATAOUT1 0xC -#define REG_SETGPIODATAOUT2 0xD -#define REG_SETGPIODATAOUT3 0xE -#define REG_GPIO_DEBEN1 0xF -#define REG_GPIO_DEBEN2 0x10 -#define REG_GPIO_DEBEN3 0x11 -#define REG_GPIO_CTRL 0x12 -#define REG_GPIOPUPDCTR1 0x13 -#define REG_GPIOPUPDCTR2 0x14 -#define REG_GPIOPUPDCTR3 0x15 -#define REG_GPIOPUPDCTR4 0x16 -#define REG_GPIOPUPDCTR5 0x17 -#define REG_GPIO_ISR1A 0x19 -#define REG_GPIO_ISR2A 0x1A -#define REG_GPIO_ISR3A 0x1B -#define REG_GPIO_IMR1A 0x1C -#define REG_GPIO_IMR2A 0x1D -#define REG_GPIO_IMR3A 0x1E -#define REG_GPIO_ISR1B 0x1F -#define REG_GPIO_ISR2B 0x20 -#define REG_GPIO_ISR3B 0x21 -#define REG_GPIO_IMR1B 0x22 -#define REG_GPIO_IMR2B 0x23 -#define REG_GPIO_IMR3B 0x24 -#define REG_GPIO_EDR1 0x28 -#define REG_GPIO_EDR2 0x29 -#define REG_GPIO_EDR3 0x2A -#define REG_GPIO_EDR4 0x2B -#define REG_GPIO_EDR5 0x2C -#define REG_GPIO_SIH_CTRL 0x2D - -/* Up to 18 signals are available as GPIOs, when their - * pins are not assigned to another use (such as ULPI/USB). - */ -#define TWL4030_GPIO_MAX 18 - -/*----------------------------------------------------------------------*/ - -/*Interface Bit Register (INTBR) offsets - *(Use TWL_4030_MODULE_INTBR) - */ - -#define REG_IDCODE_7_0 0x00 -#define REG_IDCODE_15_8 0x01 -#define REG_IDCODE_16_23 0x02 -#define REG_IDCODE_31_24 0x03 -#define REG_GPPUPDCTR1 0x0F -#define REG_UNLOCK_TEST_REG 0x12 - -/*I2C1 and I2C4(SR) SDA/SCL pull-up control bits */ - -#define I2C_SCL_CTRL_PU BIT(0) -#define I2C_SDA_CTRL_PU BIT(2) -#define SR_I2C_SCL_CTRL_PU BIT(4) -#define SR_I2C_SDA_CTRL_PU BIT(6) - -#define TWL_EEPROM_R_UNLOCK 0x49 - -/*----------------------------------------------------------------------*/ - -/* - * Keypad register offsets (use TWL4030_MODULE_KEYPAD) - * ... SIH/interrupt only - */ - -#define TWL4030_KEYPAD_KEYP_ISR1 0x11 -#define TWL4030_KEYPAD_KEYP_IMR1 0x12 -#define TWL4030_KEYPAD_KEYP_ISR2 0x13 -#define TWL4030_KEYPAD_KEYP_IMR2 0x14 -#define TWL4030_KEYPAD_KEYP_SIR 0x15 /* test register */ -#define TWL4030_KEYPAD_KEYP_EDR 0x16 -#define TWL4030_KEYPAD_KEYP_SIH_CTRL 0x17 - -/*----------------------------------------------------------------------*/ - -/* - * Multichannel ADC register offsets (use TWL4030_MODULE_MADC) - * ... SIH/interrupt only - */ - -#define TWL4030_MADC_ISR1 0x61 -#define TWL4030_MADC_IMR1 0x62 -#define TWL4030_MADC_ISR2 0x63 -#define TWL4030_MADC_IMR2 0x64 -#define TWL4030_MADC_SIR 0x65 /* test register */ -#define TWL4030_MADC_EDR 0x66 -#define TWL4030_MADC_SIH_CTRL 0x67 - -/*----------------------------------------------------------------------*/ - -/* - * Battery charger register offsets (use TWL4030_MODULE_INTERRUPTS) - */ - -#define TWL4030_INTERRUPTS_BCIISR1A 0x0 -#define TWL4030_INTERRUPTS_BCIISR2A 0x1 -#define TWL4030_INTERRUPTS_BCIIMR1A 0x2 -#define TWL4030_INTERRUPTS_BCIIMR2A 0x3 -#define TWL4030_INTERRUPTS_BCIISR1B 0x4 -#define TWL4030_INTERRUPTS_BCIISR2B 0x5 -#define TWL4030_INTERRUPTS_BCIIMR1B 0x6 -#define TWL4030_INTERRUPTS_BCIIMR2B 0x7 -#define TWL4030_INTERRUPTS_BCISIR1 0x8 /* test register */ -#define TWL4030_INTERRUPTS_BCISIR2 0x9 /* test register */ -#define TWL4030_INTERRUPTS_BCIEDR1 0xa -#define TWL4030_INTERRUPTS_BCIEDR2 0xb -#define TWL4030_INTERRUPTS_BCIEDR3 0xc -#define TWL4030_INTERRUPTS_BCISIHCTRL 0xd - -/*----------------------------------------------------------------------*/ - -/* - * Power Interrupt block register offsets (use TWL4030_MODULE_INT) - */ - -#define TWL4030_INT_PWR_ISR1 0x0 -#define TWL4030_INT_PWR_IMR1 0x1 -#define TWL4030_INT_PWR_ISR2 0x2 -#define TWL4030_INT_PWR_IMR2 0x3 -#define TWL4030_INT_PWR_SIR 0x4 /* test register */ -#define TWL4030_INT_PWR_EDR1 0x5 -#define TWL4030_INT_PWR_EDR2 0x6 -#define TWL4030_INT_PWR_SIH_CTRL 0x7 - -/*----------------------------------------------------------------------*/ - -/* - * Accessory Interrupts - */ -#define TWL5031_ACIIMR_LSB 0x05 -#define TWL5031_ACIIMR_MSB 0x06 -#define TWL5031_ACIIDR_LSB 0x07 -#define TWL5031_ACIIDR_MSB 0x08 -#define TWL5031_ACCISR1 0x0F -#define TWL5031_ACCIMR1 0x10 -#define TWL5031_ACCISR2 0x11 -#define TWL5031_ACCIMR2 0x12 -#define TWL5031_ACCSIR 0x13 -#define TWL5031_ACCEDR1 0x14 -#define TWL5031_ACCSIHCTRL 0x15 - -/*----------------------------------------------------------------------*/ - -/* - * Battery Charger Controller - */ - -#define TWL5031_INTERRUPTS_BCIISR1 0x0 -#define TWL5031_INTERRUPTS_BCIIMR1 0x1 -#define TWL5031_INTERRUPTS_BCIISR2 0x2 -#define TWL5031_INTERRUPTS_BCIIMR2 0x3 -#define TWL5031_INTERRUPTS_BCISIR 0x4 -#define TWL5031_INTERRUPTS_BCIEDR1 0x5 -#define TWL5031_INTERRUPTS_BCIEDR2 0x6 -#define TWL5031_INTERRUPTS_BCISIHCTRL 0x7 - -/*----------------------------------------------------------------------*/ - -/* - * PM Master module register offsets (use TWL4030_MODULE_PM_MASTER) - */ - -#define TWL4030_PM_MASTER_CFG_P1_TRANSITION 0x00 -#define TWL4030_PM_MASTER_CFG_P2_TRANSITION 0x01 -#define TWL4030_PM_MASTER_CFG_P3_TRANSITION 0x02 -#define TWL4030_PM_MASTER_CFG_P123_TRANSITION 0x03 -#define TWL4030_PM_MASTER_STS_BOOT 0x04 -#define TWL4030_PM_MASTER_CFG_BOOT 0x05 -#define TWL4030_PM_MASTER_SHUNDAN 0x06 -#define TWL4030_PM_MASTER_BOOT_BCI 0x07 -#define TWL4030_PM_MASTER_CFG_PWRANA1 0x08 -#define TWL4030_PM_MASTER_CFG_PWRANA2 0x09 -#define TWL4030_PM_MASTER_BACKUP_MISC_STS 0x0b -#define TWL4030_PM_MASTER_BACKUP_MISC_CFG 0x0c -#define TWL4030_PM_MASTER_BACKUP_MISC_TST 0x0d -#define TWL4030_PM_MASTER_PROTECT_KEY 0x0e -#define TWL4030_PM_MASTER_STS_HW_CONDITIONS 0x0f -#define TWL4030_PM_MASTER_P1_SW_EVENTS 0x10 -#define TWL4030_PM_MASTER_P2_SW_EVENTS 0x11 -#define TWL4030_PM_MASTER_P3_SW_EVENTS 0x12 -#define TWL4030_PM_MASTER_STS_P123_STATE 0x13 -#define TWL4030_PM_MASTER_PB_CFG 0x14 -#define TWL4030_PM_MASTER_PB_WORD_MSB 0x15 -#define TWL4030_PM_MASTER_PB_WORD_LSB 0x16 -#define TWL4030_PM_MASTER_SEQ_ADD_W2P 0x1c -#define TWL4030_PM_MASTER_SEQ_ADD_P2A 0x1d -#define TWL4030_PM_MASTER_SEQ_ADD_A2W 0x1e -#define TWL4030_PM_MASTER_SEQ_ADD_A2S 0x1f -#define TWL4030_PM_MASTER_SEQ_ADD_S2A12 0x20 -#define TWL4030_PM_MASTER_SEQ_ADD_S2A3 0x21 -#define TWL4030_PM_MASTER_SEQ_ADD_WARM 0x22 -#define TWL4030_PM_MASTER_MEMORY_ADDRESS 0x23 -#define TWL4030_PM_MASTER_MEMORY_DATA 0x24 - -#define TWL4030_PM_MASTER_KEY_CFG1 0xc0 -#define TWL4030_PM_MASTER_KEY_CFG2 0x0c - -#define TWL4030_PM_MASTER_KEY_TST1 0xe0 -#define TWL4030_PM_MASTER_KEY_TST2 0x0e - -#define TWL4030_PM_MASTER_GLOBAL_TST 0xb6 - -/*----------------------------------------------------------------------*/ - -/* Power bus message definitions */ - -/* The TWL4030/5030 splits its power-management resources (the various - * regulators, clock and reset lines) into 3 processor groups - P1, P2 and - * P3. These groups can then be configured to transition between sleep, wait-on - * and active states by sending messages to the power bus. See Section 5.4.2 - * Power Resources of TWL4030 TRM - */ - -/* Processor groups */ -#define DEV_GRP_NULL 0x0 -#define DEV_GRP_P1 0x1 /* P1: all OMAP devices */ -#define DEV_GRP_P2 0x2 /* P2: all Modem devices */ -#define DEV_GRP_P3 0x4 /* P3: all peripheral devices */ - -/* Resource groups */ -#define RES_GRP_RES 0x0 /* Reserved */ -#define RES_GRP_PP 0x1 /* Power providers */ -#define RES_GRP_RC 0x2 /* Reset and control */ -#define RES_GRP_PP_RC 0x3 -#define RES_GRP_PR 0x4 /* Power references */ -#define RES_GRP_PP_PR 0x5 -#define RES_GRP_RC_PR 0x6 -#define RES_GRP_ALL 0x7 /* All resource groups */ - -#define RES_TYPE2_R0 0x0 -#define RES_TYPE2_R1 0x1 -#define RES_TYPE2_R2 0x2 - -#define RES_TYPE_R0 0x0 -#define RES_TYPE_ALL 0x7 - -/* Resource states */ -#define RES_STATE_WRST 0xF -#define RES_STATE_ACTIVE 0xE -#define RES_STATE_SLEEP 0x8 -#define RES_STATE_OFF 0x0 - -/* Power resources */ - -/* Power providers */ -#define RES_VAUX1 1 -#define RES_VAUX2 2 -#define RES_VAUX3 3 -#define RES_VAUX4 4 -#define RES_VMMC1 5 -#define RES_VMMC2 6 -#define RES_VPLL1 7 -#define RES_VPLL2 8 -#define RES_VSIM 9 -#define RES_VDAC 10 -#define RES_VINTANA1 11 -#define RES_VINTANA2 12 -#define RES_VINTDIG 13 -#define RES_VIO 14 -#define RES_VDD1 15 -#define RES_VDD2 16 -#define RES_VUSB_1V5 17 -#define RES_VUSB_1V8 18 -#define RES_VUSB_3V1 19 -#define RES_VUSBCP 20 -#define RES_REGEN 21 -/* Reset and control */ -#define RES_NRES_PWRON 22 -#define RES_CLKEN 23 -#define RES_SYSEN 24 -#define RES_HFCLKOUT 25 -#define RES_32KCLKOUT 26 -#define RES_RESET 27 -/* Power Reference */ -#define RES_MAIN_REF 28 - -#define TOTAL_RESOURCES 28 -/* - * Power Bus Message Format ... these can be sent individually by Linux, - * but are usually part of downloaded scripts that are run when various - * power events are triggered. - * - * Broadcast Message (16 Bits): - * DEV_GRP[15:13] MT[12] RES_GRP[11:9] RES_TYPE2[8:7] RES_TYPE[6:4] - * RES_STATE[3:0] - * - * Singular Message (16 Bits): - * DEV_GRP[15:13] MT[12] RES_ID[11:4] RES_STATE[3:0] - */ - -#define MSG_BROADCAST(devgrp, grp, type, type2, state) \ - ( (devgrp) << 13 | 1 << 12 | (grp) << 9 | (type2) << 7 \ - | (type) << 4 | (state)) - -#define MSG_SINGULAR(devgrp, id, state) \ - ((devgrp) << 13 | 0 << 12 | (id) << 4 | (state)) - -#define MSG_BROADCAST_ALL(devgrp, state) \ - ((devgrp) << 5 | (state)) - -#define MSG_BROADCAST_REF MSG_BROADCAST_ALL -#define MSG_BROADCAST_PROV MSG_BROADCAST_ALL -#define MSG_BROADCAST__CLK_RST MSG_BROADCAST_ALL -/*----------------------------------------------------------------------*/ - -struct twl4030_clock_init_data { - bool ck32k_lowpwr_enable; -}; - -struct twl4030_bci_platform_data { - int *battery_tmp_tbl; - unsigned int tblsize; - int bb_uvolt; /* voltage to charge backup battery */ - int bb_uamp; /* current for backup battery charging */ -}; - -/* TWL4030_GPIO_MAX (18) GPIOs, with interrupts */ -struct twl4030_gpio_platform_data { - /* package the two LED signals as output-only GPIOs? */ - bool use_leds; - - /* gpio-n should control VMMC(n+1) if BIT(n) in mmc_cd is set */ - u8 mmc_cd; - - /* if BIT(N) is set, or VMMC(n+1) is linked, debounce GPIO-N */ - u32 debounce; - - /* For gpio-N, bit (1 << N) in "pullups" is set if that pullup - * should be enabled. Else, if that bit is set in "pulldowns", - * that pulldown is enabled. Don't waste power by letting any - * digital inputs float... - */ - u32 pullups; - u32 pulldowns; - - int (*setup)(struct device *dev, - unsigned gpio, unsigned ngpio); - int (*teardown)(struct device *dev, - unsigned gpio, unsigned ngpio); -}; - -struct twl4030_madc_platform_data { - int irq_line; -}; - -/* Boards have unique mappings of {row, col} --> keycode. - * Column and row are 8 bits each, but range only from 0..7. - * a PERSISTENT_KEY is "always on" and never reported. - */ -#define PERSISTENT_KEY(r, c) KEY((r), (c), KEY_RESERVED) - -struct twl4030_keypad_data { - const struct matrix_keymap_data *keymap_data; - unsigned rows; - unsigned cols; - bool rep; -}; - -enum twl4030_usb_mode { - T2_USB_MODE_ULPI = 1, - T2_USB_MODE_CEA2011_3PIN = 2, -}; - -struct twl4030_usb_data { - enum twl4030_usb_mode usb_mode; - unsigned long features; - - int (*phy_init)(struct device *dev); - int (*phy_exit)(struct device *dev); - /* Power on/off the PHY */ - int (*phy_power)(struct device *dev, int iD, int on); - /* enable/disable phy clocks */ - int (*phy_set_clock)(struct device *dev, int on); - /* suspend/resume of phy */ - int (*phy_suspend)(struct device *dev, int suspend); -}; - -struct twl4030_ins { - u16 pmb_message; - u8 delay; -}; - -struct twl4030_script { - struct twl4030_ins *script; - unsigned size; - u8 flags; -#define TWL4030_WRST_SCRIPT (1<<0) -#define TWL4030_WAKEUP12_SCRIPT (1<<1) -#define TWL4030_WAKEUP3_SCRIPT (1<<2) -#define TWL4030_SLEEP_SCRIPT (1<<3) -}; - -struct twl4030_resconfig { - u8 resource; - u8 devgroup; /* Processor group that Power resource belongs to */ - u8 type; /* Power resource addressed, 6 / broadcast message */ - u8 type2; /* Power resource addressed, 3 / broadcast message */ - u8 remap_off; /* off state remapping */ - u8 remap_sleep; /* sleep state remapping */ -}; - -struct twl4030_power_data { - struct twl4030_script **scripts; - unsigned num; - struct twl4030_resconfig *resource_config; - struct twl4030_resconfig *board_config; -#define TWL4030_RESCONFIG_UNDEF ((u8)-1) - bool use_poweroff; /* Board is wired for TWL poweroff */ - bool ac_charger_quirk; /* Disable AC charger on board */ -}; - -extern int twl4030_remove_script(u8 flags); -extern void twl4030_power_off(void); - -struct twl4030_codec_data { - unsigned int digimic_delay; /* in ms */ - unsigned int ramp_delay_value; - unsigned int offset_cncl_path; - unsigned int hs_extmute:1; - int hs_extmute_gpio; -}; - -struct twl4030_vibra_data { - unsigned int coexist; -}; - -struct twl4030_audio_data { - unsigned int audio_mclk; - struct twl4030_codec_data *codec; - struct twl4030_vibra_data *vibra; - - /* twl6040 */ - int audpwron_gpio; /* audio power-on gpio */ - int naudint_irq; /* audio interrupt */ - unsigned int irq_base; -}; - -struct twl4030_platform_data { - struct twl4030_clock_init_data *clock; - struct twl4030_bci_platform_data *bci; - struct twl4030_gpio_platform_data *gpio; - struct twl4030_madc_platform_data *madc; - struct twl4030_keypad_data *keypad; - struct twl4030_usb_data *usb; - struct twl4030_power_data *power; - struct twl4030_audio_data *audio; - - /* Common LDO regulators for TWL4030/TWL6030 */ - struct regulator_init_data *vdac; - struct regulator_init_data *vaux1; - struct regulator_init_data *vaux2; - struct regulator_init_data *vaux3; - struct regulator_init_data *vdd1; - struct regulator_init_data *vdd2; - struct regulator_init_data *vdd3; - /* TWL4030 LDO regulators */ - struct regulator_init_data *vpll1; - struct regulator_init_data *vpll2; - struct regulator_init_data *vmmc1; - struct regulator_init_data *vmmc2; - struct regulator_init_data *vsim; - struct regulator_init_data *vaux4; - struct regulator_init_data *vio; - struct regulator_init_data *vintana1; - struct regulator_init_data *vintana2; - struct regulator_init_data *vintdig; - /* TWL6030 LDO regulators */ - struct regulator_init_data *vmmc; - struct regulator_init_data *vpp; - struct regulator_init_data *vusim; - struct regulator_init_data *vana; - struct regulator_init_data *vcxio; - struct regulator_init_data *vusb; - struct regulator_init_data *clk32kg; - struct regulator_init_data *v1v8; - struct regulator_init_data *v2v1; - /* TWL6032 LDO regulators */ - struct regulator_init_data *ldo1; - struct regulator_init_data *ldo2; - struct regulator_init_data *ldo3; - struct regulator_init_data *ldo4; - struct regulator_init_data *ldo5; - struct regulator_init_data *ldo6; - struct regulator_init_data *ldo7; - struct regulator_init_data *ldoln; - struct regulator_init_data *ldousb; - /* TWL6032 DCDC regulators */ - struct regulator_init_data *smps3; - struct regulator_init_data *smps4; - struct regulator_init_data *vio6025; -}; - -struct twl_regulator_driver_data { - int (*set_voltage)(void *data, int target_uV); - int (*get_voltage)(void *data); - void *data; - unsigned long features; -}; -/* chip-specific feature flags, for twl_regulator_driver_data.features */ -#define TWL4030_VAUX2 BIT(0) /* pre-5030 voltage ranges */ -#define TPS_SUBSET BIT(1) /* tps659[23]0 have fewer LDOs */ -#define TWL5031 BIT(2) /* twl5031 has different registers */ -#define TWL6030_CLASS BIT(3) /* TWL6030 class */ -#define TWL6032_SUBCLASS BIT(4) /* TWL6032 has changed registers */ -#define TWL4030_ALLOW_UNSUPPORTED BIT(5) /* Some voltages are possible - * but not officially supported. - * This flag is necessary to - * enable them. - */ - -/*----------------------------------------------------------------------*/ - -int twl4030_sih_setup(struct device *dev, int module, int irq_base); - -/* Offsets to Power Registers */ -#define TWL4030_VDAC_DEV_GRP 0x3B -#define TWL4030_VDAC_DEDICATED 0x3E -#define TWL4030_VAUX1_DEV_GRP 0x17 -#define TWL4030_VAUX1_DEDICATED 0x1A -#define TWL4030_VAUX2_DEV_GRP 0x1B -#define TWL4030_VAUX2_DEDICATED 0x1E -#define TWL4030_VAUX3_DEV_GRP 0x1F -#define TWL4030_VAUX3_DEDICATED 0x22 - -static inline int twl4030charger_usb_en(int enable) { return 0; } - -/*----------------------------------------------------------------------*/ - -/* Linux-specific regulator identifiers ... for now, we only support - * the LDOs, and leave the three buck converters alone. VDD1 and VDD2 - * need to tie into hardware based voltage scaling (cpufreq etc), while - * VIO is generally fixed. - */ - -/* TWL4030 SMPS/LDO's */ -/* EXTERNAL dc-to-dc buck converters */ -#define TWL4030_REG_VDD1 0 -#define TWL4030_REG_VDD2 1 -#define TWL4030_REG_VIO 2 - -/* EXTERNAL LDOs */ -#define TWL4030_REG_VDAC 3 -#define TWL4030_REG_VPLL1 4 -#define TWL4030_REG_VPLL2 5 /* not on all chips */ -#define TWL4030_REG_VMMC1 6 -#define TWL4030_REG_VMMC2 7 /* not on all chips */ -#define TWL4030_REG_VSIM 8 /* not on all chips */ -#define TWL4030_REG_VAUX1 9 /* not on all chips */ -#define TWL4030_REG_VAUX2_4030 10 /* (twl4030-specific) */ -#define TWL4030_REG_VAUX2 11 /* (twl5030 and newer) */ -#define TWL4030_REG_VAUX3 12 /* not on all chips */ -#define TWL4030_REG_VAUX4 13 /* not on all chips */ - -/* INTERNAL LDOs */ -#define TWL4030_REG_VINTANA1 14 -#define TWL4030_REG_VINTANA2 15 -#define TWL4030_REG_VINTDIG 16 -#define TWL4030_REG_VUSB1V5 17 -#define TWL4030_REG_VUSB1V8 18 -#define TWL4030_REG_VUSB3V1 19 - -/* TWL6030 SMPS/LDO's */ -/* EXTERNAL dc-to-dc buck convertor controllable via SR */ -#define TWL6030_REG_VDD1 30 -#define TWL6030_REG_VDD2 31 -#define TWL6030_REG_VDD3 32 - -/* Non SR compliant dc-to-dc buck convertors */ -#define TWL6030_REG_VMEM 33 -#define TWL6030_REG_V2V1 34 -#define TWL6030_REG_V1V29 35 -#define TWL6030_REG_V1V8 36 - -/* EXTERNAL LDOs */ -#define TWL6030_REG_VAUX1_6030 37 -#define TWL6030_REG_VAUX2_6030 38 -#define TWL6030_REG_VAUX3_6030 39 -#define TWL6030_REG_VMMC 40 -#define TWL6030_REG_VPP 41 -#define TWL6030_REG_VUSIM 42 -#define TWL6030_REG_VANA 43 -#define TWL6030_REG_VCXIO 44 -#define TWL6030_REG_VDAC 45 -#define TWL6030_REG_VUSB 46 - -/* INTERNAL LDOs */ -#define TWL6030_REG_VRTC 47 -#define TWL6030_REG_CLK32KG 48 - -/* LDOs on 6025 have different names */ -#define TWL6032_REG_LDO2 49 -#define TWL6032_REG_LDO4 50 -#define TWL6032_REG_LDO3 51 -#define TWL6032_REG_LDO5 52 -#define TWL6032_REG_LDO1 53 -#define TWL6032_REG_LDO7 54 -#define TWL6032_REG_LDO6 55 -#define TWL6032_REG_LDOLN 56 -#define TWL6032_REG_LDOUSB 57 - -/* 6025 DCDC supplies */ -#define TWL6032_REG_SMPS3 58 -#define TWL6032_REG_SMPS4 59 -#define TWL6032_REG_VIO 60 - - -#endif /* End of __TWL4030_H */ diff --git a/include/linux/mfd/twl.h b/include/linux/mfd/twl.h new file mode 100644 index 000000000000..9ad7828d9d34 --- /dev/null +++ b/include/linux/mfd/twl.h @@ -0,0 +1,876 @@ +/* + * twl4030.h - header for TWL4030 PM and audio CODEC device + * + * Copyright (C) 2005-2006 Texas Instruments, Inc. + * + * Based on tlv320aic23.c: + * Copyright (c) by Kai Svahn + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ + +#ifndef __TWL_H_ +#define __TWL_H_ + +#include +#include + +/* + * Using the twl4030 core we address registers using a pair + * { module id, relative register offset } + * which that core then maps to the relevant + * { i2c slave, absolute register address } + * + * The module IDs are meaningful only to the twl4030 core code, + * which uses them as array indices to look up the first register + * address each module uses within a given i2c slave. + */ + +/* Module IDs for similar functionalities found in twl4030/twl6030 */ +enum twl_module_ids { + TWL_MODULE_USB, + TWL_MODULE_PIH, + TWL_MODULE_MAIN_CHARGE, + TWL_MODULE_PM_MASTER, + TWL_MODULE_PM_RECEIVER, + + TWL_MODULE_RTC, + TWL_MODULE_PWM, + TWL_MODULE_LED, + TWL_MODULE_SECURED_REG, + + TWL_MODULE_LAST, +}; + +/* Modules only available in twl4030 series */ +enum twl4030_module_ids { + TWL4030_MODULE_AUDIO_VOICE = TWL_MODULE_LAST, + TWL4030_MODULE_GPIO, + TWL4030_MODULE_INTBR, + TWL4030_MODULE_TEST, + TWL4030_MODULE_KEYPAD, + + TWL4030_MODULE_MADC, + TWL4030_MODULE_INTERRUPTS, + TWL4030_MODULE_PRECHARGE, + TWL4030_MODULE_BACKUP, + TWL4030_MODULE_INT, + + TWL5031_MODULE_ACCESSORY, + TWL5031_MODULE_INTERRUPTS, + + TWL4030_MODULE_LAST, +}; + +/* Modules only available in twl6030 series */ +enum twl6030_module_ids { + TWL6030_MODULE_ID0 = TWL_MODULE_LAST, + TWL6030_MODULE_ID1, + TWL6030_MODULE_ID2, + TWL6030_MODULE_GPADC, + TWL6030_MODULE_GASGAUGE, + + TWL6030_MODULE_LAST, +}; + +/* Until the clients has been converted to use TWL_MODULE_LED */ +#define TWL4030_MODULE_LED TWL_MODULE_LED + +#define GPIO_INTR_OFFSET 0 +#define KEYPAD_INTR_OFFSET 1 +#define BCI_INTR_OFFSET 2 +#define MADC_INTR_OFFSET 3 +#define USB_INTR_OFFSET 4 +#define CHARGERFAULT_INTR_OFFSET 5 +#define BCI_PRES_INTR_OFFSET 9 +#define USB_PRES_INTR_OFFSET 10 +#define RTC_INTR_OFFSET 11 + +/* + * Offset from TWL6030_IRQ_BASE / pdata->irq_base + */ +#define PWR_INTR_OFFSET 0 +#define HOTDIE_INTR_OFFSET 12 +#define SMPSLDO_INTR_OFFSET 13 +#define BATDETECT_INTR_OFFSET 14 +#define SIMDETECT_INTR_OFFSET 15 +#define MMCDETECT_INTR_OFFSET 16 +#define GASGAUGE_INTR_OFFSET 17 +#define USBOTG_INTR_OFFSET 4 +#define CHARGER_INTR_OFFSET 2 +#define RSV_INTR_OFFSET 0 + +/* INT register offsets */ +#define REG_INT_STS_A 0x00 +#define REG_INT_STS_B 0x01 +#define REG_INT_STS_C 0x02 + +#define REG_INT_MSK_LINE_A 0x03 +#define REG_INT_MSK_LINE_B 0x04 +#define REG_INT_MSK_LINE_C 0x05 + +#define REG_INT_MSK_STS_A 0x06 +#define REG_INT_MSK_STS_B 0x07 +#define REG_INT_MSK_STS_C 0x08 + +/* MASK INT REG GROUP A */ +#define TWL6030_PWR_INT_MASK 0x07 +#define TWL6030_RTC_INT_MASK 0x18 +#define TWL6030_HOTDIE_INT_MASK 0x20 +#define TWL6030_SMPSLDOA_INT_MASK 0xC0 + +/* MASK INT REG GROUP B */ +#define TWL6030_SMPSLDOB_INT_MASK 0x01 +#define TWL6030_BATDETECT_INT_MASK 0x02 +#define TWL6030_SIMDETECT_INT_MASK 0x04 +#define TWL6030_MMCDETECT_INT_MASK 0x08 +#define TWL6030_GPADC_INT_MASK 0x60 +#define TWL6030_GASGAUGE_INT_MASK 0x80 + +/* MASK INT REG GROUP C */ +#define TWL6030_USBOTG_INT_MASK 0x0F +#define TWL6030_CHARGER_CTRL_INT_MASK 0x10 +#define TWL6030_CHARGER_FAULT_INT_MASK 0x60 + +#define TWL6030_MMCCTRL 0xEE +#define VMMC_AUTO_OFF (0x1 << 3) +#define SW_FC (0x1 << 2) +#define STS_MMC 0x1 + +#define TWL6030_CFG_INPUT_PUPD3 0xF2 +#define MMC_PU (0x1 << 3) +#define MMC_PD (0x1 << 2) + +#define TWL_SIL_TYPE(rev) ((rev) & 0x00FFFFFF) +#define TWL_SIL_REV(rev) ((rev) >> 24) +#define TWL_SIL_5030 0x09002F +#define TWL5030_REV_1_0 0x00 +#define TWL5030_REV_1_1 0x10 +#define TWL5030_REV_1_2 0x30 + +#define TWL4030_CLASS_ID 0x4030 +#define TWL6030_CLASS_ID 0x6030 +unsigned int twl_rev(void); +#define GET_TWL_REV (twl_rev()) +#define TWL_CLASS_IS(class, id) \ +static inline int twl_class_is_ ##class(void) \ +{ \ + return ((id) == (GET_TWL_REV)) ? 1 : 0; \ +} + +TWL_CLASS_IS(4030, TWL4030_CLASS_ID) +TWL_CLASS_IS(6030, TWL6030_CLASS_ID) + +/* Set the regcache bypass for the regmap associated with the nodule */ +int twl_set_regcache_bypass(u8 mod_no, bool enable); + +/* + * Read and write several 8-bit registers at once. + */ +int twl_i2c_write(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes); +int twl_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes); + +/* + * Read and write single 8-bit registers + */ +static inline int twl_i2c_write_u8(u8 mod_no, u8 val, u8 reg) { + return twl_i2c_write(mod_no, &val, reg, 1); +} + +static inline int twl_i2c_read_u8(u8 mod_no, u8 *val, u8 reg) { + return twl_i2c_read(mod_no, val, reg, 1); +} + +static inline int twl_i2c_write_u16(u8 mod_no, u16 val, u8 reg) { + val = cpu_to_le16(val); + return twl_i2c_write(mod_no, (u8*) &val, reg, 2); +} + +static inline int twl_i2c_read_u16(u8 mod_no, u16 *val, u8 reg) { + int ret; + ret = twl_i2c_read(mod_no, (u8*) val, reg, 2); + *val = le16_to_cpu(*val); + return ret; +} + +int twl_get_type(void); +int twl_get_version(void); +int twl_get_hfclk_rate(void); + +int twl6030_interrupt_unmask(u8 bit_mask, u8 offset); +int twl6030_interrupt_mask(u8 bit_mask, u8 offset); + +/* Card detect Configuration for MMC1 Controller on OMAP4 */ +#ifdef CONFIG_TWL4030_CORE +int twl6030_mmc_card_detect_config(void); +#else +static inline int twl6030_mmc_card_detect_config(void) +{ + pr_debug("twl6030_mmc_card_detect_config not supported\n"); + return 0; +} +#endif + +/* MMC1 Controller on OMAP4 uses Phoenix irq for Card detect */ +#ifdef CONFIG_TWL4030_CORE +int twl6030_mmc_card_detect(struct device *dev, int slot); +#else +static inline int twl6030_mmc_card_detect(struct device *dev, int slot) +{ + pr_debug("Call back twl6030_mmc_card_detect not supported\n"); + return -EIO; +} +#endif +/*----------------------------------------------------------------------*/ + +/* + * NOTE: at up to 1024 registers, this is a big chip. + * + * Avoid putting register declarations in this file, instead of into + * a driver-private file, unless some of the registers in a block + * need to be shared with other drivers. One example is blocks that + * have Secondary IRQ Handler (SIH) registers. + */ + +#define TWL4030_SIH_CTRL_EXCLEN_MASK BIT(0) +#define TWL4030_SIH_CTRL_PENDDIS_MASK BIT(1) +#define TWL4030_SIH_CTRL_COR_MASK BIT(2) + +/*----------------------------------------------------------------------*/ + +/* + * GPIO Block Register offsets (use TWL4030_MODULE_GPIO) + */ + +#define REG_GPIODATAIN1 0x0 +#define REG_GPIODATAIN2 0x1 +#define REG_GPIODATAIN3 0x2 +#define REG_GPIODATADIR1 0x3 +#define REG_GPIODATADIR2 0x4 +#define REG_GPIODATADIR3 0x5 +#define REG_GPIODATAOUT1 0x6 +#define REG_GPIODATAOUT2 0x7 +#define REG_GPIODATAOUT3 0x8 +#define REG_CLEARGPIODATAOUT1 0x9 +#define REG_CLEARGPIODATAOUT2 0xA +#define REG_CLEARGPIODATAOUT3 0xB +#define REG_SETGPIODATAOUT1 0xC +#define REG_SETGPIODATAOUT2 0xD +#define REG_SETGPIODATAOUT3 0xE +#define REG_GPIO_DEBEN1 0xF +#define REG_GPIO_DEBEN2 0x10 +#define REG_GPIO_DEBEN3 0x11 +#define REG_GPIO_CTRL 0x12 +#define REG_GPIOPUPDCTR1 0x13 +#define REG_GPIOPUPDCTR2 0x14 +#define REG_GPIOPUPDCTR3 0x15 +#define REG_GPIOPUPDCTR4 0x16 +#define REG_GPIOPUPDCTR5 0x17 +#define REG_GPIO_ISR1A 0x19 +#define REG_GPIO_ISR2A 0x1A +#define REG_GPIO_ISR3A 0x1B +#define REG_GPIO_IMR1A 0x1C +#define REG_GPIO_IMR2A 0x1D +#define REG_GPIO_IMR3A 0x1E +#define REG_GPIO_ISR1B 0x1F +#define REG_GPIO_ISR2B 0x20 +#define REG_GPIO_ISR3B 0x21 +#define REG_GPIO_IMR1B 0x22 +#define REG_GPIO_IMR2B 0x23 +#define REG_GPIO_IMR3B 0x24 +#define REG_GPIO_EDR1 0x28 +#define REG_GPIO_EDR2 0x29 +#define REG_GPIO_EDR3 0x2A +#define REG_GPIO_EDR4 0x2B +#define REG_GPIO_EDR5 0x2C +#define REG_GPIO_SIH_CTRL 0x2D + +/* Up to 18 signals are available as GPIOs, when their + * pins are not assigned to another use (such as ULPI/USB). + */ +#define TWL4030_GPIO_MAX 18 + +/*----------------------------------------------------------------------*/ + +/*Interface Bit Register (INTBR) offsets + *(Use TWL_4030_MODULE_INTBR) + */ + +#define REG_IDCODE_7_0 0x00 +#define REG_IDCODE_15_8 0x01 +#define REG_IDCODE_16_23 0x02 +#define REG_IDCODE_31_24 0x03 +#define REG_GPPUPDCTR1 0x0F +#define REG_UNLOCK_TEST_REG 0x12 + +/*I2C1 and I2C4(SR) SDA/SCL pull-up control bits */ + +#define I2C_SCL_CTRL_PU BIT(0) +#define I2C_SDA_CTRL_PU BIT(2) +#define SR_I2C_SCL_CTRL_PU BIT(4) +#define SR_I2C_SDA_CTRL_PU BIT(6) + +#define TWL_EEPROM_R_UNLOCK 0x49 + +/*----------------------------------------------------------------------*/ + +/* + * Keypad register offsets (use TWL4030_MODULE_KEYPAD) + * ... SIH/interrupt only + */ + +#define TWL4030_KEYPAD_KEYP_ISR1 0x11 +#define TWL4030_KEYPAD_KEYP_IMR1 0x12 +#define TWL4030_KEYPAD_KEYP_ISR2 0x13 +#define TWL4030_KEYPAD_KEYP_IMR2 0x14 +#define TWL4030_KEYPAD_KEYP_SIR 0x15 /* test register */ +#define TWL4030_KEYPAD_KEYP_EDR 0x16 +#define TWL4030_KEYPAD_KEYP_SIH_CTRL 0x17 + +/*----------------------------------------------------------------------*/ + +/* + * Multichannel ADC register offsets (use TWL4030_MODULE_MADC) + * ... SIH/interrupt only + */ + +#define TWL4030_MADC_ISR1 0x61 +#define TWL4030_MADC_IMR1 0x62 +#define TWL4030_MADC_ISR2 0x63 +#define TWL4030_MADC_IMR2 0x64 +#define TWL4030_MADC_SIR 0x65 /* test register */ +#define TWL4030_MADC_EDR 0x66 +#define TWL4030_MADC_SIH_CTRL 0x67 + +/*----------------------------------------------------------------------*/ + +/* + * Battery charger register offsets (use TWL4030_MODULE_INTERRUPTS) + */ + +#define TWL4030_INTERRUPTS_BCIISR1A 0x0 +#define TWL4030_INTERRUPTS_BCIISR2A 0x1 +#define TWL4030_INTERRUPTS_BCIIMR1A 0x2 +#define TWL4030_INTERRUPTS_BCIIMR2A 0x3 +#define TWL4030_INTERRUPTS_BCIISR1B 0x4 +#define TWL4030_INTERRUPTS_BCIISR2B 0x5 +#define TWL4030_INTERRUPTS_BCIIMR1B 0x6 +#define TWL4030_INTERRUPTS_BCIIMR2B 0x7 +#define TWL4030_INTERRUPTS_BCISIR1 0x8 /* test register */ +#define TWL4030_INTERRUPTS_BCISIR2 0x9 /* test register */ +#define TWL4030_INTERRUPTS_BCIEDR1 0xa +#define TWL4030_INTERRUPTS_BCIEDR2 0xb +#define TWL4030_INTERRUPTS_BCIEDR3 0xc +#define TWL4030_INTERRUPTS_BCISIHCTRL 0xd + +/*----------------------------------------------------------------------*/ + +/* + * Power Interrupt block register offsets (use TWL4030_MODULE_INT) + */ + +#define TWL4030_INT_PWR_ISR1 0x0 +#define TWL4030_INT_PWR_IMR1 0x1 +#define TWL4030_INT_PWR_ISR2 0x2 +#define TWL4030_INT_PWR_IMR2 0x3 +#define TWL4030_INT_PWR_SIR 0x4 /* test register */ +#define TWL4030_INT_PWR_EDR1 0x5 +#define TWL4030_INT_PWR_EDR2 0x6 +#define TWL4030_INT_PWR_SIH_CTRL 0x7 + +/*----------------------------------------------------------------------*/ + +/* + * Accessory Interrupts + */ +#define TWL5031_ACIIMR_LSB 0x05 +#define TWL5031_ACIIMR_MSB 0x06 +#define TWL5031_ACIIDR_LSB 0x07 +#define TWL5031_ACIIDR_MSB 0x08 +#define TWL5031_ACCISR1 0x0F +#define TWL5031_ACCIMR1 0x10 +#define TWL5031_ACCISR2 0x11 +#define TWL5031_ACCIMR2 0x12 +#define TWL5031_ACCSIR 0x13 +#define TWL5031_ACCEDR1 0x14 +#define TWL5031_ACCSIHCTRL 0x15 + +/*----------------------------------------------------------------------*/ + +/* + * Battery Charger Controller + */ + +#define TWL5031_INTERRUPTS_BCIISR1 0x0 +#define TWL5031_INTERRUPTS_BCIIMR1 0x1 +#define TWL5031_INTERRUPTS_BCIISR2 0x2 +#define TWL5031_INTERRUPTS_BCIIMR2 0x3 +#define TWL5031_INTERRUPTS_BCISIR 0x4 +#define TWL5031_INTERRUPTS_BCIEDR1 0x5 +#define TWL5031_INTERRUPTS_BCIEDR2 0x6 +#define TWL5031_INTERRUPTS_BCISIHCTRL 0x7 + +/*----------------------------------------------------------------------*/ + +/* + * PM Master module register offsets (use TWL4030_MODULE_PM_MASTER) + */ + +#define TWL4030_PM_MASTER_CFG_P1_TRANSITION 0x00 +#define TWL4030_PM_MASTER_CFG_P2_TRANSITION 0x01 +#define TWL4030_PM_MASTER_CFG_P3_TRANSITION 0x02 +#define TWL4030_PM_MASTER_CFG_P123_TRANSITION 0x03 +#define TWL4030_PM_MASTER_STS_BOOT 0x04 +#define TWL4030_PM_MASTER_CFG_BOOT 0x05 +#define TWL4030_PM_MASTER_SHUNDAN 0x06 +#define TWL4030_PM_MASTER_BOOT_BCI 0x07 +#define TWL4030_PM_MASTER_CFG_PWRANA1 0x08 +#define TWL4030_PM_MASTER_CFG_PWRANA2 0x09 +#define TWL4030_PM_MASTER_BACKUP_MISC_STS 0x0b +#define TWL4030_PM_MASTER_BACKUP_MISC_CFG 0x0c +#define TWL4030_PM_MASTER_BACKUP_MISC_TST 0x0d +#define TWL4030_PM_MASTER_PROTECT_KEY 0x0e +#define TWL4030_PM_MASTER_STS_HW_CONDITIONS 0x0f +#define TWL4030_PM_MASTER_P1_SW_EVENTS 0x10 +#define TWL4030_PM_MASTER_P2_SW_EVENTS 0x11 +#define TWL4030_PM_MASTER_P3_SW_EVENTS 0x12 +#define TWL4030_PM_MASTER_STS_P123_STATE 0x13 +#define TWL4030_PM_MASTER_PB_CFG 0x14 +#define TWL4030_PM_MASTER_PB_WORD_MSB 0x15 +#define TWL4030_PM_MASTER_PB_WORD_LSB 0x16 +#define TWL4030_PM_MASTER_SEQ_ADD_W2P 0x1c +#define TWL4030_PM_MASTER_SEQ_ADD_P2A 0x1d +#define TWL4030_PM_MASTER_SEQ_ADD_A2W 0x1e +#define TWL4030_PM_MASTER_SEQ_ADD_A2S 0x1f +#define TWL4030_PM_MASTER_SEQ_ADD_S2A12 0x20 +#define TWL4030_PM_MASTER_SEQ_ADD_S2A3 0x21 +#define TWL4030_PM_MASTER_SEQ_ADD_WARM 0x22 +#define TWL4030_PM_MASTER_MEMORY_ADDRESS 0x23 +#define TWL4030_PM_MASTER_MEMORY_DATA 0x24 + +#define TWL4030_PM_MASTER_KEY_CFG1 0xc0 +#define TWL4030_PM_MASTER_KEY_CFG2 0x0c + +#define TWL4030_PM_MASTER_KEY_TST1 0xe0 +#define TWL4030_PM_MASTER_KEY_TST2 0x0e + +#define TWL4030_PM_MASTER_GLOBAL_TST 0xb6 + +/*----------------------------------------------------------------------*/ + +/* Power bus message definitions */ + +/* The TWL4030/5030 splits its power-management resources (the various + * regulators, clock and reset lines) into 3 processor groups - P1, P2 and + * P3. These groups can then be configured to transition between sleep, wait-on + * and active states by sending messages to the power bus. See Section 5.4.2 + * Power Resources of TWL4030 TRM + */ + +/* Processor groups */ +#define DEV_GRP_NULL 0x0 +#define DEV_GRP_P1 0x1 /* P1: all OMAP devices */ +#define DEV_GRP_P2 0x2 /* P2: all Modem devices */ +#define DEV_GRP_P3 0x4 /* P3: all peripheral devices */ + +/* Resource groups */ +#define RES_GRP_RES 0x0 /* Reserved */ +#define RES_GRP_PP 0x1 /* Power providers */ +#define RES_GRP_RC 0x2 /* Reset and control */ +#define RES_GRP_PP_RC 0x3 +#define RES_GRP_PR 0x4 /* Power references */ +#define RES_GRP_PP_PR 0x5 +#define RES_GRP_RC_PR 0x6 +#define RES_GRP_ALL 0x7 /* All resource groups */ + +#define RES_TYPE2_R0 0x0 +#define RES_TYPE2_R1 0x1 +#define RES_TYPE2_R2 0x2 + +#define RES_TYPE_R0 0x0 +#define RES_TYPE_ALL 0x7 + +/* Resource states */ +#define RES_STATE_WRST 0xF +#define RES_STATE_ACTIVE 0xE +#define RES_STATE_SLEEP 0x8 +#define RES_STATE_OFF 0x0 + +/* Power resources */ + +/* Power providers */ +#define RES_VAUX1 1 +#define RES_VAUX2 2 +#define RES_VAUX3 3 +#define RES_VAUX4 4 +#define RES_VMMC1 5 +#define RES_VMMC2 6 +#define RES_VPLL1 7 +#define RES_VPLL2 8 +#define RES_VSIM 9 +#define RES_VDAC 10 +#define RES_VINTANA1 11 +#define RES_VINTANA2 12 +#define RES_VINTDIG 13 +#define RES_VIO 14 +#define RES_VDD1 15 +#define RES_VDD2 16 +#define RES_VUSB_1V5 17 +#define RES_VUSB_1V8 18 +#define RES_VUSB_3V1 19 +#define RES_VUSBCP 20 +#define RES_REGEN 21 +/* Reset and control */ +#define RES_NRES_PWRON 22 +#define RES_CLKEN 23 +#define RES_SYSEN 24 +#define RES_HFCLKOUT 25 +#define RES_32KCLKOUT 26 +#define RES_RESET 27 +/* Power Reference */ +#define RES_MAIN_REF 28 + +#define TOTAL_RESOURCES 28 +/* + * Power Bus Message Format ... these can be sent individually by Linux, + * but are usually part of downloaded scripts that are run when various + * power events are triggered. + * + * Broadcast Message (16 Bits): + * DEV_GRP[15:13] MT[12] RES_GRP[11:9] RES_TYPE2[8:7] RES_TYPE[6:4] + * RES_STATE[3:0] + * + * Singular Message (16 Bits): + * DEV_GRP[15:13] MT[12] RES_ID[11:4] RES_STATE[3:0] + */ + +#define MSG_BROADCAST(devgrp, grp, type, type2, state) \ + ( (devgrp) << 13 | 1 << 12 | (grp) << 9 | (type2) << 7 \ + | (type) << 4 | (state)) + +#define MSG_SINGULAR(devgrp, id, state) \ + ((devgrp) << 13 | 0 << 12 | (id) << 4 | (state)) + +#define MSG_BROADCAST_ALL(devgrp, state) \ + ((devgrp) << 5 | (state)) + +#define MSG_BROADCAST_REF MSG_BROADCAST_ALL +#define MSG_BROADCAST_PROV MSG_BROADCAST_ALL +#define MSG_BROADCAST__CLK_RST MSG_BROADCAST_ALL +/*----------------------------------------------------------------------*/ + +struct twl4030_clock_init_data { + bool ck32k_lowpwr_enable; +}; + +struct twl4030_bci_platform_data { + int *battery_tmp_tbl; + unsigned int tblsize; + int bb_uvolt; /* voltage to charge backup battery */ + int bb_uamp; /* current for backup battery charging */ +}; + +/* TWL4030_GPIO_MAX (18) GPIOs, with interrupts */ +struct twl4030_gpio_platform_data { + /* package the two LED signals as output-only GPIOs? */ + bool use_leds; + + /* gpio-n should control VMMC(n+1) if BIT(n) in mmc_cd is set */ + u8 mmc_cd; + + /* if BIT(N) is set, or VMMC(n+1) is linked, debounce GPIO-N */ + u32 debounce; + + /* For gpio-N, bit (1 << N) in "pullups" is set if that pullup + * should be enabled. Else, if that bit is set in "pulldowns", + * that pulldown is enabled. Don't waste power by letting any + * digital inputs float... + */ + u32 pullups; + u32 pulldowns; + + int (*setup)(struct device *dev, + unsigned gpio, unsigned ngpio); + int (*teardown)(struct device *dev, + unsigned gpio, unsigned ngpio); +}; + +struct twl4030_madc_platform_data { + int irq_line; +}; + +/* Boards have unique mappings of {row, col} --> keycode. + * Column and row are 8 bits each, but range only from 0..7. + * a PERSISTENT_KEY is "always on" and never reported. + */ +#define PERSISTENT_KEY(r, c) KEY((r), (c), KEY_RESERVED) + +struct twl4030_keypad_data { + const struct matrix_keymap_data *keymap_data; + unsigned rows; + unsigned cols; + bool rep; +}; + +enum twl4030_usb_mode { + T2_USB_MODE_ULPI = 1, + T2_USB_MODE_CEA2011_3PIN = 2, +}; + +struct twl4030_usb_data { + enum twl4030_usb_mode usb_mode; + unsigned long features; + + int (*phy_init)(struct device *dev); + int (*phy_exit)(struct device *dev); + /* Power on/off the PHY */ + int (*phy_power)(struct device *dev, int iD, int on); + /* enable/disable phy clocks */ + int (*phy_set_clock)(struct device *dev, int on); + /* suspend/resume of phy */ + int (*phy_suspend)(struct device *dev, int suspend); +}; + +struct twl4030_ins { + u16 pmb_message; + u8 delay; +}; + +struct twl4030_script { + struct twl4030_ins *script; + unsigned size; + u8 flags; +#define TWL4030_WRST_SCRIPT (1<<0) +#define TWL4030_WAKEUP12_SCRIPT (1<<1) +#define TWL4030_WAKEUP3_SCRIPT (1<<2) +#define TWL4030_SLEEP_SCRIPT (1<<3) +}; + +struct twl4030_resconfig { + u8 resource; + u8 devgroup; /* Processor group that Power resource belongs to */ + u8 type; /* Power resource addressed, 6 / broadcast message */ + u8 type2; /* Power resource addressed, 3 / broadcast message */ + u8 remap_off; /* off state remapping */ + u8 remap_sleep; /* sleep state remapping */ +}; + +struct twl4030_power_data { + struct twl4030_script **scripts; + unsigned num; + struct twl4030_resconfig *resource_config; + struct twl4030_resconfig *board_config; +#define TWL4030_RESCONFIG_UNDEF ((u8)-1) + bool use_poweroff; /* Board is wired for TWL poweroff */ + bool ac_charger_quirk; /* Disable AC charger on board */ +}; + +extern int twl4030_remove_script(u8 flags); +extern void twl4030_power_off(void); + +struct twl4030_codec_data { + unsigned int digimic_delay; /* in ms */ + unsigned int ramp_delay_value; + unsigned int offset_cncl_path; + unsigned int hs_extmute:1; + int hs_extmute_gpio; +}; + +struct twl4030_vibra_data { + unsigned int coexist; +}; + +struct twl4030_audio_data { + unsigned int audio_mclk; + struct twl4030_codec_data *codec; + struct twl4030_vibra_data *vibra; + + /* twl6040 */ + int audpwron_gpio; /* audio power-on gpio */ + int naudint_irq; /* audio interrupt */ + unsigned int irq_base; +}; + +struct twl4030_platform_data { + struct twl4030_clock_init_data *clock; + struct twl4030_bci_platform_data *bci; + struct twl4030_gpio_platform_data *gpio; + struct twl4030_madc_platform_data *madc; + struct twl4030_keypad_data *keypad; + struct twl4030_usb_data *usb; + struct twl4030_power_data *power; + struct twl4030_audio_data *audio; + + /* Common LDO regulators for TWL4030/TWL6030 */ + struct regulator_init_data *vdac; + struct regulator_init_data *vaux1; + struct regulator_init_data *vaux2; + struct regulator_init_data *vaux3; + struct regulator_init_data *vdd1; + struct regulator_init_data *vdd2; + struct regulator_init_data *vdd3; + /* TWL4030 LDO regulators */ + struct regulator_init_data *vpll1; + struct regulator_init_data *vpll2; + struct regulator_init_data *vmmc1; + struct regulator_init_data *vmmc2; + struct regulator_init_data *vsim; + struct regulator_init_data *vaux4; + struct regulator_init_data *vio; + struct regulator_init_data *vintana1; + struct regulator_init_data *vintana2; + struct regulator_init_data *vintdig; + /* TWL6030 LDO regulators */ + struct regulator_init_data *vmmc; + struct regulator_init_data *vpp; + struct regulator_init_data *vusim; + struct regulator_init_data *vana; + struct regulator_init_data *vcxio; + struct regulator_init_data *vusb; + struct regulator_init_data *clk32kg; + struct regulator_init_data *v1v8; + struct regulator_init_data *v2v1; + /* TWL6032 LDO regulators */ + struct regulator_init_data *ldo1; + struct regulator_init_data *ldo2; + struct regulator_init_data *ldo3; + struct regulator_init_data *ldo4; + struct regulator_init_data *ldo5; + struct regulator_init_data *ldo6; + struct regulator_init_data *ldo7; + struct regulator_init_data *ldoln; + struct regulator_init_data *ldousb; + /* TWL6032 DCDC regulators */ + struct regulator_init_data *smps3; + struct regulator_init_data *smps4; + struct regulator_init_data *vio6025; +}; + +struct twl_regulator_driver_data { + int (*set_voltage)(void *data, int target_uV); + int (*get_voltage)(void *data); + void *data; + unsigned long features; +}; +/* chip-specific feature flags, for twl_regulator_driver_data.features */ +#define TWL4030_VAUX2 BIT(0) /* pre-5030 voltage ranges */ +#define TPS_SUBSET BIT(1) /* tps659[23]0 have fewer LDOs */ +#define TWL5031 BIT(2) /* twl5031 has different registers */ +#define TWL6030_CLASS BIT(3) /* TWL6030 class */ +#define TWL6032_SUBCLASS BIT(4) /* TWL6032 has changed registers */ +#define TWL4030_ALLOW_UNSUPPORTED BIT(5) /* Some voltages are possible + * but not officially supported. + * This flag is necessary to + * enable them. + */ + +/*----------------------------------------------------------------------*/ + +int twl4030_sih_setup(struct device *dev, int module, int irq_base); + +/* Offsets to Power Registers */ +#define TWL4030_VDAC_DEV_GRP 0x3B +#define TWL4030_VDAC_DEDICATED 0x3E +#define TWL4030_VAUX1_DEV_GRP 0x17 +#define TWL4030_VAUX1_DEDICATED 0x1A +#define TWL4030_VAUX2_DEV_GRP 0x1B +#define TWL4030_VAUX2_DEDICATED 0x1E +#define TWL4030_VAUX3_DEV_GRP 0x1F +#define TWL4030_VAUX3_DEDICATED 0x22 + +static inline int twl4030charger_usb_en(int enable) { return 0; } + +/*----------------------------------------------------------------------*/ + +/* Linux-specific regulator identifiers ... for now, we only support + * the LDOs, and leave the three buck converters alone. VDD1 and VDD2 + * need to tie into hardware based voltage scaling (cpufreq etc), while + * VIO is generally fixed. + */ + +/* TWL4030 SMPS/LDO's */ +/* EXTERNAL dc-to-dc buck converters */ +#define TWL4030_REG_VDD1 0 +#define TWL4030_REG_VDD2 1 +#define TWL4030_REG_VIO 2 + +/* EXTERNAL LDOs */ +#define TWL4030_REG_VDAC 3 +#define TWL4030_REG_VPLL1 4 +#define TWL4030_REG_VPLL2 5 /* not on all chips */ +#define TWL4030_REG_VMMC1 6 +#define TWL4030_REG_VMMC2 7 /* not on all chips */ +#define TWL4030_REG_VSIM 8 /* not on all chips */ +#define TWL4030_REG_VAUX1 9 /* not on all chips */ +#define TWL4030_REG_VAUX2_4030 10 /* (twl4030-specific) */ +#define TWL4030_REG_VAUX2 11 /* (twl5030 and newer) */ +#define TWL4030_REG_VAUX3 12 /* not on all chips */ +#define TWL4030_REG_VAUX4 13 /* not on all chips */ + +/* INTERNAL LDOs */ +#define TWL4030_REG_VINTANA1 14 +#define TWL4030_REG_VINTANA2 15 +#define TWL4030_REG_VINTDIG 16 +#define TWL4030_REG_VUSB1V5 17 +#define TWL4030_REG_VUSB1V8 18 +#define TWL4030_REG_VUSB3V1 19 + +/* TWL6030 SMPS/LDO's */ +/* EXTERNAL dc-to-dc buck convertor controllable via SR */ +#define TWL6030_REG_VDD1 30 +#define TWL6030_REG_VDD2 31 +#define TWL6030_REG_VDD3 32 + +/* Non SR compliant dc-to-dc buck convertors */ +#define TWL6030_REG_VMEM 33 +#define TWL6030_REG_V2V1 34 +#define TWL6030_REG_V1V29 35 +#define TWL6030_REG_V1V8 36 + +/* EXTERNAL LDOs */ +#define TWL6030_REG_VAUX1_6030 37 +#define TWL6030_REG_VAUX2_6030 38 +#define TWL6030_REG_VAUX3_6030 39 +#define TWL6030_REG_VMMC 40 +#define TWL6030_REG_VPP 41 +#define TWL6030_REG_VUSIM 42 +#define TWL6030_REG_VANA 43 +#define TWL6030_REG_VCXIO 44 +#define TWL6030_REG_VDAC 45 +#define TWL6030_REG_VUSB 46 + +/* INTERNAL LDOs */ +#define TWL6030_REG_VRTC 47 +#define TWL6030_REG_CLK32KG 48 + +/* LDOs on 6025 have different names */ +#define TWL6032_REG_LDO2 49 +#define TWL6032_REG_LDO4 50 +#define TWL6032_REG_LDO3 51 +#define TWL6032_REG_LDO5 52 +#define TWL6032_REG_LDO1 53 +#define TWL6032_REG_LDO7 54 +#define TWL6032_REG_LDO6 55 +#define TWL6032_REG_LDOLN 56 +#define TWL6032_REG_LDOUSB 57 + +/* 6025 DCDC supplies */ +#define TWL6032_REG_SMPS3 58 +#define TWL6032_REG_SMPS4 59 +#define TWL6032_REG_VIO 60 + + +#endif /* End of __TWL4030_H */ -- cgit v1.2.3 From e8924005b4e7964313536547d4b73406330be26d Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Mon, 28 Aug 2017 12:04:07 +0200 Subject: mfd: Add STM32 LPTimer driver STM32 Low-Power Timer hardware block can be used for: - PWM generation - IIO trigger (in sync with PWM) - IIO quadrature encoder counter PWM and IIO timer configuration are mixed in the same registers so we need a multi fonction driver to be able to share those registers. Signed-off-by: Fabrice Gasnier Signed-off-by: Lee Jones --- include/linux/mfd/stm32-lptimer.h | 62 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 include/linux/mfd/stm32-lptimer.h (limited to 'include/linux') diff --git a/include/linux/mfd/stm32-lptimer.h b/include/linux/mfd/stm32-lptimer.h new file mode 100644 index 000000000000..77c7cf40d9b4 --- /dev/null +++ b/include/linux/mfd/stm32-lptimer.h @@ -0,0 +1,62 @@ +/* + * STM32 Low-Power Timer parent driver. + * + * Copyright (C) STMicroelectronics 2017 + * + * Author: Fabrice Gasnier + * + * Inspired by Benjamin Gaignard's stm32-timers driver + * + * License terms: GNU General Public License (GPL), version 2 + */ + +#ifndef _LINUX_STM32_LPTIMER_H_ +#define _LINUX_STM32_LPTIMER_H_ + +#include +#include + +#define STM32_LPTIM_ISR 0x00 /* Interrupt and Status Reg */ +#define STM32_LPTIM_ICR 0x04 /* Interrupt Clear Reg */ +#define STM32_LPTIM_IER 0x08 /* Interrupt Enable Reg */ +#define STM32_LPTIM_CFGR 0x0C /* Configuration Reg */ +#define STM32_LPTIM_CR 0x10 /* Control Reg */ +#define STM32_LPTIM_CMP 0x14 /* Compare Reg */ +#define STM32_LPTIM_ARR 0x18 /* Autoreload Reg */ +#define STM32_LPTIM_CNT 0x1C /* Counter Reg */ + +/* STM32_LPTIM_ISR - bit fields */ +#define STM32_LPTIM_CMPOK_ARROK GENMASK(4, 3) +#define STM32_LPTIM_ARROK BIT(4) +#define STM32_LPTIM_CMPOK BIT(3) + +/* STM32_LPTIM_ICR - bit fields */ +#define STM32_LPTIM_CMPOKCF_ARROKCF GENMASK(4, 3) + +/* STM32_LPTIM_CR - bit fields */ +#define STM32_LPTIM_CNTSTRT BIT(2) +#define STM32_LPTIM_ENABLE BIT(0) + +/* STM32_LPTIM_CFGR - bit fields */ +#define STM32_LPTIM_ENC BIT(24) +#define STM32_LPTIM_COUNTMODE BIT(23) +#define STM32_LPTIM_WAVPOL BIT(21) +#define STM32_LPTIM_PRESC GENMASK(11, 9) +#define STM32_LPTIM_CKPOL GENMASK(2, 1) + +/* STM32_LPTIM_ARR */ +#define STM32_LPTIM_MAX_ARR 0xFFFF + +/** + * struct stm32_lptimer - STM32 Low-Power Timer data assigned by parent device + * @clk: clock reference for this instance + * @regmap: register map reference for this instance + * @has_encoder: indicates this Low-Power Timer supports encoder mode + */ +struct stm32_lptimer { + struct clk *clk; + struct regmap *regmap; + bool has_encoder; +}; + +#endif -- cgit v1.2.3 From b01ced2b504b2592af6703533c62cb9d1cdc1c6c Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Mon, 28 Aug 2017 12:04:11 +0200 Subject: iio: trigger: Add STM32 LPTimer trigger driver Add support for LPTIMx_OUT triggers that can be found on some STM32 devices. These triggers can be used then by ADC or DAC. Typical usage is to configure LPTimer as PWM output (via pwm-stm32-lp) and have synchronised analog conversions with these triggers. Signed-off-by: Fabrice Gasnier Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones --- include/linux/iio/timer/stm32-lptim-trigger.