diff options
Diffstat (limited to 'include')
40 files changed, 712 insertions, 142 deletions
diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h index 4d3e48373e7..0c3dd860392 100644 --- a/include/asm-generic/fcntl.h +++ b/include/asm-generic/fcntl.h @@ -73,6 +73,19 @@ #define F_SETSIG 10 /* for sockets. */ #define F_GETSIG 11 /* for sockets. */ #endif +#ifndef F_SETOWN_EX +#define F_SETOWN_EX 12 +#define F_GETOWN_EX 13 +#endif + +#define F_OWNER_TID 0 +#define F_OWNER_PID 1 +#define F_OWNER_GID 2 + +struct f_owner_ex { + int type; + pid_t pid; +}; /* for F_[GET|SET]FL */ #define FD_CLOEXEC 1 /* actually anything with low bit set goes */ diff --git a/include/asm-generic/mman-common.h b/include/asm-generic/mman-common.h index dd63bd38864..5ee13b2fd22 100644 --- a/include/asm-generic/mman-common.h +++ b/include/asm-generic/mman-common.h @@ -34,6 +34,7 @@ #define MADV_REMOVE 9 /* remove these pages & resources */ #define MADV_DONTFORK 10 /* don't inherit across fork */ #define MADV_DOFORK 11 /* do inherit across fork */ +#define MADV_HWPOISON 100 /* poison a page for testing */ #define MADV_MERGEABLE 12 /* KSM may merge identical pages */ #define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */ diff --git a/include/asm-generic/siginfo.h b/include/asm-generic/siginfo.h index c840719a8c5..942d30b5aab 100644 --- a/include/asm-generic/siginfo.h +++ b/include/asm-generic/siginfo.h @@ -82,6 +82,7 @@ typedef struct siginfo { #ifdef __ARCH_SI_TRAPNO int _trapno; /* TRAP # which caused the signal */ #endif + short _addr_lsb; /* LSB of the reported address */ } _sigfault; /* SIGPOLL */ @@ -112,6 +113,7 @@ typedef struct siginfo { #ifdef __ARCH_SI_TRAPNO #define si_trapno _sifields._sigfault._trapno #endif +#define si_addr_lsb _sifields._sigfault._addr_lsb #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd @@ -192,7 +194,11 @@ typedef struct siginfo { #define BUS_ADRALN (__SI_FAULT|1) /* invalid address alignment */ #define BUS_ADRERR (__SI_FAULT|2) /* non-existant physical address */ #define BUS_OBJERR (__SI_FAULT|3) /* object specific hardware error */ -#define NSIGBUS 3 +/* hardware memory error consumed on a machine check: action required */ +#define BUS_MCEERR_AR (__SI_FAULT|4) +/* hardware memory error detected in process but not consumed: action optional*/ +#define BUS_MCEERR_AO (__SI_FAULT|5) +#define NSIGBUS 5 /* * SIGTRAP si_codes diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h index 5fc2ef8d97f..a1c486a88e8 100644 --- a/include/linux/async_tx.h +++ b/include/linux/async_tx.h @@ -58,25 +58,60 @@ struct dma_chan_ref { * array. * @ASYNC_TX_ACK: immediately ack the descriptor, precludes setting up a * dependency chain - * @ASYNC_TX_DEP_ACK: ack the dependency descriptor. Useful for chaining. + * @ASYNC_TX_FENCE: specify that the next operation in the dependency + * chain uses this operation's result as an input */ enum async_tx_flags { ASYNC_TX_XOR_ZERO_DST = (1 << 0), ASYNC_TX_XOR_DROP_DST = (1 << 1), - ASYNC_TX_ACK = (1 << 3), - ASYNC_TX_DEP_ACK = (1 << 4), + ASYNC_TX_ACK = (1 << 2), + ASYNC_TX_FENCE = (1 << 3), +}; + +/** + * struct async_submit_ctl - async_tx submission/completion modifiers + * @flags: submission modifiers + * @depend_tx: parent dependency of the current operation being submitted + * @cb_fn: callback routine to run at operation completion + * @cb_param: parameter for the callback routine + * @scribble: caller provided space for dma/page address conversions + */ +struct async_submit_ctl { + enum async_tx_flags flags; + struct dma_async_tx_descriptor *depend_tx; + dma_async_tx_callback cb_fn; + void *cb_param; + void *scribble; }; #ifdef CONFIG_DMA_ENGINE #define async_tx_issue_pending_all dma_issue_pending_all + +/** + * async_tx_issue_pending - send pending descriptor to the hardware channel + * @tx: descriptor handle to retrieve hardware context + * + * Note: any dependent operations will have already been issued by + * async_tx_channel_switch, or (in the case of no channel switch) will + * be already pending on this channel. + */ +static inline void async_tx_issue_pending(struct dma_async_tx_descriptor *tx) +{ + if (likely(tx)) { + struct dma_chan *chan = tx->chan; + struct dma_device *dma = chan->device; + + dma->device_issue_pending(chan); + } +} #ifdef CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL #include <asm/async_tx.h> #else #define async_tx_find_channel(dep, type, dst, dst_count, src, src_count, len) \ __async_tx_find_channel(dep, type) struct dma_chan * -__async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx, - enum dma_transaction_type tx_type); +__async_tx_find_channel(struct async_submit_ctl *submit, + enum dma_transaction_type tx_type); #endif /* CONFIG_ARCH_HAS_ASYNC_TX_FIND_CHANNEL */ #else static inline void async_tx_issue_pending_all(void) @@ -84,10 +119,16 @@ static inline void async_tx_issue_pending_all(void) do { } while (0); } +static inline void async_tx_issue_pending(struct dma_async_tx_descriptor *tx) +{ + do { } while (0); +} + static inline struct dma_chan * -async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx, - enum dma_transaction_type tx_type, struct page **dst, int dst_count, - struct page **src, int src_count, size_t len) +async_tx_find_channel(struct async_submit_ctl *submit, + enum dma_transaction_type tx_type, struct page **dst, + int dst_count, struct page **src, int src_count, + size_t len) { return NULL; } @@ -99,46 +140,70 @@ async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx, * @cb_fn_param: parameter to pass to the callback routine */ static inline void -async_tx_sync_epilog(dma_async_tx_callback cb_fn, void *cb_fn_param) +async_tx_sync_epilog(struct async_submit_ctl *submit) { - if (cb_fn) - cb_fn(cb_fn_param); + if (submit->cb_fn) + submit->cb_fn(submit->cb_param); } -void -async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx, - enum async_tx_flags flags, struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); +typedef union { + unsigned long addr; + struct page *page; + dma_addr_t dma; +} addr_conv_t; + +static inline void +init_async_submit(struct async_submit_ctl *args, enum async_tx_flags flags, + struct dma_async_tx_descriptor *tx, + dma_async_tx_callback cb_fn, void *cb_param, + addr_conv_t *scribble) +{ + args->flags = flags; + args->depend_tx = tx; + args->cb_fn = cb_fn; + args->cb_param = cb_param; + args->scribble = scribble; +} + +void async_tx_submit(struct dma_chan *chan, struct dma_async_tx_descriptor *tx, + struct async_submit_ctl *submit); struct dma_async_tx_descriptor * async_xor(struct page *dest, struct page **src_list, unsigned int offset, - int src_cnt, size_t len, enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); + int src_cnt, size_t len, struct async_submit_ctl *submit); struct dma_async_tx_descriptor * -async_xor_zero_sum(struct page *dest, struct page **src_list, - unsigned int offset, int src_cnt, size_t len, - u32 *result, enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); +async_xor_val(struct