From 9d8f13ba3f4833219e50767b022b82cd0da930eb Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Mon, 6 Jun 2011 15:29:25 -0400 Subject: security: new security_inode_init_security API adds function callback This patch changes the security_inode_init_security API by adding a filesystem specific callback to write security extended attributes. This change is in preparation for supporting the initialization of multiple LSM xattrs and the EVM xattr. Initially the callback function walks an array of xattrs, writing each xattr separately, but could be optimized to write multiple xattrs at once. For existing security_inode_init_security() calls, which have not yet been converted to use the new callback function, such as those in reiserfs and ocfs2, this patch defines security_old_inode_init_security(). Signed-off-by: Mimi Zohar --- include/linux/security.h | 17 ++++++++++++----- include/linux/xattr.h | 6 ++++++ 2 files changed, 18 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index 8ce59ef3e5af..6a20c7025495 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -36,6 +36,7 @@ #include #include #include +#include #include /* Maximum number of letters for an LSM name string */ @@ -147,6 +148,10 @@ extern int mmap_min_addr_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #endif +/* security_inode_init_security callback function to write xattrs */ +typedef int (*initxattrs) (struct inode *inode, + const struct xattr *xattr_array, void *fs_data); + #ifdef CONFIG_SECURITY struct security_mnt_opts { @@ -1704,8 +1709,11 @@ int security_sb_parse_opts_str(char *options, struct security_mnt_opts *opts); int security_inode_alloc(struct inode *inode); void security_inode_free(struct inode *inode); int security_inode_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr, char **name, - void **value, size_t *len); + const struct qstr *qstr, + initxattrs initxattrs, void *fs_data); +int security_old_inode_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr, char **name, + void **value, size_t *len); int security_inode_create(struct inode *dir, struct dentry *dentry, int mode); int security_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry); @@ -2035,9 +2043,8 @@ static inline void security_inode_free(struct inode *inode) static inline int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, - char **name, - void **value, - size_t *len) + initxattrs initxattrs, + void *fs_data) { return -EOPNOTSUPP; } diff --git a/include/linux/xattr.h b/include/linux/xattr.h index aed54c50aa66..7a378662ddff 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -67,6 +67,12 @@ struct xattr_handler { size_t size, int flags, int handler_flags); }; +struct xattr { + char *name; + void *value; + size_t value_len; +}; + ssize_t xattr_getsecurity(struct inode *, const char *, void *, size_t); ssize_t vfs_getxattr(struct dentry *, const char *, void *, size_t); ssize_t vfs_listxattr(struct dentry *d, char *list, size_t size); -- cgit v1.2.3 From f381c272224f5f158f5cff64f8f3481fa0eee8b3 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 9 Mar 2011 14:13:22 -0500 Subject: integrity: move ima inode integrity data management Move the inode integrity data(iint) management up to the integrity directory in order to share the iint among the different integrity models. Changelog: - don't define MAX_DIGEST_SIZE - rename several globally visible 'ima_' prefixed functions, structs, locks, etc to 'integrity_' - replace '20' with SHA1_DIGEST_SIZE - reflect location change in appropriate Kconfig and Makefiles - remove unnecessary initialization of iint_initialized to 0 - rebased on current ima_iint.c - define integrity_iint_store/lock as static There should be no other functional changes. Signed-off-by: Mimi Zohar Acked-by: Serge Hallyn --- include/linux/ima.h | 13 ------------- include/linux/integrity.h | 30 ++++++++++++++++++++++++++++++ 2 files changed, 30 insertions(+), 13 deletions(-) create mode 100644 include/linux/integrity.h (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index 09e6e62f9953..6ac8e50c6cf5 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -15,8 +15,6 @@ struct linux_binprm; #ifdef CONFIG_IMA extern int ima_bprm_check(struct linux_binprm *bprm); -extern int ima_inode_alloc(struct inode *inode); -extern void ima_inode_free(struct inode *inode); extern int ima_file_check(struct file *file, int mask); extern void ima_file_free(struct file *file); extern int ima_file_mmap(struct file *file, unsigned long prot); @@ -27,16 +25,6 @@ static inline int ima_bprm_check(struct linux_binprm *bprm) return 0; } -static inline int ima_inode_alloc(struct inode *inode) -{ - return 0; -} - -static inline void ima_inode_free(struct inode *inode) -{ - return; -} - static inline int ima_file_check(struct file *file, int mask) { return 0; @@ -51,6 +39,5 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot) { return 0; } - #endif /* CONFIG_IMA_H */ #endif /* _LINUX_IMA_H */ diff --git a/include/linux/integrity.h b/include/linux/integrity.h new file mode 100644 index 000000000000..905981247327 --- /dev/null +++ b/include/linux/integrity.h @@ -0,0 +1,30 @@ +/* + * Copyright (C) 2009 IBM Corporation + * Author: Mimi Zohar + * + * 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 of the License. + */ + +#ifndef _LINUX_INTEGRITY_H +#define _LINUX_INTEGRITY_H + +#include + +#ifdef CONFIG_INTEGRITY +extern int integrity_inode_alloc(struct inode *inode); +extern void integrity_inode_free(struct inode *inode); + +#else +static inline int integrity_inode_alloc(struct inode *inode) +{ + return 0; +} + +static inline void integrity_inode_free(struct inode *inode) +{ + return; +} +#endif /* CONFIG_INTEGRITY_H */ +#endif /* _LINUX_INTEGRITY_H */ -- cgit v1.2.3 From 1601fbad2b14e0b8d4dbb55e749bfe31e972818a Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 9 Mar 2011 14:23:34 -0500 Subject: xattr: define vfs_getxattr_alloc and vfs_xattr_cmp vfs_getxattr_alloc() and vfs_xattr_cmp() are two new kernel xattr helper functions. vfs_getxattr_alloc() first allocates memory for the requested xattr and then retrieves it. vfs_xattr_cmp() compares a given value with the contents of an extended attribute. Signed-off-by: Mimi Zohar Acked-by: Serge Hallyn --- include/linux/xattr.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 7a378662ddff..4703f6bd1f53 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -84,7 +84,10 @@ ssize_t generic_getxattr(struct dentry *dentry, const char *name, void *buffer, ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); int generic_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); int generic_removexattr(struct dentry *dentry, const char *name); - +ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, + char **xattr_value, size_t size, gfp_t flags); +int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, + const char *value, size_t size, gfp_t flags); #endif /* __KERNEL__ */ #endif /* _LINUX_XATTR_H */ -- cgit v1.2.3 From 66dbc325afcef909043c30e90930a36823fc734c Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 15 Mar 2011 16:12:09 -0400 Subject: evm: re-release EVM protects a file's security extended attributes(xattrs) against integrity attacks. This patchset provides the framework and an initial method. The initial method maintains an HMAC-sha1 value across the security extended attributes, storing the HMAC value as the extended attribute 'security.evm'. Other methods of validating the integrity of a file's metadata will be posted separately (eg. EVM-digital-signatures). While this patchset does authenticate the security xattrs, and cryptographically binds them to the inode, coming extensions will bind other directory and inode metadata for more complete protection. To help simplify the review and upstreaming process, each extension will be posted separately (eg. IMA-appraisal, IMA-appraisal-directory). For a general overview of the proposed Linux integrity subsystem, refer to Dave Safford's whitepaper: http://downloads.sf.net/project/linux-ima/linux-ima/Integrity_overview.pdf. EVM depends on the Kernel Key Retention System to provide it with a trusted/encrypted key for the HMAC-sha1 operation. The key is loaded onto the root's keyring using keyctl. Until EVM receives notification that the key has been successfully loaded onto the keyring (echo 1 > /evm), EVM can not create or validate the 'security.evm' xattr, but returns INTEGRITY_UNKNOWN. Loading the key and signaling EVM should be done as early as possible. Normally this is done in the initramfs, which has already been measured as part of the trusted boot. For more information on creating and loading existing trusted/encrypted keys, refer to Documentation/keys-trusted-encrypted.txt. A sample dracut patch, which loads the trusted/encrypted key and enables EVM, is available from http://linux-ima.sourceforge.net/#EVM. Based on the LSMs enabled, the set of EVM protected security xattrs is defined at compile. EVM adds the following three calls to the existing security hooks: evm_inode_setxattr(), evm_inode_post_setxattr(), and evm_inode_removexattr. To initialize and update the 'security.evm' extended attribute, EVM defines three calls: evm_inode_post_init(), evm_inode_post_setattr() and evm_inode_post_removexattr() hooks. To verify the integrity of a security xattr, EVM exports evm_verifyxattr(). Changelog v7: - Fixed URL in EVM ABI documentation Changelog v6: (based on Serge Hallyn's review) - fix URL in patch description - remove evm_hmac_size definition - use SHA1_DIGEST_SIZE (removed both MAX_DIGEST_SIZE and evm_hmac_size) - moved linux include before other includes - test for crypto_hash_setkey failure - fail earlier for invalid key - clear entire encrypted key, even on failure - check xattr name length before comparing xattr names Changelog: - locking based on i_mutex, remove evm_mutex - using trusted/encrypted keys for storing the EVM key used in the HMAC-sha1 operation. - replaced crypto hash with shash (Dmitry Kasatkin) - support for additional methods of verifying the security xattrs (Dmitry Kasatkin) - iint not allocated for all regular files, but only for those appraised - Use cap_sys_admin in lieu of cap_mac_admin - Use __vfs_setxattr_noperm(), without permission checks, from EVM Signed-off-by: Mimi Zohar Acked-by: Serge Hallyn --- include/linux/integrity.h | 7 +++++++ include/linux/xattr.h | 3 +++ 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/integrity.h b/include/linux/integrity.h index 905981247327..e715a2abcea2 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -12,6 +12,13 @@ #include +enum integrity_status { + INTEGRITY_PASS = 0, + INTEGRITY_FAIL, + INTEGRITY_NOLABEL, + INTEGRITY_UNKNOWN, +}; + #ifdef CONFIG_INTEGRITY extern int integrity_inode_alloc(struct inode *inode); extern void integrity_inode_free(struct inode *inode); diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 4703f6bd1f53..b20cb965c322 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -30,6 +30,9 @@ #define XATTR_USER_PREFIX_LEN (sizeof (XATTR_USER_PREFIX) - 1) /* Security namespace */ +#define XATTR_EVM_SUFFIX "evm" +#define XATTR_NAME_EVM XATTR_SECURITY_PREFIX XATTR_EVM_SUFFIX + #define XATTR_SELINUX_SUFFIX "selinux" #define XATTR_NAME_SELINUX XATTR_SECURITY_PREFIX XATTR_SELINUX_SUFFIX -- cgit v1.2.3 From 6be5cc5246f807fd8ede9f5f1bb2826f2c598658 Mon Sep 17 00:00:00 2001 From: Dmitry Kasatkin Date: Wed, 9 Mar 2011 14:28:20 -0500 Subject: evm: add support for different security.evm data types EVM protects a file's security extended attributes(xattrs) against integrity attacks. The current patchset maintains an HMAC-sha1 value across the security xattrs, storing the value as the extended attribute 'security.evm'. We anticipate other methods for protecting the security extended attributes. This patch reserves the first byte of 'security.evm' as a place holder for the type of method. Changelog v6: - move evm_ima_xattr_type definition to security/integrity/integrity.h - defined a structure for the EVM xattr called evm_ima_xattr_data (based on Serge Hallyn's suggestion) - removed unnecessary memset Signed-off-by: Dmitry Kasatkin Signed-off-by: Mimi Zohar Acked-by: Serge Hallyn --- include/linux/integrity.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/integrity.h b/include/linux/integrity.h index e715a2abcea2..968443385678 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -19,6 +19,7 @@ enum integrity_status { INTEGRITY_UNKNOWN, }; +/* List of EVM protected security xattrs */ #ifdef CONFIG_INTEGRITY extern int integrity_inode_alloc(struct inode *inode); extern void integrity_inode_free(struct inode *inode); -- cgit v1.2.3 From 3e1be52d6c6b21d9080dd886c0e609e009831562 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 9 Mar 2011 14:38:26 -0500 Subject: security: imbed evm calls in security hooks Imbed the evm calls evm_inode_setxattr(), evm_inode_post_setxattr(), evm_inode_removexattr() in the security hooks. evm_inode_setxattr() protects security.evm xattr. evm_inode_post_setxattr() and evm_inode_removexattr() updates the hmac associated with an inode. (Assumes an LSM module protects the setting/removing of xattr.) Changelog: - Don't define evm_verifyxattr(), unless CONFIG_INTEGRITY is enabled. - xattr_name is a 'const', value is 'void *' Signed-off-by: Mimi Zohar Acked-by: Serge Hallyn --- include/linux/evm.h | 56 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 include/linux/evm.h (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h new file mode 100644 index 000000000000..8b4e9e3b395e --- /dev/null +++ b/include/linux/evm.h @@ -0,0 +1,56 @@ +/* + * evm.h + * + * Copyright (c) 2009 IBM Corporation + * Author: Mimi Zohar + */ + +#ifndef _LINUX_EVM_H +#define _LINUX_EVM_H + +#include + +#ifdef CONFIG_EVM +extern enum integrity_status evm_verifyxattr(struct dentry *dentry, + const char *xattr_name, + void *xattr_value, + size_t xattr_value_len); +extern int evm_inode_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size); +extern void evm_inode_post_setxattr(struct dentry *dentry, + const char *xattr_name, + const void *xattr_value, + size_t xattr_value_len); +extern int evm_inode_removexattr(struct dentry *dentry, const char *xattr_name); +#else +#ifdef CONFIG_INTEGRITY +static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, + const char *xattr_name, + void *xattr_value, + size_t xattr_value_len) +{ + return INTEGRITY_UNKNOWN; +} +#endif + +static inline int evm_inode_setxattr(struct dentry *dentry, const char *name, + const void *value, size_t size) +{ + return 0; +} + +static inline void evm_inode_post_setxattr(struct dentry *dentry, + const char *xattr_name, + const void *xattr_value, + size_t xattr_value_len) +{ + return; +} + +static inline int evm_inode_removexattr(struct dentry *dentry, + const char *xattr_name) +{ + return 0; +} +#endif /* CONFIG_EVM_H */ +#endif /* LINUX_EVM_H */ -- cgit v1.2.3 From c7b87de23b6fd5dfbe5c36601f29d6c515056343 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 9 Mar 2011 14:39:18 -0500 Subject: evm: evm_inode_post_removexattr When an EVM protected extended attribute is removed, update 'security.evm'. Signed-off-by: Mimi Zohar Acked-by: Serge Hallyn --- include/linux/evm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 8b4e9e3b395e..a730782da563 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -22,6 +22,8 @@ extern void evm_inode_post_setxattr(struct dentry *dentry, const void *xattr_value, size_t xattr_value_len); extern int evm_inode_removexattr(struct dentry *dentry, const char *xattr_name); +extern void evm_inode_post_removexattr(struct dentry *dentry, + const char *xattr_name); #else #ifdef CONFIG_INTEGRITY static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, @@ -52,5 +54,12 @@ static inline int evm_inode_removexattr(struct dentry *dentry, { return 0; } + +static inline void evm_inode_post_removexattr(struct dentry *dentry, + const char *xattr_name) +{ + return; +} + #endif /* CONFIG_EVM_H */ #endif /* LINUX_EVM_H */ -- cgit v1.2.3 From 975d294373d8c1c913ad2bf4eb93966d4c7ca38f Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 9 Mar 2011 14:39:57 -0500 Subject: evm: imbed evm_inode_post_setattr Changing the inode's metadata may require the 'security.evm' extended attribute to be re-calculated and updated. Signed-off-by: Mimi Zohar Acked-by: Serge Hallyn --- include/linux/evm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index a730782da563..33a92471e463 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -15,6 +15,7 @@ extern enum integrity_status evm_verifyxattr(struct dentry *dentry, const char *xattr_name, void *xattr_value, size_t xattr_value_len); +extern void evm_inode_post_setattr(struct dentry *dentry, int ia_valid); extern int evm_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size); extern void evm_inode_post_setxattr(struct dentry *dentry, @@ -35,6 +36,11 @@ static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, } #endif +static inline void evm_inode_post_setattr(struct dentry *dentry, int ia_valid) +{ + return; +} + static inline int evm_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size) { -- cgit v1.2.3 From cb72318069d5e92eb74840118732c66eb38c812f Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 9 Mar 2011 14:40:44 -0500 Subject: evm: add evm_inode_init_security to initialize new files Initialize 'security.evm' for new files. Changelog v7: - renamed evm_inode_post_init_security to evm_inode_init_security - moved struct xattr definition to earlier patch - allocate xattr name Changelog v6: - Use 'struct evm_ima_xattr_data' Signed-off-by: Mimi Zohar --- include/linux/evm.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 33a92471e463..7c10761916a2 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -9,6 +9,7 @@ #define _LINUX_EVM_H #include +#include #ifdef CONFIG_EVM extern enum integrity_status evm_verifyxattr(struct dentry *dentry, @@ -25,6 +26,9 @@ extern void evm_inode_post_setxattr(struct dentry *dentry, extern int evm_inode_removexattr(struct dentry *dentry, const char *xattr_name); extern void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name); +extern int evm_inode_init_security(struct inode *inode, + const struct xattr *xattr_array, + struct xattr *evm); #else #ifdef CONFIG_INTEGRITY static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, @@ -67,5 +71,12 @@ static inline void evm_inode_post_removexattr(struct dentry *dentry, return; } +static inline int evm_inode_init_security(struct inode *inode, + const struct xattr *xattr_array, + struct xattr *evm) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_EVM_H */ #endif /* LINUX_EVM_H */ -- cgit v1.2.3 From 2960e6cb5f7c662b8edb6b0d2edc72095b4f5672 Mon Sep 17 00:00:00 2001 From: Dmitry Kasatkin Date: Fri, 6 May 2011 11:34:13 +0300 Subject: evm: additional parameter to pass integrity cache entry 'iint' Additional iint parameter allows to skip lookup in the cache. Signed-off-by: Dmitry Kasatkin Signed-off-by: Mimi Zohar --- include/linux/evm.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 7c10761916a2..6d4e89b020c5 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -11,11 +11,14 @@ #include #include +struct integrity_iint_cache; + #ifdef CONFIG_EVM extern enum integrity_status evm_verifyxattr(struct dentry *dentry, const char *xattr_name, void *xattr_value, - size_t xattr_value_len); + size_t xattr_value_len, + struct integrity_iint_cache *iint); extern void evm_inode_post_setattr(struct dentry *dentry, int ia_valid); extern int evm_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size); @@ -34,7 +37,8 @@ extern int evm_inode_init_security(struct inode *inode, static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, const char *xattr_name, void *xattr_value, - size_t xattr_value_len) + size_t xattr_value_len, + struct integrity_iint_cache *iint) { return INTEGRITY_UNKNOWN; } -- cgit v1.2.3 From 817b54aa45db03437c6d09a7693fc6926eb8e822 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Fri, 13 May 2011 12:53:38 -0400 Subject: evm: add evm_inode_setattr to prevent updating an invalid security.evm Permit changing of security.evm only when valid, unless in fixmode. Reported-by: Roberto Sassu Signed-off-by: Mimi Zohar --- include/linux/evm.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 6d4e89b020c5..db5556dcdd27 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -19,6 +19,7 @@ extern enum integrity_status evm_verifyxattr(struct dentry *dentry, void *xattr_value, size_t xattr_value_len, struct integrity_iint_cache *iint); +extern int evm_inode_setattr(struct dentry *dentry, struct iattr *attr); extern void evm_inode_post_setattr(struct dentry *dentry, int ia_valid); extern int evm_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size); @@ -44,6 +45,11 @@ static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, } #endif +static int evm_inode_setattr(struct dentry *dentry, struct iattr *attr) +{ + return 0; +} + static inline void evm_inode_post_setattr(struct dentry *dentry, int ia_valid) { return; -- cgit v1.2.3 From dd898b209577b83283bb62400c96426d7582e5a2 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 20 Jul 2011 22:28:58 +0100 Subject: regmap: Add kerneldoc for struct regmap_config Signed-off-by: Mark Brown --- include/linux/regmap.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 60a65cd7e1a0..cf8e4cffd386 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -20,6 +20,12 @@ struct i2c_client; struct spi_device; +/** + * Configuration for the register map of a device. + * + * @reg_bits: Number of bits in a register address, mandatory. + * @val_bits: Number of bits in a register value, mandatory. + */ struct regmap_config { int reg_bits; int val_bits; -- cgit v1.2.3 From 2e2ae66df37a14c9b33889b243b0ae1352ada1dd Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 20 Jul 2011 22:33:39 +0100 Subject: regmap: Allow devices to specify which registers are accessible This is currently unused but we need to know which registers exist and their properties in order to implement diagnostics like register map dumps and the cache features. We use callbacks partly because properties can vary at runtime (eg, through access locks on registers) and partly because big switch statements are a good compromise between readable code and small data size for providing information on big register maps. Signed-off-by: Mark Brown --- include/linux/regmap.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index cf8e4cffd386..aef2b36a8ccf 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -25,10 +25,23 @@ struct spi_device; * * @reg_bits: Number of bits in a register address, mandatory. * @val_bits: Number of bits in a register value, mandatory. + * + * @max_register: Optional, specifies the maximum valid register index. + * @writeable_register: Optional callback returning true if the register + * can be written to. + * @readable_register: Optional callback returning true if the register + * can be read from. + * @volatile_register: Optional callback returning true if the register + * value can't be cached. */ struct regmap_config { int reg_bits; int val_bits; + + unsigned int max_register; + bool (*writeable_reg)(struct device *dev, unsigned int reg); + bool (*readable_reg)(struct device *dev, unsigned int reg); + bool (*volatile_reg)(struct device *dev, unsigned int reg); }; typedef int (*regmap_hw_write)(struct device *dev, const void *data, -- cgit v1.2.3 From 18694886bddb2d4d905535a0149aeef3b5f9c936 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 8 Aug 2011 15:40:22 +0900 Subject: regmap: Add precious registers to the driver interface Some devices are sensitive to reads on their registers, especially for things like clear on read interrupt status registers. Avoid creating problems with these with things like debugfs by allowing drivers to tell the core about them. If a register is marked as precious then the core will not internally generate any reads of it. Signed-off-by: Mark Brown --- include/linux/regmap.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index aef2b36a8ccf..c878a4bf717e 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -33,6 +33,9 @@ struct spi_device; * can be read from. * @volatile_register: Optional callback returning true if the register * value can't be cached. + * @precious_register: Optional callback returning true if the rgister + * should not be read outside of a call from the driver + * (eg, a clear on read interrupt status register). */ struct regmap_config { int reg_bits; @@ -42,6 +45,7 @@ struct regmap_config { bool (*writeable_reg)(struct device *dev, unsigned int reg); bool (*readable_reg)(struct device *dev, unsigned int reg); bool (*volatile_reg)(struct device *dev, unsigned int reg); + bool (*precious_reg)(struct device *dev, unsigned int reg); }; typedef int (*regmap_hw_write)(struct device *dev, const void *data, -- cgit v1.2.3 From 3566cc9d90e3f774cea47de6986c59a09090ce2b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 9 Aug 2011 10:23:22 +0900 Subject: regmap: Fix kerneldoc errors for regmap Field names didn't match between the documentation and the code. Signed-off-by: Mark Brown --- include/linux/regmap.h | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index c878a4bf717e..4de137bc16a7 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -27,15 +27,15 @@ struct spi_device; * @val_bits: Number of bits in a register value, mandatory. * * @max_register: Optional, specifies the maximum valid register index. - * @writeable_register: Optional callback returning true if the register - * can be written to. - * @readable_register: Optional callback returning true if the register - * can be read from. - * @volatile_register: Optional callback returning true if the register - * value can't be cached. - * @precious_register: Optional callback returning true if the rgister - * should not be read outside of a call from the driver - * (eg, a clear on read interrupt status register). + * @writeable_reg: Optional callback returning true if the register + * can be written to. + * @readable_reg: Optional callback returning true if the register + * can be read from. + * @volatile_reg: Optional callback returning true if the register + * value can't be cached. + * @precious_reg: Optional callback returning true if the rgister + * should not be read outside of a call from the driver + * (eg, a clear on read interrupt status register). */ struct regmap_config { int reg_bits; -- cgit v1.2.3 From 790923e56be795e14eaaeb3305cb4e171cd0a72f Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 9 Aug 2011 10:41:37 +0900 Subject: regmap: Remove unused type and list fields from bus interface We no longer enumerate the bus types, we rely on the driver telling us this on init. Signed-off-by: Mark Brown --- include/linux/regmap.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4de137bc16a7..20a8fbf19d44 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -60,8 +60,6 @@ typedef int (*regmap_hw_read)(struct device *dev, /** * Description of a hardware bus for the register map infrastructure. * - * @list: Internal use. - * @type: Bus type, used to identify bus to be used for a device. * @write: Write operation. * @gather_write: Write operation with split register/value, return -ENOTSUPP * if not implemented on a given device. @@ -73,8 +71,6 @@ typedef int (*regmap_hw_read)(struct device *dev, * a read. */ struct regmap_bus { - struct list_head list; - struct bus_type *type; regmap_hw_write write; regmap_hw_gather_write gather_write; regmap_hw_read read; -- cgit v1.2.3 From 4ea5454203d991ec85264f64f89ca8855fce69b0 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Wed, 10 Aug 2011 14:02:07 +0200 Subject: HID: Fix race condition between driver core and ll-driver HID low level drivers register new devices with the HID core which then adds the devices to the HID bus. The HID bus normally immediately probes an appropriate driver which then handles HID input for this device. The ll driver now uses the hid_input_report() function to report input events for a specific device. However, if the HID bus unloads the driver at the same time (for instance via a call to /sys/bus/hid/devices//unbind) then the hdev->driver pointer may be used by hid_input_report() and hid_device_remove() at the same time which may cause hdev->driver to point to invalid memory. This fix adds a semaphore to every hid device which protects hdev->driver from asynchronous access. This semaphore is locked during driver *_probe and *_remove and also inside hid_input_report(). The *_probe and *_remove functions may sleep so the semaphore is good here, however, hid_input_report() is in atomic context and hence only uses down_trylock(). If it cannot acquire the lock it simply drops the input package. The low-level drivers report input events synchronously so hid_input_report() should never be entered twice at the same time on the same device. Hence, the lock should always be available. But if the driver is currently probed/removed then the lock is not available and dropping the package should be safe because this is what would have happened if the package arrived some milliseconds earlier/later. This also fixes another race condition while probing drivers: First the *_probe function of the driver is called and only if that succeeds, the related input device of hidinput is registered. If the low level driver reports input events after the *_probe function returned but before the input device is registered, then a NULL pointer dereference will occur. (Equivalently on driver remove function). This is not possible anymore, since the semaphore lock drops all incoming packages until the driver/device is fully initialized. Signed-off-by: David Herrmann 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 9cf8e7ae7450..9c02d07af0d1 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -71,6 +71,7 @@ #include #include #include +#include /* * We parse each description item into this structure. Short items data @@ -475,6 +476,7 @@ struct hid_device { /* device report descriptor */ unsigned country; /* HID country */ struct hid_report_enum report_enum[HID_REPORT_TYPES]; + struct semaphore driver_lock; /* protects the current driver */ struct device dev; /* device */ struct hid_driver *driver; struct hid_ll_driver *ll_driver; -- cgit v1.2.3 From 4b41308d2d0398409620613c7eaaaf52c738b042 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 10 Aug 2011 10:37:59 -0700 Subject: alarmtimers: Change alarmtimer functions to return alarmtimer_restart values In order to properly fix the denial of service issue with high freq periodic alarm timers, we need to push the re-arming logic into the alarm timer handler, much as the hrtimer code does. This patch introduces alarmtimer_restart enum and changes the alarmtimer handler declarations to use it as a return value. Further, to ease following changes, it extends the alarmtimer handler functions to also take the time at expiration. No logic is yet modified. CC: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/alarmtimer.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index c5d6095b46f8..0289eb29e794 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -13,6 +13,11 @@ enum alarmtimer_type { ALARM_NUMTYPE, }; +enum alarmtimer_restart { + ALARMTIMER_NORESTART, + ALARMTIMER_RESTART, +}; + /** * struct alarm - Alarm timer structure * @node: timerqueue node for adding to the event list this value @@ -26,14 +31,14 @@ enum alarmtimer_type { struct alarm { struct timerqueue_node node; ktime_t period; - void (*function)(struct alarm *); + enum alarmtimer_restart (*function)(struct alarm *, ktime_t now); enum alarmtimer_type type; bool enabled; void *data; }; void alarm_init(struct alarm *alarm, enum alarmtimer_type type, - void (*function)(struct alarm *)); + enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); void alarm_start(struct alarm *alarm, ktime_t start, ktime_t period); void alarm_cancel(struct alarm *alarm); -- cgit v1.2.3 From dce75a8c71819ed4c7efdcd53c9b6f6356dc8cb5 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 10 Aug 2011 11:31:03 -0700 Subject: alarmtimers: Add alarm_forward functionality In order to avoid wasting time expiring and re-adding very high freq periodic alarmtimers, introduce alarm_forward() which is similar to hrtimer_forward and moves the timer to the next future expiration time and returns the number of overruns. CC: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/alarmtimer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 0289eb29e794..17535963b274 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -42,4 +42,6 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, void alarm_start(struct alarm *alarm, ktime_t start, ktime_t period); void alarm_cancel(struct alarm *alarm); +u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval); + #endif -- cgit v1.2.3 From 9e26476243e438f4534a562660c1296a15a9e202 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 10 Aug 2011 12:09:24 -0700 Subject: alarmtimers: Remove period from alarm structure Now that periodic alarmtimers are managed by the handler function, remove the period value from the alarm structure and let the handlers manage the interval on their own. CC: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/alarmtimer.h | 3 +-- include/linux/posix-timers.h | 5 ++++- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 17535963b274..c854a8efa863 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -30,7 +30,6 @@ enum alarmtimer_restart { */ struct alarm { struct timerqueue_node node; - ktime_t period; enum alarmtimer_restart (*function)(struct alarm *, ktime_t now); enum alarmtimer_type type; bool enabled; @@ -39,7 +38,7 @@ struct alarm { void alarm_init(struct alarm *alarm, enum alarmtimer_type type, enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); -void alarm_start(struct alarm *alarm, ktime_t start, ktime_t period); +void alarm_start(struct alarm *alarm, ktime_t start); void alarm_cancel(struct alarm *alarm); u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval); diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 959c14132f46..042058fdb0af 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -81,7 +81,10 @@ struct k_itimer { unsigned long incr; unsigned long expires; } mmtimer; - struct alarm alarmtimer; + struct { + struct alarm alarmtimer; + ktime_t interval; + } alarm; struct rcu_head rcu; } it; }; -- cgit v1.2.3 From a28cde81ab13cc251748a4c4ef06883dd09a10ea Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 10 Aug 2011 12:30:21 -0700 Subject: alarmtimers: Add more refined alarm state tracking In order to allow for functionality like try_to_cancel, add more refined state tracking (similar to hrtimers). CC: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/alarmtimer.h | 34 +++++++++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index c854a8efa863..304124a6c982 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -18,6 +18,11 @@ enum alarmtimer_restart { ALARMTIMER_RESTART, }; + +#define ALARMTIMER_STATE_INACTIVE 0x00 +#define ALARMTIMER_STATE_ENQUEUED 0x01 +#define ALARMTIMER_STATE_CALLBACK 0x02 + /** * struct alarm - Alarm timer structure * @node: timerqueue node for adding to the event list this value @@ -32,7 +37,7 @@ struct alarm { struct timerqueue_node node; enum alarmtimer_restart (*function)(struct alarm *, ktime_t now); enum alarmtimer_type type; - bool enabled; + int state; void *data; }; @@ -43,4 +48,31 @@ void alarm_cancel(struct alarm *alarm); u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval); +/* + * A alarmtimer is active, when it is enqueued into timerqueue or the + * callback function is running. + */ +static inline int alarmtimer_active(const struct alarm *timer) +{ + return timer->state != ALARMTIMER_STATE_INACTIVE; +} + +/* + * Helper function to check, whether the timer is on one of the queues + */ +static inline int alarmtimer_is_queued(struct alarm *timer) +{ + return timer->state & ALARMTIMER_STATE_ENQUEUED; +} + +/* + * Helper function to check, whether the timer is running the callback + * function + */ +static inline int alarmtimer_callback_running(struct alarm *timer) +{ + return timer->state & ALARMTIMER_STATE_CALLBACK; +} + + #endif -- cgit v1.2.3 From 9082c465a5403f4a98734193e078552991a2e283 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 10 Aug 2011 12:41:36 -0700 Subject: alarmtimers: Add try_to_cancel functionality There's a number of edge cases when cancelling a alarm, so to be sure we accurately do so, introduce try_to_cancel, which returns proper failure errors if it cannot. Also modify cancel to spin until the alarm is properly disabled. CC: Thomas Gleixner Signed-off-by: John Stultz --- include/linux/alarmtimer.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 304124a6c982..975009e1cbe6 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -44,7 +44,8 @@ struct alarm { void alarm_init(struct alarm *alarm, enum alarmtimer_type type, enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); void alarm_start(struct alarm *alarm, ktime_t start); -void alarm_cancel(struct alarm *alarm); +int alarm_try_to_cancel(struct alarm *alarm); +int alarm_cancel(struct alarm *alarm); u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval); -- cgit v1.2.3 From b75ef8b44b1cb95f5a26484b0e2fe37a63b12b44 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Wed, 10 Aug 2011 15:18:39 -0400 Subject: Tracepoint: Dissociate from module mutex Copy the information needed from struct module into a local module list held within tracepoint.c from within the module coming/going notifier. This vastly simplifies locking of tracepoint registration / unregistration, because we don't have to take the module mutex to register and unregister tracepoints anymore. Steven Rostedt ran into dependency problems related to modules mutex vs kprobes mutex vs ftrace mutex vs tracepoint mutex that seems to be hard to fix without removing this dependency between tracepoint and module mutex. (note: it should be investigated whether kprobes could benefit of being dissociated from the modules mutex too.) This also fixes module handling of tracepoint list iterators, because it was expecting the list to be sorted by pointer address. Given we have control on our own list now, it's OK to sort this list which has tracepoints as its only purpose. The reason why this sorting is required is to handle the fact that seq files (and any read() operation from user-space) cannot hold the tracepoint mutex across multiple calls, so list entries may vanish between calls. With sorting, the tracepoint iterator becomes usable even if the list don't contain the exact item pointed to by the iterator anymore. Signed-off-by: Mathieu Desnoyers Acked-by: Jason Baron CC: Ingo Molnar CC: Lai Jiangshan CC: Peter Zijlstra CC: Thomas Gleixner CC: Masami Hiramatsu Link: http://lkml.kernel.org/r/20110810191839.GC8525@Krystal Signed-off-by: Steven Rostedt --- include/linux/module.h | 12 ------------ include/linux/tracepoint.h | 25 +++++++++++-------------- 2 files changed, 11 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index 1c30087a2d81..863921637d9f 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -580,9 +580,6 @@ int unregister_module_notifier(struct notifier_block * nb); extern void print_modules(void); -extern void module_update_tracepoints(void); -extern int module_get_iter_tracepoints(struct tracepoint_iter *iter); - #else /* !CONFIG_MODULES... */ #define EXPORT_SYMBOL(sym) #define EXPORT_SYMBOL_GPL(sym) @@ -698,15 +695,6 @@ static inline int unregister_module_notifier(struct notifier_block * nb) static inline void print_modules(void) { } - -static inline void module_update_tracepoints(void) -{ -} - -static inline int module_get_iter_tracepoints(struct tracepoint_iter *iter) -{ - return 0; -} #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index d530a4460a0b..df0a779c1bbd 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -54,8 +54,18 @@ extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe, void *data); extern void tracepoint_probe_update_all(void); +#ifdef CONFIG_MODULES +struct tp_module { + struct list_head list; + unsigned int num_tracepoints; + struct tracepoint * const *tracepoints_ptrs; +}; +#endif /* CONFIG_MODULES */ + struct tracepoint_iter { - struct module *module; +#ifdef CONFIG_MODULES + struct tp_module *module; +#endif /* CONFIG_MODULES */ struct tracepoint * const *tracepoint; }; @@ -63,8 +73,6 @@ extern void tracepoint_iter_start(struct tracepoint_iter *iter); extern void tracepoint_iter_next(struct tracepoint_iter *iter); extern void tracepoint_iter_stop(struct tracepoint_iter *iter); extern void tracepoint_iter_reset(struct tracepoint_iter *iter); -extern int tracepoint_get_iter_range(struct tracepoint * const **tracepoint, - struct tracepoint * const *begin, struct tracepoint * const *end); /* * tracepoint_synchronize_unregister must be called between the last tracepoint @@ -78,17 +86,6 @@ static inline void tracepoint_synchronize_unregister(void) #define PARAMS(args...) args -#ifdef CONFIG_TRACEPOINTS -extern -void tracepoint_update_probe_range(struct tracepoint * const *begin, - struct tracepoint * const *end); -#else -static inline -void tracepoint_update_probe_range(struct tracepoint * const *begin, - struct tracepoint * const *end) -{ } -#endif /* CONFIG_TRACEPOINTS */ - #endif /* _LINUX_TRACEPOINT_H */ /* -- cgit v1.2.3 From e1c9b23adbe86c725738402857397d7a29f9d6ef Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Thu, 11 Aug 2011 00:22:51 -0400 Subject: evm: building without EVM enabled fixes - Missing 'inline' on evm_inode_setattr() definition. Introduced by commit 817b54aa45db ("evm: add evm_inode_setattr to prevent updating an invalid security.evm"). - Missing security_old_inode_init_security() stub function definition. Caused by commit 9d8f13ba3f48 ("security: new security_inode_init_security API adds function callback"). Reported-by: Stephen Rothwell Signed-off-by: Mimi Zohar Signed-off-by: James Morris --- include/linux/evm.h | 2 +- include/linux/security.h | 7 +++++++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index db5556dcdd27..62deb6557d37 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -45,7 +45,7 @@ static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, } #endif -static int evm_inode_setattr(struct dentry *dentry, struct iattr *attr) +static inline int evm_inode_setattr(struct dentry *dentry, struct iattr *attr) { return 0; } diff --git a/include/linux/security.h b/include/linux/security.h index 1c528b19a329..f399cf10e2a8 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2048,6 +2048,13 @@ static inline int security_inode_init_security(struct inode *inode, return -EOPNOTSUPP; } +int security_old_inode_init_security(struct inode *inode, struct inode *dir, + const struct qstr *qstr, char **name, + void **value, size_t *len) +{ + return -EOPNOTSUPP; +} + static inline int security_inode_create(struct inode *dir, struct dentry *dentry, int mode) -- cgit v1.2.3 From 5a4730ba9517cf2793175991243436a24b1db18f Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Thu, 11 Aug 2011 00:22:52 -0400 Subject: evm: fix evm_inode_init_security return code evm_inode_init_security() should return 0, when EVM is not enabled. (Returning an error is a remnant of evm_inode_post_init_security.) Signed-off-by: Mimi Zohar Signed-off-by: James Morris --- include/linux/evm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index 62deb6557d37..ea603c9e775d 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -85,7 +85,7 @@ static inline int evm_inode_init_security(struct inode *inode, const struct xattr *xattr_array, struct xattr *evm) { - return -EOPNOTSUPP; + return 0; } #endif /* CONFIG_EVM_H */ -- cgit v1.2.3 From ec12cb7f31e28854efae7dd6f9544e0a66379040 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Thu, 21 Jul 2011 09:43:30 -0700 Subject: sched: Accumulate per-cfs_rq cpu usage and charge against bandwidth Account bandwidth usage on the cfs_rq level versus the task_groups to which they belong. Whether we are tracking bandwidth on a given cfs_rq is maintained under cfs_rq->runtime_enabled. cfs_rq's which belong to a bandwidth constrained task_group have their runtime accounted via the update_curr() path, which withdraws bandwidth from the global pool as desired. Updates involving the global pool are currently protected under cfs_bandwidth->lock, local runtime is protected by rq->lock. This patch only assigns and tracks quota, no action is taken in the case that cfs_rq->runtime_used exceeds cfs_rq->runtime_assigned. Signed-off-by: Paul Turner Signed-off-by: Nikhil Rao Signed-off-by: Bharata B Rao Reviewed-by: Hidetoshi Seto Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110721184757.179386821@google.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ac2c0578e0f..bc6f5f2e24fa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2040,6 +2040,10 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { } static inline void sched_autogroup_exit(struct signal_struct *sig) { } #endif +#ifdef CONFIG_CFS_BANDWIDTH +extern unsigned int sysctl_sched_cfs_bandwidth_slice; +#endif + #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); -- cgit v1.2.3 From 1e39f384bb01b0395b69cb70c2cacae65012f203 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Mon, 15 Aug 2011 09:09:16 -0400 Subject: evm: fix build problems - Make the previously missing security_old_inode_init_security() stub function definition static inline. - The stub security_inode_init_security() function previously returned -EOPNOTSUPP and relied on the callers to change it to 0. The stub security/security_old_inode_init_security() functions now return 0. Reported-by: Stephen Rothwell Signed-off-by: Mimi Zohar Signed-off-by: James Morris --- include/linux/security.h | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index f399cf10e2a8..d9f7ec41ba51 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2045,14 +2045,16 @@ static inline int security_inode_init_security(struct inode *inode, initxattrs initxattrs, void *fs_data) { - return -EOPNOTSUPP; + return 0; } -int security_old_inode_init_security(struct inode *inode, struct inode *dir, - const struct qstr *qstr, char **name, - void **value, size_t *len) +static inline int security_old_inode_init_security(struct inode *inode, + struct inode *dir, + const struct qstr *qstr, + char **name, void **value, + size_t *len) { - return -EOPNOTSUPP; + return 0; } static inline int security_inode_create(struct inode *dir, -- cgit v1.2.3 From 49e2258586b423684f03c278149ab46d8f8b6700 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Tue, 9 Aug 2011 16:12:27 -0500 Subject: slub: per cpu cache for partial pages Allow filling out the rest of the kmem_cache_cpu cacheline with pointers to partial pages. The partial page list is used in slab_free() to avoid per node lock taking. In __slab_alloc() we can then take multiple partial pages off the per node partial list in one go reducing node lock pressure. We can also use the per cpu partial list in slab_alloc() to avoid scanning partial lists for pages with free objects. The main effect of a per cpu partial list is that the per node list_lock is taken for batches of partial pages instead of individual ones. Potential future enhancements: 1. The pickup from the partial list could be perhaps be done without disabling interrupts with some work. The free path already puts the page into the per cpu partial list without disabling interrupts. 