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 include/linux/iio/timer/stm32-lptim-trigger.h (limited to 'include/linux') diff --git a/include/linux/iio/timer/stm32-lptim-trigger.h b/include/linux/iio/timer/stm32-lptim-trigger.h new file mode 100644 index 000000000000..34d59bfdce2d --- /dev/null +++ b/include/linux/iio/timer/stm32-lptim-trigger.h @@ -0,0 +1,27 @@ +/* + * Copyright (C) STMicroelectronics 2017 + * + * Author: Fabrice Gasnier + * + * License terms: GNU General Public License (GPL), version 2 + */ + +#ifndef _STM32_LPTIM_TRIGGER_H_ +#define _STM32_LPTIM_TRIGGER_H_ + +#include +#include + +#define LPTIM1_OUT "lptim1_out" +#define LPTIM2_OUT "lptim2_out" +#define LPTIM3_OUT "lptim3_out" + +#if IS_ENABLED(CONFIG_IIO_STM32_LPTIMER_TRIGGER) +bool is_stm32_lptim_trigger(struct iio_trigger *trig); +#else +static inline bool is_stm32_lptim_trigger(struct iio_trigger *trig) +{ + return false; +} +#endif +#endif -- cgit v1.2.3 From 495e642939114478a5237a7d91661ba93b76f15a Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Mon, 4 Sep 2017 21:42:22 +0200 Subject: vfs: add flags to d_real() Add a separate flags argument (in addition to the open flags) to control the behavior of d_real(). Signed-off-by: Miklos Szeredi --- include/linux/dcache.h | 11 ++++++----- include/linux/fs.h | 2 +- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index aae1cdb76851..fd0721e520f4 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -147,7 +147,7 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, const struct inode *, - unsigned int); + unsigned int, unsigned int); } ____cacheline_aligned; /* @@ -566,7 +566,8 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) * d_real - Return the real dentry * @dentry: the dentry to query * @inode: inode to select the dentry from multiple layers (can be NULL) - * @flags: open flags to control copy-up behavior + * @open_flags: open flags to control copy-up behavior + * @flags: flags to control what is returned by this function * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. @@ -575,10 +576,10 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) */ static inline struct dentry *d_real(struct dentry *dentry, const struct inode *inode, - unsigned int flags) + unsigned int open_flags, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) - return dentry->d_op->d_real(dentry, inode, flags); + return dentry->d_op->d_real(dentry, inode, open_flags, flags); else return dentry; } @@ -593,7 +594,7 @@ static inline struct dentry *d_real(struct dentry *dentry, static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ - return d_backing_inode(d_real((struct dentry *) dentry, NULL, 0)); + return d_backing_inode(d_real((struct dentry *) dentry, NULL, 0, 0)); } struct name_snapshot { diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e1fd5d21248..ee1db83c39cb 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1233,7 +1233,7 @@ static inline struct inode *file_inode(const struct file *f) static inline struct dentry *file_dentry(const struct file *file) { - return d_real(file->f_path.dentry, file_inode(file), 0); + return d_real(file->f_path.dentry, file_inode(file), 0, 0); } static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) -- cgit v1.2.3 From 91f9943e1c7b6638f27312d03fe71fcc67b23571 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 29 Aug 2017 16:13:20 +0200 Subject: fs: support RWF_NOWAIT for buffered reads This is based on the old idea and code from Milosz Tanski. With the aio nowait code it becomes mostly trivial now. Buffered writes continue to return -EOPNOTSUPP if RWF_NOWAIT is passed. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Al Viro --- include/linux/fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cbfe127bccf8..94582c379dac 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -146,8 +146,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) -/* File is capable of returning -EAGAIN if AIO will block */ -#define FMODE_AIO_NOWAIT ((__force fmode_t)0x8000000) +/* File is capable of returning -EAGAIN if I/O will block */ +#define FMODE_NOWAIT ((__force fmode_t)0x8000000) /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector @@ -3149,7 +3149,7 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags) return -EOPNOTSUPP; if (flags & RWF_NOWAIT) { - if (!(ki->ki_filp->f_mode & FMODE_AIO_NOWAIT)) + if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; ki->ki_flags |= IOCB_NOWAIT; } -- cgit v1.2.3 From bdd1d2d3d251c65b74ac4493e08db18971c09240 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Sep 2017 17:39:13 +0200 Subject: fs: fix kernel_read prototype Use proper ssize_t and size_t types for the return value and count argument, move the offset last and make it an in/out argument like all other read/write helpers, and make the buf argument a void pointer to get rid of lots of casts in the callers. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cbfe127bccf8..2ba8f38a4d63 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2772,13 +2772,13 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) return kernel_read_file_str[id]; } -extern int kernel_read(struct file *, loff_t, char *, unsigned long); extern int kernel_read_file(struct file *, void **, loff_t *, loff_t, enum kernel_read_file_id); extern int kernel_read_file_from_path(char *, void **, loff_t *, loff_t, enum kernel_read_file_id); extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, enum kernel_read_file_id); +extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); extern struct file * open_exec(const char *); -- cgit v1.2.3 From e13ec939e96b13e664bb6cee361cc976a0ee621a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Sep 2017 17:39:14 +0200 Subject: fs: fix kernel_write prototype Make the position an in/out argument like all the other read/write helpers and and make the buf argument a void pointer. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2ba8f38a4d63..0e7d3da8a307 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2779,7 +2779,7 @@ extern int kernel_read_file_from_path(char *, void **, loff_t *, loff_t, extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, enum kernel_read_file_id); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); -extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); +extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); extern struct file * open_exec(const char *); -- cgit v1.2.3 From 73e18f7c0b3e1432353cdd86672c27cace7e6a7e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Sep 2017 17:39:15 +0200 Subject: fs: make the buf argument to __kernel_write a void pointer This matches kernel_read and kernel_write and avoids any need for casts in the callers. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0e7d3da8a307..9ab7e2bf7dd1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2780,7 +2780,7 @@ extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, enum kernel_read_file_id); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); -extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); +extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ -- cgit v1.2.3 From eb031849d52e61d24ba54e9d27553189ff328174 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Sep 2017 17:39:23 +0200 Subject: fs: unexport __vfs_read/__vfs_write No modular users left, and any new ones should use kernel_read/write or iov_iter variants instead. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9ab7e2bf7dd1..f24b821cee8d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1754,7 +1754,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, struct iovec **ret_pointer); extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); -extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, -- cgit v1.2.3 From 9725d4cef62229b4ec4c912e0db0761e7d400650 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 1 Sep 2017 17:39:25 +0200 Subject: fs: unexport vfs_readv and vfs_writev We've got no modular users left, and any potential modular user is better of with iov_iter based variants. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index f24b821cee8d..355cf02830a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1758,8 +1758,6 @@ extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, int); -extern ssize_t vfs_writev(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, -- cgit v1.2.3 From ec58871fb9c50429d6b5570066a7166da8faf086 Mon Sep 17 00:00:00 2001 From: Guodong Xu Date: Thu, 20 Jul 2017 15:32:42 +0800 Subject: mfd: hi6421-pmic: Add support for HiSilicon Hi6421v530 Add support for HiSilicon Hi6421v530 PMIC. Hi6421v530 communicates with main SoC via memory-mapped I/O. Hi6421v530 and Hi6421 are PMIC chips from the same vendor, HiSilicon, but at different revisions. They share the same memory-mapped I/O design. They differ in integrated devices, such as regulator details, LDO voltage points. Signed-off-by: Guodong Xu Signed-off-by: Wang Xiaoyin Acked-by: Arnd Bergmann Signed-off-by: Lee Jones --- include/linux/mfd/hi6421-pmic.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/hi6421-pmic.h b/include/linux/mfd/hi6421-pmic.h index 587273e35acf..2580c08db7b1 100644 --- a/include/linux/mfd/hi6421-pmic.h +++ b/include/linux/mfd/hi6421-pmic.h @@ -38,4 +38,9 @@ struct hi6421_pmic { struct regmap *regmap; }; +enum hi6421_type { + HI6421 = 0, + HI6421_V530, +}; + #endif /* __HI6421_PMIC_H */ -- cgit v1.2.3 From d3ea212720948acff862b4c842d5b464ad338841 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Mon, 17 Jul 2017 22:45:12 +0200 Subject: mfd: Add ROHM BD9571MWV-M MFD PMIC driver Add the MFD part of the ROHM BD9571MWV-M PMIC driver and MAINTAINERS entry. The MFD part only specifies the regmap bits for the PMIC and binds the subdevs together. Signed-off-by: Marek Vasut Signed-off-by: Lee Jones --- include/linux/mfd/bd9571mwv.h | 115 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 115 insertions(+) create mode 100644 include/linux/mfd/bd9571mwv.h (limited to 'include/linux') diff --git a/include/linux/mfd/bd9571mwv.h b/include/linux/mfd/bd9571mwv.h new file mode 100644 index 000000000000..f0708ba4cbba --- /dev/null +++ b/include/linux/mfd/bd9571mwv.h @@ -0,0 +1,115 @@ +/* + * ROHM BD9571MWV-M driver + * + * Copyright (C) 2017 Marek Vasut + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether expressed or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License version 2 for more details. + * + * Based on the TPS65086 driver + */ + +#ifndef __LINUX_MFD_BD9571MWV_H +#define __LINUX_MFD_BD9571MWV_H + +#include +#include + +/* List of registers for BD9571MWV */ +#define BD9571MWV_VENDOR_CODE 0x00 +#define BD9571MWV_VENDOR_CODE_VAL 0xdb +#define BD9571MWV_PRODUCT_CODE 0x01 +#define BD9571MWV_PRODUCT_CODE_VAL 0x60 +#define BD9571MWV_PRODUCT_REVISION 0x02 + +#define BD9571MWV_I2C_FUSA_MODE 0x10 +#define BD9571MWV_I2C_MD2_E1_BIT_1 0x11 +#define BD9571MWV_I2C_MD2_E1_BIT_2 0x12 + +#define BD9571MWV_BKUP_MODE_CNT 0x20 +#define BD9571MWV_BKUP_MODE_STATUS 0x21 +#define BD9571MWV_BKUP_RECOVERY_CNT 0x22 +#define BD9571MWV_BKUP_CTRL_TIM_CNT 0x23 +#define BD9571MWV_WAITBKUP_WDT_CNT 0x24 +#define BD9571MWV_128H_TIM_CNT 0x26 +#define BD9571MWV_QLLM_CNT 0x27 + +#define BD9571MWV_AVS_SET_MONI 0x31 +#define BD9571MWV_AVS_SET_MONI_MASK 0x3 +#define BD9571MWV_AVS_VD09_VID(n) (0x32 + (n)) +#define BD9571MWV_AVS_DVFS_VID(n) (0x36 + (n)) + +#define BD9571MWV_VD18_VID 0x42 +#define BD9571MWV_VD25_VID 0x43 +#define BD9571MWV_VD33_VID 0x44 + +#define BD9571MWV_DVFS_VINIT 0x50 +#define BD9571MWV_DVFS_SETVMAX 0x52 +#define BD9571MWV_DVFS_BOOSTVID 0x53 +#define BD9571MWV_DVFS_SETVID 0x54 +#define BD9571MWV_DVFS_MONIVDAC 0x55 +#define BD9571MWV_DVFS_PGD_CNT 0x56 + +#define BD9571MWV_GPIO_DIR 0x60 +#define BD9571MWV_GPIO_OUT 0x61 +#define BD9571MWV_GPIO_IN 0x62 +#define BD9571MWV_GPIO_DEB 0x63 +#define BD9571MWV_GPIO_INT_SET 0x64 +#define BD9571MWV_GPIO_INT 0x65 +#define BD9571MWV_GPIO_INTMASK 0x66 + +#define BD9571MWV_REG_KEEP(n) (0x70 + (n)) + +#define BD9571MWV_PMIC_INTERNAL_STATUS 0x80 +#define BD9571MWV_PROT_ERROR_STATUS0 0x81 +#define BD9571MWV_PROT_ERROR_STATUS1 0x82 +#define BD9571MWV_PROT_ERROR_STATUS2 0x83 +#define BD9571MWV_PROT_ERROR_STATUS3 0x84 +#define BD9571MWV_PROT_ERROR_STATUS4 0x85 + +#define BD9571MWV_INT_INTREQ 0x90 +#define BD9571MWV_INT_INTREQ_MD1_INT BIT(0) +#define BD9571MWV_INT_INTREQ_MD2_E1_INT BIT(1) +#define BD9571MWV_INT_INTREQ_MD2_E2_INT BIT(2) +#define BD9571MWV_INT_INTREQ_PROT_ERR_INT BIT(3) +#define BD9571MWV_INT_INTREQ_GP_INT BIT(4) +#define BD9571MWV_INT_INTREQ_128H_OF_INT BIT(5) +#define BD9571MWV_INT_INTREQ_WDT_OF_INT BIT(6) +#define BD9571MWV_INT_INTREQ_BKUP_TRG_INT BIT(7) +#define BD9571MWV_INT_INTMASK 0x91 + +#define BD9571MWV_ACCESS_KEY 0xff + +/* Define the BD9571MWV IRQ numbers */ +enum bd9571mwv_irqs { + BD9571MWV_IRQ_MD1, + BD9571MWV_IRQ_MD2_E1, + BD9571MWV_IRQ_MD2_E2, + BD9571MWV_IRQ_PROT_ERR, + BD9571MWV_IRQ_GP, + BD9571MWV_IRQ_128H_OF, + BD9571MWV_IRQ_WDT_OF, + BD9571MWV_IRQ_BKUP_TRG, +}; + +/** + * struct bd9571mwv - state holder for the bd9571mwv driver + * + * Device data may be used to access the BD9571MWV chip + */ +struct bd9571mwv { + struct device *dev; + struct regmap *regmap; + + /* IRQ Data */ + int irq; + struct regmap_irq_chip_data *irq_data; +}; + +#endif /* __LINUX_MFD_BD9571MWV_H */ -- cgit v1.2.3 From 7303733a6ca2a68b210ebdc09cace8b0ffe8b179 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Wed, 26 Jul 2017 16:28:26 +0800 Subject: mfd: axp20x: Add support for AXP813 PMIC The X-Powers AXP813 PMIC is normally used with Allwinner's A83T SoC. It has the same range of functions as other X-Powers PMICs, such as DC-DC buck converter and linear regulator outputs, AC-IN and VBUS power supplies, power button trigger, GPIOs, ADCs, and a battery charger. Note that the IRQ table given in the datasheet is incorrect: in IRQ enable/status registers 1, there are separate IRQs for ACIN and VBUS, instead of bits [7:5] being the same as bits [4:2]. So it shares the same IRQs as the AXP803, rather than the AXP288. This patch adds basic mfd support for it, with only the power button enabled. Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Lee Jones --- include/linux/mfd/axp20x.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index 965b027e31b3..e9c908c4fba8 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -23,6 +23,7 @@ enum axp20x_variants { AXP803_ID, AXP806_ID, AXP809_ID, + AXP813_ID, NR_AXP20X_VARIANTS, }; @@ -387,6 +388,34 @@ enum { AXP803_REG_ID_MAX, }; +enum { + AXP813_DCDC1 = 0, + AXP813_DCDC2, + AXP813_DCDC3, + AXP813_DCDC4, + AXP813_DCDC5, + AXP813_DCDC6, + AXP813_DCDC7, + AXP813_ALDO1, + AXP813_ALDO2, + AXP813_ALDO3, + AXP813_DLDO1, + AXP813_DLDO2, + AXP813_DLDO3, + AXP813_DLDO4, + AXP813_ELDO1, + AXP813_ELDO2, + AXP813_ELDO3, + AXP813_FLDO1, + AXP813_FLDO2, + AXP813_FLDO3, + AXP813_RTC_LDO, + AXP813_LDO_IO0, + AXP813_LDO_IO1, + AXP813_SW, + AXP813_REG_ID_MAX, +}; + /* IRQs */ enum { AXP152_IRQ_LDO0IN_CONNECT = 1, -- cgit v1.2.3 From b0f3ab20e76499db12b0bbadb5737d9870f10418 Mon Sep 17 00:00:00 2001 From: Ludovic Desroches Date: Tue, 18 Jul 2017 15:22:19 +0200 Subject: mfd: syscon: atmel-smc: Add helper to retrieve register layout For HSMC controller, the register layout depends on the device i.e. the offset of setup, pulse, cycle, mode and timings registers is not the same. An helper is added to provide the correct register layout. Fixes: fe9d7cb22ef3 ("mfd: syscon: atmel-smc: Add new helpers to ease SMC regs manipulation") Suggested-by: Boris Brezillon Signed-off-by: Ludovic Desroches Acked-by: Boris Brezillon Acked-by: Nicolas Ferre Acked-by: Alexandre Belloni Signed-off-by: Lee Jones --- include/linux/mfd/syscon/atmel-smc.h | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/syscon/atmel-smc.h b/include/linux/mfd/syscon/atmel-smc.h index afa266169800..7a367f34b66a 100644 --- a/include/linux/mfd/syscon/atmel-smc.h +++ b/include/linux/mfd/syscon/atmel-smc.h @@ -15,21 +15,26 @@ #define _LINUX_MFD_SYSCON_ATMEL_SMC_H_ #include +#include #include #define ATMEL_SMC_SETUP(cs) (((cs) * 0x10)) -#define ATMEL_HSMC_SETUP(cs) (0x600 + ((cs) * 0x14)) +#define ATMEL_HSMC_SETUP(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14)) #define ATMEL_SMC_PULSE(cs) (((cs) * 0x10) + 0x4) -#define ATMEL_HSMC_PULSE(cs) (0x600 + ((cs) * 0x14) + 0x4) +#define ATMEL_HSMC_PULSE(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14) + 0x4) #define ATMEL_SMC_CYCLE(cs) (((cs) * 0x10) + 0x8) -#define ATMEL_HSMC_CYCLE(cs) (0x600 + ((cs) * 0x14) + 0x8) +#define ATMEL_HSMC_CYCLE(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14) + 0x8) #define ATMEL_SMC_NWE_SHIFT 0 #define ATMEL_SMC_NCS_WR_SHIFT 8 #define ATMEL_SMC_NRD_SHIFT 16 #define ATMEL_SMC_NCS_RD_SHIFT 24 #define ATMEL_SMC_MODE(cs) (((cs) * 0x10) + 0xc) -#define ATMEL_HSMC_MODE(cs) (0x600 + ((cs) * 0x14) + 0x10) +#define ATMEL_HSMC_MODE(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14) + 0x10) #define ATMEL_SMC_MODE_READMODE_MASK BIT(0) #define ATMEL_SMC_MODE_READMODE_NCS (0 << 0) #define ATMEL_SMC_MODE_READMODE_NRD (1 << 0) @@ -59,7 +64,8 @@ #define ATMEL_SMC_MODE_PS_16 (2 << 28) #define ATMEL_SMC_MODE_PS_32 (3 << 28) -#define ATMEL_HSMC_TIMINGS(cs) (0x600 + ((cs) * 0x14) + 0xc) +#define ATMEL_HSMC_TIMINGS(layout, cs) \ + ((layout)->timing_regs_offset + ((cs) * 0x14) + 0xc) #define ATMEL_HSMC_TIMINGS_OCMS BIT(12) #define ATMEL_HSMC_TIMINGS_RBNSEL(x) ((x) << 28) #define ATMEL_HSMC_TIMINGS_NFSEL BIT(31) @@ -69,6 +75,10 @@ #define ATMEL_HSMC_TIMINGS_TRR_SHIFT 16 #define ATMEL_HSMC_TIMINGS_TWB_SHIFT 24 +struct atmel_hsmc_reg_layout { + unsigned int timing_regs_offset; +}; + /** * struct atmel_smc_cs_conf - SMC CS config as described in the datasheet. * @setup: NCS/NWE/NRD setup timings (not applicable to at91rm9200) @@ -98,11 +108,15 @@ int atmel_smc_cs_conf_set_cycle(struct atmel_smc_cs_conf *conf, unsigned int shift, unsigned int ncycles); void atmel_smc_cs_conf_apply(struct regmap *regmap, int cs, const struct atmel_smc_cs_conf *conf); -void atmel_hsmc_cs_conf_apply(struct regmap *regmap, int cs, - const struct atmel_smc_cs_conf *conf); +void atmel_hsmc_cs_conf_apply(struct regmap *regmap, + const struct atmel_hsmc_reg_layout *reglayout, + int cs, const struct atmel_smc_cs_conf *conf); void atmel_smc_cs_conf_get(struct regmap *regmap, int cs, struct atmel_smc_cs_conf *conf); -void atmel_hsmc_cs_conf_get(struct regmap *regmap, int cs, - struct atmel_smc_cs_conf *conf); +void atmel_hsmc_cs_conf_get(struct regmap *regmap, + const struct atmel_hsmc_reg_layout *reglayout, + int cs, struct atmel_smc_cs_conf *conf); +const struct atmel_hsmc_reg_layout * +atmel_hsmc_get_reg_layout(struct device_node *np); #endif /* _LINUX_MFD_SYSCON_ATMEL_SMC_H_ */ -- cgit v1.2.3 From 9bbf6a15ce19dd947b7fa6ad4095931ab3682da8 Mon Sep 17 00:00:00 2001 From: Rajmohan Mani Date: Fri, 28 Jul 2017 17:30:24 -0700 Subject: mfd: Add support for TPS68470 device The TPS68470 device is an advanced power management unit that powers a Compact Camera Module (CCM), generates clocks for image sensors, drives a dual LED for Flash and incorporates two LED drivers for general purpose indicators. This patch adds support for TPS68470 mfd device. Signed-off-by: Rajmohan Mani Signed-off-by: Lee Jones --- include/linux/mfd/tps68470.h | 97 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 97 insertions(+) create mode 100644 include/linux/mfd/tps68470.h (limited to 'include/linux') diff --git a/include/linux/mfd/tps68470.h b/include/linux/mfd/tps68470.h new file mode 100644 index 000000000000..44f9d9f647ed --- /dev/null +++ b/include/linux/mfd/tps68470.h @@ -0,0 +1,97 @@ +/* + * Copyright (c) 2017 Intel Corporation + * + * Functions to access TPS68470 power management chip. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_MFD_TPS68470_H +#define __LINUX_MFD_TPS68470_H + +/* Register addresses */ +#define TPS68470_REG_POSTDIV2 0x06 +#define TPS68470_REG_BOOSTDIV 0x07 +#define TPS68470_REG_BUCKDIV 0x08 +#define TPS68470_REG_PLLSWR 0x09 +#define TPS68470_REG_XTALDIV 0x0A +#define TPS68470_REG_PLLDIV 0x0B +#define TPS68470_REG_POSTDIV 0x0C +#define TPS68470_REG_PLLCTL 0x0D +#define TPS68470_REG_PLLCTL2 0x0E +#define TPS68470_REG_CLKCFG1 0x0F +#define TPS68470_REG_CLKCFG2 0x10 +#define TPS68470_REG_GPCTL0A 0x14 +#define TPS68470_REG_GPCTL0B 0x15 +#define TPS68470_REG_GPCTL1A 0x16 +#define TPS68470_REG_GPCTL1B 0x17 +#define TPS68470_REG_GPCTL2A 0x18 +#define TPS68470_REG_GPCTL2B 0x19 +#define TPS68470_REG_GPCTL3A 0x1A +#define TPS68470_REG_GPCTL3B 0x1B +#define TPS68470_REG_GPCTL4A 0x1C +#define TPS68470_REG_GPCTL4B 0x1D +#define TPS68470_REG_GPCTL5A 0x1E +#define TPS68470_REG_GPCTL5B 0x1F +#define TPS68470_REG_GPCTL6A 0x20 +#define TPS68470_REG_GPCTL6B 0x21 +#define TPS68470_REG_SGPO 0x22 +#define TPS68470_REG_GPDI 0x26 +#define TPS68470_REG_GPDO 0x27 +#define TPS68470_REG_VCMVAL 0x3C +#define TPS68470_REG_VAUX1VAL 0x3D +#define TPS68470_REG_VAUX2VAL 0x3E +#define TPS68470_REG_VIOVAL 0x3F +#define TPS68470_REG_VSIOVAL 0x40 +#define TPS68470_REG_VAVAL 0x41 +#define TPS68470_REG_VDVAL 0x42 +#define TPS68470_REG_S_I2C_CTL 0x43 +#define TPS68470_REG_VCMCTL 0x44 +#define TPS68470_REG_VAUX1CTL 0x45 +#define TPS68470_REG_VAUX2CTL 0x46 +#define TPS68470_REG_VACTL 0x47 +#define TPS68470_REG_VDCTL 0x48 +#define TPS68470_REG_RESET 0x50 +#define TPS68470_REG_REVID 0xFF + +#define TPS68470_REG_MAX TPS68470_REG_REVID + +/* Register field definitions */ + +#define TPS68470_REG_RESET_MASK GENMASK(7, 0) +#define TPS68470_VAVAL_AVOLT_MASK GENMASK(6, 0) + +#define TPS68470_VDVAL_DVOLT_MASK GENMASK(5, 0) +#define TPS68470_VCMVAL_VCVOLT_MASK GENMASK(6, 0) +#define TPS68470_VIOVAL_IOVOLT_MASK GENMASK(6, 0) +#define TPS68470_VSIOVAL_IOVOLT_MASK GENMASK(6, 0) +#define TPS68470_VAUX1VAL_AUX1VOLT_MASK GENMASK(6, 0) +#define TPS68470_VAUX2VAL_AUX2VOLT_MASK GENMASK(6, 0) + +#define TPS68470_VACTL_EN_MASK GENMASK(0, 0) +#define TPS68470_VDCTL_EN_MASK GENMASK(0, 0) +#define TPS68470_VCMCTL_EN_MASK GENMASK(0, 0) +#define TPS68470_S_I2C_CTL_EN_MASK GENMASK(1, 0) +#define TPS68470_VAUX1CTL_EN_MASK GENMASK(0, 0) +#define TPS68470_VAUX2CTL_EN_MASK GENMASK(0, 0) +#define TPS68470_PLL_EN_MASK GENMASK(0, 0) + +#define TPS68470_CLKCFG1_MODE_A_MASK GENMASK(1, 0) +#define TPS68470_CLKCFG1_MODE_B_MASK GENMASK(3, 2) + +#define TPS68470_GPIO_CTL_REG_A(x) (TPS68470_REG_GPCTL0A + (x) * 2) +#define TPS68470_GPIO_CTL_REG_B(x) (TPS68470_REG_GPCTL0B + (x) * 2) +#define TPS68470_GPIO_MODE_MASK GENMASK(1, 0) +#define TPS68470_GPIO_MODE_IN 0 +#define TPS68470_GPIO_MODE_IN_PULLUP 1 +#define TPS68470_GPIO_MODE_OUT_CMOS 2 +#define TPS68470_GPIO_MODE_OUT_ODRAIN 3 + +#endif /* __LINUX_MFD_TPS68470_H */ -- cgit v1.2.3 From cd91304e7190b4c4802f8e413ab2214b233e0260 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 5 Sep 2017 12:53:11 +0200 Subject: ovl: fix relatime for directories Need to treat non-regular overlayfs files the same as regular files when checking for an atime update. Add a d_real() flag to make it return the upper dentry for all file types. Reported-by: "zhangyi (F)" Signed-off-by: Miklos Szeredi --- include/linux/dcache.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index fd0721e520f4..ed1a7cf6923a 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -562,6 +562,9 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) return upper; } +/* d_real() flags */ +#define D_REAL_UPPER 0x2 /* return upper dentry or NULL if non-upper */ + /** * d_real - Return the real dentry * @dentry: the dentry to query -- cgit v1.2.3 From fbf1c41fc0f4d3574ac2377245efd666c1fa3075 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Sun, 3 Sep 2017 01:18:41 +0100 Subject: workqueue: Fix flag collision Commit 0a94efb5acbb ("workqueue: implicit ordered attribute should be overridable") introduced a __WQ_ORDERED_EXPLICIT flag but gave it the same value as __WQ_LEGACY. I don't believe these were intended to mean the same thing, so renumber __WQ_ORDERED_EXPLICIT. Fixes: 0a94efb5acbb ("workqueue: implicit ordered attribute should be ...") Signed-off-by: Ben Hutchings Cc: stable@vger.kernel.org # v4.13 Signed-off-by: Tejun Heo --- include/linux/workqueue.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index db6dc9dc0482..1c49431f3121 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -323,8 +323,8 @@ enum { __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ - __WQ_ORDERED_EXPLICIT = 1 << 18, /* internal: alloc_ordered_workqueue() */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ + __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ -- cgit v1.2.3 From 2c08ab3f2504bc7ba816ce6fde051b8bd5f028e4 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 5 Sep 2017 10:31:35 +0200 Subject: soc: ti/knav_dma: include dmaengine header A header file cleanup apparently caused a build regression with one driver using the knav infrastructure: In file included from drivers/net/ethernet/ti/netcp_core.c:30:0: include/linux/soc/ti/knav_dma.h:129:30: error: field 'direction' has incomplete type enum dma_transfer_direction direction; ^~~~~~~~~ drivers/net/ethernet/ti/netcp_core.c: In function 'netcp_txpipe_open': drivers/net/ethernet/ti/netcp_core.c:1349:21: error: 'DMA_MEM_TO_DEV' undeclared (first use in this function); did you mean 'DMA_MEMORY_MAP'? config.direction = DMA_MEM_TO_DEV; ^~~~~~~~~~~~~~ DMA_MEMORY_MAP drivers/net/ethernet/ti/netcp_core.c:1349:21: note: each undeclared identifier is reported only once for each function it appears in drivers/net/ethernet/ti/netcp_core.c: In function 'netcp_setup_navigator_resources': drivers/net/ethernet/ti/netcp_core.c:1659:22: error: 'DMA_DEV_TO_MEM' undeclared (first use in this function); did you mean 'DMA_DESC_HOST'? config.direction = DMA_DEV_TO_MEM; As the header is no longer included implicitly through netdevice.h, we should include it in the header that references the enum. Fixes: 0dd5759dbb1c ("net: remove dmaengine.h inclusion from netdevice.h") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/linux/soc/ti/knav_dma.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index 2b7882666ef6..66693bc4c6ad 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -17,6 +17,8 @@ #ifndef __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__ #define __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__ +#include + /* * PKTDMA descriptor manipulation macros for host packet descriptor */ -- cgit v1.2.3 From 5482a978b962abd23f17a004e46d255d11646c20 Mon Sep 17 00:00:00 2001 From: Corentin Labbe Date: Mon, 4 Sep 2017 18:30:14 +0200 Subject: net: mdio-mux: add mdio_mux parameter to mdio_mux_init() mdio_mux_init() use the parameter dev for two distinct thing: 1) Have a device for all devm_ functions 2) Get device_node from it Since it is two distinct purpose, this patch add a parameter mdio_mux that is linked to task 2. This will also permit to register an of_node mdio-mux that lacks a direct owning device. For example a mdio-mux which is a subnode of a real device. Signed-off-by: Corentin Labbe Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/mdio-mux.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdio-mux.h b/include/linux/mdio-mux.h index 61f5b21b31c7..a5d58f221939 100644 --- a/include/linux/mdio-mux.h +++ b/include/linux/mdio-mux.h @@ -12,7 +12,16 @@ #include #include +/* mdio_mux_init() - Initialize a MDIO mux + * @dev The device owning the MDIO mux + * @mux_node The device node of the MDIO mux + * @switch_fn The function called for switching target MDIO child + * mux_handle A pointer to a (void *) used internaly by mdio-mux + * @data Private data used by switch_fn() + * @mux_bus An optional parent bus (Other case are to use parent_bus property) + */ int mdio_mux_init(struct device *dev, + struct device_node *mux_node, int (*switch_fn) (int cur, int desired, void *data), void **mux_handle, void *data, -- cgit v1.2.3 From 03c6f7d64ac9c0a37cca91392ac4be8993a8f53d Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Wed, 16 Aug 2017 12:47:27 +1000 Subject: NFS: remove jiffies field from access cache This field hasn't been used since commit 57b691819ee2 ("NFS: Cache access checks more aggressively"). Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 238fdc4c46df..a0282ceaa48b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -49,7 +49,6 @@ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; - unsigned long jiffies; struct rpc_cred * cred; __u32 mask; struct rcu_head rcu_head; -- cgit v1.2.3 From 2ae409dc6a907e80f4cd32ad4482ef52441e3147 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 11 Jul 2017 16:20:05 +0800 Subject: ceph: remove unused cap_release_safety mount option Signed-off-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 8a79587e1317..dca30ac9bd34 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -93,7 +93,6 @@ struct ceph_options { #define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */ #define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */ -#define CEPH_CAP_RELEASE_SAFETY_DEFAULT (CEPH_CAPS_PER_RELEASE * 4) /* mount state */ enum { -- cgit v1.2.3 From 4214fb158cc423ac31b841000e219855be055388 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 11 Jul 2017 18:49:44 +0800 Subject: ceph: validate correctness of some mount options Signed-off-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index dca30ac9bd34..4c846aabd9f6 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -84,16 +84,6 @@ struct ceph_options { #define CEPH_AUTH_NAME_DEFAULT "guest" -/* - * Delay telling the MDS we no longer want caps, in case we reopen - * the file. Delay a minimum amount of time, even if we send a cap - * message for some other reason. Otherwise, take the oppotunity to - * update the mds to avoid sending another message later. - */ -#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */ -#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */ - - /* mount state */ enum { CEPH_MOUNT_MOUNTING, -- cgit v1.2.3 From 3fb99d483e614bc3834784c7a686572c7970bb92 Mon Sep 17 00:00:00 2001 From: Yanhu Cao Date: Fri, 21 Jul 2017 17:20:10 +0800 Subject: ceph: nuke startsync op startsync is a no-op, has been for years. Remove it. Link: http://tracker.ceph.com/issues/20604 Signed-off-by: Yanhu Cao Reviewed-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/rados.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index b8281feda9c7..01408841c9c4 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -230,7 +230,6 @@ extern const char *ceph_osd_state_name(int s); \ /* fancy write */ \ f(APPEND, __CEPH_OSD_OP(WR, DATA, 6), "append") \ - f(STARTSYNC, __CEPH_OSD_OP(WR, DATA, 7), "startsync") \ f(SETTRUNC, __CEPH_OSD_OP(WR, DATA, 8), "settrunc") \ f(TRIMTRUNC, __CEPH_OSD_OP(WR, DATA, 9), "trimtrunc") \ \ -- cgit v1.2.3 From 95569713afc0b53ded1bba67834e0be24529a8c9 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Mon, 24 Jul 2017 17:59:39 +0800 Subject: ceph: new cap message flags indicate if there is pending capsnap These flags tell mds if there is pending capsnap explicitly. Without this explicit notification, mds can only conclude if client has pending capsnap. The method mds use is inefficient and error-prone. Signed-off-by: "Yan, Zheng" Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index edf5b04b918a..d1642a4b4c5e 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -669,7 +669,9 @@ enum { extern const char *ceph_cap_op_name(int op); /* flags field in client cap messages (version >= 10) */ -#define CEPH_CLIENT_CAPS_SYNC (0x1) +#define CEPH_CLIENT_CAPS_SYNC (1<<0) +#define CEPH_CLIENT_CAPS_NO_CAPSNAP (1<<1) +#define CEPH_CLIENT_CAPS_PENDING_CAPSNAP (1<<2); /* * caps message, used for capability callbacks, acks, requests, etc. -- cgit v1.2.3 From 06d74376c8af32f5b8d777a943aa4dc99165088b Mon Sep 17 00:00:00 2001 From: Douglas Fuller Date: Wed, 16 Aug 2017 10:19:27 -0400 Subject: ceph: more accurate statfs Improve accuracy of statfs reporting for Ceph filesystems comprising exactly one data pool. In this case, the Ceph monitor can now report the space usage for the single data pool instead of the global data for the entire Ceph cluster. Include support for this message in mon_client and leverage it in ceph/super. Signed-off-by: Douglas Fuller Reviewed-by: Yan, Zheng Reviewed-by: Ilya Dryomov Signed-off-by: Ilya Dryomov --- include/linux/ceph/ceph_fs.h | 2 ++ include/linux/ceph/mon_client.h | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index d1642a4b4c5e..b422170b791a 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -167,6 +167,8 @@ struct ceph_mon_request_header { struct ceph_mon_statfs { struct ceph_mon_request_header monhdr; struct ceph_fsid fsid; + __u8 contains_data_pool; + __le64 data_pool; } __attribute__ ((packed)); struct ceph_statfs { diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index d5a3ecea578d..0fa990bf867a 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -133,8 +133,8 @@ void ceph_monc_renew_subs(struct ceph_mon_client *monc); extern int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch, unsigned long timeout); -extern int ceph_monc_do_statfs(struct ceph_mon_client *monc, - struct ceph_statfs *buf); +int ceph_monc_do_statfs(struct ceph_mon_client *monc, u64 data_pool, + struct ceph_statfs *buf); int ceph_monc_get_version(struct ceph_mon_client *monc, const char *what, u64 *newest); -- cgit v1.2.3 From b2770da6425406cf3f6d3fddbf9086b1db0106a1 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Wed, 6 Sep 2017 16:18:35 -0700 Subject: mm: add vm_insert_mixed_mkwrite() When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. This series solves these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. This reduces memory usage and decreases latencies for some workloads, and it simplifies the DAX code, removing over 100 lines in total. This patch (of 5): To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path. Link: http://lkml.kernel.org/r/20170724170616.25810-2-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Reviewed-by: Jan Kara Acked-by: Kirill A. Shutemov Cc: "Darrick J. Wong" Cc: "Theodore Ts'o" Cc: Alexander Viro Cc: Andreas Dilger Cc: Christoph Hellwig Cc: Dan Williams Cc: Dave Chinner Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c1f6c95f3496..eb5e4bc946cc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2294,6 +2294,8 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); +int vm_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); -- cgit v1.2.3 From 91d25ba8a6b0d810dc844cebeedc53029118ce3e Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Wed, 6 Sep 2017 16:18:43 -0700 Subject: dax: use common 4k zero page for dax mmap reads When servicing mmap() reads from file holes the current DAX code allocates a page cache page of all zeroes and places the struct page pointer in the mapping->page_tree radix tree. This has three major drawbacks: 1) It consumes memory unnecessarily. For every 4k page that is read via a DAX mmap() over a hole, we allocate a new page cache page. This means that if you read 1GiB worth of pages, you end up using 1GiB of zeroed memory. This is easily visible by looking at the overall memory consumption of the system or by looking at /proc/[pid]/smaps: 7f62e72b3000-7f63272b3000 rw-s 00000000 103:00 12 /root/dax/data Size: 1048576 kB Rss: 1048576 kB Pss: 1048576 kB Shared_Clean: 0 kB Shared_Dirty: 0 kB Private_Clean: 1048576 kB Private_Dirty: 0 kB Referenced: 1048576 kB Anonymous: 0 kB LazyFree: 0 kB AnonHugePages: 0 kB ShmemPmdMapped: 0 kB Shared_Hugetlb: 0 kB Private_Hugetlb: 0 kB Swap: 0 kB SwapPss: 0 kB KernelPageSize: 4 kB MMUPageSize: 4 kB Locked: 0 kB 2) It is slower than using a common zero page because each page fault has more work to do. Instead of just inserting a common zero page we have to allocate a page cache page, zero it, and then insert it. Here are the average latencies of dax_load_hole() as measured by ftrace on a random test box: Old method, using zeroed page cache pages: 3.4 us New method, using the common 4k zero page: 0.8 us This was the average latency over 1 GiB of sequential reads done by this simple fio script: [global] size=1G filename=/root/dax/data fallocate=none [io] rw=read ioengine=mmap 3) The fact that we had to check for both DAX exceptional entries and for page cache pages in the radix tree made the DAX code more complex. Solve these issues by following the lead of the DAX PMD code and using a common 4k zero page instead. As with the PMD code we will now insert a DAX exceptional entry into the radix tree instead of a struct page pointer which allows us to remove all the special casing in the DAX code. Note that we do still pretty aggressively check for regular pages in the DAX radix tree, especially where we take action based on the bits set in the page. If we ever find a regular page in our radix tree now that most likely means that someone besides DAX is inserting pages (which has happened lots of times in the past), and we want to find that out early and fail loudly. This solution also removes the extra memory consumption. Here is that same /proc/[pid]/smaps after 1GiB of reading from a hole with the new code: 7f2054a74000-7f2094a74000 rw-s 00000000 103:00 12 /root/dax/data Size: 1048576 kB Rss: 0 kB Pss: 0 kB Shared_Clean: 0 kB Shared_Dirty: 0 kB Private_Clean: 0 kB Private_Dirty: 0 kB Referenced: 0 kB Anonymous: 0 kB LazyFree: 0 kB AnonHugePages: 0 kB ShmemPmdMapped: 0 kB Shared_Hugetlb: 0 kB Private_Hugetlb: 0 kB Swap: 0 kB SwapPss: 0 kB KernelPageSize: 4 kB MMUPageSize: 4 kB Locked: 0 kB Overall system memory consumption is similarly improved. Another major change is that we remove dax_pfn_mkwrite() from our fault flow, and instead rely on the page fault itself to make the PTE dirty and writeable. The following description from the patch adding the vm_insert_mixed_mkwrite() call explains this a little more: "To be able to use the common 4k zero page in DAX we need to have our PTE fault path look more like our PMD fault path where a PTE entry can be marked as dirty and writeable as it is first inserted rather than waiting for a follow-up dax_pfn_mkwrite() => finish_mkwrite_fault() call. Right now we can rely on having a dax_pfn_mkwrite() call because we can distinguish between these two cases in do_wp_page(): case 1: 4k zero page => writable DAX storage case 2: read-only DAX storage => writeable DAX storage This distinction is made by via vm_normal_page(). vm_normal_page() returns false for the common 4k zero page, though, just as it does for DAX ptes. Instead of special casing the DAX + 4k zero page case we will simplify our DAX PTE page fault sequence so that it matches our DAX PMD sequence, and get rid of the dax_pfn_mkwrite() helper. We will instead use dax_iomap_fault() to handle write-protection faults. This means that insert_pfn() needs to follow the lead of insert_pfn_pmd() and allow us to pass in a 'mkwrite' flag. If 'mkwrite' is set insert_pfn() will do the work that was previously done by wp_page_reuse() as part of the dax_pfn_mkwrite() call path" Link: http://lkml.kernel.org/r/20170724170616.25810-4-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Reviewed-by: Jan Kara Cc: "Darrick J. Wong" Cc: "Theodore Ts'o" Cc: Alexander Viro Cc: Andreas Dilger Cc: Christoph Hellwig Cc: Dan Williams Cc: Dave Chinner Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Steven Rostedt Cc: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dax.