page *dest, struct page **src_list, unsigned int offset, + int src_cnt, size_t len, enum sum_check_flags *result, + struct async_submit_ctl *submit); struct dma_async_tx_descriptor * async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset, - unsigned int src_offset, size_t len, enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); + unsigned int src_offset, size_t len, + struct async_submit_ctl *submit); struct dma_async_tx_descriptor * async_memset(struct page *dest, int val, unsigned int offset, - size_t len, enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); + size_t len, struct async_submit_ctl *submit); + +struct dma_async_tx_descriptor *async_trigger_callback(struct async_submit_ctl *submit); + +struct dma_async_tx_descriptor * +async_gen_syndrome(struct page **blocks, unsigned int offset, int src_cnt, + size_t len, struct async_submit_ctl *submit); + +struct dma_async_tx_descriptor * +async_syndrome_val(struct page **blocks, unsigned int offset, int src_cnt, + size_t len, enum sum_check_flags *pqres, struct page *spare, + struct async_submit_ctl *submit); + +struct dma_async_tx_descriptor * +async_raid6_2data_recov(int src_num, size_t bytes, int faila, int failb, + struct page **ptrs, struct async_submit_ctl *submit); struct dma_async_tx_descriptor * -async_trigger_callback(enum async_tx_flags flags, - struct dma_async_tx_descriptor *depend_tx, - dma_async_tx_callback cb_fn, void *cb_fn_param); +async_raid6_datap_recov(int src_num, size_t bytes, int faila, + struct page **ptrs, struct async_submit_ctl *submit); void async_tx_quiesce(struct dma_async_tx_descriptor **tx); #endif /* _ASYNC_TX_H_ */ diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 2046b5b8af4..aece486ac73 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -120,7 +120,7 @@ extern int copy_strings_kernel(int argc,char ** argv,struct linux_binprm *bprm); extern int prepare_bprm_creds(struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void do_coredump(long signr, int exit_code, struct pt_regs *regs); -extern int set_binfmt(struct linux_binfmt *new); +extern void set_binfmt(struct linux_binfmt *new); extern void free_bprm(struct linux_binprm *); #endif /* __KERNEL__ */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 90bba9e6228..b62bb9294d0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -141,6 +141,38 @@ enum { CGRP_WAIT_ON_RMDIR, }; +/* which pidlist file are we talking about? */ +enum cgroup_filetype { + CGROUP_FILE_PROCS, + CGROUP_FILE_TASKS, +}; + +/* + * A pidlist is a list of pids that virtually represents the contents of one + * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, + * a pair (one each for procs, tasks) for each pid namespace that's relevant + * to the cgroup. + */ +struct cgroup_pidlist { + /* + * used to find which pidlist is wanted. doesn't change as long as + * this particular list stays in the list. + */ + struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; + /* array of xids */ + pid_t *list; + /* how many elements the above list has */ + int length; + /* how many files are using the current array */ + int use_count; + /* each of these stored in a list by its cgroup */ + struct list_head links; + /* pointer to the cgroup we belong to, for list removal purposes */ + struct cgroup *owner; + /* protects the other fields */ + struct rw_semaphore mutex; +}; + struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ @@ -179,11 +211,12 @@ struct cgroup { */ struct list_head release_list; - /* pids_mutex protects pids_list and cached pid arrays. */ - struct rw_semaphore pids_mutex; - - /* Linked list of struct cgroup_pids */ - struct list_head pids_list; + /* + * list of pidlists, up to two for each namespace (one for procs, one + * for tasks); created on demand. + */ + struct list_head pidlists; + struct mutex pidlist_mutex; /* For RCU-protected deletion */ struct rcu_head rcu_head; @@ -227,6 +260,9 @@ struct css_set { * during subsystem registration (at boot time). */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + /* For RCU-protected deletion */ + struct rcu_head rcu_head; }; /* @@ -389,10 +425,11 @@ struct cgroup_subsys { struct cgroup *cgrp); int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp); - int (*can_attach)(struct cgroup_subsys *ss, - struct cgroup *cgrp, struct task_struct *tsk); + int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk, bool threadgroup); void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *tsk); + struct cgroup *old_cgrp, struct task_struct *tsk, + bool threadgroup); void (*fork)(struct cgroup_subsys *ss, struct task_struct *task); void (*exit)(struct cgroup_subsys *ss, struct task_struct *task); int (*populate)(struct cgroup_subsys *ss, diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 7f627775c94..ddb7a97c78c 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -27,8 +27,8 @@ * * configfs Copyright (C) 2005 Oracle. All rights reserved. * - * Please read Documentation/filesystems/configfs.txt before using the - * configfs interface, ESPECIALLY the parts about reference counts and + * Please read Documentation/filesystems/configfs/configfs.txt before using + * the configfs interface, ESPECIALLY the parts about reference counts and * item destructors. */ diff --git a/include/linux/dca.h b/include/linux/dca.h index 9c20c7e87d0..d27a7a05718 100644 --- a/include/linux/dca.h +++ b/include/linux/dca.h @@ -20,6 +20,9 @@ */ #ifndef DCA_H #define DCA_H + +#include <linux/pci.h> + /* DCA Provider API */ /* DCA Notifier Interface */ @@ -36,6 +39,12 @@ struct dca_provider { int id; }; +struct dca_domain { + struct list_head node; + struct list_head dca_providers; + struct pci_bus *pci_rc; +}; + struct dca_ops { int (*add_requester) (struct dca_provider *, struct device *); int (*remove_requester) (struct dca_provider *, struct device *); @@ -47,7 +56,7 @@ struct dca_ops { struct dca_provider *alloc_dca_provider(struct dca_ops *ops, int priv_size); void free_dca_provider(struct dca_provider *dca); int register_dca_provider(struct dca_provider *dca, struct device *dev); -void unregister_dca_provider(struct dca_provider *dca); +void unregister_dca_provider(struct dca_provider *dca, struct device *dev); static inline void *dca_priv(struct dca_provider *dca) { diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index eb5c2ba2f81..fc1b930f246 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -9,7 +9,7 @@ * 2 as published by the Free Software Foundation. * * debugfs is for people to use instead of /proc or /sys. - * See Documentation/DocBook/kernel-api for more details. + * See Documentation/DocBook/filesystems for more details. */ #ifndef _DEBUGFS_H_ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index ffefba81c81..2b9f2ac7ed6 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -48,19 +48,20 @@ enum dma_status { /** * enum dma_transaction_type - DMA transaction types/indexes + * + * Note: The DMA_ASYNC_TX capability is not to be set