diff options
Diffstat (limited to 'include')
99 files changed, 1701 insertions, 423 deletions
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 2c744c7..26a92fc 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -491,11 +491,11 @@ acpi_get_sleep_type_data(u8 sleep_state, u8 * slp_typ_a, u8 * slp_typ_b); acpi_status acpi_enter_sleep_state_prep(u8 sleep_state); -acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state, u8 flags); +acpi_status asmlinkage acpi_enter_sleep_state(u8 sleep_state); ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status asmlinkage acpi_enter_sleep_state_s4bios(void)) -acpi_status acpi_leave_sleep_state_prep(u8 sleep_state, u8 flags); +acpi_status acpi_leave_sleep_state_prep(u8 sleep_state); acpi_status acpi_leave_sleep_state(u8 sleep_state); diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 3af87de..3d00bd5 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -803,7 +803,7 @@ typedef u8 acpi_adr_space_type; /* Sleep function dispatch */ -typedef acpi_status(*ACPI_SLEEP_FUNCTION) (u8 sleep_state, u8 flags); +typedef acpi_status(*ACPI_SLEEP_FUNCTION) (u8 sleep_state); struct acpi_sleep_functions { ACPI_SLEEP_FUNCTION legacy_function; diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h index 580a6d3..c04e0db 100644 --- a/include/asm-generic/mutex-xchg.h +++ b/include/asm-generic/mutex-xchg.h @@ -26,7 +26,13 @@ static inline void __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *)) { if (unlikely(atomic_xchg(count, 0) != 1)) - fail_fn(count); + /* + * We failed to acquire the lock, so mark it contended + * to ensure that any waiting tasks are woken up by the + * unlock slow path. + */ + if (likely(atomic_xchg(count, -1) != 1)) + fail_fn(count); } /** @@ -43,7 +49,8 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *)) { if (unlikely(atomic_xchg(count, 0) != 1)) - return fail_fn(count); + if (likely(atomic_xchg(count, -1) != 1)) + return fail_fn(count); return 0; } diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h index 7ff5c99..c78bb99 100644 --- a/include/drm/drm_pciids.h +++ b/include/drm/drm_pciids.h @@ -213,9 +213,12 @@ {0x1002, 0x6800, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6801, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6802, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6806, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6808, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6809, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6810, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6816, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ + {0x1002, 0x6817, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6818, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6819, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_PITCAIRN|RADEON_NEW_MEMMAP}, \ {0x1002, 0x6820, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \ diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h index 5805686..dc3a8cd 100644 --- a/include/drm/radeon_drm.h +++ b/include/drm/radeon_drm.h @@ -964,6 +964,8 @@ struct drm_radeon_cs { #define RADEON_INFO_IB_VM_MAX_SIZE 0x0f /* max pipes - needed for compute shaders */ #define RADEON_INFO_MAX_PIPES 0x10 +/* timestamp for GL_ARB_timer_query (OpenGL), returns the current GPU clock */ +#define RADEON_INFO_TIMESTAMP 0x11 struct drm_radeon_info { uint32_t request; diff --git a/include/linux/Kbuild b/include/linux/Kbuild index d9a7544..fa21760 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -391,6 +391,7 @@ header-y += v4l2-dv-timings.h header-y += v4l2-mediabus.h header-y += v4l2-subdev.h header-y += veth.h +header-y += vfio.h header-y += vhost.h header-y += videodev2.h header-y += virtio_9p.h diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 3ad510b..4f2a762 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -96,7 +96,7 @@ void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); void acpi_numa_slit_init (struct acpi_table_slit *slit); void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); -void acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); +int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); void acpi_numa_arch_fixup(void); #ifdef CONFIG_ACPI_HOTPLUG_CPU diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h index 0254901..2a5f64a 100644 --- a/include/linux/amba/pl08x.h +++ b/include/linux/amba/pl08x.h @@ -21,8 +21,9 @@ #include <linux/dmaengine.h> #include <linux/interrupt.h> -struct pl08x_lli; struct pl08x_driver_data; +struct pl08x_phy_chan; +struct pl08x_txd; /* Bitmasks for selecting AHB ports for DMA transfers */ enum { @@ -46,170 +47,29 @@ enum { * devices with static