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index df97b7af7e2c..b3518559f0da 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -91,18 +91,17 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev); /* * We use lowest available bit in exceptional entry for locking, one bit for - * the entry size (PMD) and two more to tell us if the entry is a huge zero - * page (HZP) or an empty entry that is just used for locking. In total four - * special bits. + * the entry size (PMD) and two more to tell us if the entry is a zero page or + * an empty entry that is just used for locking. In total four special bits. * - * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the HZP and - * EMPTY bits aren't set the entry is a normal DAX entry with a filesystem + * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE + * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem * block allocation. */ #define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) #define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) #define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) -#define RADIX_DAX_HZP (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) +#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) #define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) static inline unsigned long dax_radix_sector(void *entry) @@ -153,7 +152,6 @@ static inline unsigned int dax_radix_order(void *entry) return 0; } #endif -int dax_pfn_mkwrite(struct vm_fault *vmf); static inline bool dax_mapping(struct address_space *mapping) { -- cgit v1.2.3 From d01ad197ac3b50a99ea668697acefe12e73c5fea Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Wed, 6 Sep 2017 16:18:47 -0700 Subject: dax: remove DAX code from page_cache_tree_insert() Now that we no longer insert struct page pointers in DAX radix trees we can remove the special casing for DAX in page_cache_tree_insert(). This also allows us to make dax_wake_mapping_entry_waiter() local to fs/dax.c, removing it from dax.h. Link: http://lkml.kernel.org/r/20170724170616.25810-5-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Suggested-by: Jan Kara Reviewed-by: Jan Kara Cc: "Darrick J. Wong" Cc: "Theodore Ts'o" Cc: Alexander Viro Cc: Andreas Dilger Cc: Christoph Hellwig Cc: Dan Williams Cc: Dave Chinner Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Steven Rostedt Cc: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dax.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index b3518559f0da..319e0d997446 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -123,8 +123,6 @@ int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -void dax_wake_mapping_entry_waiter(struct address_space *mapping, - pgoff_t index, void *entry, bool wake_all); #ifdef CONFIG_FS_DAX int __dax_zero_page_range(struct block_device *bdev, -- cgit v1.2.3 From 527b19d0808e75fbba896beb2435c2b4d6bcd32a Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Wed, 6 Sep 2017 16:18:51 -0700 Subject: dax: move all DAX radix tree defs to fs/dax.c Now that we no longer insert struct page pointers in DAX radix trees the page cache code no longer needs to know anything about DAX exceptional entries. Move all the DAX exceptional entry definitions from dax.h to fs/dax.c. Link: http://lkml.kernel.org/r/20170724170616.25810-6-ross.zwisler@linux.intel.com Signed-off-by: Ross Zwisler Suggested-by: Jan Kara Reviewed-by: Jan Kara Cc: "Darrick J. Wong" Cc: "Theodore Ts'o" Cc: Alexander Viro Cc: Andreas Dilger Cc: Christoph Hellwig Cc: Dan Williams Cc: Dave Chinner Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Steven Rostedt Cc: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/dax.h | 41 ----------------------------------------- 1 file changed, 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index 319e0d997446..eb0bff6f1eab 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -89,33 +89,6 @@ void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); -/* - * We use lowest available bit in exceptional entry for locking, one bit for - * the entry size (PMD) and two more to tell us if the entry is a zero page or - * an empty entry that is just used for locking. In total four special bits. - * - * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE - * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem - * block allocation. - */ -#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) -#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) -#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) -#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) -#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) - -static inline unsigned long dax_radix_sector(void *entry) -{ - return (unsigned long)entry >> RADIX_DAX_SHIFT; -} - -static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags) -{ - return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags | - ((unsigned long)sector << RADIX_DAX_SHIFT) | - RADIX_DAX_ENTRY_LOCK); -} - ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, @@ -137,20 +110,6 @@ static inline int __dax_zero_page_range(struct block_device *bdev, } #endif -#ifdef CONFIG_FS_DAX_PMD -static inline unsigned int dax_radix_order(void *entry) -{ - if ((unsigned long)entry & RADIX_DAX_PMD) - return PMD_SHIFT - PAGE_SHIFT; - return 0; -} -#else -static inline unsigned int dax_radix_order(void *entry) -{ - return 0; -} -#endif - static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); -- cgit v1.2.3 From 2482ddec670fb83717d129012bc558777cb159f7 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 6 Sep 2017 16:19:18 -0700 Subject: mm: add SLUB free list pointer obfuscation This SLUB free list pointer obfuscation code is modified from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. This adds a per-cache random value to SLUB caches that is XORed with their freelist pointer address and value. This adds nearly zero overhead and frustrates the very common heap overflow exploitation method of overwriting freelist pointers. A recent example of the attack is written up here: http://cyseclabs.com/blog/cve-2016-6187-heap-off-by-one-exploit and there is a section dedicated to the technique the book "A Guide to Kernel Exploitation: Attacking the Core". This is based on patches by Daniel Micay, and refactored to minimize the use of #ifdef. With 200-count cycles of "hackbench -g 20 -l 1000" I saw the following run times: before: mean 10.11882499999999999995 variance .03320378329145728642 stdev .18221905304181911048 after: mean 10.12654000000000000014 variance .04700556623115577889 stdev .21680767106160192064 The difference gets lost in the noise, but if the above is to be taken literally, using CONFIG_FREELIST_HARDENED is 0.07% slower. Link: http://lkml.kernel.org/r/20170802180609.GA66807@beast Signed-off-by: Kees Cook Suggested-by: Daniel Micay Cc: Rik van Riel Cc: Tycho Andersen Cc: Alexander Popov Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slub_def.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index cc0faf3a90be..0783b622311e 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -115,6 +115,10 @@ struct kmem_cache { #endif #endif +#ifdef CONFIG_SLAB_FREELIST_HARDENED + unsigned long random; +#endif + #ifdef CONFIG_NUMA /* * Defragmentation by allocating from a remote node. -- cgit v1.2.3 From d460acb5bdffc19b492b70b8f416c24dc03c474e Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Wed, 6 Sep 2017 16:19:26 -0700 Subject: mm: track actual nr_scanned during shrink_slab() Some shrinkers may only be able to free a bunch of objects at a time, and so free more than the requested nr_to_scan in one pass. Whilst other shrinkers may find themselves even unable to scan as many objects as they counted, and so underreport. Account for the extra freed/scanned objects against the total number of objects we intend to scan, otherwise we may end up penalising the slab far more than intended. Similarly, we want to add the underperforming scan to the deferred pass so that we try harder and harder in future passes. Link: http://lkml.kernel.org/r/20170822135325.9191-1-chris@chris-wilson.co.uk Signed-off-by: Chris Wilson Cc: Michal Hocko Cc: Johannes Weiner Cc: Hillf Danton Cc: Minchan Kim Cc: Vlastimil Babka Cc: Mel Gorman Cc: Shaohua Li Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Joonas Lahtinen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shrinker.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 4fcacd915d45..51d189615bda 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -18,6 +18,13 @@ struct shrink_control { */ unsigned long nr_to_scan; + /* + * How many objects did scan_objects process? + * This defaults to nr_to_scan before every call, but the callee + * should track its actual progress. + */ + unsigned long nr_scanned; + /* current node being shrunk (for NUMA aware shrinkers) */ int nid; -- cgit v1.2.3 From e5e68930263377c6d4f6da0ff06f36b55d83a83f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 6 Sep 2017 16:19:37 -0700 Subject: mm, memory_hotplug: display allowed zones in the preferred ordering Prior to commit f1dd2cd13c4b ("mm, memory_hotplug: do not associate hotadded memory to zones until online") we used to allow to change the valid zone types of a memory block if it is adjacent to a different zone type. This fact was reflected in memoryNN/valid_zones by the ordering of printed zones. The first one was default (echo online > memoryNN/state) and the other one could be onlined explicitly by online_{movable,kernel}. This behavior was removed by the said patch and as such the ordering was not all that important. In most cases a kernel zone would be default anyway. The only exception is movable_node handled by "mm, memory_hotplug: support movable_node for hotpluggable nodes". Let's reintroduce this behavior again because later patch will remove the zone overlap restriction and so user will be allowed to online kernel resp. movable block regardless of its placement. Original behavior will then become significant again because it would be non-trivial for users to see what is the default zone to online into. Implementation is really simple. Pull out zone selection out of move_pfn_range into zone_for_pfn_range helper and use it in show_valid_zones to display the zone for default onlining and then both kernel and movable if they are allowed. Default online zone is not duplicated. Link: http://lkml.kernel.org/r/20170714121233.16861-2-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Joonsoo Kim Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Reza Arbab Cc: Yasuaki Ishimatsu Cc: Xishi Qiu Cc: Kani Toshimitsu Cc: Cc: Daniel Kiper Cc: Igor Mammedov Cc: Vitaly Kuznetsov Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index c8a5056a5ae0..5e6e4cc36ff4 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -319,6 +319,6 @@ extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum); extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages, int online_type); -extern struct zone *default_zone_for_pfn(int nid, unsigned long pfn, +extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, unsigned long nr_pages); #endif /* __LINUX_MEMORY_HOTPLUG_H */ -- cgit v1.2.3 From c9bff3eebc09be23fbc868f5e6731666d23cbea3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 6 Sep 2017 16:20:13 -0700 Subject: mm, page_alloc: rip out ZONELIST_ORDER_ZONE Patch series "cleanup zonelists initialization", v1. This is aimed at cleaning up the zonelists initialization code we have but the primary motivation was bug report [2] which got resolved but the usage of stop_machine is just too ugly to live. Most patches are straightforward but 3 of them need a special consideration. Patch 1 removes zone ordered zonelists completely. I am CCing linux-api because this is a user visible change. As I argue in the patch description I do not think we have a strong usecase for it these days. I have kept sysctl in place and warn into the log if somebody tries to configure zone lists ordering. If somebody has a real usecase for it we can revert this patch but I do not expect anybody will actually notice runtime differences. This patch is not strictly needed for the rest but it made patch 6 easier to implement. Patch 7 removes stop_machine from build_all_zonelists without adding any special synchronization between iterators and updater which I _believe_ is acceptable as explained in the changelog. I hope I am not missing anything. Patch 8 then removes zonelists_mutex which is kind of ugly as well and not really needed AFAICS but a care should be taken when double checking my thinking. This patch (of 9): Supporting zone ordered zonelists costs us just a lot of code while the usefulness is arguable if existent at all. Mel has already made node ordering default on 64b systems. 32b systems are still using ZONELIST_ORDER_ZONE because it is considered better to fallback to a different NUMA node rather than consume precious lowmem zones. This argument is, however, weaken by the fact that the memory reclaim has been reworked to be node rather than zone oriented. This means that lowmem requests have to skip over all highmem pages on LRUs already and so zone ordering doesn't save the reclaim time much. So the only advantage of the zone ordering is under a light memory pressure when highmem requests do not ever hit into lowmem zones and the lowmem pressure doesn't need to reclaim. Considering that 32b NUMA systems are rather suboptimal already and it is generally advisable to use 64b kernel on such a HW I believe we should rather care about the code maintainability and just get rid of ZONELIST_ORDER_ZONE altogether. Keep systcl in place and warn if somebody tries to set zone ordering either from kernel command line or the sysctl. [mhocko@suse.com: reading vm.numa_zonelist_order will never terminate] Link: http://lkml.kernel.org/r/20170721143915.14161-2-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Shaohua Li Cc: Toshi Kani Cc: Abdul Haleem Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fc14b8b3f6ce..bfdc37b77d88 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -896,7 +896,7 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, extern int numa_zonelist_order_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern char numa_zonelist_order[]; -#define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ +#define NUMA_ZONELIST_ORDER_LEN 16 #ifndef CONFIG_NEED_MULTIPLE_NODES -- cgit v1.2.3 From 72675e131eb418c78980c1e683c0c25a25b61221 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 6 Sep 2017 16:20:24 -0700 Subject: mm, memory_hotplug: drop zone from build_all_zonelists build_all_zonelists gets a zone parameter to initialize zone's pagesets. There is only a single user which gives a non-NULL zone parameter and that one doesn't really need the rest of the build_all_zonelists (see commit 6dcd73d7011b ("memory-hotplug: allocate zone's pcp before onlining pages")). Therefore remove setup_zone_pageset from build_all_zonelists and call it from its only user directly. This will also remove a pointless zonlists rebuilding which is always good. Link: http://lkml.kernel.org/r/20170721143915.14161-5-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Mel Gorman Cc: Shaohua Li Cc: Toshi Kani Cc: Wen Congyang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bfdc37b77d88..551f68bec2fa 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -771,7 +771,7 @@ static inline bool is_dev_zone(const struct zone *zone) #include extern struct mutex zonelists_mutex; -void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); +void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, int classzone_idx, unsigned int alloc_flags, -- cgit v1.2.3 From b93e0f329e24f3615aa551fd9b99a75fb7c9195f Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 6 Sep 2017 16:20:37 -0700 Subject: mm, memory_hotplug: get rid of zonelists_mutex zonelists_mutex was introduced by commit 4eaf3f64397c ("mem-hotplug: fix potential race while building zonelist for new populated zone") to protect zonelist building from races. This is no longer needed though because both memory online and offline are fully serialized. New users have grown since then. Notably setup_per_zone_wmarks wants to prevent from races between memory hotplug, khugepaged setup and manual min_free_kbytes update via sysctl (see cfd3da1e49bb ("mm: Serialize access to min_free_kbytes"). Let's add a private lock for that purpose. This will not prevent from seeing halfway through memory hotplug operation but that shouldn't be a big deal becuse memory hotplug will update watermarks explicitly so we will eventually get a full picture. The lock just makes sure we won't race when updating watermarks leading to weird results. Also __build_all_zonelists manipulates global data so add a private lock for it as well. This doesn't seem to be necessary today but it is more robust to have a lock there. While we are at it make sure we document that memory online/offline depends on a full serialization either via mem_hotplug_begin() or device_lock. Link: http://lkml.kernel.org/r/20170721143915.14161-9-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Mel Gorman Cc: Shaohua Li Cc: Toshi Kani Cc: Vlastimil Babka Cc: Haicheng Li Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 551f68bec2fa..e7e92c8f4883 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -770,7 +770,6 @@ static inline bool is_dev_zone(const struct zone *zone) #include -extern struct mutex zonelists_mutex; void build_all_zonelists(pg_data_t *pgdat); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, -- cgit v1.2.3 From 26b433d0da062d6e19d75350c0171d3cf8ff560d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 6 Sep 2017 16:21:15 -0700 Subject: fscache: remove unused ->now_uncached callback Patch series "Ranged pagevec lookup", v2. In this series I make pagevec_lookup() update the index (to be consistent with pagevec_lookup_tag() and also as a preparation for ranged lookups), provide ranged variant of pagevec_lookup() and use it in places where it makes sense. This not only removes some common code but is also a measurable performance win for some use cases (see patch 4/10) where radix tree is sparse and searching & grabing of a page after the end of the range has measurable overhead. This patch (of 10): The callback doesn't ever get called. Remove it. Link: http://lkml.kernel.org/r/20170726114704.7626-2-jack@suse.cz Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fscache.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 115bb81912cc..f4ff47d4a893 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -143,15 +143,6 @@ struct fscache_cookie_def { void (*mark_page_cached)(void *cookie_netfs_data, struct address_space *mapping, struct page *page); - - /* indicate the cookie is no longer cached - * - this function is called when the backing store currently caching - * a cookie is removed - * - the netfs should use this to clean up any markers indicating - * cached pages - * - this is mandatory for any object that may have data - */ - void (*now_uncached)(void *cookie_netfs_data); }; /* -- cgit v1.2.3 From d72dc8a25afc71ce90ee92bdd77550e9beb85d4d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 6 Sep 2017 16:21:18 -0700 Subject: mm: make pagevec_lookup() update index Make pagevec_lookup() (and underlying find_get_pages()) update index to the next page where iteration should continue. Most callers want this and also pagevec_lookup_tag() already does this. Link: http://lkml.kernel.org/r/20170726114704.7626-3-jack@suse.cz Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 2 +- include/linux/pagevec.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 79b36f57c3ba..249b1b5964c7 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -353,7 +353,7 @@ struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); -unsigned find_get_pages(struct address_space *mapping, pgoff_t start, +unsigned find_get_pages(struct address_space *mapping, pgoff_t *start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index b45d391b4540..c395a5bb58b2 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -28,7 +28,7 @@ unsigned pagevec_lookup_entries(struct pagevec *pvec, pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, - pgoff_t start, unsigned nr_pages); + pgoff_t *start, unsigned nr_pages); unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, int tag, unsigned nr_pages); -- cgit v1.2.3 From b947cee4b96306037e166ff1ea5156c0ecdd7d91 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 6 Sep 2017 16:21:21 -0700 Subject: mm: implement find_get_pages_range() Implement a variant of find_get_pages() that stops iterating at given index. This may be substantial performance gain if the mapping is sparse. See following commit for details. Furthermore lots of users of this function (through pagevec_lookup()) actually want a range lookup and all of them are currently open-coding this. Also create corresponding pagevec_lookup_range() function. Link: http://lkml.kernel.org/r/20170726114704.7626-4-jack@suse.cz Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 12 ++++++++++-- include/linux/pagevec.h | 13 +++++++++++-- 2 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 249b1b5964c7..5bbd6780f205 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -353,8 +353,16 @@ struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices); -unsigned find_get_pages(struct address_space *mapping, pgoff_t *start, - unsigned int nr_pages, struct page **pages); +unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, + pgoff_t end, unsigned int nr_pages, + struct page **pages); +static inline unsigned find_get_pages(struct address_space *mapping, + pgoff_t *start, unsigned int nr_pages, + struct page **pages) +{ + return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages, + pages); +} unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index c395a5bb58b2..7df056910437 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -27,8 +27,17 @@ unsigned pagevec_lookup_entries(struct pagevec *pvec, pgoff_t start, unsigned nr_entries, pgoff_t *indices); void pagevec_remove_exceptionals(struct pagevec *pvec); -unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, - pgoff_t *start, unsigned nr_pages); +unsigned pagevec_lookup_range(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t *start, pgoff_t end, unsigned nr_pages); +static inline unsigned pagevec_lookup(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t *start, unsigned nr_pages) +{ + return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1, + nr_pages); +} + unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, int tag, unsigned nr_pages); -- cgit v1.2.3 From 397162ffa2ed1cadffe05c324c6ddc53647f9c62 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 6 Sep 2017 16:21:43 -0700 Subject: mm: remove nr_pages argument from pagevec_lookup{,_range}() All users of pagevec_lookup() and pagevec_lookup_range() now pass PAGEVEC_SIZE as a desired number of pages. Just drop the argument. Link: http://lkml.kernel.org/r/20170726114704.7626-11-jack@suse.cz Signed-off-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagevec.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 7df056910437..4dcd5506f1ed 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -29,13 +29,12 @@ unsigned pagevec_lookup_entries(struct pagevec *pvec, void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, - pgoff_t *start, pgoff_t end, unsigned nr_pages); + pgoff_t *start, pgoff_t end); static inline unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, - pgoff_t *start, unsigned nr_pages) + pgoff_t *start) { - return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1, - nr_pages); + return pagevec_lookup_range(pvec, mapping, start, (pgoff_t)-1); } unsigned pagevec_lookup_tag(struct pagevec *pvec, -- cgit v1.2.3 From 04fecbf51b3cb79a628d50b65797c4866342b8d2 Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Wed, 6 Sep 2017 16:22:09 -0700 Subject: mm: memcontrol: use int for event/state parameter in several functions Several functions use an enum type as parameter for an event/state, but are called in some locations with an argument of a different enum type. Adjust the interface of these functions to reality by changing the parameter to int. This fixes a ton of enum-conversion warnings that are generated when building the kernel with clang. [mka@chromium.org: also change parameter type of inc/dec/mod_memcg_page_state()] Link: http://lkml.kernel.org/r/20170728213442.93823-1-mka@chromium.org Link: http://lkml.kernel.org/r/20170727211004.34435-1-mka@chromium.org Signed-off-by: Matthias Kaehlcke Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Doug Anderson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 52 ++++++++++++++++++++++++++++------------------ 1 file changed, 32 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9b15a4bcfa77..69966c461d1c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -488,8 +488,9 @@ struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { long val = 0; int cpu; @@ -503,15 +504,17 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, return val; } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, int val) + int idx, int val) { if (!mem_cgroup_disabled()) __this_cpu_add(memcg->stat->count[idx], val); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, int val) + int idx, int val) { if (!mem_cgroup_disabled()) this_cpu_add(memcg->stat->count[idx], val); @@ -535,14 +538,14 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, * Kernel pages are an exception to this, since they'll never move. */ static inline void __mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, int val) + int idx, int val) { if (page->mem_cgroup) __mod_memcg_state(page->mem_cgroup, idx, val); } static inline void mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, int val) + int idx, int val) { if (page->mem_cgroup) mod_memcg_state(page->mem_cgroup, idx, val); @@ -632,8 +635,9 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, this_cpu_add(memcg->stat->events[idx], count); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void count_memcg_page_event(struct page *page, - enum memcg_stat_item idx) + int idx) { if (page->mem_cgroup) count_memcg_events(page->mem_cgroup, idx, 1); @@ -846,31 +850,31 @@ static inline bool mem_cgroup_oom_synchronize(bool wait) } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { return 0; } static inline void __mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, + int idx, int nr) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx, + int idx, int nr) { } static inline void __mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, + int idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, - enum memcg_stat_item idx, + int idx, int nr) { } @@ -924,7 +928,7 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, } static inline void count_memcg_page_event(struct page *page, - enum memcg_stat_item idx) + int idx) { } @@ -934,26 +938,30 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) } #endif /* CONFIG_MEMCG */ +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { __mod_memcg_state(memcg, idx, 1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { __mod_memcg_state(memcg, idx, -1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_page_state(struct page *page, - enum memcg_stat_item idx) + int idx) { __mod_memcg_page_state(page, idx, 1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_page_state(struct page *page, - enum memcg_stat_item idx) + int idx) { __mod_memcg_page_state(page, idx, -1); } @@ -982,26 +990,30 @@ static inline void __dec_lruvec_page_state(struct page *page, __mod_lruvec_page_state(page, idx, -1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { mod_memcg_state(memcg, idx, 1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_state(struct mem_cgroup *memcg, - enum memcg_stat_item idx) + int idx) { mod_memcg_state(memcg, idx, -1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_page_state(struct page *page, - enum memcg_stat_item idx) + int idx) { mod_memcg_page_state(page, idx, 1); } +/* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_page_state(struct page *page, - enum memcg_stat_item idx) + int idx) { mod_memcg_page_state(page, idx, -1); } -- cgit v1.2.3 From e07098294adfd03d582af7626752255e3d170393 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:22:16 -0700 Subject: mm, THP, swap: support to reclaim swap space for THP swapped out The normal swap slot reclaiming can be done when the swap count reaches SWAP_HAS_CACHE. But for the swap slot which is backing a THP, all swap slots backing one THP must be reclaimed together, because the swap slot may be used again when the THP is swapped out again later. So the swap slots backing one THP can be reclaimed together when the swap count for all swap slots for the THP reached SWAP_HAS_CACHE. In the patch, the functions to check whether the swap count for all swap slots backing one THP reached SWAP_HAS_CACHE are implemented and used when checking whether a swap slot can be reclaimed. To make it easier to determine whether a swap slot is backing a THP, a new swap cluster flag named CLUSTER_FLAG_HUGE is added to mark a swap cluster which is backing a THP (Transparent Huge Page). Because THP swap in as a whole isn't supported now. After deleting the THP from the swap cache (for example, swapping out finished), the CLUSTER_FLAG_HUGE flag will be cleared. So that, the normal pages inside THP can be swapped in individually. [ying.huang@intel.com: fix swap_page_trans_huge_swapped on HDD] Link: http://lkml.kernel.org/r/874ltsm0bi.fsf@yhuang-dev.intel.com Link: http://lkml.kernel.org/r/20170724051840.2309-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" Acked-by: Rik van Riel Cc: Johannes Weiner Cc: Minchan Kim Cc: Hugh Dickins Cc: Shaohua Li Cc: "Kirill A . Shutemov" Cc: Andrea Arcangeli Cc: Dan Williams Cc: Jens Axboe Cc: Michal Hocko Cc: Ross Zwisler [for brd.c, zram_drv.c, pmem.c] Cc: Vishal L Verma Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index d83d28e53e62..964b4f1fba4a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -188,6 +188,7 @@ struct swap_cluster_info { }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ +#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */ /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from -- cgit v1.2.3 From ba3c4ce6def4915093be80585ff69f780630f32f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:22:19 -0700 Subject: mm, THP, swap: make reuse_swap_page() works for THP swapped out After supporting to delay THP (Transparent Huge Page) splitting after swapped out, it is possible that some page table mappings of the THP are turned into swap entries. So reuse_swap_page() need to check the swap count in addition to the map count as before. This patch done that. In the huge PMD write protect fault handler, in addition to the page map count, the swap count need to be checked too, so the page lock need to be acquired too when calling reuse_swap_page() in addition to the page table lock. [ying.huang@intel.com: silence a compiler warning] Link: http://lkml.kernel.org/r/87bmnzizjy.fsf@yhuang-dev.intel.com Link: http://lkml.kernel.org/r/20170724051840.2309-4-ying.huang@intel.com Signed-off-by: "Huang, Ying" Cc: Johannes Weiner Cc: Minchan Kim Cc: Hugh Dickins Cc: Shaohua Li Cc: Rik van Riel Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Cc: Dan Williams Cc: Jens Axboe Cc: Michal Hocko Cc: Ross Zwisler [for brd.c, zram_drv.c, pmem.c] Cc: Vishal L Verma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 964b4f1fba4a..7176ba780e83 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -510,8 +510,8 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page, total_mapcount) \ - (page_trans_huge_mapcount(page, total_mapcount) == 1) +#define reuse_swap_page(page, total_map_swapcount) \ + (page_trans_huge_mapcount(page, total_map_swapcount) == 1) static inline int try_to_free_swap(struct page *page) { -- cgit v1.2.3 From 225311a46411c37e20e73d99f4382f141e12f6f9 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:22:30 -0700 Subject: mm: test code to write THP to swap device as a whole To support delay splitting THP (Transparent Huge Page) after swapped out, we need to enhance swap writing code to support to write a THP as a whole. This will improve swap write IO performance. As Ming Lei pointed out, this should be based on multipage bvec support, which hasn't been merged yet. So this patch is only for testing the functionality of the other patches in the series. And will be reimplemented after multipage bvec support is merged. Link: http://lkml.kernel.org/r/20170724051840.2309-7-ying.huang@intel.com Signed-off-by: "Huang, Ying" Cc: "Kirill A . Shutemov" Cc: Andrea Arcangeli Cc: Dan Williams Cc: Hugh Dickins Cc: Jens Axboe Cc: Johannes Weiner Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Cc: Ross Zwisler [for brd.c, zram_drv.c, pmem.c] Cc: Shaohua Li Cc: Vishal L Verma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bio.h | 8 ++++++++ include/linux/page-flags.h | 4 ++-- include/linux/vm_event_item.h | 1 + 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 7b1cf4ba0902..1f0720de8990 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -38,7 +38,15 @@ #define BIO_BUG_ON #endif +#ifdef CONFIG_THP_SWAP +#if HPAGE_PMD_NR > 256 +#define BIO_MAX_PAGES HPAGE_PMD_NR +#else #define BIO_MAX_PAGES 256 +#endif +#else +#define BIO_MAX_PAGES 256 +#endif #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index d33e3280c8ad..ba2d470d2d0a 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,8 +303,8 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ -TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND) - TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND) +TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) + TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 37e8d31a4632..c75024e80eed 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -85,6 +85,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, + THP_SWPOUT, #endif #ifdef CONFIG_MEMORY_BALLOON BALLOON_INFLATE, -- cgit v1.2.3 From 59807685a7e77e8c8fe5925613968841538d53d7 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:22:34 -0700 Subject: mm, THP, swap: support splitting THP for THP swap out After adding swapping out support for THP (Transparent Huge Page), it is possible that a THP in swap cache (partly swapped out) need to be split. To split such a THP, the swap cluster backing the THP need to be split too, that is, the CLUSTER_FLAG_HUGE flag need to be cleared for the swap cluster. The patch implemented this. And because the THP swap writing needs the THP keeps as huge page during writing. The PageWriteback flag is checked before splitting. Link: http://lkml.kernel.org/r/20170724051840.2309-8-ying.huang@intel.com Signed-off-by: "Huang, Ying" Cc: Johannes Weiner Cc: Minchan Kim Cc: Hugh Dickins Cc: Shaohua Li Cc: Rik van Riel Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Cc: Dan Williams Cc: Jens Axboe Cc: Michal Hocko Cc: Ross Zwisler [for brd.c, zram_drv.c, pmem.c] Cc: Vishal L Verma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 7176ba780e83..461cf107ad52 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -527,6 +527,15 @@ static inline swp_entry_t get_swap_page(struct page *page) #endif /* CONFIG_SWAP */ +#ifdef CONFIG_THP_SWAP +extern int split_swap_cluster(swp_entry_t entry); +#else +static inline int split_swap_cluster(swp_entry_t entry) +{ + return 0; +} +#endif + #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { -- cgit v1.2.3 From fe490cc0fe9e6ee48cc48bb5dc463bc5f0f1428f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:22:52 -0700 Subject: mm, THP, swap: add THP swapping out fallback counting When swapping out THP (Transparent Huge Page), instead of swapping out the THP as a whole, sometimes we have to fallback to split the THP into normal pages before swapping, because no free swap clusters are available, or cgroup limit is exceeded, etc. To count the number of the fallback, a new VM event THP_SWPOUT_FALLBACK is added, and counted when we fallback to split the THP. Link: http://lkml.kernel.org/r/20170724051840.2309-13-ying.huang@intel.com Signed-off-by: "Huang, Ying" Cc: Johannes Weiner Cc: Minchan Kim Cc: Hugh Dickins Cc: Shaohua Li Cc: Rik van Riel Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Cc: Michal Hocko Cc: Dan Williams Cc: Jens Axboe Cc: Ross Zwisler [for brd.c, zram_drv.c, pmem.c] Cc: Vishal L Verma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index c75024e80eed..e02820fc2861 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -86,6 +86,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, THP_SWPOUT, + THP_SWPOUT_FALLBACK, #endif #ifdef CONFIG_MEMORY_BALLOON BALLOON_INFLATE, -- cgit v1.2.3 From 8d10396342063c79e92c4e46215370ab7b988569 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Wed, 6 Sep 2017 16:23:02 -0700 Subject: userfaultfd: shmem: add shmem_mfill_zeropage_pte for userfaultfd support shmem_mfill_zeropage_pte is the low level routine that implements the userfaultfd UFFDIO_ZEROPAGE command. Since for shmem mappings zero pages are always allocated and accounted, the new method is a slight extension of the existing shmem_mcopy_atomic_pte. Link: http://lkml.kernel.org/r/1497939652-16528-4-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Hillf Danton Cc: Hugh Dickins Cc: Pavel Emelyanov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index a7d6bd2a918f..b6c3540e07bc 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -137,9 +137,15 @@ extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, unsigned long dst_addr, unsigned long src_addr, struct page **pagep); +extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, + pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr); #else #define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) +#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \ + dst_addr) ({ BUG(); 0; }) #endif #endif -- cgit v1.2.3 From a446d6f9ce545248c62ab9694d05ac6f68563706 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 6 Sep 2017 16:23:22 -0700 Subject: include/linux/fs.h: remove unneeded forward definition of mm_struct Link: http://lkml.kernel.org/r/20170525102927.6163-1-jlayton@redhat.com Signed-off-by: Jeff Layton Reviewed-by: Jan Kara Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index cc2e0f5a8fd1..baea880c5c03 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1270,8 +1270,6 @@ extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); -struct mm_struct; - /* * Umount options */ -- cgit v1.2.3 From 4da243ac1cf6aeb30b7c555d56208982d66d6d33 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 6 Sep 2017 16:23:33 -0700 Subject: mm: shm: use new hugetlb size encoding definitions Use the common definitions from hugetlb_encode.h header file for encoding hugetlb size definitions in shmget system call flags. In addition, move these definitions from the internal (kernel) to user (uapi) header file. Link: http://lkml.kernel.org/r/1501527386-10736-4-git-send-email-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Suggested-by: Matthew Wilcox Acked-by: Michal Hocko Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Aneesh Kumar K.V Cc: Anshuman Khandual Cc: Arnd Bergmann Cc: Davidlohr Bueso Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shm.