by drivers. It is + * automatically set as dma devices are registered. */ enum dma_transaction_type { DMA_MEMCPY, DMA_XOR, - DMA_PQ_XOR, - DMA_DUAL_XOR, - DMA_PQ_UPDATE, - DMA_ZERO_SUM, - DMA_PQ_ZERO_SUM, + DMA_PQ, + DMA_XOR_VAL, + DMA_PQ_VAL, DMA_MEMSET, - DMA_MEMCPY_CRC32C, DMA_INTERRUPT, DMA_PRIVATE, + DMA_ASYNC_TX, DMA_SLAVE, }; @@ -70,18 +71,25 @@ enum dma_transaction_type { /** * enum dma_ctrl_flags - DMA flags to augment operation preparation, - * control completion, and communicate status. + * control completion, and communicate status. * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of - * this transaction + * this transaction * @DMA_CTRL_ACK - the descriptor cannot be reused until the client - * acknowledges receipt, i.e. has has a chance to establish any - * dependency chains + * acknowledges receipt, i.e. has has a chance to establish any dependency + * chains * @DMA_COMPL_SKIP_SRC_UNMAP - set to disable dma-unmapping the source buffer(s) * @DMA_COMPL_SKIP_DEST_UNMAP - set to disable dma-unmapping the destination(s) * @DMA_COMPL_SRC_UNMAP_SINGLE - set to do the source dma-unmapping as single * (if not set, do the source dma-unmapping as page) * @DMA_COMPL_DEST_UNMAP_SINGLE - set to do the destination dma-unmapping as single * (if not set, do the destination dma-unmapping as page) + * @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q + * @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P + * @DMA_PREP_CONTINUE - indicate to a driver that it is reusing buffers as + * sources that were the result of a previous operation, in the case of a PQ + * operation it continues the calculation with new sources + * @DMA_PREP_FENCE - tell the driver that subsequent operations depend + * on the result of this operation */ enum dma_ctrl_flags { DMA_PREP_INTERRUPT = (1 << 0), @@ -90,9 +98,32 @@ enum dma_ctrl_flags { DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3), DMA_COMPL_SRC_UNMAP_SINGLE = (1 << 4), DMA_COMPL_DEST_UNMAP_SINGLE = (1 << 5), + DMA_PREP_PQ_DISABLE_P = (1 << 6), + DMA_PREP_PQ_DISABLE_Q = (1 << 7), + DMA_PREP_CONTINUE = (1 << 8), + DMA_PREP_FENCE = (1 << 9), }; /** + * enum sum_check_bits - bit position of pq_check_flags + */ +enum sum_check_bits { + SUM_CHECK_P = 0, + SUM_CHECK_Q = 1, +}; + +/** + * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations + * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise + * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise + */ +enum sum_check_flags { + SUM_CHECK_P_RESULT = (1 << SUM_CHECK_P), + SUM_CHECK_Q_RESULT = (1 << SUM_CHECK_Q), +}; + + +/** * dma_cap_mask_t - capabilities bitmap modeled after cpumask_t. * See linux/cpumask.h */ @@ -180,8 +211,6 @@ typedef void (*dma_async_tx_callback)(void *dma_async_param); * @flags: flags to augment operation preparation, control completion, and * communicate status * @phys: physical address of the descriptor - * @tx_list: driver common field for operations that require multiple - * descriptors * @chan: target channel for this operation * @tx_submit: set the prepared descriptor(s) to be executed by the engine * @callback: routine to call after this operation is complete @@ -195,7 +224,6 @@ struct dma_async_tx_descriptor { dma_cookie_t cookie; enum dma_ctrl_flags flags; /* not a 'long' to pack with cookie */ dma_addr_t phys; - struct list_head tx_list; struct dma_chan *chan; dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx); dma_async_tx_callback callback; @@ -213,6 +241,11 @@ struct dma_async_tx_descriptor { * @global_node: list_head for global dma_device_list * @cap_mask: one or more dma_capability flags * @max_xor: maximum number of xor sources, 0 if no capability + * @max_pq: maximum number of PQ sources and PQ-continue capability + * @copy_align: alignment shift for memcpy operations + * @xor_align: alignment shift for xor operations + * @pq_align: alignment shift for pq operations + * @fill_align: alignment shift for memset operations * @dev_id: unique device ID * @dev: struct device reference for dma mapping api * @device_alloc_chan_resources: allocate resources and return the @@ -220,7 +253,9 @@ struct dma_async_tx_descriptor { * @device_free_chan_resources: release DMA channel's resources * @device_prep_dma_memcpy: prepares a memcpy operation * @device_prep_dma_xor: prepares a xor operation - * @device_prep_dma_zero_sum: prepares a zero_sum operation + * @device_prep_dma_xor_val: prepares a xor validation operation + * @device_prep_dma_pq: prepares a pq operation + * @device_prep_dma_pq_val: prepares a pqzero_sum operation * @device_prep_dma_memset: prepares a memset operation * @device_prep_dma_interrupt: prepares an end of chain interrupt operation * @device_prep_slave_sg: prepares a slave dma operation @@ -235,7 +270,13 @@ struct dma_device { struct list_head channels; struct list_head global_node; dma_cap_mask_t cap_mask; - int max_xor; + unsigned short max_xor; + unsigned short max_pq; + u8 copy_align; + u8 xor_align; + u8 pq_align; + u8 fill_align; + #define DMA_HAS_PQ_CONTINUE (1 << 15) int dev_id; struct device *dev; @@ -249,9 +290,17 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_dma_xor)( struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src, unsigned int src_cnt, size_t len, unsigned long flags); - struct dma_async_tx_descriptor *(*device_prep_dma_zero_sum)( + struct dma_async_tx_descriptor *(*device_prep_dma_xor_val)( struct dma_chan *chan, dma_addr_t *src, unsigned int src_cnt, - size_t len, u32 *result, unsigned long flags); + size_t len, enum sum_check_flags *result, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_pq)( + struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src, + unsigned int src_cnt, const unsigned char *scf, + size_t len, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_pq_val)( + struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src, + unsigned int src_cnt, const unsigned char *scf, size_t len, + enum sum_check_flags *pqres, unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_memset)( struct dma_chan *chan, dma_addr_t dest, int value, size_t len, unsigned long flags); @@ -270,6 +319,96 @@ struct dma_device { void (*device_issue_pending)(struct dma_chan *chan); }; +static inline bool dmaengine_check_align(u8 align, size_t off1, size_t off2, size_t len) +{ + size_t mask; + + if (!align) + return true; + mask = (1 << align) - 1; + if (mask & (off1 | off2 | len)) + return false; + return true; +} + +static inline bool is_dma_copy_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->copy_align, off1, off2, len); +} + +static inline bool is_dma_xor_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->xor_align, off1, off2, len); +} + +static inline bool is_dma_pq_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->pq_align, off1, off2, len); +} + +static inline bool is_dma_fill_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->fill_align, off1, off2, len); +} + +static inline void +dma_set_maxpq(struct dma_device *dma, int