2. __slab_free() may have some code paths that could use optimization. Performance: Before After ./hackbench 100 process 200000 Time: 1953.047 1564.614 ./hackbench 100 process 20000 Time: 207.176 156.940 ./hackbench 100 process 20000 Time: 204.468 156.940 ./hackbench 100 process 20000 Time: 204.879 158.772 ./hackbench 10 process 20000 Time: 20.153 15.853 ./hackbench 10 process 20000 Time: 20.153 15.986 ./hackbench 10 process 20000 Time: 19.363 16.111 ./hackbench 1 process 20000 Time: 2.518 2.307 ./hackbench 1 process 20000 Time: 2.258 2.339 ./hackbench 1 process 20000 Time: 2.864 2.163 Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/mm_types.h | 14 +++++++++++++- include/linux/slub_def.h | 4 ++++ 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 774b8952deb4..7870e473033c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -79,9 +79,21 @@ struct page { }; /* Third double word block */ - struct list_head lru; /* Pageout list, eg. active_list + union { + struct list_head lru; /* Pageout list, eg. active_list * protected by zone->lru_lock ! */ + struct { /* slub per cpu partial pages */ + struct page *next; /* Next partial slab */ +#ifdef CONFIG_64BIT + int pages; /* Nr of partial slabs left */ + int pobjects; /* Approximate # of objects */ +#else + short int pages; + short int pobjects; +#endif + }; + }; /* Remainder is not double word aligned */ union { diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index f58d6413d230..4890ef79d752 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -36,12 +36,15 @@ enum stat_item { ORDER_FALLBACK, /* Number of times fallback was necessary */ CMPXCHG_DOUBLE_CPU_FAIL,/* Failure of this_cpu_cmpxchg_double */ CMPXCHG_DOUBLE_FAIL, /* Number of times that cmpxchg double did not match */ + CPU_PARTIAL_ALLOC, /* Used cpu partial on alloc */ + CPU_PARTIAL_FREE, /* USed cpu partial on free */ NR_SLUB_STAT_ITEMS }; struct kmem_cache_cpu { void **freelist; /* Pointer to next available object */ unsigned long tid; /* Globally unique transaction id */ struct page *page; /* The slab from which we are allocating */ + struct page *partial; /* Partially allocated frozen slabs */ int node; /* The node of the page (or -1 for debug) */ #ifdef CONFIG_SLUB_STATS unsigned stat[NR_SLUB_STAT_ITEMS]; @@ -79,6 +82,7 @@ struct kmem_cache { int size; /* The size of an object including meta data */ int objsize; /* The size of an object without meta data */ int offset; /* Free pointer offset. */ + int cpu_partial; /* Number of per cpu partial pages to keep around */ struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ -- cgit v1.2.3 From 710b7216964d6455cf1b215c43b03a1a79008c7d Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 26 Jul 2011 16:28:29 -0400 Subject: locks: move F_INPROGRESS from fl_type to fl_flags field F_INPROGRESS isn't exposed to userspace. To me it makes more sense in fl_flags.... Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- 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 178cdb4f1d4a..327fdd4de85f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1065,6 +1065,7 @@ static inline int file_check_writeable(struct file *filp) #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ +#define FL_INPROGRESS 256 /* Lease is being broken */ /* * Special return value from posix_lock_file() and vfs_lock_file() for @@ -1111,7 +1112,7 @@ struct file_lock { struct list_head fl_link; /* doubly linked list of all locks */ struct list_head fl_block; /* circular list of blocked processes */ fl_owner_t fl_owner; - unsigned char fl_flags; + unsigned int fl_flags; unsigned char fl_type; unsigned int fl_pid; struct pid *fl_nspid; -- cgit v1.2.3 From 778fc546f749c588aa2f6cd50215d2715c374252 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 26 Jul 2011 18:25:49 -0400 Subject: locks: fix tracking of inprogress lease breaks We currently use a bit in fl_flags to record whether a lease is being broken, and set fl_type to the type (RDLCK or UNLCK) that it will eventually have. This means that once the lease break starts, we forget what the lease's type *used* to be. Breaking a read lease will then result in blocking read opens, even though there's no conflict--because the lease type is now F_UNLCK and we can no longer tell whether it was previously a read or write lease. So, instead keep fl_type as the original type (the type which we enforce), and keep track of whether we're unlocking or merely downgrading by replacing the single FL_INPROGRESS flag by FL_UNLOCK_PENDING and FL_DOWNGRADE_PENDING flags. To get this right we also need to track separate downgrade and break times, to handle the case where a write-leased file gets conflicting opens first for read, then later for write. (I first considered just eliminating the downgrade behavior completely--nfsv4 doesn't need it, and nobody as far as I can tell actually uses it currently--but Jeremy Allison tells me that Windows oplocks do behave this way, so Samba will probably use this some day.) Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/fs.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 327fdd4de85f..76460edf1648 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1065,7 +1065,8 @@ static inline int file_check_writeable(struct file *filp) #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ -#define FL_INPROGRESS 256 /* Lease is being broken */ +#define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ +#define FL_UNLOCK_PENDING 512 /* Lease is being broken */ /* * Special return value from posix_lock_file() and vfs_lock_file() for @@ -1122,7 +1123,9 @@ struct file_lock { loff_t fl_end; struct fasync_struct * fl_fasync; /* for lease break notifications */ - unsigned long fl_break_time; /* for nonblocking lease breaks */ + /* for lease breaks: */ + unsigned long fl_break_time; + unsigned long fl_downgrade_time; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ -- cgit v1.2.3 From 11fd165c68b73434ca1273e21f21db5eecc90926 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 28 Jul 2011 20:04:09 +0200 Subject: sunrpc: use better NUMA affinities Use NUMA aware allocations to reduce latencies and increase throughput. sunrpc kthreads can use kthread_create_on_node() if pool_mode is "percpu" or "pernode", and svc_prepare_thread()/svc_init_buffer() can also take into account NUMA node affinity for memory allocations. Signed-off-by: Eric Dumazet CC: "J. Bruce Fields" CC: Neil Brown CC: David Miller Reviewed-by: Greg Banks [bfields@redhat.com: fix up caller nfs41_callback_up] Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 223588a976a0..a78a51e93373 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -404,7 +404,7 @@ struct svc_procedure { struct svc_serv *svc_create(struct svc_program *, unsigned int, void (*shutdown)(struct svc_serv *)); struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, - struct svc_pool *pool); + struct svc_pool *pool, int node); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, void (*shutdown)(struct svc_serv *), -- cgit v1.2.3 From 5b1b0b812a7b1a5b968c5d06d90d1cb88621b941 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 19 Aug 2011 23:49:48 +0200 Subject: PM / Runtime: Add macro to test for runtime PM events This patch (as1482) adds a macro for testing whether or not a pm_message value represents an autosuspend or autoresume (i.e., a runtime PM) event. Encapsulating this notion seems preferable to open-coding the test all over the place. Signed-off-by: Alan Stern Acked-by: Greg Kroah-Hartman Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index f7c84c9abd30..18de9f893497 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -366,6 +366,8 @@ extern struct dev_pm_ops generic_subsys_pm_ops; #define PMSG_AUTO_RESUME ((struct pm_message) \ { .event = PM_EVENT_AUTO_RESUME, }) +#define PMSG_IS_AUTO(msg) (((msg).event & PM_EVENT_AUTO) != 0) + /** * Device run-time power management status. * -- cgit v1.2.3 From bd20eb541ebbb17a5e047cd20e74b9ccf19a4123 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 19 Aug 2011 18:09:38 +0900 Subject: regmap: Allow drivers to specify register defaults It is useful for the register cache code to be able to specify the default values for the device registers. The major use is when restoring the register cache after suspend, knowing the register defaults allows us to skip registers that are at their default values when we resume which can be a substantial win on larger modern devices. For some devices (mostly older ones) the hardware does not support readback so the only way we can know the values is from code and so initializing the cache with default values makes it much easier for drivers work with read/modify/write updates. Signed-off-by: Mark Brown --- include/linux/regmap.h | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4de137bc16a7..e2200f21c602 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -20,13 +20,25 @@ struct i2c_client; struct spi_device; +/** + * Default value for a register. We use an array of structs rather + * than a simple array as many modern devices have very sparse + * register maps. + * + * @reg: Register address. + * @def: Register default value. + */ +struct reg_default { + unsigned int reg; + unsigned int def; +}; + /** * Configuration for the register map of a device. * * @reg_bits: Number of bits in a register address, mandatory. * @val_bits: Number of bits in a register value, mandatory. * - * @max_register: Optional, specifies the maximum valid register index. * @writeable_reg: Optional callback returning true if the register * can be written to. * @readable_reg: Optional callback returning true if the register @@ -36,16 +48,24 @@ struct spi_device; * @precious_reg: Optional callback returning true if the rgister * should not be read outside of a call from the driver * (eg, a clear on read interrupt status register). + * + * @max_register: Optional, specifies the maximum valid register index. + * @reg_defaults: Power on reset values for registers (for use with + * register cache support). + * @num_reg_defaults: Number of elements in reg_defaults. */ struct regmap_config { int reg_bits; int val_bits; - unsigned int max_register; bool (*writeable_reg)(struct device *dev, unsigned int reg); bool (*readable_reg)(struct device *dev, unsigned int reg); bool (*volatile_reg)(struct device *dev, unsigned int reg); bool (*precious_reg)(struct device *dev, unsigned int reg); + + unsigned int max_register; + struct reg_default *reg_defaults; + int num_reg_defaults; }; typedef int (*regmap_hw_write)(struct device *dev, const void *data, -- cgit v1.2.3 From 1df5981b82d9eabdd6e66d1d9514164c02329345 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 10 Jun 2011 19:28:10 +0100 Subject: mfd: Convert WM831x to use regmap API Factor out the register read/write code to use the register map API. We still need some wm831x specific code and locking in place to check that the user key is handled correctly but only on the write side, reads are not affected by the key. Signed-off-by: Mark Brown Acked-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 8dda8ded5cda..44acdb25681b 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -18,6 +18,7 @@ #include #include #include +#include /* * Register values. @@ -361,12 +362,8 @@ struct wm831x { struct mutex io_lock; struct device *dev; - int (*read_dev)(struct wm831x *wm831x, unsigned short reg, - int bytes, void *dest); - int (*write_dev)(struct wm831x *wm831x, unsigned short reg, - int bytes, void *src); - void *control_data; + struct regmap *regmap; int irq; /* Our chip IRQ */ struct mutex irq_lock; @@ -416,4 +413,6 @@ int wm831x_irq_init(struct wm831x *wm831x, int irq); void wm831x_irq_exit(struct wm831x *wm831x); void wm831x_auxadc_init(struct wm831x *wm831x); +extern struct regmap_config wm831x_regmap_config; + #endif -- cgit v1.2.3 From d6c645fc00777a6f8a7df1f580065ec30c71be7b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 17 Jun 2011 13:02:27 +0100 Subject: mfd: Convert WM8994 to use new register map API Signed-off-by: Mark Brown Acked-by: Samuel Ortiz --- include/linux/mfd/wm8994/core.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8994/core.h b/include/linux/mfd/wm8994/core.h index f0b69cdae41c..45df450d869f 100644 --- a/include/linux/mfd/wm8994/core.h +++ b/include/linux/mfd/wm8994/core.h @@ -24,6 +24,7 @@ enum wm8994_type { struct regulator_dev; struct regulator_bulk_data; +struct regmap; #define WM8994_NUM_GPIO_REGS 11 #define WM8994_NUM_LDO_REGS 2 @@ -50,18 +51,12 @@ struct regulator_bulk_data; #define WM8994_IRQ_GPIO(x) (x + WM8994_IRQ_TEMP_WARN) struct wm8994 { - struct mutex io_lock; struct mutex irq_lock; enum wm8994_type type; struct device *dev; - int (*read_dev)(struct wm8994 *wm8994, unsigned short reg, - int bytes, void *dest); - int (*write_dev)(struct wm8994 *wm8994, unsigned short reg, - int bytes, const void *src); - - void *control_data; + struct regmap *regmap; int gpio_base; int irq_base; -- cgit v1.2.3 From 50eeef5d3cea5afcced17a0410e8b0bf88997845 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 9 Aug 2011 16:34:29 +0900 Subject: mfd: Convert WM8400 to regmap API Signed-off-by: Mark Brown --- include/linux/mfd/wm8400-private.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/wm8400-private.h b/include/linux/mfd/wm8400-private.h index 2aab4e93a5c9..0147b6968510 100644 --- a/include/linux/mfd/wm8400-private.h +++ b/include/linux/mfd/wm8400-private.h @@ -25,16 +25,15 @@ #include #include +struct regmap; + #define WM8400_REGISTER_COUNT 0x55 struct wm8400 { struct device *dev; - int (*read_dev)(void *data, char reg, int count, u16 *dst); - int (*write_dev)(void *data, char reg, int count, const u16 *src); - struct mutex io_lock; - void *io_data; + struct regmap *regmap; u16 reg_cache[WM8400_REGISTER_COUNT]; -- cgit v1.2.3 From 939f325f4a0fb7eb189268a4593e427d3a075514 Mon Sep 17 00:00:00 2001 From: "kuninori.morimoto.gx@renesas.com" Date: Mon, 25 Jul 2011 00:39:30 -0700 Subject: usb: add usb_endpoint_maxp() macro Signed-off-by: Kuninori Morimoto Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 0fd3fbdd8283..e809deabf503 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -34,6 +34,7 @@ #define __LINUX_USB_CH9_H #include /* __u8 etc */ +#include /* le16_to_cpu */ /*-------------------------------------------------------------------------*/ @@ -570,6 +571,17 @@ static inline int usb_endpoint_is_isoc_out( return usb_endpoint_xfer_isoc(epd) && usb_endpoint_dir_out(epd); } +/** + * usb_endpoint_maxp - get endpoint's max packet size + * @epd: endpoint to be checked + * + * Returns @epd's max packet + */ +static inline int usb_endpoint_maxp(const struct usb_endpoint_descriptor *epd) +{ + return le16_to_cpu(epd->wMaxPacketSize); +} + /*-------------------------------------------------------------------------*/ /* USB_DT_SS_ENDPOINT_COMP: SuperSpeed Endpoint Companion descriptor */ -- cgit v1.2.3 From da6819dbffb34861b79d91c05c4eeb37a3792433 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 19 Aug 2011 18:10:56 +0300 Subject: usb: ch9: add function defines from ch9, USB 3.0 spec not to confuse with Table 9-7 in USB 2.0 spec Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Felipe Balbi Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index e809deabf503..1ded281eff88 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -144,6 +144,11 @@ #define USB_INTRF_FUNC_SUSPEND 0 /* function suspend */ #define USB_INTR_FUNC_SUSPEND_OPT_MASK 0xFF00 +/* + * Suspend Options, Table 9-7 USB 3.0 spec + */ +#define USB_INTRF_FUNC_SUSPEND_LP (1 << (8 + 0)) +#define USB_INTRF_FUNC_SUSPEND_RW (1 << (8 + 1)) #define USB_ENDPOINT_HALT 0 /* IN/OUT will STALL */ -- cgit v1.2.3 From cbc4663552ee476f57933920d782222d94878e7e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 11 Aug 2011 14:36:21 -0400 Subject: dynamic_debug: Add __dynamic_dev_dbg Unlike dynamic_pr_debug, dynamic uses of dev_dbg can not currently add task_pid/KBUILD_MODNAME/__func__/__LINE__ to selected debug output. Add a new function similar to dynamic_pr_debug to optionally emit these prefixes. Cc: Aloisio Almeida Noticed-by: Aloisio Almeida Signed-off-by: Joe Perches Signed-off-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- include/linux/device.h | 5 +++++ include/linux/dynamic_debug.h | 10 ++++++++-- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c20dfbfc49b4..4639419522da 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -785,6 +785,8 @@ extern const char *dev_driver_string(const struct device *dev); #ifdef CONFIG_PRINTK +extern int __dev_printk(const char *level, const struct device *dev, + struct va_format *vaf); extern int dev_printk(const char *level, const struct device *dev, const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); @@ -805,6 +807,9 @@ extern int _dev_info(const struct device *dev, const char *fmt, ...) #else +static inline int __dev_printk(const char *level, const struct device *dev, + struct va_format *vaf) + { return 0; } static inline int dev_printk(const char *level, const struct device *dev, const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index e747ecd48e1c..bdf15319944e 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -47,6 +47,13 @@ extern int ddebug_remove_module(const char *mod_name); extern int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...) __attribute__ ((format (printf, 2, 3))); +struct device; + +extern int __dynamic_dev_dbg(struct _ddebug *descriptor, + const struct device *dev, + const char *fmt, ...) + __attribute__ ((format (printf, 3, 4))); + #define dynamic_pr_debug(fmt, ...) do { \ static struct _ddebug descriptor \ __used \ @@ -57,7 +64,6 @@ extern int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...) __dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) - #define dynamic_dev_dbg(dev, fmt, ...) do { \ static struct _ddebug descriptor \ __used \ @@ -65,7 +71,7 @@ extern int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...) { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ _DPRINTK_FLAGS_DEFAULT }; \ if (unlikely(descriptor.enabled)) \ - dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); \ + __dynamic_dev_dbg(&descriptor, dev, fmt, ##__VA_ARGS__); \ } while (0) #else -- cgit v1.2.3 From fae8d206a188080d3d23b621fc2652f15f3457b6 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 11 Aug 2011 14:36:38 -0400 Subject: dynamic_debug: remove unused control variables Remove no longer used dynamic debug control variables. The definitions were removed a while ago, but we forgot to clean up the extern references. Signed-off-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- include/linux/dynamic_debug.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index bdf15319944e..843cb9eb4226 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -1,13 +1,6 @@ #ifndef _DYNAMIC_DEBUG_H #define _DYNAMIC_DEBUG_H -/* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which - * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They - * use independent hash functions, to reduce the chance of false positives. - */ -extern long long dynamic_debug_enabled; -extern long long dynamic_debug_enabled2; - /* * An instance of this structure is created in a special * ELF section at every dynamic debug callsite. At runtime, -- cgit v1.2.3 From ffa10cb47a94c9b456c83301c8047e2a898dd409 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 11 Aug 2011 14:36:48 -0400 Subject: dynamic_debug: make netdev_dbg() call __netdev_printk() Previously, if dynamic debug was enabled netdev_dbg() was using dynamic_dev_dbg() to print out the underlying msg. Fix this by making sure netdev_dbg() uses __netdev_printk(). Cc: David S. Miller Signed-off-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- include/linux/dynamic_debug.h | 17 +++++++++++++++++ include/linux/netdevice.h | 6 ++++-- 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 843cb9eb4226..feaac1ee3001 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -47,6 +47,13 @@ extern int __dynamic_dev_dbg(struct _ddebug *descriptor, const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); +struct net_device; + +extern int __dynamic_netdev_dbg(struct _ddebug *descriptor, + const struct net_device *dev, + const char *fmt, ...) + __attribute__ ((format (printf, 3, 4))); + #define dynamic_pr_debug(fmt, ...) do { \ static struct _ddebug descriptor \ __used \ @@ -67,6 +74,16 @@ extern int __dynamic_dev_dbg(struct _ddebug *descriptor, __dynamic_dev_dbg(&descriptor, dev, fmt, ##__VA_ARGS__); \ } while (0) +#define dynamic_netdev_dbg(dev, fmt, ...) do { \ + static struct _ddebug descriptor \ + __used \ + __attribute__((section("__verbose"), aligned(8))) = \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ + _DPRINTK_FLAGS_DEFAULT }; \ + if (unlikely(descriptor.enabled)) \ + __dynamic_netdev_dbg(&descriptor, dev, fmt, ##__VA_ARGS__);\ + } while (0) + #else static inline int ddebug_remove_module(const char *mod) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ddee79bb8f15..9333a0300c5e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2617,6 +2617,9 @@ static inline const char *netdev_name(const struct net_device *dev) return dev->name; } +extern int __netdev_printk(const char *level, const struct net_device *dev, + struct va_format *vaf); + extern int netdev_printk(const char *level, const struct net_device *dev, const char *format, ...) __attribute__ ((format (printf, 3, 4))); @@ -2644,8 +2647,7 @@ extern int netdev_info(const struct net_device *dev, const char *format, ...) #elif defined(CONFIG_DYNAMIC_DEBUG) #define netdev_dbg(__dev, format, args...) \ do { \ - dynamic_dev_dbg((__dev)->dev.parent, "%s: " format, \ - netdev_name(__dev), ##args); \ + dynamic_netdev_dbg(__dev, format, ##args); \ } while (0) #else #define netdev_dbg(__dev, format, args...) \ -- cgit v1.2.3 From b5fb0a03214dfd02bc34bda659d5b89ef12741b2 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 11 Aug 2011 14:36:53 -0400 Subject: dynamic_debug: make netif_dbg() call __netdev_printk() Previously, netif_dbg() was using dynamic_dev_dbg() to perform the underlying printk. Fix it to use __netdev_printk(), instead. Cc: David S. Miller Signed-off-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- include/linux/netdevice.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9333a0300c5e..279726039f00 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2714,9 +2714,7 @@ do { \ #define netif_dbg(priv, type, netdev, format, args...) \ do { \ if (netif_msg_##type(priv)) \ - dynamic_dev_dbg((netdev)->dev.parent, \ - "%s: " format, \ - netdev_name(netdev), ##args); \ + dynamic_netdev_dbg(netdev, format, ##args); \ } while (0) #else #define netif_dbg(priv, type, dev, format, args...) \ -- cgit v1.2.3 From 29cc88979a8818cd8c5019426e945aed118b400e Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Tue, 23 Aug 2011 03:12:03 -0700 Subject: USB: use usb_endpoint_maxp() instead of le16_to_cpu() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now ${LINUX}/drivers/usb/* can use usb_endpoint_maxp(desc) to get maximum packet size instead of le16_to_cpu(desc->wMaxPacketSize). This patch fix it up Cc: Armin Fuerst Cc: Pavel Machek Cc: Johannes Erdfelt Cc: Vojtech Pavlik Cc: Oliver Neukum Cc: David Kubicek Cc: Johan Hovold Cc: Brad Hards Acked-by: Felipe Balbi Cc: Sebastian Andrzej Siewior Cc: Thomas Dahlmann Cc: David Brownell Cc: David Lopo Cc: Alan Stern Cc: Michal Nazarewicz Cc: Xie Xiaobo Cc: Li Yang Cc: Jiang Bo Cc: Yuan-hsin Chen Cc: Darius Augulis Cc: Xiaochen Shen Cc: Yoshihiro Shimoda Cc: OKI SEMICONDUCTOR, Cc: Robert Jarzmik Cc: Ben Dooks Cc: Thomas Abraham Cc: Herbert Pötzl Cc: Arnaud Patard Cc: Roman Weissgaerber Acked-by: Sarah Sharp Cc: Tony Olech Cc: Florian Floe Echtler Cc: Christian Lucht Cc: Juergen Stuber Cc: Georges Toth Cc: Bill Ryder Cc: Kuba Ober Cc: Inaky Perez-Gonzalez Signed-off-by: Kuninori Morimoto Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 73c7df489607..c19f9100c307 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1574,7 +1574,7 @@ usb_maxpacket(struct usb_device *udev, int pipe, int is_out) return 0; /* NOTE: only 0x07ff bits are for packet size... */ - return le16_to_cpu(ep->desc.wMaxPacketSize); + return usb_endpoint_maxp(&ep->desc); } /* ----------------------------------------------------------------------- */ -- cgit v1.2.3 From 6a3e492b6daaf7ec4dc41e51d87d2aae8ff886f2 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 14 Jul 2011 14:35:12 +0200 Subject: TTY: serial, remove tasklet for tty_wakeup tty_wakeup can be called from any context. So there is no need to have an extra tasklet for calling that. Hence save some space and remove the tasklet completely. Signed-off-by: Jiri Slaby Cc: Alan Cox 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 a5c31146a337..76e110363745 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -384,7 +384,6 @@ struct uart_state { int pm_state; struct circ_buf xmit; - struct tasklet_struct tlet; struct uart_port *uart_port; }; -- cgit v1.2.3 From 906cbe1364d94da7cbf74c1d05e3e78b2883f661 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 14 Jul 2011 14:35:14 +0200 Subject: TTY: remove tty_locked We used it really only serial and ami_serial. The rest of the callsites were BUG/WARN_ONs to check if BTM is held. Now that we pruned tty_locked from both of the real users, we can get rid of tty_lock along with __big_tty_mutex_owner. Signed-off-by: Jiri Slaby Acked-by: Arnd Bergmann Cc: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 44bc0c5617e1..6d5eceb165be 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -600,8 +600,6 @@ extern long vt_compat_ioctl(struct tty_struct *tty, /* functions for preparation of BKL removal */ extern void __lockfunc tty_lock(void) __acquires(tty_lock); extern void __lockfunc tty_unlock(void) __releases(tty_lock); -extern struct task_struct *__big_tty_mutex_owner; -#define tty_locked() (current == __big_tty_mutex_owner) /* * wait_event_interruptible_tty -- wait for a condition with the tty lock held -- cgit v1.2.3 From a74036f51272975e9538e80cd1bb64dce164b208 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Mon, 15 Aug 2011 10:17:51 +0100 Subject: tty: serial: allow ports to override the irq handler Some serial ports may have unusal requirements for interrupt handling (e.g. the Synopsys DesignWare 8250-alike port and it's busy detect interrupt). Add a .handle_irq callback that can be used for platforms to override the interrupt behaviour in a similar fashion to the .serial_out and .serial_in callbacks. Signed-off-by: Jamie Iles Acked-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 76e110363745..c31ae43c073d 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -300,6 +300,7 @@ struct uart_port { void (*set_termios)(struct uart_port *, struct ktermios *new, struct ktermios *old); + int (*handle_irq)(struct uart_port *); void (*pm)(struct uart_port *, unsigned int state, unsigned int old); unsigned int irq; /* irq number */ -- cgit v1.2.3 From 583d28e92f667eb6cc81ea87daaa7e321c23fe14 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Mon, 15 Aug 2011 10:17:52 +0100 Subject: tty: serial8250: allow platforms to override irq handler Some ports (e.g. Synopsys DesignWare 8250) have special requirements for handling the interrupts. Allow these platforms to specify their own interrupt handler that will override the default. serial8250_handle_irq() is provided so that platforms can extend the IRQ handler rather than completely replacing it. Signed-off-by: Jamie Iles Acked-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 97f5b45bbc07..1f05bbeac01e 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -35,6 +35,7 @@ struct plat_serial8250_port { void (*set_termios)(struct uart_port *, struct ktermios *new, struct ktermios *old); + int (*handle_irq)(struct uart_port *); void (*pm)(struct uart_port *, unsigned int state, unsigned old); }; @@ -80,6 +81,7 @@ extern void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old); extern void serial8250_do_pm(struct uart_port *port, unsigned int state, unsigned int oldstate); +int serial8250_handle_irq(struct uart_port *port, unsigned int iir); extern void serial8250_set_isa_configurator(void (*v) (int port, struct uart_port *up, -- cgit v1.2.3 From 4834d028978583dfe8e1fc19f1180ceb03d8dfb7 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Mon, 15 Aug 2011 10:17:55 +0100 Subject: tty: serial8250: remove UPIO_DWAPB{,32} Now that platforms can override the port IRQ handler and the only user of these UPIO modes has been converted over, kill off UPIO_DWAPB and UPIO_DWAPB32. Acked-by: Alan Cox Signed-off-by: Jamie Iles Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index c31ae43c073d..493773e3b46d 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -318,9 +318,7 @@ struct uart_port { #define UPIO_MEM32 (3) #define UPIO_AU (4) /* Au1x00 type IO */ #define UPIO_TSI (5) /* Tsi108/109 type IO */ -#define UPIO_DWAPB (6) /* DesignWare APB UART */ -#define UPIO_RM9000 (7) /* RM9000 type IO */ -#define UPIO_DWAPB32 (8) /* DesignWare APB UART (32 bit accesses) */ +#define UPIO_RM9000 (6) /* RM9000 type IO */ unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ -- cgit v1.2.3 From 6b1a98d1c4851235d9b6764b3f7b7db7909fc760 Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Tue, 16 Aug 2011 17:47:46 +0100 Subject: tty: serial8250: add helpers for the DesignWare 8250 The Synopsys DesignWare 8250 is an 8250 that has an extra interrupt that gets raised when writing to the LCR when busy. To handle this we need special serial_out, serial_in and handle_irq methods. Add a new function serial8250_use_designware_io() that configures a uart_port with these accessors. Cc: Alan Cox Acked-by: Arnd Bergmann Signed-off-by: Jamie Iles Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 1f05bbeac01e..09e2dbcd7ca3 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -86,5 +86,13 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir); extern void serial8250_set_isa_configurator(void (*v) (int port, struct uart_port *up, unsigned short *capabilities)); +#ifndef SERIAL_8250_DW +extern int serial8250_use_designware_io(struct uart_port *up); +#else +static inline int serial8250_use_designware_io(struct uart_port *up) +{ + return -EIO; +} +#endif #endif -- cgit v1.2.3 From 9a234349de01de3437784c0ef03d95353f055fae Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 24 Aug 2011 15:25:49 -0700 Subject: Revert "tty: serial8250: add helpers for the DesignWare 8250" This reverts commit 6b1a98d1c4851235d9b6764b3f7b7db7909fc760. It causes a build error that needs to be resolved differently. Cc: Alan Cox Cc: Arnd Bergmann Cc: Jamie Iles Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_8250.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 09e2dbcd7ca3..1f05bbeac01e 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -86,13 +86,5 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir); extern void serial8250_set_isa_configurator(void (*v) (int port, struct uart_port *up, unsigned short *capabilities)); -#ifndef SERIAL_8250_DW -extern int serial8250_use_designware_io(struct uart_port *up); -#else -static inline int serial8250_use_designware_io(struct uart_port *up) -{ - return -EIO; -} -#endif #endif -- cgit v1.2.3 From 83cac9f3b45ba8e99c5305be42c67f1c83adf0aa Mon Sep 17 00:00:00 2001 From: Bernhard Roth Date: Wed, 24 Aug 2011 09:48:23 +0200 Subject: atmel_serial: RS485: receiving enabled when sending data By default the atmel_serial driver in RS485 mode disables receiving data until all data in the send buffer has been sent. This flag allows to receive data even whilst sending data. Signed-off-by: Bernhard Roth Signed-off-by: Claudio Scordino Acked-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/serial.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/serial.h b/include/linux/serial.h index ef914061511e..97ff8e27a6cc 100644 --- a/include/linux/serial.h +++ b/include/linux/serial.h @@ -211,6 +211,7 @@ struct serial_rs485 { #define SER_RS485_RTS_ON_SEND (1 << 1) #define SER_RS485_RTS_AFTER_SEND (1 << 2) #define SER_RS485_RTS_BEFORE_SEND (1 << 3) +#define SER_RS485_RX_DURING_TX (1 << 4) __u32 delay_rts_before_send; /* Milliseconds */ __u32 delay_rts_after_send; /* Milliseconds */ __u32 padding[5]; /* Memory is cheap, new structs -- cgit v1.2.3 From c4bb3160c8823d3a1e581d7e05fb8b343097e7c8 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 8 Aug 2011 23:43:04 +0200 Subject: PM / Domains: Implement subdomain counters as atomic fields Currently, pm_genpd_poweron() and pm_genpd_poweroff() need to take the parent PM domain's lock in order to modify the parent's counter of active subdomains in a nonracy way. This causes the locking to be considerably complex and in fact is not necessary, because the subdomain counters may be implemented as atomic fields and they won't have to be modified under a lock. Replace the unsigned in sd_count field in struct generic_pm_domain by an atomic_t one and modify the code in drivers/base/power/domain.c to take this change into account. This patch doesn't change the locking yet, that is going to be done in a separate subsequent patch. Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index f9ec1736a116..81c5782d90a3 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -33,7 +33,7 @@ struct generic_pm_domain { struct dev_power_governor *gov; struct work_struct power_off_work; unsigned int in_progress; /* Number of devices being suspended now */ - unsigned int sd_count; /* Number of subdomains with power "on" */ + atomic_t sd_count; /* Number of subdomains with power "on" */ enum gpd_status status; /* Current state of the domain */ wait_queue_head_t status_wait_queue; struct task_struct *poweroff_task; /* Powering off task */ -- cgit v1.2.3 From 3f241775c30365c33a0d2f6d40f4cf12470f48c6 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 8 Aug 2011 23:43:29 +0200 Subject: PM / Domains: Add "wait for parent" status for generic PM domains The next patch will make it possible for a generic PM domain to have multiple parents (i.e. multiple PM domains it depends on). To prepare for that change it is necessary to change pm_genpd_poweron() so that it doesn't jump to the start label after running itself recursively for the parent domain. For this purpose, introduce a new PM domain status value GPD_STATE_WAIT_PARENT that will be set by pm_genpd_poweron() before calling itself recursively for the parent domain and modify the code in drivers/base/power/domain.c so that the GPD_STATE_WAIT_PARENT status is guaranteed to be preserved during the execution of pm_genpd_poweron() for the parent. This change also causes pm_genpd_add_subdomain() and pm_genpd_remove_subdomain() to wait for started pm_genpd_poweron() to complete and allows pm_genpd_runtime_resume() to avoid dropping the lock after powering on the PM domain. Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 81c5782d90a3..97e3f8eb4978 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -13,6 +13,7 @@ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ + GPD_STATE_WAIT_PARENT, /* PM domain's parent is being waited for */ GPD_STATE_BUSY, /* Something is happening to the PM domain */ GPD_STATE_REPEAT, /* Power off in progress, to be repeated */ GPD_STATE_POWER_OFF, /* PM domain is off */ -- cgit v1.2.3 From 5063ce1571b73865cbdcd92db002e85809750c97 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 8 Aug 2011 23:43:40 +0200 Subject: PM / Domains: Allow generic PM domains to have multiple masters Currently, for a given generic PM domain there may be only one parent domain (i.e. a PM domain it depends on). However, there is at least one real-life case in which there should be two parents (masters) for one PM domain (the A3RV domain on SH7372 turns out to depend on the A4LC domain and it depends on the A4R domain and the same time). For this reason, allow a PM domain to have multiple parents (masters) by introducing objects representing links between PM domains. The (logical) links between PM domains represent relationships in which one domain is a master (i.e. it is depended on) and another domain is a slave (i.e. it depends on the master) with the rule that the slave cannot be powered on if the master is not powered on and the master cannot be powered off if the slave is not powered off. Each struct generic_pm_domain object representing a PM domain has two lists of links, a list of links in which it is a master and a list of links in which it is a slave. The first of these lists replaces the list of subdomains and the second one is used in place of the parent pointer. Each link is represented by struct gpd_link object containing pointers to the master and the slave and two struct list_head members allowing it to hook into two lists (the master's list of "master" links and the slave's list of "slave" links). This allows the code to get to the link from each side (either from the master or from the slave) and follow it in each direction. Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 97e3f8eb4978..5f5154d79253 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -26,9 +26,8 @@ struct dev_power_governor { struct generic_pm_domain { struct dev_pm_domain domain; /* PM domain operations */ struct list_head gpd_list_node; /* Node in the global PM domains list */ - struct list_head sd_node; /* Node in the parent's subdomain list */ - struct generic_pm_domain *parent; /* Parent PM domain */ - struct list_head sd_list; /* List of dubdomains */ + struct list_head master_links; /* Links with PM domain as a master */ + struct list_head slave_links; /* Links with PM domain as a slave */ struct list_head dev_list; /* List of devices */ struct mutex lock; struct dev_power_governor *gov; @@ -55,6 +54,13 @@ static inline struct generic_pm_domain *pd_to_genpd(struct dev_pm_domain *pd) return container_of(pd, struct generic_pm_domain, domain); } +struct gpd_link { + struct generic_pm_domain *master; + struct list_head master_node; + struct generic_pm_domain *slave; + struct list_head slave_node; +}; + struct dev_list_entry { struct list_head node; struct device *dev; -- cgit v1.2.3 From 17877eb5a900f32bb5827a7b2109b6c9adff5fc3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 8 Aug 2011 23:43:50 +0200 Subject: PM / Domains: Rename GPD_STATE_WAIT_PARENT to GPD_STATE_WAIT_MASTER Since it is now possible for a PM domain to have multiple masters instead of one parent, rename the "wait for parent" status to reflect the new situation. Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 5f5154d79253..bf679f59f9a8 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -13,7 +13,7 @@ enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ - GPD_STATE_WAIT_PARENT, /* PM domain's parent is being waited for */ + GPD_STATE_WAIT_MASTER, /* PM domain's master is being waited for */ GPD_STATE_BUSY, /* Something is happening to the PM domain */ GPD_STATE_REPEAT, /* Power off in progress, to be repeated */ GPD_STATE_POWER_OFF, /* PM domain is off */ -- cgit v1.2.3 From 5c095a0e0d600d5a5a4207eaadabd18db46395ce Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 25 Aug 2011 15:33:50 +0200 Subject: PM: Introduce struct pm_subsys_data Introduce struct pm_subsys_data that may be subclassed by subsystems to store subsystem-specific information related to the device. Move the clock management fields accessed through the power.subsys_data pointer in struct device to the new strucutre. Signed-off-by: Rafael J. Wysocki --- include/linux/device.h | 5 +++++ include/linux/pm.h | 9 ++++++++- include/linux/pm_runtime.h | 8 ++++++-- 3 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c20dfbfc49b4..5d200ed0071a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -636,6 +636,11 @@ static inline void set_dev_node(struct device *dev, int node) } #endif +static inline struct pm_subsys_data *dev_to_psd(struct device *dev) +{ + return dev ? dev->power.subsys_data : NULL; +} + static inline unsigned int dev_get_uevent_suppress(const struct device *dev) { return dev->kobj.uevent_suppress; diff --git a/include/linux/pm.h b/include/linux/pm.h index f7c84c9abd30..bf5ee37388d4 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -421,6 +421,13 @@ enum rpm_request { struct wakeup_source; +struct pm_subsys_data { + spinlock_t lock; +#ifdef CONFIG_PM_CLK + struct list_head clock_list; +#endif +}; + struct dev_pm_info { pm_message_t power_state; unsigned int can_wakeup:1; @@ -462,7 +469,7 @@ struct dev_pm_info { unsigned long suspended_jiffies; unsigned long accounting_timestamp; #endif - void *subsys_data; /* Owned by the subsystem. */ + struct pm_subsys_data *subsys_data; /* Owned by the subsystem. */ }; extern void update_pm_runtime_accounting(struct device *dev); diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index daac05d751b2..6b90630e3c98 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -258,14 +258,18 @@ struct pm_clk_notifier_block { }; #ifdef CONFIG_PM_CLK -extern int pm_clk_init(struct device *dev); +extern void pm_clk_init(struct device *dev); +extern int pm_clk_create(struct device *dev); extern void pm_clk_destroy(struct device *dev); extern int pm_clk_add(struct device *dev, const char *con_id); extern void pm_clk_remove(struct device *dev, const char *con_id); extern int pm_clk_suspend(struct device *dev); extern int pm_clk_resume(struct device *dev); #else -static inline int pm_clk_init(struct device *dev) +static inline void pm_clk_init(struct device *dev) +{ +} +static inline int pm_clk_create(struct device *dev) { return -EINVAL; } -- cgit v1.2.3 From ef27bed1870dbd5fd363ff5ec51eebd5a695e277 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 25 Aug 2011 15:34:01 +0200 Subject: PM: Reference counting of power.subsys_data Since the power.subsys_data device field will be used by multiple filesystems, introduce a reference counting mechanism for it to avoid freeing it prematurely or changing its value at a wrong time. Make the PM clocks management code that currently is the only user of power.subsys_data use the new reference counting. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index bf5ee37388d4..c6b5a0a41ab3 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -423,6 +423,7 @@ struct wakeup_source; struct pm_subsys_data { spinlock_t lock; + unsigned int refcount; #ifdef CONFIG_PM_CLK struct list_head clock_list; #endif @@ -473,6 +474,8 @@ struct dev_pm_info { }; extern void update_pm_runtime_accounting(struct device *dev); +extern int dev_pm_get_subsys_data(struct device *dev); +extern int dev_pm_put_subsys_data(struct device *dev); /* * Power domains provide callbacks that are executed during system suspend, -- cgit v1.2.3 From 4605ab653c1f9d7cc2dda8033de215c9cee325f4 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 25 Aug 2011 15:34:12 +0200 Subject: PM / Domains: Use power.sybsys_data to reduce overhead Currently pm_genpd_runtime_resume() has to walk the list of devices from the device's PM domain to find the corresponding device list object containing the need_restore field to check if the driver's .runtime_resume() callback should be executed for the device. This is suboptimal and can be simplified by using power.sybsys_data to store device information used by the generic PM domains code. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 9 +++++++++ include/linux/pm_domain.h | 6 ------ include/linux/pm_runtime.h | 10 ++++++++++ 3 files changed, 19 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index c6b5a0a41ab3..ed10f24d5259 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -421,12 +421,21 @@ enum rpm_request { struct wakeup_source; +struct pm_domain_data { + struct list_head list_node; + struct device *dev; + bool need_restore; +}; + struct pm_subsys_data { spinlock_t lock; unsigned int refcount; #ifdef CONFIG_PM_CLK struct list_head clock_list; #endif +#ifdef CONFIG_PM_GENERIC_DOMAINS + struct pm_domain_data domain_data; +#endif }; struct dev_pm_info { diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index bf679f59f9a8..5cce46c2d926 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -61,12 +61,6 @@ struct gpd_link { struct list_head slave_node; }; -struct dev_list_entry { - struct list_head node; - struct device *dev; - bool need_restore; -}; - #ifdef CONFIG_PM_GENERIC_DOMAINS extern int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev); diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 6b90630e3c98..a5a41a850efb 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -258,6 +258,12 @@ struct pm_clk_notifier_block { }; #ifdef CONFIG_PM_CLK +static inline bool pm_clk_no_clocks(struct device *dev) +{ + return dev && dev->power.subsys_data + && list_empty(&dev->power.subsys_data->clock_list); +} + extern void pm_clk_init(struct device *dev); extern int pm_clk_create(struct device *dev); extern void pm_clk_destroy(struct device *dev); @@ -266,6 +272,10 @@ extern void pm_clk_remove(struct device *dev, const char *con_id); extern int pm_clk_suspend(struct device *dev); extern int pm_clk_resume(struct device *dev); #else +static inline bool pm_clk_no_clocks(struct device *dev) +{ + return true; +} static inline void pm_clk_init(struct device *dev) { } -- cgit v1.2.3 From b5e8d269d814763d597ccc0108d1fa6639ad35a1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 25 Aug 2011 15:34:19 +0200 Subject: PM: Move clock-related definitions and headers to separate file Since the PM clock management code in drivers/base/power/clock_ops.c is used for both runtime PM and system suspend/hibernation, the definitions of data structures and headers related to it should not be located in include/linux/pm_rumtime.h. Move them to a separate header file. Signed-off-by: Rafael J. Wysocki --- include/linux/pm_clock.h | 71 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_runtime.h | 56 ------------------------------------ 2 files changed, 71 insertions(+), 56 deletions(-) create mode 100644 include/linux/pm_clock.h (limited to 'include/linux') diff --git a/include/linux/pm_clock.h b/include/linux/pm_clock.h new file mode 100644 index 000000000000..8348866e7b05 --- /dev/null +++ b/include/linux/pm_clock.h @@ -0,0 +1,71 @@ +/* + * pm_clock.h - Definitions and headers related to device clocks. + * + * Copyright (C) 2011 Rafael J. Wysocki , Renesas Electronics Corp. + * + * This file is released under the GPLv2. + */ + +#ifndef _LINUX_PM_CLOCK_H +#define _LINUX_PM_CLOCK_H + +#include +#include + +struct pm_clk_notifier_block { + struct notifier_block nb; + struct dev_pm_domain *pm_domain; + char *con_ids[]; +}; + +#ifdef CONFIG_PM_CLK +static inline bool pm_clk_no_clocks(struct device *dev) +{ + return dev && dev->power.subsys_data + && list_empty(&dev->power.subsys_data->clock_list); +} + +extern void pm_clk_init(struct device *dev); +extern int pm_clk_create(struct device *dev); +extern void pm_clk_destroy(struct device *dev); +extern int pm_clk_add(struct device *dev, const char *con_id); +extern void pm_clk_remove(struct device *dev, const char *con_id); +extern int pm_clk_suspend(struct device *dev); +extern int pm_clk_resume(struct device *dev); +#else +static inline bool pm_clk_no_clocks(struct device *dev) +{ + return true; +} +static inline void pm_clk_init(struct device *dev) +{ +} +static inline int pm_clk_create(struct device *dev) +{ + return -EINVAL; +} +static inline void pm_clk_destroy(struct device *dev) +{ +} +static inline int pm_clk_add(struct device *dev, const char *con_id) +{ + return -EINVAL; +} +static inline void pm_clk_remove(struct device *dev, const char *con_id) +{ +} +#define pm_clk_suspend NULL +#define pm_clk_resume NULL +#endif + +#ifdef CONFIG_HAVE_CLK +extern void pm_clk_add_notifier(struct bus_type *bus, + struct pm_clk_notifier_block *clknb); +#else +static inline void pm_clk_add_notifier(struct bus_type *bus, + struct pm_clk_notifier_block *clknb) +{ +} +#endif + +#endif diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index a5a41a850efb..70b284024d9e 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -251,60 +251,4 @@ static inline void pm_runtime_dont_use_autosuspend(struct device *dev) __pm_runtime_use_autosuspend(dev, false); } -struct pm_clk_notifier_block { - struct notifier_block nb; - struct dev_pm_domain *pm_domain; - char *con_ids[]; -}; - -#ifdef CONFIG_PM_CLK -static inline bool pm_clk_no_clocks(struct device *dev) -{ - return dev && dev->power.subsys_data - && list_empty(&dev->power.subsys_data->clock_list); -} - -extern void pm_clk_init(struct device *dev); -extern int pm_clk_create(struct device *dev); -extern void pm_clk_destroy(struct device *dev); -extern int pm_clk_add(struct device *dev, const char *con_id); -extern void pm_clk_remove(struct device *dev, const char *con_id); -extern int pm_clk_suspend(struct device *dev); -extern int pm_clk_resume(struct device *dev); -#else -static inline bool pm_clk_no_clocks(struct device *dev) -{ - return true; -} -static inline void pm_clk_init(struct device *dev) -{ -} -static inline int pm_clk_create(struct device *dev) -{ - return -EINVAL; -} -static inline void pm_clk_destroy(struct device *dev) -{ -} -static inline int pm_clk_add(struct device *dev, const char *con_id) -{ - return -EINVAL; -} -static inline void pm_clk_remove(struct device *dev, const char *con_id) -{ -} -#define pm_clk_suspend NULL -#define pm_clk_resume NULL -#endif - -#ifdef CONFIG_HAVE_CLK -extern void pm_clk_add_notifier(struct bus_type *bus, - struct pm_clk_notifier_block *clknb); -#else -static inline void pm_clk_add_notifier(struct bus_type *bus, - struct pm_clk_notifier_block *clknb) -{ -} -#endif - #endif -- cgit v1.2.3 From e8db0be1245de16a6cc6365506abc392c3c212d4 Mon Sep 17 00:00:00 2001 From: Jean Pihet Date: Thu, 25 Aug 2011 15:35:03 +0200 Subject: PM QoS: Move and rename the implementation files The PM QoS implementation files are better named kernel/power/qos.c and include/linux/pm_qos.h. The PM QoS support is compiled under the CONFIG_PM option. Signed-off-by: Jean Pihet Acked-by: markgross Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/netdevice.h | 2 +- include/linux/pm_qos.h | 61 +++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_qos_params.h | 38 --------------------------- 3 files changed, 62 insertions(+), 39 deletions(-) create mode 100644 include/linux/pm_qos.h delete mode 100644 include/linux/pm_qos_params.h (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ddee79bb8f15..f72ac6b972b7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -31,7 +31,7 @@ #include #ifdef __KERNEL__ -#include +#include #include #include #include diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h new file mode 100644 index 000000000000..7ba675413b08 --- /dev/null +++ b/include/linux/pm_qos.h @@ -0,0 +1,61 @@ +#ifndef _LINUX_PM_QOS_H +#define _LINUX_PM_QOS_H +/* interface for the pm_qos_power infrastructure of the linux kernel. + * + * Mark Gross + */ +#include +#include +#include + +#define PM_QOS_RESERVED 0 +#define PM_QOS_CPU_DMA_LATENCY 1 +#define PM_QOS_NETWORK_LATENCY 2 +#define PM_QOS_NETWORK_THROUGHPUT 3 + +#define PM_QOS_NUM_CLASSES 4 +#define PM_QOS_DEFAULT_VALUE -1 + +#define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE (2000 * USEC_PER_SEC) +#define PM_QOS_NETWORK_LAT_DEFAULT_VALUE (2000 * USEC_PER_SEC) +#define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE 0 + +struct pm_qos_request_list { + struct plist_node list; + int pm_qos_class; +}; + +#ifdef CONFIG_PM +void pm_qos_add_request(struct pm_qos_request_list *l, + int pm_qos_class, s32 value); +void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req, + s32 new_value); +void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req); + +int pm_qos_request(int pm_qos_class); +int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier); +int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier); +int pm_qos_request_active(struct pm_qos_request_list *req); +#else +static inline void pm_qos_add_request(struct pm_qos_request_list *l, + int pm_qos_class, s32 value) + { return; } +static inline void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req, + s32 new_value) + { return; } +static inline void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req) + { return; } + +static inline int pm_qos_request(int pm_qos_class) + { return 0; } +static inline int pm_qos_add_notifier(int pm_qos_class, + struct notifier_block *notifier) + { return 0; } +static inline int pm_qos_remove_notifier(int pm_qos_class, + struct notifier_block *notifier) + { return 0; } +static inline int pm_qos_request_active(struct pm_qos_request_list *req) + { return 0; } +#endif + +#endif diff --git a/include/linux/pm_qos_params.h b/include/linux/pm_qos_params.h deleted file mode 100644 index a7d87f911cab..000000000000 --- a/include/linux/pm_qos_params.h +++ /dev/null @@ -1,38 +0,0 @@ -#ifndef _LINUX_PM_QOS_PARAMS_H -#define _LINUX_PM_QOS_PARAMS_H -/* interface for the pm_qos_power infrastructure of the linux kernel. - * - * Mark Gross - */ -#include -#include -#include - -#define PM_QOS_RESERVED 0 -#define PM_QOS_CPU_DMA_LATENCY 1 -#define PM_QOS_NETWORK_LATENCY 2 -#define PM_QOS_NETWORK_THROUGHPUT 3 - -#define PM_QOS_NUM_CLASSES 4 -#define PM_QOS_DEFAULT_VALUE -1 - -#define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE (2000 * USEC_PER_SEC) -#define PM_QOS_NETWORK_LAT_DEFAULT_VALUE (2000 * USEC_PER_SEC) -#define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE 0 - -struct pm_qos_request_list { - struct plist_node list; - int pm_qos_class; -}; - -void pm_qos_add_request(struct pm_qos_request_list *l, int pm_qos_class, s32 value); -void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req, - s32 new_value); -void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req); - -int pm_qos_request(int pm_qos_class); -int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier); -int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier); -int pm_qos_request_active(struct pm_qos_request_list *req); - -#endif -- cgit v1.2.3 From cc74998618a66d34651c784dd02412614c3e81cc Mon Sep 17 00:00:00 2001 From: Jean Pihet Date: Thu, 25 Aug 2011 15:35:12 +0200 Subject: PM QoS: Minor clean-ups - Misc fixes to improve code readability: * rename struct pm_qos_request_list to struct pm_qos_request, * rename pm_qos_req parameter to req in internal code, consistenly use req in the API parameters, * update the in-kernel API callers to the new parameters names, * rename of fields names (requests, list, node, constraints) Signed-off-by: Jean Pihet Acked-by: markgross Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/netdevice.h | 2 +- include/linux/pm_qos.h | 22 +++++++++++----------- 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f72ac6b972b7..f38ab5b7e768 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -964,7 +964,7 @@ struct net_device { */ char name[IFNAMSIZ]; - struct pm_qos_request_list pm_qos_req; + struct pm_qos_request pm_qos_req; /* device name hash chain */ struct hlist_node name_hlist; diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 7ba675413b08..6b0968f8bc6e 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -20,30 +20,30 @@ #define PM_QOS_NETWORK_LAT_DEFAULT_VALUE (2000 * USEC_PER_SEC) #define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE 0 -struct pm_qos_request_list { - struct plist_node list; +struct pm_qos_request { + struct plist_node node; int pm_qos_class; }; #ifdef CONFIG_PM -void pm_qos_add_request(struct pm_qos_request_list *l, - int pm_qos_class, s32 value); -void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req, +void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class, + s32 value); +void pm_qos_update_request(struct pm_qos_request *req, s32 new_value); -void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req); +void pm_qos_remove_request(struct pm_qos_request *req); int pm_qos_request(int pm_qos_class); int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier); int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier); -int pm_qos_request_active(struct pm_qos_request_list *req); +int pm_qos_request_active(struct pm_qos_request *req); #else -static inline void pm_qos_add_request(struct pm_qos_request_list *l, +static inline void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class, s32 value) { return; } -static inline void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req, +static inline void pm_qos_update_request(struct pm_qos_request *req, s32 new_value) { return; } -static inline void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req) +static inline void pm_qos_remove_request(struct pm_qos_request *req) { return; } static inline int pm_qos_request(int pm_qos_class) @@ -54,7 +54,7 @@ static inline int pm_qos_add_notifier(int pm_qos_class, static inline int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier) { return 0; } -static inline int pm_qos_request_active(struct pm_qos_request_list *req) +static inline int pm_qos_request_active(struct pm_qos_request *req) { return 0; } #endif -- cgit v1.2.3 From 4e1779baaa542c83b459b0a56585e0c1a04c7782 Mon Sep 17 00:00:00 2001 From: Jean Pihet Date: Thu, 25 Aug 2011 15:35:27 +0200 Subject: PM QoS: Reorganize data structs In preparation for the per-device constratins support, re-organize the data strctures: - add a struct pm_qos_constraints which contains the constraints related data - update struct pm_qos_object contents to the PM QoS internal object data. Add a pointer to struct pm_qos_constraints - update the internal code to use the new data structs. Signed-off-by: Jean Pihet Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 6b0968f8bc6e..97723113ae92 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -25,6 +25,25 @@ struct pm_qos_request { int pm_qos_class; }; +enum pm_qos_type { + PM_QOS_UNITIALIZED, + PM_QOS_MAX, /* return the largest value */ + PM_QOS_MIN /* return the smallest value */ +}; + +/* + * Note: The lockless read path depends on the CPU accessing + * target_value atomically. Atomic access is only guaranteed on all CPU + * types linux supports for 32 bit quantites + */ +struct pm_qos_constraints { + struct plist_head list; + s32 target_value; /* Do not change to 64 bit */ + s32 default_value; + enum pm_qos_type type; + struct blocking_notifier_head *notifiers; +}; + #ifdef CONFIG_PM void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class, s32 value); -- cgit v1.2.3 From abe98ec2d86279fe821c9051003a0abc43444f15 Mon Sep 17 00:00:00 2001 From: Jean Pihet Date: Thu, 25 Aug 2011 15:35:34 +0200 Subject: PM QoS: Generalize and export constraints management code In preparation for the per-device constratins support: - rename update_target to pm_qos_update_target - generalize and export pm_qos_update_target for usage by the upcoming per-device latency constraints framework: * operate on struct pm_qos_constraints for constraints management, * introduce an 'action' parameter for constraints add/update/remove, * the return value indicates if the aggregated constraint value has changed, - update the internal code to operate on struct pm_qos_constraints - add a NULL pointer check in the API functions Signed-off-by: Jean Pihet Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 97723113ae92..84aa15089896 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -44,7 +44,16 @@ struct pm_qos_constraints { struct blocking_notifier_head *notifiers; }; +/* Action requested to pm_qos_update_target */ +enum pm_qos_req_action { + PM_QOS_ADD_REQ, /* Add a new request */ + PM_QOS_UPDATE_REQ, /* Update an existing request */ + PM_QOS_REMOVE_REQ /* Remove an existing request */ +}; + #ifdef CONFIG_PM +int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, + enum pm_qos_req_action action, int value); void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class, s32 value); void pm_qos_update_request(struct pm_qos_request *req, @@ -56,6 +65,11 @@ int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier); int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier); int pm_qos_request_active(struct pm_qos_request *req); #else +static inline int pm_qos_update_target(struct pm_qos_constraints *c, + struct plist_node *node, + enum pm_qos_req_action action, + int value) + { return 0; } static inline void pm_qos_add_request(struct pm_qos_request *req, int pm_qos_class, s32 value) { return; } -- cgit v1.2.3 From 91ff4cb803df6de9114351b9f2f0f39f397ee03e Mon Sep 17 00:00:00 2001 From: Jean Pihet Date: Thu, 25 Aug 2011 15:35:41 +0200 Subject: PM QoS: Implement per-device PM QoS constraints Implement the per-device PM QoS constraints by creating a device PM QoS API, which calls the PM QoS constraints management core code. The per-device latency constraints data strctures are stored in the device dev_pm_info struct. The device PM code calls the init and destroy of the per-device constraints data struct in order to support the dynamic insertion and removal of the devices in the system. To minimize the data usage by the per-device constraints, the data struct is only allocated at the first call to dev_pm_qos_add_request. The data is later free'd when the device is removed from the system. A global mutex protects the constraints users from the data being allocated and free'd. Signed-off-by: Jean Pihet Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 9 +++++++++ include/linux/pm_qos.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index ed10f24d5259..d78187e9ca99 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -419,6 +419,13 @@ enum rpm_request { RPM_REQ_RESUME, }; +/* Per-device PM QoS constraints data struct state */ +enum dev_pm_qos_state { + DEV_PM_QOS_NO_DEVICE, /* No device present */ + DEV_PM_QOS_DEVICE_PRESENT, /* Device present, data not allocated */ + DEV_PM_QOS_ALLOCATED, /* Device present, data allocated */ +}; + struct wakeup_source; struct pm_domain_data { @@ -480,6 +487,8 @@ struct dev_pm_info { unsigned long accounting_timestamp; #endif struct pm_subsys_data *subsys_data; /* Owned by the subsystem. */ + struct pm_qos_constraints *constraints; + enum dev_pm_qos_state constraints_state; }; extern void update_pm_runtime_accounting(struct device *dev); diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 84aa15089896..f75f74dd9b90 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -19,12 +19,18 @@ #define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE (2000 * USEC_PER_SEC) #define PM_QOS_NETWORK_LAT_DEFAULT_VALUE (2000 * USEC_PER_SEC) #define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE 0 +#define PM_QOS_DEV_LAT_DEFAULT_VALUE 0 struct pm_qos_request { struct plist_node node; int pm_qos_class; }; +struct dev_pm_qos_request { + struct plist_node node; + struct device *dev; +}; + enum pm_qos_type { PM_QOS_UNITIALIZED, PM_QOS_MAX, /* return the largest value */ @@ -51,6 +57,11 @@ enum pm_qos_req_action { PM_QOS_REMOVE_REQ /* Remove an existing request */ }; +static inline int dev_pm_qos_request_active(struct dev_pm_qos_request *req) +{ + return req->dev != 0; +} + #ifdef CONFIG_PM int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, enum pm_qos_req_action action, int value); @@ -64,6 +75,17 @@ int pm_qos_request(int pm_qos_class); int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier); int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier); int pm_qos_request_active(struct pm_qos_request *req); + +int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, + s32 value); +int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value); +int dev_pm_qos_remove_request(struct dev_pm_qos_request *req); +int dev_pm_qos_add_notifier(struct device *dev, + struct notifier_block *notifier); +int dev_pm_qos_remove_notifier(struct device *dev, + struct notifier_block *notifier); +void dev_pm_qos_constraints_init(struct device *dev); +void dev_pm_qos_constraints_destroy(struct device *dev); #else static inline int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, @@ -89,6 +111,26 @@ static inline int pm_qos_remove_notifier(int pm_qos_class, { return 0; } static inline int pm_qos_request_active(struct pm_qos_request *req) { return 0; } + +static inline int dev_pm_qos_add_request(struct device *dev, + struct dev_pm_qos_request *req, + s32 value) + { return 0; } +static inline int dev_pm_qos_update_request(struct dev_pm_qos_request *req, + s32 new_value) + { return 0; } +static inline int dev_pm_qos_remove_request(struct dev_pm_qos_request *req) + { return 0; } +static inline int dev_pm_qos_add_notifier(struct device *dev, + struct notifier_block *notifier) + { return 0; } +static inline int dev_pm_qos_remove_notifier(struct device *dev, + struct notifier_block *notifier) + { return 0; } +static inline void dev_pm_qos_constraints_init(struct device *dev) + { return; } +static inline void dev_pm_qos_constraints_destroy(struct device *dev) + { return; } #endif #endif -- cgit v1.2.3 From b66213cdb002b08b29603d488c451dfe25e2ca20 Mon Sep 17 00:00:00 2001 From: Jean Pihet Date: Thu, 25 Aug 2011 15:35:47 +0200 Subject: PM QoS: Add global notification mechanism for device constraints Add a global notification chain that gets called upon changes to the aggregated constraint value for any device. The notification callbacks are passing the full constraint request data in order for the callees to have access to it. The current use is for the platform low-level code to access the target device of the constraint. Signed-off-by: Jean Pihet Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/pm_qos.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index f75f74dd9b90..ca7bd3f98cb4 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -75,6 +75,7 @@ int pm_qos_request(int pm_qos_class); int pm_qos_add_notifier(int pm_qos_class, struct notifier_block *notifier); int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier); int pm_qos_request_active(struct pm_qos_request *req); +s32 pm_qos_read_value(struct pm_qos_constraints *c); int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, s32 value); @@ -84,6 +85,8 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier); int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier); +int dev_pm_qos_add_global_notifier(struct notifier_block *notifier); +int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier); void dev_pm_qos_constraints_init(struct device *dev); void dev_pm_qos_constraints_destroy(struct device *dev); #else @@ -111,6 +114,8 @@ static inline int pm_qos_remove_notifier(int pm_qos_class, { return 0; } static inline int pm_qos_request_active(struct pm_qos_request *req) { return 0; } +static inline s32 pm_qos_read_value(struct pm_qos_constraints *c) + { return 0; } static inline int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, @@ -127,6 +132,12 @@ static inline int dev_pm_qos_add_notifier(struct device *dev, static inline int dev_pm_qos_remove_notifier(struct device *dev, struct notifier_block *notifier) { return 0; } +static inline int dev_pm_qos_add_global_notifier( + struct notifier_block *notifier) + { return 0; } +static inline int dev_pm_qos_remove_global_notifier( + struct notifier_block *notifier) + { return 0; } static inline void dev_pm_qos_constraints_init(struct device *dev) { return; } static inline void dev_pm_qos_constraints_destroy(struct device *dev) -- cgit v1.2.3 From 0aa2a221696cc8ea20a4cdca01315d3b6b4ecc4d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 25 Aug 2011 15:37:04 +0200 Subject: PM / Domains: Preliminary support for devices with power.irq_safe set The generic PM domains framework currently doesn't work with devices whose power.irq_safe flag is set, because runtime PM callbacks for such devices are run with interrupts disabled and the callbacks provided by the generic PM domains framework use domain mutexes and may sleep. However, such devices very well may belong to power domains on some systems, so the generic PM domains framework should take them into account. For this reason, modify the generic PM domains framework so that the domain .power_off() and .power_on() callbacks are never executed for a domain containing devices with power.irq_safe set, although the .stop_device() and .start_device() callbacks are still run for them. Additionally, introduce a flag allowing the creator of a struct generic_pm_domain object to indicate that its .stop_device() and .start_device() callbacks may be run in interrupt context (might_sleep_if() triggers if that flag is not set and one of those callbacks is run in interrupt context). Signed-off-by: Rafael J. Wysocki --- include/linux/pm_domain.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 5cce46c2d926..2538d906bcd1 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -42,6 +42,7 @@ struct generic_pm_domain { unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ bool suspend_power_off; /* Power status before system suspend */ + bool dev_irq_safe; /* Device callbacks are IRQ-safe */ int (*power_off)(struct generic_pm_domain *domain); int (*power_on)(struct generic_pm_domain *domain); int (*start_device)(struct device *dev); -- cgit v1.2.3 From a57a7bf3fc7eff00f07eb9c805774d911a3f2472 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 25 Aug 2011 15:12:06 +0200 Subject: TTY: define tty_wait_until_sent_from_close We need this helper to fix system stalls. The issue is that the rest of the system TTYs wait for us to finish waiting. This wasn't an issue with BKL. BKL used to unlock implicitly. This is based on the Arnd suggestion. Signed-off-by: Jiri Slaby Acked-by: Arnd Bergmann Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 6d5eceb165be..0ad68889fc1a 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -601,6 +601,24 @@ extern long vt_compat_ioctl(struct tty_struct *tty, extern void __lockfunc tty_lock(void) __acquires(tty_lock); extern void __lockfunc tty_unlock(void) __releases(tty_lock); +/* + * this shall be called only from where BTM is held (like close) + * + * We need this to ensure nobody waits for us to finish while we are waiting. + * Without this we were encountering system stalls. + * + * This should be indeed removed with BTM removal later. + * + * Locking: BTM required. Nobody is allowed to hold port->mutex. + */ +static inline void tty_wait_until_sent_from_close(struct tty_struct *tty, + long timeout) +{ + tty_unlock(); /* tty->ops->close holds the BTM, drop it while waiting */ + tty_wait_until_sent(tty, timeout); + tty_lock(); +} + /* * wait_event_interruptible_tty -- wait for a condition with the tty lock held * -- cgit v1.2.3 From 17be18c2b5f5c8acd75e4edf1211abf2cfd60fa5 Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Thu, 25 Aug 2011 09:48:29 -0700 Subject: Staging: hv: Add struct hv_vmbus_device_id to mod_devicetable.h In preparation for implementing vmbus aliases for auto-loading Hyper-V drivers, define vmbus specific device ID. Signed-off-by: K. Y. Srinivasan Signed-off-by: Haiyang Zhang Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index ae28e93fd072..5a123774c2e6 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -405,6 +405,13 @@ struct virtio_device_id { }; #define VIRTIO_DEV_ANY_ID 0xffffffff +/* + * For Hyper-V devices we use the device guid as the id. + */ +struct hv_vmbus_device_id { + __u8 guid[16]; +}; + /* i2c */ #define I2C_NAME_SIZE 20 -- cgit v1.2.3 From a91befc116f424883602fb7b57b63b5fcfe18719 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 25 Aug 2011 10:25:37 -0700 Subject: Staging: hv: add driver_data to hv_vmbus_device_id This is going to be needed by some drivers that handle more than one device, like all other bus types do, so prepare for that in advance before the user/kernel api is used. Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 5a123774c2e6..468819cdde87 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -410,6 +410,8 @@ struct virtio_device_id { */ struct hv_vmbus_device_id { __u8 guid[16]; + kernel_ulong_t driver_data /* Data private to the driver */ + __attribute__((aligned(sizeof(kernel_ulong_t)))); }; /* i2c */ -- cgit v1.2.3 From 01dcc60a7cb8cd5193676554b94a90d349bdfd15 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 25 Aug 2011 11:16:00 +0200 Subject: new helper to create platform devices with dma mask MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit compared to the most powerful and already existing helper (namely platform_device_register_resndata) this allows to specify a dma_mask. To make eventual extensions later more easy, a struct holding the used information is created instead of passing the information by function parameters. Signed-off-by: Uwe Kleine-König Signed-off-by: Greg Kroah-Hartman --- include/linux/platform_device.h | 48 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 46 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 27bb05aae70d..651a066686ac 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -49,10 +49,54 @@ extern struct resource *platform_get_resource_byname(struct platform_device *, u extern int platform_get_irq_byname(struct platform_device *, const char *); extern int platform_add_devices(struct platform_device **, int); -extern struct platform_device *platform_device_register_resndata( +struct platform_device_info { + struct device *parent; + + const char *name; + int id; + + const struct resource *res; + unsigned int num_res; + + const void *data; + size_t size_data; + u64 dma_mask; +}; +extern struct platform_device *platform_device_register_full( + struct platform_device_info *pdevinfo); + +/** + * platform_device_register_resndata - add a platform-level device with + * resources and platform-specific data + * + * @parent: parent device for the device we're adding + * @name: base name of the device we're adding + * @id: instance id + * @res: set of resources that needs to be allocated for the device + * @num: number of resources + * @data: platform specific data for this platform device + * @size: size of platform specific data + * + * Returns &struct platform_device pointer on success, or ERR_PTR() on error. + */ +static inline struct platform_device *platform_device_register_resndata( struct device *parent, const char *name, int id, const struct resource *res, unsigned int num, - const void *data, size_t size); + const void *data, size_t size) { + + struct platform_device_info pdevinfo = { + .parent = parent, + .name = name, + .id = id, + .res = res, + .num_res = num, + .data = data, + .size_data = size, + .dma_mask = 0, + }; + + return platform_device_register_full(&pdevinfo); +} /** * platform_device_register_simple - add a platform-level device and its resources -- cgit v1.2.3 From 8cfb79134027e96bc11067da00d7ca73e58e69ce Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 8 Aug 2011 07:09:03 -0400 Subject: nfsd: remove unused defines At least one of these is actually wrong anyway. Signed-off-by: J. Bruce Fields --- include/linux/nfsd/const.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/const.h b/include/linux/nfsd/const.h index 323f8cfa060a..feb3764617a4 100644 --- a/include/linux/nfsd/const.h +++ b/include/linux/nfsd/const.h @@ -14,11 +14,6 @@ #include #include -/* - * Maximum protocol version supported by knfsd - */ -#define NFSSVC_MAXVERS 3 - /* * Maximum blocksizes supported by daemon under various circumstances. */ @@ -42,14 +37,6 @@ */ #define NFSD_BUFSIZE ((RPC_MAX_HEADER_WITH_AUTH+26)*XDR_UNIT + NFSSVC_MAXBLKSIZE) -#ifdef CONFIG_NFSD_V4 -# define NFSSVC_XDRSIZE NFS4_SVC_XDRSIZE -#elif defined(CONFIG_NFSD_V3) -# define NFSSVC_XDRSIZE NFS3_SVC_XDRSIZE -#else -# define NFSSVC_XDRSIZE NFS2_SVC_XDRSIZE -#endif - #endif /* __KERNEL__ */ #endif /* _LINUX_NFSD_CONST_H */ -- cgit v1.2.3 From c10bd39d800d42adef55ed9016f802677cd0ab5f Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 19 Aug 2011 11:38:52 -0400 Subject: Remove include/linux/nfsd/const.h Userspace shouldn't have a use for these constants. Nothing here is used outside fs/nfsd. Signed-off-by: J. Bruce Fields --- include/linux/nfsd/Kbuild | 1 - include/linux/nfsd/const.h | 42 ------------------------------------------ include/linux/nfsd/nfsfh.h | 7 +++++-- 3 files changed, 5 insertions(+), 45 deletions(-) delete mode 100644 include/linux/nfsd/const.h (limited to 'include/linux') diff --git a/include/linux/nfsd/Kbuild b/include/linux/nfsd/Kbuild index 55d1467de3c1..0e528606d46f 100644 --- a/include/linux/nfsd/Kbuild +++ b/include/linux/nfsd/Kbuild @@ -1,4 +1,3 @@ -header-y += const.h header-y += debug.h header-y += export.h header-y += nfsfh.h diff --git a/include/linux/nfsd/const.h b/include/linux/nfsd/const.h deleted file mode 100644 index feb3764617a4..000000000000 --- a/include/linux/nfsd/const.h +++ /dev/null @@ -1,42 +0,0 @@ -/* - * include/linux/nfsd/const.h - * - * Various constants related to NFS. - * - * Copyright (C) 1995-1997 Olaf Kirch - */ - -#ifndef _LINUX_NFSD_CONST_H -#define _LINUX_NFSD_CONST_H - -#include -#include -#include -#include - -/* - * Maximum blocksizes supported by daemon under various circumstances. - */ -#define NFSSVC_MAXBLKSIZE RPCSVC_MAXPAYLOAD -/* NFSv2 is limited by the protocol specification, see RFC 1094 */ -#define NFSSVC_MAXBLKSIZE_V2 (8*1024) - -#ifdef __KERNEL__ - -#include - -/* - * Largest number of bytes we need to allocate for an NFS - * call or reply. Used to control buffer sizes. We use - * the length of v3 WRITE, READDIR and READDIR replies - * which are an RPC header, up to 26 XDR units of reply - * data, and some page data. - * - * Note that accuracy here doesn't matter too much as the - * size is rounded up to a page size when allocating space. - */ -#define NFSD_BUFSIZE ((RPC_MAX_HEADER_WITH_AUTH+26)*XDR_UNIT + NFSSVC_MAXBLKSIZE) - -#endif /* __KERNEL__ */ - -#endif /* _LINUX_NFSD_CONST_H */ diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index f76d80ccec10..ce4743a26015 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -14,11 +14,14 @@ #ifndef _LINUX_NFSD_FH_H #define _LINUX_NFSD_FH_H -# include +#include +#include +#include +#include +#include #ifdef __KERNEL__ # include #endif -#include /* * This is the old "dentry style" Linux NFSv2 file handle. -- cgit v1.2.3 From a9004abc34239705840eaf6fe3d6cc9cb7656cba Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Tue, 23 Aug 2011 15:43:04 -0400 Subject: nfsd4: cleanup and consolidate seqid_mutating_err Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 76f99e8714f3..b875b0324fc0 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -373,6 +373,22 @@ enum nfsstat4 { NFS4ERR_DELEG_REVOKED = 10087, /* deleg./layout revoked */ }; +static inline bool seqid_mutating_err(u32 err) +{ + /* rfc 3530 section 8.1.5: */ + switch (err) { + case NFS4ERR_STALE_CLIENTID: + case NFS4ERR_STALE_STATEID: + case NFS4ERR_BAD_STATEID: + case NFS4ERR_BAD_SEQID: + case NFS4ERR_BADXDR: + case NFS4ERR_RESOURCE: + case NFS4ERR_NOFILEHANDLE: + return false; + }; + return true; +} + /* * Note: NF4BAD is not actually part of the protocol; it is just used * internally by nfsd. -- cgit v1.2.3 From c64e148a3be3cb786534ad38298c25c833116c26 Mon Sep 17 00:00:00 2001 From: Vaibhav Nagarnaik Date: Tue, 16 Aug 2011 14:46:16 -0700 Subject: trace: Add ring buffer stats to measure rate of events The stats file under per_cpu folder provides the number of entries, overruns and other statistics about the CPU ring buffer. However, the numbers do not provide any indication of how full the ring buffer is in bytes compared to the overall size in bytes. Also, it is helpful to know the rate at which the cpu buffer is filling up. This patch adds an entry "bytes: " in printed stats for per_cpu ring buffer which provides the actual bytes consumed in the ring buffer. This field includes the number of bytes used by recorded events and the padding bytes added when moving the tail pointer to next page. It also adds the following time stamps: "oldest event ts:" - the oldest timestamp in the ring buffer "now ts:" - the timestamp at the time of reading The field "now ts" provides a consistent time snapshot to the userspace when being read. This is read from the same trace clock used by tracing event timestamps. Together, these values provide the rate at which the buffer is filling up, from the formula: bytes / (now_ts - oldest_event_ts) Signed-off-by: Vaibhav Nagarnaik Cc: Michael Rubin Cc: David Sharp Link: http://lkml.kernel.org/r/1313531179-9323-3-git-send-email-vnagarnaik@google.com Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b891de96000f..67be0376d8e3 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -154,6 +154,8 @@ void ring_buffer_record_enable(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); +unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu); +unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu); unsigned long ring_buffer_entries(struct ring_buffer *buffer); unsigned long ring_buffer_overruns(struct ring_buffer *buffer); unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu); -- cgit v1.2.3 From c152292f9ee7eb4ed30edc0bd5027a5beef5f5e8 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 26 Aug 2011 17:22:06 -0400 Subject: nfsd: remove include/linux/nfsd/syscall.h We don't need this any more. Signed-off-by: J. Bruce Fields --- include/linux/nfsd/Kbuild | 1 - include/linux/nfsd/syscall.h | 116 ------------------------------------------- 2 files changed, 117 deletions(-) delete mode 100644 include/linux/nfsd/syscall.h (limited to 'include/linux') diff --git a/include/linux/nfsd/Kbuild b/include/linux/nfsd/Kbuild index 0e528606d46f..b8d4001212b3 100644 --- a/include/linux/nfsd/Kbuild +++ b/include/linux/nfsd/Kbuild @@ -2,4 +2,3 @@ header-y += debug.h header-y += export.h header-y += nfsfh.h header-y += stats.h -header-y += syscall.h diff --git a/include/linux/nfsd/syscall.h b/include/linux/nfsd/syscall.h deleted file mode 100644 index 812bc1e160dc..000000000000 --- a/include/linux/nfsd/syscall.h +++ /dev/null @@ -1,116 +0,0 @@ -/* - * include/linux/nfsd/syscall.h - * - * This file holds all declarations for the knfsd syscall interface. - * - * Copyright (C) 1995-1997 Olaf Kirch - */ - -#ifndef NFSD_SYSCALL_H -#define NFSD_SYSCALL_H - -#include -#include - -/* - * Version of the syscall interface - */ -#define NFSCTL_VERSION 0x0201 - -/* - * These are the commands understood by nfsctl(). - */ -#define NFSCTL_SVC 0 /* This is a server process. */ -#define NFSCTL_ADDCLIENT 1 /* Add an NFS client. */ -#define NFSCTL_DELCLIENT 2 /* Remove an NFS client. */ -#define NFSCTL_EXPORT 3 /* export a file system. */ -#define NFSCTL_UNEXPORT 4 /* unexport a file system. */ -/*#define NFSCTL_UGIDUPDATE 5 / * update a client's uid/gid map. DISCARDED */ -/*#define NFSCTL_GETFH 6 / * get an fh by ino DISCARDED */ -#define NFSCTL_GETFD 7 /* get an fh by path (used by mountd) */ -#define NFSCTL_GETFS 8 /* get an fh by path with max FH len */ - -/* SVC */ -struct nfsctl_svc { - unsigned short svc_port; - int svc_nthreads; -}; - -/* ADDCLIENT/DELCLIENT */ -struct nfsctl_client { - char cl_ident[NFSCLNT_IDMAX+1]; - int cl_naddr; - struct in_addr cl_addrlist[NFSCLNT_ADDRMAX]; - int cl_fhkeytype; - int cl_fhkeylen; - unsigned char cl_fhkey[NFSCLNT_KEYMAX]; -}; - -/* EXPORT/UNEXPORT */ -struct nfsctl_export { - char ex_client[NFSCLNT_IDMAX+1]; - char ex_path[NFS_MAXPATHLEN+1]; - __kernel_old_dev_t ex_dev; - __kernel_ino_t ex_ino; - int ex_flags; - __kernel_uid_t ex_anon_uid; - __kernel_gid_t ex_anon_gid; -}; - -/* GETFD */ -struct nfsctl_fdparm { - struct sockaddr gd_addr; - char gd_path[NFS_MAXPATHLEN+1]; - int gd_version; -}; - -/* GETFS - GET Filehandle with Size */ -struct nfsctl_fsparm { - struct sockaddr gd_addr; - char gd_path[NFS_MAXPATHLEN+1]; - int gd_maxlen; -}; - -/* - * This is the argument union. - */ -struct nfsctl_arg { - int ca_version; /* safeguard */ - union { - struct nfsctl_svc u_svc; - struct nfsctl_client u_client; - struct nfsctl_export u_export; - struct nfsctl_fdparm u_getfd; - struct nfsctl_fsparm u_getfs; - /* - * The following dummy member is needed to preserve binary compatibility - * on platforms where alignof(void*)>alignof(int). It's needed because - * this union used to contain a member (u_umap) which contained a - * pointer. - */ - void *u_ptr; - } u; -#define ca_svc u.u_svc -#define ca_client u.u_client -#define ca_export u.u_export -#define ca_getfd u.u_getfd -#define ca_getfs u.u_getfs -}; - -union nfsctl_res { - __u8 cr_getfh[NFS_FHSIZE]; - struct knfsd_fh cr_getfs; -}; - -#ifdef __KERNEL__ -/* - * Kernel syscall implementation. - */ -extern int exp_addclient(struct nfsctl_client *ncp); -extern int exp_delclient(struct nfsctl_client *ncp); -extern int exp_export(struct nfsctl_export *nxp); -extern int exp_unexport(struct nfsctl_export *nxp); - -#endif /* __KERNEL__ */ - -#endif /* NFSD_SYSCALL_H */ -- cgit v1.2.3 From 5b457e3910251ef28712ba5d14adac8194bd5b2c Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 5 Sep 2011 08:12:05 -0700 Subject: regmap: Remove redundant owner field from the bus type struct No longer used as users link directly with the bus types so the core module infrastructure does refcounting for us. Signed-off-by: Mark Brown --- include/linux/regmap.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 449e2642da95..9438a89e1573 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -85,8 +85,6 @@ typedef int (*regmap_hw_read)(struct device *dev, * if not implemented on a given device. * @read: Read operation. Data is returned in the buffer used to transmit * data. - * @owner: Module with the bus implementation, used to pin the implementation - * in memory. * @read_flag_mask: Mask to be set in the top byte of the register when doing * a read. */ @@ -94,7 +92,6 @@ struct regmap_bus { regmap_hw_write write; regmap_hw_gather_write gather_write; regmap_hw_read read; - struct module *owner; u8 read_flag_mask; }; -- cgit v1.2.3 From 6f306441e97f8f9d27c43a536360fe221f675a71 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 5 Sep 2011 20:46:32 +0200 Subject: regmap: Add support for device specific write and read flag masks. Some buses like SPI have no standard notation of read or write operations. The general scheme here is to set or clear specific bits in the register address to indicate whether the operation is a read or write. We already support having a read flag mask per bus, but as there is no standard the bits which need to be set or cleared differ between devices and vendors, thus we need a mechanism to specify them per device. This patch adds two new entries to the regmap_config struct, read_flag_mask and write_flag_mask. These will be or'ed onto the top byte when doing a read or write operation. If both masks are empty the device will fallback to the regmap_bus masks. Signed-off-by: Lars-Peter Clausen Signed-off-by: Mark Brown --- include/linux/regmap.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 9438a89e1573..18d4afaac166 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -53,6 +53,12 @@ struct reg_default { * @reg_defaults: Power on reset values for registers (for use with * register cache support). * @num_reg_defaults: Number of elements in reg_defaults. + * + * @read_flag_mask: Mask to be set in the top byte of the register when doing + * a read. + * @write_flag_mask: Mask to be set in the top byte of the register when doing + * a write. If both read_flag_mask and write_flag_mask are + * empty the regmap_bus default masks are used. */ struct regmap_config { int reg_bits; @@ -66,6 +72,9 @@ struct regmap_config { unsigned int max_register; struct reg_default *reg_defaults; int num_reg_defaults; + + u8 read_flag_mask; + u8 write_flag_mask; }; typedef int (*regmap_hw_write)(struct device *dev, const void *data, -- cgit v1.2.3 From d1748302f70be7469809809283fe164156a34231 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Tue, 23 Aug 2011 15:29:42 +0200 Subject: clockevents: Make minimum delay adjustments configurable The automatic increase of the min_delta_ns of a clockevents device should be done in the clockevents code as the minimum delay is an attribute of the clockevents device. In addition not all architectures want the automatic adjustment, on a massively virtualized system it can happen that the programming of a clock event fails several times in a row because the virtual cpu has been rescheduled quickly enough. In that case the minimum delay will erroneously be increased with no way back. The new config symbol GENERIC_CLOCKEVENTS_MIN_ADJUST is used to enable the automatic adjustment. The config option is selected only for x86. Signed-off-by: Martin Schwidefsky Cc: john stultz Link: http://lkml.kernel.org/r/20110823133142.494157493@de.ibm.com Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index d6733e27af34..39bb050bdbb2 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -140,7 +140,7 @@ extern void clockevents_set_mode(struct clock_event_device *dev, enum clock_event_mode mode); extern int clockevents_register_notifier(struct notifier_block *nb); extern int clockevents_program_event(struct clock_event_device *dev, - ktime_t expires, ktime_t now); + ktime_t expires, bool force); extern void clockevents_handle_noop(struct clock_event_device *dev); -- cgit v1.2.3 From 65516f8a7c2028381f0dae4c16ddb621c96158cc Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Tue, 23 Aug 2011 15:29:43 +0200 Subject: clockevents: Add direct ktime programming function There is at least one architecture (s390) with a sane clockevent device that can be programmed with the equivalent of a ktime. No need to create a delta against the current time, the ktime can be used directly. A new clock device function 'set_next_ktime' is introduced that is called with the unmodified ktime for the timer if the clock event device has the CLOCK_EVT_FEAT_KTIME bit set. Signed-off-by: Martin Schwidefsky Cc: john stultz Link: http://lkml.kernel.org/r/20110823133142.815350967@de.ibm.com Signed-off-by: Thomas Gleixner --- include/linux/clockchips.h | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 39bb050bdbb2..81e803e90aa4 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -45,20 +45,22 @@ enum clock_event_nofitiers { */ #define CLOCK_EVT_FEAT_PERIODIC 0x000001 #define CLOCK_EVT_FEAT_ONESHOT 0x000002 +#define CLOCK_EVT_FEAT_KTIME 0x000004 /* * x86(64) specific misfeatures: * * - Clockevent source stops in C3 State and needs broadcast support. * - Local APIC timer is used as a dummy device. */ -#define CLOCK_EVT_FEAT_C3STOP 0x000004 -#define CLOCK_EVT_FEAT_DUMMY 0x000008 +#define CLOCK_EVT_FEAT_C3STOP 0x000008 +#define CLOCK_EVT_FEAT_DUMMY 0x000010 /** * struct clock_event_device - clock event device descriptor * @event_handler: Assigned by the framework to be called by the low * level handler of the event source - * @set_next_event: set next event function + * @set_next_event: set next event function using a clocksource delta + * @set_next_ktime: set next event function using a direct ktime value * @next_event: local storage for the next event in oneshot mode * @max_delta_ns: maximum delta value in ns * @min_delta_ns: minimum delta value in ns @@ -81,6 +83,8 @@ struct clock_event_device { void (*event_handler)(struct clock_event_device *); int (*set_next_event)(unsigned long evt, struct clock_event_device *); + int (*set_next_ktime)(ktime_t expires, + struct clock_event_device *); ktime_t next_event; u64 max_delta_ns; u64 min_delta_ns; -- cgit v1.2.3 From e8abccb719377af63cb0f1fed289db405e3def16 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 1 Sep 2011 12:42:04 +0200 Subject: posix-cpu-timers: Cure SMP accounting oddities David reported: Attached below is a watered-down version of rt/tst-cpuclock2.c from GLIBC. Just build it with "gcc -o test test.c -lpthread -lrt" or similar. Run it several times, and you will see cases where the main thread will measure a process clock difference before and after the nanosleep which is smaller than the cpu-burner thread's individual thread clock difference. This doesn't make any sense since the cpu-burner thread is part of the top-level process's thread group. I've reproduced this on both x86-64 and sparc64 (using both 32-bit and 64-bit binaries). For example: [davem@boricha build-x86_64-linux]$ ./test process: before(0.001221967) after(0.498624371) diff(497402404) thread: before(0.000081692) after(0.498316431) diff(498234739) self: before(0.001223521) after(0.001240219) diff(16698) [davem@boricha build-x86_64-linux]$ The diff of 'process' should always be >= the diff of 'thread'. I make sure to wrap the 'thread' clock measurements the most tightly around the nanosleep() call, and that the 'process' clock measurements are the outer-most ones. --- #include #include #include #include #include #include #include #include static pthread_barrier_t barrier; static void *chew_cpu(void *arg) { pthread_barrier_wait(&barrier); while (1) __asm__ __volatile__("" : : : "memory"); return NULL; } int main(void) { clockid_t process_clock, my_thread_clock, th_clock; struct timespec process_before, process_after; struct timespec me_before, me_after; struct timespec th_before, th_after; struct timespec sleeptime; unsigned long diff; pthread_t th; int err; err = clock_getcpuclockid(0, &process_clock); if (err) return 1; err = pthread_getcpuclockid(pthread_self(), &my_thread_clock); if (err) return 1; pthread_barrier_init(&barrier, NULL, 2); err = pthread_create(&th, NULL, chew_cpu, NULL); if (err) return 1; err = pthread_getcpuclockid(th, &th_clock); if (err) return 1; pthread_barrier_wait(&barrier); err = clock_gettime(process_clock, &process_before); if (err) return 1; err = clock_gettime(my_thread_clock, &me_before); if (err) return 1; err = clock_gettime(th_clock, &th_before); if (err) return 1; sleeptime.tv_sec = 0; sleeptime.tv_nsec = 500000000; nanosleep(&sleeptime, NULL); err = clock_gettime(th_clock, &th_after); if (err) return 1; err = clock_gettime(my_thread_clock, &me_after); if (err) return 1; err = clock_gettime(process_clock, &process_after); if (err) return 1; diff = process_after.tv_nsec - process_before.tv_nsec; printf("process: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", process_before.tv_sec, process_before.tv_nsec, process_after.tv_sec, process_after.tv_nsec, diff); diff = th_after.tv_nsec - th_before.tv_nsec; printf("thread: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", th_before.tv_sec, th_before.tv_nsec, th_after.tv_sec, th_after.tv_nsec, diff); diff = me_after.tv_nsec - me_before.tv_nsec; printf("self: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", me_before.tv_sec, me_before.tv_nsec, me_after.tv_sec, me_after.tv_nsec, diff); return 0; } This is due to us using p->se.sum_exec_runtime in thread_group_cputime() where we iterate the thread group and sum all data. This does not take time since the last schedule operation (tick or otherwise) into account. We can cure this by using task_sched_runtime() at the cost of having to take locks. This also means we can (and must) do away with thread_group_sched_runtime() since the modified thread_group_cputime() is now more accurate and would deadlock when called from thread_group_sched_runtime(). Reported-by: David Miller Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1314874459.7945.22.camel@twins Cc: stable@kernel.org Signed-off-by: Thomas Gleixner --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 20b03bf94748..2909fe7a622d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1955,7 +1955,6 @@ static inline void disable_sched_clock_irqtime(void) {} extern unsigned long long task_sched_runtime(struct task_struct *task); -extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP -- cgit v1.2.3 From 9962444f592a53c08ce439b6dc362bba7ce5fd7e Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Thu, 1 Sep 2011 22:26:25 +0300 Subject: usb: dwc3: omap: distinguish between SW and HW modes The OMAP wrapper allows us to either control internal OTG signals via SW or HW. Different boards might wish to use one or the other mode of operation. Let's have have that information passed via platform_data for now. After DT conversion is finished for OMAP, we can easily convert this to a DT attribute. Signed-off-by: Felipe Balbi --- include/linux/platform_data/dwc3-omap.h | 47 +++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 include/linux/platform_data/dwc3-omap.h (limited to 'include/linux') diff --git a/include/linux/platform_data/dwc3-omap.h b/include/linux/platform_data/dwc3-omap.h new file mode 100644 index 000000000000..ada401244e0b --- /dev/null +++ b/include/linux/platform_data/dwc3-omap.h @@ -0,0 +1,47 @@ +/** + * dwc3-omap.h - OMAP Specific Glue layer, header. + * + * Copyright (C) 2010-2011 Texas Instruments Incorporated - http://www.ti.com + * All rights reserved. + * + * Author: Felipe Balbi + * + * 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, + * without modification. + * 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. The names of the above-listed copyright holders may not 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. + */ + +enum dwc3_omap_utmi_mode { + DWC3_OMAP_UTMI_MODE_UNKNOWN = 0, + DWC3_OMAP_UTMI_MODE_HW, + DWC3_OMAP_UTMI_MODE_SW, +}; + +struct dwc3_omap_data { + enum dwc3_omap_utmi_mode utmi_mode; +}; -- cgit v1.2.3 From fc9ff9b7e3eaff3f49bc0fbbddfc1416212e888a Mon Sep 17 00:00:00 2001 From: "rongqing.li@windriver.com" Date: Tue, 6 Sep 2011 11:35:36 +0800 Subject: security: Fix a typo Fix a typo. Signed-off-by: Roy.Li Signed-off-by: James Morris --- include/linux/security.