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shm.h b/include/linux/shm.h index 0fb7061ec54c..21a5e6c43385 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -27,23 +27,6 @@ struct shmid_kernel /* private to the kernel */ /* shm_mode upper byte flags */ #define SHM_DEST 01000 /* segment will be destroyed on last detach */ #define SHM_LOCKED 02000 /* segment will not be swapped */ -#define SHM_HUGETLB 04000 /* segment will use huge TLB pages */ -#define SHM_NORESERVE 010000 /* don't check for reservations */ - -/* Bits [26:31] are reserved */ - -/* - * When SHM_HUGETLB is set bits [26:31] encode the log2 of the huge page size. - * This gives us 6 bits, which is enough until someone invents 128 bit address - * spaces. - * - * Assume these are all power of twos. - * When 0 use the default page size. - */ -#define SHM_HUGE_SHIFT 26 -#define SHM_HUGE_MASK 0x3f -#define SHM_HUGE_2MB (21 << SHM_HUGE_SHIFT) -#define SHM_HUGE_1GB (30 << SHM_HUGE_SHIFT) #ifdef CONFIG_SYSVIPC struct sysv_shm { -- cgit v1.2.3 From c41f012ade0b95b0a6e25c7150673e0554736165 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 6 Sep 2017 16:23:36 -0700 Subject: mm: rename global_page_state to global_zone_page_state global_page_state is error prone as a recent bug report pointed out [1]. It only returns proper values for zone based counters as the enum it gets suggests. We already have global_node_page_state so let's rename global_page_state to global_zone_page_state to be more explicit here. All existing users seems to be correct: $ git grep "global_page_state(NR_" | sed 's@.*(\(NR_[A-Z_]*\)).*@\1@' | sort | uniq -c 2 NR_BOUNCE 2 NR_FREE_CMA_PAGES 11 NR_FREE_PAGES 1 NR_KERNEL_STACK_KB 1 NR_MLOCK 2 NR_PAGETABLE This patch shouldn't introduce any functional change. [1] http://lkml.kernel.org/r/201707260628.v6Q6SmaS030814@www262.sakura.ne.jp Link: http://lkml.kernel.org/r/20170801134256.5400-2-hannes@cmpxchg.org Signed-off-by: Michal Hocko Signed-off-by: Johannes Weiner Cc: Tetsuo Handa Cc: Josef Bacik Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 ++-- include/linux/vmstat.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 461cf107ad52..76f1632eea5a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -263,8 +263,8 @@ extern unsigned long totalreserve_pages; extern unsigned long nr_free_buffer_pages(void); extern unsigned long nr_free_pagecache_pages(void); -/* Definition of global_page_state not available yet */ -#define nr_free_pages() global_page_state(NR_FREE_PAGES) +/* Definition of global_zone_page_state not available yet */ +#define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index b3d85f30d424..97e11ab573f0 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -123,7 +123,7 @@ static inline void node_page_state_add(long x, struct pglist_data *pgdat, atomic_long_add(x, &vm_node_stat[item]); } -static inline unsigned long global_page_state(enum zone_stat_item item) +static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP @@ -199,7 +199,7 @@ extern unsigned long sum_zone_node_page_state(int node, extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); #else -#define sum_zone_node_page_state(node, item) global_page_state(item) +#define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #endif /* CONFIG_NUMA */ -- cgit v1.2.3 From cbc65df240c104bf540af1ad58595bf1eaa5ee10 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:24:29 -0700 Subject: mm, swap: add swap readahead hit statistics Patch series "mm, swap: VMA based swap readahead", v4. The swap readahead is an important mechanism to reduce the swap in latency. Although pure sequential memory access pattern isn't very popular for anonymous memory, the space locality is still considered valid. In the original swap readahead implementation, the consecutive blocks in swap device are readahead based on the global space locality estimation. But the consecutive blocks in swap device just reflect the order of page reclaiming, don't necessarily reflect the access pattern in virtual memory space. And the different tasks in the system may have different access patterns, which makes the global space locality estimation incorrect. In this patchset, when page fault occurs, the virtual pages near the fault address will be readahead instead of the swap slots near the fault swap slot in swap device. This avoid to readahead the unrelated swap slots. At the same time, the swap readahead is changed to work on per-VMA from globally. So that the different access patterns of the different VMAs could be distinguished, and the different readahead policy could be applied accordingly. The original core readahead detection and scaling algorithm is reused, because it is an effect algorithm to detect the space locality. In addition to the swap readahead changes, some new sysfs interface is added to show the efficiency of the readahead algorithm and some other swap statistics. This new implementation will incur more small random read, on SSD, the improved correctness of estimation and readahead target should beat the potential increased overhead, this is also illustrated in the test results below. But on HDD, the overhead may beat the benefit, so the original implementation will be used by default. The test and result is as follow, Common test condition ===================== Test Machine: Xeon E5 v3 (2 sockets, 72 threads, 32G RAM) Swap device: NVMe disk Micro-benchmark with combined access pattern ============================================ vm-scalability, sequential swap test case, 4 processes to eat 50G virtual memory space, repeat the sequential memory writing until 300 seconds. The first round writing will trigger swap out, the following rounds will trigger sequential swap in and out. At the same time, run vm-scalability random swap test case in background, 8 processes to eat 30G virtual memory space, repeat the random memory write until 300 seconds. This will trigger random swap-in in the background. This is a combined workload with sequential and random memory accessing at the same time. The result (for sequential workload) is as follow, Base Optimized ---- --------- throughput 345413 KB/s 414029 KB/s (+19.9%) latency.average 97.14 us 61.06 us (-37.1%) latency.50th 2 us 1 us latency.60th 2 us 1 us latency.70th 98 us 2 us latency.80th 160 us 2 us latency.90th 260 us 217 us latency.95th 346 us 369 us latency.99th 1.34 ms 1.09 ms ra_hit% 52.69% 99.98% The original swap readahead algorithm is confused by the background random access workload, so readahead hit rate is lower. The VMA-base readahead algorithm works much better. Linpack ======= The test memory size is bigger than RAM to trigger swapping. Base Optimized ---- --------- elapsed_time 393.49 s 329.88 s (-16.2%) ra_hit% 86.21% 98.82% The score of base and optimized kernel hasn't visible changes. But the elapsed time reduced and readahead hit rate improved, so the optimized kernel runs better for startup and tear down stages. And the absolute value of readahead hit rate is high, shows that the space locality is still valid in some practical workloads. This patch (of 5): The statistics for total readahead pages and total readahead hits are recorded and exported via the following sysfs interface. /sys/kernel/mm/swap/ra_hits /sys/kernel/mm/swap/ra_total With them, the efficiency of the swap readahead could be measured, so that the swap readahead algorithm and parameters could be tuned accordingly. [akpm@linux-foundation.org: don't display swap stats if CONFIG_SWAP=n] Link: http://lkml.kernel.org/r/20170807054038.1843-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" Cc: Johannes Weiner Cc: Minchan Kim Cc: Rik van Riel Cc: Shaohua Li Cc: Hugh Dickins Cc: Fengguang Wu Cc: Tim Chen Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index e02820fc2861..d77bc35278b0 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -105,6 +105,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, VMACACHE_FIND_CALLS, VMACACHE_FIND_HITS, VMACACHE_FULL_FLUSHES, +#endif +#ifdef CONFIG_SWAP + SWAP_RA, + SWAP_RA_HIT, #endif NR_VM_EVENT_ITEMS }; -- cgit v1.2.3 From ec560175c0b6fce86994bdf036754d48122c5c87 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:24:36 -0700 Subject: mm, swap: VMA based swap readahead The swap readahead is an important mechanism to reduce the swap in latency. Although pure sequential memory access pattern isn't very popular for anonymous memory, the space locality is still considered valid. In the original swap readahead implementation, the consecutive blocks in swap device are readahead based on the global space locality estimation. But the consecutive blocks in swap device just reflect the order of page reclaiming, don't necessarily reflect the access pattern in virtual memory. And the different tasks in the system may have different access patterns, which makes the global space locality estimation incorrect. In this patch, when page fault occurs, the virtual pages near the fault address will be readahead instead of the swap slots near the fault swap slot in swap device. This avoid to readahead the unrelated swap slots. At the same time, the swap readahead is changed to work on per-VMA from globally. So that the different access patterns of the different VMAs could be distinguished, and the different readahead policy could be applied accordingly. The original core readahead detection and scaling algorithm is reused, because it is an effect algorithm to detect the space locality. The test and result is as follow, Common test condition ===================== Test Machine: Xeon E5 v3 (2 sockets, 72 threads, 32G RAM) Swap device: NVMe disk Micro-benchmark with combined access pattern ============================================ vm-scalability, sequential swap test case, 4 processes to eat 50G virtual memory space, repeat the sequential memory writing until 300 seconds. The first round writing will trigger swap out, the following rounds will trigger sequential swap in and out. At the same time, run vm-scalability random swap test case in background, 8 processes to eat 30G virtual memory space, repeat the random memory write until 300 seconds. This will trigger random swap-in in the background. This is a combined workload with sequential and random memory accessing at the same time. The result (for sequential workload) is as follow, Base Optimized ---- --------- throughput 345413 KB/s 414029 KB/s (+19.9%) latency.average 97.14 us 61.06 us (-37.1%) latency.50th 2 us 1 us latency.60th 2 us 1 us latency.70th 98 us 2 us latency.80th 160 us 2 us latency.90th 260 us 217 us latency.95th 346 us 369 us latency.99th 1.34 ms 1.09 ms ra_hit% 52.69% 99.98% The original swap readahead algorithm is confused by the background random access workload, so readahead hit rate is lower. The VMA-base readahead algorithm works much better. Linpack ======= The test memory size is bigger than RAM to trigger swapping. Base Optimized ---- --------- elapsed_time 393.49 s 329.88 s (-16.2%) ra_hit% 86.21% 98.82% The score of base and optimized kernel hasn't visible changes. But the elapsed time reduced and readahead hit rate improved, so the optimized kernel runs better for startup and tear down stages. And the absolute value of readahead hit rate is high, shows that the space locality is still valid in some practical workloads. Link: http://lkml.kernel.org/r/20170807054038.1843-4-ying.huang@intel.com Signed-off-by: "Huang, Ying" Cc: Johannes Weiner Cc: Minchan Kim Cc: Rik van Riel Cc: Shaohua Li Cc: Hugh Dickins Cc: Fengguang Wu Cc: Tim Chen Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 1 + include/linux/swap.h | 57 ++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 56 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 57378c7cb5f8..f45ad815b7d7 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -335,6 +335,7 @@ struct vm_area_struct { struct file * vm_file; /* File we map to (can be NULL). */ void * vm_private_data; /* was vm_pte (shared mem) */ + atomic_long_t swap_readahead_info; #ifndef CONFIG_MMU struct vm_region *vm_region; /* NOMMU mapping region */ #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index 76f1632eea5a..61d63379e956 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -251,6 +251,25 @@ struct swap_info_struct { struct swap_cluster_list discard_clusters; /* discard clusters list */ }; +#ifdef CONFIG_64BIT +#define SWAP_RA_ORDER_CEILING 5 +#else +/* Avoid stack overflow, because we need to save part of page table */ +#define SWAP_RA_ORDER_CEILING 3 +#define SWAP_RA_PTE_CACHE_SIZE (1 << SWAP_RA_ORDER_CEILING) +#endif + +struct vma_swap_readahead { + unsigned short win; + unsigned short offset; + unsigned short nr_pte; +#ifdef CONFIG_64BIT + pte_t *ptes; +#else + pte_t ptes[SWAP_RA_PTE_CACHE_SIZE]; +#endif +}; + /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); @@ -350,6 +369,7 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *, #define SWAP_ADDRESS_SPACE_SHIFT 14 #define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT) extern struct address_space *swapper_spaces[]; +extern bool swap_vma_readahead; #define swap_address_space(entry) \ (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ >> SWAP_ADDRESS_SPACE_SHIFT]) @@ -362,7 +382,9 @@ extern void __delete_from_swap_cache(struct page *); extern void delete_from_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); -extern struct page *lookup_swap_cache(swp_entry_t); +extern struct page *lookup_swap_cache(swp_entry_t entry, + struct vm_area_struct *vma, + unsigned long addr); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool do_poll); @@ -372,6 +394,17 @@ extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); +extern struct page *swap_readahead_detect(struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra); +extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf, + struct vma_swap_readahead *swap_ra); + +static inline bool swap_use_vma_readahead(void) +{ + return READ_ONCE(swap_vma_readahead); +} + /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; @@ -466,12 +499,32 @@ static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask, return NULL; } +static inline bool swap_use_vma_readahead(void) +{ + return false; +} + +static inline struct page *swap_readahead_detect( + struct vm_fault *vmf, struct vma_swap_readahead *swap_ra) +{ + return NULL; +} + +static inline struct page *do_swap_page_readahead( + swp_entry_t fentry, gfp_t gfp_mask, + struct vm_fault *vmf, struct vma_swap_readahead *swap_ra) +{ + return NULL; +} + static inline int swap_writepage(struct page *p, struct writeback_control *wbc) { return 0; } -static inline struct page *lookup_swap_cache(swp_entry_t swp) +static inline struct page *lookup_swap_cache(swp_entry_t swp, + struct vm_area_struct *vma, + unsigned long addr) { return NULL; } -- cgit v1.2.3 From 81a0298bdfab0203d360df7c9bf690d1d457f999 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:24:43 -0700 Subject: mm, swap: don't use VMA based swap readahead if HDD is used as swap VMA based swap readahead will readahead the virtual pages that is continuous in the virtual address space. While the original swap readahead will readahead the swap slots that is continuous in the swap device. Although VMA based swap readahead is more correct for the swap slots to be readahead, it will trigger more small random readings, which may cause the performance of HDD (hard disk) to degrade heavily, and may finally exceed the benefit. To avoid the issue, in this patch, if the HDD is used as swap, the VMA based swap readahead will be disabled, and the original swap readahead will be used instead. Link: http://lkml.kernel.org/r/20170807054038.1843-6-ying.huang@intel.com Signed-off-by: "Huang, Ying" Cc: Johannes Weiner Cc: Minchan Kim Cc: Rik van Riel Cc: Shaohua Li Cc: Hugh Dickins Cc: Fengguang Wu Cc: Tim Chen Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 61d63379e956..9c4ae6f14eea 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -400,16 +400,17 @@ extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask, struct vm_fault *vmf, struct vma_swap_readahead *swap_ra); -static inline bool swap_use_vma_readahead(void) -{ - return READ_ONCE(swap_vma_readahead); -} - /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; +extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); +static inline bool swap_use_vma_readahead(void) +{ + return READ_ONCE(swap_vma_readahead) && !atomic_read(&nr_rotate_swap); +} + /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { -- cgit v1.2.3 From a2468cc9bfdff6139f59ca896671e5819ff5f94a Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Wed, 6 Sep 2017 16:24:57 -0700 Subject: swap: choose swap device according to numa node If the system has more than one swap device and swap device has the node information, we can make use of this information to decide which swap device to use in get_swap_pages() to get better performance. The current code uses a priority based list, swap_avail_list, to decide which swap device to use and if multiple swap devices share the same priority, they are used round robin. This patch changes the previous single global swap_avail_list into a per-numa-node list, i.e. for each numa node, it sees its own priority based list of available swap devices. Swap device's priority can be promoted on its matching node's swap_avail_list. The current swap device's priority is set as: user can set a >=0 value, or the system will pick one starting from -1 then downwards. The priority value in the swap_avail_list is the negated value of the swap device's due to plist being sorted from low to high. The new policy doesn't change the semantics for priority >=0 cases, the previous starting from -1 then downwards now becomes starting from -2 then downwards and -1 is reserved as the promoted value. Take 4-node EX machine as an example, suppose 4 swap devices are available, each sit on a different node: swapA on node 0 swapB on node 1 swapC on node 2 swapD on node 3 After they are all swapped on in the sequence of ABCD. Current behaviour: their priorities will be: swapA: -1 swapB: -2 swapC: -3 swapD: -4 And their position in the global swap_avail_list will be: swapA -> swapB -> swapC -> swapD prio:1 prio:2 prio:3 prio:4 New behaviour: their priorities will be(note that -1 is skipped): swapA: -2 swapB: -3 swapC: -4 swapD: -5 And their positions in the 4 swap_avail_lists[nid] will be: swap_avail_lists[0]: /* node 0's available swap device list */ swapA -> swapB -> swapC -> swapD prio:1 prio:3 prio:4 prio:5 swap_avali_lists[1]: /* node 1's available swap device list */ swapB -> swapA -> swapC -> swapD prio:1 prio:2 prio:4 prio:5 swap_avail_lists[2]: /* node 2's available swap device list */ swapC -> swapA -> swapB -> swapD prio:1 prio:2 prio:3 prio:5 swap_avail_lists[3]: /* node 3's available swap device list */ swapD -> swapA -> swapB -> swapC prio:1 prio:2 prio:3 prio:4 To see the effect of the patch, a test that starts N process, each mmap a region of anonymous memory and then continually write to it at random position to trigger both swap in and out is used. On a 2 node Skylake EP machine with 64GiB memory, two 170GB SSD drives are used as swap devices with each attached to a different node, the result is: runtime=30m/processes=32/total test size=128G/each process mmap region=4G kernel throughput vanilla 13306 auto-binding 15169 +14% runtime=30m/processes=64/total test size=128G/each process mmap region=2G kernel throughput vanilla 11885 auto-binding 14879 +25% [aaron.lu@intel.com: v2] Link: http://lkml.kernel.org/r/20170814053130.GD2369@aaronlu.sh.intel.com Link: http://lkml.kernel.org/r/20170816024439.GA10925@aaronlu.sh.intel.com [akpm@linux-foundation.org: use kmalloc_array()] Link: http://lkml.kernel.org/r/20170814053130.GD2369@aaronlu.sh.intel.com Link: http://lkml.kernel.org/r/20170816024439.GA10925@aaronlu.sh.intel.com Signed-off-by: Aaron Lu Cc: "Chen, Tim C" Cc: Huang Ying Cc: Andi Kleen Cc: Michal Hocko Cc: Minchan Kim Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 9c4ae6f14eea..8bf3487fb204 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -212,7 +212,7 @@ struct swap_info_struct { unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ - struct plist_node avail_list; /* entry in swap_avail_head */ + struct plist_node avail_lists[MAX_NUMNODES];/* entry in swap_avail_heads */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ -- cgit v1.2.3 From 212925802454672e6cd2949a727f5e2c1377bf06 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 6 Sep 2017 16:25:00 -0700 Subject: mm: oom: let oom_reap_task and exit_mmap run concurrently This is purely required because exit_aio() may block and exit_mmap() may never start, if the oom_reap_task cannot start running on a mm with mm_users == 0. At the same time if the OOM reaper doesn't wait at all for the memory of the current OOM candidate to be freed by exit_mmap->unmap_vmas, it would generate a spurious OOM kill. If it wasn't because of the exit_aio or similar blocking functions in the last mmput, it would be enough to change the oom_reap_task() in the case it finds mm_users == 0, to wait for a timeout or to wait for __mmput to set MMF_OOM_SKIP itself, but it's not just exit_mmap the problem here so the concurrency of exit_mmap and oom_reap_task is apparently warranted. It's a non standard runtime, exit_mmap() runs without mmap_sem, and oom_reap_task runs with the mmap_sem for reading as usual (kind of MADV_DONTNEED). The race between the two is solved with a combination of tsk_is_oom_victim() (serialized by task_lock) and MMF_OOM_SKIP (serialized by a dummy down_write/up_write cycle on the same lines of the ksm_exit method). If the oom_reap_task() may be running concurrently during exit_mmap, exit_mmap will wait it to finish in down_write (before taking down mm structures that would make the oom_reap_task fail with use after free). If exit_mmap comes first, oom_reap_task() will skip the mm if MMF_OOM_SKIP is already set and in turn all memory is already freed and furthermore the mm data structures may already have been taken down by free_pgtables. [aarcange@redhat.com: incremental one liner] Link: http://lkml.kernel.org/r/20170726164319.GC29716@redhat.com [rientjes@google.com: remove unused mmput_async] Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1708141733130.50317@chino.kir.corp.google.com [aarcange@redhat.com: microoptimization] Link: http://lkml.kernel.org/r/20170817171240.GB5066@redhat.com Link: http://lkml.kernel.org/r/20170726162912.GA29716@redhat.com Fixes: 26db62f179d1 ("oom: keep mm of the killed task available") Signed-off-by: Andrea Arcangeli Signed-off-by: David Rientjes Reported-by: David Rientjes Tested-by: David Rientjes Reviewed-by: Michal Hocko Cc: Tetsuo Handa Cc: Oleg Nesterov Cc: Hugh Dickins Cc: "Kirill A. Shutemov" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/mm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2b0a281f9d26..3a19c253bdb1 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -84,12 +84,6 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); -#ifdef CONFIG_MMU -/* same as above but performs the slow path from the async context. Can - * be called from the atomic context as well - */ -extern void mmput_async(struct mm_struct *); -#endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); -- cgit v1.2.3 From c79b57e462b5d2f47afa5f175cf1828f16e18612 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:25:04 -0700 Subject: mm: hugetlb: clear target sub-page last when clearing huge page Huge page helps to reduce TLB miss rate, but it has higher cache footprint, sometimes this may cause some issue. For example, when clearing huge page on x86_64 platform, the cache footprint is 2M. But on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M LLC (last level cache). That is, in average, there are 2.5M LLC for each core and 1.25M LLC for each thread. If the cache pressure is heavy when clearing the huge page, and we clear the huge page from the begin to the end, it is possible that the begin of huge page is evicted from the cache after we finishing clearing the end of the huge page. And it is possible for the application to access the begin of the huge page after clearing the huge page. To help the above situation, in this patch, when we clear a huge page, the order to clear sub-pages is changed. In quite some situation, we can get the address that the application will access after we clear the huge page, for example, in a page fault handler. Instead of clearing the huge page from begin to end, we will clear the sub-pages farthest from the the sub-page to access firstly, and clear the sub-page to access last. This will make the sub-page to access most cache-hot and sub-pages around it more cache-hot too. If we cannot know the address the application will access, the begin of the huge page is assumed to be the the address the application will access. With this patch, the throughput increases ~28.3% in vm-scalability anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699 system (36 cores, 72 threads). The test case creates 72 processes, each process mmap a big anonymous memory area and writes to it from the begin to the end. For each process, other processes could be seen as other workload which generates heavy cache pressure. At the same time, the cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per cycle) increased from 0.56 to 0.74, and the time spent in user space is reduced ~7.9% Christopher Lameter suggests to clear bytes inside a sub-page from end to begin too. But tests show no visible performance difference in the tests. May because the size of page is small compared with the cache size. Thanks Andi Kleen to propose to use address to access to determine the order of sub-pages to clear. The hugetlbfs access address could be improved, will do that in another patch. [ying.huang@intel.com: improve readability of clear_huge_page()] Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com Suggested-by: Andi Kleen Signed-off-by: "Huang, Ying" Acked-by: Jan Kara Reviewed-by: Michal Hocko Cc: Andrea Arcangeli Cc: "Kirill A. Shutemov" Cc: Nadia Yvette Chambers Cc: Matthew Wilcox Cc: Hugh Dickins Cc: Minchan Kim Cc: Shaohua Li Cc: Christopher Lameter Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index eb5e4bc946cc..0acea73af839 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2508,7 +2508,7 @@ enum mf_action_page_type { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, - unsigned long addr, + unsigned long addr_hint, unsigned int pages_per_huge_page); extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, -- cgit v1.2.3 From df3735c5b40fad8d0d28eb8ab065fe955b3347ee Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 6 Sep 2017 16:25:11 -0700 Subject: x86,mpx: make mpx depend on x86-64 to free up VMA flag MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "mm,fork,security: introduce MADV_WIPEONFORK", v4. If a child process accesses memory that was MADV_WIPEONFORK, it will get zeroes. The address ranges are still valid, they are just empty. If a child process accesses memory that was MADV_DONTFORK, it will get a segmentation fault, since those address ranges are no longer valid in the child after fork. Since MADV_DONTFORK also seems to be used to allow very large programs to fork in systems with strict memory overcommit restrictions, changing the semantics of MADV_DONTFORK might break existing programs. The use case is libraries that store or cache information, and want to know that they need to regenerate it in the child process after fork. Examples of this would be: - systemd/pulseaudio API checks (fail after fork) (replacing a getpid check, which is too slow without a PID cache) - PKCS#11 API reinitialization check (mandated by specification) - glibc's upcoming PRNG (reseed after fork) - OpenSSL PRNG (reseed after fork) The security benefits of a forking server having a re-inialized PRNG in every child process are pretty obvious. However, due to libraries having all kinds of internal state, and programs getting compiled with many different versions of each library, it is unreasonable to expect calling programs to re-initialize everything manually after fork. A further complication is the proliferation of clone flags, programs bypassing glibc's functions to call clone directly, and programs calling unshare, causing the glibc pthread_atfork hook to not get called. It would be better to have the kernel take care of this automatically. The patchset also adds MADV_KEEPONFORK, to undo the effects of a prior MADV_WIPEONFORK. This is similar to the OpenBSD minherit syscall with MAP_INHERIT_ZERO: https://man.openbsd.org/minherit.2 This patch (of 2): MPX only seems to be available on 64 bit CPUs, starting with Skylake and Goldmont. Move VM_MPX into the 64 bit only portion of vma->vm_flags, in order to free up a VMA flag. Link: http://lkml.kernel.org/r/20170811212829.29186-2-riel@redhat.com Signed-off-by: Rik van Riel Acked-by: Dave Hansen Cc: Mike Kravetz Cc: Florian Weimer Cc: Kees Cook Cc: Andy Lutomirski Cc: Will Drewry Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: "Kirill A. Shutemov" Cc: Matthew Wilcox Cc: Colm MacCártaigh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0acea73af839..9efe62032094 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -208,10 +208,12 @@ extern unsigned int kobjsize(const void *objp); #define VM_HIGH_ARCH_BIT_1 33 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_2 34 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */ +#define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */ #define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0) #define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1) #define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2) #define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3) +#define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4) #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */ #if defined(CONFIG_X86) @@ -235,9 +237,11 @@ extern unsigned int kobjsize(const void *objp); # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif -#if defined(CONFIG_X86) +#if defined(CONFIG_X86_INTEL_MPX) /* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_ARCH_2 +# define VM_MPX VM_HIGH_ARCH_BIT_4 +#else +# define VM_MPX VM_NONE #endif #ifndef VM_GROWSUP -- cgit v1.2.3 From d2cd9ede6e193dd7d88b6d27399e96229a551b19 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 6 Sep 2017 16:25:15 -0700 Subject: mm,fork: introduce MADV_WIPEONFORK MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce MADV_WIPEONFORK semantics, which result in a VMA being empty in the child process after fork. This differs from MADV_DONTFORK in one important way. If a child process accesses memory that was MADV_WIPEONFORK, it will get zeroes. The address ranges are still valid, they are just empty. If a child process accesses memory that was MADV_DONTFORK, it will get a segmentation fault, since those address ranges are no longer valid in the child after fork. Since MADV_DONTFORK also seems to be used to allow very large programs to fork in systems with strict memory overcommit restrictions, changing the semantics of MADV_DONTFORK might break existing programs. MADV_WIPEONFORK only works on private, anonymous VMAs. The use case is libraries that store or cache information, and want to know that they need to regenerate it in the child process after fork. Examples of this would be: - systemd/pulseaudio API checks (fail after fork) (replacing a getpid check, which is too slow without a PID cache) - PKCS#11 API reinitialization check (mandated by specification) - glibc's upcoming PRNG (reseed after fork) - OpenSSL PRNG (reseed after fork) The security benefits of a forking server having a re-inialized PRNG in every child process are pretty obvious. However, due to libraries having all kinds of internal state, and programs getting compiled with many different versions of each library, it is unreasonable to expect calling programs to re-initialize everything manually after fork. A further complication is the proliferation of clone flags, programs bypassing glibc's functions to call clone directly, and programs calling unshare, causing the glibc pthread_atfork hook to not get called. It would be better to have the kernel take care of this automatically. The patch also adds MADV_KEEPONFORK, to undo the effects of a prior MADV_WIPEONFORK. This is similar to the OpenBSD minherit syscall with MAP_INHERIT_ZERO: https://man.openbsd.org/minherit.2 [akpm@linux-foundation.org: numerically order arch/parisc/include/uapi/asm/mman.h #defines] Link: http://lkml.kernel.org/r/20170811212829.29186-3-riel@redhat.com Signed-off-by: Rik van Riel Reported-by: Florian Weimer Reported-by: Colm MacCártaigh Reviewed-by: Mike Kravetz Cc: "H. Peter Anvin" Cc: "Kirill A. Shutemov" Cc: Andy Lutomirski Cc: Dave Hansen Cc: Ingo Molnar Cc: Helge Deller Cc: Kees Cook Cc: Matthew Wilcox Cc: Thomas Gleixner Cc: Will Drewry Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9efe62032094..39db8e54c5d5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -189,7 +189,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ -#define VM_ARCH_2 0x02000000 +#define VM_WIPEONFORK 0x02000000 /* Wipe VMA contents in child. */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #ifdef CONFIG_MEM_SOFT_DIRTY -- cgit v1.2.3 From 50e76632339d4655859523a39249dd95ee5e93e7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Sep 2017 11:13:38 +0200 Subject: sched/cpuset/pm: Fix cpuset vs. suspend-resume bugs Cpusets vs. suspend-resume is _completely_ broken. And it got noticed because it now resulted in non-cpuset usage breaking too. On suspend cpuset_cpu_inactive() doesn't call into cpuset_update_active_cpus() because it doesn't want to move tasks about, there is no need, all tasks are frozen and won't run again until after we've resumed everything. But this means that when we finally do call into cpuset_update_active_cpus() after resuming the last frozen cpu in cpuset_cpu_active(), the top_cpuset will not have any difference with the cpu_active_mask and this it will not in fact do _anything_. So the cpuset configuration will not be restored. This was largely hidden because we would unconditionally create identity domains and mobile users would not in fact use cpusets much. And servers what do use cpusets tend to not suspend-resume much. An addition problem is that we'd not in fact wait for the cpuset work to finish before resuming the tasks, allowing spurious migrations outside of the specified domains. Fix the rebuild by introducing cpuset_force_rebuild() and fix the ordering with cpuset_wait_for_hotplug(). Reported-by: Andy Lutomirski Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Tejun Heo Cc: Thomas Gleixner Fixes: deb7aa308ea2 ("cpuset: reorganize CPU / memory hotplug handling") Link: http://lkml.kernel.org/r/20170907091338.orwxrqkbfkki3c24@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/cpuset.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index e74655d941b7..a1e6a33a4b03 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -51,7 +51,9 @@ static inline void cpuset_dec(void) extern int cpuset_init(void); extern void cpuset_init_smp(void); +extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); +extern void cpuset_wait_for_hotplug(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern void cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -164,11 +166,15 @@ static inline bool cpusets_enabled(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} +static inline void cpuset_force_rebuild(void) { } + static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } +static inline void cpuset_wait_for_hotplug(void) { } + static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { -- cgit v1.2.3 From 21d9bb4a05bac50fb4f850517af4030baecd00f6 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Thu, 7 Sep 2017 11:38:37 +0200 Subject: x86/mm: Make the SME mask a u64 The SME encryption mask is for masking 64-bit pagetable entries. It being an unsigned long works fine on X86_64 but on 32-bit builds in truncates bits leading to Xen guests crashing very early. And regardless, the whole SME mask handling shouldnt've leaked into 32-bit because SME is X86_64-only feature. So, first make the mask u64. And then, add trivial 32-bit versions of the __sme_* macros so that nothing happens there. Reported-and-tested-by: Boris Ostrovsky Tested-by: Brijesh Singh Signed-off-by: Borislav Petkov Acked-by: Tom Lendacky Acked-by: Thomas Gleixner Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Fixes: 21729f81ce8a ("x86/mm: Provide general kernel support for memory encryption") Link: http://lkml.kernel.org/r/20170907093837.76zojtkgebwtqc74@pd.tnic Signed-off-by: Ingo Molnar --- include/linux/mem_encrypt.