maxpq, int has_pq_continue) +{ + dma->max_pq = maxpq; + if (has_pq_continue) + dma->max_pq |= DMA_HAS_PQ_CONTINUE; +} + +static inline bool dmaf_continue(enum dma_ctrl_flags flags) +{ + return (flags & DMA_PREP_CONTINUE) == DMA_PREP_CONTINUE; +} + +static inline bool dmaf_p_disabled_continue(enum dma_ctrl_flags flags) +{ + enum dma_ctrl_flags mask = DMA_PREP_CONTINUE | DMA_PREP_PQ_DISABLE_P; + + return (flags & mask) == mask; +} + +static inline bool dma_dev_has_pq_continue(struct dma_device *dma) +{ + return (dma->max_pq & DMA_HAS_PQ_CONTINUE) == DMA_HAS_PQ_CONTINUE; +} + +static unsigned short dma_dev_to_maxpq(struct dma_device *dma) +{ + return dma->max_pq & ~DMA_HAS_PQ_CONTINUE; +} + +/* dma_maxpq - reduce maxpq in the face of continued operations + * @dma - dma device with PQ capability + * @flags - to check if DMA_PREP_CONTINUE and DMA_PREP_PQ_DISABLE_P are set + * + * When an engine does not support native continuation we need 3 extra + * source slots to reuse P and Q with the following coefficients: + * 1/ {00} * P : remove P from Q', but use it as a source for P' + * 2/ {01} * Q : use Q to continue Q' calculation + * 3/ {00} * Q : subtract Q from P' to cancel (2) + * + * In the case where P is disabled we only need 1 extra source: + * 1/ {01} * Q : use Q to continue Q' calculation + */ +static inline int dma_maxpq(struct dma_device *dma, enum dma_ctrl_flags flags) +{ + if (dma_dev_has_pq_continue(dma) || !dmaf_continue(flags)) + return dma_dev_to_maxpq(dma); + else if (dmaf_p_disabled_continue(flags)) + return dma_dev_to_maxpq(dma) - 1; + else if (dmaf_continue(flags)) + return dma_dev_to_maxpq(dma) - 3; + BUG(); +} + /* --- public DMA engine API --- */ #ifdef CONFIG_DMA_ENGINE @@ -299,7 +438,11 @@ static inline void net_dmaengine_put(void) #ifdef CONFIG_ASYNC_TX_DMA #define async_dmaengine_get() dmaengine_get() #define async_dmaengine_put() dmaengine_put() +#ifdef CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH +#define async_dma_find_channel(type) dma_find_channel(DMA_ASYNC_TX) +#else #define async_dma_find_channel(type) dma_find_channel(type) +#endif /* CONFIG_ASYNC_TX_DISABLE_CHANNEL_SWITCH */ #else static inline void async_dmaengine_get(void) { @@ -312,7 +455,7 @@ async_dma_find_channel(enum dma_transaction_type type) { return NULL; } -#endif +#endif /* CONFIG_ASYNC_TX_DMA */ dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest, void *src, size_t len); diff --git a/include/linux/fs.h b/include/linux/fs.h index 51803528b09..2adaa2529f1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -595,6 +595,7 @@ struct address_space_operations { int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, read_descriptor_t *, unsigned long); + int (*error_remove_page)(struct address_space *, struct page *); }; /* @@ -640,7 +641,6 @@ struct block_device { struct super_block * bd_super; int bd_openers; struct mutex bd_mutex; /* open/close mutex */ - struct semaphore bd_mount_sem; struct list_head bd_inodes; void * bd_holder; int bd_holders; @@ -1315,7 +1315,7 @@ struct super_block { unsigned long s_blocksize; unsigned char s_blocksize_bits; unsigned char s_dirt; - unsigned long long s_maxbytes; /* Max file size */ + loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; @@ -2156,6 +2156,7 @@ extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern void generic_delete_inode(struct inode *inode); extern void generic_drop_inode(struct inode *inode); +extern int generic_detach_inode(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), @@ -2334,6 +2335,7 @@ extern void get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); +extern struct super_block *get_active_super(struct block_device *bdev); extern struct super_block *user_get_super(dev_t); extern void drop_super(struct super_block *sb); @@ -2381,7 +2383,8 @@ extern int buffer_migrate_page(struct address_space *, #define buffer_migrate_page NULL #endif -extern int inode_change_ok(struct inode *, struct iattr *); +extern int inode_change_ok(const struct inode *, struct iattr *); +extern int inode_newsize_ok(const struct inode *, loff_t offset); extern int __must_check inode_setattr(struct inode *, struct iattr *); extern void file_update_time(struct file *file); @@ -2467,7 +2470,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, struct file *filp, +int proc_nr_files(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); int __init get_filesystem_list(char *buf); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 3c0924a18da..cd3d2abaf30 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -19,7 +19,7 @@ extern int ftrace_enabled; extern int ftrace_enable_sysctl(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip); @@ -94,7 +94,7 @@ static inline void ftrace_start(void) { } extern int stack_tracer_enabled; int stack_trace_sysctl(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); #endif diff --git a/include/linux/futex.h b/include/linux/futex.h index 34956c8fdeb..8ec17997d94 100644 --- a/include/linux/futex.h +++ b/include/linux/futex.h @@ -4,11 +4,6 @@ #include <linux/compiler.h> #include <linux/types.h> -struct inode; -struct mm_struct; -struct task_struct; -union ktime; - /* Second argument to futex syscall */ @@ -129,6 +124,11 @@ struct robust_list_head { #define FUTEX_BITSET_MATCH_ANY 0xffffffff #ifdef __KERNEL__ +struct inode; +struct mm_struct; +struct task_struct; +union ktime; + long do_futex(u32 __user *uaddr, int op, u32 val, union ktime *timeout, u32 __user *uaddr2, u32 val2, u32 val3); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 176e7ee73ef..11ab19ac6b3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -20,9 +20,9 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma) } void reset_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); +int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); +int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e46a0734ab6..bf9213b2db8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -118,6 +118,9 @@ static inline bool mem_cgroup_disabled(void) extern bool mem_cgroup_oom_called(struct task_struct *task); void mem_cgroup_update_mapped_file_stat(struct page *page, int val); +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, int nid, + int zid); #else /* CONFIG_CGROUP_MEM_RES_CTLR */ struct mem_cgroup; @@ -276,6 +279,13 @@ static inline void mem_cgroup_update_mapped_file_stat(struct page *page, { } +static inline +unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, + gfp_t gfp_mask, int nid, int zid) +{ + return 0; +} + #endif /* CONFIG_CGROUP_MEM_CONT */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index b6eae5e3144..df08551cb0a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -695,11 +695,12 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_SIGBUS 0x0002 #define VM_FAULT_MAJOR 0x0004 #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ +#define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned page */ #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ -#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS) +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON) /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. @@ -791,8 +792,14 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, unmap_mapping_range(mapping, holebegin, holelen, 0); } -extern int vmtruncate(struct inode * inode, loff_t offset); -extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end); +extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new); +extern int vmtruncate(struct inode *inode, loff_t offset); +extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end); + +int truncate_inode_page(struct address_space *mapping, struct page *page); +int generic_error_remove_page(struct address_space *mapping, struct page *page); + +int invalidate_inode_page(struct page *page); #ifdef CONFIG_MMU extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, @@ -1279,7 +1286,7 @@ int in_gate_area_no_task(unsigned long addr); #define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);}) #endif /* __HAVE_ARCH_GATE_AREA */ -int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *, +int drop_caches_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, unsigned long lru_pages); @@ -1308,5 +1315,12 @@ void vmemmap_populate_print_last(void); extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim, size_t size); extern void refund_locked_memory(struct mm_struct *mm, size_t size); + +extern void memory_failure(unsigned long pfn, int trapno); +extern int __memory_failure(unsigned long pfn, int trapno, int ref); +extern int sysctl_memory_failure_early_kill; +extern int sysctl_memory_failure_recovery; +extern atomic_long_t mce_bad_pages; + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0042090a4d7..21d6aa45206 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -240,6 +240,8 @@ struct mm_struct { unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */ + struct linux_binfmt *binfmt; + cpumask_t cpu_vm_mask; /* Architecture-specific MM context */ @@ -259,11 +261,10 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access the bits */ struct core_state *core_state; /* coredumping support */ - - /* aio bits */ +#ifdef CONFIG_AIO spinlock_t ioctx_lock; struct hlist_head ioctx_list; - +#endif #ifdef CONFIG_MM_OWNER /* * "owner" points to a task that is regarded as the canonical diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 652ef01be58..6f7561730d8 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -755,21 +755,20 @@ static inline int is_dma(struct zone *zone) /* These two functions are used to setup the per zone pages min values */ struct ctl_table; -struct file; -int min_free_kbytes_sysctl_handler(struct ctl_table *, int, struct file *, +int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1]; -int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *, +int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *, +int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern int numa_zonelist_order_handler(struct ctl_table *, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern char numa_zonelist_order[]; #define NUMA_ZONELIST_ORDER_LEN 16 /* string buffer size */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 13de789f0a5..6b202b17395 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -51,6 +51,9 @@ * PG_buddy is set to indicate that the page is free and in the buddy system * (see mm/page_alloc.c). * + * PG_hwpoison indicates that a page got corrupted in hardware and contains + * data with incorrect ECC bits that triggered a machine check. Accessing is + * not safe since it may cause another machine check. Don't touch! */ /* @@ -102,6 +105,9 @@ enum pageflags { #ifdef CONFIG_ARCH_USES_PG_UNCACHED PG_uncached, /* Page has been mapped as uncached */ #endif +#ifdef CONFIG_MEMORY_FAILURE + PG_hwpoison, /* hardware poisoned page. Don't touch */ +#endif __NR_PAGEFLAGS, /* Filesystems */ @@ -269,6 +275,15 @@ PAGEFLAG(Uncached, uncached) PAGEFLAG_FALSE(Uncached) #endif +#ifdef CONFIG_MEMORY_FAILURE +PAGEFLAG(HWPoison, hwpoison) +TESTSETFLAG(HWPoison, hwpoison) +#define __PG_HWPOISON (1UL << PG_hwpoison) +#else +PAGEFLAG_FALSE(HWPoison) +#define __PG_HWPOISON 0 +#endif + static inline int PageUptodate(struct page *page) { int ret = test_bit(PG_uptodate, &(page)->flags); @@ -393,7 +408,7 @@ static inline void __ClearPageTail(struct page *page) 1 << PG_private | 1 << PG_private_2 | \ 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ - 1 << PG_unevictable | __PG_MLOCKED) + 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON) /* * Flags checked when a page is prepped for return by the page allocator. diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index ada779f2417..4b938d4f3ac 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -38,6 +38,7 @@ enum { PCG_LOCK, /* page cgroup is locked */ PCG_CACHE, /* charged as cache */ PCG_USED, /* this object is in use. */ + PCG_ACCT_LRU, /* page has been accounted for */ }; #define TESTPCGFLAG(uname, lname) \ @@ -52,11 +53,23 @@ static inline void SetPageCgroup##uname(struct page_cgroup *pc)\ static inline void ClearPageCgroup##uname(struct page_cgroup *pc) \ { clear_bit(PCG_##lname, &pc->flags); } +#define TESTCLEARPCGFLAG(uname, lname) \ +static inline int TestClearPageCgroup##uname(struct page_cgroup *pc) \ + { return test_and_clear_bit(PCG_##lname, &pc->flags); } + /* Cache flag is set only once (at allocation) */ TESTPCGFLAG(Cache, CACHE) +CLEARPCGFLAG(Cache, CACHE) +SETPCGFLAG(Cache, CACHE) TESTPCGFLAG(Used, USED) CLEARPCGFLAG(Used, USED) +SETPCGFLAG(Used, USED) + +SETPCGFLAG(AcctLRU, ACCT_LRU) +CLEARPCGFLAG(AcctLRU, ACCT_LRU) +TESTPCGFLAG(AcctLRU, ACCT_LRU) +TESTCLEARPCGFLAG(AcctLRU, ACCT_LRU) static inline int page_cgroup_nid(struct page_cgroup *pc) { diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 7803565aa87..da1fda8623e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2527,6 +2527,16 @@ #define PCI_DEVICE_ID_INTEL_E7525_MCH 0x359e #define PCI_DEVICE_ID_INTEL_IOAT_CNB 0x360b #define PCI_DEVICE_ID_INTEL_FBD_CNB 0x360c +#define PCI_DEVICE_ID_INTEL_IOAT_JSF0 0x3710 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF1 0x3711 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF2 0x3712 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF3 0x3713 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF4 0x3714 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF5 0x3715 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF6 0x3716 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF7 0x3717 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF8 0x3718 +#define PCI_DEVICE_ID_INTEL_IOAT_JSF9 0x3719 #define PCI_DEVICE_ID_INTEL_ICH10_0 0x3a14 #define PCI_DEVICE_ID_INTEL_ICH10_1 0x3a16 #define PCI_DEVICE_ID_INTEL_ICH10_2 0x3a18 diff --git a/include/linux/prctl.h b/include/linux/prctl.h index 07bff666e65..931150566ad 100644 --- a/include/linux/prctl.h +++ b/include/linux/prctl.h @@ -88,4 +88,6 @@ #define PR_TASK_PERF_EVENTS_DISABLE 31 #define PR_TASK_PERF_EVENTS_ENABLE 32 +#define PR_MCE_KILL 33 + #endif /* _LINUX_PRCTL_H */ diff --git a/include/linux/relay.h b/include/linux/relay.h index 953fc055e87..14a86bc7102 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -140,7 +140,7 @@ struct rchan_callbacks * cause relay_open() to create a single global buffer rather * than the default set of per-cpu buffers. * - * See Documentation/filesystems/relayfs.txt for more info. + * See Documentation/filesystems/relay.txt for more info. */ struct dentry *(*create_buf_file)(const char *filename, struct dentry *parent, diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 511f42fc681..731af71cddc 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -35,6 +35,10 @@ struct res_counter { */ unsigned long long limit; /* + * the limit that usage can be exceed + */ + unsigned long long soft_limit; + /* * the number of unsuccessful attempts to consume the resource */ unsigned long long failcnt; @@ -87,6 +91,7 @@ enum { RES_MAX_USAGE, RES_LIMIT, RES_FAILCNT, + RES_SOFT_LIMIT, }; /* @@ -109,7 +114,8 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent); int __must_check res_counter_charge_locked(struct res_counter *counter, unsigned long val); int __must_check res_counter_charge(struct res_counter *counter, - unsigned long val, struct res_counter **limit_fail_at); + unsigned long val, struct res_counter **limit_fail_at, + struct res_counter **soft_limit_at); /* * uncharge - tell that some portion of the resource is released @@ -122,7 +128,8 @@ int __must_check res_counter_charge(struct res_counter *counter, */ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val); -void res_counter_uncharge(struct res_counter *counter, unsigned long val); +void res_counter_uncharge(struct res_counter *counter, unsigned long val, + bool *was_soft_limit_excess); static inline bool res_counter_limit_check_locked(struct res_counter *cnt) { @@ -132,6 +139,36 @@ static inline bool res_counter_limit_check_locked(struct res_counter *cnt) return false; } +static inline bool res_counter_soft_limit_check_locked(struct res_counter *cnt) +{ + if (cnt->usage < cnt->soft_limit) + return true; + + return false; +} + +/** + * Get the difference between the usage and the soft limit + * @cnt: The counter + * + * Returns 0 if usage is less than or equal to soft limit + * The difference between usage and soft limit, otherwise. + */ +static inline unsigned long long +res_counter_soft_limit_excess(struct res_counter *cnt) +{ + unsigned long long excess; + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + if (cnt->usage <= cnt->soft_limit) + excess = 0; + else + excess = cnt->usage - cnt->soft_limit; + spin_unlock_irqrestore(&cnt->lock, flags); + return excess; +} + /* * Helper function to detect if the cgroup is within it's limit or * not. It's currently called from cgroup_rss_prepare() @@ -147,6 +184,17 @@ static inline bool res_counter_check_under_limit(struct res_counter *cnt) return ret; } +static inline bool res_counter_check_under_soft_limit(struct res_counter *cnt) +{ + bool ret; + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + ret = res_counter_soft_limit_check_locked(cnt); + spin_unlock_irqrestore(&cnt->lock, flags); + return ret; +} + static inline void res_counter_reset_max(struct res_counter *cnt) { unsigned long flags; @@ -180,4 +228,16 @@ static inline int res_counter_set_limit(struct res_counter *cnt, return ret; } +static inline int +res_counter_set_soft_limit(struct res_counter *cnt, + unsigned long long soft_limit) +{ + unsigned long flags; + + spin_lock_irqsave(&cnt->lock, flags); + cnt->soft_limit = soft_limit; + spin_unlock_irqrestore(&cnt->lock, flags); + return 0; +} + #endif diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 477841d29fc..cb0ba703260 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -81,7 +81,19 @@ static inline void page_dup_rmap(struct page *page) */ int page_referenced(struct page *, int is_locked, struct mem_cgroup *cnt, unsigned long *vm_flags); -int try_to_unmap(struct page *, int ignore_refs); +enum ttu_flags { + TTU_UNMAP = 0, /* unmap mode */ + TTU_MIGRATION = 1, /* migration mode */ + TTU_MUNLOCK = 2, /* munlock mode */ + TTU_ACTION_MASK = 0xff, + + TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */ + TTU_IGNORE_ACCESS = (1 << 9), /* don't age */ + TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */ +}; +#define TTU_ACTION(x) ((x) & TTU_ACTION_MASK) + +int try_to_unmap(struct page *, enum ttu_flags flags); /* * Called from mm/filemap_xip.c to unmap empty zero page @@ -108,6 +120,13 @@ int page_mkclean(struct page *); */ int try_to_munlock(struct page *); +/* + * Called by memory-failure.c to kill processes. + */ +struct anon_vma *page_lock_anon_vma(struct page *page); +void page_unlock_anon_vma(struct anon_vma *anon_vma); +int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); + #else /* !CONFIG_MMU */ #define anon_vma_init() do {} while (0) diff --git a/include/linux/sched.h b/include/linux/sched.h index 848d1f20086..75e6e60bf58 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -309,7 +309,7 @@ extern void softlockup_tick(void); extern void touch_softlockup_watchdog(void); extern void touch_all_softlockup_watchdogs(void); extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; extern int softlockup_thresh; @@ -331,7 +331,7 @@ extern unsigned long sysctl_hung_task_check_count; extern unsigned long sysctl_hung_task_timeout_secs; extern unsigned long sysctl_hung_task_warnings; extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); #endif @@ -1271,7 +1271,6 @@ struct task_struct { struct mm_struct *mm, *active_mm; /* task state */ - struct linux_binfmt *binfmt; int exit_state; int exit_code, exit_signal; int pdeath_signal; /* The signal sent when the parent dies */ @@ -1735,6 +1734,7 @@ extern cputime_t task_gtime(struct task_struct *p); #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ +#define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* dumped core */ #define PF_SIGNALED 0x00000400 /* killed by a signal */ @@ -1754,6 +1754,7 @@ extern cputime_t task_gtime(struct task_struct *p); #define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ #define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ #define PF_THREAD_BOUND 0x04000000 /* Thread bound to specific cpu */ +#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezeable */ @@ -1906,7 +1907,7 @@ extern unsigned int sysctl_sched_time_avg; extern unsigned int sysctl_timer_migration; int sched_nr_latency_handler(struct ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length, + void __user *buffer, size_t *length, loff_t *ppos); #endif #ifdef CONFIG_SCHED_DEBUG @@ -1924,7 +1925,7 @@ extern unsigned int sysctl_sched_rt_period; extern int sysctl_sched_rt_runtime; int sched_rt_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern unsigned int sysctl_sched_compat_yield; @@ -2059,6 +2060,7 @@ 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); extern int