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index d9f7ec41ba51..a14c2d4b22cf 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1372,7 +1372,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @inode_getsecctx: * Returns a string containing all relavent security context information * - * @inode we wish to set the security context of. + * @inode we wish to get the security context of. * @ctx is a pointer in which to place the allocated security context. * @ctxlen points to the place to put the length of @ctx. * This is the main security structure. -- cgit v1.2.3 From 5dbe3040c74eef18e66951347eda05b153e69328 Mon Sep 17 00:00:00 2001 From: James Morris Date: Tue, 30 Aug 2011 13:48:53 +1000 Subject: security: sparse fix: Move security_fixup_op to security.h Fix sparse warning by moving declaraion to global header. Signed-off-by: James Morris --- include/linux/security.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/security.h b/include/linux/security.h index a14c2d4b22cf..19d8e04e1688 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1660,6 +1660,8 @@ struct security_operations { extern int security_init(void); extern int security_module_enable(struct security_operations *ops); extern int register_security(struct security_operations *ops); +extern void __init security_fixup_ops(struct security_operations *ops); + /* Security operations */ int security_ptrace_access_check(struct task_struct *child, unsigned int mode); -- cgit v1.2.3 From 60f96b41f71d2a13d1c0a457b8b77958f77142d1 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Fri, 9 Sep 2011 13:59:35 +0530 Subject: genirq: Add IRQCHIP_SKIP_SET_WAKE flag Some irq chips need the irq_set_wake() functionality, but do not require a irq_set_wake() callback. Instead of forcing an empty callback to be implemented add a flag which notes this fact. Check for the flag in set_irq_wake_real() and return success when set. Signed-off-by: Santosh Shilimkar Cc: Thomas Gleixner --- 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 59517300a315..73e31abeba1c 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -336,12 +336,14 @@ struct irq_chip { * IRQCHIP_MASK_ON_SUSPEND: Mask non wake irqs in the suspend path * IRQCHIP_ONOFFLINE_ENABLED: Only call irq_on/off_line callbacks * when irq enabled + * IRQCHIP_SKIP_SET_WAKE: Skip chip.irq_set_wake(), for this irq chip */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), IRQCHIP_EOI_IF_HANDLED = (1 << 1), IRQCHIP_MASK_ON_SUSPEND = (1 << 2), IRQCHIP_ONOFFLINE_ENABLED = (1 << 3), + IRQCHIP_SKIP_SET_WAKE = (1 << 4), }; /* This include will go away once we isolated irq_desc usage to core code */ -- cgit v1.2.3 From ec484608c5885931c432e99ecfd2772288cd993c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 25 Jul 2009 16:09:17 +0200 Subject: locking, kprobes: Annotate the hash locks and kretprobe.lock as raw The kprobe locks can be taken in atomic context and therefore cannot be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/kprobes.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index dd7c12e875bc..dce6e4dbeda7 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -181,7 +181,7 @@ struct kretprobe { int nmissed; size_t data_size; struct hlist_head free_instances; - spinlock_t lock; + raw_spinlock_t lock; }; struct kretprobe_instance { -- cgit v1.2.3 From f032a450812f6c7edd532772cc7c48091bca9f27 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 25 Jul 2009 16:21:48 +0200 Subject: locking, percpu_counter: Annotate ::lock as raw The percpu_counter::lock can be taken in atomic context and therefore cannot be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/percpu_counter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 5edc9014263a..b9df9ed1adc0 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -16,7 +16,7 @@ #ifdef CONFIG_SMP struct percpu_counter { - spinlock_t lock; + raw_spinlock_t lock; s64 count; #ifdef CONFIG_HOTPLUG_CPU struct list_head list; /* All percpu_counters are on a list */ -- cgit v1.2.3 From 740969f91e950b64a18fdd0a25164cdee042abf0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 25 Jul 2009 16:43:30 +0200 Subject: locking, lib/proportions: Annotate prop_local_percpu::lock as raw The prop_local_percpu::lock can be taken in atomic context and therefore cannot be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/proportions.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proportions.h b/include/linux/proportions.h index cf793bbbd05e..ef35bb73f69b 100644 --- a/include/linux/proportions.h +++ b/include/linux/proportions.h @@ -58,7 +58,7 @@ struct prop_local_percpu { */ int shift; unsigned long period; - spinlock_t lock; /* protect the snapshot state */ + raw_spinlock_t lock; /* protect the snapshot state */ }; int prop_local_init_percpu(struct prop_local_percpu *pl); @@ -106,11 +106,11 @@ struct prop_local_single { */ unsigned long period; int shift; - spinlock_t lock; /* protect the snapshot state */ + raw_spinlock_t lock; /* protect the snapshot state */ }; #define INIT_PROP_LOCAL_SINGLE(name) \ -{ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ +{ .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ } int prop_local_init_single(struct prop_local_single *pl); -- cgit v1.2.3 From 07354eb1a74d1e1ece29f8bafe0b46e8c77a95ef Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 25 Jul 2009 17:50:36 +0200 Subject: locking, printk: Annotate logbuf_lock as raw The logbuf_lock lock can be taken in atomic context and therefore cannot be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner [ merged and fixed it ] Signed-off-by: Ingo Molnar --- include/linux/ratelimit.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h index 2f007157fab9..e11ccb4cf48d 100644 --- a/include/linux/ratelimit.h +++ b/include/linux/ratelimit.h @@ -8,7 +8,7 @@ #define DEFAULT_RATELIMIT_BURST 10 struct ratelimit_state { - spinlock_t lock; /* protect the state */ + raw_spinlock_t lock; /* protect the state */ int interval; int burst; @@ -20,7 +20,7 @@ struct ratelimit_state { #define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init) \ \ struct ratelimit_state name = { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock), \ .interval = interval_init, \ .burst = burst_init, \ } @@ -28,7 +28,7 @@ struct ratelimit_state { static inline void ratelimit_state_init(struct ratelimit_state *rs, int interval, int burst) { - spin_lock_init(&rs->lock); + raw_spin_lock_init(&rs->lock); rs->interval = interval; rs->burst = burst; rs->printed = 0; -- cgit v1.2.3 From ee30a7b2fc072f139dac44826860d2c1f422137c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 25 Jul 2009 18:56:56 +0200 Subject: locking, sched: Annotate thread_group_cputimer as raw The thread_group_cputimer lock can be taken in atomic context and therefore cannot be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/init_task.h | 2 +- include/linux/sched.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index d14e058aaeed..08ffab01e76c 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -42,7 +42,7 @@ extern struct fs_struct init_fs; .cputimer = { \ .cputime = INIT_CPUTIME, \ .running = 0, \ - .lock = __SPIN_LOCK_UNLOCKED(sig.cputimer.lock), \ + .lock = __RAW_SPIN_LOCK_UNLOCKED(sig.cputimer.lock), \ }, \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ac2c0578e0f..e672236c08e0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -510,7 +510,7 @@ struct task_cputime { struct thread_group_cputimer { struct task_cputime cputime; int running; - spinlock_t lock; + raw_spinlock_t lock; }; #include @@ -2566,7 +2566,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times); static inline void thread_group_cputime_init(struct signal_struct *sig) { - spin_lock_init(&sig->cputimer.lock); + raw_spin_lock_init(&sig->cputimer.lock); } /* -- cgit v1.2.3 From 8292c9e15c3b069459794a04f5e2cf0d5665ddc4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 24 Feb 2010 09:50:22 +0100 Subject: locking, semaphores: Annotate inner lock as raw There is no reason to have the spin_lock protecting the semaphore preemptible on -rt. Annotate it as a raw_spinlock. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. ( On rt this also solves lockdep complaining about the rt_mutex.wait_lock being not initialized. ) Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/semaphore.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index 39fa04966aa8..dc368b8ce215 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -14,14 +14,14 @@ /* Please don't access any members of this structure directly */ struct semaphore { - spinlock_t lock; + raw_spinlock_t lock; unsigned int count; struct list_head wait_list; }; #define __SEMAPHORE_INITIALIZER(name, n) \ { \ - .lock = __SPIN_LOCK_UNLOCKED((name).lock), \ + .lock = __RAW_SPIN_LOCK_UNLOCKED((name).lock), \ .count = n, \ .wait_list = LIST_HEAD_INIT((name).wait_list), \ } -- cgit v1.2.3 From ddb6c9b58a19edcfac93ac670b066c836ff729f1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 24 Feb 2010 09:54:54 +0100 Subject: locking, rwsem: Annotate inner lock as raw There is no reason to allow the lock protecting rwsems (the ownerless variant) to be preemptible on -rt. Convert it to raw. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/rwsem-spinlock.h | 2 +- include/linux/rwsem.h | 10 ++++++---- 2 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h index 34701241b673..d5b13bc07a0b 100644 --- a/include/linux/rwsem-spinlock.h +++ b/include/linux/rwsem-spinlock.h @@ -22,7 +22,7 @@ */ struct rw_semaphore { __s32 activity; - spinlock_t wait_lock; + raw_spinlock_t wait_lock; struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 6a6741440cb7..63d406554391 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -25,7 +25,7 @@ struct rw_semaphore; /* All arch specific implementations share the same struct */ struct rw_semaphore { long count; - spinlock_t wait_lock; + raw_spinlock_t wait_lock; struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; @@ -56,9 +56,11 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem) # define __RWSEM_DEP_MAP_INIT(lockname) #endif -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED(name.wait_lock), \ - LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) } +#define __RWSEM_INITIALIZER(name) \ + { RWSEM_UNLOCKED_VALUE, \ + __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ + LIST_HEAD_INIT((name).wait_list) \ + __RWSEM_DEP_MAP_INIT(name) } #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) -- cgit v1.2.3 From 2d21a29fb62f142b8a62496700d8d82a6a8fd783 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 25 Jul 2009 16:18:34 +0200 Subject: locking, oprofile: Annotate oprofilefs lock as raw The oprofilefs_lock can be taken in atomic context (in profiling interrupts) and therefore cannot cannot be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/oprofile.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h index 49c8727eeb57..a4c562453f6b 100644 --- a/include/linux/oprofile.h +++ b/include/linux/oprofile.h @@ -166,7 +166,7 @@ ssize_t oprofilefs_ulong_to_user(unsigned long val, char __user * buf, size_t co int oprofilefs_ulong_from_user(unsigned long * val, char const __user * buf, size_t count); /** lock for read/write safety */ -extern spinlock_t oprofilefs_lock; +extern raw_spinlock_t oprofilefs_lock; /** * Add the contents of a circular buffer to the event buffer. -- cgit v1.2.3 From 1f5b3c3fd2d73d6b30e9ef6dcbf131a791d5cbbd Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 19 Jul 2011 16:19:51 +0200 Subject: locking, x86, iommu: Annotate iommu->register_lock as raw The iommu->register_lock can be taken in atomic context and therefore must not be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/intel-iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 9310c699a37d..19728c462399 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -311,7 +311,7 @@ struct intel_iommu { u64 cap; u64 ecap; u32 gcmd; /* Holds TE, EAFL. Don't need SRTP, SFL, WBF */ - spinlock_t register_lock; /* protect register handling */ + raw_spinlock_t register_lock; /* protect register handling */ int seq_id; /* sequence id of the iommu */ int agaw; /* agaw of this iommu */ int msagaw; /* max sagaw of this iommu */ -- cgit v1.2.3 From 3b8f40481513a7b6123def5a02db4cff96ae2198 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 19 Jul 2011 17:02:07 +0200 Subject: locking, x86, iommu: Annotate qi->q_lock as raw The qi->q_lock lock can be taken in atomic context and therefore cannot be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/intel-iommu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 19728c462399..8b9b5d365f4e 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -271,7 +271,7 @@ struct qi_desc { }; struct q_inval { - spinlock_t q_lock; + raw_spinlock_t q_lock; struct qi_desc *desc; /* invalidation queue */ int *desc_status; /* desc status */ int free_head; /* first free entry */ -- cgit v1.2.3 From ed748aacb8e3318fa2cf24e1c197d35b5fd29605 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 12 Sep 2011 19:37:06 -0400 Subject: NFSD: Cleanup for nfsd4_path() The current code is sort of hackish in that it assumes a referral is always matched to an export. When we add support for junctions that may not be the case. We can replace nfsd4_path() with a function that encodes the components directly from the dentries. Since nfsd4_path is currently the only user of the 'ex_pathname' field in struct svc_export, this has the added benefit of allowing us to get rid of that. Signed-off-by: Trond Myklebust Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/nfsd/export.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 8a31a20efe7e..7ba3fd43f312 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -137,6 +137,7 @@ struct svc_export * rqst_exp_get_by_name(struct svc_rqst *, struct path *); struct svc_export * rqst_exp_parent(struct svc_rqst *, struct path *); +struct svc_export * rqst_find_fsidzero_export(struct svc_rqst *); int exp_rootfh(struct auth_domain *, char *path, struct knfsd_fh *, int maxsize); __be32 exp_pseudoroot(struct svc_rqst *, struct svc_fh *); -- cgit v1.2.3 From 2f1ddda1749a223d1a05e16dc6ea28632b9ec570 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 12 Sep 2011 19:37:16 -0400 Subject: NFSD: Remove the ex_pathname field from struct svc_export There are no more users... Signed-off-by: Trond Myklebust Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/nfsd/export.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h index 7ba3fd43f312..f85308e688fd 100644 --- a/include/linux/nfsd/export.h +++ b/include/linux/nfsd/export.h @@ -96,7 +96,6 @@ struct svc_export { struct auth_domain * ex_client; int ex_flags; struct path ex_path; - char *ex_pathname; uid_t ex_anon_uid; gid_t ex_anon_gid; int ex_fsid; -- cgit v1.2.3 From 849a1cf13d4394d398d91752166e92e9ecd64f8d Mon Sep 17 00:00:00 2001 From: Mi Jinlong Date: Tue, 30 Aug 2011 17:18:41 +0800 Subject: SUNRPC: Replace svc_addr_u by sockaddr_storage For IPv6 local address, lockd can not callback to client for missing scope id when binding address at inet6_bind: 324 if (addr_type & IPV6_ADDR_LINKLOCAL) { 325 if (addr_len >= sizeof(struct sockaddr_in6) && 326 addr->sin6_scope_id) { 327 /* Override any existing binding, if another one 328 * is supplied by user. 329 */ 330 sk->sk_bound_dev_if = addr->sin6_scope_id; 331 } 332 333 /* Binding to link-local address requires an interface */ 334 if (!sk->sk_bound_dev_if) { 335 err = -EINVAL; 336 goto out_unlock; 337 } Replacing svc_addr_u by sockaddr_storage, let rqstp->rq_daddr contains more info besides address. Reviewed-by: Jeff Layton Reviewed-by: Chuck Lever Signed-off-by: Mi Jinlong Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index a78a51e93373..d8d5d93071b3 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -212,11 +212,6 @@ static inline void svc_putu32(struct kvec *iov, __be32 val) iov->iov_len += sizeof(__be32); } -union svc_addr_u { - struct in_addr addr; - struct in6_addr addr6; -}; - /* * The context of a single thread, including the request currently being * processed. @@ -225,8 +220,12 @@ struct svc_rqst { struct list_head rq_list; /* idle list */ struct list_head rq_all; /* all threads list */ struct svc_xprt * rq_xprt; /* transport ptr */ + struct sockaddr_storage rq_addr; /* peer address */ size_t rq_addrlen; + struct sockaddr_storage rq_daddr; /* dest addr of request + * - reply from here */ + size_t rq_daddrlen; struct svc_serv * rq_server; /* RPC service definition */ struct svc_pool * rq_pool; /* thread pool */ @@ -255,9 +254,6 @@ struct svc_rqst { unsigned short rq_secure : 1; /* secure port */ - union svc_addr_u rq_daddr; /* dest addr of request - * - reply from here */ - void * rq_argp; /* decoded arguments */ void * rq_resp; /* xdr'd results */ void * rq_auth_data; /* flavor-specific data */ @@ -300,6 +296,21 @@ static inline struct sockaddr *svc_addr(const struct svc_rqst *rqst) return (struct sockaddr *) &rqst->rq_addr; } +static inline struct sockaddr_in *svc_daddr_in(const struct svc_rqst *rqst) +{ + return (struct sockaddr_in *) &rqst->rq_daddr; +} + +static inline struct sockaddr_in6 *svc_daddr_in6(const struct svc_rqst *rqst) +{ + return (struct sockaddr_in6 *) &rqst->rq_daddr; +} + +static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst) +{ + return (struct sockaddr *) &rqst->rq_daddr; +} + /* * Check buffer bounds after decoding arguments */ @@ -340,7 +351,8 @@ struct svc_deferred_req { struct svc_xprt *xprt; struct sockaddr_storage addr; /* where reply must go */ size_t addrlen; - union svc_addr_u daddr; /* where reply must come from */ + struct sockaddr_storage daddr; /* where reply must come from */ + size_t daddrlen; struct cache_deferred_req handle; size_t xprt_hlen; int argslen; -- cgit v1.2.3 From 038c01598e728cda5b2996c4bf883e8485b2fe50 Mon Sep 17 00:00:00 2001 From: Mi Jinlong Date: Tue, 30 Aug 2011 17:22:49 +0800 Subject: SUNRPC: compare scopeid for link-local addresses For ipv6 link-local addresses, sunrpc do not compare those scope id. This patch let sunrpc compares scope id only on link-local addresses. Signed-off-by: Mi Jinlong Reviewed-by: Chuck Lever Reviewed-by: Jeff Layton Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/clnt.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index db7bcaf7c5bd..ee1bb67f525e 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -218,7 +218,13 @@ static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1, { const struct sockaddr_in6 *sin1 = (const struct sockaddr_in6 *)sap1; const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2; - return ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr); + + if (!ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr)) + return false; + else if (ipv6_addr_type(&sin1->sin6_addr) & IPV6_ADDR_LINKLOCAL) + return sin1->sin6_scope_id == sin2->sin6_scope_id; + + return true; } static inline bool __rpc_copy_addr6(struct sockaddr *dst, -- cgit v1.2.3 From bf6d0f5dcda17df3cc5577e203d0f8ea1c2ad6aa Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Thu, 18 Aug 2011 18:07:44 -0400 Subject: evm: posix acls modify i_mode The posix xattr acls are 'system' prefixed, which normally would not affect security.evm. An interesting side affect of writing posix xattr acls is their modifying of the i_mode, which is included in security.evm. This patch updates security.evm when posix xattr acls are written. Signed-off-by: Mimi Zohar --- include/linux/evm.h | 8 ++++++++ include/linux/xattr.h | 5 +++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/evm.h b/include/linux/evm.h index ea603c9e775d..9fc13a760928 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -33,6 +33,14 @@ extern void evm_inode_post_removexattr(struct dentry *dentry, extern int evm_inode_init_security(struct inode *inode, const struct xattr *xattr_array, struct xattr *evm); +#ifdef CONFIG_FS_POSIX_ACL +extern int posix_xattr_acl(const char *xattrname); +#else +static inline int posix_xattr_acl(const char *xattrname) +{ + return 0; +} +#endif #else #ifdef CONFIG_INTEGRITY static inline enum integrity_status evm_verifyxattr(struct dentry *dentry, diff --git a/include/linux/xattr.h b/include/linux/xattr.h index b20cb965c322..e5d122031542 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -52,6 +52,11 @@ #define XATTR_CAPS_SUFFIX "capability" #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX +#define XATTR_POSIX_ACL_ACCESS "posix_acl_access" +#define XATTR_NAME_POSIX_ACL_ACCESS XATTR_SYSTEM_PREFIX XATTR_POSIX_ACL_ACCESS +#define XATTR_POSIX_ACL_DEFAULT "posix_acl_default" +#define XATTR_NAME_POSIX_ACL_DEFAULT XATTR_SYSTEM_PREFIX XATTR_POSIX_ACL_DEFAULT + #ifdef __KERNEL__ #include -- cgit v1.2.3 From 566be59ab86c0e030b980645a580d683a015a483 Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Mon, 22 Aug 2011 09:14:18 -0400 Subject: evm: permit mode bits to be updated Before permitting 'security.evm' to be updated, 'security.evm' must exist and be valid. In the case that there are no existing EVM protected xattrs, it is safe for posix acls to update the mode bits. To differentiate between no 'security.evm' xattr and no xattrs used to calculate 'security.evm', this patch defines INTEGRITY_NOXATTR. Signed-off-by: Mimi Zohar --- include/linux/integrity.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/integrity.h b/include/linux/integrity.h index 968443385678..a0c41256cb92 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -16,6 +16,7 @@ enum integrity_status { INTEGRITY_PASS = 0, INTEGRITY_FAIL, INTEGRITY_NOLABEL, + INTEGRITY_NOXATTRS, INTEGRITY_UNKNOWN, }; -- cgit v1.2.3 From 1d273b929cad7b1ee95d5c15ac806b3abc764278 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 3 Jun 2011 02:28:46 -0700 Subject: drbd: Use angle brackets for system includes Use the normal include style. Signed-off-by: Joe Perches Signed-off-by: Jiri Kosina --- include/linux/drbd_tag_magic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/drbd_tag_magic.h b/include/linux/drbd_tag_magic.h index 069543190516..81f52f2c5724 100644 --- a/include/linux/drbd_tag_magic.h +++ b/include/linux/drbd_tag_magic.h @@ -28,7 +28,7 @@ enum packet_types { #define NL_STRING(pn, pr, member, len) \ unsigned char member[len]; int member ## _len; \ int tag_and_len ## member; -#include "linux/drbd_nl.h" +#include /* declare tag-list-sizes */ static const int tag_list_sizes[] = { -- cgit v1.2.3 From e81b15168e2d3d1ab56b13782fe8ad0cb362379d Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Mon, 1 Aug 2011 23:04:30 +0200 Subject: Remove unneeded version.h includes from include/ It was pointed out by 'make versioncheck' that some includes of linux/version.h are not needed in include/. This patch removes them. When I last posted the patch, the ceph bit was ACK'ed by Sage Weil, so I've added that below. The pwc-ioctl change generated quite a bit of discussion about V4L version numbers in general, but as far as I can tell, no concensus was reached on what the long term solution should be, so in the mean time I think we could start by just removing the unneeded include, which is why I'm resending the patch with that hunk still included. Signed-off-by: Jesper Juhl Acked-by: Sage Weil Signed-off-by: Jiri Kosina --- include/linux/ceph/messenger.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 31d91a64838b..291aa6e18d31 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -6,7 +6,6 @@ #include #include #include -#include #include #include "types.h" -- cgit v1.2.3 From e538dfdae85244fd2c4231725d82cc1f1bc4942c Mon Sep 17 00:00:00 2001 From: Michal Nazarewicz Date: Tue, 30 Aug 2011 17:11:19 +0200 Subject: usb: Provide usb_speed_string() function In a few places in the kernel, the code prints a human-readable USB device speed (eg. "high speed"). This involves a switch statement sometimes wrapped around in ({ ... }) block leading to code repetition. To mitigate this issue, this commit introduces usb_speed_string() function, which returns a human-readable name of provided speed. It also changes a few places switch was used to use this new function. This changes a bit the way the speed is printed in few instances at the same time standardising it. Signed-off-by: Michal Nazarewicz Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 1ded281eff88..f32a64e57f97 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -868,6 +868,18 @@ enum usb_device_speed { USB_SPEED_SUPER, /* usb 3.0 */ }; +#ifdef __KERNEL__ + +/** + * usb_speed_string() - Returns human readable-name of the speed. + * @speed: The speed to return human-readable name for. If it's not + * any of the speeds defined in usb_device_speed enum, string for + * USB_SPEED_UNKNOWN will be returned. + */ +extern const char *usb_speed_string(enum usb_device_speed speed); + +#endif + enum usb_device_state { /* NOTATTACHED isn't in the USB spec, and this state acts * the same as ATTACHED ... but it's clearer this way. -- cgit v1.2.3 From 6249687f76b69cc0b2ad34636f4a18d693ef3262 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 19 Sep 2011 11:35:58 -0400 Subject: tracing: Add a counter clock for those that do not trust clocks When debugging tight race conditions, it can be helpful to have a synchronized tracing method. Although in most cases the global clock provides this functionality, if timings is not the issue, it is more comforting to know that the order of events really happened in a precise order. Instead of using a clock, add a "counter" that is simply an incrementing atomic 64bit counter that orders the events as they are perceived to happen. The trace_clock_counter() is added from the attempt by Peter Zijlstra trying to convert the trace_clock_global() to it. I took Peter's counter code and made trace_clock_counter() instead, and added it to the choice of clocks. Just echo counter > /debug/tracing/trace_clock to activate it. Requested-by: Thomas Gleixner Requested-by: Peter Zijlstra Reviewed-By: Valdis Kletnieks Signed-off-by: Steven Rostedt --- include/linux/trace_clock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/trace_clock.h b/include/linux/trace_clock.h index 7a8130384087..4eb490237d4c 100644 --- a/include/linux/trace_clock.h +++ b/include/linux/trace_clock.h @@ -15,5 +15,6 @@ extern u64 notrace trace_clock_local(void); extern u64 notrace trace_clock(void); extern u64 notrace trace_clock_global(void); +extern u64 notrace trace_clock_counter(void); #endif /* _LINUX_TRACE_CLOCK_H */ -- cgit v1.2.3 From 9fabe24e9b1af84509b842731d2beaf85e66681e Mon Sep 17 00:00:00 2001 From: Dimitris Papastamos Date: Mon, 19 Sep 2011 14:34:00 +0100 Subject: regmap: Introduce caching support This patch introduces caching support for regmap. The regcache API has evolved essentially out of ASoC soc-cache so most of the actual caching types (except LZO) have been tested in the past. The purpose of regcache is to optimize in time and space the handling of register caches. Time optimization is achieved by not having to go over a slow bus like I2C to read the value of a register, instead it is cached locally in memory and can be retrieved faster. Regarding space optimization, some of the cache types are better at packing the caches, for e.g. the rbtree and the LZO caches. By doing this the sacrifice in time still wins over doing I2C transactions. Signed-off-by: Dimitris Papastamos Tested-by: Lars-Peter Clausen Signed-off-by: Mark Brown --- include/linux/regmap.h | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 18d4afaac166..9d8029449292 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -20,6 +20,11 @@ struct i2c_client; struct spi_device; +/* An enum of all the supported cache types */ +enum regcache_type { + REGCACHE_NONE, +}; + /** * Default value for a register. We use an array of structs rather * than a simple array as many modern devices have very sparse @@ -59,6 +64,11 @@ struct reg_default { * @write_flag_mask: Mask to be set in the top byte of the register when doing * a write. If both read_flag_mask and write_flag_mask are * empty the regmap_bus default masks are used. + * + * @cache_type: The actual cache type. + * @reg_defaults_raw: Power on reset values for registers (for use with + * register cache support). + * @num_reg_defaults_raw: Number of elements in reg_defaults_raw. */ struct regmap_config { int reg_bits; @@ -71,7 +81,10 @@ struct regmap_config { unsigned int max_register; struct reg_default *reg_defaults; - int num_reg_defaults; + unsigned int num_reg_defaults; + enum regcache_type cache_type; + const void *reg_defaults_raw; + unsigned int num_reg_defaults_raw; u8 read_flag_mask; u8 write_flag_mask; -- cgit v1.2.3 From 195af65ca92179ac2b524d35d732dc6fecec2744 Mon Sep 17 00:00:00 2001 From: Dimitris Papastamos Date: Mon, 19 Sep 2011 14:34:01 +0100 Subject: regmap: Add the indexed cache support This is the simplest form of a cache available in regcache. Any registers whose default value is 0 are ignored. If any of those registers are modified in the future, they will be placed in the cache on demand. The cache layout is essentially using the provided register defaults by the regcache core directly and does not re-map it to another representation. Signed-off-by: Dimitris Papastamos Signed-off-by: Mark Brown --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 9d8029449292..ae6d3a4cee97 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -23,6 +23,7 @@ struct spi_device; /* An enum of all the supported cache types */ enum regcache_type { REGCACHE_NONE, + REGCACHE_INDEXED, }; /** -- cgit v1.2.3 From 28644c809f44498b8cd91d00b4cdb09e63b99843 Mon Sep 17 00:00:00 2001 From: Dimitris Papastamos Date: Mon, 19 Sep 2011 14:34:02 +0100 Subject: regmap: Add the rbtree cache support This patch adds support for the rbtree cache compression type. Each rbnode manages a variable length block of registers. There can be no two nodes with overlapping blocks. Each block has a base register and a currently top register, all the other registers, if any, lie in between these two and in ascending order. The reasoning behind the construction of this rbtree is simple. In the snd_soc_rbtree_cache_init() function, we iterate over the register defaults provided by the regcache core. For each register value that is non-zero we insert it in the rbtree. In order to determine in which rbnode we need to add the register, we first look if there is another register already added that is adjacent to the one we are about to add. If that is the case we append it in that rbnode block, otherwise we create a new rbnode with a single register in its block and add it to the tree. There are various optimizations across the implementation to speed up lookups by caching the most recently used rbnode. Signed-off-by: Dimitris Papastamos Tested-by: Lars-Peter Clausen Signed-off-by: Mark Brown --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index ae6d3a4cee97..63c4a5e126e9 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -24,6 +24,7 @@ struct spi_device; enum regcache_type { REGCACHE_NONE, REGCACHE_INDEXED, + REGCACHE_RBTREE, }; /** -- cgit v1.2.3 From 2cbbb579bcbe3e11baf1c59920dcd5a780b80447 Mon Sep 17 00:00:00 2001 From: Dimitris Papastamos Date: Mon, 19 Sep 2011 14:34:03 +0100 Subject: regmap: Add the LZO cache support This patch adds support for LZO compression when storing the register cache. For a typical device whose register map would normally occupy 25kB or 50kB by using the LZO compression technique, one can get down to ~5-7kB. There might be a performance penalty associated with each individual read/write due to decompressing/compressing the underlying cache, however that should not be noticeable. These memory benefits depend on whether the target architecture can get rid of the memory occupied by the original register defaults cache which is marked as __devinitconst. Nevertheless there will be some memory gain even if the target architecture can't get rid of the original register map, this should be around ~30-32kB instead of 50kB. Signed-off-by: Dimitris Papastamos Signed-off-by: Mark Brown --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 63c4a5e126e9..cae69e637dff 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -25,6 +25,7 @@ enum regcache_type { REGCACHE_NONE, REGCACHE_INDEXED, REGCACHE_RBTREE, + REGCACHE_LZO }; /** -- cgit v1.2.3 From 39a58439d6006c48941511276c0041f56352c529 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 19 Sep 2011 18:21:49 +0100 Subject: regmap: Prototype regcache_sync() Signed-off-by: Mark Brown --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index cae69e637dff..63b30752adfd 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -140,4 +140,5 @@ int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, int regmap_update_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val); +int regcache_sync(struct regmap *map); #endif -- cgit v1.2.3 From 92afb286d744511f51a05f8acb6c111d05737617 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 19 Sep 2011 18:22:14 +0100 Subject: regmap: Allow drivers to control cache_only flag Signed-off-by: Mark Brown --- include/linux/regmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 63b30752adfd..76ac255a17a5 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -141,4 +141,6 @@ int regmap_update_bits(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val); int regcache_sync(struct regmap *map); +void regcache_cache_only(struct regmap *map, bool enable); + #endif -- cgit v1.2.3 From 523d9cfbb2094e095ff08a01c4eac10cc7d287c3 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Thu, 15 Sep 2011 18:54:53 +0200 Subject: mfd: Support software initiated shutdown of WM831x PMICs In systems where there is no hardware signal from the processor to the PMIC to initiate the final power off sequence we must initiate the shutdown with a register write to the PMIC. Support such systems in the driver. Since this may prevent a full shutdown of the system platform data is used to enable the feature. Signed-off-by: Mark Brown Signed-off-by: Samuel Ortiz --- include/linux/mfd/wm831x/core.h | 3 +++ include/linux/mfd/wm831x/pdata.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h index 44acdb25681b..ed8fe0d04097 100644 --- a/include/linux/mfd/wm831x/core.h +++ b/include/linux/mfd/wm831x/core.h @@ -371,6 +371,8 @@ struct wm831x { int irq_masks_cur[WM831X_NUM_IRQ_REGS]; /* Currently active value */ int irq_masks_cache[WM831X_NUM_IRQ_REGS]; /* Cached hardware value */ + bool soft_shutdown; + /* Chip revision based flags */ unsigned has_gpio_ena:1; /* Has GPIO enable bit */ unsigned has_cs_sts:1; /* Has current sink status bit */ @@ -409,6 +411,7 @@ int wm831x_bulk_read(struct wm831x *wm831x, unsigned short reg, int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq); void wm831x_device_exit(struct wm831x *wm831x); int wm831x_device_suspend(struct wm831x *wm831x); +void wm831x_device_shutdown(struct wm831x *wm831x); int wm831x_irq_init(struct wm831x *wm831x, int irq); void wm831x_irq_exit(struct wm831x *wm831x); void wm831x_auxadc_init(struct wm831x *wm831x); diff --git a/include/linux/mfd/wm831x/pdata.h b/include/linux/mfd/wm831x/pdata.h index 0ba24599fe51..1d7a3f7b3b5d 100644 --- a/include/linux/mfd/wm831x/pdata.h +++ b/include/linux/mfd/wm831x/pdata.h @@ -123,6 +123,9 @@ struct wm831x_pdata { /** Disable the touchscreen */ bool disable_touch; + /** The driver should initiate a power off sequence during shutdown */ + bool soft_shutdown; + int irq_base; int gpio_base; int gpio_defaults[WM831X_GPIO_NUM]; -- cgit v1.2.3 From b78049831ffed65f0b4e61f69df14f3ab17922cb Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Tue, 20 Sep 2011 11:23:49 -0400 Subject: lib: add error checking to hex2bin hex2bin converts a hexadecimal string to its binary representation. The original version of hex2bin did not do any error checking. This patch adds error checking and returns the result. Changelog v1: - removed unpack_hex_byte() - changed return code from boolean to int Changelog: - use the new unpack_hex_byte() - add __must_check compiler option (Andy Shevchenko's suggestion) - change function API to return error checking result (based on Tetsuo Handa's initial patch) Signed-off-by: Mimi Zohar Acked-by: Andy Shevchenko --- include/linux/kernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 46ac9a50528d..8eefcf7e95eb 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -382,7 +382,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) } extern int hex_to_bin(char ch); -extern void hex2bin(u8 *dst, const char *src, size_t count); +extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); /* * General tracing related utility functions - trace_printk(), -- cgit v1.2.3 From 41750d31fc9599fd81763e685a6b7b42d298c4f8 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 23 Aug 2011 17:05:18 -0700 Subject: x86, x2apic: Enable the bios request for x2apic optout On the platforms which are x2apic and interrupt-remapping capable, Linux kernel is enabling x2apic even if the BIOS doesn't. This is to take advantage of the features that x2apic brings in. Some of the OEM platforms are running into issues because of this, as their bios is not x2apic aware. For example, this was resulting in interrupt migration issues on one of the platforms. Also if the BIOS SMI handling uses APIC interface to send SMI's, then the BIOS need to be aware of x2apic mode that OS has enabled. On some of these platforms, BIOS doesn't have a HW mechanism to turnoff the x2apic feature to prevent OS from enabling it. To resolve this mess, recent changes to the VT-d2 specification: http://download.intel.com/technology/computing/vptech/Intel(r)_VT_for_Direct_IO.pdf includes a mechanism that provides BIOS a way to request system software to opt out of enabling x2apic mode. Look at the x2apic optout flag in the DMAR tables before enabling the x2apic mode in the platform. Also print a warning that we have disabled x2apic based on the BIOS request. Kernel boot parameter "intremap=no_x2apic_optout" can be used to override the BIOS x2apic optout request. Signed-off-by: Youquan Song Signed-off-by: Suresh Siddha Cc: yinghai@kernel.org Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.171766616@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar --- include/linux/dmar.h | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 7b776d71d36d..2dc810e35dd0 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -26,8 +26,13 @@ #include #include +/* DMAR Flags */ +#define DMAR_INTR_REMAP 0x1 +#define DMAR_X2APIC_OPT_OUT 0x2 + struct intel_iommu; #if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP) +extern struct acpi_table_header *dmar_tbl; struct dmar_drhd_unit { struct list_head list; /* list of drhd units */ struct acpi_dmar_header *hdr; /* ACPI header */ @@ -110,7 +115,7 @@ struct irte { #ifdef CONFIG_INTR_REMAP extern int intr_remapping_enabled; extern int intr_remapping_supported(void); -extern int enable_intr_remapping(int); +extern int enable_intr_remapping(void); extern void disable_intr_remapping(void); extern int reenable_intr_remapping(int); @@ -177,7 +182,7 @@ static inline int set_msi_sid(struct irte *irte, struct pci_dev *dev) #define intr_remapping_enabled (0) -static inline int enable_intr_remapping(int eim) +static inline int enable_intr_remapping(void) { return -1; } @@ -192,6 +197,11 @@ static inline int reenable_intr_remapping(int eim) } #endif +enum { + IRQ_REMAP_XAPIC_MODE, + IRQ_REMAP_X2APIC_MODE, +}; + /* Can't use the common MSI interrupt functions * since DMAR is not a pci device */ -- cgit v1.2.3 From 318fe7df9d8456f778451b01913b5d0dc0a25854 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 23 Aug 2011 17:05:20 -0700 Subject: iommu: Move IOMMU specific code to intel-iommu.c Move the IOMMU specific routines to intel-iommu.c leaving the dmar.c to the common ACPI dmar code shared between DMA-remapping and Interrupt-remapping. Signed-off-by: Suresh Siddha Cc: yinghai@kernel.org Cc: youquan.song@intel.com Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.282401285@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar --- include/linux/dma_remapping.h | 5 ++++- include/linux/dmar.h | 17 +++++++++++++++++ 2 files changed, 21 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h index bbd8661b3473..aaa12cb8227a 100644 --- a/include/linux/dma_remapping.h +++ b/include/linux/dma_remapping.h @@ -25,9 +25,9 @@ struct intel_iommu; struct dmar_domain; struct root_entry; -extern void free_dmar_iommu(struct intel_iommu *iommu); #ifdef CONFIG_DMAR +extern void free_dmar_iommu(struct intel_iommu *iommu); extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); #else @@ -39,6 +39,9 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) { return 0; } +static inline void free_dmar_iommu(struct intel_iommu *iommu) +{ +} #endif extern int dmar_disabled; diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 2dc810e35dd0..a7992ec36570 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -237,9 +237,26 @@ struct dmar_atsr_unit { u8 include_all:1; /* include all ports */ }; +int dmar_parse_rmrr_atsr_dev(void); +extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header); +extern int dmar_parse_one_atsr(struct acpi_dmar_header *header); +extern int dmar_parse_dev_scope(void *start, void *end, int *cnt, + struct pci_dev ***devices, u16 segment); extern int intel_iommu_init(void); #else /* !CONFIG_DMAR: */ static inline int intel_iommu_init(void) { return -ENODEV; } +static inline int dmar_parse_one_rmrr(struct acpi_dmar_header *header) +{ + return 0; +} +static inline int dmar_parse_one_atsr(struct acpi_dmar_header *header) +{ + return 0; +} +static inline int dmar_parse_rmrr_atsr_dev(void) +{ + return 0; +} #endif /* CONFIG_DMAR */ #endif /* __DMAR_H__ */ -- cgit v1.2.3 From f5d1b97bcdd8ac195f48c645bffcb88bcea533e4 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 23 Aug 2011 17:05:22 -0700 Subject: iommu: Cleanup ifdefs in detect_intel_iommu() Signed-off-by: Suresh Siddha Cc: yinghai@kernel.org Cc: youquan.song@intel.com Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.386003047@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar --- include/linux/dma_remapping.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h index aaa12cb8227a..b98b61b3743e 100644 --- a/include/linux/dma_remapping.h +++ b/include/linux/dma_remapping.h @@ -30,6 +30,7 @@ struct root_entry; extern void free_dmar_iommu(struct intel_iommu *iommu); extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); +extern int dmar_disabled; #else static inline int iommu_calculate_agaw(struct intel_iommu *iommu) { @@ -42,8 +43,8 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) static inline void free_dmar_iommu(struct intel_iommu *iommu) { } +#define dmar_disabled (1) #endif -extern int dmar_disabled; #endif -- cgit v1.2.3 From d3f138106b4b40640dc667f0222fd9f137387b32 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Tue, 23 Aug 2011 17:05:25 -0700 Subject: iommu: Rename the DMAR and INTR_REMAP config options Change the CONFIG_DMAR to CONFIG_INTEL_IOMMU to be consistent with the other IOMMU options. Rename the CONFIG_INTR_REMAP to CONFIG_IRQ_REMAP to match the irq subsystem name. And define the CONFIG_DMAR_TABLE for the common ACPI DMAR routines shared by both CONFIG_INTEL_IOMMU and CONFIG_IRQ_REMAP. Signed-off-by: Suresh Siddha Cc: yinghai@kernel.org Cc: youquan.song@intel.com Cc: joerg.roedel@amd.com Cc: tony.luck@intel.com Cc: dwmw2@infradead.org Link: http://lkml.kernel.org/r/20110824001456.558630224@sbsiddha-desk.sc.intel.com Signed-off-by: Ingo Molnar --- include/linux/dma_remapping.h | 2 +- include/linux/dmar.h | 12 ++++++------ include/linux/intel-iommu.h | 6 +++--- 3 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h index b98b61b3743e..ef90cbd8e173 100644 --- a/include/linux/dma_remapping.h +++ b/include/linux/dma_remapping.h @@ -26,7 +26,7 @@ struct dmar_domain; struct root_entry; -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU extern void free_dmar_iommu(struct intel_iommu *iommu); extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); diff --git a/include/linux/dmar.h b/include/linux/dmar.h index a7992ec36570..a8b1a847c103 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -31,7 +31,7 @@ #define DMAR_X2APIC_OPT_OUT 0x2 struct intel_iommu; -#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP) +#ifdef CONFIG_DMAR_TABLE extern struct acpi_table_header *dmar_tbl; struct dmar_drhd_unit { struct list_head list; /* list of drhd units */ @@ -81,7 +81,7 @@ static inline int enable_drhd_fault_handling(void) { return -1; } -#endif /* !CONFIG_DMAR && !CONFIG_INTR_REMAP */ +#endif /* !CONFIG_DMAR_TABLE */ struct irte { union { @@ -112,7 +112,7 @@ struct irte { }; }; -#ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_IRQ_REMAP extern int intr_remapping_enabled; extern int intr_remapping_supported(void); extern int enable_intr_remapping(void); @@ -214,7 +214,7 @@ extern int dmar_set_interrupt(struct intel_iommu *iommu); extern irqreturn_t dmar_fault(int irq, void *dev_id); extern int arch_setup_dmar_msi(unsigned int irq); -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU extern int iommu_detected, no_iommu; extern struct list_head dmar_rmrr_units; struct dmar_rmrr_unit { @@ -243,7 +243,7 @@ extern int dmar_parse_one_atsr(struct acpi_dmar_header *header); extern int dmar_parse_dev_scope(void *start, void *end, int *cnt, struct pci_dev ***devices, u16 segment); extern int intel_iommu_init(void); -#else /* !CONFIG_DMAR: */ +#else /* !CONFIG_INTEL_IOMMU: */ static inline int intel_iommu_init(void) { return -ENODEV; } static inline int dmar_parse_one_rmrr(struct acpi_dmar_header *header) { @@ -257,6 +257,6 @@ static inline int dmar_parse_rmrr_atsr_dev(void) { return 0; } -#endif /* CONFIG_DMAR */ +#endif /* CONFIG_INTEL_IOMMU */ #endif /* __DMAR_H__ */ diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 9310c699a37d..235b8879af45 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -279,7 +279,7 @@ struct q_inval { int free_cnt; }; -#ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_IRQ_REMAP /* 1MB - maximum possible interrupt remapping table size */ #define INTR_REMAP_PAGE_ORDER 8 #define INTR_REMAP_TABLE_REG_SIZE 0xf @@ -318,7 +318,7 @@ struct intel_iommu { unsigned int irq; unsigned char name[13]; /* Device Name */ -#ifdef CONFIG_DMAR +#ifdef CONFIG_INTEL_IOMMU unsigned long *domain_ids; /* bitmap of domains */ struct dmar_domain **domains; /* ptr to domains */ spinlock_t lock; /* protect context, domain ids */ @@ -329,7 +329,7 @@ struct intel_iommu { struct q_inval *qi; /* Queued invalidation info */ u32 *iommu_state; /* Store iommu states between suspend and resume.