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h index 1255f09f5e42..265a9cd21cb4 100644 --- a/include/linux/mem_encrypt.h +++ b/include/linux/mem_encrypt.h @@ -21,7 +21,7 @@ #else /* !CONFIG_ARCH_HAS_MEM_ENCRYPT */ -#define sme_me_mask 0UL +#define sme_me_mask 0ULL #endif /* CONFIG_ARCH_HAS_MEM_ENCRYPT */ @@ -30,18 +30,23 @@ static inline bool sme_active(void) return !!sme_me_mask; } -static inline unsigned long sme_get_me_mask(void) +static inline u64 sme_get_me_mask(void) { return sme_me_mask; } +#ifdef CONFIG_AMD_MEM_ENCRYPT /* * The __sme_set() and __sme_clr() macros are useful for adding or removing * the encryption mask from a value (e.g. when dealing with pagetable * entries). */ -#define __sme_set(x) ((unsigned long)(x) | sme_me_mask) -#define __sme_clr(x) ((unsigned long)(x) & ~sme_me_mask) +#define __sme_set(x) ((x) | sme_me_mask) +#define __sme_clr(x) ((x) & ~sme_me_mask) +#else +#define __sme_set(x) (x) +#define __sme_clr(x) (x) +#endif #endif /* __ASSEMBLY__ */ -- cgit v1.2.3 From ca2c1418efe9f7fe37aa1f355efdf4eb293673ce Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 6 Sep 2017 14:44:36 +0200 Subject: udp: drop head states only when all skb references are gone After commit 0ddf3fb2c43d ("udp: preserve skb->dst if required for IP options processing") we clear the skb head state as soon as the skb carrying them is first processed. Since the same skb can be processed several times when MSG_PEEK is used, we can end up lacking the required head states, and eventually oopsing. Fix this clearing the skb head state only when processing the last skb reference. Reported-by: Eric Dumazet Fixes: 0ddf3fb2c43d ("udp: preserve skb->dst if required for IP options processing") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f751f3b93039..72299ef00061 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -958,7 +958,7 @@ void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_tx_error(struct sk_buff *skb); void consume_skb(struct sk_buff *skb); -void consume_stateless_skb(struct sk_buff *skb); +void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); extern struct kmem_cache *skbuff_head_cache; -- cgit v1.2.3 From b5ff8161e37cef3265e186ecded23324e4dc2973 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 8 Sep 2017 16:10:49 -0700 Subject: mm: thp: introduce separate TTU flag for thp freezing TTU_MIGRATION is used to convert pte into migration entry until thp split completes. This behavior conflicts with thp migration added later patches, so let's introduce a new TTU flag specifically for freezing. try_to_unmap() is used both for thp split (via freeze_page()) and page migration (via __unmap_and_move()). In freeze_page(), ttu_flag given for head page is like below (assuming anonymous thp): (TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED | \ TTU_MIGRATION | TTU_SPLIT_HUGE_PMD) and ttu_flag given for tail pages is: (TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED | \ TTU_MIGRATION) __unmap_and_move() calls try_to_unmap() with ttu_flag: (TTU_MIGRATION | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS) Now I'm trying to insert a branch for thp migration at the top of try_to_unmap_one() like below static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long address, void *arg) { ... /* PMD-mapped THP migration entry */ if (!pvmw.pte && (flags & TTU_MIGRATION)) { if (!PageAnon(page)) continue; set_pmd_migration_entry(&pvmw, page); continue; } ... } so try_to_unmap() for tail pages called by thp split can go into thp migration code path (which converts *pmd* into migration entry), while the expectation is to freeze thp (which converts *pte* into migration entry.) I detected this failure as a "bad page state" error in a testcase where split_huge_page() is called from queue_pages_pte_range(). Link: http://lkml.kernel.org/r/20170717193955.20207-4-zi.yan@sent.com Signed-off-by: Naoya Horiguchi Signed-off-by: Zi Yan Acked-by: Kirill A. Shutemov Cc: "H. Peter Anvin" Cc: Anshuman Khandual Cc: Dave Hansen Cc: David Nellans Cc: Ingo Molnar Cc: Mel Gorman Cc: Minchan Kim Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rmap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 43ef2c30cb0f..f8ca2e74b819 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -93,8 +93,9 @@ enum ttu_flags { TTU_BATCH_FLUSH = 0x40, /* Batch TLB flushes where possible * and caller guarantees they will * do a final flush if necessary */ - TTU_RMAP_LOCKED = 0x80 /* do not grab rmap lock: + TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ + TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ }; #ifdef CONFIG_MMU -- cgit v1.2.3 From 9c670ea37947a82cb6d4df69139f7e46ed71a0ac Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 8 Sep 2017 16:10:53 -0700 Subject: mm: thp: introduce CONFIG_ARCH_ENABLE_THP_MIGRATION Introduce CONFIG_ARCH_ENABLE_THP_MIGRATION to limit thp migration functionality to x86_64, which should be safer at the first step. Link: http://lkml.kernel.org/r/20170717193955.20207-5-zi.yan@sent.com Signed-off-by: Naoya Horiguchi Signed-off-by: Zi Yan Reviewed-by: Anshuman Khandual Cc: "H. Peter Anvin" Cc: Dave Hansen Cc: David Nellans Cc: Ingo Molnar Cc: Kirill A. Shutemov Cc: Mel Gorman Cc: Minchan Kim Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ee696347f928..d8f35a0865dc 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -233,6 +233,11 @@ void mm_put_huge_zero_page(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) +static inline bool thp_migration_supported(void) +{ + return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); +} + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) @@ -336,6 +341,11 @@ static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, { return NULL; } + +static inline bool thp_migration_supported(void) +{ + return false; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ -- cgit v1.2.3 From 616b8371539a6c487404c3b8fb04078016dab4ba Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Fri, 8 Sep 2017 16:10:57 -0700 Subject: mm: thp: enable thp migration in generic path Add thp migration's core code, including conversions between a PMD entry and a swap entry, setting PMD migration entry, removing PMD migration entry, and waiting on PMD migration entries. This patch makes it possible to support thp migration. If you fail to allocate a destination page as a thp, you just split the source thp as we do now, and then enter the normal page migration. If you succeed to allocate destination thp, you enter thp migration. Subsequent patches actually enable thp migration for each caller of page migration by allowing its get_new_page() callback to allocate thps. [zi.yan@cs.rutgers.edu: fix gcc-4.9.0 -Wmissing-braces warning] Link: http://lkml.kernel.org/r/A0ABA698-7486-46C3-B209-E95A9048B22C@cs.rutgers.edu [akpm@linux-foundation.org: fix x86_64 allnoconfig warning] Signed-off-by: Zi Yan Acked-by: Kirill A. Shutemov Cc: "H. Peter Anvin" Cc: Anshuman Khandual Cc: Dave Hansen Cc: David Nellans Cc: Ingo Molnar Cc: Mel Gorman Cc: Minchan Kim Cc: Naoya Horiguchi Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 73 +++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 70 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index c5ff7b217ee6..82089fd88c29 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -103,7 +103,8 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) #ifdef CONFIG_MIGRATION static inline swp_entry_t make_migration_entry(struct page *page, int write) { - BUG_ON(!PageLocked(page)); + BUG_ON(!PageLocked(compound_head(page))); + return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ, page_to_pfn(page)); } @@ -126,7 +127,7 @@ static inline struct page *migration_entry_to_page(swp_entry_t entry) * Any use of migration entries may only occur while the * corresponding page is locked */ - BUG_ON(!PageLocked(p)); + BUG_ON(!PageLocked(compound_head(p))); return p; } @@ -148,7 +149,11 @@ static inline int is_migration_entry(swp_entry_t swp) { return 0; } -#define migration_entry_to_page(swp) NULL +static inline struct page *migration_entry_to_page(swp_entry_t entry) +{ + return NULL; +} + static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } @@ -163,6 +168,68 @@ static inline int is_write_migration_entry(swp_entry_t entry) #endif +struct page_vma_mapped_walk; + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, + struct page *page); + +extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, + struct page *new); + +extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd); + +static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) +{ + swp_entry_t arch_entry; + + arch_entry = __pmd_to_swp_entry(pmd); + return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); +} + +static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) +{ + swp_entry_t arch_entry; + + arch_entry = __swp_entry(swp_type(entry), swp_offset(entry)); + return __swp_entry_to_pmd(arch_entry); +} + +static inline int is_pmd_migration_entry(pmd_t pmd) +{ + return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); +} +#else +static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, + struct page *page) +{ + BUILD_BUG(); +} + +static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, + struct page *new) +{ + BUILD_BUG(); +} + +static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { } + +static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) +{ + return swp_entry(0, 0); +} + +static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) +{ + return __pmd(0); +} + +static inline int is_pmd_migration_entry(pmd_t pmd) +{ + return 0; +} +#endif + #ifdef CONFIG_MEMORY_FAILURE extern atomic_long_t num_poisoned_pages __read_mostly; -- cgit v1.2.3 From 84c3fc4e9c563d8fb91cfdf5948da48fe1af34d3 Mon Sep 17 00:00:00 2001 From: Zi Yan Date: Fri, 8 Sep 2017 16:11:01 -0700 Subject: mm: thp: check pmd migration entry in common path When THP migration is being used, memory management code needs to handle pmd migration entries properly. This patch uses !pmd_present() or is_swap_pmd() (depending on whether pmd_none() needs separate code or not) to check pmd migration entries at the places where a pmd entry is present. Since pmd-related code uses split_huge_page(), split_huge_pmd(), pmd_trans_huge(), pmd_trans_unstable(), or pmd_none_or_trans_huge_or_clear_bad(), this patch: 1. adds pmd migration entry split code in split_huge_pmd(), 2. takes care of pmd migration entries whenever pmd_trans_huge() is present, 3. makes pmd_none_or_trans_huge_or_clear_bad() pmd migration entry aware. Since split_huge_page() uses split_huge_pmd() and pmd_trans_unstable() is equivalent to pmd_none_or_trans_huge_or_clear_bad(), we do not change them. Until this commit, a pmd entry should be: 1. pointing to a pte page, 2. is_swap_pmd(), 3. pmd_trans_huge(), 4. pmd_devmap(), or 5. pmd_none(). Signed-off-by: Zi Yan Cc: Kirill A. Shutemov Cc: "H. Peter Anvin" Cc: Anshuman Khandual Cc: Dave Hansen Cc: David Nellans Cc: Ingo Molnar Cc: Mel Gorman Cc: Minchan Kim Cc: Naoya Horiguchi Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index d8f35a0865dc..14bc21c2ee7f 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -147,7 +147,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ - if (pmd_trans_huge(*____pmd) \ + if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ false, NULL); \ @@ -178,12 +178,18 @@ extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); extern spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); + +static inline int is_swap_pmd(pmd_t pmd) +{ + return !pmd_none(pmd) && !pmd_present(pmd); +} + /* mmap_sem must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); - if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) + if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else return NULL; @@ -299,6 +305,10 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, long adjust_next) { } +static inline int is_swap_pmd(pmd_t pmd) +{ + return 0; +} static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { -- cgit v1.2.3 From ab6e3d0939bb332d72444a532f0f72e0dfde7b7b Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 8 Sep 2017 16:11:04 -0700 Subject: mm: soft-dirty: keep soft-dirty bits over thp migration Soft dirty bit is designed to keep tracked over page migration. This patch makes it work in the same manner for thp migration too. Signed-off-by: Naoya Horiguchi Signed-off-by: Zi Yan Cc: "H. Peter Anvin" Cc: Anshuman Khandual Cc: Dave Hansen Cc: David Nellans Cc: Ingo Molnar Cc: Kirill A. Shutemov Cc: Mel Gorman Cc: Minchan Kim Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 82089fd88c29..45b092aa6419 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -183,6 +183,8 @@ static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) { swp_entry_t arch_entry; + if (pmd_swp_soft_dirty(pmd)) + pmd = pmd_swp_clear_soft_dirty(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } -- cgit v1.2.3 From 8135d8926c08e553e39b0b040c6d01f0daef0676 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 8 Sep 2017 16:11:15 -0700 Subject: mm: memory_hotplug: memory hotremove supports thp migration This patch enables thp migration for memory hotremove. Link: http://lkml.kernel.org/r/20170717193955.20207-11-zi.yan@sent.com Signed-off-by: Naoya Horiguchi Signed-off-by: Zi Yan Cc: "H. Peter Anvin" Cc: Anshuman Khandual Cc: Dave Hansen Cc: David Nellans Cc: Ingo Molnar Cc: Kirill A. Shutemov Cc: Mel Gorman Cc: Minchan Kim Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3e0d405dc842..ce15989521a1 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -35,15 +35,28 @@ static inline struct page *new_page_nodemask(struct page *page, int preferred_nid, nodemask_t *nodemask) { gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; + unsigned int order = 0; + struct page *new_page = NULL; if (PageHuge(page)) return alloc_huge_page_nodemask(page_hstate(compound_head(page)), preferred_nid, nodemask); + if (thp_migration_supported() && PageTransHuge(page)) { + order = HPAGE_PMD_ORDER; + gfp_mask |= GFP_TRANSHUGE; + } + if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) gfp_mask |= __GFP_HIGHMEM; - return __alloc_pages_nodemask(gfp_mask, 0, preferred_nid, nodemask); + new_page = __alloc_pages_nodemask(gfp_mask, order, + preferred_nid, nodemask); + + if (new_page && PageTransHuge(page)) + prep_transhuge_page(new_page); + + return new_page; } #ifdef CONFIG_MIGRATION -- cgit v1.2.3 From 133ff0eac95b7dc6edf89dc51bd139a0630bbae7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:11:23 -0700 Subject: mm/hmm: heterogeneous memory management (HMM for short) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit HMM provides 3 separate types of functionality: - Mirroring: synchronize CPU page table and device page table - Device memory: allocating struct page for device memory - Migration: migrating regular memory to device memory This patch introduces some common helpers and definitions to all of those 3 functionality. Link: http://lkml.kernel.org/r/20170817000548.32038-3-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Evgeny Baskakov Signed-off-by: John Hubbard Signed-off-by: Mark Hairgrove Signed-off-by: Sherry Cheung Signed-off-by: Subhash Gutti Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 152 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 6 ++ 2 files changed, 158 insertions(+) create mode 100644 include/linux/hmm.h (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h new file mode 100644 index 000000000000..5d83fec6dfdd --- /dev/null +++ b/include/linux/hmm.h @@ -0,0 +1,152 @@ +/* + * Copyright 2013 Red Hat Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Authors: Jérôme Glisse + */ +/* + * Heterogeneous Memory Management (HMM) + * + * See Documentation/vm/hmm.txt for reasons and overview of what HMM is and it + * is for. Here we focus on the HMM API description, with some explanation of + * the underlying implementation. + * + * Short description: HMM provides a set of helpers to share a virtual address + * space between CPU and a device, so that the device can access any valid + * address of the process (while still obeying memory protection). HMM also + * provides helpers to migrate process memory to device memory, and back. Each + * set of functionality (address space mirroring, and migration to and from + * device memory) can be used independently of the other. + * + * + * HMM address space mirroring API: + * + * Use HMM address space mirroring if you want to mirror range of the CPU page + * table of a process into a device page table. Here, "mirror" means "keep + * synchronized". Prerequisites: the device must provide the ability to write- + * protect its page tables (at PAGE_SIZE granularity), and must be able to + * recover from the resulting potential page faults. + * + * HMM guarantees that at any point in time, a given virtual address points to + * either the same memory in both CPU and device page tables (that is: CPU and + * device page tables each point to the same pages), or that one page table (CPU + * or device) points to no entry, while the other still points to the old page + * for the address. The latter case happens when the CPU page table update + * happens first, and then the update is mirrored over to the device page table. + * This does not cause any issue, because the CPU page table cannot start + * pointing to a new page until the device page table is invalidated. + * + * HMM uses mmu_notifiers to monitor the CPU page tables, and forwards any + * updates to each device driver that has registered a mirror. It also provides + * some API calls to help with taking a snapshot of the CPU page table, and to + * synchronize with any updates that might happen concurrently. + * + * + * HMM migration to and from device memory: + * + * HMM provides a set of helpers to hotplug device memory as ZONE_DEVICE, with + * a new MEMORY_DEVICE_PRIVATE type. This provides a struct page for each page + * of the device memory, and allows the device driver to manage its memory + * using those struct pages. Having struct pages for device memory makes + * migration easier. Because that memory is not addressable by the CPU it must + * never be pinned to the device; in other words, any CPU page fault can always + * cause the device memory to be migrated (copied/moved) back to regular memory. + * + * A new migrate helper (migrate_vma()) has been added (see mm/migrate.c) that + * allows use of a device DMA engine to perform the copy operation between + * regular system memory and device memory. + */ +#ifndef LINUX_HMM_H +#define LINUX_HMM_H + +#include + +#if IS_ENABLED(CONFIG_HMM) + + +/* + * hmm_pfn_t - HMM uses its own pfn type to keep several flags per page + * + * Flags: + * HMM_PFN_VALID: pfn is valid + * HMM_PFN_WRITE: CPU page table has write permission set + */ +typedef unsigned long hmm_pfn_t; + +#define HMM_PFN_VALID (1 << 0) +#define HMM_PFN_WRITE (1 << 1) +#define HMM_PFN_SHIFT 2 + +/* + * hmm_pfn_t_to_page() - return struct page pointed to by a valid hmm_pfn_t + * @pfn: hmm_pfn_t to convert to struct page + * Returns: struct page pointer if pfn is a valid hmm_pfn_t, NULL otherwise + * + * If the hmm_pfn_t is valid (ie valid flag set) then return the struct page + * matching the pfn value stored in the hmm_pfn_t. Otherwise return NULL. + */ +static inline struct page *hmm_pfn_t_to_page(hmm_pfn_t pfn) +{ + if (!(pfn & HMM_PFN_VALID)) + return NULL; + return pfn_to_page(pfn >> HMM_PFN_SHIFT); +} + +/* + * hmm_pfn_t_to_pfn() - return pfn value store in a hmm_pfn_t + * @pfn: hmm_pfn_t to extract pfn from + * Returns: pfn value if hmm_pfn_t is valid, -1UL otherwise + */ +static inline unsigned long hmm_pfn_t_to_pfn(hmm_pfn_t pfn) +{ + if (!(pfn & HMM_PFN_VALID)) + return -1UL; + return (pfn >> HMM_PFN_SHIFT); +} + +/* + * hmm_pfn_t_from_page() - create a valid hmm_pfn_t value from struct page + * @page: struct page pointer for which to create the hmm_pfn_t + * Returns: valid hmm_pfn_t for the page + */ +static inline hmm_pfn_t hmm_pfn_t_from_page(struct page *page) +{ + return (page_to_pfn(page) << HMM_PFN_SHIFT) | HMM_PFN_VALID; +} + +/* + * hmm_pfn_t_from_pfn() - create a valid hmm_pfn_t value from pfn + * @pfn: pfn value for which to create the hmm_pfn_t + * Returns: valid hmm_pfn_t for the pfn + */ +static inline hmm_pfn_t hmm_pfn_t_from_pfn(unsigned long pfn) +{ + return (pfn << HMM_PFN_SHIFT) | HMM_PFN_VALID; +} + + +/* Below are for HMM internal use only! Not to be used by device driver! */ +void hmm_mm_destroy(struct mm_struct *mm); + +static inline void hmm_mm_init(struct mm_struct *mm) +{ + mm->hmm = NULL; +} + +#else /* IS_ENABLED(CONFIG_HMM) */ + +/* Below are for HMM internal use only! Not to be used by device driver! */ +static inline void hmm_mm_destroy(struct mm_struct *mm) {} +static inline void hmm_mm_init(struct mm_struct *mm) {} + +#endif /* IS_ENABLED(CONFIG_HMM) */ +#endif /* LINUX_HMM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index f45ad815b7d7..46f4ecf5479a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -23,6 +23,7 @@ struct address_space; struct mem_cgroup; +struct hmm; /* * Each physical page in the system has a struct page associated with @@ -503,6 +504,11 @@ struct mm_struct { atomic_long_t hugetlb_usage; #endif struct work_struct async_put_work; + +#if IS_ENABLED(CONFIG_HMM) + /* HMM needs to track a few things per mm */ + struct hmm *hmm; +#endif } __randomize_layout; extern struct mm_struct init_mm; -- cgit v1.2.3 From c0b124054f9e42eb6da545a10fe9122a7d7c3f72 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:11:27 -0700 Subject: mm/hmm/mirror: mirror process address space on device with HMM helpers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Evgeny Baskakov Signed-off-by: John Hubbard Signed-off-by: Mark Hairgrove Signed-off-by: Sherry Cheung Signed-off-by: Subhash Gutti Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 110 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 110 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 5d83fec6dfdd..76310726ee9c 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -72,6 +72,7 @@ #if IS_ENABLED(CONFIG_HMM) +struct hmm; /* * hmm_pfn_t - HMM uses its own pfn type to keep several flags per page @@ -134,6 +135,115 @@ static inline hmm_pfn_t hmm_pfn_t_from_pfn(unsigned long pfn) } +#if IS_ENABLED(CONFIG_HMM_MIRROR) +/* + * Mirroring: how to synchronize device page table with CPU page table. + * + * A device driver that is participating in HMM mirroring must always + * synchronize with CPU page table updates. For this, device drivers can either + * directly use mmu_notifier APIs or they can use the hmm_mirror API. Device + * drivers can decide to register one mirror per device per process, or just + * one mirror per process for a group of devices. The pattern is: + * + * int device_bind_address_space(..., struct mm_struct *mm, ...) + * { + * struct device_address_space *das; + * + * // Device driver specific initialization, and allocation of das + * // which contains an hmm_mirror struct as one of its fields. + * ... + * + * ret = hmm_mirror_register(&das->mirror, mm, &device_mirror_ops); + * if (ret) { + * // Cleanup on error + * return ret; + * } + * + * // Other device driver specific initialization + * ... + * } + * + * Once an hmm_mirror is registered for an address space, the device driver + * will get callbacks through sync_cpu_device_pagetables() operation (see + * hmm_mirror_ops struct). + * + * Device driver must not free the struct containing the hmm_mirror struct + * before calling hmm_mirror_unregister(). The expected usage is to do that when + * the device driver is unbinding from an address space. + * + * + * void device_unbind_address_space(struct device_address_space *das) + * { + * // Device driver specific cleanup + * ... + * + * hmm_mirror_unregister(&das->mirror); + * + * // Other device driver specific cleanup, and now das can be freed + * ... + * } + */ + +struct hmm_mirror; + +/* + * enum hmm_update_type - type of update + * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why) + */ +enum hmm_update_type { + HMM_UPDATE_INVALIDATE, +}; + +/* + * struct hmm_mirror_ops - HMM mirror device operations callback + * + * @update: callback to update range on a device + */ +struct hmm_mirror_ops { + /* sync_cpu_device_pagetables() - synchronize page tables + * + * @mirror: pointer to struct hmm_mirror + * @update_type: type of update that occurred to the CPU page table + * @start: virtual start address of the range to update + * @end: virtual end address of the range to update + * + * This callback ultimately originates from mmu_notifiers when the CPU + * page table is updated. The device driver must update its page table + * in response to this callback. The update argument tells what action + * to perform. + * + * The device driver must not return from this callback until the device + * page tables are completely updated (TLBs flushed, etc); this is a + * synchronous call. + */ + void (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, + enum hmm_update_type update_type, + unsigned long start, + unsigned long end); +}; + +/* + * struct hmm_mirror - mirror struct for a device driver + * + * @hmm: pointer to struct hmm (which is unique per mm_struct) + * @ops: device driver callback for HMM mirror operations + * @list: for list of mirrors of a given mm + * + * Each address space (mm_struct) being mirrored by a device must register one + * instance of an hmm_mirror struct with HMM. HMM will track the list of all + * mirrors for each mm_struct. + */ +struct hmm_mirror { + struct hmm *hmm; + const struct hmm_mirror_ops *ops; + struct list_head list; +}; + +int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm); +void hmm_mirror_unregister(struct hmm_mirror *mirror); +#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ + + /* Below are for HMM internal use only! Not to be used by device driver! */ void hmm_mm_destroy(struct mm_struct *mm); -- cgit v1.2.3 From da4c3c735ea4dcc2a0b0ff0bd4803c336361b6f5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:11:31 -0700 Subject: mm/hmm/mirror: helper to snapshot CPU page table MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This does not use existing page table walker because we want to share same code for our page fault handler. Link: http://lkml.kernel.org/r/20170817000548.32038-5-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Evgeny Baskakov Signed-off-by: John Hubbard Signed-off-by: Mark Hairgrove Signed-off-by: Sherry Cheung Signed-off-by: Subhash Gutti Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 53 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 76310726ee9c..62899c9829c9 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -79,13 +79,26 @@ struct hmm; * * Flags: * HMM_PFN_VALID: pfn is valid + * HMM_PFN_READ: CPU page table has read permission set * HMM_PFN_WRITE: CPU page table has write permission set + * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory + * HMM_PFN_EMPTY: corresponding CPU page table entry is pte_none() + * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the + * result of vm_insert_pfn() or vm_insert_page(). Therefore, it should not + * be mirrored by a device, because the entry will never have HMM_PFN_VALID + * set and the pfn value is undefined. + * HMM_PFN_DEVICE_UNADDRESSABLE: unaddressable device memory (ZONE_DEVICE) */ typedef unsigned long hmm_pfn_t; #define HMM_PFN_VALID (1 << 0) -#define HMM_PFN_WRITE (1 << 1) -#define HMM_PFN_SHIFT 2 +#define HMM_PFN_READ (1 << 1) +#define HMM_PFN_WRITE (1 << 2) +#define HMM_PFN_ERROR (1 << 3) +#define HMM_PFN_EMPTY (1 << 4) +#define HMM_PFN_SPECIAL (1 << 5) +#define HMM_PFN_DEVICE_UNADDRESSABLE (1 << 6) +#define HMM_PFN_SHIFT 7 /* * hmm_pfn_t_to_page() - return struct page pointed to by a valid hmm_pfn_t @@ -241,6 +254,44 @@ struct hmm_mirror { int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm); void hmm_mirror_unregister(struct hmm_mirror *mirror); + + +/* + * struct hmm_range - track invalidation lock on virtual address range + * + * @list: all range lock are on a list + * @start: range virtual start address (inclusive) + * @end: range virtual end address (exclusive) + * @pfns: array of pfns (big enough for the range) + * @valid: pfns array did not change since it has been fill by an HMM function + */ +struct hmm_range { + struct list_head list; + unsigned long start; + unsigned long end; + hmm_pfn_t *pfns; + bool valid; +}; + +/* + * To snapshot the CPU page table, call hmm_vma_get_pfns(), then take a device + * driver lock that serializes device page table updates, then call + * hmm_vma_range_done(), to check if the snapshot is still valid. The same + * device driver page table update lock must also be used in the + * hmm_mirror_ops.sync_cpu_device_pagetables() callback, so that CPU page + * table invalidation serializes on it. + * + * YOU MUST CALL hmm_vma_range_done() ONCE AND ONLY ONCE EACH TIME YOU CALL + * hmm_vma_get_pfns() WITHOUT ERROR ! + * + * IF YOU DO NOT FOLLOW THE ABOVE RULE THE SNAPSHOT CONTENT MIGHT BE INVALID ! + */ +int hmm_vma_get_pfns(struct vm_area_struct *vma, + struct hmm_range *range, + unsigned long start, + unsigned long end, + hmm_pfn_t *pfns); +bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range); #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -- cgit v1.2.3 From 74eee180b935fcb9b83a56dd7648fb75caf38f0e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:11:35 -0700 Subject: mm/hmm/mirror: device page fault handler MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This handles page fault on behalf of device driver, unlike handle_mm_fault() it does not trigger migration back to system memory for device memory. Link: http://lkml.kernel.org/r/20170817000548.32038-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Evgeny Baskakov Signed-off-by: John Hubbard Signed-off-by: Mark Hairgrove Signed-off-by: Sherry Cheung Signed-off-by: Subhash Gutti Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 62899c9829c9..61a6535fe438 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -292,6 +292,33 @@ int hmm_vma_get_pfns(struct vm_area_struct *vma, unsigned long end, hmm_pfn_t *pfns); bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range); + + +/* + * Fault memory on behalf of device driver. Unlike handle_mm_fault(), this will + * not migrate any device memory back to system memory. The hmm_pfn_t array will + * be updated with the fault result and current snapshot of the CPU page table + * for the range. + * + * The mmap_sem must be taken in read mode before entering and it might be + * dropped by the function if the block argument is false. In that case, the + * function returns -EAGAIN. + * + * Return value does not reflect if the fault was successful for every single + * address or not. Therefore, the caller must to inspect the hmm_pfn_t array to + * determine fault status for each address. + * + * Trying to fault inside an invalid vma will result in -EINVAL. + * + * See the function description in mm/hmm.c for further documentation. + */ +int hmm_vma_fault(struct vm_area_struct *vma, + struct hmm_range *range, + unsigned long start, + unsigned long end, + hmm_pfn_t *pfns, + bool write, + bool block); #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -- cgit v1.2.3 From 3072e413e305e353cd4654f8a57d953b66e85bf3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 8 Sep 2017 16:11:39 -0700 Subject: mm/memory_hotplug: introduce add_pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are new users of memory hotplug emerging. Some of them require different subset of arch_add_memory. There are some which only require allocation of struct pages without mapping those pages to the kernel address space. We currently have __add_pages for that purpose. But this is rather lowlevel and not very suitable for the code outside of the memory hotplug. E.g. x86_64 wants to update max_pfn which should be done by the caller. Introduce add_pages() which should care about those details if they are needed. Each architecture should define its implementation and select CONFIG_ARCH_HAS_ADD_PAGES. All others use the currently existing __add_pages. Link: http://lkml.kernel.org/r/20170817000548.32038-7-jglisse@redhat.com Signed-off-by: Michal Hocko Signed-off-by: Jérôme Glisse Acked-by: Balbir Singh Cc: Aneesh Kumar Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Evgeny Baskakov Cc: Johannes Weiner Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Mark Hairgrove Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Sherry Cheung Cc: Subhash Gutti Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 5e6e4cc36ff4..0995e1a2b458 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -133,6 +133,17 @@ extern int __remove_pages(struct zone *zone, unsigned long start_pfn, extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, bool want_memblock); +#ifndef CONFIG_ARCH_HAS_ADD_PAGES +static inline int add_pages(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool want_memblock) +{ + return __add_pages(nid, start_pfn, nr_pages, want_memblock); +} +#else /* ARCH_HAS_ADD_PAGES */ +int add_pages(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool want_memblock); +#endif /* ARCH_HAS_ADD_PAGES */ + #ifdef CONFIG_NUMA extern int memory_add_physaddr_to_nid(u64 start); #else -- cgit v1.2.3 From 5042db43cc26f51eed51c56192e2c2317e44315f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:11:43 -0700 Subject: mm/ZONE_DEVICE: new type of ZONE_DEVICE for unaddressable memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit HMM (heterogeneous memory management) need struct page to support migration from system main memory to device memory. Reasons for HMM and migration to device memory is explained with HMM core patch. This patch deals with device memory that is un-addressable memory (ie CPU can not access it). Hence we do not want those struct page to be manage like regular memory. That is why we extend ZONE_DEVICE to support different types of memory. A persistent memory type is define for existing user of ZONE_DEVICE and a new device un-addressable type is added for the un-addressable memory type. There is a clear separation between what is expected from each memory type and existing user of ZONE_DEVICE are un-affected by new requirement and new use of the un-addressable type. All specific code path are protect with test against the memory type. Because memory is un-addressable we use a new special swap type for when a page is migrated to device memory (this reduces the number of maximum swap file). The main two additions beside memory type to ZONE_DEVICE is two callbacks. First one, page_free() is call whenever page refcount reach 1 (which means the page is free as ZONE_DEVICE page never reach a refcount of 0). This allow device driver to manage its memory and associated struct page. The second callback page_fault() happens when there is a CPU access to an address that is back by a device page (which are un-addressable by the CPU). This callback is responsible to migrate the page back to system main memory. Device driver can not block migration back to system memory, HMM make sure that such page can not be pin into device memory. If device is in some error condition and can not migrate memory back then a CPU page fault to device memory should end with SIGBUS. [arnd@arndb.de: fix warning] Link: http://lkml.kernel.org/r/20170823133213.712917-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20170817000548.32038-8-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Arnd Bergmann Acked-by: Dan Williams Cc: Ross Zwisler Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: David Nellans Cc: Evgeny Baskakov Cc: Johannes Weiner Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Mark Hairgrove Cc: Michal Hocko Cc: Paul E. McKenney Cc: Sherry Cheung Cc: Subhash Gutti Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ioport.h | 1 + include/linux/memremap.h | 73 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm.h | 12 ++++++++ include/linux/swap.h | 24 ++++++++++++++-- include/linux/swapops.h | 68 ++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 175 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 6230064d7f95..3a4f69137bc2 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -130,6 +130,7 @@ enum { IORES_DESC_ACPI_NV_STORAGE = 3, IORES_DESC_PERSISTENT_MEMORY = 4, IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5, + IORES_DESC_DEVICE_PRIVATE_MEMORY = 6, }; /* helpers to define resources */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 93416196ba64..8e164ec9eed0 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -4,6 +4,8 @@ #include #include +#include + struct resource; struct device; @@ -35,18 +37,89 @@ static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) } #endif +/* + * Specialize ZONE_DEVICE memory into multiple types each having differents + * usage. + * + * MEMORY_DEVICE_HOST: + * Persistent device memory (pmem): struct page might be allocated in different + * memory and architecture might want to perform special actions. It is similar + * to regular memory, in that the CPU can access it transparently. However, + * it is likely to have different bandwidth and latency than regular memory. + * See Documentation/nvdimm/nvdimm.txt for more information. + * + * MEMORY_DEVICE_PRIVATE: + * Device memory that is not directly addressable by the CPU: CPU can neither + * read nor write private memory. In this case, we do still have struct pages + * backing the device memory. Doing so simplifies the implementation, but it is + * important to remember that there are certain points at which the struct page + * must be treated as an opaque object, rather than a "normal" struct page. + * + * A more complete discussion of unaddressable memory may be found in + * include/linux/hmm.h and Documentation/vm/hmm.txt. + */ +enum memory_type { + MEMORY_DEVICE_HOST = 0, + MEMORY_DEVICE_PRIVATE, +}; + +/* + * For MEMORY_DEVICE_PRIVATE we use ZONE_DEVICE and extend it with two + * callbacks: + * page_fault() + * page_free() + * + * Additional notes about MEMORY_DEVICE_PRIVATE may be found in + * include/linux/hmm.h and Documentation/vm/hmm.txt. There is also a brief + * explanation in include/linux/memory_hotplug.h. + * + * The page_fault() callback must migrate page back, from device memory to + * system memory, so that the CPU can access it. This might fail for various + * reasons (device issues, device have been unplugged, ...). When such error + * conditions happen, the page_fault() callback must return VM_FAULT_SIGBUS and + * set the CPU page table entry to "poisoned". + * + * Note that because memory cgroup charges are transferred to the device memory, + * this should never fail due to memory restrictions. However, allocation + * of a regular system page might still fail because we are out of memory. If + * that happens, the page_fault() callback must return VM_FAULT_OOM. + * + * The page_fault() callback can also try to migrate back multiple pages in one + * chunk, as an optimization. It must, however, prioritize the faulting address + * over all the others. + * + * + * The page_free() callback is called once the page refcount reaches 1 + * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug. + * This allows the device driver to implement its own memory management.) + */ +typedef int (*dev_page_fault_t)(struct vm_area_struct *vma, + unsigned long addr, + const struct page *page, + unsigned int flags, + pmd_t *pmdp); +typedef void (*dev_page_free_t)(struct page *page, void *data); + /** * struct dev_pagemap - metadata for ZONE_DEVICE mappings + * @page_fault: callback when CPU fault on an unaddressable device page + * @page_free: free page callback when page refcount reaches 1 * @altmap: pre-allocated/reserved memory for vmemmap allocations * @res: physical address range covered by @ref * @ref: reference count that pins the devm_memremap_pages() mapping * @dev: host device of the mapping for debug + * @data: private data pointer for page_free() + * @type: memory type: see MEMORY_* in memory_hotplug.h */ struct dev_pagemap { + dev_page_fault_t page_fault; + dev_page_free_t page_free; struct vmem_altmap *altmap; const struct resource *res; struct percpu_ref *ref; struct device *dev; + void *data; + enum memory_type type; }; #ifdef CONFIG_ZONE_DEVICE diff --git a/include/linux/mm.h b/include/linux/mm.h index 39db8e54c5d5..a74c4e954352 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -792,11 +792,23 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } + +static inline bool is_device_private_page(const struct page *page) +{ + /* See MEMORY_DEVICE_PRIVATE in include/linux/memory_hotplug.h */ + return ((page_zonenum(page) == ZONE_DEVICE) && + (page->pgmap->type == MEMORY_DEVICE_PRIVATE)); +} #else static inline bool is_zone_device_page(const struct page *page) { return false; } + +static inline bool is_device_private_page(const struct page *page) +{ + return false; +} #endif static inline void get_page(struct page *page) diff --git a/include/linux/swap.h b/include/linux/swap.h index 8bf3487fb204..8a807292037f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -50,6 +50,23 @@ static inline int current_is_kswapd(void) * actions on faults. */ +/* + * Unaddressable device memory support. See include/linux/hmm.h and + * Documentation/vm/hmm.txt. Short description is we need struct pages for + * device memory that is unaddressable (inaccessible) by CPU, so that we can + * migrate part of a process memory to device memory. + * + * When a page is migrated from CPU to device, we set the CPU page table entry + * to a special SWP_DEVICE_* entry. + */ +#ifdef CONFIG_DEVICE_PRIVATE +#define SWP_DEVICE_NUM 2 +#define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) +#define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) +#else +#define SWP_DEVICE_NUM 0 +#endif + /* * NUMA node memory migration support */ @@ -72,7 +89,8 @@ static inline int current_is_kswapd(void) #endif #define MAX_SWAPFILES \ - ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) /* * Magic header for a swap area. The first part of the union is @@ -469,8 +487,8 @@ static inline void show_swap_cache_info(void) { } -#define free_swap_and_cache(swp) is_migration_entry(swp) -#define swapcache_prepare(swp) is_migration_entry(swp) +#define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) +#define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 45b092aa6419..291c4b534658 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -100,6 +100,74 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY); } +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) +static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +{ + return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ, + page_to_pfn(page)); +} + +static inline bool is_device_private_entry(swp_entry_t entry) +{ + int type = swp_type(entry); + return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; +} + +static inline void make_device_private_entry_read(swp_entry_t *entry) +{ + *entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry)); +} + +static inline bool is_write_device_private_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); +} + +static inline struct page *device_private_entry_to_page(swp_entry_t entry) +{ + return pfn_to_page(swp_offset(entry)); +} + +int device_private_entry_fault(struct vm_area_struct *vma, + unsigned long addr, + swp_entry_t entry, + unsigned int flags, + pmd_t *pmdp); +#else /* CONFIG_DEVICE_PRIVATE */ +static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +{ + return swp_entry(0, 0); +} + +static inline void make_device_private_entry_read(swp_entry_t *entry) +{ +} + +static inline bool is_device_private_entry(swp_entry_t entry) +{ + return false; +} + +static inline bool is_write_device_private_entry(swp_entry_t entry) +{ + return false; +} + +static inline struct page *device_private_entry_to_page(swp_entry_t entry) +{ + return NULL; +} + +static inline int device_private_entry_fault(struct vm_area_struct *vma, + unsigned long addr, + swp_entry_t entry, + unsigned int flags, + pmd_t *pmdp) +{ + return VM_FAULT_SIGBUS; +} +#endif /* CONFIG_DEVICE_PRIVATE */ + #ifdef CONFIG_MIGRATION static inline swp_entry_t make_migration_entry(struct page *page, int write) { -- cgit v1.2.3 From 7b2d55d2c8961ae9d456d3133f4ae2f0fbd3e14f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:11:46 -0700 Subject: mm/ZONE_DEVICE: special case put_page() for device private pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A ZONE_DEVICE page that reach a refcount of 1 is free ie no longer have any user. For device private pages this is important to catch and thus we need to special case put_page() for this. Link: http://lkml.kernel.org/r/20170817000548.32038-9-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Kirill A. Shutemov Cc: Dan Williams Cc: Ross Zwisler Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: David Nellans Cc: Evgeny Baskakov Cc: Johannes Weiner Cc: John Hubbard Cc: Mark Hairgrove Cc: Michal Hocko Cc: Paul E. McKenney Cc: Sherry Cheung Cc: Subhash Gutti Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memremap.h | 13 +++++++++++++ include/linux/mm.h | 31 ++++++++++++++++++++++--------- 2 files changed, 35 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 8e164ec9eed0..8aa6b82679e2 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -126,6 +126,14 @@ struct dev_pagemap { void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap); struct dev_pagemap *find_dev_pagemap(resource_size_t phys); + +static inline bool is_zone_device_page(const struct page *page); + +static inline bool is_device_private_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PRIVATE; +} #else static inline void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, @@ -144,6 +152,11 @@ static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) { return NULL; } + +static inline bool is_device_private_page(const struct page *page) +{ + return false; +} #endif /** diff --git a/include/linux/mm.h b/include/linux/mm.h index a74c4e954352..eccdab4bb44a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -23,6 +23,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -792,25 +793,25 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } - -static inline bool is_device_private_page(const struct page *page) -{ - /* See MEMORY_DEVICE_PRIVATE in include/linux/memory_hotplug.h */ - return ((page_zonenum(page) == ZONE_DEVICE) && - (page->pgmap->type == MEMORY_DEVICE_PRIVATE)); -} #else static inline bool is_zone_device_page(const struct page *page) { return false; } +#endif -static inline bool is_device_private_page(const struct page *page) +#ifdef CONFIG_DEVICE_PRIVATE +void put_zone_device_private_page(struct page *page); +#else +static inline void put_zone_device_private_page(struct page *page) { - return false; } #endif +static inline bool is_device_private_page(const struct page *page); + +DECLARE_STATIC_KEY_FALSE(device_private_key); + static inline void get_page(struct page *page) { page = compound_head(page); @@ -826,6 +827,18 @@ static inline void put_page(struct page *page) { page = compound_head(page); + /* + * For private device pages we need to catch refcount transition from + * 2 to 1, when refcount reach one it means the private device page is + * free and we need to inform the device driver through callback. See + * include/linux/memremap.h and HMM for details. + */ + if (static_branch_unlikely(&device_private_key) && + unlikely(is_device_private_page(page))) { + put_zone_device_private_page(page); + return; + } + if (put_page_testzero(page)) __put_page(page); } -- cgit v1.2.3 From 4ef589dc9b10cdcae75a2b2b0e9b2c5e8a92c378 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:11:58 -0700 Subject: mm/hmm/devmem: device memory hotplug using ZONE_DEVICE MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This introduce a simple struct and associated helpers for device driver to use when hotpluging un-addressable device memory as ZONE_DEVICE. It will find a unuse physical address range and trigger memory hotplug for it which allocates and initialize struct page for the device memory. Device driver should use this helper during device initialization to hotplug the device memory. It should only need to remove the memory once the device is going offline (shutdown or hotremove). There should not be any userspace API to hotplug memory expect maybe for host device driver to allow to add more memory to a guest device driver. Device's memory is manage by the device driver and HMM only provides helpers to that effect. Link: http://lkml.kernel.org/r/20170817000548.32038-12-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Evgeny Baskakov Signed-off-by: John Hubbard Signed-off-by: Mark Hairgrove Signed-off-by: Sherry Cheung Signed-off-by: Subhash Gutti Signed-off-by: Balbir Singh Cc: Aneesh Kumar Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 155 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 155 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 61a6535fe438..16f916b437cc 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -72,6 +72,11 @@ #if IS_ENABLED(CONFIG_HMM) +#include +#include +#include + + struct hmm; /* @@ -322,6 +327,156 @@ int hmm_vma_fault(struct vm_area_struct *vma, #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) +struct hmm_devmem; + +struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma, + unsigned long addr); + +/* + * struct hmm_devmem_ops - callback for ZONE_DEVICE memory events + * + * @free: call when refcount on page reach 1 and thus is no longer use + * @fault: call when there is a page fault to unaddressable memory + * + * Both callback happens from page_free() and page_fault() callback of struct + * dev_pagemap respectively. See include/linux/memremap.h for more details on + * those. + * + * The hmm_devmem_ops callback are just here to provide a coherent and + * uniq API to device driver and device driver should not register their + * own page_free() or page_fault() but rely on the hmm_devmem_ops call- + * back. + */ +struct hmm_devmem_ops { + /* + * free() - free a device page + * @devmem: device memory structure (see struct hmm_devmem) + * @page: pointer to struct page being freed + * + * Call back occurs whenever a device page refcount reach 1 which + * means that no one is holding any reference on the page anymore + * (ZONE_DEVICE page have an elevated refcount of 1 as default so + * that they are not release to the general page allocator). + * + * Note that callback has exclusive ownership of the page (as no + * one is holding any reference). + */ + void (*free)(struct hmm_devmem *devmem, struct page *page); + /* + * fault() - CPU page fault or get user page (GUP) + * @devmem: device memory structure (see struct hmm_devmem) + * @vma: virtual memory area containing the virtual address + * @addr: virtual address that faulted or for which there is a GUP + * @page: pointer to struct page backing virtual address (unreliable) + * @flags: FAULT_FLAG_* (see include/linux/mm.h) + * @pmdp: page middle directory + * Returns: VM_FAULT_MINOR/MAJOR on success or one of VM_FAULT_ERROR + * on error + * + * The callback occurs whenever there is a CPU page fault or GUP on a + * virtual address. This means that the device driver must migrate the + * page back to regular memory (CPU accessible). + * + * The device driver is free to migrate more than one page from the + * fault() callback as an optimization. However if device decide to + * migrate more than one page it must always priotirize the faulting + * address over the others. + * + * The struct page pointer is only given as an hint to allow quick + * lookup of internal device driver data. A concurrent migration + * might have already free that page and the virtual address might + * not longer be back by it. So it should not be modified by the + * callback. + * + * Note that mmap semaphore is held in read mode at least when this + * callback occurs, hence the vma is valid upon callback entry. + */ + int (*fault)(struct hmm_devmem *devmem, + struct vm_area_struct *vma, + unsigned long addr, + const struct page *page, + unsigned int flags, + pmd_t *pmdp); +}; + +/* + * struct hmm_devmem - track device memory + * + * @completion: completion object for device memory + * @pfn_first: first pfn for this resource (set by hmm_devmem_add()) + * @pfn_last: last pfn for this resource (set by hmm_devmem_add()) + * @resource: IO resource reserved for this chunk of memory + * @pagemap: device page map for that chunk + * @device: device to bind resource to + * @ops: memory operations callback + * @ref: per CPU refcount + * + * This an helper structure for device drivers that do not wish to implement + * the gory details related to hotplugging new memoy and allocating struct + * pages. + * + * Device drivers can directly use ZONE_DEVICE memory on their own if they + * wish to do so. + */ +struct hmm_devmem { + struct completion completion; + unsigned long pfn_first; + unsigned long pfn_last; + struct resource *resource; + struct device *device; + struct dev_pagemap pagemap; + const struct hmm_devmem_ops *ops; + struct percpu_ref ref; +}; + +/* + * To add (hotplug) device memory, HMM assumes that there is no real resource + * that reserves a range in the physical address space (this is intended to be + * use by unaddressable device memory). It will reserve a physical range big + * enough and allocate struct page for it. + * + * The device driver can wrap the hmm_devmem struct inside a private device + * driver struct. The device driver must call hmm_devmem_remove() before the + * device goes away and before freeing the hmm_devmem struct memory. + */ +struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, + struct device *device, + unsigned long size); +void hmm_devmem_remove(struct hmm_devmem *devmem); + +/* + * hmm_devmem_page_set_drvdata - set per-page driver data field + * + * @page: pointer to struct page + * @data: driver data value to set + * + * Because page can not be on lru we have an unsigned long that driver can use + * to store a per page field. This just a simple helper to do that. + */ +static inline void hmm_devmem_page_set_drvdata(struct page *page, + unsigned long data) +{ + unsigned long *drvdata = (unsigned long *)&page->pgmap; + + drvdata[1] = data; +} + +/* + * hmm_devmem_page_get_drvdata - get per page driver data field + * + * @page: pointer to struct page + * Return: driver data value + */ +static inline unsigned long hmm_devmem_page_get_drvdata(struct page *page) +{ + unsigned long *drvdata = (unsigned long *)&page->pgmap; + + return drvdata[1]; +} +#endif /* IS_ENABLED(CONFIG_DEVICE_PRIVATE) */ + + /* Below are for HMM internal use only! Not to be used by device driver! */ void hmm_mm_destroy(struct mm_struct *mm); -- cgit v1.2.3 From 858b54dabf4363daa3a97b9a722130a8e7cea8c9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:12:02 -0700 Subject: mm/hmm/devmem: dummy HMM device for ZONE_DEVICE memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This introduce a dummy HMM device class so device driver can use it to create hmm_device for the sole purpose of registering device memory. It is useful to device driver that want to manage multiple physical device memory under same struct device umbrella. Link: http://lkml.kernel.org/r/20170817000548.32038-13-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Evgeny Baskakov Signed-off-by: John Hubbard Signed-off-by: Mark Hairgrove Signed-off-by: Sherry Cheung Signed-off-by: Subhash Gutti Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 16f916b437cc..67a03b20a2db 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -72,11 +72,11 @@ #if IS_ENABLED(CONFIG_HMM) +#include #include #include #include - struct hmm; /* @@ -474,6 +474,26 @@ static inline unsigned long hmm_devmem_page_get_drvdata(struct page *page) return drvdata[1]; } + + +/* + * struct hmm_device - fake device to hang device memory onto + * + * @device: device struct + * @minor: device minor number + */ +struct hmm_device { + struct device device; + unsigned int minor; +}; + +/* + * A device driver that wants to handle multiple devices memory through a + * single fake device can use hmm_device to do so. This is purely a helper and + * it is not strictly needed, in order to make use of any HMM functionality. + */ +struct hmm_device *hmm_device_new(void *drvdata); +void hmm_device_put(struct hmm_device *hmm_device); #endif /* IS_ENABLED(CONFIG_DEVICE_PRIVATE) */ -- cgit v1.2.3 From 2916ecc0f9d435d849c98f4da50e453124c87531 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:12:06 -0700 Subject: mm/migrate: new migrate mode MIGRATE_SYNC_NO_COPY MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce a new migration mode that allow to offload the copy to a device DMA engine. This changes the workflow of migration and not all address_space migratepage callback can support this. This is intended to be use by migrate_vma() which itself is use for thing like HMM (see include/linux/hmm.h). No additional per-filesystem migratepage testing is needed. I disables MIGRATE_SYNC_NO_COPY in all problematic migratepage() callback and i added comment in those to explain why (part of this patch). The commit message is unclear it should say that any callback that wish to support this new mode need to be aware of the difference in the migration flow from other mode. Some of these callbacks do extra locking while copying (aio, zsmalloc, balloon, ...) and for DMA to be effective you want to copy multiple pages in one DMA operations. But in the problematic case you can not easily hold the extra lock accross multiple call to this callback. Usual flow is: For each page { 1 - lock page 2 - call migratepage() callback 3 - (extra locking in some migratepage() callback) 4 - migrate page state (freeze refcount, update page cache, buffer head, ...) 5 - copy page 6 - (unlock any extra lock of migratepage() callback) 7 - return from migratepage() callback 8 - unlock page } The new mode MIGRATE_SYNC_NO_COPY: 1 - lock multiple pages For each page { 2 - call migratepage() callback 3 - abort in all problematic migratepage() callback 4 - migrate page state (freeze refcount, update page cache, buffer head, ...) } // finished all calls to migratepage() callback 5 - DMA copy multiple pages 6 - unlock all the pages To support MIGRATE_SYNC_NO_COPY in the problematic case we would need a new callback migratepages() (for instance) that deals with multiple pages in one transaction. Because the problematic cases are not important for current usage I did not wanted to complexify this patchset even more for no good reason. Link: http://lkml.kernel.org/r/20170817000548.32038-14-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Evgeny Baskakov Cc: Johannes Weiner Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Mark Hairgrove Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Sherry Cheung Cc: Subhash Gutti Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 5 +++++ include/linux/migrate_mode.h | 5 +++++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index ce15989521a1..7db4c812a2a6 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -72,6 +72,7 @@ extern void putback_movable_page(struct page *page); extern int migrate_prep(void); extern int migrate_prep_local(void); +extern void migrate_page_states(struct page *newpage, struct page *page); extern void migrate_page_copy(struct page *newpage, struct page *page); extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); @@ -92,6 +93,10 @@ static inline int isolate_movable_page(struct page *page, isolate_mode_t mode) static inline int migrate_prep(void) { return -ENOSYS; } static inline int migrate_prep_local(void) { return -ENOSYS; } +static inline void migrate_page_states(struct page *newpage, struct page *page) +{ +} + static inline void migrate_page_copy(struct page *newpage, struct page *page) {} diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h index ebf3d89a3919..bdf66af9b937 100644 --- a/include/linux/migrate_mode.h +++ b/include/linux/migrate_mode.h @@ -6,11 +6,16 @@ * on most operations but not ->writepage as the potential stall time * is too significant * MIGRATE_SYNC will block when migrating pages + * MIGRATE_SYNC_NO_COPY will block when migrating pages but will not copy pages + * with the CPU. Instead, page copy happens outside the migratepage() + * callback and is likely using a DMA engine. See migrate_vma() and HMM + * (mm/hmm.c) for users of this mode. */ enum migrate_mode { MIGRATE_ASYNC, MIGRATE_SYNC_LIGHT, MIGRATE_SYNC, + MIGRATE_SYNC_NO_COPY, }; #endif /* MIGRATE_MODE_H_INCLUDED */ -- cgit v1.2.3 From 8763cb45ab967a92a5ee49e9c544c0f0ea90e2d6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:12:09 -0700 Subject: mm/migrate: new memory migration helper for use with device memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch add a new memory migration helpers, which migrate memory backing a range of virtual address of a process to different memory (which can be allocated through special allocator). It differs from numa migration by working on a range of virtual address and thus by doing migration in chunk that can be large enough to use DMA engine or special copy offloading engine. Expected users are any one with heterogeneous memory where different memory have different characteristics (latency, bandwidth, ...). As an example IBM platform with CAPI bus can make use of this feature to migrate between regular memory and CAPI device memory. New CPU architecture with a pool of high performance memory not manage as cache but presented as regular memory (while being faster and with lower latency than DDR) will also be prime user of this patch. Migration to private device memory will be useful for device that have large pool of such like GPU, NVidia plans to use HMM for that. Link: http://lkml.kernel.org/r/20170817000548.32038-15-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Evgeny Baskakov Signed-off-by: John Hubbard Signed-off-by: Mark Hairgrove Signed-off-by: Sherry Cheung Signed-off-by: Subhash Gutti Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 104 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 104 insertions(+) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 7db4c812a2a6..8f73cebfc3f5 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -156,4 +156,108 @@ static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm, } #endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/ + +#ifdef CONFIG_MIGRATION + +#define MIGRATE_PFN_VALID (1UL << 0) +#define MIGRATE_PFN_MIGRATE (1UL << 1) +#define MIGRATE_PFN_LOCKED (1UL << 2) +#define MIGRATE_PFN_WRITE (1UL << 3) +#define MIGRATE_PFN_ERROR (1UL << 4) +#define MIGRATE_PFN_SHIFT 5 + +static inline struct page *migrate_pfn_to_page(unsigned long mpfn) +{ + if (!(mpfn & MIGRATE_PFN_VALID)) + return NULL; + return pfn_to_page(mpfn >> MIGRATE_PFN_SHIFT); +} + +static inline unsigned long migrate_pfn(unsigned long pfn) +{ + return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID; +} + +/* + * struct migrate_vma_ops - migrate operation callback + * + * @alloc_and_copy: alloc destination memory and copy source memory to it + * @finalize_and_map: allow caller to map the successfully migrated pages + * + * + * The alloc_and_copy() callback happens once all source pages have been locked, + * unmapped and checked (checked whether pinned or not). All pages that can be + * migrated will have an entry in the src array set with the pfn value of the + * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set (other + * flags might be set but should be ignored by the callback). + * + * The alloc_and_copy() callback can then allocate destination memory and copy + * source memory to it for all those entries (ie with MIGRATE_PFN_VALID and + * MIGRATE_PFN_MIGRATE flag set). Once these are allocated and copied, the + * callback must update each corresponding entry in the dst array with the pfn + * value of the destination page and with the MIGRATE_PFN_VALID and + * MIGRATE_PFN_LOCKED flags set (destination pages must have their struct pages + * locked, via lock_page()). + * + * At this point the alloc_and_copy() callback is done and returns. + * + * Note that the callback does not have to migrate all the pages that are + * marked with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration + * from device memory to system memory (ie the MIGRATE_PFN_DEVICE flag is also + * set in the src array entry). If the device driver cannot migrate a device + * page back to system memory, then it must set the corresponding dst array + * entry to MIGRATE_PFN_ERROR. This will trigger a SIGBUS if CPU tries to + * access any of the virtual addresses originally backed by this page. Because + * a SIGBUS is such a severe result for the userspace process, the device + * driver should avoid setting MIGRATE_PFN_ERROR unless it is really in an + * unrecoverable state. + * + * THE alloc_and_copy() CALLBACK MUST NOT CHANGE ANY OF THE SRC ARRAY ENTRIES + * OR BAD THINGS WILL HAPPEN ! + * + * + * The finalize_and_map() callback happens after struct page migration from + * source to destination (destination struct pages are the struct pages for the + * memory allocated by the alloc_and_copy() callback). Migration can fail, and + * thus the finalize_and_map() allows the driver to inspect which pages were + * successfully migrated, and which were not. Successfully migrated pages will + * have the MIGRATE_PFN_MIGRATE flag set for their src array entry. + * + * It is safe to update device page table from within the finalize_and_map() + * callback because both destination and source page are still locked, and the + * mmap_sem is held in read mode (hence no one can unmap the range being + * migrated). + * + * Once callback is done cleaning up things and updating its page table (if it + * chose to do so, this is not an obligation) then it returns. At this point, + * the HMM core will finish up the final steps, and the migration is complete. + * + * THE finalize_and_map() CALLBACK MUST NOT CHANGE ANY OF THE SRC OR DST ARRAY + * ENTRIES OR BAD THINGS WILL HAPPEN ! + */ +struct migrate_vma_ops { + void (*alloc_and_copy)(struct vm_area_struct *vma, + const unsigned long *src, + unsigned long *dst, + unsigned long start, + unsigned long end, + void *private); + void (*finalize_and_map)(struct vm_area_struct *vma, + const unsigned long *src, + const unsigned long *dst, + unsigned long start, + unsigned long end, + void *private); +}; + +int migrate_vma(const struct migrate_vma_ops *ops, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + unsigned long *src, + unsigned long *dst, + void *private); + +#endif /* CONFIG_MIGRATION */ + #endif /* _LINUX_MIGRATE_H */ -- cgit v1.2.3 From a5430dda8a3a1cdd532e37270e6f36436241b6e7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:12:17 -0700 Subject: mm/migrate: support un-addressable ZONE_DEVICE page in migration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow to unmap and restore special swap entry of un-addressable ZONE_DEVICE memory. Link: http://lkml.kernel.org/r/20170817000548.32038-17-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Kirill A. Shutemov Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Evgeny Baskakov Cc: Johannes Weiner Cc: John Hubbard Cc: Mark Hairgrove Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Sherry Cheung Cc: Subhash Gutti Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 8f73cebfc3f5..8dc8f0a3f1af 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -159,12 +159,18 @@ static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm, #ifdef CONFIG_MIGRATION +/* + * Watch out for PAE architecture, which has an unsigned long, and might not + * have enough bits to store all physical address and flags. So far we have + * enough room for all our flags. + */ #define MIGRATE_PFN_VALID (1UL << 0) #define MIGRATE_PFN_MIGRATE (1UL << 1) #define MIGRATE_PFN_LOCKED (1UL << 2) #define MIGRATE_PFN_WRITE (1UL << 3) -#define MIGRATE_PFN_ERROR (1UL << 4) -#define MIGRATE_PFN_SHIFT 5 +#define MIGRATE_PFN_DEVICE (1UL << 4) +#define MIGRATE_PFN_ERROR (1UL << 5) +#define MIGRATE_PFN_SHIFT 6 static inline struct page *migrate_pfn_to_page(unsigned long mpfn) { -- cgit v1.2.3 From 8315ada7f095bfa2cae0cd1e915b95bf6226897d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:12:21 -0700 Subject: mm/migrate: allow migrate_vma() to alloc new page on empty entry MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows callers of migrate_vma() to allocate new page for empty CPU page table entry (pte_none or back by zero page). This is only for anonymous memory and it won't allow new page to be instanced if the userfaultfd is armed. This is useful to device driver that want to migrate a range of virtual address and would rather allocate new memory than having to fault later on. Link: http://lkml.kernel.org/r/20170817000548.32038-18-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Aneesh Kumar Cc: Balbir Singh Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Evgeny Baskakov Cc: Johannes Weiner Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Mark Hairgrove Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Sherry Cheung Cc: Subhash Gutti Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 8dc8f0a3f1af..d4e6d12a0b40 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -218,6 +218,15 @@ static inline unsigned long migrate_pfn(unsigned long pfn) * driver should avoid setting MIGRATE_PFN_ERROR unless it is really in an * unrecoverable state. * + * For empty entry inside CPU page table (pte_none() or pmd_none() is true) we + * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus + * allowing device driver to allocate device memory for those unback virtual + * address. For this the device driver simply have to allocate device memory + * and properly set the destination entry like for regular migration. Note that + * this can still fails and thus inside the device driver must check if the + * migration was successful for those entry inside the finalize_and_map() + * callback just like for regular migration. + * * THE alloc_and_copy() CALLBACK MUST NOT CHANGE ANY OF THE SRC ARRAY ENTRIES * OR BAD THINGS WILL HAPPEN ! * -- cgit v1.2.3 From df6ad69838fc9dcdbee0dcf2fc2c6f1113f8d609 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:12:24 -0700 Subject: mm/device-public-memory: device memory cache coherent with CPU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Platform with advance system bus (like CAPI or CCIX) allow device memory to be accessible from CPU in a cache coherent fashion. Add a new type of ZONE_DEVICE to represent such memory. The use case are the same as for the un-addressable device memory but without all the corners cases. Link: http://lkml.kernel.org/r/20170817000548.32038-19-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Aneesh Kumar Cc: Paul E. McKenney Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: Ross Zwisler Cc: Balbir Singh Cc: David Nellans Cc: Evgeny Baskakov Cc: Johannes Weiner Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Mark Hairgrove Cc: Michal Hocko Cc: Sherry Cheung Cc: Subhash Gutti Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 4 ++-- include/linux/ioport.h | 1 + include/linux/memremap.h | 21 +++++++++++++++++++++ include/linux/mm.h | 20 ++++++++++++-------- 4 files changed, 36 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 67a03b20a2db..6d3b0b4fed4e 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -327,7 +327,7 @@ int hmm_vma_fault(struct vm_area_struct *vma, #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) struct hmm_devmem; struct page *hmm_vma_alloc_locked_page(struct vm_area_struct *vma, @@ -494,7 +494,7 @@ struct hmm_device { */ struct hmm_device *hmm_device_new(void *drvdata); void hmm_device_put(struct hmm_device *hmm_device); -#endif /* IS_ENABLED(CONFIG_DEVICE_PRIVATE) */ +#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ /* Below are for HMM internal use only! Not to be used by device driver! */ diff --git a/include/linux/ioport.h b/include/linux/ioport.h index 3a4f69137bc2..f5cf32e80041 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -131,6 +131,7 @@ enum { IORES_DESC_PERSISTENT_MEMORY = 4, IORES_DESC_PERSISTENT_MEMORY_LEGACY = 5, IORES_DESC_DEVICE_PRIVATE_MEMORY = 6, + IORES_DESC_DEVICE_PUBLIC_MEMORY = 7, }; /* helpers to define resources */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 8aa6b82679e2..f8ee1c73ad2d 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -57,10 +57,18 @@ static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) * * A more complete discussion of unaddressable memory may be found in * include/linux/hmm.h and Documentation/vm/hmm.txt. + * + * MEMORY_DEVICE_PUBLIC: + * Device memory that is cache coherent from device and CPU point of view. This + * is use on platform that have an advance system bus (like CAPI or CCIX). A + * driver can hotplug the device memory using ZONE_DEVICE and with that memory + * type. Any page of a process can be migrated to such memory. However no one + * should be allow to pin such memory so that it can always be evicted. */ enum memory_type { MEMORY_DEVICE_HOST = 0, MEMORY_DEVICE_PRIVATE, + MEMORY_DEVICE_PUBLIC, }; /* @@ -92,6 +100,8 @@ enum memory_type { * The page_free() callback is called once the page refcount reaches 1 * (ZONE_DEVICE pages never reach 0 refcount unless there is a refcount bug. * This allows the device driver to implement its own memory management.) + * + * For MEMORY_DEVICE_PUBLIC only the page_free() callback matter. */ typedef int (*dev_page_fault_t)(struct vm_area_struct *vma, unsigned long addr, @@ -134,6 +144,12 @@ static inline bool is_device_private_page(const struct page *page) return is_zone_device_page(page) && page->pgmap->type == MEMORY_DEVICE_PRIVATE; } + +static inline bool is_device_public_page(const struct page *page) +{ + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PUBLIC; +} #else static inline void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, @@ -157,6 +173,11 @@ static inline bool is_device_private_page(const struct page *page) { return false; } + +static inline bool is_device_public_page(const struct page *page) +{ + return false; +} #endif /** diff --git a/include/linux/mm.h b/include/linux/mm.h index eccdab4bb44a..de66a1127db4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -800,15 +800,16 @@ static inline bool is_zone_device_page(const struct page *page) } #endif -#ifdef CONFIG_DEVICE_PRIVATE -void put_zone_device_private_page(struct page *page); +#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) +void put_zone_device_private_or_public_page(struct page *page); #else -static inline void put_zone_device_private_page(struct page *page) +static inline void put_zone_device_private_or_public_page(struct page *page) { } -#endif +#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ static inline bool is_device_private_page(const struct page *page); +static inline bool is_device_public_page(const struct page *page); DECLARE_STATIC_KEY_FALSE(device_private_key); @@ -834,8 +835,9 @@ static inline void put_page(struct page *page) * include/linux/memremap.h and HMM for details. */ if (static_branch_unlikely(&device_private_key) && - unlikely(is_device_private_page(page))) { - put_zone_device_private_page(page); + unlikely(is_device_private_page(page) || + is_device_public_page(page))) { + put_zone_device_private_or_public_page(page); return; } @@ -1224,8 +1226,10 @@ struct zap_details { pgoff_t last_index; /* Highest page->index to unmap */ }; -struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, - pte_t pte); +struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte, bool with_public_device); +#define vm_normal_page(vma, addr, pte) _vm_normal_page(vma, addr, pte, false) + struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd); -- cgit v1.2.3 From d3df0a423397c9a1ae05c3857e8c04240dd85e68 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:12:28 -0700 Subject: mm/hmm: add new helper to hotplug CDM memory region MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Unlike unaddressable memory, coherent device memory has a real resource associated with it on the system (as CPU can address it). Add a new helper to hotplug such memory within the HMM framework. Link: http://lkml.kernel.org/r/20170817000548.32038-20-jglisse@redhat.com Signed-off-by: Jérôme Glisse Reviewed-by: Balbir Singh Cc: Aneesh Kumar Cc: Benjamin Herrenschmidt Cc: Dan Williams Cc: David Nellans Cc: Evgeny Baskakov Cc: Johannes Weiner Cc: John Hubbard Cc: Kirill A. Shutemov Cc: Mark Hairgrove Cc: Michal Hocko Cc: Paul E. McKenney Cc: Ross Zwisler Cc: Sherry Cheung Cc: Subhash Gutti Cc: Vladimir Davydov Cc: Bob Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 6d3b0b4fed4e..8385e75356ca 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -443,6 +443,9 @@ struct hmm_devmem { struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, struct device *device, unsigned long size); +struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, + struct device *device, + struct resource *res); void hmm_devmem_remove(struct hmm_devmem *devmem); /* -- cgit v1.2.3 From 6b368cd4a44ce95b33f1d31f2f932e6ae707f319 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:12:32 -0700 Subject: mm/hmm: avoid bloating arch that do not make use of HMM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This moves all new code including new page migration helper behind kernel Kconfig option so that there is no codee bloat for arch or user that do not want to use HMM or any of its associated features. arm allyesconfig (without all the patchset, then with and this patch): text data bss dec hex filename 83721896 46511131 27582964 157815991 96814b7 ../without/vmlinux 83722364 46511131 27582964 157816459 968168b vmlinux [jglisse@redhat.com: struct hmm is only use by HMM mirror functionality] Link: http://lkml.kernel.org/r/20170825213133.27286-1-jglisse@redhat.com [sfr@canb.auug.org.au: fix build (arm multi_v7_defconfig)] Link: http://lkml.kernel.org/r/20170828181849.323ab81b@canb.auug.org.au Link: http://lkml.kernel.org/r/20170818032858.7447-1-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Stephen Rothwell Cc: Dan Williams Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 9 ++++++--- include/linux/memremap.h | 22 +++++++--------------- include/linux/migrate.h | 13 +++++++++++++ include/linux/mm.h | 26 +++++++++++++++++--------- 4 files changed, 43 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 8385e75356ca..28e14345bd8d 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -501,18 +501,21 @@ void hmm_device_put(struct hmm_device *hmm_device); /* Below are for HMM internal use only! Not to be used by device driver! */ +#if IS_ENABLED(CONFIG_HMM_MIRROR) void hmm_mm_destroy(struct mm_struct *mm); static inline void hmm_mm_init(struct mm_struct *mm) { mm->hmm = NULL; } +#else /* IS_ENABLED(CONFIG_HMM_MIRROR) */ +static inline void hmm_mm_destroy(struct mm_struct *mm) {} +static inline void hmm_mm_init(struct mm_struct *mm) {} +#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -#else /* IS_ENABLED(CONFIG_HMM) */ -/* Below are for HMM internal use only! Not to be used by device driver! */ +#else /* IS_ENABLED(CONFIG_HMM) */ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} - #endif /* IS_ENABLED(CONFIG_HMM) */ #endif /* LINUX_HMM_H */ diff --git a/include/linux/memremap.h b/include/linux/memremap.h index f8ee1c73ad2d..79f8ba7c3894 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -138,18 +138,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, struct dev_pagemap *find_dev_pagemap(resource_size_t phys); static inline bool is_zone_device_page(const struct page *page); - -static inline bool is_device_private_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PRIVATE; -} - -static inline bool is_device_public_page(const struct page *page) -{ - return is_zone_device_page(page) && - page->pgmap->type == MEMORY_DEVICE_PUBLIC; -} #else static inline void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, @@ -168,17 +156,21 @@ static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys) { return NULL; } +#endif +#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) static inline bool is_device_private_page(const struct page *page) { - return false; + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool is_device_public_page(const struct page *page) { - return false; + return is_zone_device_page(page) && + page->pgmap->type == MEMORY_DEVICE_PUBLIC; } -#endif +#endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ /** * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn diff --git a/include/linux/migrate.h b/include/linux/migrate.h index d4e6d12a0b40..643c7ae7d7b4 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -265,6 +265,7 @@ struct migrate_vma_ops { void *private); }; +#if defined(CONFIG_MIGRATE_VMA_HELPER) int migrate_vma(const struct migrate_vma_ops *ops, struct vm_area_struct *vma, unsigned long start, @@ -272,6 +273,18 @@ int migrate_vma(const struct migrate_vma_ops *ops, unsigned long *src, unsigned long *dst, void *private); +#else +static inline int migrate_vma(const struct migrate_vma_ops *ops, + struct vm_area_struct *vma, + unsigned long start, + unsigned long end, + unsigned long *src, + unsigned long *dst, + void *private) +{ + return -EINVAL; +} +#endif /* IS_ENABLED(CONFIG_MIGRATE_VMA_HELPER) */ #endif /* CONFIG_MIGRATION */ diff --git a/include/linux/mm.h b/include/linux/mm.h index de66a1127db4..5195e272fc4a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -800,18 +800,27 @@ static inline bool is_zone_device_page(const struct page *page) } #endif -#if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) +#if defined(CONFIG_DEVICE_PRIVATE) || defined(CONFIG_DEVICE_PUBLIC) void put_zone_device_private_or_public_page(struct page *page); -#else +DECLARE_STATIC_KEY_FALSE(device_private_key); +#define IS_HMM_ENABLED static_branch_unlikely(&device_private_key) +static inline bool is_device_private_page(const struct page *page); +static inline bool is_device_public_page(const struct page *page); +#else /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ static inline void put_zone_device_private_or_public_page(struct page *page) { } +#define IS_HMM_ENABLED 0 +static inline bool is_device_private_page(const struct page *page) +{ + return false; +} +static inline bool is_device_public_page(const struct page *page) +{ + return false; +} #endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ -static inline bool is_device_private_page(const struct page *page); -static inline bool is_device_public_page(const struct page *page); - -DECLARE_STATIC_KEY_FALSE(device_private_key); static inline void get_page(struct page *page) { @@ -834,9 +843,8 @@ static inline void put_page(struct page *page) * free and we need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ - if (static_branch_unlikely(&device_private_key) && - unlikely(is_device_private_page(page) || - is_device_public_page(page))) { + if (IS_HMM_ENABLED && unlikely(is_device_private_page(page) || + unlikely(is_device_public_page(page)))) { put_zone_device_private_or_public_page(page); return; } -- cgit v1.2.3 From de540a9763efcd5b6339158ac2e5932fb3e691b9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= Date: Fri, 8 Sep 2017 16:12:35 -0700 Subject: mm/hmm: fix build when HMM is disabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Combinatorial Kconfig is painfull. Withi this patch all below combination build. 