do_notify_parent(struct task_struct *, int); +extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int, struct task_struct *); extern void force_sig_specific(int, struct task_struct *); extern int send_sig(int, struct task_struct *, int); @@ -2336,7 +2338,10 @@ static inline int signal_pending(struct task_struct *p) return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } -extern int __fatal_signal_pending(struct task_struct *p); +static inline int __fatal_signal_pending(struct task_struct *p) +{ + return unlikely(sigismember(&p->pending.signal, SIGKILL)); +} static inline int fatal_signal_pending(struct task_struct *p) { diff --git a/include/linux/security.h b/include/linux/security.h index d050b66ab9e..239e40d0450 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -133,7 +133,7 @@ static inline unsigned long round_hint_to_min(unsigned long hint) return PAGE_ALIGN(mmap_min_addr); return hint; } -extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp, +extern int mmap_min_addr_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_SECURITY diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 0c6a86b7959..8366d8f12e5 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -35,6 +35,44 @@ struct seq_operations { #define SEQ_SKIP 1 +/** + * seq_get_buf - get buffer to write arbitrary data to + * @m: the seq_file handle + * @bufp: the beginning of the buffer is stored here + * + * Return the number of bytes available in the buffer, or zero if + * there's no space. + */ +static inline size_t seq_get_buf(struct seq_file *m, char **bufp) +{ + BUG_ON(m->count > m->size); + if (m->count < m->size) + *bufp = m->buf + m->count; + else + *bufp = NULL; + + return m->size - m->count; +} + +/** + * seq_commit - commit data to the buffer + * @m: the seq_file handle + * @num: the number of bytes to commit + * + * Commit @num bytes of data written to a buffer previously acquired + * by seq_buf_get. To signal an error condition, or that the data + * didn't fit in the available space, pass a negative @num value. + */ +static inline void seq_commit(struct seq_file *m, int num) +{ + if (num < 0) { + m->count = m->size; + } else { + BUG_ON(m->count + num > m->size); + m->count += num; + } +} + char *mangle_path(char *s, char *p, char *esc); int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); diff --git a/include/linux/signal.h b/include/linux/signal.h index c7552836bd9..ab9272cc270 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -233,6 +233,8 @@ static inline int valid_signal(unsigned long sig) } extern int next_signal(struct sigpending *pending, sigset_t *mask); +extern int do_send_sig_info(int sig, struct siginfo *info, + struct task_struct *p, bool group); extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p); extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); extern long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, diff --git a/include/linux/swap.h b/include/linux/swap.h index 6c990e658f4..4ec90019c1a 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -34,16 +34,38 @@ static inline int current_is_kswapd(void) * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 -#ifndef CONFIG_MIGRATION -#define MAX_SWAPFILES (1 << MAX_SWAPFILES_SHIFT) + +/* + * Use some of the swap files numbers for other purposes. This + * is a convenient way to hook into the VM to trigger special + * actions on faults. + */ + +/* + * NUMA node memory migration support + */ +#ifdef CONFIG_MIGRATION +#define SWP_MIGRATION_NUM 2 +#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) +#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #else -/* Use last two entries for page migration swap entries */ -#define MAX_SWAPFILES ((1 << MAX_SWAPFILES_SHIFT)-2) -#define SWP_MIGRATION_READ MAX_SWAPFILES -#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + 1) +#define SWP_MIGRATION_NUM 0 #endif /* + * Handling of hardware poisoned pages with memory corruption. + */ +#ifdef CONFIG_MEMORY_FAILURE +#define SWP_HWPOISON_NUM 1 +#define SWP_HWPOISON MAX_SWAPFILES +#else +#define SWP_HWPOISON_NUM 0 +#endif + +#define MAX_SWAPFILES \ + ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM) + +/* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) * swap area format, the second part of the union adds - in the @@ -217,6 +239,11 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, unsigned int swappiness); +extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem, + gfp_t gfp_mask, bool noswap, + unsigned int swappiness, + struct zone *zone, + int nid); extern int __isolate_lru_page(struct page *page, int mode, int file); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; @@ -240,7 +267,7 @@ extern int page_evictable(struct page *page, struct vm_area_struct *vma); extern void scan_mapping_unevictable_pages(struct address_space *); extern unsigned long scan_unevictable_pages; -extern int scan_unevictable_handler(struct ctl_table *, int, struct file *, +extern int scan_unevictable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int scan_unevictable_register_node(struct node *node); extern void scan_unevictable_unregister_node(struct node *node); diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 6ec39ab27b4..cd42e30b7c6 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -131,3 +131,41 @@ static inline int is_write_migration_entry(swp_entry_t entry) #endif +#ifdef CONFIG_MEMORY_FAILURE +/* + * Support for hardware poisoned pages + */ +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + BUG_ON(!PageLocked(page)); + return swp_entry(SWP_HWPOISON, page_to_pfn(page)); +} + +static inline int is_hwpoison_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_HWPOISON; +} +#else + +static inline swp_entry_t make_hwpoison_entry(struct page *page) +{ + return swp_entry(0, 0); +} + +static inline int is_hwpoison_entry(swp_entry_t swp) +{ + return 0; +} +#endif + +#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) +static inline int non_swap_entry(swp_entry_t entry) +{ + return swp_type(entry) >= MAX_SWAPFILES; +} +#else +static inline int non_swap_entry(swp_entry_t entry) +{ + return 0; +} +#endif diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index e76d3b22a46..1e4743ee683 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -29,7 +29,6 @@ #include <linux/types.h> #include <linux/compiler.h> -struct file; struct completion; #define CTL_MAXNAME 10 /* how many path components do we allow in a @@ -977,25 +976,25 @@ typedef int ctl_handler (struct ctl_table *table, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); -typedef int proc_handler (struct ctl_table *ctl, int write, struct file * filp, +typedef int proc_handler (struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -extern int proc_dostring(struct ctl_table *, int, struct file *, +extern int proc_dostring(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec(struct ctl_table *, int, struct file *, +extern int proc_dointvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_minmax(struct