*/ -#ifdef CONFIG_INTR_REMAP +#ifdef CONFIG_IRQ_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ #endif int node; -- cgit v1.2.3 From cbbc719fccdb8cbd87350a05c0d33167c9b79365 Mon Sep 17 00:00:00 2001 From: hank Date: Tue, 20 Sep 2011 13:53:39 -0700 Subject: time: Change jiffies_to_clock_t() argument type to unsigned long The parameter's origin type is long. On an i386 architecture, it can easily be larger than 0x80000000, causing this function to convert it to a sign-extended u64 type. Change the type to unsigned long so we get the correct result. Signed-off-by: hank Cc: John Stultz Cc: [ build fix ] Signed-off-by: Andrew Morton Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar --- include/linux/jiffies.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index f97672a36fa8..265e2c3cbd1c 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -303,7 +303,7 @@ extern void jiffies_to_timespec(const unsigned long jiffies, extern unsigned long timeval_to_jiffies(const struct timeval *value); extern void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value); -extern clock_t jiffies_to_clock_t(long x); +extern clock_t jiffies_to_clock_t(unsigned long x); extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); -- cgit v1.2.3 From 06315348b16178e4c006e7892ef8e5e65f49c66a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?S=C3=B8ren=20Holm?= Date: Fri, 2 Sep 2011 22:55:37 +0200 Subject: serial: Support the EFR-register of XR1715x uarts. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The EFR (Enhenced-Features-Register) is located at a different offset than the other devices supporting UART_CAP_EFR. This change add a special setup quick to set UPF_EXAR_EFR on the port. UPF_EXAR_EFR is then used to the port type to PORT_XR17D15X since it is for sure a XR17D15X uart. Signed-off-by: Søren Holm Acked-by: Alan Cox Signed-off-by: Greg Kroah-Hartman --- include/linux/serial_core.h | 4 +++- include/linux/serial_reg.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 493773e3b46d..eadf33d0abba 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -46,7 +46,8 @@ #define PORT_AR7 18 /* Texas Instruments AR7 internal UART */ #define PORT_U6_16550A 19 /* ST-Ericsson U6xxx internal UART */ #define PORT_TEGRA 20 /* NVIDIA Tegra internal UART */ -#define PORT_MAX_8250 20 /* max port ID */ +#define PORT_XR17D15X 21 /* Exar XR17D15x UART */ +#define PORT_MAX_8250 21 /* max port ID */ /* * ARM specific type numbers. These are not currently guaranteed @@ -349,6 +350,7 @@ struct uart_port { #define UPF_MAGIC_MULTIPLIER ((__force upf_t) (1 << 16)) #define UPF_CONS_FLOW ((__force upf_t) (1 << 23)) #define UPF_SHARE_IRQ ((__force upf_t) (1 << 24)) +#define UPF_EXAR_EFR ((__force upf_t) (1 << 25)) /* The exact UART type is known and should not be probed. */ #define UPF_FIXED_TYPE ((__force upf_t) (1 << 27)) #define UPF_BOOT_AUTOCONF ((__force upf_t) (1 << 28)) diff --git a/include/linux/serial_reg.h b/include/linux/serial_reg.h index c75bda37c18e..8ce70d76f836 100644 --- a/include/linux/serial_reg.h +++ b/include/linux/serial_reg.h @@ -152,6 +152,7 @@ * LCR=0xBF (or DLAB=1 for 16C660) */ #define UART_EFR 2 /* I/O: Extended Features Register */ +#define UART_XR_EFR 9 /* I/O: Extended Features Register (XR17D15x) */ #define UART_EFR_CTS 0x80 /* CTS flow control */ #define UART_EFR_RTS 0x40 /* RTS flow control */ #define UART_EFR_SCD 0x20 /* Special character detect */ -- cgit v1.2.3 From b77c3920e90e96103e4f41442999402925fe5f73 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Wed, 21 Sep 2011 16:56:54 +0200 Subject: HID: add autodetection of multitouch devices As mentioned by http://www.microsoft.com/whdc/device/input/DigitizerDrvs_touch.mspx multitouch devices are those that have the input report HID_CONTACTID. This patch detects this and unloads the generic-usb driver. Signed-off-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- include/linux/hid.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 9cf8e7ae7450..6fb743d72bfe 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -312,6 +312,7 @@ struct hid_item { #define HID_QUIRK_BADPAD 0x00000020 #define HID_QUIRK_MULTI_INPUT 0x00000040 #define HID_QUIRK_HIDINPUT_FORCE 0x00000080 +#define HID_QUIRK_MULTITOUCH 0x00000100 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000 #define HID_QUIRK_NO_INIT_REPORTS 0x20000000 -- cgit v1.2.3 From cd0ea672f58d5cfdea271c45cec0c897f2b792aa Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 26 Sep 2011 20:22:02 +0200 Subject: PM / Domains: Split device PM domain data into base and need_restore The struct pm_domain_data data type is defined in such a way that adding new fields specific to the generic PM domains code will require include/linux/pm.h to be modified. As a result, data types used only by the generic PM domains code will be defined in two headers, although they all should be defined in pm_domain.h and pm.h will need to include more headers, which won't be very nice. For this reason change the definition of struct pm_subsys_data so that its domain_data member is a pointer, which will allow struct pm_domain_data to be subclassed by various PM domains implementations. Remove the need_restore member from struct pm_domain_data and make the generic PM domains code subclass it by adding the need_restore member to the new data type. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 3 +-- include/linux/pm_domain.h | 10 ++++++++++ 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index ed10f24d5259..f25682477f08 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -424,7 +424,6 @@ struct wakeup_source; struct pm_domain_data { struct list_head list_node; struct device *dev; - bool need_restore; }; struct pm_subsys_data { @@ -434,7 +433,7 @@ struct pm_subsys_data { struct list_head clock_list; #endif #ifdef CONFIG_PM_GENERIC_DOMAINS - struct pm_domain_data domain_data; + struct pm_domain_data *domain_data; #endif }; diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 2538d906bcd1..65633e5a2bc0 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -62,6 +62,16 @@ struct gpd_link { struct list_head slave_node; }; +struct generic_pm_domain_data { + struct pm_domain_data base; + bool need_restore; +}; + +static inline struct generic_pm_domain_data *to_gpd_data(struct pm_domain_data *pdd) +{ + return container_of(pdd, struct generic_pm_domain_data, base); +} + #ifdef CONFIG_PM_GENERIC_DOMAINS extern int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev); -- cgit v1.2.3 From 3148bf041d169a083aa31bd69bedd5bfb7ffe215 Mon Sep 17 00:00:00 2001 From: Andiry Xu Date: Fri, 23 Sep 2011 14:19:47 -0700 Subject: usbcore: get BOS descriptor set This commit gets BOS(Binary Device Object Store) descriptor set for Super Speed devices and High Speed devices which support BOS descriptor. BOS descriptor is used to report additional USB device-level capabilities that are not reported via the Device descriptor. By getting BOS descriptor set, driver can check device's device-level capability such as LPM capability. Signed-off-by: Andiry Xu Signed-off-by: Sarah Sharp Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index c19f9100c307..90ab9dc1f080 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -292,6 +292,16 @@ struct usb_host_config { int extralen; }; +/* USB2.0 and USB3.0 device BOS descriptor set */ +struct usb_host_bos { + struct usb_bos_descriptor *desc; + + /* wireless cap descriptor is handled by wusb */ + struct usb_ext_cap_descriptor *ext_cap; + struct usb_ss_cap_descriptor *ss_cap; + struct usb_ss_container_id_descriptor *ss_id; +}; + int __usb_get_extra_descriptor(char *buffer, unsigned size, unsigned char type, void **ptr); #define usb_get_extra_descriptor(ifpoint, type, ptr) \ @@ -381,6 +391,7 @@ struct usb_tt; * @ep0: endpoint 0 data (default control pipe) * @dev: generic device interface * @descriptor: USB device descriptor + * @bos: USB device BOS descriptor set * @config: all of the device's configs * @actconfig: the active configuration * @ep_in: array of IN endpoints @@ -442,6 +453,7 @@ struct usb_device { struct device dev; struct usb_device_descriptor descriptor; + struct usb_host_bos *bos; struct usb_host_config *config; struct usb_host_config *actconfig; -- cgit v1.2.3 From 1ff4df56846d10379939166713bb2908e6a5ee0e Mon Sep 17 00:00:00 2001 From: Andiry Xu Date: Fri, 23 Sep 2011 14:19:48 -0700 Subject: usbcore: check device's LPM capability Check device's LPM capability by examining the bmAttibutes field of the USB2.0 Extension Descriptor. Signed-off-by: Andiry Xu Signed-off-by: Sarah Sharp Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 90ab9dc1f080..1d00d9bc5d65 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -410,6 +410,7 @@ struct usb_tt; * FIXME -- complete doc * @authenticated: Crypto authentication passed * @wusb: device is Wireless USB + * @lpm_capable: device supports LPM * @string_langid: language ID for strings * @product: iProduct string, if present (static) * @manufacturer: iManufacturer string, if present (static) @@ -472,6 +473,7 @@ struct usb_device { unsigned authorized:1; unsigned authenticated:1; unsigned wusb:1; + unsigned lpm_capable:1; int string_langid; /* static strings from the device */ -- cgit v1.2.3 From 65580b4321eb36f16ae8b5987bfa1bb948fc5112 Mon Sep 17 00:00:00 2001 From: Andiry Xu Date: Fri, 23 Sep 2011 14:19:52 -0700 Subject: xHCI: set USB2 hardware LPM If the device pass the USB2 software LPM and the host supports hardware LPM, enable hardware LPM for the device to let the host decide when to put the link into lower power state. If hardware LPM is enabled for a port and driver wants to put it into suspend, it must first disable hardware LPM, resume the port into U0, and then suspend the port. Signed-off-by: Andiry Xu Signed-off-by: Sarah Sharp Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 4 ++++ include/linux/usb/hcd.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 1d00d9bc5d65..6f49a1b39fa6 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -411,6 +411,8 @@ struct usb_tt; * @authenticated: Crypto authentication passed * @wusb: device is Wireless USB * @lpm_capable: device supports LPM + * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM + * @usb2_hw_lpm_enabled: USB2 hardware LPM enabled * @string_langid: language ID for strings * @product: iProduct string, if present (static) * @manufacturer: iManufacturer string, if present (static) @@ -474,6 +476,8 @@ struct usb_device { unsigned authenticated:1; unsigned wusb:1; unsigned lpm_capable:1; + unsigned usb2_hw_lpm_capable:1; + unsigned usb2_hw_lpm_enabled:1; int string_langid; /* static strings from the device */ diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 0097136ba45d..a4cd6c58870a 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -343,6 +343,7 @@ struct hc_driver { * address is set */ int (*update_device)(struct usb_hcd *, struct usb_device *); + int (*set_usb2_hw_lpm)(struct usb_hcd *, struct usb_device *, int); }; extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb); -- cgit v1.2.3 From 395cf9691d72173d8cdaa613c5f0255f993af94b Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Mon, 15 Aug 2011 02:02:26 +0200 Subject: doc: fix broken references There are numerous broken references to Documentation files (in other Documentation files, in comments, etc.). These broken references are caused by typo's in the references, and by renames or removals of the Documentation files. Some broken references are simply odd. Fix these broken references, sometimes by dropping the irrelevant text they were part of. Signed-off-by: Paul Bolle Signed-off-by: Jiri Kosina --- include/linux/io-mapping.h | 2 +- include/linux/isdn.h | 2 +- include/linux/platform_data/ntc_thermistor.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 8cdcc2a199ad..c81ed2ac16bd 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -27,7 +27,7 @@ * The io_mapping mechanism provides an abstraction for mapping * individual pages from an io device to the CPU in an efficient fashion. * - * See Documentation/io_mapping.txt + * See Documentation/io-mapping.txt */ #ifdef CONFIG_HAVE_ATOMIC_IOMAP diff --git a/include/linux/isdn.h b/include/linux/isdn.h index 44cd663c53b6..4ccf95d681b4 100644 --- a/include/linux/isdn.h +++ b/include/linux/isdn.h @@ -68,7 +68,7 @@ #define ISDN_NET_ENCAP_SYNCPPP 4 #define ISDN_NET_ENCAP_UIHDLC 5 #define ISDN_NET_ENCAP_CISCOHDLCK 6 /* With SLARP and keepalive */ -#define ISDN_NET_ENCAP_X25IFACE 7 /* Documentation/networking/x25-iface.txt*/ +#define ISDN_NET_ENCAP_X25IFACE 7 /* Documentation/networking/x25-iface.txt */ #define ISDN_NET_ENCAP_MAX_ENCAP ISDN_NET_ENCAP_X25IFACE /* Facility which currently uses an ISDN-channel */ diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h index abd286215279..88734e871e3a 100644 --- a/include/linux/platform_data/ntc_thermistor.h +++ b/include/linux/platform_data/ntc_thermistor.h @@ -36,7 +36,7 @@ struct ntc_thermistor_platform_data { * read_uV() * * How to setup pullup_ohm, pulldown_ohm, and connect is - * described at Documentation/hwmon/ntc + * described at Documentation/hwmon/ntc_thermistor * * pullup/down_ohm: 0 for infinite / not-connected */ -- cgit v1.2.3 From 9f26490412cf15b04ac8f44a512ba0b09e774576 Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Thu, 1 Sep 2011 11:32:18 +0800 Subject: slub: correct comments error for per cpu partial Correct comment errors, that mistake cpu partial objects number as pages number, may make reader misunderstand. Signed-off-by: Alex Shi Reviewed-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slub_def.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 4890ef79d752..a32bcfdc7834 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -82,7 +82,7 @@ struct kmem_cache { int size; /* The size of an object including meta data */ int objsize; /* The size of an object without meta data */ int offset; /* Free pointer offset. */ - int cpu_partial; /* Number of per cpu partial pages to keep around */ + int cpu_partial; /* Number of per cpu partial objects to keep around */ struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ -- cgit v1.2.3 From b3fbab0571eb09746cc0283648165ec00efc8eb2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 24 May 2011 08:31:09 -0700 Subject: rcu: Restore checks for blocking in RCU read-side critical sections Long ago, using TREE_RCU with PREEMPT would result in "scheduling while atomic" diagnostics if you blocked in an RCU read-side critical section. However, PREEMPT now implies TREE_PREEMPT_RCU, which defeats this diagnostic. This commit therefore adds a replacement diagnostic based on PROVE_RCU. Because rcu_lockdep_assert() and lockdep_rcu_dereference() are now being used for things that have nothing to do with rcu_dereference(), rename lockdep_rcu_dereference() to lockdep_rcu_suspicious() and add a third argument that is a string indicating what is suspicious. This third argument is passed in from a new third argument to rcu_lockdep_assert(). Update all calls to rcu_lockdep_assert() to add an informative third argument. Also, add a pair of rcu_lockdep_assert() calls from within rcu_note_context_switch(), one complaining if a context switch occurs in an RCU-bh read-side critical section and another complaining if a context switch occurs in an RCU-sched read-side critical section. These are present only if the PROVE_RCU kernel parameter is enabled. Finally, fix some checkpatch whitespace complaints in lockdep.c. Again, you must enable PROVE_RCU to see these new diagnostics. But you are enabling PROVE_RCU to check out new RCU uses in any case, aren't you? Signed-off-by: Paul E. McKenney --- include/linux/lockdep.h | 2 +- include/linux/rcupdate.h | 28 ++++++++++++++++++++++------ 2 files changed, 23 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index ef820a3c378b..b6a56e37284c 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -548,7 +548,7 @@ do { \ #endif #ifdef CONFIG_PROVE_RCU -extern void lockdep_rcu_dereference(const char *file, const int line); +void lockdep_rcu_suspicious(const char *file, const int line, const char *s); #endif #endif /* __LINUX_LOCKDEP_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 8f4f881a0ad8..8e7470d8b676 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -297,19 +297,31 @@ extern int rcu_my_thread_group_empty(void); /** * rcu_lockdep_assert - emit lockdep splat if specified condition not met * @c: condition to check + * @s: informative message */ -#define rcu_lockdep_assert(c) \ +#define rcu_lockdep_assert(c, s) \ do { \ static bool __warned; \ if (debug_lockdep_rcu_enabled() && !__warned && !(c)) { \ __warned = true; \ - lockdep_rcu_dereference(__FILE__, __LINE__); \ + lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) +#define rcu_sleep_check() \ + do { \ + rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), \ + "Illegal context switch in RCU-bh" \ + " read-side critical section"); \ + rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), \ + "Illegal context switch in RCU-sched"\ + " read-side critical section"); \ + } while (0) + #else /* #ifdef CONFIG_PROVE_RCU */ -#define rcu_lockdep_assert(c) do { } while (0) +#define rcu_lockdep_assert(c, s) do { } while (0) +#define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ @@ -338,14 +350,16 @@ extern int rcu_my_thread_group_empty(void); #define __rcu_dereference_check(p, c, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ - rcu_lockdep_assert(c); \ + rcu_lockdep_assert(c, "suspicious rcu_dereference_check()" \ + " usage"); \ rcu_dereference_sparse(p, space); \ smp_read_barrier_depends(); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ - rcu_lockdep_assert(c); \ + rcu_lockdep_assert(c, "suspicious rcu_dereference_protected()" \ + " usage"); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) @@ -359,7 +373,9 @@ extern int rcu_my_thread_group_empty(void); #define __rcu_dereference_index_check(p, c) \ ({ \ typeof(p) _________p1 = ACCESS_ONCE(p); \ - rcu_lockdep_assert(c); \ + rcu_lockdep_assert(c, \ + "suspicious rcu_dereference_index_check()" \ + " usage"); \ smp_read_barrier_depends(); \ (_________p1); \ }) -- cgit v1.2.3 From 990987511c200877bb20201772d5de46644151f2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 31 May 2011 21:03:55 -0700 Subject: rcu: Move rcu_head definition to types.h Take a first step towards untangling Linux kernel header files by placing the struct rcu_head definition into include/linux/types.h and including include/linux/types.h in include/linux/rcupdate.h where struct rcu_head used to be defined. The actual inclusion point for include/linux/types.h is with the rest of the #include directives rather than at the point where struct rcu_head used to be defined, as suggested by Mathieu Desnoyers. Once this is in place, then header files that need only rcu_head can include types.h rather than rcupdate.h. Signed-off-by: Paul E. McKenney Cc: Paul Gortmaker Acked-by: Mathieu Desnoyers --- include/linux/rcupdate.h | 11 +---------- include/linux/types.h | 10 ++++++++++ 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 8e7470d8b676..87bd390df73f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -33,6 +33,7 @@ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H +#include #include #include #include @@ -64,16 +65,6 @@ static inline void rcutorture_record_progress(unsigned long vernum) #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) -/** - * struct rcu_head - callback structure for use with RCU - * @next: next update requests in a list - * @func: actual update function to call after the grace period. - */ -struct rcu_head { - struct rcu_head *next; - void (*func)(struct rcu_head *head); -}; - /* Exported common interfaces */ extern void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); diff --git a/include/linux/types.h b/include/linux/types.h index 176da8c1fbb1..57a97234bec1 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -238,6 +238,16 @@ struct ustat { char f_fpack[6]; }; +/** + * struct rcu_head - callback structure for use with RCU + * @next: next update requests in a list + * @func: actual update function to call after the grace period. + */ +struct rcu_head { + struct rcu_head *next; + void (*func)(struct rcu_head *head); +}; + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ #endif /* _LINUX_TYPES_H */ -- cgit v1.2.3 From 2c42818e962e2858334bf45bfc56662b3752df34 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 26 May 2011 22:14:36 -0700 Subject: rcu: Abstract common code for RCU grace-period-wait primitives Pull the code that waits for an RCU grace period into a single function, which is then called by synchronize_rcu() and friends in the case of TREE_RCU and TREE_PREEMPT_RCU, and from rcu_barrier() and friends in the case of TINY_RCU and TINY_PREEMPT_RCU. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 130 ++++++++++++++++++++++++++--------------------- include/linux/rcutiny.h | 16 +++++- include/linux/rcutree.h | 2 + 3 files changed, 90 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 87bd390df73f..ae5327de41aa 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -66,11 +66,73 @@ static inline void rcutorture_record_progress(unsigned long vernum) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) /* Exported common interfaces */ + +#ifdef CONFIG_PREEMPT_RCU + +/** + * call_rcu() - Queue an RCU callback for invocation after a grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. However, the callback function + * might well execute concurrently with RCU read-side critical sections + * that started after call_rcu() was invoked. RCU read-side critical + * sections are delimited by rcu_read_lock() and rcu_read_unlock(), + * and may be nested. + */ +extern void call_rcu(struct rcu_head *head, + void (*func)(struct rcu_head *head)); + +#else /* #ifdef CONFIG_PREEMPT_RCU */ + +/* In classic RCU, call_rcu() is just call_rcu_sched(). */ +#define call_rcu call_rcu_sched + +#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + +/** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_bh() assumes + * that the read-side critical sections end on completion of a softirq + * handler. This means that read-side critical sections in process + * context must not be interrupted by softirqs. This interface is to be + * used when most of the read-side critical sections are in softirq context. + * RCU read-side critical sections are delimited by : + * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. + * OR + * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. + * These may be nested. + */ +extern void call_rcu_bh(struct rcu_head *head, + void (*func)(struct rcu_head *head)); + +/** + * call_rcu_sched() - Queue an RCU for invocation after sched grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_sched() assumes + * that the read-side critical sections end on enabling of preemption + * or on voluntary preemption. + * RCU read-side critical sections are delimited by : + * - rcu_read_lock_sched() and rcu_read_unlock_sched(), + * OR + * anything that disables preemption. + * These may be nested. + */ extern void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); + extern void synchronize_sched(void); -extern void rcu_barrier_bh(void); -extern void rcu_barrier_sched(void); static inline void __rcu_read_lock_bh(void) { @@ -143,6 +205,15 @@ static inline void rcu_exit_nohz(void) #endif /* #else #ifdef CONFIG_NO_HZ */ +/* + * Infrastructure to implement the synchronize_() primitives in + * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. + */ + +typedef void call_rcu_func_t(struct rcu_head *head, + void (*func)(struct rcu_head *head)); +void wait_rcu_gp(call_rcu_func_t crf); + #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) #include #elif defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU) @@ -723,61 +794,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define RCU_INIT_POINTER(p, v) \ p = (typeof(*v) __force __rcu *)(v) -/* Infrastructure to implement the synchronize_() primitives. */ - -struct rcu_synchronize { - struct rcu_head head; - struct completion completion; -}; - -extern void wakeme_after_rcu(struct rcu_head *head); - -#ifdef CONFIG_PREEMPT_RCU - -/** - * call_rcu() - Queue an RCU callback for invocation after a grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all pre-existing RCU read-side - * critical sections have completed. However, the callback function - * might well execute concurrently with RCU read-side critical sections - * that started after call_rcu() was invoked. RCU read-side critical - * sections are delimited by rcu_read_lock() and rcu_read_unlock(), - * and may be nested. - */ -extern void call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *head)); - -#else /* #ifdef CONFIG_PREEMPT_RCU */ - -/* In classic RCU, call_rcu() is just call_rcu_sched(). */ -#define call_rcu call_rcu_sched - -#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ - -/** - * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all currently executing RCU - * read-side critical sections have completed. call_rcu_bh() assumes - * that the read-side critical sections end on completion of a softirq - * handler. This means that read-side critical sections in process - * context must not be interrupted by softirqs. This interface is to be - * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. - */ -extern void call_rcu_bh(struct rcu_head *head, - void (*func)(struct rcu_head *head)); - /* * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally * by call_rcu() and rcu callback execution, and are therefore not part of the diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 52b3e0281fd0..4eab233a00cd 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -31,6 +31,16 @@ static inline void rcu_init(void) { } +static inline void rcu_barrier_bh(void) +{ + wait_rcu_gp(call_rcu_bh); +} + +static inline void rcu_barrier_sched(void) +{ + wait_rcu_gp(call_rcu_sched); +} + #ifdef CONFIG_TINY_RCU static inline void synchronize_rcu_expedited(void) @@ -45,9 +55,13 @@ static inline void rcu_barrier(void) #else /* #ifdef CONFIG_TINY_RCU */ -void rcu_barrier(void); void synchronize_rcu_expedited(void); +static inline void rcu_barrier(void) +{ + wait_rcu_gp(call_rcu); +} + #endif /* #else #ifdef CONFIG_TINY_RCU */ static inline void synchronize_rcu_bh(void) diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index e65d06634dd8..67458468f1a8 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -67,6 +67,8 @@ static inline void synchronize_rcu_bh_expedited(void) } extern void rcu_barrier(void); +extern void rcu_barrier_bh(void); +extern void rcu_barrier_sched(void); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; -- cgit v1.2.3 From 29c00b4a1d9e277786120032aa8364631820d863 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 17 Jun 2011 15:53:19 -0700 Subject: rcu: Add event-tracing for RCU callback invocation There was recently some controversy about the overhead of invoking RCU callbacks. Add TRACE_EVENT()s to obtain fine-grained timings for the start and stop of a batch of callbacks and also for each callback invoked. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 50 ------------------------------------------------ 1 file changed, 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index ae5327de41aa..dd2bc2c6a285 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -794,44 +794,6 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define RCU_INIT_POINTER(p, v) \ p = (typeof(*v) __force __rcu *)(v) -/* - * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally - * by call_rcu() and rcu callback execution, and are therefore not part of the - * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. - */ - -#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD -# define STATE_RCU_HEAD_READY 0 -# define STATE_RCU_HEAD_QUEUED 1 - -extern struct debug_obj_descr rcuhead_debug_descr; - -static inline void debug_rcu_head_queue(struct rcu_head *head) -{ - WARN_ON_ONCE((unsigned long)head & 0x3); - debug_object_activate(head, &rcuhead_debug_descr); - debug_object_active_state(head, &rcuhead_debug_descr, - STATE_RCU_HEAD_READY, - STATE_RCU_HEAD_QUEUED); -} - -static inline void debug_rcu_head_unqueue(struct rcu_head *head) -{ - debug_object_active_state(head, &rcuhead_debug_descr, - STATE_RCU_HEAD_QUEUED, - STATE_RCU_HEAD_READY); - debug_object_deactivate(head, &rcuhead_debug_descr); -} -#else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -static inline void debug_rcu_head_queue(struct rcu_head *head) -{ -} - -static inline void debug_rcu_head_unqueue(struct rcu_head *head) -{ -} -#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ - static __always_inline bool __is_kfree_rcu_offset(unsigned long offset) { return offset < 4096; @@ -850,18 +812,6 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset) call_rcu(head, (rcu_callback)offset); } -extern void kfree(const void *); - -static inline void __rcu_reclaim(struct rcu_head *head) -{ - unsigned long offset = (unsigned long)head->func; - - if (__is_kfree_rcu_offset(offset)) - kfree((void *)head - offset); - else - head->func(head); -} - /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree -- cgit v1.2.3 From 965a002b4f1a458c5dcb334ec29f48a0046faa25 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sat, 18 Jun 2011 09:55:39 -0700 Subject: rcu: Make TINY_RCU also use softirq for RCU_BOOST=n This patch #ifdefs TINY_RCU kthreads out of the kernel unless RCU_BOOST=y, thus eliminating context-switch overhead if RCU priority boosting has not been configured. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 4eab233a00cd..00b7a5e493d2 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -27,9 +27,13 @@ #include +#ifdef CONFIG_RCU_BOOST static inline void rcu_init(void) { } +#else /* #ifdef CONFIG_RCU_BOOST */ +void rcu_init(void); +#endif /* #else #ifdef CONFIG_RCU_BOOST */ static inline void rcu_barrier_bh(void) { -- cgit v1.2.3 From 22507ed9b9d587486fb4681e93a8c58837738a25 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 18 Jul 2011 16:54:51 -0700 Subject: rcu: Remove unused and redundant interfaces The rcu_dereference_bh_protected() and rcu_dereference_sched_protected() macros are synonyms for rcu_dereference_protected() and are not used anywhere in mainline. This commit therefore removes them. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index dd2bc2c6a285..caf22e84a743 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -578,26 +578,6 @@ extern int rcu_my_thread_group_empty(void); #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), (c), __rcu) -/** - * rcu_dereference_bh_protected() - fetch RCU-bh pointer when updates prevented - * @p: The pointer to read, prior to dereferencing - * @c: The conditions under which the dereference will take place - * - * This is the RCU-bh counterpart to rcu_dereference_protected(). - */ -#define rcu_dereference_bh_protected(p, c) \ - __rcu_dereference_protected((p), (c), __rcu) - -/** - * rcu_dereference_sched_protected() - fetch RCU-sched pointer when updates prevented - * @p: The pointer to read, prior to dereferencing - * @c: The conditions under which the dereference will take place - * - * This is the RCU-sched counterpart to rcu_dereference_protected(). - */ -#define rcu_dereference_sched_protected(p, c) \ - __rcu_dereference_protected((p), (c), __rcu) - /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing -- cgit v1.2.3 From fc0763f53e3ff6a6bfa66934662a3446b9ca6f16 Mon Sep 17 00:00:00 2001 From: "Shi, Alex" Date: Thu, 28 Jul 2011 14:56:12 +0800 Subject: nohz: Remove nohz_cpu_mask RCU no longer uses this global variable, nor does anyone else. This commit therefore removes this variable. This reduces memory footprint and also removes some atomic instructions and memory barriers from the dyntick-idle path. Signed-off-by: Alex Shi Signed-off-by: Paul E. McKenney --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ac2c0578e0f..6ee91e20353b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -270,7 +270,6 @@ extern void init_idle_bootup_task(struct task_struct *idle); extern int runqueue_is_locked(int cpu); -extern cpumask_var_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) extern void select_nohz_load_balancer(int stop_tick); extern int get_nohz_timer_target(void); -- cgit v1.2.3 From d322f45ceed525daa9401154590bbae3222cfefb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 31 Jul 2011 22:09:25 -0700 Subject: rcu: Make rcu_assign_pointer() unconditionally insert a memory barrier Recent changes to gcc give warning messages on rcu_assign_pointers()'s checks that allow it to determine when it is OK to omit the memory barrier. Stephen Hemminger tried a number of gcc tricks to silence this warning, but #pragmas and CPP macros do not work together in the way that would be required to make this work. However, we now have RCU_INIT_POINTER(), which already omits this memory barrier, and which therefore may be used when assigning NULL to an RCU-protected pointer that is accessible to readers. This commit therefore makes rcu_assign_pointer() unconditionally emit the memory barrier. Reported-by: Stephen Hemminger Signed-off-by: Eric Dumazet Acked-by: David S. Miller Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index caf22e84a743..d7accc5f8892 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -443,9 +443,7 @@ extern int rcu_my_thread_group_empty(void); }) #define __rcu_assign_pointer(p, v, space) \ ({ \ - if (!__builtin_constant_p(v) || \ - ((v) != NULL)) \ - smp_wmb(); \ + smp_wmb(); \ (p) = (typeof(*v) __force space *)(v); \ }) -- cgit v1.2.3 From 6846c0c54074d47927c90eab4a805115e1ae3292 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 31 Jul 2011 22:33:02 -0700 Subject: rcu: Improve rcu_assign_pointer() and RCU_INIT_POINTER() documentation The differences between rcu_assign_pointer() and RCU_INIT_POINTER() are subtle, and it is easy to use the the cheaper RCU_INIT_POINTER() when the more-expensive rcu_assign_pointer() should have been used instead. The consequences of this mistake are quite severe. This commit therefore carefully lays out the situations in which it it permissible to use RCU_INIT_POINTER(). Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 47 ++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 40 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index d7accc5f8892..af186e260c43 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -754,11 +754,18 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * any prior initialization. Returns the value assigned. * * Inserts memory barriers on architectures that require them - * (pretty much all of them other than x86), and also prevents - * the compiler from reordering the code that initializes the - * structure after the pointer assignment. More importantly, this - * call documents which pointers will be dereferenced by RCU read-side - * code. + * (which is most of them), and also prevents the compiler from + * reordering the code that initializes the structure after the pointer + * assignment. More importantly, this call documents which pointers + * will be dereferenced by RCU read-side code. + * + * In some special cases, you may use RCU_INIT_POINTER() instead + * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due + * to the fact that it does not constrain either the CPU or the compiler. + * That said, using RCU_INIT_POINTER() when you should have used + * rcu_assign_pointer() is a very bad thing that results in + * impossible-to-diagnose memory corruption. So please be careful. + * See the RCU_INIT_POINTER() comment header for details. */ #define rcu_assign_pointer(p, v) \ __rcu_assign_pointer((p), (v), __rcu) @@ -766,8 +773,34 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * - * Initialize an RCU-protected pointer in such a way to avoid RCU-lockdep - * splats. + * Initialize an RCU-protected pointer in special cases where readers + * do not need ordering constraints on the CPU or the compiler. These + * special cases are: + * + * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer -or- + * 2. The caller has taken whatever steps are required to prevent + * RCU readers from concurrently accessing this pointer -or- + * 3. The referenced data structure has already been exposed to + * readers either at compile time or via rcu_assign_pointer() -and- + * a. You have not made -any- reader-visible changes to + * this structure since then -or- + * b. It is OK for readers accessing this structure from its + * new location to see the old state of the structure. (For + * example, the changes were to statistical counters or to + * other state where exact synchronization is not required.) + * + * Failure to follow these rules governing use of RCU_INIT_POINTER() will + * result in impossible-to-diagnose memory corruption. As in the structures + * will look OK in crash dumps, but any concurrent RCU readers might + * see pre-initialized values of the referenced data structure. So + * please be very careful how you use RCU_INIT_POINTER()!!! + * + * If you are creating an RCU-protected linked structure that is accessed + * by a single external-to-structure RCU-protected pointer, then you may + * use RCU_INIT_POINTER() to initialize the internal RCU-protected + * pointers, but you must use rcu_assign_pointer() to initialize the + * external-to-structure pointer -after- you have completely initialized + * the reader-accessible portions of the linked structure. */ #define RCU_INIT_POINTER(p, v) \ p = (typeof(*v) __force __rcu *)(v) -- cgit v1.2.3 From 6206ab9bab620fc0fbbed30ce20d145b0b3d1840 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 1 Aug 2011 06:22:11 -0700 Subject: rcu: Move __rcu_read_unlock()'s barrier() within if-statement We only need to constrain the compiler if we are actually exiting the top-level RCU read-side critical section. This commit therefore moves the first barrier() cal in __rcu_read_unlock() to inside the "if" statement, thus avoiding needless register flushes for inner rcu_read_unlock() calls. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index af186e260c43..2cf4226ade7e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -134,16 +134,6 @@ extern void call_rcu_sched(struct rcu_head *head, extern void synchronize_sched(void); -static inline void __rcu_read_lock_bh(void) -{ - local_bh_disable(); -} - -static inline void __rcu_read_unlock_bh(void) -{ - local_bh_enable(); -} - #ifdef CONFIG_PREEMPT_RCU extern void __rcu_read_lock(void); @@ -686,7 +676,7 @@ static inline void rcu_read_unlock(void) */ static inline void rcu_read_lock_bh(void) { - __rcu_read_lock_bh(); + local_bh_disable(); __acquire(RCU_BH); rcu_read_acquire_bh(); } @@ -700,7 +690,7 @@ static inline void rcu_read_unlock_bh(void) { rcu_read_release_bh(); __release(RCU_BH); - __rcu_read_unlock_bh(); + local_bh_enable(); } /** -- cgit v1.2.3 From 82e78d80fc392ac7e98326bc8beeb8a679913ffd Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 4 Aug 2011 07:55:34 -0700 Subject: rcu: Simplify unboosting checks Commit 7765be (Fix RCU_BOOST race handling current->rcu_read_unlock_special) introduced a new ->rcu_boosted field in the task structure. This is redundant because the existing ->rcu_boost_mutex will be non-NULL at any time that ->rcu_boosted is nonzero. Therefore, this commit removes ->rcu_boosted and tests ->rcu_boost_mutex instead. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- include/linux/sched.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 6ee91e20353b..acca43560805 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1259,9 +1259,6 @@ struct task_struct { #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; char rcu_read_unlock_special; -#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) - int rcu_boosted; -#endif /* #if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) */ struct list_head rcu_node_entry; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TREE_PREEMPT_RCU -- cgit v1.2.3 From d178bc3a708f39cbfefc3fab37032d3f2511b4ec Mon Sep 17 00:00:00 2001 From: Serge Hallyn Date: Mon, 26 Sep 2011 10:45:18 -0500 Subject: user namespace: usb: make usb urbs user namespace aware (v2) Add to the dev_state and alloc_async structures the user namespace corresponding to the uid and euid. Pass these to kill_pid_info_as_uid(), which can then implement a proper, user-namespace-aware uid check. Changelog: Sep 20: Per Oleg's suggestion: Instead of caching and passing user namespace, uid, and euid each separately, pass a struct cred. Sep 26: Address Alan Stern's comments: don't define a struct cred at usbdev_open(), and take and put a cred at async_completed() to ensure it lasts for the duration of kill_pid_info_as_cred(). Signed-off-by: Serge Hallyn Cc: Oleg Nesterov Cc: "Eric W. Biederman" Cc: Tejun Heo Signed-off-by: Greg Kroah-Hartman --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ac2c0578e0f..57ddb5283d9f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2166,7 +2166,8 @@ extern int force_sigsegv(int, struct task_struct *); extern int force_sig_info(int, struct siginfo *, struct task_struct *); extern int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct siginfo *info, struct pid *pid); -extern int kill_pid_info_as_uid(int, struct siginfo *, struct pid *, uid_t, uid_t, u32); +extern int kill_pid_info_as_cred(int, struct siginfo *, struct pid *, + const struct cred *, u32); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern int kill_proc_info(int, struct siginfo *, pid_t); -- cgit v1.2.3 From 6eb0f5e0154facfe4f0acdb9f474cde773319efc Mon Sep 17 00:00:00 2001 From: Dimitris Papastamos Date: Thu, 29 Sep 2011 14:36:27 +0100 Subject: regmap: Implement regcache_cache_bypass helper function Ensure we've got a function so users can enable/disable the cache bypass option. Signed-off-by: Dimitris Papastamos Signed-off-by: Mark Brown --- include/linux/regmap.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 76ac255a17a5..3daac2d8dc37 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -142,5 +142,6 @@ int regmap_update_bits(struct regmap *map, unsigned int reg, int regcache_sync(struct regmap *map); void regcache_cache_only(struct regmap *map, bool enable); +void regcache_cache_bypass(struct regmap *map, bool enable); #endif -- cgit v1.2.3 From 03ca370fbf7b76d6d002380dbdc2cdc2319f9c80 Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Fri, 30 Sep 2011 22:35:12 +0200 Subject: PM / OPP: Add OPP availability change notifier. The patch enables to register notifier_block for an OPP-device in order to get notified for any changes in the availability of OPPs of the device. For example, if a new OPP is inserted or enable/disable status of an OPP is changed, the notifier is executed. This enables the usage of opp_add, opp_enable, and opp_disable to directly take effect with any connected entities such as cpufreq or devfreq. Signed-off-by: MyungJoo Ham Signed-off-by: Kyungmin Park Reviewed-by: Mike Turquette Reviewed-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/opp.