1) 2) CONFIG_HMM_MIRROR=y 3) CONFIG_DEVICE_PRIVATE=y 4) CONFIG_DEVICE_PUBLIC=y 5) CONFIG_HMM_MIRROR=y CONFIG_DEVICE_PUBLIC=y 6) CONFIG_HMM_MIRROR=y CONFIG_DEVICE_PRIVATE=y 7) CONFIG_DEVICE_PRIVATE=y CONFIG_DEVICE_PUBLIC=y 8) CONFIG_HMM_MIRROR=y CONFIG_DEVICE_PRIVATE=y CONFIG_DEVICE_PUBLIC=y Link: http://lkml.kernel.org/r/20170826002149.20919-1-jglisse@redhat.com Reported-by: Randy Dunlap Signed-off-by: Jérôme Glisse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 28e14345bd8d..96e69979f84d 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -498,7 +498,7 @@ struct hmm_device { struct hmm_device *hmm_device_new(void *drvdata); void hmm_device_put(struct hmm_device *hmm_device); #endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ - +#endif /* IS_ENABLED(CONFIG_HMM) */ /* Below are for HMM internal use only! Not to be used by device driver! */ #if IS_ENABLED(CONFIG_HMM_MIRROR) @@ -517,5 +517,4 @@ static inline void hmm_mm_init(struct mm_struct *mm) {} #else /* IS_ENABLED(CONFIG_HMM) */ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} -#endif /* IS_ENABLED(CONFIG_HMM) */ #endif /* LINUX_HMM_H */ -- cgit v1.2.3 From 3a321d2a3dde812142e06ab5c2f062ed860182a5 Mon Sep 17 00:00:00 2001 From: Kemi Wang Date: Fri, 8 Sep 2017 16:12:48 -0700 Subject: mm: change the call sites of numa statistics items Patch series "Separate NUMA statistics from zone statistics", v2. Each page allocation updates a set of per-zone statistics with a call to zone_statistics(). As discussed in 2017 MM summit, these are a substantial source of overhead in the page allocator and are very rarely consumed. This significant overhead in cache bouncing caused by zone counters (NUMA associated counters) update in parallel in multi-threaded page allocation (pointed out by Dave Hansen). A link to the MM summit slides: http://people.netfilter.org/hawk/presentations/MM-summit2017/MM-summit2017-JesperBrouer.pdf To mitigate this overhead, this patchset separates NUMA statistics from zone statistics framework, and update NUMA counter threshold to a fixed size of MAX_U16 - 2, as a small threshold greatly increases the update frequency of the global counter from local per cpu counter (suggested by Ying Huang). The rationality is that these statistics counters don't need to be read often, unlike other VM counters, so it's not a problem to use a large threshold and make readers more expensive. With this patchset, we see 31.3% drop of CPU cycles(537-->369, see below) for per single page allocation and reclaim on Jesper's page_bench03 benchmark. Meanwhile, this patchset keeps the same style of virtual memory statistics with little end-user-visible effects (only move the numa stats to show behind zone page stats, see the first patch for details). I did an experiment of single page allocation and reclaim concurrently using Jesper's page_bench03 benchmark on a 2-Socket Broadwell-based server (88 processors with 126G memory) with different size of threshold of pcp counter. Benchmark provided by Jesper D Brouer(increase loop times to 10000000): https://github.com/netoptimizer/prototype-kernel/tree/master/kernel/mm/bench Threshold CPU cycles Throughput(88 threads) 32 799 241760478 64 640 301628829 125 537 358906028 <==> system by default 256 468 412397590 512 428 450550704 4096 399 482520943 20000 394 489009617 30000 395 488017817 65533 369(-31.3%) 521661345(+45.3%) <==> with this patchset N/A 342(-36.3%) 562900157(+56.8%) <==> disable zone_statistics This patch (of 3): In this patch, NUMA statistics is separated from zone statistics framework, all the call sites of NUMA stats are changed to use numa-stats-specific functions, it does not have any functionality change except that the number of NUMA stats is shown behind zone page stats when users *read* the zone info. E.g. cat /proc/zoneinfo ***Base*** ***With this patch*** nr_free_pages 3976 nr_free_pages 3976 nr_zone_inactive_anon 0 nr_zone_inactive_anon 0 nr_zone_active_anon 0 nr_zone_active_anon 0 nr_zone_inactive_file 0 nr_zone_inactive_file 0 nr_zone_active_file 0 nr_zone_active_file 0 nr_zone_unevictable 0 nr_zone_unevictable 0 nr_zone_write_pending 0 nr_zone_write_pending 0 nr_mlock 0 nr_mlock 0 nr_page_table_pages 0 nr_page_table_pages 0 nr_kernel_stack 0 nr_kernel_stack 0 nr_bounce 0 nr_bounce 0 nr_zspages 0 nr_zspages 0 numa_hit 0 *nr_free_cma 0* numa_miss 0 numa_hit 0 numa_foreign 0 numa_miss 0 numa_interleave 0 numa_foreign 0 numa_local 0 numa_interleave 0 numa_other 0 numa_local 0 *nr_free_cma 0* numa_other 0 ... ... vm stats threshold: 10 vm stats threshold: 10 ... ... The next patch updates the numa stats counter size and threshold. [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1503568801-21305-2-git-send-email-kemi.wang@intel.com Signed-off-by: Kemi Wang Reported-by: Jesper Dangaard Brouer Acked-by: Mel Gorman Cc: Michal Hocko Cc: Johannes Weiner Cc: Christopher Lameter Cc: Dave Hansen Cc: Andi Kleen Cc: Ying Huang Cc: Aaron Lu Cc: Tim Chen Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 25 +++++++++++++++++-------- include/linux/vmstat.h | 29 ++++++++++++++++++++++++++++- 2 files changed, 45 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e7e92c8f4883..e65d91c02e30 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -114,6 +114,20 @@ struct zone_padding { #define ZONE_PADDING(name) #endif +#ifdef CONFIG_NUMA +enum numa_stat_item { + NUMA_HIT, /* allocated in intended node */ + NUMA_MISS, /* allocated in non intended node */ + NUMA_FOREIGN, /* was intended here, hit elsewhere */ + NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ + NUMA_LOCAL, /* allocation from local node */ + NUMA_OTHER, /* allocation from other node */ + NR_VM_NUMA_STAT_ITEMS +}; +#else +#define NR_VM_NUMA_STAT_ITEMS 0 +#endif + enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, @@ -131,14 +145,6 @@ enum zone_stat_item { NR_BOUNCE, #if IS_ENABLED(CONFIG_ZSMALLOC) NR_ZSPAGES, /* allocated in zsmalloc */ -#endif -#ifdef CONFIG_NUMA - NUMA_HIT, /* allocated in intended node */ - NUMA_MISS, /* allocated in non intended node */ - NUMA_FOREIGN, /* was intended here, hit elsewhere */ - NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ - NUMA_LOCAL, /* allocation from local node */ - NUMA_OTHER, /* allocation from other node */ #endif NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; @@ -276,6 +282,8 @@ struct per_cpu_pageset { struct per_cpu_pages pcp; #ifdef CONFIG_NUMA s8 expire; + s8 numa_stat_threshold; + s8 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; #endif #ifdef CONFIG_SMP s8 stat_threshold; @@ -496,6 +504,7 @@ struct zone { ZONE_PADDING(_pad3_) /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; + atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; } ____cacheline_internodealigned_in_smp; enum pgdat_flags { diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 97e11ab573f0..9ac82e29948f 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -107,8 +107,33 @@ static inline void vm_events_fold_cpu(int cpu) * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; +extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; +#ifdef CONFIG_NUMA +static inline void zone_numa_state_add(long x, struct zone *zone, + enum numa_stat_item item) +{ + atomic_long_add(x, &zone->vm_numa_stat[item]); + atomic_long_add(x, &vm_numa_stat[item]); +} + +static inline unsigned long global_numa_state(enum numa_stat_item item) +{ + long x = atomic_long_read(&vm_numa_stat[item]); + + return x; +} + +static inline unsigned long zone_numa_state(struct zone *zone, + enum numa_stat_item item) +{ + long x = atomic_long_read(&zone->vm_numa_stat[item]); + + return x; +} +#endif /* CONFIG_NUMA */ + static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { @@ -194,8 +219,10 @@ static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat, #ifdef CONFIG_NUMA +extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item); extern unsigned long sum_zone_node_page_state(int node, - enum zone_stat_item item); + enum zone_stat_item item); +extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); #else -- cgit v1.2.3 From 1d90ca897cb05cf38bd62f36756d219e02913b7d Mon Sep 17 00:00:00 2001 From: Kemi Wang Date: Fri, 8 Sep 2017 16:12:52 -0700 Subject: mm: update NUMA counter threshold size There is significant overhead in cache bouncing caused by zone counters (NUMA associated counters) update in parallel in multi-threaded page allocation (suggested by Dave Hansen). This patch updates NUMA counter threshold to a fixed size of MAX_U16 - 2, as a small threshold greatly increases the update frequency of the global counter from local per cpu counter(suggested by Ying Huang). The rationality is that these statistics counters don't affect the kernel's decision, unlike other VM counters, so it's not a problem to use a large threshold. With this patchset, we see 31.3% drop of CPU cycles(537-->369) for per single page allocation and reclaim on Jesper's page_bench03 benchmark. Benchmark provided by Jesper D Brouer(increase loop times to 10000000): https://github.com/netoptimizer/prototype-kernel/tree/master/kernel/mm/ bench Threshold CPU cycles Throughput(88 threads) 32 799 241760478 64 640 301628829 125 537 358906028 <==> system by default (base) 256 468 412397590 512 428 450550704 4096 399 482520943 20000 394 489009617 30000 395 488017817 65533 369(-31.3%) 521661345(+45.3%) <==> with this patchset N/A 342(-36.3%) 562900157(+56.8%) <==> disable zone_statistics Link: http://lkml.kernel.org/r/1503568801-21305-3-git-send-email-kemi.wang@intel.com Signed-off-by: Kemi Wang Reported-by: Jesper Dangaard Brouer Suggested-by: Dave Hansen Suggested-by: Ying Huang Acked-by: Mel Gorman Cc: Aaron Lu Cc: Andi Kleen Cc: Christopher Lameter Cc: Johannes Weiner Cc: Michal Hocko Cc: Tim Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index e65d91c02e30..356a814e7c8e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -282,8 +282,7 @@ struct per_cpu_pageset { struct per_cpu_pages pcp; #ifdef CONFIG_NUMA s8 expire; - s8 numa_stat_threshold; - s8 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; + u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS]; #endif #ifdef CONFIG_SMP s8 stat_threshold; -- cgit v1.2.3 From 638032224ed762a29baca1fc37f1168efc2554ae Mon Sep 17 00:00:00 2001 From: Kemi Wang Date: Fri, 8 Sep 2017 16:12:55 -0700 Subject: mm: consider the number in local CPUs when reading NUMA stats To avoid deviation, the per cpu number of NUMA stats in vm_numa_stat_diff[] is included when a user *reads* the NUMA stats. Since NUMA stats does not be read by users frequently, and kernel does not need it to make a decision, it will not be a problem to make the readers more expensive. Link: http://lkml.kernel.org/r/1503568801-21305-4-git-send-email-kemi.wang@intel.com Signed-off-by: Kemi Wang Reported-by: Jesper Dangaard Brouer Acked-by: Mel Gorman Cc: Aaron Lu Cc: Andi Kleen Cc: Christopher Lameter Cc: Dave Hansen Cc: Johannes Weiner Cc: Michal Hocko Cc: Tim Chen Cc: Ying Huang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 9ac82e29948f..ade7cb5f1359 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -125,10 +125,14 @@ static inline unsigned long global_numa_state(enum numa_stat_item item) return x; } -static inline unsigned long zone_numa_state(struct zone *zone, +static inline unsigned long zone_numa_state_snapshot(struct zone *zone, enum numa_stat_item item) { long x = atomic_long_read(&zone->vm_numa_stat[item]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; return x; } -- cgit v1.2.3 From 855d97657d4d335970622f0d95ca4966d3f77ee7 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 8 Sep 2017 16:13:38 -0700 Subject: proc: uninline proc_create() Save some code from ~320 invocations all clearing last argument. add/remove: 3/0 grow/shrink: 0/158 up/down: 45/-702 (-657) function old new delta proc_create - 17 +17 __ksymtab_proc_create - 16 +16 __kstrtab_proc_create - 12 +12 yam_init_driver 301 298 -3 ... cifs_proc_init 249 228 -21 via_fb_pci_probe 2304 2280 -24 Link: http://lkml.kernel.org/r/20170819094702.GA27864@avx2 Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/proc_fs.h | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 2d2bf592d9db..76124dd4e36d 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -28,13 +28,7 @@ extern struct proc_dir_entry *proc_create_data(const char *, umode_t, const struct file_operations *, void *); -static inline struct proc_dir_entry *proc_create( - const char *name, umode_t mode, struct proc_dir_entry *parent, - const struct file_operations *proc_fops) -{ - return proc_create_data(name, mode, parent, proc_fops, NULL); -} - +struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct file_operations *proc_fops); extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); extern void *PDE_DATA(const struct inode *); -- cgit v1.2.3 From 604df322363e5770735df85368f83cac4a955a24 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 8 Sep 2017 16:13:45 -0700 Subject: linux/kernel.h: move DIV_ROUND_DOWN_ULL() macro This macro is useful to avoid link error on 32-bit systems. We have the same definition in two drivers, so move it to include/linux/kernel.h While we are here, refactor DIV_ROUND_UP_ULL() by using DIV_ROUND_DOWN_ULL(). Link: http://lkml.kernel.org/r/1500945156-12907-1-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Acked-by: Mark Brown Cc: Cyrille Pitchen Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: Liam Girdwood Cc: Boris Brezillon Cc: Marek Vasut Cc: Brian Norris Cc: Richard Weinberger Cc: David Woodhouse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 6607225d0ea4..0ad4c3044cf9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -78,8 +78,11 @@ #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP -#define DIV_ROUND_UP_ULL(ll,d) \ - ({ unsigned long long _tmp = (ll)+(d)-1; do_div(_tmp, d); _tmp; }) + +#define DIV_ROUND_DOWN_ULL(ll, d) \ + ({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; }) + +#define DIV_ROUND_UP_ULL(ll, d) DIV_ROUND_DOWN_ULL((ll) + (d) - 1, (d)) #if BITS_PER_LONG == 32 # define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d) -- cgit v1.2.3 From 3b3c4babd898715926d24ae10aa64778ace33aae Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 8 Sep 2017 16:13:48 -0700 Subject: lib/string.c: add multibyte memset functions Patch series "Multibyte memset variations", v4. A relatively common idiom we're missing is a function to fill an area of memory with a pattern which is larger than a single byte. I first noticed this with a zram patch which wanted to fill a page with an 'unsigned long' value. There turn out to be quite a few places in the kernel which can benefit from using an optimised function rather than a loop; sometimes text size, sometimes speed, and sometimes both. The optimised PowerPC version (not included here) improves performance by about 30% on POWER8 on just the raw memset_l(). Most of the extra lines of code come from the three testcases I added. This patch (of 8): memset16(), memset32() and memset64() are like memset(), but allow the caller to fill the destination with a value larger than a single byte. memset_l() and memset_p() allow the caller to use unsigned long and pointer values respectively. Link: http://lkml.kernel.org/r/20170720184539.31609-2-willy@infradead.org Signed-off-by: Matthew Wilcox Cc: "H. Peter Anvin" Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: David Miller Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Minchan Kim Cc: Ralf Baechle Cc: Richard Henderson Cc: Russell King Cc: Sam Ravnborg Cc: Sergey Senozhatsky Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index a467e617eeb0..c8bdafffd2f0 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -99,6 +99,36 @@ extern __kernel_size_t strcspn(const char *,const char *); #ifndef __HAVE_ARCH_MEMSET extern void * memset(void *,int,__kernel_size_t); #endif + +#ifndef __HAVE_ARCH_MEMSET16 +extern void *memset16(uint16_t *, uint16_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET32 +extern void *memset32(uint32_t *, uint32_t, __kernel_size_t); +#endif + +#ifndef __HAVE_ARCH_MEMSET64 +extern void *memset64(uint64_t *, uint64_t, __kernel_size_t); +#endif + +static inline void *memset_l(unsigned long *p, unsigned long v, + __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, v, n); + else + return memset64((uint64_t *)p, v, n); +} + +static inline void *memset_p(void **p, void *v, __kernel_size_t n) +{ + if (BITS_PER_LONG == 32) + return memset32((uint32_t *)p, (uintptr_t)v, n); + else + return memset64((uint64_t *)p, (uintptr_t)v, n); +} + #ifndef __HAVE_ARCH_MEMCPY extern void * memcpy(void *,const void *,__kernel_size_t); #endif -- cgit v1.2.3 From ac036f9570a2d318b7d8dbbdbf0e269d7cc68cef Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 8 Sep 2017 16:14:15 -0700 Subject: vga: optimise console scrolling Where possible, call memset16(), memmove() or memcpy() instead of using open-coded loops. I don't like the calling convention that uses a byte count instead of a count of u16s, but it's a little late to change that. Reduces code size of fbcon.o by almost 400 bytes on my laptop build. [akpm@linux-foundation.org: fix build] Link: http://lkml.kernel.org/r/20170720184539.31609-9-willy@infradead.org Signed-off-by: Matthew Wilcox Cc: Ralf Baechle Cc: David Miller Cc: Sam Ravnborg Cc: "H. Peter Anvin" Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Minchan Kim Cc: Richard Henderson Cc: Russell King Cc: Sergey Senozhatsky Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vt_buffer.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index f38c10ba3ff5..30b6e0d2a942 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -13,6 +13,7 @@ #ifndef _LINUX_VT_BUFFER_H_ #define _LINUX_VT_BUFFER_H_ +#include #if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_MDA_CONSOLE) #include @@ -26,24 +27,33 @@ #ifndef VT_BUF_HAVE_MEMSETW static inline void scr_memsetw(u16 *s, u16 c, unsigned int count) { +#ifdef VT_BUF_HAVE_RW count /= 2; while (count--) scr_writew(c, s++); +#else + memset16(s, c, count / 2); +#endif } #endif #ifndef VT_BUF_HAVE_MEMCPYW static inline void scr_memcpyw(u16 *d, const u16 *s, unsigned int count) { +#ifdef VT_BUF_HAVE_RW count /= 2; while (count--) scr_writew(scr_readw(s++), d++); +#else + memcpy(d, s, count); +#endif } #endif #ifndef VT_BUF_HAVE_MEMMOVEW static inline void scr_memmovew(u16 *d, const u16 *s, unsigned int count) { +#ifdef VT_BUF_HAVE_RW if (d < s) scr_memcpyw(d, s, count); else { @@ -53,6 +63,9 @@ static inline void scr_memmovew(u16 *d, const u16 *s, unsigned int count) while (count--) scr_writew(scr_readw(--s), --d); } +#else + memmove(d, s, count); +#endif } #endif -- cgit v1.2.3 From 9b130ad5bb8255ee8534d92d67e12b2a4887eacb Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 8 Sep 2017 16:14:18 -0700 Subject: treewide: make "nr_cpu_ids" unsigned First, number of CPUs can't be negative number. Second, different signnnedness leads to suboptimal code in the following cases: 1) kmalloc(nr_cpu_ids * sizeof(X)); "int" has to be sign extended to size_t. 2) while (loff_t *pos < nr_cpu_ids) MOVSXD is 1 byte longed than the same MOV. Other cases exist as well. Basically compiler is told that nr_cpu_ids can't be negative which can't be deduced if it is "int". Code savings on allyesconfig kernel: -3KB add/remove: 0/0 grow/shrink: 25/264 up/down: 261/-3631 (-3370) function old new delta coretemp_cpu_online 450 512 +62 rcu_init_one 1234 1272 +38 pci_device_probe 374 399 +25 ... pgdat_reclaimable_pages 628 556 -72 select_fallback_rq 446 369 -77 task_numa_find_cpu 1923 1807 -116 Link: http://lkml.kernel.org/r/20170819114959.GA30580@avx2 Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 4bf4479a3a80..68c5a8290275 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -32,15 +32,15 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if NR_CPUS == 1 -#define nr_cpu_ids 1 +#define nr_cpu_ids 1U #else -extern int nr_cpu_ids; +extern unsigned int nr_cpu_ids; #endif #ifdef CONFIG_CPUMASK_OFFSTACK /* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, * not all bits may be allocated. */ -#define nr_cpumask_bits ((unsigned int)nr_cpu_ids) +#define nr_cpumask_bits nr_cpu_ids #else #define nr_cpumask_bits ((unsigned int)NR_CPUS) #endif -- cgit v1.2.3 From e9ef073a0796e46c24f037237291efe56fc28ad9 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Fri, 8 Sep 2017 16:14:29 -0700 Subject: include: warn for inconsistent endian config definition We have seen some generic code use config parameter CONFIG_CPU_BIG_ENDIAN to decide the endianness. Here are the few examples. include/asm-generic/qrwlock.h drivers/of/base.c drivers/of/fdt.c drivers/tty/serial/earlycon.c drivers/tty/serial/serial_core.c Display warning if CPU_BIG_ENDIAN is not defined on big endian architecture and also warn if it defined on little endian architectures. Here is our original discussion https://lkml.org/lkml/2017/5/24/620 Link: http://lkml.kernel.org/r/1499358861-179979-4-git-send-email-babu.moger@oracle.com Signed-off-by: Babu Moger Suggested-by: Arnd Bergmann Acked-by: Geert Uytterhoeven Cc: "James E.J. Bottomley" Cc: Alexander Viro Cc: David S. Miller Cc: Greg KH Cc: Helge Deller Cc: Ingo Molnar Cc: Jonas Bonn Cc: Max Filippov Cc: Michael Ellerman (powerpc) Cc: Michal Simek Cc: Peter Zijlstra Cc: Stafford Horne Cc: Stefan Kristiansson Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/byteorder/big_endian.h | 4 ++++ include/linux/byteorder/little_endian.h | 4 ++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/byteorder/big_endian.h b/include/linux/byteorder/big_endian.h index 392041475c72..ffd215988392 100644 --- a/include/linux/byteorder/big_endian.h +++ b/include/linux/byteorder/big_endian.h @@ -3,5 +3,9 @@ #include +#ifndef CONFIG_CPU_BIG_ENDIAN +#warning inconsistent configuration, needs CONFIG_CPU_BIG_ENDIAN +#endif + #include #endif /* _LINUX_BYTEORDER_BIG_ENDIAN_H */ diff --git a/include/linux/byteorder/little_endian.h b/include/linux/byteorder/little_endian.h index 08057377aa23..ba910bb9aad0 100644 --- a/include/linux/byteorder/little_endian.h +++ b/include/linux/byteorder/little_endian.h @@ -3,5 +3,9 @@ #include +#ifdef CONFIG_CPU_BIG_ENDIAN +#warning inconsistent configuration, CONFIG_CPU_BIG_ENDIAN is set +#endif + #include #endif /* _LINUX_BYTEORDER_LITTLE_ENDIAN_H */ -- cgit v1.2.3 From c32ee3d9abd284b4fcaacc250b101f93829c7bae Mon Sep 17 00:00:00 2001 From: Matthias Kaehlcke Date: Fri, 8 Sep 2017 16:14:33 -0700 Subject: bitops: avoid integer overflow in GENMASK(_ULL) GENMASK(_ULL) performs a left-shift of ~0UL(L), which technically results in an integer overflow. clang raises a warning if the overflow occurs in a preprocessor expression. Clear the low-order bits through a substraction instead of the left-shift to avoid the overflow. (akpm: no change in .text size in my testing) Link: http://lkml.kernel.org/r/20170803212020.24939-1-mka@chromium.org Signed-off-by: Matthias Kaehlcke Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index a83c822c35c2..8fbe259b197c 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -19,10 +19,11 @@ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. */ #define GENMASK(h, l) \ - (((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) #define GENMASK_ULL(h, l) \ - (((~0ULL) << (l)) & (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + (((~0ULL) - (1ULL << (l)) + 1) & \ + (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); -- cgit v1.2.3 From cd9e61ed1eebbcd5dfad59475d41ec58d9b64b6a Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 8 Sep 2017 16:14:36 -0700 Subject: rbtree: cache leftmost node internally Patch series "rbtree: Cache leftmost node internally", v4. A series to extending rbtrees to internally cache the leftmost node such that we can have fast overlap check optimization for all interval tree users[1]. The benefits of this series are that: (i) Unify users that do internal leftmost node caching. (ii) Optimize all interval tree users. (iii) Convert at least two new users (epoll and procfs) to the new interface. This patch (of 16): Red-black tree semantics imply that nodes with smaller or greater (or equal for duplicates) keys always be to the left and right, respectively. For the kernel this is extremely evident when considering our rb_first() semantics. Enabling lookups for the smallest node in the tree in O(1) can save a good chunk of cycles in not having to walk down the tree each time. To this end there are a few core users that explicitly do this, such as the scheduler and rtmutexes. There is also the desire for interval trees to have this optimization allowing faster overlap checking. This patch introduces a new 'struct rb_root_cached' which is just the root with a cached pointer to the leftmost node. The reason why the regular rb_root was not extended instead of adding a new structure was that this allows the user to have the choice between memory footprint and actual tree performance. The new wrappers on top of the regular rb_root calls are: - rb_first_cached(cached_root) -- which is a fast replacement for rb_first. - rb_insert_color_cached(node, cached_root, new) - rb_erase_cached(node, cached_root) In addition, augmented cached interfaces are also added for basic insertion and deletion operations; which becomes important for the interval tree changes. With the exception of the inserts, which adds a bool for updating the new leftmost, the interfaces are kept the same. To this end, porting rb users to the cached version becomes really trivial, and keeping current rbtree semantics for users that don't care about the optimization requires zero overhead. Link: http://lkml.kernel.org/r/20170719014603.19029-2-dave@stgolabs.net Signed-off-by: Davidlohr Bueso Reviewed-by: Jan Kara Acked-by: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rbtree.h | 21 +++++++++++++++++++++ include/linux/rbtree_augmented.h | 33 ++++++++++++++++++++++++++++++--- 2 files changed, 51 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index e585018498d5..d574361943ea 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -44,10 +44,25 @@ struct rb_root { struct rb_node *rb_node; }; +/* + * Leftmost-cached rbtrees. + * + * We do not cache the rightmost node based on footprint + * size vs number of potential users that could benefit + * from O(1) rb_last(). Just not worth it, users that want + * this feature can always implement the logic explicitly. + * Furthermore, users that want to cache both pointers may + * find it a bit asymmetric, but that's ok. + */ +struct rb_root_cached { + struct rb_root rb_root; + struct rb_node *rb_leftmost; +}; #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define RB_ROOT (struct rb_root) { NULL, } +#define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) @@ -69,6 +84,12 @@ extern struct rb_node *rb_prev(const struct rb_node *); extern struct rb_node *rb_first(const struct rb_root *); extern struct rb_node *rb_last(const struct rb_root *); +extern void rb_insert_color_cached(struct rb_node *, + struct rb_root_cached *, bool); +extern void rb_erase_cached(struct rb_node *node, struct rb_root_cached *); +/* Same as rb_first(), but O(1) */ +#define rb_first_cached(root) (root)->rb_leftmost + /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 9702b6e183bc..6bfd2b581f75 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -41,7 +41,9 @@ struct rb_augment_callbacks { void (*rotate)(struct rb_node *old, struct rb_node *new); }; -extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, +extern void __rb_insert_augmented(struct rb_node *node, + struct rb_root *root, + bool newleft, struct rb_node **leftmost, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. @@ -57,7 +59,16 @@ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - __rb_insert_augmented(node, root, augment->rotate); + __rb_insert_augmented(node, root, false, NULL, augment->rotate); +} + +static inline void +rb_insert_augmented_cached(struct rb_node *node, + struct rb_root_cached *root, bool newleft, + const struct rb_augment_callbacks *augment) +{ + __rb_insert_augmented(node, &root->rb_root, + newleft, &root->rb_leftmost, augment->rotate); } #define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield, \ @@ -150,6 +161,7 @@ extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, + struct rb_node **leftmost, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; @@ -157,6 +169,9 @@ __rb_erase_augmented(struct rb_node *node, struct rb_root *root, struct rb_node *parent, *rebalance; unsigned long pc; + if (leftmost && node == *leftmost) + *leftmost = rb_next(node); + if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) @@ -256,9 +271,21 @@ static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { - struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); + struct rb_node *rebalance = __rb_erase_augmented(node, root, + NULL, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } +static __always_inline void +rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, + const struct rb_augment_callbacks *augment) +{ + struct rb_node *rebalance = __rb_erase_augmented(node, &root->rb_root, + &root->rb_leftmost, + augment); + if (rebalance) + __rb_erase_color(rebalance, &root->rb_root, augment->rotate); +} + #endif /* _LINUX_RBTREE_AUGMENTED_H */ -- cgit v1.2.3 From a23ba907d5e65d6aeea3e59c82fda9cd206a7aad Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 8 Sep 2017 16:15:01 -0700 Subject: locking/rtmutex: replace top-waiter and pi_waiters leftmost caching ... with the generic rbtree flavor instead. No changes in semantics whatsoever. Link: http://lkml.kernel.org/r/20170719014603.19029-10-dave@stgolabs.net Signed-off-by: Davidlohr Bueso Acked-by: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/init_task.h | 5 ++--- include/linux/rtmutex.h | 11 +++++------ include/linux/sched.h | 3 +-- 3 files changed, 8 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 0e849715e5be..3c07ace5b431 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -175,9 +175,8 @@ extern struct cred init_cred; #ifdef CONFIG_RT_MUTEXES # define INIT_RT_MUTEXES(tsk) \ - .pi_waiters = RB_ROOT, \ - .pi_top_task = NULL, \ - .pi_waiters_leftmost = NULL, + .pi_waiters = RB_ROOT_CACHED, \ + .pi_top_task = NULL, #else # define INIT_RT_MUTEXES(tsk) #endif diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 44fd002f7cd5..53fcbe9de7fd 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -22,18 +22,17 @@ extern int max_lock_depth; /* for sysctl */ * The rt_mutex structure * * @wait_lock: spinlock to protect the structure - * @waiters: rbtree root to enqueue waiters in priority order - * @waiters_leftmost: top waiter + * @waiters: rbtree root to enqueue waiters in priority order; + * caches top-waiter (leftmost node). * @owner: the mutex owner */ struct rt_mutex { raw_spinlock_t wait_lock; - struct rb_root waiters; - struct rb_node *waiters_leftmost; + struct rb_root_cached waiters; struct task_struct *owner; #ifdef CONFIG_DEBUG_RT_MUTEXES int save_state; - const char *name, *file; + const char *name, *file; int line; void *magic; #endif @@ -84,7 +83,7 @@ do { \ #define __RT_MUTEX_INITIALIZER(mutexname) \ { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ - , .waiters = RB_ROOT \ + , .waiters = RB_ROOT_CACHED \ , .owner = NULL \ __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)} diff --git a/include/linux/sched.h b/include/linux/sched.h index 68b38335d33c..92fb8dd5a9e4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -812,8 +812,7 @@ struct task_struct { #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ - struct rb_root pi_waiters; - struct rb_node *pi_waiters_leftmost; + struct rb_root_cached pi_waiters; /* Updated under owner's pi_lock and rq lock */ struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ -- cgit v1.2.3 From f808c13fd3738948e10196496959871130612b61 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 8 Sep 2017 16:15:08 -0700 Subject: lib/interval_tree: fast overlap detection MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Allow interval trees to quickly check for overlaps to avoid unnecesary tree lookups in interval_tree_iter_first(). As of this patch, all interval tree flavors will require using a 'rb_root_cached' such that we can have the leftmost node easily available. While most users will make use of this feature, those with special functions (in addition to the generic insert, delete, search calls) will avoid using the cached option as they can do funky things with insertions -- for example, vma_interval_tree_insert_after(). [jglisse@redhat.com: fix deadlock from typo vm_lock_anon_vma()] Link: http://lkml.kernel.org/r/20170808225719.20723-1-jglisse@redhat.com Link: http://lkml.kernel.org/r/20170719014603.19029-12-dave@stgolabs.net Signed-off-by: Davidlohr Bueso Signed-off-by: Jérôme Glisse Acked-by: Christian König Acked-by: Peter Zijlstra (Intel) Acked-by: Doug Ledford Acked-by: Michael S. Tsirkin Cc: David Airlie Cc: Jason Wang Cc: Christian Benvenuti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 4 +-- include/linux/interval_tree.h | 8 +++--- include/linux/interval_tree_generic.h | 46 +++++++++++++++++++++++++++-------- include/linux/mm.h | 17 +++++++------ include/linux/rmap.h | 4 ++- 5 files changed, 55 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 509434aaf5a4..6111976848ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -392,7 +392,7 @@ struct address_space { struct radix_tree_root page_tree; /* radix tree of all pages */ spinlock_t tree_lock; /* and lock protecting it */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ - struct rb_root i_mmap; /* tree of private and shared mappings */ + struct rb_root_cached i_mmap; /* tree of private and shared mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ @@ -487,7 +487,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping) */ static inline int mapping_mapped(struct address_space *mapping) { - return !RB_EMPTY_ROOT(&mapping->i_mmap); + return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* diff --git a/include/linux/interval_tree.h b/include/linux/interval_tree.h index 724556aa3c95..202ee1283f4b 100644 --- a/include/linux/interval_tree.h +++ b/include/linux/interval_tree.h @@ -11,13 +11,15 @@ struct interval_tree_node { }; extern void -interval_tree_insert(struct interval_tree_node *node, struct rb_root *root); +interval_tree_insert(struct interval_tree_node *node, + struct rb_root_cached *root); extern void -interval_tree_remove(struct interval_tree_node *node, struct rb_root *root); +interval_tree_remove(struct interval_tree_node *node, + struct rb_root_cached *root); extern struct interval_tree_node * -interval_tree_iter_first(struct rb_root *root, +interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); extern struct interval_tree_node * diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h index 58370e1862ad..f096423c8cbd 100644 --- a/include/linux/interval_tree_generic.h +++ b/include/linux/interval_tree_generic.h @@ -65,11 +65,13 @@ RB_DECLARE_CALLBACKS(static, ITPREFIX ## _augment, ITSTRUCT, ITRB, \ \ /* Insert / remove interval nodes from the tree */ \ \ -ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, struct rb_root *root) \ +ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, \ + struct rb_root_cached *root) \ { \ - struct rb_node **link = &root->rb_node, *rb_parent = NULL; \ + struct rb_node **link = &root->rb_root.rb_node, *rb_parent = NULL; \ ITTYPE start = ITSTART(node), last = ITLAST(node); \ ITSTRUCT *parent; \ + bool leftmost = true; \ \ while (*link) { \ rb_parent = *link; \ @@ -78,18 +80,22 @@ ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, struct rb_root *root) \ parent->ITSUBTREE = last; \ if (start < ITSTART(parent)) \ link = &parent->ITRB.rb_left; \ - else \ + else { \ link = &parent->ITRB.rb_right; \ + leftmost = false; \ + } \ } \ \ node->ITSUBTREE = last; \ rb_link_node(&node->ITRB, rb_parent, link); \ - rb_insert_augmented(&node->ITRB, root, &ITPREFIX ## _augment); \ + rb_insert_augmented_cached(&node->ITRB, root, \ + leftmost, &ITPREFIX ## _augment); \ } \ \ -ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, struct rb_root *root) \ +ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, \ + struct rb_root_cached *root) \ { \ - rb_erase_augmented(&node->ITRB, root, &ITPREFIX ## _augment); \ + rb_erase_augmented_cached(&node->ITRB, root, &ITPREFIX ## _augment); \ } \ \ /* \ @@ -140,15 +146,35 @@ ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last) \ } \ \ ITSTATIC ITSTRUCT * \ -ITPREFIX ## _iter_first(struct rb_root *root, ITTYPE start, ITTYPE last) \ +ITPREFIX ## _iter_first(struct rb_root_cached *root, \ + ITTYPE start, ITTYPE last) \ { \ - ITSTRUCT *node; \ + ITSTRUCT *node, *leftmost; \ \ - if (!root->rb_node) \ + if (!root->rb_root.rb_node) \ return NULL; \ - node = rb_entry(root->rb_node, ITSTRUCT, ITRB); \ + \ + /* \ + * Fastpath range intersection/overlap between A: [a0, a1] and \ + * B: [b0, b1] is given by: \ + * \ + * a0 <= b1 && b0 <= a1 \ + * \ + * ... where A holds the lock range and B holds the smallest \ + * 'start' and largest 'last' in the tree. For the later, we \ + * rely on the root node, which by augmented interval tree \ + * property, holds the largest value in its last-in-subtree. \ + * This allows mitigating some of the tree walk overhead for \ + * for non-intersecting ranges, maintained and consulted in O(1). \ + */ \ + node = rb_entry(root->rb_root.rb_node, ITSTRUCT, ITRB); \ if (node->ITSUBTREE < start) \ return NULL; \ + \ + leftmost = rb_entry(root->rb_leftmost, ITSTRUCT, ITRB); \ + if (ITSTART(leftmost) > last) \ + return NULL; \ + \ return ITPREFIX ## _subtree_search(node, start, last); \ } \ \ diff --git a/include/linux/mm.h b/include/linux/mm.h index 5195e272fc4a..f8c10d336e42 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2034,13 +2034,13 @@ extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t); /* interval_tree.c */ void vma_interval_tree_insert(struct vm_area_struct *node, - struct rb_root *root); + struct rb_root_cached *root); void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, - struct rb_root *root); + struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, - struct rb_root *root); -struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root *root, + struct rb_root_cached *root); +struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, unsigned long start, unsigned long last); @@ -2050,11 +2050,12 @@ struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, vma; vma = vma_interval_tree_iter_next(vma, start, last)) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, - struct rb_root *root); + struct rb_root_cached *root); void anon_vma_interval_tree_remove(struct anon_vma_chain *node, - struct rb_root *root); -struct anon_vma_chain *anon_vma_interval_tree_iter_first( - struct rb_root *root, unsigned long start, unsigned long last); + struct rb_root_cached *root); +struct anon_vma_chain * +anon_vma_interval_tree_iter_first(struct rb_root_cached *root, + unsigned long start, unsigned long last); struct anon_vma_chain *anon_vma_interval_tree_iter_next( struct anon_vma_chain *node, unsigned long start, unsigned long last); #ifdef CONFIG_DEBUG_VM_RB diff --git a/include/linux/rmap.h b/include/linux/rmap.h index f8ca2e74b819..733d3d8181e2 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -55,7 +55,9 @@ struct anon_vma { * is serialized by a system wide lock only visible to * mm_take_all_locks() (mm_all_locks_mutex). */ - struct rb_root rb_root; /* Interval tree of private "related" vmas */ + + /* Interval tree of private "related" vmas */ + struct rb_root_cached rb_root; }; /* -- cgit v1.2.3 From f2686bb48618718c7141f117e2d607594e959bfc Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 8 Sep 2017 16:15:12 -0700 Subject: lib/interval-tree: correct comment wrt generic flavor interval_tree.h _is_ the generic flavor. Link: http://lkml.kernel.org/r/20170719014603.19029-13-dave@stgolabs.net Signed-off-by: Davidlohr Bueso Acked-by: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/interval_tree_generic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h index f096423c8cbd..1f97ce26cccc 100644 --- a/include/linux/interval_tree_generic.h +++ b/include/linux/interval_tree_generic.h @@ -33,7 +33,7 @@ * ITSTATIC: 'static' or empty * ITPREFIX: prefix to use for the inline tree definitions * - * Note - before using this, please consider if non-generic version + * Note - before using this, please consider if generic version * (interval_tree.h) would work for you... */ -- cgit v1.2.3 From 60ef690018b262ddcd0d51edf10e40710deb9c9f Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Fri, 8 Sep 2017 16:15:41 -0700 Subject: bitmap: introduce BITMAP_FROM_U64() The macro is the compile-time analogue of bitmap_from_u64() with the same purpose: convert the 64-bit number to the properly ordered pair of 32-bit parts, suitable for filling the bitmap in 32-bit BE environment. Use it to make test_bitmap_parselist() correct for 32-bit BE ABIs. Tested on BE mips/qemu. [akpm@linux-foundation.org: tweak code comment] Link: http://lkml.kernel.org/r/20170810172916.24144-1-ynorov@caviumnetworks.com Signed-off-by: Yury Norov Cc: Noam Camus Cc: Rasmus Villemoes Cc: Matthew Wilcox Cc: Mauro Carvalho Chehab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 5797ca6fdfe2..700cf5f67118 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -360,6 +360,38 @@ static inline int bitmap_parse(const char *buf, unsigned int buflen, return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits); } +/* + * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. + * + * Linux bitmaps are internally arrays of unsigned longs, i.e. 32-bit + * integers in 32-bit environment, and 64-bit integers in 64-bit one. + * + * There are four combinations of endianness and length of the word in linux + * ABIs: LE64, BE64, LE32 and BE32. + * + * On 64-bit kernels 64-bit LE and BE numbers are naturally ordered in + * bitmaps and therefore don't require any special handling. + * + * On 32-bit kernels 32-bit LE ABI orders lo word of 64-bit number in memory + * prior to hi, and 32-bit BE orders hi word prior to lo. The bitmap on the + * other hand is represented as an array of 32-bit words and the position of + * bit N may therefore be calculated as: word #(N/32) and bit #(N%32) in that + * word. For example, bit #42 is located at 10th position of 2nd word. + * It matches 32-bit LE ABI, and we can simply let the compiler store 64-bit + * values in memory as it usually does. But for BE we need to swap hi and lo + * words manually. + * + * With all that, the macro BITMAP_FROM_U64() does explicit reordering of hi and + * lo parts of u64. For LE32 it does nothing, and for BE environment it swaps + * hi and lo words, as is expected by bitmap. + */ +#if __BITS_PER_LONG == 64 +#define BITMAP_FROM_U64(n) (n) +#else +#define BITMAP_FROM_U64(n) ((unsigned long) ((u64)(n) & ULONG_MAX)), \ + ((unsigned long) ((u64)(n) >> 32)) +#endif + /* * bitmap_from_u64 - Check and swap words within u64. * @mask: source bitmap -- cgit v1.2.3 From 895a60728f83684e738cce34d7d4e64631505ae4 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 8 Sep 2017 16:15:45 -0700 Subject: lib/rhashtable: fix comment on locks_mul default value As of commit 4cf0b354d92 ("rhashtable: avoid large lock-array allocations"), the default value for the locks multiplier was reduced from 128 to 32. Update the header file to reflect this. Link: http://lkml.kernel.org/r/20170815215401.30745-1-dave@stgolabs.net Signed-off-by: Davidlohr Bueso Cc: Florian Westphal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rhashtable.