assignments * @muxval: a number usually used to poke into some mux regiser to * mux in the signal to this channel - * @cctl_opt: default options for the channel control register + * @cctl_memcpy: options for the channel control register for memcpy + * *** not used for slave channels *** * @addr: source/target address in physical memory for this DMA channel, * can be the address of a FIFO register for burst requests for example. * This can be left undefined if the PrimeCell API is used for configuring * this. - * @circular_buffer: whether the buffer passed in is circular and - * shall simply be looped round round (like a record baby round - * round round round) * @single: the device connected to this channel will request single DMA * transfers, not bursts. (Bursts are default.) * @periph_buses: the device connected to this channel is accessible via * these buses (use PL08X_AHB1 | PL08X_AHB2). */ struct pl08x_channel_data { - char *bus_id; + const char *bus_id; int min_signal; int max_signal; u32 muxval; - u32 cctl; + u32 cctl_memcpy; dma_addr_t addr; - bool circular_buffer; bool single; u8 periph_buses; }; /** - * Struct pl08x_bus_data - information of source or destination - * busses for a transfer - * @addr: current address - * @maxwidth: the maximum width of a transfer on this bus - * @buswidth: the width of this bus in bytes: 1, 2 or 4 - */ -struct pl08x_bus_data { - dma_addr_t addr; - u8 maxwidth; - u8 buswidth; -}; - -/** - * struct pl08x_phy_chan - holder for the physical channels - * @id: physical index to this channel - * @lock: a lock to use when altering an instance of this struct - * @signal: the physical signal (aka channel) serving this physical channel - * right now - * @serving: the virtual channel currently being served by this physical - * channel - * @locked: channel unavailable for the system, e.g. dedicated to secure - * world - */ -struct pl08x_phy_chan { - unsigned int id; - void __iomem *base; - spinlock_t lock; - int signal; - struct pl08x_dma_chan *serving; - bool locked; -}; - -/** - * struct pl08x_sg - structure containing data per sg - * @src_addr: src address of sg - * @dst_addr: dst address of sg - * @len: transfer len in bytes - * @node: node for txd's dsg_list - */ -struct pl08x_sg { - dma_addr_t src_addr; - dma_addr_t dst_addr; - size_t len; - struct list_head node; -}; - -/** - * struct pl08x_txd - wrapper for struct dma_async_tx_descriptor - * @tx: async tx descriptor - * @node: node for txd list for channels - * @dsg_list: list of children sg's - * @direction: direction of transfer - * @llis_bus: DMA memory address (physical) start for the LLIs - * @llis_va: virtual memory address start for the LLIs - * @cctl: control reg values for current txd - * @ccfg: config reg values for current txd - */ -struct pl08x_txd { - struct dma_async_tx_descriptor tx; - struct list_head node; - struct list_head dsg_list; - enum dma_transfer_direction direction; - dma_addr_t llis_bus; - struct pl08x_lli *llis_va; - /* Default cctl value for LLIs */ - u32 cctl; - /* - * Settings to be put into the physical channel when we - * trigger this txd. Other registers are in llis_va[0]. - */ - u32 ccfg; -}; - -/** - * struct pl08x_dma_chan_state - holds the PL08x specific virtual channel - * states - * @PL08X_CHAN_IDLE: the channel is idle - * @PL08X_CHAN_RUNNING: the channel has allocated a physical transport - * channel and is running a transfer on it - * @PL08X_CHAN_PAUSED: the channel has allocated a physical transport - * channel, but the transfer is currently paused - * @PL08X_CHAN_WAITING: the channel is waiting for a physical transport - * channel to become available (only pertains to memcpy channels) - */ -enum pl08x_dma_chan_state { - PL08X_CHAN_IDLE, - PL08X_CHAN_RUNNING, - PL08X_CHAN_PAUSED, - PL08X_CHAN_WAITING, -}; - -/** - * struct pl08x_dma_chan - this structure wraps a DMA ENGINE channel - * @chan: wrappped abstract channel - * @phychan: the physical channel utilized by this channel, if there is one - * @phychan_hold: if non-zero, hold on to the physical channel even if we - * have no pending entries - * @tasklet: tasklet scheduled by the IRQ to handle actual work etc - * @name: name of channel - * @cd: channel platform data - * @runtime_addr: address for RX/TX according to the runtime config - * @runtime_direction: current direction of this channel according to - * runtime config - * @pend_list: queued transactions pending on this channel - * @at: active transaction on this channel - * @lock: a lock for this channel data - * @host: a pointer to the host (internal use) - * @state: whether the channel is idle, paused, running etc - * @slave: whether this channel is a device (slave) or for memcpy - * @device_fc: Flow Controller Settings for ccfg register. Only valid for slave - * channels. Fill with 'true' if peripheral should be flow controller. Direction - * will be selected at Runtime. - * @waiting: a TX descriptor on this channel which is waiting for a physical - * channel to become available - */ -struct pl08x_dma_chan { - struct dma_chan chan; - struct pl08x_phy_chan *phychan; - int phychan_hold; - struct tasklet_struct tasklet; - char *name; - const struct pl08x_channel_data *cd; - dma_addr_t src_addr; - dma_addr_t dst_addr; - u32 src_cctl; - u32 dst_cctl; - enum dma_transfer_direction runtime_direction; - struct list_head pend_list; - struct pl08x_txd *at; - spinlock_t lock; - struct pl08x_driver_data *host; - enum pl08x_dma_chan_state state; - bool slave; - bool device_fc; - struct pl08x_txd *waiting; -}; - -/** * struct pl08x_platform_data - the platform configuration for the PL08x * PrimeCells. * @slave_channels: the channels defined for the different devices on the @@ -229,8 +89,8 @@ struct pl08x_platform_data { const struct pl08x_channel_data *slave_channels; unsigned int num_slave_channels; struct pl08x_channel_data memcpy_channel; - int (*get_signal)(struct pl08x_dma_chan *); - void (*put_signal)(struct pl08x_dma_chan *); + int (*get_signal)(const struct pl08x_channel_data *); + void (*put_signal)(const struct pl08x_channel_data *, int); u8 lli_buses; u8 mem_buses; }; diff --git a/include/linux/audit.h b/include/linux/audit.h index 22f292a..36abf2a 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -130,6 +130,7 @@ #define AUDIT_LAST_KERN_ANOM_MSG 1799 #define AUDIT_ANOM_PROMISCUOUS 1700 /* Device changed promiscuous mode */ #define AUDIT_ANOM_ABEND 1701 /* Process ended abnormally */ +#define AUDIT_ANOM_LINK 1702 /* Suspicious use of file links */ #define AUDIT_INTEGRITY_DATA 1800 /* Data integrity verification */ #define AUDIT_INTEGRITY_METADATA 1801 /* Metadata integrity verification */ #define AUDIT_INTEGRITY_STATUS 1802 /* Integrity enable status */ @@ -687,6 +688,8 @@ extern void audit_log_d_path(struct audit_buffer *ab, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); +extern void audit_log_link_denied(const char *operation, + struct path *link); extern void audit_log_lost(const char *message); #ifdef CONFIG_SECURITY extern void audit_log_secctx(struct audit_buffer *ab, u32 secid); @@ -716,6 +719,7 @@ extern int audit_enabled; #define audit_log_untrustedstring(a,s) do { ; } while (0) #define audit_log_d_path(b, p, d) do { ; } while (0) #define audit_log_key(b, k) do { ; } while (0) +#define audit_log_link_denied(o, l) do { ; } while (0) #define audit_log_secctx(b,s) do { ; } while (0) #define audit_enabled 0 #endif diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 489de62..2a9a9ab 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,6 +17,7 @@ #include <linux/timer.h> #include <linux/writeback.h> #include <linux/atomic.h> +#include <linux/sysctl.h> struct page; struct device; @@ -123,7 +124,6 @@ void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, void bdi_start_background_writeback(struct backing_dev_info *bdi); int bdi_writeback_thread(void *data); int bdi_has_dirty_io(struct backing_dev_info *bdi); -void bdi_arm_supers_timer(void); void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi); void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2); @@ -304,6 +304,8 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync); void set_bdi_congested(struct backing_dev_info *bdi, int sync); long congestion_wait(int sync, long timeout); long wait_iff_congested(struct zone *zone, int sync, long timeout); +int pdflush_proc_obsolete(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) { diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index 3c80885..d323a4b 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -89,6 +89,12 @@ #define BCMA_CC_CHIPST_4313_OTP_PRESENT 2 #define BCMA_CC_CHIPST_4331_SPROM_PRESENT 2 #define BCMA_CC_CHIPST_4331_OTP_PRESENT 4 +#define BCMA_CC_CHIPST_43228_ILP_DIV_EN 0x00000001 +#define BCMA_CC_CHIPST_43228_OTP_PRESENT 0x00000002 +#define BCMA_CC_CHIPST_43228_SERDES_REFCLK_PADSEL 0x00000004 +#define BCMA_CC_CHIPST_43228_SDIO_MODE 0x00000008 +#define BCMA_CC_CHIPST_43228_SDIO_OTP_PRESENT 0x00000010 +#define BCMA_CC_CHIPST_43228_SDIO_RESET 0x00000020 #define BCMA_CC_CHIPST_4706_PKG_OPTION BIT(0) /* 0: full-featured package 1: low-cost package */ #define BCMA_CC_CHIPST_4706_SFLASH_PRESENT BIT(1) /* 0: parallel, 1: serial flash is present */ #define BCMA_CC_CHIPST_4706_SFLASH_TYPE BIT(2) /* 0: 8b-p/ST-s flash, 