ctl_table *, int, struct file *, +extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_jiffies(struct ctl_table *, int, struct file *, +extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, struct file *, +extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_dointvec_ms_jiffies(struct ctl_table *, int, struct file *, +extern int proc_dointvec_ms_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int proc_doulongvec_minmax(struct ctl_table *, int, struct file *, +extern int proc_doulongvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, - struct file *, void __user *, size_t *, loff_t *); + void __user *, size_t *, loff_t *); extern int do_sysctl (int __user *name, int nlen, void __user *oldval, size_t __user *oldlenp, diff --git a/include/linux/time.h b/include/linux/time.h index 56787c09334..fe04e5ef6a5 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -155,6 +155,34 @@ extern void timekeeping_leap_insert(int leapsecond); struct tms; extern void do_sys_times(struct tms *); +/* + * Similar to the struct tm in userspace <time.h>, but it needs to be here so + * that the kernel source is self contained. + */ +struct tm { + /* + * the number of seconds after the minute, normally in the range + * 0 to 59, but can be up to 60 to allow for leap seconds + */ + int tm_sec; + /* the number of minutes after the hour, in the range 0 to 59*/ + int tm_min; + /* the number of hours past midnight, in the range 0 to 23 */ + int tm_hour; + /* the day of the month, in the range 1 to 31 */ + int tm_mday; + /* the number of months since January, in the range 0 to 11 */ + int tm_mon; + /* the number of years since 1900 */ + long tm_year; + /* the number of days since Sunday, in the range 0 to 6 */ + int tm_wday; + /* the number of days since January 1, in the range 0 to 365 */ + int tm_yday; +}; + +void time_to_tm(time_t totalsecs, int offset, struct tm *result); + /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 17ba82efa48..1eb44a924e5 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -1,7 +1,7 @@ /* * Tracing hooks * - * Copyright (C) 2008 Red Hat, Inc. All rights reserved. + * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions @@ -463,22 +463,38 @@ static inline int tracehook_get_signal(struct task_struct *task, /** * tracehook_notify_jctl - report about job control stop/continue - * @notify: nonzero if this is the last thread in the group to stop + * @notify: zero, %CLD_STOPPED or %CLD_CONTINUED * @why: %CLD_STOPPED or %CLD_CONTINUED * * This is called when we might call do_notify_parent_cldstop(). - * It's called when about to stop for job control; we are already in - * %TASK_STOPPED state, about to call schedule(). It's also called when - * a delayed %CLD_STOPPED or %CLD_CONTINUED report is ready to be made. * - * Return nonzero to generate a %SIGCHLD with @why, which is - * normal if @notify is nonzero. + * @notify is zero if we would not ordinarily send a %SIGCHLD, + * or is the %CLD_STOPPED or %CLD_CONTINUED .si_code for %SIGCHLD. * - * Called with no locks held. + * @why is %CLD_STOPPED when about to stop for job control; + * we are already in %TASK_STOPPED state, about to call schedule(). + * It might also be that we have just exited (check %PF_EXITING), + * but need to report that a group-wide stop is complete. + * + * @why is %CLD_CONTINUED when waking up after job control stop and + * ready to make a delayed @notify report. + * + * Return the %CLD_* value for %SIGCHLD, or zero to generate no signal. + * + * Called with the siglock held. */ static inline int tracehook_notify_jctl(int notify, int why) { - return notify || (current->ptrace & PT_PTRACED); + return notify ?: (current->ptrace & PT_PTRACED) ? why : 0; +} + +/** + * tracehook_finish_jctl - report about return from job control stop + * + * This is called by do_signal_stop() after wakeup. + */ +static inline void tracehook_finish_jctl(void) +{ } #define DEATH_REAP -1 diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 63a3f7a8058..660a9de96f8 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -4,7 +4,7 @@ /* * Kernel Tracepoint API. * - * See Documentation/tracepoint.txt. + * See Documentation/trace/tracepoints.txt. * * (C) Copyright 2008 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> * diff --git a/include/linux/unaligned/be_byteshift.h b/include/linux/unaligned/be_byteshift.h index 46dd12c5709..9356b24223a 100644 --- a/include/linux/unaligned/be_byteshift.h +++ b/include/linux/unaligned/be_byteshift.h @@ -1,7 +1,7 @@ #ifndef _LINUX_UNALIGNED_BE_BYTESHIFT_H #define _LINUX_UNALIGNED_BE_BYTESHIFT_H -#include <linux/kernel.h> +#include <linux/types.h> static inline u16 __get_unaligned_be16(const u8 *p) { diff --git a/include/linux/unaligned/le_byteshift.h b/include/linux/unaligned/le_byteshift.h index 59777e951ba..be376fb79b6 100644 --- a/include/linux/unaligned/le_byteshift.h +++ b/include/linux/unaligned/le_byteshift.h @@ -1,7 +1,7 @@ #ifndef _LINUX_UNALIGNED_LE_BYTESHIFT_H #define _LINUX_UNALIGNED_LE_BYTESHIFT_H -#include <linux/kernel.h> +#include <linux/types.h> static inline u16 __get_unaligned_le16(const u8 *p) { diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 75cf58666ff..66ebddcff66 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -110,21 +110,20 @@ extern int laptop_mode; extern unsigned long determine_dirtyable_memory(void); extern int dirty_background_ratio_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern int dirty_background_bytes_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern int dirty_ratio_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); extern int dirty_bytes_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos); struct ctl_table; -struct file; -int dirty_writeback_centisecs_handler(struct ctl_table *, int, struct file *, +int dirty_writeback_centisecs_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); void get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty, diff --git a/include/net/ip.h b/include/net/ip.h index 72c36926c26..5b26a0bd178 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -399,7 +399,7 @@ extern void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 dport, * fed into the routing cache should use these handlers. */ int ipv4_doint_and_flush(ctl_table *ctl, int write, - struct file* filp, void __user *buffer, + void __user *buffer, size_t *lenp, loff_t *ppos); int ipv4_doint_and_flush_strategy(ctl_table *table, void __user *oldval, size_t __user *oldlenp, diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 1459ed3e269..f76f22d0572 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -55,7 +55,6 @@ enum { #include <net/neighbour.h> struct ctl_table; -struct file; struct inet6_dev; struct net_device; struct net_proto_family; @@ -139,7 +138,6 @@ extern int igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL extern int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, - struct file * filp, void __user *buffer, size_t *lenp, loff_t *ppos); |