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/opp.h b/include/linux/opp.h index 7020e9736fc5..87a9208f8aec 100644 --- a/include/linux/opp.h +++ b/include/linux/opp.h @@ -16,9 +16,14 @@ #include #include +#include struct opp; +enum opp_event { + OPP_EVENT_ADD, OPP_EVENT_ENABLE, OPP_EVENT_DISABLE, +}; + #if defined(CONFIG_PM_OPP) unsigned long opp_get_voltage(struct opp *opp); @@ -40,6 +45,8 @@ int opp_enable(struct device *dev, unsigned long freq); int opp_disable(struct device *dev, unsigned long freq); +struct srcu_notifier_head *opp_get_notifier(struct device *dev); + #else static inline unsigned long opp_get_voltage(struct opp *opp) { @@ -89,6 +96,11 @@ static inline int opp_disable(struct device *dev, unsigned long freq) { return 0; } + +struct srcu_notifier_head *opp_get_notifier(struct device *dev) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_PM */ #if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP) -- cgit v1.2.3 From a3c98b8b2ede1f4230f49f9af7135cd902e71e83 Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Sun, 2 Oct 2011 00:19:15 +0200 Subject: PM: Introduce devfreq: generic DVFS framework with device-specific OPPs With OPPs, a device may have multiple operable frequency and voltage sets. However, there can be multiple possible operable sets and a system will need to choose one from them. In order to reduce the power consumption (by reducing frequency and voltage) without affecting the performance too much, a Dynamic Voltage and Frequency Scaling (DVFS) scheme may be used. This patch introduces the DVFS capability to non-CPU devices with OPPs. DVFS is a techique whereby the frequency and supplied voltage of a device is adjusted on-the-fly. DVFS usually sets the frequency as low as possible with given conditions (such as QoS assurance) and adjusts voltage according to the chosen frequency in order to reduce power consumption and heat dissipation. The generic DVFS for devices, devfreq, may appear quite similar with /drivers/cpufreq. However, cpufreq does not allow to have multiple devices registered and is not suitable to have multiple heterogenous devices with different (but simple) governors. Normally, DVFS mechanism controls frequency based on the demand for the device, and then, chooses voltage based on the chosen frequency. devfreq also controls the frequency based on the governor's frequency recommendation and let OPP pick up the pair of frequency and voltage based on the recommended frequency. Then, the chosen OPP is passed to device driver's "target" callback. When PM QoS is going to be used with the devfreq device, the device driver should enable OPPs that are appropriate with the current PM QoS requests. In order to do so, the device driver may call opp_enable and opp_disable at the notifier callback of PM QoS so that PM QoS's update_target() call enables the appropriate OPPs. Note that at least one of OPPs should be enabled at any time; be careful when there is a transition. Signed-off-by: MyungJoo Ham Signed-off-by: Kyungmin Park Reviewed-by: Mike Turquette Acked-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/devfreq.h | 203 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 203 insertions(+) create mode 100644 include/linux/devfreq.h (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h new file mode 100644 index 000000000000..b3be3d3cbaa7 --- /dev/null +++ b/include/linux/devfreq.h @@ -0,0 +1,203 @@ +/* + * devfreq: Generic Dynamic Voltage and Frequency Scaling (DVFS) Framework + * for Non-CPU Devices. + * + * Copyright (C) 2011 Samsung Electronics + * MyungJoo Ham + * + * 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 __LINUX_DEVFREQ_H__ +#define __LINUX_DEVFREQ_H__ + +#include +#include +#include + +#define DEVFREQ_NAME_LEN 16 + +struct devfreq; + +/** + * struct devfreq_dev_status - Data given from devfreq user device to + * governors. Represents the performance + * statistics. + * @total_time The total time represented by this instance of + * devfreq_dev_status + * @busy_time The time that the device was working among the + * total_time. + * @current_frequency The operating frequency. + * @private_data An entry not specified by the devfreq framework. + * A device and a specific governor may have their + * own protocol with private_data. However, because + * this is governor-specific, a governor using this + * will be only compatible with devices aware of it. + */ +struct devfreq_dev_status { + /* both since the last measure */ + unsigned long total_time; + unsigned long busy_time; + unsigned long current_frequency; + void *private_date; +}; + +/** + * struct devfreq_dev_profile - Devfreq's user device profile + * @initial_freq The operating frequency when devfreq_add_device() is + * called. + * @polling_ms The polling interval in ms. 0 disables polling. + * @target The device should set its operating frequency at + * freq or lowest-upper-than-freq value. If freq is + * higher than any operable frequency, set maximum. + * Before returning, target function should set + * freq at the current frequency. + * @get_dev_status The device should provide the current performance + * status to devfreq, which is used by governors. + * @exit An optional callback that is called when devfreq + * is removing the devfreq object due to error or + * from devfreq_remove_device() call. If the user + * has registered devfreq->nb at a notifier-head, + * this is the time to unregister it. + */ +struct devfreq_dev_profile { + unsigned long initial_freq; + unsigned int polling_ms; + + int (*target)(struct device *dev, unsigned long *freq); + int (*get_dev_status)(struct device *dev, + struct devfreq_dev_status *stat); + void (*exit)(struct device *dev); +}; + +/** + * struct devfreq_governor - Devfreq policy governor + * @name Governor's name + * @get_target_freq Returns desired operating frequency for the device. + * Basically, get_target_freq will run + * devfreq_dev_profile.get_dev_status() to get the + * status of the device (load = busy_time / total_time). + * If no_central_polling is set, this callback is called + * only with update_devfreq() notified by OPP. + * @init Called when the devfreq is being attached to a device + * @exit Called when the devfreq is being removed from a + * device. Governor should stop any internal routines + * before return because related data may be + * freed after exit(). + * @no_central_polling Do not use devfreq's central polling mechanism. + * When this is set, devfreq will not call + * get_target_freq with devfreq_monitor(). However, + * devfreq will call get_target_freq with + * devfreq_update() notified by OPP framework. + * + * Note that the callbacks are called with devfreq->lock locked by devfreq. + */ +struct devfreq_governor { + const char name[DEVFREQ_NAME_LEN]; + int (*get_target_freq)(struct devfreq *this, unsigned long *freq); + int (*init)(struct devfreq *this); + void (*exit)(struct devfreq *this); + const bool no_central_polling; +}; + +/** + * struct devfreq - Device devfreq structure + * @node list node - contains the devices with devfreq that have been + * registered. + * @lock a mutex to protect accessing devfreq. + * @dev device registered by devfreq class. dev.parent is the device + * using devfreq. + * @profile device-specific devfreq profile + * @governor method how to choose frequency based on the usage. + * @nb notifier block used to notify devfreq object that it should + * reevaluate operable frequencies. Devfreq users may use + * devfreq.nb to the corresponding register notifier call chain. + * @polling_jiffies interval in jiffies. + * @previous_freq previously configured frequency value. + * @next_polling the number of remaining jiffies to poll with + * "devfreq_monitor" executions to reevaluate + * frequency/voltage of the device. Set by + * profile's polling_ms interval. + * @data Private data of the governor. The devfreq framework does not + * touch this. + * @being_removed a flag to mark that this object is being removed in + * order to prevent trying to remove the object multiple times. + * + * This structure stores the devfreq information for a give device. + * + * Note that when a governor accesses entries in struct devfreq in its + * functions except for the context of callbacks defined in struct + * devfreq_governor, the governor should protect its access with the + * struct mutex lock in struct devfreq. A governor may use this mutex + * to protect its own private data in void *data as well. + */ +struct devfreq { + struct list_head node; + + struct mutex lock; + struct device dev; + struct devfreq_dev_profile *profile; + const struct devfreq_governor *governor; + struct notifier_block nb; + + unsigned long polling_jiffies; + unsigned long previous_freq; + unsigned int next_polling; + + void *data; /* private data for governors */ + + bool being_removed; +}; + +#if defined(CONFIG_PM_DEVFREQ) +extern struct devfreq *devfreq_add_device(struct device *dev, + struct devfreq_dev_profile *profile, + const struct devfreq_governor *governor, + void *data); +extern int devfreq_remove_device(struct devfreq *devfreq); + +/* Helper functions for devfreq user device driver with OPP. */ +extern struct opp *devfreq_recommended_opp(struct device *dev, + unsigned long *freq); +extern int devfreq_register_opp_notifier(struct device *dev, + struct devfreq *devfreq); +extern int devfreq_unregister_opp_notifier(struct device *dev, + struct devfreq *devfreq); + +#else /* !CONFIG_PM_DEVFREQ */ +static struct devfreq *devfreq_add_device(struct device *dev, + struct devfreq_dev_profile *profile, + struct devfreq_governor *governor, + void *data); +{ + return NULL; +} + +static int devfreq_remove_device(struct devfreq *devfreq); +{ + return 0; +} + +static struct opp *devfreq_recommended_opp(struct device *dev, + unsigned long *freq) +{ + return -EINVAL; +} + +static int devfreq_register_opp_notifier(struct device *dev, + struct devfreq *devfreq) +{ + return -EINVAL; +} + +static int devfreq_unregister_opp_notifier(struct device *dev, + struct devfreq *devfreq) +{ + return -EINVAL; +} + +#endif /* CONFIG_PM_DEVFREQ */ + +#endif /* __LINUX_DEVFREQ_H__ */ -- cgit v1.2.3 From ce26c5bb9569d8b826f01b8620fc16d8da6821e9 Mon Sep 17 00:00:00 2001 From: MyungJoo Ham Date: Sun, 2 Oct 2011 00:19:34 +0200 Subject: PM / devfreq: Add basic governors Four cpufreq-like governors are provided as examples. powersave: use the lowest frequency possible. The user (device) should set the polling_ms as 0 because polling is useless for this governor. performance: use the highest freqeuncy possible. The user (device) should set the polling_ms as 0 because polling is useless for this governor. userspace: use the user specified frequency stored at devfreq.user_set_freq. With sysfs support in the following patch, a user may set the value with the sysfs interface. simple_ondemand: simplified version of cpufreq's ondemand governor. When a user updates OPP entries (enable/disable/add), OPP framework automatically notifies devfreq to update operating frequency accordingly. Thus, devfreq users (device drivers) do not need to update devfreq manually with OPP entry updates or set polling_ms for powersave , performance, userspace, or any other "static" governors. Note that these are given only as basic examples for governors and any devices with devfreq may implement their own governors with the drivers and use them. Signed-off-by: MyungJoo Ham Signed-off-by: Kyungmin Park Reviewed-by: Mike Turquette Acked-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki --- include/linux/devfreq.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/linux') diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index b3be3d3cbaa7..afb94583960c 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -166,6 +166,36 @@ extern int devfreq_register_opp_notifier(struct device *dev, extern int devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq); +#ifdef CONFIG_DEVFREQ_GOV_POWERSAVE +extern const struct devfreq_governor devfreq_powersave; +#endif +#ifdef CONFIG_DEVFREQ_GOV_PERFORMANCE +extern const struct devfreq_governor devfreq_performance; +#endif +#ifdef CONFIG_DEVFREQ_GOV_USERSPACE +extern const struct devfreq_governor devfreq_userspace; +#endif +#ifdef CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND +extern const struct devfreq_governor devfreq_simple_ondemand; +/** + * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq + * and devfreq_add_device + * @ upthreshold If the load is over this value, the frequency jumps. + * Specify 0 to use the default. Valid value = 0 to 100. + * @ downdifferential If the load is under upthreshold - downdifferential, + * the governor may consider slowing the frequency down. + * Specify 0 to use the default. Valid value = 0 to 100. + * downdifferential < upthreshold must hold. + * + * If the fed devfreq_simple_ondemand_data pointer is NULL to the governor, + * the governor uses the default values. + */ +struct devfreq_simple_ondemand_data { + unsigned int upthreshold; + unsigned int downdifferential; +}; +#endif + #else /* !CONFIG_PM_DEVFREQ */ static struct devfreq *devfreq_add_device(struct device *dev, struct devfreq_dev_profile *profile, @@ -198,6 +228,11 @@ static int devfreq_unregister_opp_notifier(struct device *dev, return -EINVAL; } +#define devfreq_powersave NULL +#define devfreq_performance NULL +#define devfreq_userspace NULL +#define devfreq_simple_ondemand NULL + #endif /* CONFIG_PM_DEVFREQ */ #endif /* __LINUX_DEVFREQ_H__ */ -- cgit v1.2.3 From 31d9d9b6d83030f748d013e61502fa5477e2ac0e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 23 Sep 2011 17:03:06 +0100 Subject: genirq: Add support for per-cpu dev_id interrupts The ARM GIC interrupt controller offers per CPU interrupts (PPIs), which are usually used to connect local timers to each core. Each CPU has its own private interface to the GIC, and only sees the PPIs that are directly connect to it. While these timers are separate devices and have a separate interrupt line to a core, they all use the same IRQ number. For these devices, request_irq() is not the right API as it assumes that an IRQ number is visible by a number of CPUs (through the affinity setting), but makes it very awkward to express that an IRQ number can be handled by all CPUs, and yet be a different interrupt line on each CPU, requiring a different dev_id cookie to be passed back to the handler. The *_percpu_irq() functions is designed to overcome these limitations, by providing a per-cpu dev_id vector: int request_percpu_irq(unsigned int irq, irq_handler_t handler, const char *devname, void __percpu *percpu_dev_id); void free_percpu_irq(unsigned int, void __percpu *); int setup_percpu_irq(unsigned int irq, struct irqaction *new); void remove_percpu_irq(unsigned int irq, struct irqaction *act); void enable_percpu_irq(unsigned int irq); void disable_percpu_irq(unsigned int irq); The API has a number of limitations: - no interrupt sharing - no threading - common handler across all the CPUs Once the interrupt is requested using setup_percpu_irq() or request_percpu_irq(), it must be enabled by each core that wishes its local interrupt to be delivered. Based on an initial patch by Thomas Gleixner. Signed-off-by: Marc Zyngier Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1316793788-14500-2-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 38 +++++++++++++++++++++++++++----------- include/linux/irq.h | 16 +++++++++++++++- include/linux/irqdesc.h | 1 + 3 files changed, 43 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a103732b7588..1cdfd09c8abc 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -95,6 +95,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); * @flags: flags (see IRQF_* above) * @name: name of the device * @dev_id: cookie to identify the device + * @percpu_dev_id: cookie to identify the device * @next: pointer to the next irqaction for shared interrupts * @irq: interrupt number * @dir: pointer to the proc/irq/NN/name entry @@ -104,17 +105,18 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); * @thread_mask: bitmask for keeping track of @thread activity */ struct irqaction { - irq_handler_t handler; - unsigned long flags; - void *dev_id; - struct irqaction *next; - int irq; - irq_handler_t thread_fn; - struct task_struct *thread; - unsigned long thread_flags; - unsigned long thread_mask; - const char *name; - struct proc_dir_entry *dir; + irq_handler_t handler; + unsigned long flags; + void *dev_id; + void __percpu *percpu_dev_id; + struct irqaction *next; + int irq; + irq_handler_t thread_fn; + struct task_struct *thread; + unsigned long thread_flags; + unsigned long thread_mask; + const char *name; + struct proc_dir_entry *dir; } ____cacheline_internodealigned_in_smp; extern irqreturn_t no_action(int cpl, void *dev_id); @@ -136,6 +138,10 @@ extern int __must_check request_any_context_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev_id); +extern int __must_check +request_percpu_irq(unsigned int irq, irq_handler_t handler, + const char *devname, void __percpu *percpu_dev_id); + extern void exit_irq_thread(void); #else @@ -164,10 +170,18 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler, return request_irq(irq, handler, flags, name, dev_id); } +static inline int __must_check +request_percpu_irq(unsigned int irq, irq_handler_t handler, + const char *devname, void __percpu *percpu_dev_id) +{ + return request_irq(irq, handler, 0, devname, percpu_dev_id); +} + static inline void exit_irq_thread(void) { } #endif extern void free_irq(unsigned int, void *); +extern void free_percpu_irq(unsigned int, void __percpu *); struct device; @@ -207,7 +221,9 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); extern void disable_irq_nosync(unsigned int irq); extern void disable_irq(unsigned int irq); +extern void disable_percpu_irq(unsigned int irq); extern void enable_irq(unsigned int irq); +extern void enable_percpu_irq(unsigned int irq); /* The following three functions are for the core kernel use only. */ #ifdef CONFIG_GENERIC_HARDIRQS diff --git a/include/linux/irq.h b/include/linux/irq.h index 73e31abeba1c..59e49c80cc2c 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -66,6 +66,7 @@ typedef void (*irq_preflow_handler_t)(struct irq_data *data); * IRQ_NO_BALANCING - Interrupt cannot be balanced (affinity set) * IRQ_MOVE_PCNTXT - Interrupt can be migrated from process context * IRQ_NESTED_TRHEAD - Interrupt nests into another thread + * IRQ_PER_CPU_DEVID - Dev_id is a per-cpu variable */ enum { IRQ_TYPE_NONE = 0x00000000, @@ -88,12 +89,13 @@ enum { IRQ_MOVE_PCNTXT = (1 << 14), IRQ_NESTED_THREAD = (1 << 15), IRQ_NOTHREAD = (1 << 16), + IRQ_PER_CPU_DEVID = (1 << 17), }; #define IRQF_MODIFY_MASK \ (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ - IRQ_PER_CPU | IRQ_NESTED_THREAD) + IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID) #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) @@ -367,6 +369,8 @@ enum { struct irqaction; extern int setup_irq(unsigned int irq, struct irqaction *new); extern void remove_irq(unsigned int irq, struct irqaction *act); +extern int setup_percpu_irq(unsigned int irq, struct irqaction *new); +extern void remove_percpu_irq(unsigned int irq, struct irqaction *act); extern void irq_cpu_online(void); extern void irq_cpu_offline(void); @@ -394,6 +398,7 @@ extern void handle_edge_irq(unsigned int irq, struct irq_desc *desc); extern void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc); extern void handle_simple_irq(unsigned int irq, struct irq_desc *desc); extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc); +extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc); extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); @@ -422,6 +427,8 @@ static inline void irq_set_chip_and_handler(unsigned int irq, struct irq_chip *c irq_set_chip_and_handler_name(irq, chip, handle, NULL); } +extern int irq_set_percpu_devid(unsigned int irq); + extern void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, const char *name); @@ -483,6 +490,13 @@ static inline void irq_set_nested_thread(unsigned int irq, bool nest) irq_clear_status_flags(irq, IRQ_NESTED_THREAD); } +static inline void irq_set_percpu_devid_flags(unsigned int irq) +{ + irq_set_status_flags(irq, + IRQ_NOAUTOEN | IRQ_PER_CPU | IRQ_NOTHREAD | + IRQ_NOPROBE | IRQ_PER_CPU_DEVID); +} + /* Handle dynamic irq creation and destruction */ extern unsigned int create_irq_nr(unsigned int irq_want, int node); extern int create_irq(void); diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 150134ac709a..6b69c2c9dff1 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -53,6 +53,7 @@ struct irq_desc { unsigned long last_unhandled; /* Aging timer for unhandled count */ unsigned int irqs_unhandled; raw_spinlock_t lock; + struct cpumask *percpu_enabled; #ifdef CONFIG_SMP const struct cpumask *affinity_hint; struct irq_affinity_notify *affinity_notify; -- cgit v1.2.3 From 1e7c5fd29487ee88cb3abac945bafa60ae026146 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 30 Sep 2011 10:48:47 +0100 Subject: genirq: percpu: allow interrupt type to be set at enable time As request_percpu_irq() doesn't allow for a percpu interrupt to have its type configured (it is generally impossible to configure it on all CPUs at once), add a 'type' argument to enable_percpu_irq(). This allows some low-level, board specific init code to be switched to a generic API. [ tglx: Added WARN_ON argument ] Signed-off-by: Marc Zyngier Cc: Abhijeet Dharmapurikar Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 1cdfd09c8abc..664544ff77d5 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -223,7 +223,7 @@ extern void disable_irq_nosync(unsigned int irq); extern void disable_irq(unsigned int irq); extern void disable_percpu_irq(unsigned int irq); extern void enable_irq(unsigned int irq); -extern void enable_percpu_irq(unsigned int irq); +extern void enable_percpu_irq(unsigned int irq, unsigned int type); /* The following three functions are for the core kernel use only. */ #ifdef CONFIG_GENERIC_HARDIRQS -- cgit v1.2.3 From 1230db8e1543c0471dd165727d34647ab098cc1e Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Sep 2011 14:00:42 +0800 Subject: llist: Make some llist functions inline Because llist code will be used in performance critical scheduler code path, make llist_add() and llist_del_all() inline to avoid function calling overhead and related 'glue' overhead. Signed-off-by: Huang Ying Acked-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1315461646-1379-2-git-send-email-ying.huang@intel.com Signed-off-by: Ingo Molnar --- include/linux/llist.h | 64 ++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 58 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index aa0c8b5b3cd0..3eccdfd66096 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -37,8 +37,28 @@ * architectures that don't have NMI-safe cmpxchg implementation, the * list can NOT be used in NMI handler. So code uses the list in NMI * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. + * + * Copyright 2010,2011 Intel Corp. + * Author: Huang Ying + * + * 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, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ +#include +#include +#include + struct llist_head { struct llist_node *first; }; @@ -113,14 +133,46 @@ static inline void init_llist_head(struct llist_head *list) * test whether the list is empty without deleting something from the * list. */ -static inline int llist_empty(const struct llist_head *head) +static inline bool llist_empty(const struct llist_head *head) { return ACCESS_ONCE(head->first) == NULL; } -void llist_add(struct llist_node *new, struct llist_head *head); -void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, - struct llist_head *head); -struct llist_node *llist_del_first(struct llist_head *head); -struct llist_node *llist_del_all(struct llist_head *head); +/** + * llist_add - add a new entry + * @new: new entry to be added + * @head: the head for your lock-less list + */ +static inline void llist_add(struct llist_node *new, struct llist_head *head) +{ + struct llist_node *entry, *old_entry; + +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + BUG_ON(in_nmi()); +#endif + + entry = head->first; + do { + old_entry = entry; + new->next = entry; + cpu_relax(); + } while ((entry = cmpxchg(&head->first, old_entry, new)) != old_entry); +} + +/** + * llist_del_all - delete all entries from lock-less list + * @head: the head of lock-less list to delete all entries + * + * If list is empty, return NULL, otherwise, delete all entries and + * return the pointer to the first entry. The order of entries + * deleted is from the newest to the oldest added one. + */ +static inline struct llist_node *llist_del_all(struct llist_head *head) +{ +#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG + BUG_ON(in_nmi()); +#endif + + return xchg(&head->first, NULL); +} #endif /* LLIST_H */ -- cgit v1.2.3 From 2c30245c65e8ebc3080b75ce65572ab8140bad0b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 4 Oct 2011 12:43:11 +0200 Subject: llist: Remove the platform-dependent NMI checks Remove the nmi() checks spread around the code. in_nmi() is not available on every architecture and it's a pretty obscure and ugly check in any case. Cc: Huang Ying Cc: Mathieu Desnoyers Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1315461646-1379-3-git-send-email-ying.huang@intel.com Signed-off-by: Ingo Molnar --- include/linux/llist.h | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index 3eccdfd66096..65fca1cbf514 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -35,8 +35,8 @@ * * The basic atomic operation of this list is cmpxchg on long. On * architectures that don't have NMI-safe cmpxchg implementation, the - * list can NOT be used in NMI handler. So code uses the list in NMI - * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. + * list can NOT be used in NMI handlers. So code that uses the list in + * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * Copyright 2010,2011 Intel Corp. * Author: Huang Ying @@ -147,10 +147,6 @@ static inline void llist_add(struct llist_node *new, struct llist_head *head) { struct llist_node *entry, *old_entry; -#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG - BUG_ON(in_nmi()); -#endif - entry = head->first; do { old_entry = entry; @@ -169,10 +165,6 @@ static inline void llist_add(struct llist_node *new, struct llist_head *head) */ static inline struct llist_node *llist_del_all(struct llist_head *head) { -#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG - BUG_ON(in_nmi()); -#endif - return xchg(&head->first, NULL); } #endif /* LLIST_H */ -- cgit v1.2.3 From a3127336b71f6833d1483c856dce91fe558dc3a9 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Sep 2011 14:00:44 +0800 Subject: llist: Move cpu_relax() to after the cmpxchg() If in llist_add()/etc. functions the first cmpxchg() call succeeds, it is not necessary to use cpu_relax() before the cmpxchg(). So cpu_relax() in a busy loop involving cmpxchg() should go after cmpxchg() instead of before that. This patch fixes this for all involved llist functions. Signed-off-by: Huang Ying Acked-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1315461646-1379-4-git-send-email-ying.huang@intel.com Signed-off-by: Ingo Molnar --- include/linux/llist.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index 65fca1cbf514..ca91875286bf 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -148,11 +148,14 @@ static inline void llist_add(struct llist_node *new, struct llist_head *head) struct llist_node *entry, *old_entry; entry = head->first; - do { + for (;;) { old_entry = entry; new->next = entry; + entry = cmpxchg(&head->first, old_entry, new); + if (entry == old_entry) + break; cpu_relax(); - } while ((entry = cmpxchg(&head->first, old_entry, new)) != old_entry); + } } /** -- cgit v1.2.3 From 781f7fd916fc77a862e20063ed3aeedf173234f9 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Sep 2011 14:00:45 +0800 Subject: llist: Return whether list is empty before adding in llist_add() Extend the llist_add*() functions to return a success indicator, this allows us in the scheduler code to send an IPI if the queue was empty. ( There's no effect on existing users, because the list_add_xxx() functions are inline, thus this will be optimized out by the compiler if not used by callers. ) Signed-off-by: Huang Ying Cc: Mathieu Desnoyers Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1315461646-1379-5-git-send-email-ying.huang@intel.com Signed-off-by: Ingo Molnar --- include/linux/llist.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index ca91875286bf..27bbdf5ddf82 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -142,8 +142,10 @@ static inline bool llist_empty(const struct llist_head *head) * llist_add - add a new entry * @new: new entry to be added * @head: the head for your lock-less list + * + * Return whether list is empty before adding. */ -static inline void llist_add(struct llist_node *new, struct llist_head *head) +static inline bool llist_add(struct llist_node *new, struct llist_head *head) { struct llist_node *entry, *old_entry; @@ -156,6 +158,8 @@ static inline void llist_add(struct llist_node *new, struct llist_head *head) break; cpu_relax(); } + + return old_entry == NULL; } /** -- cgit v1.2.3 From 38aaf8090d34b623b7919d8c933f6e938c9bf44b Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Thu, 8 Sep 2011 14:00:46 +0800 Subject: irq_work: Use llist in the struct irq_work logic Use llist in irq_work instead of the lock-less linked list implementation in irq_work to avoid the code duplication. Signed-off-by: Huang Ying Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1315461646-1379-6-git-send-email-ying.huang@intel.com Signed-off-by: Ingo Molnar --- include/linux/irq_work.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 4fa09d4d0b71..6a9e8f5399e2 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -1,20 +1,23 @@ #ifndef _LINUX_IRQ_WORK_H #define _LINUX_IRQ_WORK_H +#include + struct irq_work { - struct irq_work *next; + unsigned long flags; + struct llist_node llnode; void (*func)(struct irq_work *); }; static inline -void init_irq_work(struct irq_work *entry, void (*func)(struct irq_work *)) +void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) { - entry->next = NULL; - entry->func = func; + work->flags = 0; + work->func = func; } -bool irq_work_queue(struct irq_work *entry); +bool irq_work_queue(struct irq_work *work); void irq_work_run(void); -void irq_work_sync(struct irq_work *entry); +void irq_work_sync(struct irq_work *work); #endif /* _LINUX_IRQ_WORK_H */ -- cgit v1.2.3 From 924f8f5af31423529cc3940cb2ae9fee736b7517 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 12 Sep 2011 13:12:28 +0200 Subject: llist: Add llist_next() So we don't have to expose the struct list_node member. Cc: Huang Ying Cc: Andrew Morton Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1315836348.26517.41.camel@twins Signed-off-by: Ingo Molnar --- include/linux/llist.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index 27bbdf5ddf82..e2e96d04ee48 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -138,6 +138,11 @@ static inline bool llist_empty(const struct llist_head *head) return ACCESS_ONCE(head->first) == NULL; } +static inline struct llist_node *llist_next(struct llist_node *node) +{ + return node->next; +} + /** * llist_add - add a new entry * @new: new entry to be added -- cgit v1.2.3 From fa14ff4accfb24e59d2473f3d864d6648d80563b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 12 Sep 2011 13:06:17 +0200 Subject: sched: Convert to struct llist Use the generic llist primitives. We had a private lockless list implementation in the scheduler in the wake-list code, now that we have a generic llist implementation that provides all required operations, switch to it. This patch is not expected to change any behavior. Signed-off-by: Peter Zijlstra Cc: Huang Ying Cc: Andrew Morton Link: http://lkml.kernel.org/r/1315836353.26517.42.camel@twins Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 9fda2888a6ab..fc3e8911818a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -90,6 +90,7 @@ struct sched_param { #include #include #include +#include #include @@ -1225,7 +1226,7 @@ struct task_struct { unsigned int ptrace; #ifdef CONFIG_SMP - struct task_struct *wake_entry; + struct llist_node wake_entry; int on_cpu; #endif int on_rq; -- cgit v1.2.3 From f0f1d32f931b705c4ee5dd374074d34edf3eae14 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 12 Sep 2011 15:50:49 +0200 Subject: llist: Remove cpu_relax() usage in cmpxchg loops Initial benchmarks show they're a net loss: $ for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i; done $ echo 4096 32000 64 128 > /proc/sys/kernel/sem $ ./sembench -t 2048 -w 1900 -o 0 Pre: run time 30 seconds 778936 worker burns per second run time 30 seconds 912190 worker burns per second run time 30 seconds 817506 worker burns per second run time 30 seconds 830870 worker burns per second run time 30 seconds 845056 worker burns per second Post: run time 30 seconds 905920 worker burns per second run time 30 seconds 849046 worker burns per second run time 30 seconds 886286 worker burns per second run time 30 seconds 822320 worker burns per second run time 30 seconds 900283 worker burns per second So about 4% faster. (!) cpu_relax() stalls the pipeline, therefore, when used in a tight loop it has the following benefits: - allows SMT siblings to have a go; - reduces pressure on the CPU interconnect. However, cmpxchg loops are unfair and thus have unbounded completion time, therefore we should avoid getting in such heavily contended situations where the above benefits make any difference. A typical cmpxchg loop should not go round more than a handfull of times at worst, therefore adding extra delays just slows things down. Since the llist primitives are new, there aren't any bad users yet, and we should avoid growing them. Heavily contended sites should generally be better off using the ticket locks for serialization since they provide bounded completion times (fifo-fair over the cpus). Signed-off-by: Peter Zijlstra Cc: Huang Ying Cc: Andrew Morton Link: http://lkml.kernel.org/r/1315836358.26517.43.camel@twins Signed-off-by: Ingo Molnar --- include/linux/llist.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index e2e96d04ee48..837fb4ae66fb 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -161,7 +161,6 @@ static inline bool llist_add(struct llist_node *new, struct llist_head *head) entry = cmpxchg(&head->first, old_entry, new); if (entry == old_entry) break; - cpu_relax(); } return old_entry == NULL; -- cgit v1.2.3 From 1a9a91525d806f2b3bd8b57b963755a96fd36ce2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 29 Sep 2011 22:29:44 +0200 Subject: PM / QoS: Add function dev_pm_qos_read_value() (v3) To read the current PM QoS value for a given device we need to make sure that the device's power.constraints object won't be removed while we're doing that. For this reason, put the operation under dev->power.lock and acquire the lock around the initialization and removal of power.constraints. Moreover, since we're using the value of power.constraints to determine whether or not the object is present, the power.constraints_state field isn't necessary any more and may be removed. However, dev_pm_qos_add_request() needs to check if the device is being removed from the system before allocating a new PM QoS constraints object for it, so make it use the power.power_state field of struct device for this purpose. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 10 ++-------- include/linux/pm_qos.h | 12 ++++++++++-- 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index d78187e9ca99..62a876ec4d4e 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -326,6 +326,7 @@ extern struct dev_pm_ops generic_subsys_pm_ops; * requested by a driver. */ +#define PM_EVENT_INVALID (-1) #define PM_EVENT_ON 0x0000 #define PM_EVENT_FREEZE 0x0001 #define PM_EVENT_SUSPEND 0x0002 @@ -346,6 +347,7 @@ extern struct dev_pm_ops generic_subsys_pm_ops; #define PM_EVENT_AUTO_SUSPEND (PM_EVENT_AUTO | PM_EVENT_SUSPEND) #define PM_EVENT_AUTO_RESUME (PM_EVENT_AUTO | PM_EVENT_RESUME) +#define PMSG_INVALID ((struct pm_message){ .event = PM_EVENT_INVALID, }) #define PMSG_ON ((struct pm_message){ .event = PM_EVENT_ON, }) #define PMSG_FREEZE ((struct pm_message){ .event = PM_EVENT_FREEZE, }) #define PMSG_QUIESCE ((struct pm_message){ .event = PM_EVENT_QUIESCE, }) @@ -419,13 +421,6 @@ enum rpm_request { RPM_REQ_RESUME, }; -/* Per-device PM QoS constraints data struct state */ -enum dev_pm_qos_state { - DEV_PM_QOS_NO_DEVICE, /* No device present */ - DEV_PM_QOS_DEVICE_PRESENT, /* Device present, data not allocated */ - DEV_PM_QOS_ALLOCATED, /* Device present, data allocated */ -}; - struct wakeup_source; struct pm_domain_data { @@ -488,7 +483,6 @@ struct dev_pm_info { #endif struct pm_subsys_data *subsys_data; /* Owned by the subsystem. */ struct pm_qos_constraints *constraints; - enum dev_pm_qos_state constraints_state; }; extern void update_pm_runtime_accounting(struct device *dev); diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index ca7bd3f98cb4..83b0ea302a80 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -7,6 +7,7 @@ #include #include #include +#include #define PM_QOS_RESERVED 0 #define PM_QOS_CPU_DMA_LATENCY 1 @@ -77,6 +78,7 @@ int pm_qos_remove_notifier(int pm_qos_class, struct notifier_block *notifier); int pm_qos_request_active(struct pm_qos_request *req); s32 pm_qos_read_value(struct pm_qos_constraints *c); +s32 dev_pm_qos_read_value(struct device *dev); int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, s32 value); int dev_pm_qos_update_request(struct dev_pm_qos_request *req, s32 new_value); @@ -117,6 +119,8 @@ static inline int pm_qos_request_active(struct pm_qos_request *req) static inline s32 pm_qos_read_value(struct pm_qos_constraints *c) { return 0; } +static inline s32 dev_pm_qos_read_value(struct device *dev) + { return 0; } static inline int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, s32 value) @@ -139,9 +143,13 @@ static inline int dev_pm_qos_remove_global_notifier( struct notifier_block *notifier) { return 0; } static inline void dev_pm_qos_constraints_init(struct device *dev) - { return; } +{ + dev->power.power_state = PMSG_ON; +} static inline void dev_pm_qos_constraints_destroy(struct device *dev) - { return; } +{ + dev->power.power_state = PMSG_INVALID; +} #endif #endif -- cgit v1.2.3 From a1330228f9eec7e355d41f45c17e1297d681f40d Mon Sep 17 00:00:00 2001 From: Jamie Iles Date: Mon, 25 Jul 2011 16:34:37 +0100 Subject: dw_apb_timer: constify clocksource name The clocksource name should be const for correctness. Cc: John Stultz Signed-off-by: Jamie Iles Signed-off-by: John Stultz --- include/linux/dw_apb_timer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h index 49638ea3b776..07261d52a6df 100644 --- a/include/linux/dw_apb_timer.h +++ b/include/linux/dw_apb_timer.h @@ -46,7 +46,7 @@ struct dw_apb_clock_event_device * dw_apb_clockevent_init(int cpu, const char *name, unsigned rating, void __iomem *base, int irq, unsigned long freq); struct dw_apb_clocksource * -dw_apb_clocksource_init(unsigned rating, char *name, void __iomem *base, +dw_apb_clocksource_init(unsigned rating, const char *name, void __iomem *base, unsigned long freq); void dw_apb_clocksource_register(struct dw_apb_clocksource *dw_cs); void dw_apb_clocksource_start(struct dw_apb_clocksource *dw_cs); -- cgit v1.2.3 From a240f76165e6255384d4bdb8139895fac7988799 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Wed, 5 Oct 2011 14:01:16 +0200 Subject: perf, core: Introduce attrs to count in either host or guest mode The two new attributes exclude_guest and exclude_host can bes used by user-space to tell the kernel to setup performance counter to either only count while the CPU is in guest or in host mode. An additional check is also introduced to make sure user-space does not try to exclude guest and host mode from counting. Signed-off-by: Joerg Roedel Signed-off-by: Gleb Natapov Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1317816084-18026-2-git-send-email-gleb@redhat.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c816075c01ce..1e9ebe5e0091 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -220,7 +220,10 @@ struct perf_event_attr { mmap_data : 1, /* non-exec mmap data */ sample_id_all : 1, /* sample_type all events */ - __reserved_1 : 45; + exclude_host : 1, /* don't count in host */ + exclude_guest : 1, /* don't count in guest */ + + __reserved_1 : 43; union { __u32 wakeup_events; /* wakeup every n events */ -- cgit v1.2.3 From 276532ba9666b36974cbe16f303fc8be99c9da17 Mon Sep 17 00:00:00 2001 From: Harro Haan Date: Mon, 10 Oct 2011 14:38:27 +0200 Subject: USB: fix ehci alignment error The Kirkwood gave an unaligned memory access error on line 742 of drivers/usb/host/echi-hcd.c: "ehci->last_periodic_enable = ktime_get_real();" Signed-off-by: Harro Haan Cc: stable Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/hcd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index a4cd6c58870a..03354d557b79 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -178,7 +178,7 @@ struct usb_hcd { * this structure. */ unsigned long hcd_priv[0] - __attribute__ ((aligned(sizeof(unsigned long)))); + __attribute__ ((aligned(sizeof(s64)))); }; /* 2.4 does this a bit differently ... */ -- cgit v1.2.3 From 46a971913611a23478283931460a95be962ce329 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 4 Oct 2011 12:29:52 -0700 Subject: Staging: hv: move hyperv code out of staging directory After many years wandering the desert, it is finally time for the Microsoft HyperV code to move out of the staging directory. Or at least the core hyperv bus code, and the utility driver, the rest still have some review to get through by the various subsystem maintainers. Signed-off-by: Greg Kroah-Hartman Signed-off-by: K. Y. Srinivasan --- include/linux/hyperv.h | 969 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 969 insertions(+) create mode 100644 include/linux/hyperv.h (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h new file mode 100644 index 000000000000..edaa9e2f58ec --- /dev/null +++ b/include/linux/hyperv.h @@ -0,0 +1,969 @@ +/* + * + * Copyright (c) 2011, Microsoft Corporation. + * + * 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, write to the Free Software Foundation, Inc., 59 Temple + * Place - Suite 330, Boston, MA 02111-1307 USA. + * + * Authors: + * Haiyang Zhang + * Hank Janssen + * K. Y. Srinivasan + * + */ + +#ifndef _HYPERV_H +#define _HYPERV_H + +#include +#include +#include +#include +#include +#include +#include +#include + + +#include + + +#define MAX_PAGE_BUFFER_COUNT 16 +#define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ + +#pragma pack(push, 1) + +/* Single-page buffer */ +struct hv_page_buffer { + u32 len; + u32 offset; + u64 pfn; +}; + +/* Multiple-page buffer */ +struct hv_multipage_buffer { + /* Length and Offset determines the # of pfns in the array */ + u32 len; + u32 offset; + u64 pfn_array[MAX_MULTIPAGE_BUFFER_COUNT]; +}; + +/* 0x18 includes the proprietary packet header */ +#define MAX_PAGE_BUFFER_PACKET (0x18 + \ + (sizeof(struct hv_page_buffer) * \ + MAX_PAGE_BUFFER_COUNT)) +#define MAX_MULTIPAGE_BUFFER_PACKET (0x18 + \ + sizeof(struct hv_multipage_buffer)) + + +#pragma pack(pop) + +struct hv_ring_buffer { + /* Offset in bytes from the start of ring data below */ + u32 write_index; + + /* Offset in bytes from the start of ring data below */ + u32 read_index; + + u32 interrupt_mask; + + /* Pad it to PAGE_SIZE so that data starts on page boundary */ + u8 reserved[4084]; + + /* NOTE: + * The interrupt_mask field is used only for channels but since our + * vmbus connection also uses this data structure and its data starts + * here, we commented out this field. + */ + + /* + * Ring data starts here + RingDataStartOffset + * !!! DO NOT place any fields below this !!! + */ + u8 buffer[0]; +} __packed; + +struct hv_ring_buffer_info { + struct hv_ring_buffer *ring_buffer; + u32 ring_size; /* Include the shared header */ + spinlock_t ring_lock; + + u32 ring_datasize; /* < ring_size */ + u32 ring_data_startoffset; +}; + +struct hv_ring_buffer_debug_info { + u32 current_interrupt_mask; + u32 current_read_index; + u32 current_write_index; + u32 bytes_avail_toread; + u32 bytes_avail_towrite; +}; + +/* + * We use the same version numbering for all Hyper-V modules. + * + * Definition of versioning is as follows; + * + * Major Number Changes for these scenarios; + * 1. When a new version of Windows Hyper-V + * is released. + * 2. A Major change has occurred in the + * Linux IC's. + * (For example the merge for the first time + * into the kernel) Every time the Major Number + * changes, the Revision number is reset to 0. + * Minor Number Changes when new functionality is added + * to the Linux IC's that is not a bug fix. + * + * 3.1 - Added completed hv_utils driver. Shutdown/Heartbeat/Timesync + */ +#define HV_DRV_VERSION "3.1" + + +/* + * A revision number of vmbus that is used for ensuring both ends on a + * partition are using compatible versions. + */ +#define VMBUS_REVISION_NUMBER 13 + +/* Make maximum size of pipe payload of 16K */ +#define MAX_PIPE_DATA_PAYLOAD (sizeof(u8) * 16384) + +/* Define PipeMode values. */ +#define VMBUS_PIPE_TYPE_BYTE 0x00000000 +#define VMBUS_PIPE_TYPE_MESSAGE 0x00000004 + +/* The size of the user defined data buffer for non-pipe offers. */ +#define MAX_USER_DEFINED_BYTES 120 + +/* The size of the user defined data buffer for pipe offers. */ +#define MAX_PIPE_USER_DEFINED_BYTES 116 + +/* + * At the center of the Channel Management library is the Channel Offer. This + * struct contains the fundamental information about an offer. + */ +struct vmbus_channel_offer { + uuid_le if_type; + uuid_le if_instance; + u64 int_latency; /* in 100ns units */ + u32 if_revision; + u32 server_ctx_size; /* in bytes */ + u16 chn_flags; + u16 mmio_megabytes; /* in bytes * 1024 * 1024 */ + + union { + /* Non-pipes: The user has MAX_USER_DEFINED_BYTES bytes. */ + struct { + unsigned char user_def[MAX_USER_DEFINED_BYTES]; + } std; + + /* + * Pipes: + * The following sructure is an integrated pipe protocol, which + * is implemented on top of standard user-defined data. Pipe + * clients have MAX_PIPE_USER_DEFINED_BYTES left for their own + * use. + */ + struct { + u32 pipe_mode; + unsigned char user_def[MAX_PIPE_USER_DEFINED_BYTES]; + } pipe; + } u; + u32 padding; +} __packed; + +/* Server Flags */ +#define VMBUS_CHANNEL_ENUMERATE_DEVICE_INTERFACE 1 +#define VMBUS_CHANNEL_SERVER_SUPPORTS_TRANSFER_PAGES 2 +#define VMBUS_CHANNEL_SERVER_SUPPORTS_GPADLS 4 +#define VMBUS_CHANNEL_NAMED_PIPE_MODE 0x10 +#define VMBUS_CHANNEL_LOOPBACK_OFFER 0x100 +#define VMBUS_CHANNEL_PARENT_OFFER 0x200 +#define VMBUS_CHANNEL_REQUEST_MONITORED_NOTIFICATION 0x400 + +struct vmpacket_descriptor { + u16 type; + u16 offset8; + u16 len8; + u16 flags; + u64 trans_id; +} __packed; + +struct vmpacket_header { + u32 prev_pkt_start_offset; + struct vmpacket_descriptor descriptor; +} __packed; + +struct vmtransfer_page_range { + u32 byte_count; + u32 byte_offset; +} __packed; + +struct vmtransfer_page_packet_header { + struct vmpacket_descriptor d; + u16 xfer_pageset_id; + bool sender_owns_set; + u8 reserved; + u32 range_cnt; + struct vmtransfer_page_range ranges[1]; +} __packed; + +struct vmgpadl_packet_header { + struct vmpacket_descriptor d; + u32 gpadl; + u32 reserved; +} __packed; + +struct vmadd_remove_transfer_page_set { + struct vmpacket_descriptor d; + u32 gpadl; + u16 xfer_pageset_id; + u16 reserved; +} __packed; + +/* + * This structure defines a range in guest physical space that can be made to + * look virtually contiguous. + */ +struct gpa_range { + u32 byte_count; + u32 byte_offset; + u64 pfn_array[0]; +}; + +/* + * This is the format for an Establish Gpadl packet, which contains a handle by + * which this GPADL will be known and a set of GPA ranges associated with it. + * This can be converted to a MDL by the guest OS. If there are multiple GPA + * ranges, then the resulting MDL will be "chained," representing multiple VA + * ranges. + */ +struct vmestablish_gpadl { + struct vmpacket_descriptor d; + u32 gpadl; + u32 range_cnt; + struct gpa_range range[1]; +} __packed; + +/* + * This is the format for a Teardown Gpadl packet, which indicates that the + * GPADL handle in the Establish Gpadl packet will never be referenced again. + */ +struct vmteardown_gpadl { + struct vmpacket_descriptor d; + u32 gpadl; + u32 reserved; /* for alignment to a 8-byte boundary */ +} __packed; + +/* + * This is the format for a GPA-Direct packet, which contains a set of GPA + * ranges, in addition to commands and/or data. + */ +struct vmdata_gpa_direct { + struct vmpacket_descriptor d; + u32 reserved; + u32 range_cnt; + struct gpa_range range[1]; +} __packed; + +/* This is the format for a Additional Data Packet. */ +struct vmadditional_data { + struct vmpacket_descriptor d; + u64 total_bytes; + u32 offset; + u32 byte_cnt; + unsigned char data[1]; +} __packed; + +union vmpacket_largest_possible_header { + struct vmpacket_descriptor simple_hdr; + struct vmtransfer_page_packet_header xfer_page_hdr; + struct vmgpadl_packet_header gpadl_hdr; + struct vmadd_remove_transfer_page_set add_rm_xfer_page_hdr; + struct vmestablish_gpadl establish_gpadl_hdr; + struct vmteardown_gpadl teardown_gpadl_hdr; + struct vmdata_gpa_direct data_gpa_direct_hdr; +}; + +#define VMPACKET_DATA_START_ADDRESS(__packet) \ + (void *)(((unsigned char *)__packet) + \ + ((struct vmpacket_descriptor)__packet)->offset8 * 8) + +#define VMPACKET_DATA_LENGTH(__packet) \ + ((((struct vmpacket_descriptor)__packet)->len8 - \ + ((struct vmpacket_descriptor)__packet)->offset8) * 8) + +#define VMPACKET_TRANSFER_MODE(__packet) \ + (((struct IMPACT)__packet)->type) + +enum vmbus_packet_type { + VM_PKT_INVALID = 0x0, + VM_PKT_SYNCH = 0x1, + VM_PKT_ADD_XFER_PAGESET = 0x2, + VM_PKT_RM_XFER_PAGESET = 0x3, + VM_PKT_ESTABLISH_GPADL = 0x4, + VM_PKT_TEARDOWN_GPADL = 0x5, + VM_PKT_DATA_INBAND = 0x6, + VM_PKT_DATA_USING_XFER_PAGES = 0x7, + VM_PKT_DATA_USING_GPADL = 0x8, + VM_PKT_DATA_USING_GPA_DIRECT = 0x9, + VM_PKT_CANCEL_REQUEST = 0xa, + VM_PKT_COMP = 0xb, + VM_PKT_DATA_USING_ADDITIONAL_PKT = 0xc, + VM_PKT_ADDITIONAL_DATA = 0xd +}; + +#define VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED 1 + + +/* Version 1 messages */ +enum vmbus_channel_message_type { + CHANNELMSG_INVALID = 0, + CHANNELMSG_OFFERCHANNEL = 1, + CHANNELMSG_RESCIND_CHANNELOFFER = 2, + CHANNELMSG_REQUESTOFFERS = 3, + CHANNELMSG_ALLOFFERS_DELIVERED = 4, + CHANNELMSG_OPENCHANNEL = 5, + CHANNELMSG_OPENCHANNEL_RESULT = 6, + CHANNELMSG_CLOSECHANNEL = 7, + CHANNELMSG_GPADL_HEADER = 8, + CHANNELMSG_GPADL_BODY = 9, + CHANNELMSG_GPADL_CREATED = 10, + CHANNELMSG_GPADL_TEARDOWN = 11, + CHANNELMSG_GPADL_TORNDOWN = 12, + CHANNELMSG_RELID_RELEASED = 13, + CHANNELMSG_INITIATE_CONTACT = 14, + CHANNELMSG_VERSION_RESPONSE = 15, + CHANNELMSG_UNLOAD = 16, +#ifdef VMBUS_FEATURE_PARENT_OR_PEER_MEMORY_MAPPED_INTO_A_CHILD + CHANNELMSG_VIEWRANGE_ADD = 17, + CHANNELMSG_VIEWRANGE_REMOVE = 18, +#endif + CHANNELMSG_COUNT +}; + +struct vmbus_channel_message_header { + enum vmbus_channel_message_type msgtype; + u32 padding; +} __packed; + +/* Query VMBus Version parameters */ +struct vmbus_channel_query_vmbus_version { + struct vmbus_channel_message_header header; + u32 version; +} __packed; + +/* VMBus Version Supported parameters */ +struct vmbus_channel_version_supported { + struct vmbus_channel_message_header header; + bool version_supported; +} __packed; + +/* Offer Channel parameters */ +struct vmbus_channel_offer_channel { + struct vmbus_channel_message_header header; + struct vmbus_channel_offer offer; + u32 child_relid; + u8 monitorid; + bool monitor_allocated; +} __packed; + +/* Rescind Offer parameters */ +struct vmbus_channel_rescind_offer { + struct vmbus_channel_message_header header; + u32 child_relid; +} __packed; + +/* + * Request Offer -- no parameters, SynIC message contains the partition ID + * Set Snoop -- no parameters, SynIC message contains the partition ID + * Clear Snoop -- no parameters, SynIC message contains the partition ID + * All Offers Delivered -- no parameters, SynIC message contains the partition + * ID + * Flush Client -- no parameters, SynIC message contains the partition ID + */ + +/* Open Channel parameters */ +struct vmbus_channel_open_channel { + struct vmbus_channel_message_header header; + + /* Identifies the specific VMBus channel that is being opened. */ + u32 child_relid; + + /* ID making a particular open request at a channel offer unique. */ + u32 openid; + + /* GPADL for the channel's ring buffer. */ + u32 ringbuffer_gpadlhandle; + + /* GPADL for the channel's server context save area. */ + u32 server_contextarea_gpadlhandle; + + /* + * The upstream ring buffer begins at offset zero in the memory + * described by RingBufferGpadlHandle. The downstream ring buffer + * follows it at this offset (in pages). + */ + u32 downstream_ringbuffer_pageoffset; + + /* User-specific data to be passed along to the server endpoint. */ + unsigned char userdata[MAX_USER_DEFINED_BYTES]; +} __packed; + +/* Open Channel Result parameters */ +struct vmbus_channel_open_result { + struct vmbus_channel_message_header header; + u32 child_relid; + u32 openid; + u32 status; +} __packed; + +/* Close channel parameters; */ +struct vmbus_channel_close_channel { + struct vmbus_channel_message_header header; + u32 child_relid; +} __packed; + +/* Channel Message GPADL */ +#define GPADL_TYPE_RING_BUFFER 1 +#define GPADL_TYPE_SERVER_SAVE_AREA 2 +#define GPADL_TYPE_TRANSACTION 8 + +/* + * The number of PFNs in a GPADL message is defined by the number of + * pages that would be spanned by ByteCount and ByteOffset. If the + * implied number of PFNs won't fit in this packet, there will be a + * follow-up packet that contains more. + */ +struct vmbus_channel_gpadl_header { + struct vmbus_channel_message_header header; + u32 child_relid; + u32 gpadl; + u16 range_buflen; + u16 rangecount; + struct gpa_range range[0]; +} __packed; + +/* This is the followup packet that contains more PFNs. */ +struct vmbus_channel_gpadl_body { + struct vmbus_channel_message_header header; + u32 msgnumber; + u32 gpadl; + u64 pfn[0]; +} __packed; + +struct vmbus_channel_gpadl_created { + struct vmbus_channel_message_header header; + u32 child_relid; + u32 gpadl; + u32 creation_status; +} __packed; + +struct vmbus_channel_gpadl_teardown { + struct vmbus_channel_message_header header; + u32 child_relid; + u32 gpadl; +} __packed; + +struct vmbus_channel_gpadl_torndown { + struct vmbus_channel_message_header header; + u32 gpadl; +} __packed; + +#ifdef VMBUS_FEATURE_PARENT_OR_PEER_MEMORY_MAPPED_INTO_A_CHILD +struct vmbus_channel_view_range_add { + struct vmbus_channel_message_header header; + PHYSICAL_ADDRESS viewrange_base; + u64 viewrange_length; + u32 child_relid; +} __packed; + +struct vmbus_channel_view_range_remove { + struct vmbus_channel_message_header header; + PHYSICAL_ADDRESS viewrange_base; + u32 child_relid; +} __packed; +#endif + +struct vmbus_channel_relid_released { + struct vmbus_channel_message_header header; + u32 child_relid; +} __packed; + +struct vmbus_channel_initiate_contact { + struct vmbus_channel_message_header header; + u32 vmbus_version_requested; + u32 padding2; + u64 interrupt_page; + u64 monitor_page1; + u64 monitor_page2; +} __packed; + +struct vmbus_channel_version_response { + struct vmbus_channel_message_header header; + bool version_supported; +} __packed; + +enum vmbus_channel_state { + CHANNEL_OFFER_STATE, + CHANNEL_OPENING_STATE, + CHANNEL_OPEN_STATE, +}; + +struct vmbus_channel_debug_info { + u32 relid; + enum vmbus_channel_state state; + uuid_le interfacetype; + uuid_le interface_instance; + u32 monitorid; + u32 servermonitor_pending; + u32 servermonitor_latency; + u32 servermonitor_connectionid; + u32 clientmonitor_pending; + u32 clientmonitor_latency; + u32 clientmonitor_connectionid; + + struct hv_ring_buffer_debug_info inbound; + struct hv_ring_buffer_debug_info outbound; +}; + +/* + * Represents each channel msg on the vmbus connection This is a + * variable-size data structure depending on the msg type itself + */ +struct vmbus_channel_msginfo { + /* Bookkeeping stuff */ + struct list_head msglistentry; + + /* So far, this is only used to handle gpadl body message */ + struct list_head submsglist; + + /* Synchronize the request/response if needed */ + struct completion waitevent; + union { + struct vmbus_channel_version_supported version_supported; + struct vmbus_channel_open_result open_result; + struct vmbus_channel_gpadl_torndown gpadl_torndown; + struct vmbus_channel_gpadl_created gpadl_created; + struct vmbus_channel_version_response version_response; + } response; + + u32 msgsize; + /* + * The channel message that goes out on the "wire". + * It will contain at minimum the VMBUS_CHANNEL_MESSAGE_HEADER header + */ + unsigned char msg[0]; +}; + +struct vmbus_close_msg { + struct vmbus_channel_msginfo info; + struct vmbus_channel_close_channel msg; +}; + +struct vmbus_channel { + struct list_head listentry; + + struct hv_device *device_obj; + + struct work_struct work; + + enum vmbus_channel_state state; + + struct vmbus_channel_offer_channel offermsg; + /* + * These are based on the OfferMsg.MonitorId. + * Save it here for easy access. + */ + u8 monitor_grp; + u8 monitor_bit; + + u32 ringbuffer_gpadlhandle; + + /* Allocated memory for ring buffer */ + void *ringbuffer_pages; + u32 ringbuffer_pagecount; + struct hv_ring_buffer_info outbound; /* send to parent */ + struct hv_ring_buffer_info inbound; /* receive from parent */ + spinlock_t inbound_lock; + struct workqueue_struct *controlwq; + + struct vmbus_close_msg close_msg; + + /* Channel callback are invoked in this workqueue context */ + /* HANDLE dataWorkQueue; */ + + void (*onchannel_callback)(void *context); + void *channel_callback_context; +}; + +void free_channel(struct vmbus_channel *channel); + +void vmbus_onmessage(void *context); + +int vmbus_request_offers(void); + +/* The format must be the same as struct vmdata_gpa_direct */ +struct vmbus_channel_packet_page_buffer { + u16 type; + u16 dataoffset8; + u16 length8; + u16 flags; + u64 transactionid; + u32 reserved; + u32 rangecount; + struct hv_page_buffer range[MAX_PAGE_BUFFER_COUNT]; +} __packed; + +/* The format must be the same as struct vmdata_gpa_direct */ +struct vmbus_channel_packet_multipage_buffer { + u16 type; + u16 dataoffset8; + u16 length8; + u16 flags; + u64 transactionid; + u32 reserved; + u32 rangecount; /* Always 1 in this case */ + struct hv_multipage_buffer range; +} __packed; + + +extern int vmbus_open(struct vmbus_channel *channel, + u32 send_ringbuffersize, + u32 recv_ringbuffersize, + void *userdata, + u32 userdatalen, + void(*onchannel_callback)(void *context), + void *context); + +extern void vmbus_close(struct vmbus_channel *channel); + +extern int vmbus_sendpacket(struct vmbus_channel *channel, + const 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, + void *buffer, + u32 bufferlen, + u64 requestid); + +extern int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, + struct hv_multipage_buffer *mpb, + void *buffer, + u32 bufferlen, + u64 requestid); + +extern int vmbus_establish_gpadl(struct vmbus_channel *channel, + void *kbuffer, + u32 size, + u32 *gpadl_handle); + +extern int vmbus_teardown_gpadl(struct vmbus_channel *channel, + u32 gpadl_handle); + +extern int vmbus_recvpacket(struct vmbus_channel *channel, + void *buffer, + u32 bufferlen, + u32 *buffer_actual_len, + u64 *requestid); + +extern int vmbus_recvpacket_raw(struct vmbus_channel *channel, + void *buffer, + u32 bufferlen, + u32 *buffer_actual_len, + u64 *requestid); + + +extern void vmbus_get_debug_info(struct vmbus_channel *channel, + struct vmbus_channel_debug_info *debug); + +extern void vmbus_ontimer(unsigned long data); + + +#define LOWORD(dw) ((unsigned short)(dw)) +#define HIWORD(dw) ((unsigned short)(((unsigned int) (dw) >> 16) & 0xFFFF)) + + +#define VMBUS 0x0001 +#define STORVSC 0x0002 +#define NETVSC 0x0004 +#define INPUTVSC 0x0008 +#define BLKVSC 0x0010 +#define VMBUS_DRV 0x0100 +#define STORVSC_DRV 0x0200 +#define NETVSC_DRV 0x0400 +#define INPUTVSC_DRV 0x0800 +#define BLKVSC_DRV 0x1000 + +#define ALL_MODULES (VMBUS |\ + STORVSC |\ + NETVSC |\ + INPUTVSC |\ + BLKVSC |\ + VMBUS_DRV |\ + STORVSC_DRV |\ + NETVSC_DRV |\ + INPUTVSC_DRV|\ + BLKVSC_DRV) + +/* Logging Level */ +#define ERROR_LVL 3 +#define WARNING_LVL 4 +#define INFO_LVL 6 +#define DEBUG_LVL 7 +#define DEBUG_LVL_ENTEREXIT 8 +#define DEBUG_RING_LVL 9 + +extern unsigned int vmbus_loglevel; + +#define DPRINT(mod, lvl, fmt, args...) do {\ + if ((mod & (HIWORD(vmbus_loglevel))) && \ + (lvl <= LOWORD(vmbus_loglevel))) \ + printk(KERN_DEBUG #mod": %s() " fmt "\n", __func__, ## args);\ + } while (0) + +#define DPRINT_DBG(mod, fmt, args...) do {\ + if ((mod & (HIWORD(vmbus_loglevel))) && \ + (DEBUG_LVL <= LOWORD(vmbus_loglevel))) \ + printk(KERN_DEBUG #mod": %s() " fmt "\n", __func__, ## args);\ + } while (0) + +#define DPRINT_INFO(mod, fmt, args...) do {\ + if ((mod & (HIWORD(vmbus_loglevel))) && \ + (INFO_LVL <= LOWORD(vmbus_loglevel))) \ + printk(KERN_INFO #mod": " fmt "\n", ## args);\ + } while (0) + +#define DPRINT_WARN(mod, fmt, args...) do {\ + if ((mod & (HIWORD(vmbus_loglevel))) && \ + (WARNING_LVL <= LOWORD(vmbus_loglevel))) \ + printk(KERN_WARNING #mod": WARNING! " fmt "\n", ## args);\ + } while (0) + +#define DPRINT_ERR(mod, fmt, args...) do {\ + if ((mod & (HIWORD(vmbus_loglevel))) && \ + (ERROR_LVL <= LOWORD(vmbus_loglevel))) \ + printk(KERN_ERR #mod": %s() ERROR!! " fmt "\n", \ + __func__, ## args);\ + } while (0) + + + +struct hv_driver; +struct hv_device; + +struct hv_dev_port_info { + u32 int_mask; + u32 read_idx; + u32 write_idx; + u32 bytes_avail_toread; + u32 bytes_avail_towrite; +}; + +struct hv_device_info { + u32 chn_id; + u32 chn_state; + uuid_le chn_type; + uuid_le chn_instance; + + u32 monitor_id; + u32 server_monitor_pending; + u32 server_monitor_latency; + u32 server_monitor_conn_id; + u32 client_monitor_pending; + u32 client_monitor_latency; + u32 client_monitor_conn_id; + + struct hv_dev_port_info inbound; + struct hv_dev_port_info outbound; +}; + +/* Base driver object */ +struct hv_driver { + const char *name; + + /* the device type supported by this driver */ + uuid_le dev_type; + const struct hv_vmbus_device_id *id_table; + + struct device_driver driver; + + int (*probe)(struct hv_device *, const struct hv_vmbus_device_id *); + int (*remove)(struct hv_device *); + void (*shutdown)(struct hv_device *); + +}; + +/* Base device object */ +struct hv_device { + /* the device type id of this device */ + uuid_le dev_type; + + /* the device instance id of this device */ + uuid_le dev_instance; + + struct device device; + + struct vmbus_channel *channel; +}; + + +static inline struct hv_device *device_to_hv_device(struct device *d) +{ + return container_of(d, struct hv_device, device); +} + +static inline struct hv_driver *drv_to_hv_drv(struct device_driver *d) +{ + return container_of(d, struct hv_driver, driver); +} + +static inline void hv_set_drvdata(struct hv_device *dev, void *data) +{ + dev_set_drvdata(&dev->device, data); +} + +static inline void *hv_get_drvdata(struct hv_device *dev) +{ + return dev_get_drvdata(&dev->device); +} + +/* Vmbus interface */ +#define vmbus_driver_register(driver) \ + __vmbus_driver_register(driver, THIS_MODULE, KBUILD_MODNAME) +int __must_check __vmbus_driver_register(struct hv_driver *hv_driver, + struct module *owner, + const char *mod_name); +void vmbus_driver_unregister(struct hv_driver *hv_driver); + +/** + * VMBUS_DEVICE - macro used to describe a specific hyperv vmbus device + * + * This macro is used to create a struct hv_vmbus_device_id that matches a + * specific device. + */ +#define VMBUS_DEVICE(g0, g1, g2, g3, g4, g5, g6, g7, \ + g8, g9, ga, gb, gc, gd, ge, gf) \ + .guid = { g0, g1, g2, g3, g4, g5, g6, g7, \ + g8, g9, ga, gb, gc, gd, ge, gf }, + +/* + * Common header for Hyper-V ICs + */ + +#define ICMSGTYPE_NEGOTIATE 0 +#define ICMSGTYPE_HEARTBEAT 1 +#define ICMSGTYPE_KVPEXCHANGE 2 +#define ICMSGTYPE_SHUTDOWN 3 +#define ICMSGTYPE_TIMESYNC 4 +#define ICMSGTYPE_VSS 5 + +#define ICMSGHDRFLAG_TRANSACTION 1 +#define ICMSGHDRFLAG_REQUEST 2 +#define ICMSGHDRFLAG_RESPONSE 4 + +#define HV_S_OK 0x00000000 +#define HV_E_FAIL 0x80004005 +#define HV_ERROR_NOT_SUPPORTED 0x80070032 +#define HV_ERROR_MACHINE_LOCKED 0x800704F7 + +/* + * While we want to handle util services as regular devices, + * there is only one instance of each of these services; so + * we statically allocate the service specific state. + */ + +struct hv_util_service { + u8 *recv_buffer; + void (*util_cb)(void *); + int (*util_init)(struct hv_util_service *); + void (*util_deinit)(void); +}; + +struct vmbuspipe_hdr { + u32 flags; + u32 msgsize; +} __packed; + +struct ic_version { + u16 major; + u16 minor; +} __packed; + +struct icmsg_hdr { + struct ic_version icverframe; + u16 icmsgtype; + struct ic_version icvermsg; + u16 icmsgsize; + u32 status; + u8 ictransaction_id; + u8 icflags; + u8 reserved[2]; +} __packed; + +struct icmsg_negotiate { + u16 icframe_vercnt; + u16 icmsg_vercnt; + u32 reserved; + struct ic_version icversion_data[1]; /* any size array */ +} __packed; + +struct shutdown_msg_data { + u32 reason_code; + u32 timeout_seconds; + u32 flags; + u8 display_message[2048]; +} __packed; + +struct heartbeat_msg_data { + u64 seq_num; + u32 reserved[8]; +} __packed; + +/* Time Sync IC defs */ +#define ICTIMESYNCFLAG_PROBE 0 +#define ICTIMESYNCFLAG_SYNC 1 +#define ICTIMESYNCFLAG_SAMPLE 2 + +#ifdef __x86_64__ +#define WLTIMEDELTA 116444736000000000L /* in 100ns unit */ +#else +#define WLTIMEDELTA 116444736000000000LL +#endif + +struct ictimesync_data { + u64 parenttime; + u64 childtime; + u64 roundtriptime; + u8 flags; +} __packed; + +struct hyperv_service_callback { + u8 msg_type; + char *log_msg; + uuid_le data; + struct vmbus_channel *channel; + void (*callback) (void *context); +}; + +extern void prep_negotiate_resp(struct icmsg_hdr *, + struct icmsg_negotiate *, u8 *); + +#endif /* _HYPERV_H */ -- cgit v1.2.3 From 540f41edc15473ca3b2876de72646546ae101374 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 5 Oct 2011 17:25:28 +1100 Subject: llist: Add back llist_add_batch() and llist_del_first() prototypes Commit 1230db8e1543 ("llist: Make some llist functions inline") has deleted the definitions, causing problems for (not upstream yet) code that tries to make use of them. Signed-off-by: Stephen Rothwell Acked-by: Peter Zijlstra Cc: Huang Ying Cc: David Miller Link: http://lkml.kernel.org/r/20111005172528.0d0a8afc65acef7ace22a24e@canb.auug.org.au Signed-off-by: Ingo Molnar --- include/linux/llist.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index 837fb4ae66fb..7287734e08d1 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -178,4 +178,10 @@ static inline struct llist_node *llist_del_all(struct llist_head *head) { return xchg(&head->first, NULL); } + +extern bool llist_add_batch(struct llist_node *new_first, + struct llist_node *new_last, + struct llist_head *head); +extern struct llist_node *llist_del_first(struct llist_head *head); + #endif /* LLIST_H */ -- cgit v1.2.3 From 407dd1644302ea78fa5d740e67a1c09677aa18a4 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 08:36:44 -0600 Subject: Staging: hv: remove unneeded asm include file in hyperv.h No one outside of the hyperv core needs to include the asm/hyperv.h file, so don't put it in the "global" include/linux/hyperv.h file. Cc: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index edaa9e2f58ec..4c8414a8b07f 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -35,9 +35,6 @@ #include -#include - - #define MAX_PAGE_BUFFER_COUNT 16 #define MAX_MULTIPAGE_BUFFER_COUNT 32 /* 128K */ -- cgit v1.2.3 From da0e96315ca703ab6540cc7665549622f71c155f Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 08:42:28 -0600 Subject: hv: rename prep_negotiate_resp() to vmbus_prep_negotiate_resp() It's a global symbol, so properly prefix it and use the proper EXPORT value as well. Cc: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 4c8414a8b07f..98a57a51acfc 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -960,7 +960,7 @@ struct hyperv_service_callback { void (*callback) (void *context); }; -extern void prep_negotiate_resp(struct icmsg_hdr *, - struct icmsg_negotiate *, u8 *); +extern void vmbus_prep_negotiate_resp(struct icmsg_hdr *, + struct icmsg_negotiate *, u8 *); #endif /* _HYPERV_H */ -- cgit v1.2.3 From a832a1eba94096513bc42c96f33957cc46c5f2bf Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 08:47:32 -0600 Subject: hv: remove a bunch of unused debug macros from hyperv.h These aren't used by anyone anymore, so remove them before someone tries to use them again. Cc: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 98a57a51acfc..2229073874b0 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -721,11 +721,8 @@ extern void vmbus_ontimer(unsigned long data); BLKVSC_DRV) /* Logging Level */ -#define ERROR_LVL 3 #define WARNING_LVL 4 #define INFO_LVL 6 -#define DEBUG_LVL 7 -#define DEBUG_LVL_ENTEREXIT 8 #define DEBUG_RING_LVL 9 extern unsigned int vmbus_loglevel; @@ -736,33 +733,12 @@ extern unsigned int vmbus_loglevel; printk(KERN_DEBUG #mod": %s() " fmt "\n", __func__, ## args);\ } while (0) -#define DPRINT_DBG(mod, fmt, args...) do {\ - if ((mod & (HIWORD(vmbus_loglevel))) && \ - (DEBUG_LVL <= LOWORD(vmbus_loglevel))) \ - printk(KERN_DEBUG #mod": %s() " fmt "\n", __func__, ## args);\ - } while (0) - -#define DPRINT_INFO(mod, fmt, args...) do {\ - if ((mod & (HIWORD(vmbus_loglevel))) && \ - (INFO_LVL <= LOWORD(vmbus_loglevel))) \ - printk(KERN_INFO #mod": " fmt "\n", ## args);\ - } while (0) - #define DPRINT_WARN(mod, fmt, args...) do {\ if ((mod & (HIWORD(vmbus_loglevel))) && \ (WARNING_LVL <= LOWORD(vmbus_loglevel))) \ printk(KERN_WARNING #mod": WARNING! " fmt "\n", ## args);\ } while (0) -#define DPRINT_ERR(mod, fmt, args...) do {\ - if ((mod & (HIWORD(vmbus_loglevel))) && \ - (ERROR_LVL <= LOWORD(vmbus_loglevel))) \ - printk(KERN_ERR #mod": %s() ERROR!! " fmt "\n", \ - __func__, ## args);\ - } while (0) - - - struct hv_driver; struct hv_device; -- cgit v1.2.3 From d181daa06dd72fa88652b1d8bf723570a9fc55ea Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 09:20:31 -0600 Subject: Staging: hv: storvsc: remove last usage of DPRINT_WARN Used the correct dev_warn() call instead. Cc: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- 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 2229073874b0..097d6dbe685a 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -721,7 +721,6 @@ extern void vmbus_ontimer(unsigned long data); BLKVSC_DRV) /* Logging Level */ -#define WARNING_LVL 4 #define INFO_LVL 6 #define DEBUG_RING_LVL 9 @@ -733,11 +732,6 @@ extern unsigned int vmbus_loglevel; printk(KERN_DEBUG #mod": %s() " fmt "\n", __func__, ## args);\ } while (0) -#define DPRINT_WARN(mod, fmt, args...) do {\ - if ((mod & (HIWORD(vmbus_loglevel))) && \ - (WARNING_LVL <= LOWORD(vmbus_loglevel))) \ - printk(KERN_WARNING #mod": WARNING! " fmt "\n", ## args);\ - } while (0) struct hv_driver; struct hv_device; -- cgit v1.2.3 From 1a2643012fa2262e823b7f11d9732b7fea4c25ce Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 09:25:14 -0600 Subject: Staging: hv: remove last user of DPRINT() macro This also removed the unused function hv_dump_ring_info(). Cc: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- 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 097d6dbe685a..4fa32ec43aa4 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -722,17 +722,9 @@ extern void vmbus_ontimer(unsigned long data); /* Logging Level */ #define INFO_LVL 6 -#define DEBUG_RING_LVL 9 extern unsigned int vmbus_loglevel; -#define DPRINT(mod, lvl, fmt, args...) do {\ - if ((mod & (HIWORD(vmbus_loglevel))) && \ - (lvl <= LOWORD(vmbus_loglevel))) \ - printk(KERN_DEBUG #mod": %s() " fmt "\n", __func__, ## args);\ - } while (0) - - struct hv_driver; struct hv_device; -- cgit v1.2.3 From 815166b95df1acb4890e9dbdb26660e9c00a7505 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 09:27:48 -0600 Subject: Staging: hv: remove vmbus_loglevel as it is not used at all anymore As there is no user of this variable, it's time to delete it. For dynamic debugging of the hyperv code, use the standard dynamic debug kernel interface. Cc: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 4fa32ec43aa4..7211e2ce24f5 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -720,11 +720,6 @@ extern void vmbus_ontimer(unsigned long data); INPUTVSC_DRV|\ BLKVSC_DRV) -/* Logging Level */ -#define INFO_LVL 6 - -extern unsigned int vmbus_loglevel; - struct hv_driver; struct hv_device; -- cgit v1.2.3 From 5557e8a60570d0c2f3a06d6e9e6a0f5074c313f2 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 09:30:22 -0600 Subject: hv: remove unused LOWORD and HIWORD macros from hyperv.h They aren't used anywhere anymore now that the debugging macros are gone, so remove it from hyperv.h as well. Cc: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 7211e2ce24f5..6d9a53fc8a37 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -694,10 +694,6 @@ extern void vmbus_get_debug_info(struct vmbus_channel *channel, extern void vmbus_ontimer(unsigned long data); -#define LOWORD(dw) ((unsigned short)(dw)) -#define HIWORD(dw) ((unsigned short)(((unsigned int) (dw) >> 16) & 0xFFFF)) - - #define VMBUS 0x0001 #define STORVSC 0x0002 #define NETVSC 0x0004 -- cgit v1.2.3 From 7a4ba88cc11eb4ba72778f491d8241385cb0475d Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 09:33:29 -0600 Subject: hv: hyperv.h: remove unused module macros I have no idea what these were ever for, but they aren't used, so delete them. Cc: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 23 ----------------------- 1 file changed, 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 6d9a53fc8a37..f2bf0a51914b 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -693,29 +693,6 @@ extern void vmbus_get_debug_info(struct vmbus_channel *channel, extern void vmbus_ontimer(unsigned long data); - -#define VMBUS 0x0001 -#define STORVSC 0x0002 -#define NETVSC 0x0004 -#define INPUTVSC 0x0008 -#define BLKVSC 0x0010 -#define VMBUS_DRV 0x0100 -#define STORVSC_DRV 0x0200 -#define NETVSC_DRV 0x0400 -#define INPUTVSC_DRV 0x0800 -#define BLKVSC_DRV 0x1000 - -#define ALL_MODULES (VMBUS |\ - STORVSC |\ - NETVSC |\ - INPUTVSC |\ - BLKVSC |\ - VMBUS_DRV |\ - STORVSC_DRV |\ - NETVSC_DRV |\ - INPUTVSC_DRV|\ - BLKVSC_DRV) - struct hv_driver; struct hv_device; -- cgit v1.2.3 From 2726f95e0b6c850b6162f287f2f83d9db37decd7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 09:37:27 -0600 Subject: hv: hyperv.h: remove unneeded forward declarations of structures This file was created by mushing different .h files together and it shows. This change removes some unneeded forward declarations. Cc: K. Y. Srinivasan Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f2bf0a51914b..ae865a11ad46 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -693,9 +693,6 @@ extern void vmbus_get_debug_info(struct vmbus_channel *channel, extern void vmbus_ontimer(unsigned long data); -struct hv_driver; -struct hv_device; - struct hv_dev_port_info { u32 int_mask; u32 read_idx; -- cgit v1.2.3 From 9f3e28e375a8d509a27efe89f3c8ea2a15aeb524 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 09:40:01 -0600 Subject: hv: remove free_channel() from hyperv.h This function is only used in the file it is declared in (channel_mgmt.c) so make it static and remove it from the hyperv.h file. Cc: 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 ae865a11ad46..240e1141cbbd 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -606,8 +606,6 @@ struct vmbus_channel { void *channel_callback_context; }; -void free_channel(struct vmbus_channel *channel); - void vmbus_onmessage(void *context); int vmbus_request_offers(void); -- cgit v1.2.3 From 15b80d641793968605254c2bbb2aa9a10accb415 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Tue, 11 Oct 2011 09:43:14 -0600 Subject: hv: remove struct hv_device_info from hyperv.h This is only used/needed by the vmbus core code, so move it out of the hyperv.h file and into the .c file that uses it. Signed-off-by: Greg Kroah-Hartman --- include/linux/hyperv.h | 18 ------------------ 1 file changed, 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 240e1141cbbd..12ec328481de 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -699,24 +699,6 @@ struct hv_dev_port_info { u32 bytes_avail_towrite; }; -struct hv_device_info { - u32 chn_id; - u32 chn_state; - uuid_le chn_type; - uuid_le chn_instance; - - u32 monitor_id; - u32 server_monitor_pending; - u32 server_monitor_latency; - u32 server_monitor_conn_id; - u32 client_monitor_pending; - u32 client_monitor_latency; - u32 client_monitor_conn_id; - - struct hv_dev_port_info inbound; - struct hv_dev_port_info outbound; -}; - /* Base driver object */ struct hv_driver { const char *name; -- cgit v1.2.3 From 2744e8afb3b76343e7eb8197e8b3e085036010a5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Mon, 2 May 2011 20:50:54 +0200 Subject: drivers: create a pin control subsystem This creates a subsystem for handling of pin control devices. These are devices that control different aspects of package pins. Currently it handles pinmuxing, i.e. assigning electronic functions to groups of pins on primarily PGA and BGA type of chip packages which are common in embedded systems. The plan is to also handle other I/O pin control aspects such as biasing, driving, input properties such as schmitt-triggering, load capacitance etc within this subsystem, to remove a lot of ARM arch code as well as feature-creepy GPIO drivers which are implementing the same thing over and over again. This is being done to depopulate the arch/arm/* directory of such custom drivers and try to abstract the infrastructure they all need. See the Documentation/pinctrl.txt file that is part of this patch for more details. ChangeLog v1->v2: - Various minor fixes from Joe's and Stephens review comments - Added a pinmux_config() that can invoke custom configuration with arbitrary data passed in or out to/from the pinmux driver ChangeLog v2->v3: - Renamed subsystem folder to "pinctrl" since we will likely want to keep other pin control such as biasing in this subsystem too, so let us keep to something generic even though we're mainly doing pinmux now. - As a consequence, register pins as an abstract entity separate from the pinmux. The muxing functions will claim pins out of the pin pool and make sure they do not collide. Pins can now be named by the pinctrl core. - Converted the pin lookup from a static array into a radix tree, I agreed with Grant Likely to try to avoid any static allocation (which is crap for device tree stuff) so I just rewrote this to be dynamic, just like irq number descriptors. The platform-wide definition of number of pins goes away - this is now just the sum total of the pins registered to the subsystem. - Make sure mappings with only a function name and no device works properly. ChangeLog v3->v4: - Define a number space per controller instead of globally, Stephen and Grant requested the same thing so now maps need to define target controller, and the radix tree of pin descriptors is a property on each pin controller device. - Add a compulsory pinctrl device entry to the pinctrl mapping table. This must match the pinctrl device, like "pinctrl.0" - Split the file core.c in two: core.c and pinmux.c where the latter carry all pinmux stuff, the core is for generic pin control, and use local headers to access functionality between files. It is now possible to implement a "blank" pin controller without pinmux capabilities. This split will make new additions like pindrive.c, pinbias.c etc possible for combined drivers and chunks of functionality which is a GoodThing(TM). - Rewrite the interaction with the GPIO subsystem - the pin controller descriptor now handles this by defining an offset into the GPIO numberspace for its handled pin range. This is used to look up the apropriate pin controller for a GPIO pin. Then that specific GPIO range is matched 1-1 for the target controller instance. - Fixed a number of review comments from Joe Perches. - Broke out a header file pinctrl.h for the core pin handling stuff that will be reused by other stuff than pinmux. - Fixed some erroneous EXPORT() stuff. - Remove mispatched U300 Kconfig and Makefile entries - Fixed a number of review comments from Stephen Warren, not all of them - still WIP. But I think the new mapping that will specify which function goes to which pin mux controller address 50% of your concerns (else beat me up). ChangeLog v4->v5: - Defined a "position" for each function, so the pin controller now tracks a function in a certain position, and the pinmux maps define what position you want the function in. (Feedback from Stephen Warren and Sascha Hauer). - Since we now need to request a combined function+position from the machine mapping table that connect mux settings to drivers, it was extended with a position field and a name field. The name field is now used if you e.g. need to switch between two mux map settings at runtime. - Switched from a class device to using struct bus_type for this subsystem. Verified sysfs functionality: seems to work fine. (Feedback from Arnd Bergmann and Greg Kroah-Hartman) - Define a per pincontroller list of GPIO ranges from the GPIO pin space that can be handled by the pin controller. These can be added one by one at runtime. (Feedback from Barry Song) - Expanded documentation of regulator_[get|enable|disable|put] semantics. - Fixed a number of review comments from Barry Song. (Thanks!) ChangeLog v5->v6: - Create an abstract pin group concept that can sort pins into named and enumerated groups no matter what the use of these groups may be, one possible usecase is a group of pins being muxed in or so. The intention is however to also use these groups for other pin control activities. - Make it compulsory for pinmux functions to associate with at least one group, so the abstract pin group concept is used to define the groups of pins affected by a pinmux function. The pinmux driver interface has been altered so as to enforce a function to list applicable groups per function. - Provide an optional .group entry in the pinmux machine map so the map can select beteween different available groups to be used with a certain function. - Consequent changes all over the place so that e.g. debugfs present reasonable information about the world. - Drop the per-pin mux (*config) function in the pinmux_ops struct - I was afraid that this would start to be used for things totally unrelated to muxing, we can introduce that to the generic struct pinctrl_ops if needed. I want to keep muxing orthogonal to other pin control subjects and not mix these things up. ChangeLog v6->v7: - Make it possible to have several map entries matching the same device, pin controller and function, but using a different group, and alter the semantics so that pinmux_get() will pick all matching map entries, and store the associated groups in a list. The list will then be iterated over at pinmux_enable()/pinmux_disable() and corresponding driver functions called for each defined group. Notice that you're only allowed to map multiple *groups* to the same { device, pin controller, function } triplet, attempts to map the same device to multiple pin controllers will for example fail. This is hopefully the crucial feature requested by Stephen Warren. - Add a pinmux hogging field to the pinmux mapping entries, and enable the pinmux core to hog pinmux map entries. This currently only works for pinmuxes without assigned devices as it looks now, but with device trees we can look up the corresponding struct device * entries when we register the pinmux driver, and have it hog each pinmux map in turn, for a simple approach to non-dynamic pin muxing. This addresses an issue from Grant Likely that the machine should take care of as much of the pinmux setup as possible, not the devices. By supplying a list of hogs, it can now instruct the core to take care of any static mappings. - Switch pinmux group retrieveal function to grab an array of strings representing the groups rather than an array of unsigned and rewrite accordingly. - Alter debugfs to show the grouplist handled by each pinmux. Also add a list of hogs. - Dynamically allocate a struct pinmux at pinmux_get() and free it at pinmux_put(), then add these to the global list of pinmuxes active as we go along. - Go over the list of pinmux maps at pinmux_get() time and repeatedly apply matches. - Retrieve applicable groups per function from the driver as a string array rather than a unsigned array, then lookup the enumerators. - Make the device to pinmux map a singleton - only allow the mapping table to be registered once and even tag the registration function with __init so it surely won't be abused. - Create a separate debugfs file to view the pinmux map at runtime. - Introduce a spin lock to the pin descriptor struct, lock it when modifying pin status entries. Reported by Stijn Devriendt. - Fix up the documentation after review from Stephen Warren. - Let the GPIO ranges give names as const char * instead of some fixed-length string. - add a function to unregister GPIO ranges to mirror the registration function. - Privatized the struct pinctrl_device and removed it from the API, the drivers do not need to know the members of this struct. It is now in the local header "core.h". - Rename the concept of "anonymous" mux maps to "system" muxes and add convenience macros and documentation. ChangeLog v7->v8: - Delete the leftover pinmux_config() function from the header. - Fix a race condition found by Stijn Devriendt in pin_request() ChangeLog v8->v9: - Drop the bus_type and the sysfs attributes and all, we're not on the clear about how this should be used for e.g. userspace interfaces so let us save this for the future. - Use the right name in MAINTAINERS, PIN CONTROL rather than PINMUX - Don't kfree() the device state holder, let the .remove() callback handle this. - Fix up numerous kerneldoc headers to have one line for the function description and more verbose documentation below the parameters ChangeLog v9->v10: - pinctrl: EXPORT_SYMBOL needs export.h, folded in a patch from Steven Rothwell - fix pinctrl_register error handling, folded in a patch from Axel Lin - Various fixes to documentation text so that it's consistent. - Removed pointless comment from drivers/Kconfig - Removed dependency on SYSFS since we removed the bus in v9. - Renamed hopelessly abbreviated pctldev_* functions to the more verbose pinctrl_dev_* - Drop mutex properly when looking up GPIO ranges - Return NULL instead of ERR_PTR() errors on registration of pin controllers, using cast pointers is fragile. We can live without the detailed error codes for sure. Cc: Stijn Devriendt Cc: Joe Perches Cc: Russell King Acked-by: Grant Likely Acked-by: Stephen Warren Tested-by: Barry Song <21cnbao@gmail.com> Signed-off-by: Linus Walleij --- include/linux/pinctrl/machine.h | 107 ++++++++++++++++++++++++++++++++ include/linux/pinctrl/pinctrl.h | 133 ++++++++++++++++++++++++++++++++++++++++ include/linux/pinctrl/pinmux.h | 117 +++++++++++++++++++++++++++++++++++ 3 files changed, 357 insertions(+) create mode 100644 include/linux/pinctrl/machine.h create mode 100644 include/linux/pinctrl/pinctrl.h create mode 100644 include/linux/pinctrl/pinmux.h (limited to 'include/linux') diff --git a/include/linux/pinctrl/machine.h b/include/linux/pinctrl/machine.h new file mode 100644 index 000000000000..88863531d862 --- /dev/null +++ b/include/linux/pinctrl/machine.h @@ -0,0 +1,107 @@ +/* + * Machine interface for the pinctrl subsystem. + * + * Copyright (C) 2011 ST-Ericsson SA + * Written on behalf of Linaro for ST-Ericsson + * Based on bits of regulator core, gpio core and clk core + * + * Author: Linus Walleij + * + * License terms: GNU General Public License (GPL) version 2 + */ +#ifndef __LINUX_PINMUX_MACHINE_H +#define __LINUX_PINMUX_MACHINE_H + +/** + * struct pinmux_map - boards/machines shall provide this map for devices + * @name: the name of this specific map entry for the particular machine. + * This is the second parameter passed to pinmux_get() when you want + * to have several mappings to the same device + * @ctrl_dev: the pin control device to be used by this mapping, may be NULL + * if you provide .ctrl_dev_name instead (this is more common) + * @ctrl_dev_name: the name of the device controlling this specific mapping, + * the name must be the same as in your struct device*, may be NULL if + * you provide .ctrl_dev instead + * @function: a function in the driver to use for this mapping, the driver + * will lookup the function referenced by this ID on the specified + * pin control device + * @group: sometimes a function can map to different pin groups, so this + * selects a certain specific pin group to activate for the function, if + * left as NULL, the first applicable group will be used + * @dev: the device using this specific mapping, may be NULL if you provide + * .dev_name instead (this is more common) + * @dev_name: the name of the device using this specific mapping, the name + * must be the same as in your struct device*, may be NULL if you + * provide .dev instead + * @hog_on_boot: if this is set to true, the pin control subsystem will itself + * hog the mappings as the pinmux device drivers are attached, so this is + * typically used with system maps (mux mappings without an assigned + * device) that you want to get hogged and enabled by default as soon as + * a pinmux device supporting it is registered. These maps will not be + * disabled and put until the system shuts down. + */ +struct pinmux_map { + const char *name; + struct device *ctrl_dev; + const char *ctrl_dev_name; + const char *function; + const char *group; + struct device *dev; + const char *dev_name; + const bool hog_on_boot; +}; + +/* + * Convenience macro to set a simple map from a certain pin controller and a + * certain function to a named device + */ +#define PINMUX_MAP(a, b, c, d) \ + { .name = a, .ctrl_dev_name = b, .function = c, .dev_name = d } + +/* + * Convenience macro to map a system function onto a certain pinctrl device. + * System functions are not assigned to a particular device. + */ +#define PINMUX_MAP_SYS(a, b, c) \ + { .name = a, .ctrl_dev_name = b, .function = c } + +/* + * Convenience macro to map a function onto the primary device pinctrl device + * this is especially helpful on systems that have only one pin controller + * or need to set up a lot of mappings on the primary controller. + */ +#define PINMUX_MAP_PRIMARY(a, b, c) \ + { .name = a, .ctrl_dev_name = "pinctrl.0", .function = b, \ + .dev_name = c } + +/* + * Convenience macro to map a system function onto the primary pinctrl device. + * System functions are not assigned to a particular device. + */ +#define PINMUX_MAP_PRIMARY_SYS(a, b) \ + { .name = a, .ctrl_dev_name = "pinctrl.0", .function = b } + +/* + * Convenience macro to map a system function onto the primary pinctrl device, + * to be hogged by the pinmux core until the system shuts down. + */ +#define PINMUX_MAP_PRIMARY_SYS_HOG(a, b) \ + { .name = a, .ctrl_dev_name = "pinctrl.0", .function = b, \ + .hog_on_boot = true } + + +#ifdef CONFIG_PINMUX + +extern int pinmux_register_mappings(struct pinmux_map const *map, + unsigned num_maps); + +#else + +static inline int pinmux_register_mappings(struct pinmux_map const *map, + unsigned num_maps) +{ + return 0; +} + +#endif /* !CONFIG_PINMUX */ +#endif diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h new file mode 100644 index 000000000000..4f8d2089acce --- /dev/null +++ b/include/linux/pinctrl/pinctrl.h @@ -0,0 +1,133 @@ +/* + * Interface the pinctrl subsystem + * + * Copyright (C) 2011 ST-Ericsson SA + * Written on behalf of Linaro for ST-Ericsson + * This interface is used in the core to keep track of pins. + * + * Author: Linus Walleij + * + * License terms: GNU General Public License (GPL) version 2 + */ +#ifndef __LINUX_PINCTRL_PINCTRL_H +#define __LINUX_PINCTRL_PINCTRL_H + +#ifdef CONFIG_PINCTRL + +#include +#include +#include +#include + +struct pinctrl_dev; +struct pinmux_ops; +struct gpio_chip; + +/** + * struct pinctrl_pin_desc - boards/machines provide information on their + * pins, pads or other muxable units in this struct + * @number: unique pin number from the global pin number space + * @name: a name for this pin + */ +struct pinctrl_pin_desc { + unsigned number; + const char *name; +}; + +/* Convenience macro to define a single named or anonymous pin descriptor */ +#define PINCTRL_PIN(a, b) { .number = a, .name = b } +#define PINCTRL_PIN_ANON(a) { .number = a } + +/** + * struct pinctrl_gpio_range - each pin controller can provide subranges of + * the GPIO number space to be handled by the controller + * @node: list node for internal use + * @name: a name for the chip in this range + * @id: an ID number for the chip in this range + * @base: base offset of the GPIO range + * @npins: number of pins in the GPIO range, including the base number + * @gc: an optional pointer to a gpio_chip + */ +struct pinctrl_gpio_range { + struct list_head node; + const char *name; + unsigned int id; + unsigned int base; + unsigned int npins; + struct gpio_chip *gc; +}; + +/** + * struct pinctrl_ops - global pin control operations, to be implemented by + * pin controller drivers. + * @list_groups: list the number of selectable named groups available + * in this pinmux driver, the core will begin on 0 and call this + * repeatedly as long as it returns >= 0 to enumerate the groups + * @get_group_name: return the group name of the pin group + * @get_group_pins: return an array of pins corresponding to a certain + * group selector @pins, and the size of the array in @num_pins + * @pin_dbg_show: optional debugfs display hook that will provide per-device + * info for a certain pin in debugfs + */ +struct pinctrl_ops { + int (*list_groups) (struct pinctrl_dev *pctldev, unsigned selector); + const char *(*get_group_name) (struct pinctrl_dev *pctldev, + unsigned selector); + int (*get_group_pins) (struct pinctrl_dev *pctldev, + unsigned selector, + unsigned ** const pins, + unsigned * const num_pins); + void (*pin_dbg_show) (struct pinctrl_dev *pctldev, struct seq_file *s, + unsigned offset); +}; + +/** + * struct pinctrl_desc - pin controller descriptor, register this to pin + * control subsystem + * @name: name for the pin controller + * @pins: an array of pin descriptors describing all the pins handled by + * this pin controller + * @npins: number of descriptors in the array, usually just ARRAY_SIZE() + * of the pins field above + * @maxpin: since pin spaces may be sparse, there can he "holes" in the + * pin range, this attribute gives the maximum pin number in the + * total range. This should not be lower than npins for example, + * but may be equal to npins if you have no holes in the pin range. + * @pctlops: pin control operation vtable, to support global concepts like + * grouping of pins, this is optional. + * @pmxops: pinmux operation vtable, if you support pinmuxing in your driver + * @owner: module providing the pin controller, used for refcounting + */ +struct pinctrl_desc { + const char *name; + struct pinctrl_pin_desc const *pins; + unsigned int npins; + unsigned int maxpin; + struct pinctrl_ops *pctlops; + struct pinmux_ops *pmxops; + struct module *owner; +}; + +/* External interface to pin controller */ +extern struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc, + struct device *dev, void *driver_data); +extern void pinctrl_unregister(struct pinctrl_dev *pctldev); +extern bool pin_is_valid(struct pinctrl_dev *pctldev, int pin); +extern void pinctrl_add_gpio_range(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range); +extern void pinctrl_remove_gpio_range(struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range); +extern const char *pinctrl_dev_get_name(struct pinctrl_dev *pctldev); +extern void *pinctrl_dev_get_drvdata(struct pinctrl_dev *pctldev); +#else + + +/* Sufficiently stupid default function when pinctrl is not in use */ +static inline bool pin_is_valid(struct pinctrl_dev *pctldev, int pin) +{ + return pin >= 0; +} + +#endif /* !CONFIG_PINCTRL */ + +#endif /* __LINUX_PINCTRL_PINCTRL_H */ diff --git a/include/linux/pinctrl/pinmux.h b/include/linux/pinctrl/pinmux.h new file mode 100644 index 000000000000..3c430e797efc --- /dev/null +++ b/include/linux/pinctrl/pinmux.h @@ -0,0 +1,117 @@ +/* + * Interface the pinmux subsystem + * + * Copyright (C) 2011 ST-Ericsson SA + * Written on behalf of Linaro for ST-Ericsson + * Based on bits of regulator core, gpio core and clk core + * + * Author: Linus Walleij + * + * License terms: GNU General Public License (GPL) version 2 + */ +#ifndef __LINUX_PINCTRL_PINMUX_H +#define __LINUX_PINCTRL_PINMUX_H + +#include +#include +#include "pinctrl.h" + +/* This struct is private to the core and should be regarded as a cookie */ +struct pinmux; + +#ifdef CONFIG_PINMUX + +struct pinctrl_dev; + +/** + * struct pinmux_ops - pinmux operations, to be implemented by pin controller + * drivers that support pinmuxing + * @request: called by the core to see if a certain pin can be made available + * available for muxing. This is called by the core to acquire the pins + * before selecting any actual mux setting across a function. The driver + * is allowed to answer "no" by returning a negative error code + * @free: the reverse function of the request() callback, frees a pin after + * being requested + * @list_functions: list the number of selectable named functions available + * in this pinmux driver, the core will begin on 0 and call this + * repeatedly as long as it returns >= 0 to enumerate mux settings + * @get_function_name: return the function name of the muxing selector, + * called by the core to figure out which mux setting it shall map a + * certain device to + * @get_function_groups: return an array of groups names (in turn + * referencing pins) connected to a certain function selector. The group + * name can be used with the generic @pinctrl_ops to retrieve the + * actual pins affected. The applicable groups will be returned in + * @groups and the number of groups in @num_groups + * @enable: enable a certain muxing function with a certain pin group. The + * driver does not need to figure out whether enabling this function + * conflicts some other use of the pins in that group, such collisions + * are handled by the pinmux subsystem. The @func_selector selects a + * certain function whereas @group_selector selects a certain set of pins + * to be used. On simple controllers the latter argument may be ignored + * @disable: disable a certain muxing selector with a certain pin group + * @gpio_request_enable: requests and enables GPIO on a certain pin. + * Implement this only if you can mux every pin individually as GPIO. The + * affected GPIO range is passed along with an offset into that + * specific GPIO range - function selectors and pin groups are orthogonal + * to this, the core will however make sure the pins do not collide + */ +struct pinmux_ops { + int (*request) (struct pinctrl_dev *pctldev, unsigned offset); + int (*free) (struct pinctrl_dev *pctldev, unsigned offset); + int (*list_functions) (struct pinctrl_dev *pctldev, unsigned selector); + const char *(*get_function_name) (struct pinctrl_dev *pctldev, + unsigned selector); + int (*get_function_groups) (struct pinctrl_dev *pctldev, + unsigned selector, + const char * const **groups, + unsigned * const num_groups); + int (*enable) (struct pinctrl_dev *pctldev, unsigned func_selector, + unsigned group_selector); + void (*disable) (struct pinctrl_dev *pctldev, unsigned func_selector, + unsigned group_selector); + int (*gpio_request_enable) (struct pinctrl_dev *pctldev, + struct pinctrl_gpio_range *range, + unsigned offset); +}; + +/* External interface to pinmux */ +extern int pinmux_request_gpio(unsigned gpio); +extern void pinmux_free_gpio(unsigned gpio); +extern struct pinmux * __must_check pinmux_get(struct device *dev, const char *name); +extern void pinmux_put(struct pinmux *pmx); +extern int pinmux_enable(struct pinmux *pmx); +extern void pinmux_disable(struct pinmux *pmx); + +#else /* !CONFIG_PINMUX */ + +static inline int pinmux_request_gpio(unsigned gpio) +{ + return 0; +} + +static inline void pinmux_free_gpio(unsigned gpio) +{ +} + +static inline struct pinmux * __must_check pinmux_get(struct device *dev, const char *name) +{ + return NULL; +} + +static inline void pinmux_put(struct pinmux *pmx) +{ +} + +static inline int pinmux_enable(struct pinmux *pmx) +{ + return 0; +} + +static inline void pinmux_disable(struct pinmux *pmx) +{ +} + +#endif /* CONFIG_PINMUX */ + +#endif /* __LINUX_PINCTRL_PINMUX_H */ -- cgit v1.2.3 From b8a56e17e18cca2402b390c10b8d7f3cd0f6265b Mon Sep 17 00:00:00 2001 From: Yoshihiro Shimoda Date: Fri, 30 Sep 2011 20:07:38 +0900 Subject: usb: gadget: r8a66597-udc: add support for SUDMAC SH7757 has a USB function with internal DMA controller (SUDMAC). This patch supports the SUDMAC. The SUDMAC is incompatible with general-purpose DMAC. So, it doesn't use dmaengine. Signed-off-by: Yoshihiro Shimoda Signed-off-by: Felipe Balbi --- include/linux/usb/r8a66597.h | 60 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/r8a66597.h b/include/linux/usb/r8a66597.h index b6b8660d0c68..55805f9dcf21 100644 --- a/include/linux/usb/r8a66597.h +++ b/include/linux/usb/r8a66597.h @@ -48,6 +48,9 @@ struct r8a66597_platdata { /* (external controller only) set one = WR0_N shorted to WR1_N */ unsigned wr0_shorted_to_wr1:1; + + /* set one = using SUDMAC */ + unsigned sudmac:1; }; /* Register definitions */ @@ -417,5 +420,62 @@ struct r8a66597_platdata { #define USBSPD 0x00C0 #define RTPORT 0x0001 +/* SUDMAC registers */ +#define CH0CFG 0x00 +#define CH1CFG 0x04 +#define CH0BA 0x10 +#define CH1BA 0x14 +#define CH0BBC 0x18 +#define CH1BBC 0x1C +#define CH0CA 0x20 +#define CH1CA 0x24 +#define CH0CBC 0x28 +#define CH1CBC 0x2C +#define CH0DEN 0x30 +#define CH1DEN 0x34 +#define DSTSCLR 0x38 +#define DBUFCTRL 0x3C +#define DINTCTRL 0x40 +#define DINTSTS 0x44 +#define DINTSTSCLR 0x48 +#define CH0SHCTRL 0x50 +#define CH1SHCTRL 0x54 + +/* SUDMAC Configuration Registers */ +#define SENDBUFM 0x1000 /* b12: Transmit Buffer Mode */ +#define RCVENDM 0x0100 /* b8: Receive Data Transfer End Mode */ +#define LBA_WAIT 0x0030 /* b5-4: Local Bus Access Wait */ + +/* DMA Enable Registers */ +#define DEN 0x0001 /* b1: DMA Transfer Enable */ + +/* DMA Status Clear Register */ +#define CH1STCLR 0x0002 /* b2: Ch1 DMA Status Clear */ +#define CH0STCLR 0x0001 /* b1: Ch0 DMA Status Clear */ + +/* DMA Buffer Control Register */ +#define CH1BUFW 0x0200 /* b9: Ch1 DMA Buffer Data Transfer Enable */ +#define CH0BUFW 0x0100 /* b8: Ch0 DMA Buffer Data Transfer Enable */ +#define CH1BUFS 0x0002 /* b2: Ch1 DMA Buffer Data Status */ +#define CH0BUFS 0x0001 /* b1: Ch0 DMA Buffer Data Status */ + +/* DMA Interrupt Control Register */ +#define CH1ERRE 0x0200 /* b9: Ch1 SHwy Res Err Detect Int Enable */ +#define CH0ERRE 0x0100 /* b8: Ch0 SHwy Res Err Detect Int Enable */ +#define CH1ENDE 0x0002 /* b2: Ch1 DMA Transfer End Int Enable */ +#define CH0ENDE 0x0001 /* b1: Ch0 DMA Transfer End Int Enable */ + +/* DMA Interrupt Status Register */ +#define CH1ERRS 0x0200 /* b9: Ch1 SHwy Res Err Detect Int Status */ +#define CH0ERRS 0x0100 /* b8: Ch0 SHwy Res Err Detect Int Status */ +#define CH1ENDS 0x0002 /* b2: Ch1 DMA Transfer End Int Status */ +#define CH0ENDS 0x0001 /* b1: Ch0 DMA Transfer End Int Status */ + +/* DMA Interrupt Status Clear Register */ +#define CH1ERRC 0x0200 /* b9: Ch1 SHwy Res Err Detect Int Stat Clear */ +#define CH0ERRC 0x0100 /* b8: Ch0 SHwy Res Err Detect Int Stat Clear */ +#define CH1ENDC 0x0002 /* b2: Ch1 DMA Transfer End Int Stat Clear */ +#define CH0ENDC 0x0001 /* b1: Ch0 DMA Transfer End Int Stat Clear */ + #endif /* __LINUX_USB_R8A66597_H */ -- cgit v1.2.3 From 089b837a39552ee49a4ea4c188e8c3517473f10c Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Mon, 10 Oct 2011 09:43:44 +0300 Subject: usb: gadget: fix typo for default U1/U2 exit latencies s/DEFULT/DEFAULT/, no functional changes. Signed-off-by: Felipe Balbi --- include/linux/usb/gadget.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 087f4b931833..1d3a67523ffc 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -437,9 +437,9 @@ static inline void usb_ep_fifo_flush(struct usb_ep *ep) struct usb_dcd_config_params { __u8 bU1devExitLat; /* U1 Device exit Latency */ -#define USB_DEFULT_U1_DEV_EXIT_LAT 0x01 /* Less then 1 microsec */ +#define USB_DEFAULT_U1_DEV_EXIT_LAT 0x01 /* Less then 1 microsec */ __le16 bU2DevExitLat; /* U2 Device exit Latency */ -#define USB_DEFULT_U2_DEV_EXIT_LAT 0x1F4 /* Less then 500 microsec */ +#define USB_DEFAULT_U2_DEV_EXIT_LAT 0x1F4 /* Less then 500 microsec */ }; -- cgit v1.2.3 From 11935de5579a5d01b3c89d69b4fc7a38b4dd8eae Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 10 Oct 2011 22:01:28 -0700 Subject: usb: gadget: renesas_usbhs: change usbhsc_bus_ctrl() to usbsc_set_buswait() renesas_usbhs will have register DVSTCTR control function for HOST support. This patch changes usbhsc_bus_ctrl() to usbsc_set_buswait(), to remove DVSTCTR access from it, Signed-off-by: Kuninori Morimoto Signed-off-by: Felipe Balbi --- include/linux/usb/renesas_usbhs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index 8977431259c6..959af02d3af6 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -101,6 +101,8 @@ struct renesas_usbhs_driver_param { * option: * * for BUSWAIT :: BWAIT + * see + * renesas_usbhs/common.c :: usbhsc_set_buswait() * */ int buswait_bwait; -- cgit v1.2.3 From 258485d9904703c4cb3a2b3ee38fe2a0cbf01f48 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 10 Oct 2011 22:01:40 -0700 Subject: usb: gadget: renesas_usbhs: add bus control functions this patch add DVSTCTR control function for HOST support Signed-off-by: Kuninori Morimoto Signed-off-by: Felipe Balbi --- include/linux/usb/renesas_usbhs.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index 959af02d3af6..040d8bb2b5a2 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -82,6 +82,13 @@ struct renesas_usbhs_platform_callback { * get VBUS status function. */ int (*get_vbus)(struct platform_device *pdev); + + /* + * option: + * + * VBUS control is needed for Host + */ + int (*set_vbus)(struct platform_device *pdev, int enable); }; /* -- cgit v1.2.3 From f427eb64f4c5433a91da5eb139970dd5cbad9082 Mon Sep 17 00:00:00 2001 From: Kuninori Morimoto Date: Mon, 10 Oct 2011 22:06:12 -0700 Subject: usb: gadget: renesas_usbhs: support otg pin control some renesas_usbhs device is supporting OTG external device interface. In that device, it is necessary to control PWEN/EXTLP on DVSTCTR. This patch support it. But renesas_usbhs driver doesn't have OTG support for now. Signed-off-by: Kuninori Morimoto Signed-off-by: Felipe Balbi --- include/linux/usb/renesas_usbhs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index 040d8bb2b5a2..e5a40c318548 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -136,6 +136,11 @@ struct renesas_usbhs_driver_param { * pio <--> dma border. */ int pio_dma_border; /* default is 64byte */ + + /* + * option: + */ + u32 has_otg:1; /* for controlling PWEN/EXTLP */ }; /* -- cgit v1.2.3 From dde34cc5019b51088c18ca789d4b1a20cf9bc617 Mon Sep 17 00:00:00 2001 From: Neil Zhang Date: Wed, 12 Oct 2011 16:49:24 +0800 Subject: usb: gadget: mv_udc: refine the driver structure This patch do the following things: 1. Add header and Copyright for marvell usb driver. 2. Add mv_usb.h in include/linux/platform_data, make the driver fits all the marvell platform using the same ChipIdea usb ip. 3. Some SOC may has mutiple clock sources, so let me define it in mv_usb_platform_data and give two helper functions named udc_clock_enable/udc_clock_disable to deal with the clocks. 4. Different SOCs will have some difference in PHY initialization, so we will remove file mv_udc_phy.c and add two funtions in mv_usb_platform_data, let the platform relative driver to realize it. 5. Rewrite probe function according to the modification list above. Find it will kernel panic when probe failed. The root cause is as follows: When probe failed, the error handle may call device_unregister() which in return will call gadget_release.In current code, gadget_release have two issues: 1: the_controller is a NULL pointer. 2: if we free udc here, then the following code in probe will access NULL pointer. Signed-off-by: Neil Zhang Signed-off-by: Felipe Balbi --- include/linux/platform_data/mv_usb.h | 50 ++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) create mode 100644 include/linux/platform_data/mv_usb.h (limited to 'include/linux') diff --git a/include/linux/platform_data/mv_usb.h b/include/linux/platform_data/mv_usb.h new file mode 100644 index 000000000000..e9d9149ddf38 --- /dev/null +++ b/include/linux/platform_data/mv_usb.h @@ -0,0 +1,50 @@ +/* + * Copyright (C) 2011 Marvell International Ltd. All rights reserved. + * + * 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 __MV_PLATFORM_USB_H +#define __MV_PLATFORM_USB_H + +enum pxa_ehci_type { + EHCI_UNDEFINED = 0, + PXA_U2OEHCI, /* pxa 168, 9xx */ + PXA_SPH, /* pxa 168, 9xx SPH */ + MMP3_HSIC, /* mmp3 hsic */ + MMP3_FSIC, /* mmp3 fsic */ +}; + +enum { + MV_USB_MODE_OTG, + MV_USB_MODE_HOST, +}; + +enum { + VBUS_LOW = 0, + VBUS_HIGH = 1 << 0, +}; + +struct mv_usb_addon_irq { + unsigned int irq; + int (*poll)(void); +}; + +struct mv_usb_platform_data { + unsigned int clknum; + char **clkname; + struct mv_usb_addon_irq *id; /* Only valid for OTG. ID pin change*/ + struct mv_usb_addon_irq *vbus; /* valid for OTG/UDC. VBUS change*/ + + /* only valid for HCD. OTG or Host only*/ + unsigned int mode; + + int (*phy_init)(unsigned int regbase); + void (*phy_deinit)(unsigned int regbase); + int (*set_vbus)(unsigned int vbus); +}; + +#endif -- cgit v1.2.3 From 2a77c46de1e3dace73745015635ebbc648eca69c Mon Sep 17 00:00:00 2001 From: ShuoX Liu Date: Wed, 10 Aug 2011 23:01:26 +0200 Subject: PM / Suspend: Add statistics debugfs file for suspend to RAM Record S3 failure time about each reason and the latest two failed devices' names in S3 progress. We can check it through 'suspend_stats' entry in debugfs. The motivation of the patch: We are enabling power features on Medfield. Comparing with PC/notebook, a mobile enters/exits suspend-2-ram (we call it s3 on Medfield) far more frequently. If it can't enter suspend-2-ram in time, the power might be used up soon. We often find sometimes, a device suspend fails. Then, system retries s3 over and over again. As display is off, testers and developers don't know what happens. Some testers and developers complain they don't know if system tries suspend-2-ram, and what device fails to suspend. They need such info for a quick check. The patch adds suspend_stats under debugfs for users to check suspend to RAM statistics quickly. If not using this patch, we have other methods to get info about what device fails. One is to turn on CONFIG_PM_DEBUG, but users would get too much info and testers need recompile the system. In addition, dynamic debug is another good tool to dump debug info. But it still doesn't match our utilization scenario closely. 1) user need write a user space parser to process the syslog output; 2) Our testing scenario is we leave the mobile for at least hours. Then, check its status. No serial console available during the testing. One is because console would be suspended, and the other is serial console connecting with spi or HSU devices would consume power. These devices are powered off at suspend-2-ram. Signed-off-by: ShuoX Liu Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 52 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 6bbcef22e105..76f42e49b72d 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -34,6 +34,58 @@ typedef int __bitwise suspend_state_t; #define PM_SUSPEND_MEM ((__force suspend_state_t) 3) #define PM_SUSPEND_MAX ((__force suspend_state_t) 4) +enum suspend_stat_step { + SUSPEND_FREEZE = 1, + SUSPEND_PREPARE, + SUSPEND_SUSPEND, + SUSPEND_SUSPEND_NOIRQ, + SUSPEND_RESUME_NOIRQ, + SUSPEND_RESUME +}; + +struct suspend_stats { + int success; + int fail; + int failed_freeze; + int failed_prepare; + int failed_suspend; + int failed_suspend_noirq; + int failed_resume; + int failed_resume_noirq; +#define REC_FAILED_NUM 2 + int last_failed_dev; + char failed_devs[REC_FAILED_NUM][40]; + int last_failed_errno; + int errno[REC_FAILED_NUM]; + int last_failed_step; + enum suspend_stat_step failed_steps[REC_FAILED_NUM]; +}; + +extern struct suspend_stats suspend_stats; + +static inline void dpm_save_failed_dev(const char *name) +{ + strlcpy(suspend_stats.failed_devs[suspend_stats.last_failed_dev], + name, + sizeof(suspend_stats.failed_devs[0])); + suspend_stats.last_failed_dev++; + suspend_stats.last_failed_dev %= REC_FAILED_NUM; +} + +static inline void dpm_save_failed_errno(int err) +{ + suspend_stats.errno[suspend_stats.last_failed_errno] = err; + suspend_stats.last_failed_errno++; + suspend_stats.last_failed_errno %= REC_FAILED_NUM; +} + +static inline void dpm_save_failed_step(enum suspend_stat_step step) +{ + suspend_stats.failed_steps[suspend_stats.last_failed_step] = step; + suspend_stats.last_failed_step++; + suspend_stats.last_failed_step %= REC_FAILED_NUM; +} + /** * struct platform_suspend_ops - Callbacks for managing platform dependent * system sleep states. -- cgit v1.2.3 From 85055dd805f0822f13f736bee2a521e222c38293 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Wed, 17 Aug 2011 20:42:24 +0200 Subject: PM / Hibernate: Include storage keys in hibernation image on s390 For s390 there is one additional byte associated with each page, the storage key. This byte contains the referenced and changed bits and needs to be included into the hibernation image. If the storage keys are not restored to their previous state all original pages would appear to be dirty. This can cause inconsistencies e.g. with read-only filesystems. Signed-off-by: Martin Schwidefsky Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 76f42e49b72d..46f3548aef2d 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -386,4 +386,38 @@ static inline void unlock_system_sleep(void) } #endif +#ifdef CONFIG_ARCH_SAVE_PAGE_KEYS +/* + * The ARCH_SAVE_PAGE_KEYS functions can be used by an architecture + * to save/restore additional information to/from the array of page + * frame numbers in the hibernation image. For s390 this is used to + * save and restore the storage key for each page that is included + * in the hibernation image. + */ +unsigned long page_key_additional_pages(unsigned long pages); +int page_key_alloc(unsigned long pages); +void page_key_free(void); +void page_key_read(unsigned long *pfn); +void page_key_memorize(unsigned long *pfn); +void page_key_write(void *address); + +#else /* !CONFIG_ARCH_SAVE_PAGE_KEYS */ + +static inline unsigned long page_key_additional_pages(unsigned long pages) +{ + return 0; +} + +static inline int page_key_alloc(unsigned long pages) +{ + return 0; +} + +static inline void page_key_free(void) {} +static inline void page_key_read(unsigned long *pfn) {} +static inline void page_key_memorize(unsigned long *pfn) {} +static inline void page_key_write(void *address) {} + +#endif /* !CONFIG_ARCH_SAVE_PAGE_KEYS */ + #endif /* _LINUX_SUSPEND_H */ -- cgit v1.2.3 From 37cce26b32142f09a8967f6d238178af654b20de Mon Sep 17 00:00:00 2001 From: H Hartley Sweeten Date: Wed, 21 Sep 2011 22:47:55 +0200 Subject: PM / VT: Cleanup #if defined uglyness and fix compile error Introduce the config option CONFIG_VT_CONSOLE_SLEEP in order to cleanup the #if defined ugliness for the vt suspend support functions. Note that CONFIG_VT_CONSOLE is already dependant on CONFIG_VT. The function pm_set_vt_switch is actually dependant on CONFIG_VT and not CONFIG_PM_SLEEP. This fixes a compile error when CONFIG_PM_SLEEP is not set: drivers/tty/vt/vt_ioctl.c:1794: error: redefinition of 'pm_set_vt_switch' include/linux/suspend.h:17: error: previous definition of 'pm_set_vt_switch' was here Also, remove the incorrect path from the comment in console.c. [rjw: Replaced #if defined() with #ifdef in suspend.h.] Signed-off-by: H Hartley Sweeten Acked-by: Arnd Bergmann Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 46f3548aef2d..57a692432f8a 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -8,15 +8,18 @@ #include #include -#if defined(CONFIG_PM_SLEEP) && defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE) +#ifdef CONFIG_VT extern void pm_set_vt_switch(int); -extern int pm_prepare_console(void); -extern void pm_restore_console(void); #else static inline void pm_set_vt_switch(int do_switch) { } +#endif +#ifdef CONFIG_VT_CONSOLE_SLEEP +extern int pm_prepare_console(void); +extern void pm_restore_console(void); +#else static inline int pm_prepare_console(void) { return 0; -- cgit v1.2.3 From 2aede851ddf08666f68ffc17be446420e9d2a056 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 26 Sep 2011 20:32:27 +0200 Subject: PM / Hibernate: Freeze kernel threads after preallocating memory There is a problem with the current ordering of hibernate code which leads to deadlocks in some filesystems' memory shrinkers. Namely, some filesystems use freezable kernel threads that are inactive when the hibernate memory preallocation is carried out. Those same filesystems use memory shrinkers that may be triggered by the hibernate memory preallocation. If those memory shrinkers wait for the frozen kernel threads, the hibernate process deadlocks (this happens with XFS, for one example). Apparently, it is not technically viable to redesign the filesystems in question to avoid the situation described above, so the only possible solution of this issue is to defer the freezing of kernel threads until the hibernate memory preallocation is done, which is implemented by this change. Unfortunately, this requires the memory preallocation to be done before the "prepare" stage of device freeze, so after this change the only way drivers can allocate additional memory for their freeze routines in a clean way is to use PM notifiers. Reported-by: Christoph Signed-off-by: Rafael J. Wysocki --- include/linux/freezer.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 1effc8b56b4e..aa56cf31f7ff 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -49,6 +49,7 @@ extern int thaw_process(struct task_struct *p); extern void refrigerator(void); extern int freeze_processes(void); +extern int freeze_kernel_threads(void); extern void thaw_processes(void); static inline int try_to_freeze(void) @@ -171,7 +172,8 @@ static inline void clear_freeze_flag(struct task_struct *p) {} static inline int thaw_process(struct task_struct *p) { return 1; } static inline void refrigerator(void) {} -static inline int freeze_processes(void) { BUG(); return 0; } +static inline int freeze_processes(void) { return -ENOSYS; } +static inline int freeze_kernel_threads(void) { return -ENOSYS; } static inline void thaw_processes(void) {} static inline int try_to_freeze(void) { return 0; } -- cgit v1.2.3 From 9bab0b7fbaceec47d32db51cd9e59c82fb071f5a Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Mon, 3 Oct 2011 15:37:00 +0100 Subject: genirq: Add IRQF_RESUME_EARLY and resume such IRQs earlier This adds a mechanism to resume selected IRQs during syscore_resume instead of dpm_resume_noirq. Under Xen we need to resume IRQs associated with IPIs early enough that the resched IPI is unmasked and we can therefore schedule ourselves out of the stop_machine where the suspend/resume takes place. This issue was introduced by 676dc3cf5bc3 "xen: Use IRQF_FORCE_RESUME". Signed-off-by: Ian Campbell Cc: Rafael J. Wysocki Cc: Jeremy Fitzhardinge Cc: xen-devel Cc: Konrad Rzeszutek Wilk Link: http://lkml.kernel.org/r/1318713254.11016.52.camel@dagon.hellion.org.uk Cc: stable@kernel.org (at least to 2.6.32.y) Signed-off-by: Thomas Gleixner --- include/linux/interrupt.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 664544ff77d5..a64b00e286f5 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -59,6 +59,8 @@ * IRQF_NO_SUSPEND - Do not disable this IRQ during suspend * IRQF_FORCE_RESUME - Force enable it on resume even if IRQF_NO_SUSPEND is set * IRQF_NO_THREAD - Interrupt cannot be threaded + * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device + * resume time. */ #define IRQF_DISABLED 0x00000020 #define IRQF_SAMPLE_RANDOM 0x00000040 @@ -72,6 +74,7 @@ #define IRQF_NO_SUSPEND 0x00004000 #define IRQF_FORCE_RESUME 0x00008000 #define IRQF_NO_THREAD 0x00010000 +#define IRQF_EARLY_RESUME 0x00020000 #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) -- cgit v1.2.3 From c1225158a8dad9e9d5eee8a17dbbd9c7cda05ab9 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Thu, 22 Sep 2011 21:50:10 -0400 Subject: SUNRPC/NFS: make rpc pipe upcall generic The same function is used by idmap, gss and blocklayout code. Make it generic. Signed-off-by: Peng Tao Signed-off-by: Jim Rees Cc: stable@kernel.org [3.0] Signed-off-by: Trond Myklebust --- include/linux/sunrpc/rpc_pipe_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index cf14db975da0..e4ea43058d8f 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -44,6 +44,8 @@ RPC_I(struct inode *inode) return container_of(inode, struct rpc_inode, vfs_inode); } +extern ssize_t rpc_pipe_generic_upcall(struct file *, struct rpc_pipe_msg *, + char __user *, size_t); extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *); struct rpc_clnt; -- cgit v1.2.3 From d77385f23830ee6c400569bac8b37e6eb3b7d360 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 17 Oct 2011 16:08:10 -0700 Subject: SUNRPC: Fix rpc_sockaddr2uaddr rpc_sockaddr2uaddr is only used by net/sunrpc/rpcb_clnt.c, where it is used in a non-blockable context in at least one case. Add non-blocking capability by adding a gfp_t argument Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index db7bcaf7c5bd..d926fd1a5313 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -9,6 +9,7 @@ #ifndef _LINUX_SUNRPC_CLNT_H #define _LINUX_SUNRPC_CLNT_H +#include #include #include #include @@ -161,7 +162,7 @@ const char *rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t); size_t rpc_ntop(const struct sockaddr *, char *, const size_t); size_t rpc_pton(const char *, const size_t, struct sockaddr *, const size_t); -char * rpc_sockaddr2uaddr(const struct sockaddr *); +char * rpc_sockaddr2uaddr(const struct sockaddr *, gfp_t); size_t rpc_uaddr2sockaddr(const char *, const size_t, struct sockaddr *, const size_t); -- cgit v1.2.3 From a9a4a87a5942e9271523197a90aaa82349c818fb Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 17 Oct 2011 16:08:46 -0700 Subject: NFS: Use the inode->i_version to cache NFSv4 change attribute information 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 eaac770f886e..60a137b7f171 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -149,7 +149,6 @@ struct nfs_inode { unsigned long read_cache_jiffies; unsigned long attrtimeo; unsigned long attrtimeo_timestamp; - __u64 change_attr; /* v4 only */ unsigned long attr_gencount; /* "Generation counter" for the attribute cache. This is -- cgit v1.2.3 From 27a90700a4275c5178b883b65927affdafa5185c Mon Sep 17 00:00:00 2001 From: Kai Jiang Date: Mon, 17 Oct 2011 20:50:20 +0200 Subject: uio: Support physical addresses >32 bits on 32-bit systems To support >32-bit physical addresses for UIO_MEM_PHYS type we need to extend the width of 'addr' in struct uio_mem. Numerous platforms like embedded PPC, ARM, and X86 have support for systems with larger physical address than logical. Since 'addr' may contain a physical, logical, or virtual address the easiest solution is to just change the type to 'phys_addr_t' which should always be greater than or equal to the sizeof(void *) such that it can properly hold any of the address types. For physical address we can support up to a 44-bit physical address on a typical 32-bit system as we utilize remap_pfn_range() for the mapping of the memory region and pfn's are represnted by shifting the address by the page size (typically 4k). Signed-off-by: Kai Jiang Signed-off-by: Minghuan Lian Signed-off-by: Kumar Gala Signed-off-by: Hans J. Koch Signed-off-by: Greg Kroah-Hartman --- include/linux/uio_driver.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h index 665517c05eaf..fd99ff9298c6 100644 --- a/include/linux/uio_driver.h +++ b/include/linux/uio_driver.h @@ -23,7 +23,10 @@ struct uio_map; /** * struct uio_mem - description of a UIO memory region * @name: name of the memory region for identification - * @addr: address of the device's memory + * @addr: address of the device's memory (phys_addr is used since + * addr can be logical, virtual, or physical & phys_addr_t + * should always be large enough to handle any of the + * address types) * @size: size of IO * @memtype: type of memory addr points to * @internal_addr: ioremap-ped version of addr, for driver internal use @@ -31,7 +34,7 @@ struct uio_map; */ struct uio_mem { const char *name; - unsigned long addr; + phys_addr_t addr; unsigned long size; int memtype; void __iomem *internal_addr; -- cgit v1.2.3 From 07613b0b5ef8570033aa806d1731dce599862223 Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Tue, 4 Oct 2011 14:13:15 -0700 Subject: dynamic_debug: consolidate repetitive struct _ddebug descriptor definitions Replace the repetitive struct _ddebug descriptor definitions with a new DECLARE_DYNAMIC_DEBUG_META_DATA(name, fmt) macro. [akpm@linux-foundation.org: s/DECLARE/DEFINE/] Signed-off-by: Jason Baron Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/dynamic_debug.h | 64 +++++++++++++++++++++++-------------------- 1 file changed, 35 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index feaac1ee3001..13aae8087b56 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -54,35 +54,41 @@ extern int __dynamic_netdev_dbg(struct _ddebug *descriptor, const char *fmt, ...) __attribute__ ((format (printf, 3, 4))); -#define dynamic_pr_debug(fmt, ...) do { \ - static struct _ddebug descriptor \ - __used \ - __attribute__((section("__verbose"), aligned(8))) = \ - { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ - _DPRINTK_FLAGS_DEFAULT }; \ - if (unlikely(descriptor.enabled)) \ - __dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \ - } while (0) - -#define dynamic_dev_dbg(dev, fmt, ...) do { \ - static struct _ddebug descriptor \ - __used \ - __attribute__((section("__verbose"), aligned(8))) = \ - { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ - _DPRINTK_FLAGS_DEFAULT }; \ - if (unlikely(descriptor.enabled)) \ - __dynamic_dev_dbg(&descriptor, dev, fmt, ##__VA_ARGS__); \ - } while (0) - -#define dynamic_netdev_dbg(dev, fmt, ...) do { \ - static struct _ddebug descriptor \ - __used \ - __attribute__((section("__verbose"), aligned(8))) = \ - { KBUILD_MODNAME, __func__, __FILE__, fmt, __LINE__, \ - _DPRINTK_FLAGS_DEFAULT }; \ - if (unlikely(descriptor.enabled)) \ - __dynamic_netdev_dbg(&descriptor, dev, fmt, ##__VA_ARGS__);\ - } while (0) +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) \ + static struct _ddebug __used __aligned(8) \ + __attribute__((section("__verbose"))) name = { \ + .modname = KBUILD_MODNAME, \ + .function = __func__, \ + .filename = __FILE__, \ + .format = (fmt), \ + .lineno = __LINE__, \ + .flags = _DPRINTK_FLAGS_DEFAULT, \ + .enabled = false, \ + } + +#define dynamic_pr_debug(fmt, ...) \ +do { \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + if (unlikely(descriptor.enabled)) \ + __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ + ##__VA_ARGS__); \ +} while (0) + +#define dynamic_dev_dbg(dev, fmt, ...) \ +do { \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + if (unlikely(descriptor.enabled)) \ + __dynamic_dev_dbg(&descriptor, dev, fmt, \ + ##__VA_ARGS__); \ +} while (0) + +#define dynamic_netdev_dbg(dev, fmt, ...) \ +do { \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + if (unlikely(descriptor.enabled)) \ + __dynamic_netdev_dbg(&descriptor, dev, fmt, \ + ##__VA_ARGS__); \ +} while (0) #else -- cgit v1.2.3 From 8193c4290620d9b2a6ac116719f11aa99053a90d Mon Sep 17 00:00:00 2001 From: Thomas Meyer Date: Wed, 5 Oct 2011 23:13:13 +0200 Subject: tty: Support compat_ioctl get/set termios_locked When running a Fedora 15 (x86) on an x86_64 kernel, in the boot process plymouthd complains about those two missing ioctls: [ 2.581783] ioctl32(plymouthd:186): Unknown cmd fd(10) cmd(00005457){t:'T';sz:0} arg(ffb6a5d0) on /dev/tty1 [ 2.581803] ioctl32(plymouthd:186): Unknown cmd fd(10) cmd(00005456){t:'T';sz:0} arg(ffb6a680) on /dev/tty1 both ioctl functions work on the 'struct termios' resp. 'struct termios2', which has the same size (36 bytes resp. 44 bytes) on x86 and x86_64, so it's just a matter of converting the pointer from userland. Signed-off-by: Thomas Meyer Cc: Arnd Bergmann Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 0ad68889fc1a..64c12a3e65f0 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -579,6 +579,8 @@ extern int __init tty_init(void); /* tty_ioctl.c */ extern int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); +extern long n_tty_compat_ioctl_helper(struct tty_struct *tty, struct file *file, + unsigned int cmd, unsigned long arg); /* serial.c */ -- cgit v1.2.3 From fa90e1c935472281de314e6d7c9a37db9cbc2e4e Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Wed, 12 Oct 2011 11:32:43 +0200 Subject: TTY: make tty_add_file non-failing If tty_add_file fails at the point it is now, we have to revert all the changes we did to the tty. It means either decrease all refcounts if this was a tty reopen or delete the tty if it was newly allocated. There was a try to fix this in v3.0-rc2 using tty_release in 0259894c7 (TTY: fix fail path in tty_open). But instead it introduced a NULL dereference. It's because tty_release dereferences filp->private_data, but that one is set even in our tty_add_file. And when tty_add_file fails, it's still NULL/garbage. Hence tty_release cannot be called there. To circumvent the original leak (and the current NULL deref) we split tty_add_file into two functions, making the latter non-failing. In that case we may do the former early in open, where handling failures is easy. The latter stays as it is now. So there is no change in functionality. The original bug (leak) was introduced by f573bd176 (tty: Remove __GFP_NOFAIL from tty_add_file()). Thanks Dan for reporting this. Later, we may split tty_release into more functions and call only some of them in this fail path instead. (If at all possible.) Introduced-in: v2.6.37-rc2 Signed-off-by: Jiri Slaby Reported-by: Dan Carpenter Cc: stable Cc: Alan Cox Cc: Pekka Enberg Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 64c12a3e65f0..ff2925aa4e79 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -471,7 +471,9 @@ extern void proc_clear_tty(struct task_struct *p); extern struct tty_struct *get_current_tty(void); extern void tty_default_fops(struct file_operations *fops); extern struct tty_struct *alloc_tty_struct(void); -extern int tty_add_file(struct tty_struct *tty, struct file *file); +extern int tty_alloc_file(struct file *file); +extern void tty_add_file(struct tty_struct *tty, struct file *file); +extern void tty_free_file(struct file *file); extern void free_tty_struct(struct tty_struct *tty); extern void initialize_tty_struct(struct tty_struct *tty, struct tty_driver *driver, int idx); -- cgit v1.2.3 From 0c2e53f11a6dae9e3af5f50f5ad0382e7c3e0cfa Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Oct 2011 16:11:22 -0700 Subject: NFS: Remove the unused "lookupfh()" version of nfs4_proc_lookup() ...and also remove the associated nfs_v4_clientops entry. Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index abd615d74a29..1e31e1c8655b 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1197,9 +1197,6 @@ struct nfs_rpc_ops { int (*getroot) (struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); - int (*lookupfh)(struct nfs_server *, struct nfs_fh *, - struct qstr *, struct nfs_fh *, - struct nfs_fattr *); int (*getattr) (struct nfs_server *, struct nfs_fh *, struct nfs_fattr *); int (*setattr) (struct dentry *, struct nfs_fattr *, -- cgit v1.2.3 From 8b289b2c2355c3bea75f3e499b4aa251a3191382 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Wed, 19 Oct 2011 11:52:12 -0400 Subject: nfsd4: implement new 4.1 open reclaim types Signed-off-by: J. Bruce Fields --- include/linux/nfs4.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index b875b0324fc0..32345c2805c0 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -410,7 +410,10 @@ enum open_claim_type4 { NFS4_OPEN_CLAIM_NULL = 0, NFS4_OPEN_CLAIM_PREVIOUS = 1, NFS4_OPEN_CLAIM_DELEGATE_CUR = 2, - NFS4_OPEN_CLAIM_DELEGATE_PREV = 3 + NFS4_OPEN_CLAIM_DELEGATE_PREV = 3, + NFS4_OPEN_CLAIM_FH = 4, /* 4.1 */ + NFS4_OPEN_CLAIM_DELEG_CUR_FH = 5, /* 4.1 */ + NFS4_OPEN_CLAIM_DELEG_PREV_FH = 6, /* 4.1 */ }; enum opentype4 { -- cgit v1.2.3 From a1940805d0636c6cdf37636f55b43b9681d53e73 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 19 Oct 2011 12:17:29 -0700 Subject: NFS: Get rid of the unused nfs_read_data->flags field Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 1e31e1c8655b..c1cceb83f709 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1133,7 +1133,6 @@ struct nfs_page; #define NFS_PAGEVEC_SIZE (8U) struct nfs_read_data { - int flags; struct rpc_task task; struct inode *inode; struct rpc_cred *cred; -- cgit v1.2.3 From b8ef70639b609c5d12c618f1d9ffae6ac13aebe3 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 19 Oct 2011 12:17:29 -0700 Subject: NFS: Get rid of the unused nfs_write_data->flags field Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index c1cceb83f709..c74595ba7094 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1155,7 +1155,6 @@ struct nfs_read_data { }; struct nfs_write_data { - int flags; struct rpc_task task; struct inode *inode; struct rpc_cred *cred; -- cgit v1.2.3 From fba730050d1246d0e6ef44e026e0b584732fec2b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Wed, 19 Oct 2011 12:17:29 -0700 Subject: NFS: Don't rely on PageError in nfs_readpage_release_partial Don't rely on the PageError flag to tell us if one of the partial reads of the page failed. Instead, replace that with a dedicated flag in the struct nfs_page. Then clean out redundant uses of the PageError flag: the VM no longer checks it for reads. Signed-off-by: Trond Myklebust --- include/linux/nfs_page.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index e2791a27a901..ab465fe8c3d6 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -34,6 +34,7 @@ enum { PG_NEED_COMMIT, PG_NEED_RESCHED, PG_PNFS_COMMIT, + PG_PARTIAL_READ_FAILED, }; struct nfs_inode; -- cgit v1.2.3 From a5818a8bd095a08cfb1871b63af9c8bed103e4b9 Mon Sep 17 00:00:00 2001 From: Stephen Warren Date: Wed, 19 Oct 2011 16:19:25 -0600 Subject: pinctrl: get_group_pins() const fixes get_group_pins() "returns" a pointer to an array of const objects, through a pointer parameter. Fix the prototype so what's pointed at by the returned pointer is const, rather than the function parameter being const. This also allows the removal of a cast in each of the two current pinmux drivers. Signed-off-by: Stephen Warren Signed-off-by: Linus Walleij --- include/linux/pinctrl/pinctrl.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h index 4f8d2089acce..3605e947fa90 100644 --- a/include/linux/pinctrl/pinctrl.h +++ b/include/linux/pinctrl/pinctrl.h @@ -75,8 +75,8 @@ struct pinctrl_ops { unsigned selector); int (*get_group_pins) (struct pinctrl_dev *pctldev, unsigned selector, - unsigned ** const pins, - unsigned * const num_pins); + const unsigned **pins, + unsigned *num_pins); void (*pin_dbg_show) (struct pinctrl_dev *pctldev, struct seq_file *s, unsigned offset); }; -- cgit v1.2.3 From 4ca46ff3e0d8c234cb40ebb6457653b59584426c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 16 Oct 2011 23:34:36 +0200 Subject: PM / Sleep: Mark devices involved in wakeup signaling during suspend The generic PM domains code in drivers/base/power/domain.c has to avoid powering off domains that provide power to wakeup devices during system suspend. Currently, however, this only works for wakeup devices directly belonging to the given domain and not for their children (or the children of their children and so on). Thus, if there's a wakeup device whose parent belongs to a power domain handled by the generic PM domains code, the domain will be powered off during system suspend preventing the device from signaling wakeup. To address this problem introduce a device flag, power.wakeup_path, that will be set during system suspend for all wakeup devices, their parents, the parents of their parents and so on. This way, all wakeup paths in the device hierarchy will be marked and the generic PM domains code will only need to avoid powering off domains containing devices whose power.wakeup_path is set. Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index f25682477f08..74711a9c2f69 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -448,6 +448,7 @@ struct dev_pm_info { struct list_head entry; struct completion completion; struct wakeup_source *wakeup; + bool wakeup_path:1; #else unsigned int should_wakeup:1; #endif -- cgit v1.2.3 From 9d97e5c81e15afaef65d00f077f863c94f750839 Mon Sep 17 00:00:00 2001 From: Donggeun Kim Date: Wed, 7 Sep 2011 18:49:08 +0900 Subject: hwmon: Add driver for EXYNOS4 TMU This patch allows to read temperature from TMU(Thermal Management Unit) of SAMSUNG EXYNOS4 series of SoC. Signed-off-by: Donggeun Kim Signed-off-by: MyungJoo Ham Signed-off-by: Kyungmin Park Signed-off-by: Guenter Roeck --- include/linux/platform_data/exynos4_tmu.h | 83 +++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) create mode 100644 include/linux/platform_data/exynos4_tmu.h (limited to 'include/linux') diff --git a/include/linux/platform_data/exynos4_tmu.h b/include/linux/platform_data/exynos4_tmu.h new file mode 100644 index 000000000000..39e038cca590 --- /dev/null +++ b/include/linux/platform_data/exynos4_tmu.h @@ -0,0 +1,83 @@ +/* + * exynos4_tmu.h - Samsung EXYNOS4 TMU (Thermal Management Unit) + * + * Copyright (C) 2011 Samsung Electronics + * Donggeun Kim + * + * 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 _LINUX_EXYNOS4_TMU_H +#define _LINUX_EXYNOS4_TMU_H + +enum calibration_type { + TYPE_ONE_POINT_TRIMMING, + TYPE_TWO_POINT_TRIMMING, + TYPE_NONE, +}; + +/** + * struct exynos4_tmu_platform_data + * @threshold: basic temperature for generating interrupt + * 25 <= threshold <= 125 [unit: degree Celsius] + * @trigger_levels: array for each interrupt levels + * [unit: degree Celsius] + * 0: temperature for trigger_level0 interrupt + * condition for trigger_level0 interrupt: + * current temperature > threshold + trigger_levels[0] + * 1: temperature for trigger_level1 interrupt + * condition for trigger_level1 interrupt: + * current temperature > threshold + trigger_levels[1] + * 2: temperature for trigger_level2 interrupt + * condition for trigger_level2 interrupt: + * current temperature > threshold + trigger_levels[2] + * 3: temperature for trigger_level3 interrupt + * condition for trigger_level3 interrupt: + * current temperature > threshold + trigger_levels[3] + * @trigger_level0_en: + * 1 = enable trigger_level0 interrupt, + * 0 = disable trigger_level0 interrupt + * @trigger_level1_en: + * 1 = enable trigger_level1 interrupt, + * 0 = disable trigger_level1 interrupt + * @trigger_level2_en: + * 1 = enable trigger_level2 interrupt, + * 0 = disable trigger_level2 interrupt + * @trigger_level3_en: + * 1 = enable trigger_level3 interrupt, + * 0 = disable trigger_level3 interrupt + * @gain: gain of amplifier in the positive-TC generator block + * 0 <= gain <= 15 + * @reference_voltage: reference voltage of amplifier + * in the positive-TC generator block + * 0 <= reference_voltage <= 31 + * @cal_type: calibration type for temperature + * + * This structure is required for configuration of exynos4_tmu driver. + */ +struct exynos4_tmu_platform_data { + u8 threshold; + u8 trigger_levels[4]; + bool trigger_level0_en; + bool trigger_level1_en; + bool trigger_level2_en; + bool trigger_level3_en; + + u8 gain; + u8 reference_voltage; + + enum calibration_type cal_type; +}; +#endif /* _LINUX_EXYNOS4_TMU_H */ -- cgit v1.2.3 From b1e4d20cbf2ef8e27515da032b95fdcbb5b06bf1 Mon Sep 17 00:00:00 2001 From: Michal Schmidt Date: Mon, 10 Oct 2011 00:03:37 +0200 Subject: params: make dashes and underscores in parameter names truly equal The user may use "foo-bar" for a kernel parameter defined as "foo_bar". Make sure it works the other way around too. Apply the equality of dashes and underscores on early_params and __setup params as well. The example given in Documentation/kernel-parameters.txt indicates that this is the intended behaviour. With the patch the kernel accepts "log-buf-len=1M" as expected. https://bugzilla.redhat.com/show_bug.cgi?id=744545 Signed-off-by: Michal Schmidt Signed-off-by: Rusty Russell (neatened implementations) --- include/linux/moduleparam.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h index ddaae98c53f9..fffb10bd5514 100644 --- a/include/linux/moduleparam.h +++ b/include/linux/moduleparam.h @@ -262,6 +262,26 @@ static inline void __kernel_param_unlock(void) .str = &__param_string_##name, 0, perm); \ __MODULE_PARM_TYPE(name, "string") +/** + * parameq - checks if two parameter names match + * @name1: parameter name 1 + * @name2: parameter name 2 + * + * Returns true if the two parameter names are equal. + * Dashes (-) are considered equal to underscores (_). + */ +extern bool parameq(const char *name1, const char *name2); + +/** + * parameqn - checks if two parameter names match + * @name1: parameter name 1 + * @name2: parameter name 2 + * @n: the length to compare + * + * Similar to parameq(), except it compares @n characters. + */ +extern bool parameqn(const char *name1, const char *name2, size_t n); + /* Called on module insert or kernel boot */ extern int parse_args(const char *name, char *args, -- cgit v1.2.3 From 6a32e4f9dd9219261f8856f817e6655114cfec2f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 29 Oct 2011 06:13:39 +0000 Subject: vlan: allow nested vlan_do_receive() commit 2425717b27eb (net: allow vlan traffic to be received under bond) broke ARP processing on vlan on top of bonding. +-------+ eth0 --| bond0 |---bond0.103 eth1 --| | +-------+ 52870.115435: skb_gro_reset_offset <-napi_gro_receive 52870.115435: dev_gro_receive <-napi_gro_receive 52870.115435: napi_skb_finish <-napi_gro_receive 52870.115435: netif_receive_skb <-napi_skb_finish 52870.115435: get_rps_cpu <-netif_receive_skb 52870.115435: __netif_receive_skb <-netif_receive_skb 52870.115436: vlan_do_receive <-__netif_receive_skb 52870.115436: bond_handle_frame <-__netif_receive_skb 52870.115436: vlan_do_receive <-__netif_receive_skb 52870.115436: arp_rcv <-__netif_receive_skb 52870.115436: kfree_skb <-arp_rcv Packet is dropped in arp_rcv() because its pkt_type was set to PACKET_OTHERHOST in the first vlan_do_receive() call, since no eth0.103 exists. We really need to change pkt_type only if no more rx_handler is about to be called for the packet. Signed-off-by: Eric Dumazet Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 44da4822bcab..12d5543b14f2 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -106,7 +106,7 @@ extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, extern struct net_device *vlan_dev_real_dev(const struct net_device *dev); extern u16 vlan_dev_vlan_id(const struct net_device *dev); -extern bool vlan_do_receive(struct sk_buff **skb); +extern bool vlan_do_receive(struct sk_buff **skb, bool last_handler); extern struct sk_buff *vlan_untag(struct sk_buff *skb); #else @@ -128,9 +128,9 @@ static inline u16 vlan_dev_vlan_id(const struct net_device *dev) return 0; } -static inline bool vlan_do_receive(struct sk_buff **skb) +static inline bool vlan_do_receive(struct sk_buff **skb, bool last_handler) { - if ((*skb)->vlan_tci & VLAN_VID_MASK) + if (((*skb)->vlan_tci & VLAN_VID_MASK) && last_handler) (*skb)->pkt_type = PACKET_OTHERHOST; return false; } -- cgit v1.2.3