1: 16b-p/Atmal-s flash */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 0edb65d..7b7ac9c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -160,6 +160,7 @@ enum rq_flag_bits { __REQ_FLUSH_SEQ, /* request for flush sequence */ __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ + __REQ_KERNEL, /* direct IO to kernel pages */ __REQ_NR_BITS, /* stops here */ }; @@ -201,5 +202,6 @@ enum rq_flag_bits { #define REQ_IO_STAT (1 << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1 << __REQ_MIXED_MERGE) #define REQ_SECURE (1 << __REQ_SECURE) +#define REQ_KERNEL (1 << __REQ_KERNEL) #endif /* __LINUX_BLK_TYPES_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 07954b0..4e72a9d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -46,16 +46,23 @@ struct blkcg_gq; struct request; typedef void (rq_end_io_fn)(struct request *, int); +#define BLK_RL_SYNCFULL (1U << 0) +#define BLK_RL_ASYNCFULL (1U << 1) + struct request_list { + struct request_queue *q; /* the queue this rl belongs to */ +#ifdef CONFIG_BLK_CGROUP + struct blkcg_gq *blkg; /* blkg this request pool belongs to */ +#endif /* * count[], starved[], and wait[] are indexed by * BLK_RW_SYNC/BLK_RW_ASYNC */ - int count[2]; - int starved[2]; - int elvpriv; - mempool_t *rq_pool; - wait_queue_head_t wait[2]; + int count[2]; + int starved[2]; + mempool_t *rq_pool; + wait_queue_head_t wait[2]; + unsigned int flags; }; /* @@ -138,6 +145,7 @@ struct request { struct hd_struct *part; unsigned long start_time; #ifdef CONFIG_BLK_CGROUP + struct request_list *rl; /* rl this rq is alloced from */ unsigned long long start_time_ns; unsigned long long io_start_time_ns; /* when passed to hardware */ #endif @@ -282,11 +290,16 @@ struct request_queue { struct list_head queue_head; struct request *last_merge; struct elevator_queue *elevator; + int nr_rqs[2]; /* # allocated [a]sync rqs */ + int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ /* - * the queue request freelist, one for reads and one for writes + * If blkcg is not used, @q->root_rl serves all requests. If blkcg + * is used, root blkg allocates from @q->root_rl and all other + * blkgs from their own blkg->rl. Which one to use should be + * determined using bio_request_list(). */ - struct request_list rq; + struct request_list root_rl; request_fn_proc *request_fn; make_request_fn *make_request_fn; @@ -561,27 +574,25 @@ static inline bool rq_is_sync(struct request *rq) return rw_is_sync(rq->cmd_flags); } -static inline int blk_queue_full(struct request_queue *q, int sync) +static inline bool blk_rl_full(struct request_list *rl, bool sync) { - if (sync) - return test_bit(QUEUE_FLAG_SYNCFULL, &q->queue_flags); - return test_bit(QUEUE_FLAG_ASYNCFULL, &q->queue_flags); + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + return rl->flags & flag; } -static inline void blk_set_queue_full(struct request_queue *q, int sync) +static inline void blk_set_rl_full(struct request_list *rl, bool sync) { - if (sync) - queue_flag_set(QUEUE_FLAG_SYNCFULL, q); - else - queue_flag_set(QUEUE_FLAG_ASYNCFULL, q); + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + rl->flags |= flag; } -static inline void blk_clear_queue_full(struct request_queue *q, int sync) +static inline void blk_clear_rl_full(struct request_list *rl, bool sync) { - if (sync) - queue_flag_clear(QUEUE_FLAG_SYNCFULL, q); - else - queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q); + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + rl->flags &= ~flag; } @@ -911,11 +922,15 @@ struct blk_plug { }; #define BLK_MAX_REQUEST_COUNT 16 +struct blk_plug_cb; +typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); struct blk_plug_cb { struct list_head list; - void (*callback)(struct blk_plug_cb *); + blk_plug_cb_fn callback; + void *data; }; - +extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, + void *data, int size); extern void blk_start_plug(struct blk_plug *); extern void blk_finish_plug(struct blk_plug *); extern void blk_flush_plug_list(struct blk_plug *, bool); diff --git a/include/linux/blkpg.h b/include/linux/blkpg.h index faf8a45..a851944 100644 --- a/include/linux/blkpg.h +++ b/include/linux/blkpg.h @@ -40,6 +40,7 @@ struct blkpg_ioctl_arg { /* The subfunctions (for the op field) */ #define BLKPG_ADD_PARTITION 1 #define BLKPG_DEL_PARTITION 2 +#define BLKPG_RESIZE_PARTITION 3 /* Sizes of name fields. Unused at present. */ #define BLKPG_DEVNAMELTH 64 diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index f55ab8c..4d0fb3d 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -67,7 +67,6 @@ void bsg_job_done(struct bsg_job *job, int