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 7d56a7ea2b2e..361c08e35dbc 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -127,7 +127,7 @@ struct rhashtable; * @head_offset: Offset of rhash_head in struct to be hashed * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking - * @locks_mul: Number of bucket locks to allocate per cpu (default: 128) + * @locks_mul: Number of bucket locks to allocate per cpu (default: 32) * @automatic_shrinking: Enable automatic shrinking of tables * @nulls_base: Base value to generate nulls marker * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash) -- cgit v1.2.3 From 42f46148217865a545e129612075f3d828a2c4e4 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Fri, 8 Sep 2017 16:16:24 -0700 Subject: autofs: fix AT_NO_AUTOMOUNT not being honored The fstatat(2) and statx() calls can pass the flag AT_NO_AUTOMOUNT which is meant to clear the LOOKUP_AUTOMOUNT flag and prevent triggering of an automount by the call. But this flag is unconditionally cleared for all stat family system calls except statx(). stat family system calls have always triggered mount requests for the negative dentry case in follow_automount() which is intended but prevents the fstatat(2) and statx() AT_NO_AUTOMOUNT case from being handled. In order to handle the AT_NO_AUTOMOUNT for both system calls the negative dentry case in follow_automount() needs to be changed to return ENOENT when the LOOKUP_AUTOMOUNT flag is clear (and the other required flags are clear). AFAICT this change doesn't have any noticable side effects and may, in some use cases (although I didn't see it in testing) prevent unnecessary callbacks to the automount daemon. It's also possible that a stat family call has been made with a path that is in the process of being mounted by some other process. But stat family calls should return the automount state of the path as it is "now" so it shouldn't wait for mount completion. This is the same semantic as the positive dentry case already handled. Link: http://lkml.kernel.org/r/150216641255.11652.4204561328197919771.stgit@pluto.themaw.net Fixes: deccf497d804a4c5fca ("Make stat/lstat/fstatat pass AT_NO_AUTOMOUNT to vfs_statx()") Signed-off-by: Ian Kent Cc: David Howells Cc: Colin Walters Cc: Ondrej Holy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 6111976848ff..2d0e6748e46e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3043,8 +3043,7 @@ static inline int vfs_lstat(const char __user *name, struct kstat *stat) static inline int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags) { - return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, - stat, STATX_BASIC_STATS); + return vfs_statx(dfd, filename, flags, stat, STATX_BASIC_STATS); } static inline int vfs_fstat(int fd, struct kstat *stat) { -- cgit v1.2.3 From c1f3fa2a4fde2818623b42e3f749bd478be5dec7 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Fri, 8 Sep 2017 16:17:08 -0700 Subject: kmod: split off umh headers into its own file In the future usermode helper users do not need to carry in all the of kmod headers declarations. Since kmod.h still includes umh.h this change has no functional changes, each umh user can be cleaned up separately later and with time. Link: http://lkml.kernel.org/r/20170810180618.22457-4-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Cc: Kees Cook Cc: Dmitry Torokhov Cc: Jessica Yu Cc: Rusty Russell Cc: Michal Marek Cc: Petr Mladek Cc: Miroslav Benes Cc: Josh Poimboeuf Cc: Guenter Roeck Cc: "Eric W. Biederman" Cc: Matt Redfearn Cc: Dan Carpenter Cc: Colin Ian King Cc: Daniel Mentz Cc: David Binderman Cc: Greg Kroah-Hartman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmod.h | 60 +-------------------------------------------- include/linux/umh.h | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+), 59 deletions(-) create mode 100644 include/linux/umh.h (limited to 'include/linux') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 655082c88fd9..40c89ad4bea6 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -19,6 +19,7 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ +#include #include #include #include @@ -44,63 +45,4 @@ static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; #define try_then_request_module(x, mod...) (x) #endif - -struct cred; -struct file; - -#define UMH_NO_WAIT 0 /* don't wait at all */ -#define UMH_WAIT_EXEC 1 /* wait for the exec, but not the process */ -#define UMH_WAIT_PROC 2 /* wait for the process to complete */ -#define UMH_KILLABLE 4 /* wait for EXEC/PROC killable */ - -struct subprocess_info { - struct work_struct work; - struct completion *complete; - const char *path; - char **argv; - char **envp; - int wait; - int retval; - int (*init)(struct subprocess_info *info, struct cred *new); - void (*cleanup)(struct subprocess_info *info); - void *data; -} __randomize_layout; - -extern int -call_usermodehelper(const char *path, char **argv, char **envp, int wait); - -extern struct subprocess_info * -call_usermodehelper_setup(const char *path, char **argv, char **envp, - gfp_t gfp_mask, - int (*init)(struct subprocess_info *info, struct cred *new), - void (*cleanup)(struct subprocess_info *), void *data); - -extern int -call_usermodehelper_exec(struct subprocess_info *info, int wait); - -extern struct ctl_table usermodehelper_table[]; - -enum umh_disable_depth { - UMH_ENABLED = 0, - UMH_FREEZING, - UMH_DISABLED, -}; - -extern int __usermodehelper_disable(enum umh_disable_depth depth); -extern void __usermodehelper_set_disable_depth(enum umh_disable_depth depth); - -static inline int usermodehelper_disable(void) -{ - return __usermodehelper_disable(UMH_DISABLED); -} - -static inline void usermodehelper_enable(void) -{ - __usermodehelper_set_disable_depth(UMH_ENABLED); -} - -extern int usermodehelper_read_trylock(void); -extern long usermodehelper_read_lock_wait(long timeout); -extern void usermodehelper_read_unlock(void); - #endif /* __LINUX_KMOD_H__ */ diff --git a/include/linux/umh.h b/include/linux/umh.h new file mode 100644 index 000000000000..244aff638220 --- /dev/null +++ b/include/linux/umh.h @@ -0,0 +1,69 @@ +#ifndef __LINUX_UMH_H__ +#define __LINUX_UMH_H__ + +#include +#include +#include +#include +#include +#include + +struct cred; +struct file; + +#define UMH_NO_WAIT 0 /* don't wait at all */ +#define UMH_WAIT_EXEC 1 /* wait for the exec, but not the process */ +#define UMH_WAIT_PROC 2 /* wait for the process to complete */ +#define UMH_KILLABLE 4 /* wait for EXEC/PROC killable */ + +struct subprocess_info { + struct work_struct work; + struct completion *complete; + const char *path; + char **argv; + char **envp; + int wait; + int retval; + int (*init)(struct subprocess_info *info, struct cred *new); + void (*cleanup)(struct subprocess_info *info); + void *data; +} __randomize_layout; + +extern int +call_usermodehelper(const char *path, char **argv, char **envp, int wait); + +extern struct subprocess_info * +call_usermodehelper_setup(const char *path, char **argv, char **envp, + gfp_t gfp_mask, + int (*init)(struct subprocess_info *info, struct cred *new), + void (*cleanup)(struct subprocess_info *), void *data); + +extern int +call_usermodehelper_exec(struct subprocess_info *info, int wait); + +extern struct ctl_table usermodehelper_table[]; + +enum umh_disable_depth { + UMH_ENABLED = 0, + UMH_FREEZING, + UMH_DISABLED, +}; + +extern int __usermodehelper_disable(enum umh_disable_depth depth); +extern void __usermodehelper_set_disable_depth(enum umh_disable_depth depth); + +static inline int usermodehelper_disable(void) +{ + return __usermodehelper_disable(UMH_DISABLED); +} + +static inline void usermodehelper_enable(void) +{ + __usermodehelper_set_disable_depth(UMH_ENABLED); +} + +extern int usermodehelper_read_trylock(void); +extern long usermodehelper_read_lock_wait(long timeout); +extern void usermodehelper_read_unlock(void); + +#endif /* __LINUX_UMH_H__ */ -- cgit v1.2.3 From f22ef333c32cc683922d7e3361a83ebc31b2ac6d Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 8 Sep 2017 16:17:15 -0700 Subject: cpumask: make cpumask_next() out-of-line Every for_each_XXX_cpu() invocation calls cpumask_next() which is an inline function: static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } However! find_next_bit() is regular out-of-line function which means "nr_cpu_ids" load and increment happen at the caller resulting in a lot of bloat x86_64 defconfig: add/remove: 3/0 grow/shrink: 8/373 up/down: 155/-5668 (-5513) x86_64 allyesconfig-ish: add/remove: 3/1 grow/shrink: 57/634 up/down: 3515/-28177 (-24662) !!! Some archs redefine find_next_bit() but it is OK: m68k inline but SMP is not supported arm out-of-line unicore32 out-of-line Function call will happen anyway, so move load and increment into callee. Link: http://lkml.kernel.org/r/20170824230010.GA1593@avx2 Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 68c5a8290275..cd415b733c2a 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -178,20 +178,7 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } -/** - * cpumask_next - get the next cpu in a cpumask - * @n: the cpu prior to the place to search (ie. return will be > @n) - * @srcp: the cpumask pointer - * - * Returns >= nr_cpu_ids if no further cpus set. - */ -static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) -{ - /* -1 is a legal arg here. */ - if (n != -1) - cpumask_check(n); - return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); -} +unsigned int cpumask_next(int n, const struct cpumask *srcp); /** * cpumask_next_zero - get the next unset cpu in a cpumask -- cgit v1.2.3 From a2d818030135c293f878fbb772cf40e7a14c5acc Mon Sep 17 00:00:00 2001 From: "Robert P. J. Day" Date: Fri, 8 Sep 2017 16:17:19 -0700 Subject: drivers/pps: aesthetic tweaks to PPS-related content Collection of aesthetic adjustments to various PPS-related files, directories and Documentation, some quite minor just for the sake of consistency, including: * Updated example of pps device tree node (courtesy Rodolfo G.) * "PPS-API" -> "PPS API" * "pps_source_info_s" -> "pps_source_info" * "ktimer driver" -> "pps-ktimer driver" * "ppstest /dev/pps0" -> "ppstest /dev/pps1" to match example * Add missing PPS-related entries to MAINTAINERS file * Other trivialities Link: http://lkml.kernel.org/r/alpine.LFD.2.20.1708261048220.8106@localhost.localdomain Signed-off-by: Robert P. J. Day Acked-by: Rodolfo Giometti Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pps-gpio.h | 2 +- include/linux/pps_kernel.h | 16 +++++++--------- 2 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pps-gpio.h b/include/linux/pps-gpio.h index 0035abe41b9a..56f35dd3d01d 100644 --- a/include/linux/pps-gpio.h +++ b/include/linux/pps-gpio.h @@ -29,4 +29,4 @@ struct pps_gpio_platform_data { const char *gpio_label; }; -#endif +#endif /* _PPS_GPIO_H */ diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 35ac903956c7..80a980cc8d95 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -22,7 +22,6 @@ #define LINUX_PPS_KERNEL_H #include - #include #include #include @@ -35,9 +34,9 @@ struct pps_device; /* The specific PPS source info */ struct pps_source_info { - char name[PPS_MAX_NAME_LEN]; /* simbolic name */ + char name[PPS_MAX_NAME_LEN]; /* symbolic name */ char path[PPS_MAX_NAME_LEN]; /* path of connected device */ - int mode; /* PPS's allowed mode */ + int mode; /* PPS allowed mode */ void (*echo)(struct pps_device *pps, int event, void *data); /* PPS echo function */ @@ -57,10 +56,10 @@ struct pps_event_time { struct pps_device { struct pps_source_info info; /* PSS source info */ - struct pps_kparams params; /* PPS's current params */ + struct pps_kparams params; /* PPS current params */ - __u32 assert_sequence; /* PPS' assert event seq # */ - __u32 clear_sequence; /* PPS' clear event seq # */ + __u32 assert_sequence; /* PPS assert event seq # */ + __u32 clear_sequence; /* PPS clear event seq # */ struct pps_ktime assert_tu; struct pps_ktime clear_tu; int current_mode; /* PPS mode at event time */ @@ -69,7 +68,7 @@ struct pps_device { wait_queue_head_t queue; /* PPS event queue */ unsigned int id; /* PPS source unique ID */ - void const *lookup_cookie; /* pps_lookup_dev only */ + void const *lookup_cookie; /* For pps_lookup_dev() only */ struct cdev cdev; struct device *dev; struct fasync_struct *async_queue; /* fasync method */ @@ -101,7 +100,7 @@ extern struct pps_device *pps_register_source( extern void pps_unregister_source(struct pps_device *pps); extern void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, void *data); -/* Look up a pps device by magic cookie */ +/* Look up a pps_device by magic cookie */ struct pps_device *pps_lookup_dev(void const *cookie); static inline void timespec_to_pps_ktime(struct pps_ktime *kt, @@ -132,4 +131,3 @@ static inline void pps_sub_ts(struct pps_event_time *ts, struct timespec64 delta } #endif /* LINUX_PPS_KERNEL_H */ - -- cgit v1.2.3 From a2e0602c36ed9fe042714694dd5a889ecd8cb556 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Fri, 8 Sep 2017 16:17:38 -0700 Subject: ipc: convert ipc_namespace.count from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Link: http://lkml.kernel.org/r/1499417992-3238-2-git-send-email-elena.reshetova@intel.com Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Cc: Peter Zijlstra Cc: Greg Kroah-Hartman Cc: "Eric W. Biederman" Cc: Ingo Molnar Cc: Alexey Dobriyan Cc: Serge Hallyn Cc: Cc: Davidlohr Bueso Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 65327ee0936b..e81445cc7c57 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -7,6 +7,7 @@ #include #include #include +#include struct user_namespace; @@ -19,7 +20,7 @@ struct ipc_ids { }; struct ipc_namespace { - atomic_t count; + refcount_t count; struct ipc_ids ids[3]; int sem_ctls[4]; @@ -118,7 +119,7 @@ extern struct ipc_namespace *copy_ipcs(unsigned long flags, static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) { if (ns) - atomic_inc(&ns->count); + refcount_inc(&ns->count); return ns; } -- cgit v1.2.3 From 9405c03ee778cd3e353e55fff6e16dfdd9609c02 Mon Sep 17 00:00:00 2001 From: Elena Reshetova Date: Fri, 8 Sep 2017 16:17:45 -0700 Subject: ipc: convert kern_ipc_perm.refcount from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Link: http://lkml.kernel.org/r/1499417992-3238-4-git-send-email-elena.reshetova@intel.com Signed-off-by: Elena Reshetova Signed-off-by: Hans Liljestrand Signed-off-by: Kees Cook Signed-off-by: David Windsor Cc: Peter Zijlstra Cc: Greg Kroah-Hartman Cc: "Eric W. Biederman" Cc: Ingo Molnar Cc: Alexey Dobriyan Cc: Serge Hallyn Cc: Cc: Davidlohr Bueso Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipc.h b/include/linux/ipc.h index fadd579d577d..ae68980e9d48 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -4,6 +4,7 @@ #include #include #include +#include #define IPCMNI 32768 /* <= MAX_INT limit for ipc arrays (including sysctl changes) */ @@ -22,7 +23,7 @@ struct kern_ipc_perm { void *security; struct rcu_head rcu; - atomic_t refcount; + refcount_t refcount; } ____cacheline_aligned_in_smp __randomize_layout; #endif /* _LINUX_IPC_H */ -- cgit v1.2.3 From 0cfb6aee70bddbef6ec796b255f588ce0e126766 Mon Sep 17 00:00:00 2001 From: Guillaume Knispel Date: Fri, 8 Sep 2017 16:17:55 -0700 Subject: ipc: optimize semget/shmget/msgget for lots of keys MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ipc_findkey() used to scan all objects to look for the wanted key. This is slow when using a high number of keys. This change adds an rhashtable of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n). This change gives a 865% improvement of benchmark reaim.jobs_per_min on a 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1] Other (more micro) benchmark results, by the author: On an i5 laptop, the following loop executed right after a reboot took, without and with this change: for (int i = 0, k=0x424242; i < KEYS; ++i) semget(k++, 1, IPC_CREAT | 0600); total total max single max single KEYS without with call without call with 1 3.5 4.9 µs 3.5 4.9 10 7.6 8.6 µs 3.7 4.7 32 16.2 15.9 µs 4.3 5.3 100 72.9 41.8 µs 3.7 4.7 1000 5,630.0 502.0 µs * * 10000 1,340,000.0 7,240.0 µs * * 31900 17,600,000.0 22,200.0 µs * * *: unreliable measure: high variance The duration for a lookup-only usage was obtained by the same loop once the keys are present: total total max single max single KEYS without with call without call with 1 2.1 2.5 µs 2.1 2.5 10 4.5 4.8 µs 2.2 2.3 32 13.0 10.8 µs 2.3 2.8 100 82.9 25.1 µs * 2.3 1000 5,780.0 217.0 µs * * 10000 1,470,000.0 2,520.0 µs * * 31900 17,400,000.0 7,810.0 µs * * Finally, executing each semget() in a new process gave, when still summing only the durations of these syscalls: creation: total total KEYS without with 1 3.7 5.0 µs 10 32.9 36.7 µs 32 125.0 109.0 µs 100 523.0 353.0 µs 1000 20,300.0 3,280.0 µs 10000 2,470,000.0 46,700.0 µs 31900 27,800,000.0 219,000.0 µs lookup-only: total total KEYS without with 1 2.5 2.7 µs 10 25.4 24.4 µs 32 106.0 72.6 µs 100 591.0 352.0 µs 1000 22,400.0 2,250.0 µs 10000 2,510,000.0 25,700.0 µs 31900 28,200,000.0 115,000.0 µs [1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix Signed-off-by: Guillaume Knispel Reviewed-by: Marc Pardo Cc: Davidlohr Bueso Cc: Kees Cook Cc: Manfred Spraul Cc: Alexey Dobriyan Cc: "Eric W. Biederman" Cc: "Peter Zijlstra (Intel)" Cc: Ingo Molnar Cc: Sebastian Andrzej Siewior Cc: Serge Hallyn Cc: Andrey Vagin Cc: Guillaume Knispel Cc: Marc Pardo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc.h | 3 +++ include/linux/ipc_namespace.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ipc.h b/include/linux/ipc.h index ae68980e9d48..92a2ccff80c5 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -3,6 +3,7 @@ #include #include +#include #include #include @@ -22,6 +23,8 @@ struct kern_ipc_perm { unsigned long seq; void *security; + struct rhash_head khtnode; + struct rcu_head rcu; refcount_t refcount; } ____cacheline_aligned_in_smp __randomize_layout; diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e81445cc7c57..83f0bf7a587d 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -8,15 +8,18 @@ #include #include #include +#include struct user_namespace; struct ipc_ids { int in_use; unsigned short seq; + bool tables_initialized; struct rw_semaphore rwsem; struct idr ipcs_idr; int next_id; + struct rhashtable key_ht; }; struct ipc_namespace { -- cgit v1.2.3 From 5a67da2a71c64daeb456f6f3e87b5c7cecdc5ffa Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 8 Sep 2017 14:00:49 -0700 Subject: bpf: add support for sockmap detach programs The bpf map sockmap supports adding programs via attach commands. This patch adds the detach command to keep the API symmetric and allow users to remove previously added programs. Otherwise the user would have to delete the map and re-add it to get in this state. This also adds a series of additional tests to capture detach operation and also attaching/detaching invalid prog types. API note: socks will run (or not run) programs depending on the state of the map at the time the sock is added. We do not for example walk the map and remove programs from previously attached socks. Acked-by: Daniel Borkmann Signed-off-by: John Fastabend Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c2cb1b5c094e..8390859e79e7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -385,16 +385,16 @@ static inline void __dev_map_flush(struct bpf_map *map) #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); -int sock_map_attach_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); +int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); #else static inline struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) { return NULL; } -static inline int sock_map_attach_prog(struct bpf_map *map, - struct bpf_prog *prog, - u32 type) +static inline int sock_map_prog(struct bpf_map *map, + struct bpf_prog *prog, + u32 type) { return -EOPNOTSUPP; } -- cgit v1.2.3 From c3ca015fab6df124c933b91902f3f2a3473f9da5 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 31 Aug 2017 21:47:43 -0400 Subject: dax: remove the pmem_dax_ops->flush abstraction Commit abebfbe2f731 ("dm: add ->flush() dax operation support") is buggy. A DM device may be composed of multiple underlying devices and all of them need to be flushed. That commit just routes the flush request to the first device and ignores the other devices. It could be fixed by adding more complex logic to the device mapper. But there is only one implementation of the method pmem_dax_ops->flush - that is pmem_dax_flush() - and it calls arch_wb_cache_pmem(). Consequently, we don't need the pmem_dax_ops->flush abstraction at all, we can call arch_wb_cache_pmem() directly from dax_flush() because dax_dev->ops->flush can't ever reach anything different from arch_wb_cache_pmem(). It should be also pointed out that for some uses of persistent memory it is needed to flush only a very small amount of data (such as 1 cacheline), and it would be overkill if we go through that device mapper machinery for a single flushed cache line. Fix this by removing the pmem_dax_ops->flush abstraction and call arch_wb_cache_pmem() directly from dax_flush(). Also, remove the device mapper code that forwards the flushes. Fixes: abebfbe2f731 ("dm: add ->flush() dax operation support") Cc: stable@vger.kernel.org Signed-off-by: Mikulas Patocka Reviewed-by: Dan Williams Signed-off-by: Mike Snitzer --- include/linux/dax.h | 5 +---- include/linux/device-mapper.h | 3 --- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index df97b7af7e2c..0d8f35f6c53d 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -19,8 +19,6 @@ struct dax_operations { /* copy_from_iter: required operation for fs-dax direct-i/o */ size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, struct iov_iter *); - /* flush: optional driver-specific cache management after writes */ - void (*flush)(struct dax_device *, pgoff_t, void *, size_t); }; extern struct attribute_group dax_attribute_group; @@ -84,8 +82,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); -void dax_flush(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, - size_t size); +void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 3b5fdf308148..a5538433c927 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -134,8 +134,6 @@ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); typedef size_t (*dm_dax_copy_from_iter_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); -typedef void (*dm_dax_flush_fn)(struct dm_target *ti, pgoff_t pgoff, void *addr, - size_t size); #define PAGE_SECTORS (PAGE_SIZE / 512) void dm_error(const char *message); @@ -186,7 +184,6 @@ struct target_type { dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; dm_dax_copy_from_iter_fn dax_copy_from_iter; - dm_dax_flush_fn dax_flush; /* For internal device-mapper use. */ struct list_head list; -- cgit v1.2.3 From 044a9df1a7cbb89f48fcc0e9e39997989342966b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 11 Sep 2017 12:09:28 -0400 Subject: nvme-pci: implement the HMB entry number and size limitations Adds support for the new Host Memory Buffer Minimum Descriptor Entry Size and Host Memory Maximum Descriptors Entries field that were added in TP 4002 HMB Enhancements. These allow the controller to advertise limits for the usual number of segments in the host memory buffer, as well as a minimum usable per-segment size. Signed-off-by: Christoph Hellwig Reviewed-by: Keith Busch --- include/linux/nvme.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 5144f9103723..87723c86f136 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -226,7 +226,9 @@ struct nvme_id_ctrl { __le16 mntmt; __le16 mxtmt; __le32 sanicap; - __u8 rsvd332[180]; + __le32 hmminds; + __le16 hmmaxd; + __u8 rsvd338[174]; __u8 sqes; __u8 cqes; __le16 maxcmd; -- cgit v1.2.3 From 1359798f9d4082eb04575efdd19512fbd9c28464 Mon Sep 17 00:00:00 2001 From: Martin Wilck Date: Wed, 6 Sep 2017 14:36:57 +0200 Subject: string.h: un-fortify memcpy_and_pad The way I'd implemented the new helper memcpy_and_pad with __FORTIFY_INLINE caused compiler warnings for certain kernel configurations. This helper is only used in a single place at this time, and thus doesn't benefit much from fortification. So simplify the code by dropping fortification support for now. Fixes: 01f33c336e2d "string.h: add memcpy_and_pad()" Signed-off-by: Martin Wilck Acked-by: Arnd Bergmann Signed-off-by: Christoph Hellwig --- include/linux/string.h | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index e1eeb0a8a969..54d21783e18d 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -434,20 +434,9 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) * @count: The number of bytes to copy * @pad: Character to use for padding if space is left in destination. */ -__FORTIFY_INLINE void memcpy_and_pad(void *dest, size_t dest_len, - const void *src, size_t count, int pad) +static inline void memcpy_and_pad(void *dest, size_t dest_len, + const void *src, size_t count, int pad) { - size_t dest_size = __builtin_object_size(dest, 0); - size_t src_size = __builtin_object_size(src, 0); - - if (__builtin_constant_p(dest_len) && __builtin_constant_p(count)) { - if (dest_size < dest_len && dest_size < count) - __write_overflow(); - else if (src_size < dest_len && src_size < count) - __read_overflow3(); - } - if (dest_size < dest_len) - fortify_panic(__func__); if (dest_len > count) { memcpy(dest, src, count); memset(dest + count, pad, dest_len - count); -- cgit v1.2.3 From 609320c8a22715b74b39796930c3542719f8ab62 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 7 Sep 2017 18:36:15 -0700 Subject: perf/bpf: fix a clang compilation issue clang does not support variable length array for structure member. It has the following error during compilation: kernel/trace/trace_syscalls.c:568:17: error: fields must have a constant size: 'variable length array in structure' extension will never be supported unsigned long args[sys_data->nb_args]; ^ The fix is to use a fixed array length instead. Reported-by: Nick Desaulniers Signed-off-by: Yonghong Song Signed-off-by: David S. Miller --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 88951b795ee3..95606a2d556f 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -200,6 +200,8 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define SYSCALL_DEFINE5(name, ...) SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) #define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) +#define SYSCALL_DEFINE_MAXARGS 6 + #define SYSCALL_DEFINEx(x, sname, ...) \ SYSCALL_METADATA(sname, x, __VA_ARGS__) \ __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) -- cgit v1.2.3 From 0ee931c4e31a5efb134c76440405e9219f896e33 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 13 Sep 2017 16:28:29 -0700 Subject: mm: treewide: remove GFP_TEMPORARY allocation flag GFP_TEMPORARY was introduced by commit e12ba74d8ff3 ("Group short-lived and reclaimable kernel allocations") along with __GFP_RECLAIMABLE. It's primary motivation was to allow users to tell that an allocation is short lived and so the allocator can try to place such allocations close together and prevent long term fragmentation. As much as this sounds like a reasonable semantic it becomes much less clear when to use the highlevel GFP_TEMPORARY allocation flag. How long is temporary? Can the context holding that memory sleep? Can it take locks? It seems there is no good answer for those questions. The current implementation of GFP_TEMPORARY is basically GFP_KERNEL | __GFP_RECLAIMABLE which in itself is tricky because basically none of the existing caller provide a way to reclaim the allocated memory. So this is rather misleading and hard to evaluate for any benefits. I have checked some random users and none of them has added the flag with a specific justification. I suspect most of them just copied from other existing users and others just thought it might be a good idea to use without any measuring. This suggests that GFP_TEMPORARY just motivates for cargo cult usage without any reasoning. I believe that our gfp flags are quite complex already and especially those with highlevel semantic should be clearly defined to prevent from confusion and abuse. Therefore I propose dropping GFP_TEMPORARY and replace all existing users to simply use GFP_KERNEL. Please note that SLAB users with shrinkers will still get __GFP_RECLAIMABLE heuristic and so they will be placed properly for memory fragmentation prevention. I can see reasons we might want some gfp flag to reflect shorterm allocations but I propose starting from a clear semantic definition and only then add users with proper justification. This was been brought up before LSF this year by Matthew [1] and it turned out that GFP_TEMPORARY really doesn't have a clear semantic. It seems to be a heuristic without any measured advantage for most (if not all) its current users. The follow up discussion has revealed that opinions on what might be temporary allocation differ a lot between developers. So rather than trying to tweak existing users into a semantic which they haven't expected I propose to simply remove the flag and start from scratch if we really need a semantic for short term allocations. [1] http://lkml.kernel.org/r/20170118054945.GD18349@bombadil.infradead.org [akpm@linux-foundation.org: fix typo] [akpm@linux-foundation.org: coding-style fixes] [sfr@canb.auug.org.au: drm/i915: fix up] Link: http://lkml.kernel.org/r/20170816144703.378d4f4d@canb.auug.org.au Link: http://lkml.kernel.org/r/20170728091904.14627-1-mhocko@kernel.org Signed-off-by: Michal Hocko Signed-off-by: Stephen Rothwell Acked-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Matthew Wilcox Cc: Neil Brown Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index bcfb9f7c46f5..f780718b7391 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -288,8 +288,6 @@ struct vm_area_struct; #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) #define GFP_NOIO (__GFP_RECLAIM) #define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) -#define GFP_TEMPORARY (__GFP_RECLAIM | __GFP_IO | __GFP_FS | \ - __GFP_RECLAIMABLE) #define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 -- cgit v1.2.3 From 2554db916586b228ce93e6f74a12fd7fe430a004 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Fri, 25 Aug 2017 09:13:54 -0700 Subject: sched/wait: Break up long wake list walk We encountered workloads that have very long wake up list on large systems. A waker takes a long time to traverse the entire wake list and execute all the wake functions. We saw page wait list that are up to 3700+ entries long in tests of large 4 and 8 socket systems. It took 0.8 sec to traverse such list during wake up. Any other CPU that contends for the list spin lock will spin for a long time. It is a result of the numa balancing migration of hot pages that are shared by many threads. Multiple CPUs waking are queued up behind the lock, and the last one queued has to wait until all CPUs did all the wakeups. The page wait list is traversed with interrupt disabled, which caused various problems. This was the original cause that triggered the NMI watch dog timer in: https://patchwork.kernel.org/patch/9800303/ . Only extending the NMI watch dog timer there helped. This patch bookmarks the waker's scan position in wake list and break the wake up walk, to allow access to the list before the waker resume its walk down the rest of the wait list. It lowers the interrupt and rescheduling latency. This patch also provides a performance boost when combined with the next patch to break up page wakeup list walk. We saw 22% improvement in the will-it-scale file pread2 test on a Xeon Phi system running 256 threads. [ v2: Merged in Linus' changes to remove the bookmark_wake_function, and simply access to flags. ] Reported-by: Kan Liang Tested-by: Kan Liang Signed-off-by: Tim Chen Signed-off-by: Linus Torvalds --- include/linux/wait.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index dc19880c02f5..78401ef02d29 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -18,6 +18,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int /* wait_queue_entry::flags */ #define WQ_FLAG_EXCLUSIVE 0x01 #define WQ_FLAG_WOKEN 0x02 +#define WQ_FLAG_BOOKMARK 0x04 /* * A single wait-queue entry structure: -- cgit v1.2.3 From 11a19c7b099f96d00a8dec52bfbb8475e89b6745 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Fri, 25 Aug 2017 09:13:55 -0700 Subject: sched/wait: Introduce wakeup boomark in wake_up_page_bit Now that we have added breaks in the wait queue scan and allow bookmark on scan position, we put this logic in the wake_up_page_bit function. We can have very long page wait list in large system where multiple pages share the same wait list. We break the wake up walk here to allow other cpus a chance to access the list, and not to disable the interrupts when traversing the list for too long. This reduces the interrupt and rescheduling latency, and excessive page wait queue lock hold time. [ v2: Remove bookmark_wake_function ] Signed-off-by: Tim Chen Signed-off-by: Linus Torvalds --- include/linux/wait.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 78401ef02d29..87c4641023fb 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -185,6 +185,8 @@ __remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq void __wake_up(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); +void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head, + unsigned int mode, void *key, wait_queue_entry_t *bookmark); void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, int nr, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr); -- cgit v1.2.3 From 711aab1dbb324d321e3d84368a435a78908c7bce Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 12 Sep 2017 22:45:33 -0400 Subject: vfs: constify path argument to kernel_read_file_from_path This patch constifies the path argument to kernel_read_file_from_path(). Signed-off-by: Mimi Zohar Cc: Christoph Hellwig Signed-off-by: Linus Torvalds --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index bc475dfeb4ce..339e73742e73 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2815,7 +2815,7 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) extern int kernel_read_file(struct file *, void **, loff_t *, loff_t, enum kernel_read_file_id); -extern int kernel_read_file_from_path(char *, void **, loff_t *, loff_t, +extern int kernel_read_file_from_path(const char *, void **, loff_t *, loff_t, enum kernel_read_file_id); extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, enum kernel_read_file_id); -- cgit v1.2.3 From 8cd641e3c7cbf86c7cbd2a17a160dd137d86c860 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Wed, 13 Sep 2017 13:08:18 -0700 Subject: sched/wait: Add swq_has_sleeper() Which is the equivalent of what we have in regular waitqueues. I'm not crazy about the name, but this also helps us get both apis closer -- which iirc comes originally from the -net folks. We also duplicate the comments for the lockless swait_active(), from wait.h. Future users will make use of this interface. Signed-off-by: Davidlohr Bueso Signed-off-by: Paolo Bonzini --- include/linux/swait.h | 58 +++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 56 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swait.h b/include/linux/swait.h index 4a4e180d0a35..73e97a08d3d0 100644 --- a/include/linux/swait.h +++ b/include/linux/swait.h @@ -79,9 +79,63 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name DECLARE_SWAIT_QUEUE_HEAD(name) #endif -static inline int swait_active(struct swait_queue_head *q) +/** + * swait_active -- locklessly test for waiters on the queue + * @wq: the waitqueue to test for waiters + * + * returns true if the wait list is not empty + * + * NOTE: this function is lockless and requires care, incorrect usage _will_ + * lead to sporadic and non-obvious failure. + * + * NOTE2: this function has the same above implications as regular waitqueues. + * + * Use either while holding swait_queue_head::lock or when used for wakeups + * with an extra smp_mb() like: + * + * CPU0 - waker CPU1 - waiter + * + * for (;;) { + * @cond = true; prepare_to_swait(&wq_head, &wait, state); + * smp_mb(); // smp_mb() from set_current_state() + * if (swait_active(wq_head)) if (@cond) + * wake_up(wq_head); break; + * schedule(); + * } + * finish_swait(&wq_head, &wait); + * + * Because without the explicit smp_mb() it's possible for the + * swait_active() load to get hoisted over the @cond store such that we'll + * observe an empty wait list while the waiter might not observe @cond. + * This, in turn, can trigger missing wakeups. + * + * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), + * which (when the lock is uncontended) are of roughly equal cost. + */ +static inline int swait_active(struct swait_queue_head *wq) +{ + return !list_empty(&wq->task_list); +} + +/** + * swq_has_sleeper - check if there are any waiting processes + * @wq: the waitqueue to test for waiters + * + * Returns true if @wq has waiting processes + * + * Please refer to the comment for swait_active. + */ +static inline bool swq_has_sleeper(struct swait_queue_head *wq) { - return !list_empty(&q->task_list); + /* + * We need to be sure we are in sync with the list_add() + * modifications to the wait queue (task_list). + * + * This memory barrier should be paired with one on the + * waiting side. + */ + smp_mb(); + return swait_active(wq); } extern void swake_up(struct swait_queue_head *q); -- cgit v1.2.3 From bf29ed1567b67854dc13504f685c45a2ea9b2081 Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Thu, 7 Sep 2017 08:30:44 -0700 Subject: syscalls: Use CHECK_DATA_CORRUPTION for addr_limit_user_check Use CHECK_DATA_CORRUPTION instead of BUG_ON to provide more flexibility on address limit failures. By default, send a SIGKILL signal to kill the current process preventing exploitation of a bad address limit. Make the TIF_FSCHECK flag optional so ARM can use this function. Signed-off-by: Thomas Garnier Signed-off-by: Kees Cook Signed-off-by: Thomas Gleixner Cc: Pratyush Anand Cc: Dave Martin Cc: Will Drewry Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Will Deacon Cc: Russell King Cc: Andy Lutomirski Cc: David Howells Cc: Dave Hansen Cc: Al Viro Cc: linux-api@vger.kernel.org Cc: Yonghong Song Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1504798247-48833-2-git-send-email-keescook@chromium.org --- include/linux/syscalls.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 95606a2d556f..a78186d826d7 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -221,21 +221,25 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) } \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) -#ifdef TIF_FSCHECK /* * Called before coming back to user-mode. Returning to user-mode with an * address limit different than USER_DS can allow to overwrite kernel memory. */ static inline void addr_limit_user_check(void) { - +#ifdef TIF_FSCHECK if (!test_thread_flag(TIF_FSCHECK)) return; +#endif - BUG_ON(!segment_eq(get_fs(), USER_DS)); + if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS), + "Invalid address limit on user-mode return")) + force_sig(SIGKILL, current); + +#ifdef TIF_FSCHECK clear_thread_flag(TIF_FSCHECK); -} #endif +} asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr); -- cgit v1.2.3 From 74378c5c8cdaf0ce9f65e67cbd0613286f2c3bad Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 5 Sep 2017 20:16:27 +0200 Subject: driver core: Fix link to device power management documentation Correct location as of commit 2728b2d2e5be4b82 (PM / core / docs: Convert sleep states API document to reST). Fixes: 2728b2d2e5be4b82 (PM / core / docs: Convert sleep states API document to reST) Signed-off-by: Geert Uytterhoeven Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c6f27207dbe8..1d2607923a24 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -838,7 +838,7 @@ struct dev_links_info { * @driver_data: Private pointer for driver specific info. * @links: Links to suppliers and consumers of this device. * @power: For device power management. - * See Documentation/power/admin-guide/devices.rst for details. + * See Documentation/driver-api/pm/devices.rst for details. * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. -- cgit v1.2.3 From aa767cfb75341a6b93742f4d7d1589ac2532c29e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 11 Sep 2017 22:07:50 +0200 Subject: of: provide inline helper for of_find_device_by_node The ipmmu-vmsa driver fails in compile-testing on non-OF platforms: drivers/iommu/ipmmu-vmsa.o: In function `ipmmu_of_xlate': ipmmu-vmsa.c:(.text+0x740): undefined reference to `of_find_device_by_node' It would be reasonable to assume that this interface works but returns failure on non-OF builds, like it does on machines that have been booted in another way, so this adds another inline function helper. Fixes: 7b2d59611fef ("iommu/ipmmu-vmsa: Replace local utlb code with fwspec ids") Signed-off-by: Arnd Bergmann Signed-off-by: Rob Herring --- include/linux/of_platform.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index e0d1946270f3..fb908e598348 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -57,7 +57,14 @@ extern const struct of_device_id of_default_bus_match_table[]; extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, struct device *parent); +#ifdef CONFIG_OF extern struct platform_device *of_find_device_by_node(struct device_node *np); +#else +static inline struct platform_device *of_find_device_by_node(struct device_node *np) +{ + return NULL; +} +#endif /* Platform devices and busses creation */ extern struct platform_device *of_platform_device_create(struct device_node *np, -- cgit v1.2.3 From ec9dd352d591f0c90402ec67a317c1ed4fb2e638 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 18 Sep 2017 16:38:36 -0700 Subject: bpf: one perf event close won't free bpf program attached by another perf event This patch fixes a bug exhibited by the following scenario: 1. fd1 = perf_event_open with attr.config = ID1 2. attach bpf program prog1 to fd1 3. fd2 = perf_event_open with attr.config = ID1 4. user program closes fd2 and prog1 is detached from the tracepoint. 5. user program with fd1 does not work properly as tracepoint no output any more. The issue happens at step 4. Multiple perf_event_open can be called successfully, but only one bpf prog pointer in the tp_event. In the current logic, any fd release for the same tp_event will free the tp_event->prog. The fix is to free tp_event->prog only when the closing fd corresponds to the one which registered the program. Signed-off-by: Yonghong Song Signed-off-by: David S. Miller --- include/linux/trace_events.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 7f11050746ae..2e0f22298fe9 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -272,6 +272,7 @@ struct trace_event_call { int perf_refcount; struct hlist_head __percpu *perf_events; struct bpf_prog *prog; + struct perf_event *bpf_prog_owner; int (*perf_perm)(struct trace_event_call *, struct perf_event *); -- cgit v1.2.3 From 0551968add53777fddd18f4ffb4e3bbc1f646d79 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Sep 2017 11:54:44 +0200 Subject: Revert "genirq: Restrict effective affinity to interrupts actually using it" This reverts commit 74def747bcd09692bdbf8c6a15350795b0f11ca8. The change to the helper function is only correct for the /proc/irq/ readout usage, but breaks the existing x86 usage of that function. Reported-by: Yanko Kaneti Signed-off-by: Thomas Gleixner Cc: Marc Zyngier --- include/linux/irq.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index b99a784635ff..d4728bf6a537 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -783,10 +783,7 @@ static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) static inline struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d) { - if (!cpumask_empty(d->common->effective_affinity)) - return d->common->effective_affinity; - - return d->common->affinity; + return d->common->effective_affinity; } static inline void irq_data_update_effective_affinity(struct irq_data *d, const struct cpumask *m) -- cgit v1.2.3 From e8b95728f724797f958912fd9b765a695595d3a6 Mon Sep 17 00:00:00 2001 From: Dmitry Torokhov Date: Fri, 1 Sep 2017 17:13:43 -0700 Subject: Input: uinput - avoid FF flush when destroying device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Normally, when input device supporting force feedback effects is being destroyed, we try to "flush" currently playing effects, so that the physical device does not continue vibrating (or executing other effects). Unfortunately this does not work well for uinput as flushing of the effects deadlocks with the destroy action: - if device is being destroyed because the file descriptor is being closed, then there is noone to even service FF requests; - if device is being destroyed because userspace sent UI_DEV_DESTROY, while theoretically it could be possible to service FF requests, userspace is unlikely to do so (they'd need to make sure FF handling happens on a separate thread) even if kernel solves the issue with FF ioctls deadlocking with UI_DEV_DESTROY ioctl on udev->mutex. To avoid lockups like the one below, let's install a custom input device flush handler, and avoid trying to flush force feedback effects when we destroying the device, and instead rely on uinput to shut off the device properly. NMI watchdog: Watchdog detected hard LOCKUP on cpu 3 ... <> [] _raw_spin_lock_irqsave+0x37/0x40 [] complete+0x1d/0x50 [] uinput_request_done+0x3c/0x40 [uinput] [] uinput_request_submit.part.7+0x47/0xb0 [uinput] [] uinput_dev_erase_effect+0x5b/0x76 [uinput] [] erase_effect+0xad/0xf0 [] flush_effects+0x4d/0x90 [] input_flush_device+0x40/0x60 [] evdev_cleanup+0xac/0xc0 [] evdev_disconnect+0x2b/0x60 [] __input_unregister_device+0xac/0x150 [] input_unregister_device+0x47/0x70 [] uinput_destroy_device+0xb5/0xc0 [uinput] [] uinput_ioctl_handler.isra.9+0x65e/0x740 [uinput] [] ? do_futex+0x12b/0xad0 [] uinput_ioctl+0x18/0x20 [uinput] [] do_vfs_ioctl+0x298/0x480 [] ? security_file_ioctl+0x43/0x60 [] SyS_ioctl+0x79/0x90 [] entry_SYSCALL_64_fastpath+0x12/0x71 Reported-by: Rodrigo Rivas Costa Reported-by: Clément VUCHENER Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=193741 Signed-off-by: Dmitry Torokhov --- include/linux/input.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/input.h b/include/linux/input.h index a65e3b24fb18..fb5e23c7ed98 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -529,6 +529,7 @@ int input_ff_event(struct input_dev *dev, unsigned int type, unsigned int code, int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, struct file *file); int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file); +int input_ff_flush(struct input_dev *dev, struct file *file); int input_ff_create_memless(struct input_dev *dev, void *data, int (*play_effect)(struct input_dev *, void *, struct ff_effect *)); -- cgit v1.2.3