result, int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name, bsg_job_fn *job_fn, int dd_job_size); void bsg_request_fn(struct request_queue *q); -void bsg_remove_queue(struct request_queue *q); void bsg_goose_queue(struct request_queue *q); #endif diff --git a/include/linux/can.h b/include/linux/can.h index 018055e..e52958d 100644 --- a/include/linux/can.h +++ b/include/linux/can.h @@ -74,20 +74,21 @@ struct can_frame { /* * defined bits for canfd_frame.flags * - * As the default for CAN FD should be to support the high data rate in the - * payload section of the frame (HDR) and to support up to 64 byte in the - * data section (EDL) the bits are only set in the non-default case. - * Btw. as long as there's no real implementation for CAN FD network driver - * these bits are only preliminary. + * The use of struct canfd_frame implies the Extended Data Length (EDL) bit to + * be set in the CAN frame bitstream on the wire. The EDL bit switch turns + * the CAN controllers bitstream processor into the CAN FD mode which creates + * two new options within the CAN FD frame specification: * - * RX: NOHDR/NOEDL - info about received CAN FD frame - * ESI - bit from originating CAN controller - * TX: NOHDR/NOEDL - control per-frame settings if supported by CAN controller - * ESI - bit is set by local CAN controller + * Bit Rate Switch - to indicate a second bitrate is/was used for the payload + * Error State Indicator - represents the error state of the transmitting node + * + * As the CANFD_ESI bit is internally generated by the transmitting CAN + * controller only the CANFD_BRS bit is relevant for real CAN controllers when + * building a CAN FD frame for transmission. Setting the CANFD_ESI bit can make + * sense for virtual CAN interfaces to test applications with echoed frames. */ -#define CANFD_NOHDR 0x01 /* frame without high data rate */ -#define CANFD_NOEDL 0x02 /* frame without extended data length */ -#define CANFD_ESI 0x04 /* error state indicator */ +#define CANFD_BRS 0x01 /* bit rate switch (second bitrate for payload data) */ +#define CANFD_ESI 0x02 /* error state indicator of the transmitting node */ /** * struct canfd_frame - CAN flexible data rate frame structure diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 0bd390c..dfae957 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -31,7 +31,7 @@ SUBSYS(cpuacct) /* */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG SUBSYS(mem_cgroup) #endif @@ -72,3 +72,9 @@ SUBSYS(net_prio) #endif /* */ + +#ifdef CONFIG_CGROUP_HUGETLB +SUBSYS(hugetlb) +#endif + +/* */ diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 51a90b7..133ddcf 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -58,7 +58,7 @@ static inline bool compaction_deferred(struct zone *zone, int order) if (++zone->compact_considered > defer_limit) zone->compact_considered = defer_limit; - return zone->compact_considered < (1UL << zone->compact_defer_shift); + return zone->compact_considered < defer_limit; } #else @@ -85,7 +85,7 @@ static inline void defer_compaction(struct zone *zone, int order) static inline bool compaction_deferred(struct zone *zone, int order) { - return 1; + return true; } #endif /* CONFIG_COMPACTION */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 103adc6..ec45ccd 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -503,6 +503,8 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size); extern int __init efi_uart_console_only (void); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); +extern unsigned long efi_get_time(void); +extern int efi_set_rtc_mmss(unsigned long nowtime); extern void efi_reserve_boot_services(void); extern struct efi_memory_map memmap; diff --git a/include/linux/fs.h b/include/linux/fs.h index b178f9e..aa11047 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -165,6 +165,8 @@ struct inodes_stat_t { #define READ 0 #define WRITE RW_MASK #define READA RWA_MASK +#define KERNEL_READ (READ|REQ_KERNEL) +#define KERNEL_WRITE (WRITE|REQ_KERNEL) #define READ_SYNC (READ | REQ_SYNC) #define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE) @@ -412,6 +414,7 @@ struct inodes_stat_t { #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> +#include <linux/lockdep.h> #include <asm/byteorder.h> @@ -427,6 +430,7 @@ struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; +struct swap_info_struct; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -437,6 +441,8 @@ extern unsigned long get_max_files(void); extern int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; +extern int sysctl_protected_symlinks; +extern int sysctl_protected_hardlinks; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, @@ -636,6 +642,11 @@ struct address_space_operations { int (*is_partially_uptodate) (struct page *, read_descriptor_t *, unsigned long); int (*error_remove_page)(struct address_space *, struct page *); + + /* swapfile support */ + int (*swap_activate)(struct swap_info_struct *sis, struct file *file, + sector_t *span); + void (*swap_deactivate)(struct file *file); }; extern const struct address_space_operations empty_aops; @@ -1154,7 +1165,6 @@ struct lock_manager_operations { int (*lm_compare_owner)(struct file_lock *, struct file_lock *); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, struct file_lock *, int); - void (*lm_release_private)(struct file_lock *); void (*lm_break)(struct file_lock *); int (*lm_change)(struct file_lock **, int); }; @@ -1438,6 +1448,8 @@ extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct fown_struct *fown); +struct mm_struct; + /* * Umount options */ @@ -1451,10 +1463,34 @@ extern int send_sigurg(struct fown_struct *fown); extern struct list_head super_blocks; extern spinlock_t sb_lock; +/* Possible states of 'frozen' field */ +enum { + SB_UNFROZEN = 0, /* FS is unfrozen */ + SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ + SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ + SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop + * internal threads if needed) */ + SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ +}; + +#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) + +struct sb_writers { + /* Counters for counting writers at each level */ + struct percpu_counter counter[SB_FREEZE_LEVELS]; + wait_queue_head_t wait; /* queue for waiting for + writers / faults to finish */ + int frozen; /* Is sb frozen? */ + wait_queue_head_t wait_unfrozen; /* queue for waiting for + sb to be thawed */ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lockdep_map lock_map[SB_FREEZE_LEVELS]; +#endif +}; + struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ - unsigned char s_dirt; unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ @@ -1498,8 +1534,7 @@ struct super_block { struct hlist_node s_instances; struct quota_info s_dquot; /* Diskquota specific options */ - int s_frozen; - wait_queue_head_t s_wait_unfrozen; + struct sb_writers s_writers; char s_id[32]; /* Informational name */ u8 s_uuid[16]; /* UUID */ @@ -1554,14 +1589,117 @@ extern struct timespec current_fs_time(struct super_block *sb); /* * Snapshotting support. */ -enum { - SB_UNFROZEN = 0, - SB_FREEZE_WRITE = 1, - SB_FREEZE_TRANS = 2, -}; -#define vfs_check_frozen(sb, level) \ - wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level))) +void __sb_end_write(struct super_block *sb, int level); +int __sb_start_write(struct super_block *sb, int level, bool wait); + +/** + * sb_end_write - drop write access to a superblock + * @sb: the super we wrote to + * + * Decrement number of writers to the filesystem. Wake up possible waiters + * wanting to freeze the filesystem. + */ +static inline void sb_end_write(struct super_block *sb) +{ + __sb_end_write(sb, SB_FREEZE_WRITE); +} + +/** + * sb_end_pagefault - drop write access to a superblock from a page fault + * @sb: the super we wrote to + * + * Decrement number of processes handling write page fault to the filesystem. + * Wake up possible waiters wanting to freeze the filesystem. + */ +static inline void sb_end_pagefault(struct super_block *sb) +{ + __sb_end_write(sb, SB_FREEZE_PAGEFAULT); +} + +/** + * sb_end_intwrite - drop write access to a superblock for internal fs purposes + * @sb: the super we wrote to + * + * Decrement fs-internal number of writers to the filesystem. Wake up possible + * waiters wanting to freeze the filesystem. + */ +static inline void sb_end_intwrite(struct super_block *sb) +{ + __sb_end_write(sb, SB_FREEZE_FS); +} + +/** + * sb_start_write - get write access to a superblock + * @sb: the super we write to + * + * When a process wants to write data or metadata to a file system (i.e. dirty + * a page or an inode), it should embed the operation in a sb_start_write() - + * sb_end_write() pair to get exclusion against file system freezing. This + * function increments number of writers preventing freezing. If the file + * system is already frozen, the function waits until the file system is + * thawed. + * + * Since freeze protection behaves as a lock, users have to preserve + * ordering of freeze protection and other filesystem locks. Generally, + * freeze protection should be the outermost lock. In particular, we have: + * + * sb_start_write + * -> i_mutex (write path, truncate, directory ops, ...) + * -> s_umount (freeze_super, thaw_super) + */ +static inline void sb_start_write(struct super_block *sb) +{ + __sb_start_write(sb, SB_FREEZE_WRITE, true); +} + +static inline int sb_start_write_trylock(struct super_block *sb) +{ + return __sb_start_write(sb, SB_FREEZE_WRITE, false); +} + +/** + * sb_start_pagefault - get write access to a superblock from a page fault + * @sb: the super we write to + * + * When a process starts handling write page fault, it should embed the + * operation into sb_start_pagefault() - sb_end_pagefault() pair to get + * exclusion against file system freezing. This is needed since the page fault + * is going to dirty a page. This function increments number of running page + * faults preventing freezing. If the file system is already frozen, the + * function waits until the file system is thawed. + * + * Since page fault freeze protection behaves as a lock, users have to preserve + * ordering of freeze protection and other filesystem locks. It is advised to + * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault + * handling code implies lock dependency: + * + * mmap_sem + * -> sb_start_pagefault + */ +static inline void sb_start_pagefault(struct super_block *sb) +{ + __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true); +} + +/* + * sb_start_intwrite - get write access to a superblock for internal fs purposes + * @sb: the super we write to + * + * This is the third level of protection against filesystem freezing. It is + * free for use by a filesystem. The only requirement is that it must rank + * below sb_start_pagefault. + * + * For example filesystem can call sb_start_intwrite() when starting a + * transaction which somewhat eases handling of freezing for internal sources + * of filesystem changes (internal fs threads, discarding preallocation on file + * close, etc.). + */ +static inline void sb_start_intwrite(struct super_block *sb) +{ + __sb_start_write(sb, SB_FREEZE_FS, true); +} + extern bool inode_owner_or_capable(const struct inode *inode); @@ -1722,7 +1860,6 @@ struct super_operations { int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); - void (*write_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_fs) (struct super_block *); int (*unfreeze_fs) (struct super_block *); @@ -1885,6 +2022,7 @@ struct file_system_type { struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; + struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; @@ -2257,7 +2395,6 @@ extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); -extern void sync_supers(void); extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK @@ -2327,9 +2464,6 @@ static inline void i_readcount_inc(struct inode *inode) } #endif extern int do_pipe_flags(int *, int); -extern struct file *create_read_pipe(struct file *f, int flags); -extern struct file *create_write_pipe(int flags); -extern void free_write_pipe(struct file *); extern int kernel_read(struct file *, loff_t, char *, unsigned long); extern struct file * open_exec(const char *); diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index af961d6..642928c 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -306,9 +306,10 @@ extern void *perf_trace_buf_prepare(int size, unsigned short type, static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr, - u64 count, struct pt_regs *regs, void *head) + u64 count, struct pt_regs *regs, void *head, + struct task_struct *task) { - perf_tp_event(addr, count, raw_data, size, regs, head, rctx); + perf_tp_event(addr, count, raw_data, size, regs, head, rctx, task); } #endif diff --git a/include/linux/fuse.h b/include/linux/fuse.h index 9303348..d8c713e 100644 --- a/include/linux/fuse.h +++ b/include/linux/fuse.h @@ -57,6 +57,9 @@ * * 7.19 * - add FUSE_FALLOCATE + * + * 7.20 + * - add FUSE_AUTO_INVAL_DATA */ #ifndef _LINUX_FUSE_H @@ -88,7 +91,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 19 +#define FUSE_KERNEL_MINOR_VERSION 20 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -163,10 +166,19 @@ struct fuse_file_lock { /** * INIT request/reply flags * + * FUSE_ASYNC_READ: asynchronous read requests * FUSE_POSIX_LOCKS: remote locking for POSIX file locks + * FUSE_FILE_OPS: kernel sends file handle for fstat, etc... (not yet supported) + * FUSE_ATOMIC_O_TRUNC: handles the O_TRUNC open flag in the filesystem * FUSE_EXPORT_SUPPORT: filesystem handles lookups of "." and ".." + * FUSE_BIG_WRITES: filesystem can handle write size larger than 4kB * FUSE_DONT_MASK: don't apply umask to file mode on create operations + * FUSE_SPLICE_WRITE: kernel supports splice write on the device + * FUSE_SPLICE_MOVE: kernel supports splice move on the device + * FUSE_SPLICE_READ: kernel supports splice read on the device * FUSE_FLOCK_LOCKS: remote locking for BSD style file locks + * FUSE_HAS_IOCTL_DIR: kernel supports ioctl on directories + * FUSE_AUTO_INVAL_DATA: automatically invalidate cached pages */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -175,7 +187,12 @@ struct fuse_file_lock { #define FUSE_EXPORT_SUPPORT (1 << 4) #define FUSE_BIG_WRITES (1 << 5) #define FUSE_DONT_MASK (1 << 6) +#define FUSE_SPLICE_WRITE (1 << 7) +#define FUSE_SPLICE_MOVE (1 << 8) +#define FUSE_SPLICE_READ (1 << 9) #define FUSE_FLOCK_LOCKS (1 << 10) +#define FUSE_HAS_IOCTL_DIR (1 << 11) +#define FUSE_AUTO_INVAL_DATA (1 << 12) /** * CUSE INIT request/reply flags diff --git a/include/linux/genhd.h b/include/linux/genhd.h index ae0aaa9..4f440b3 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -97,7 +97,13 @@ struct partition_meta_info { struct hd_struct { sector_t start_sect; + /* + * nr_sects is protected by sequence counter. One might extend a + * partition while IO is happening to it and update of nr_sects + * can be non-atomic on 32bit machines with 64bit sector_t. + */ sector_t nr_sects; + seqcount_t nr_sects_seq; sector_t alignment_offset; unsigned int discard_alignment; struct device __dev; @@ -647,6 +653,57 @@ static inline void hd_struct_put(struct hd_struct *part) __delete_partition(part); } +/* + * Any access of part->nr_sects which is not protected by partition + * bd_mutex or gendisk bdev bd_mutex, should be done using this + * accessor function. + * + * Code written along the lines of i_size_read() and i_size_write(). + * CONFIG_PREEMPT case optimizes the case of UP kernel with preemption + * on. + */ +static inline sector_t part_nr_sects_read(struct hd_struct *part) +{ +#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP) + sector_t nr_sects; + unsigned seq; + do { + seq = read_seqcount_begin(&part->nr_sects_seq); + nr_sects = part->nr_sects; + } while (read_seqcount_retry(&part->nr_sects_seq, seq)); + return nr_sects; +#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT) + sector_t nr_sects; + + preempt_disable(); + nr_sects = part->nr_sects; + preempt_enable(); + return nr_sects; +#else + return part->nr_sects; +#endif +} + +/* + * Should be called with mutex lock held (typically bd_mutex) of partition + * to provide mutual exlusion among writers otherwise seqcount might be + * left in wrong state leaving the readers spinning infinitely. + */ +static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) +{ +#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP) + write_seqcount_begin(&part->nr_sects_seq); + part->nr_sects = size; + write_seqcount_end(&part->nr_sects_seq); +#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT) + preempt_disable(); + part->nr_sects = size; + preempt_enable(); +#else + part->nr_sects = size; +#endif +} + #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 1e49be4..4883f39 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -23,6 +23,7 @@ struct vm_area_struct; #define ___GFP_REPEAT 0x400u #define ___GFP_NOFAIL 0x800u #define ___GFP_NORETRY 0x1000u +#define ___GFP_MEMALLOC 0x2000u #define ___GFP_COMP 0x4000u #define ___GFP_ZERO 0x8000u #define ___GFP_NOMEMALLOC 0x10000u @@ -76,9 +77,14 @@ struct vm_area_struct; #define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) /* See above */ #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) /* See above */ #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) /* See above */ +#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC)/* Allow access to emergency reserves */ #define __GFP_COMP ((__force gfp_t)___GFP_COMP) /* Add compound page metadata */ #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) /* Return zeroed page on success */ -#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves */ +#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves. + * This takes precedence over the + * __GFP_MEMALLOC flag if both are + * set + */ #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */ #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */ @@ -129,7 +135,7 @@ struct vm_area_struct; /* Control page allocator reclaim behavior */ #define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\ - __GFP_NORETRY|__GFP_NOMEMALLOC) + __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC) /* Control slab gfp mask during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS)) @@ -379,6 +385,9 @@ void drain_local_pages(void *dummy); */ extern gfp_t gfp_allowed_mask; +/* Returns true if the gfp_mask allows use of ALLOC_NO_WATERMARK */ +bool gfp_pfmemalloc_allowed(gfp_t gfp_mask); + extern void pm_restrict_gfp_mask(void); extern void pm_restore_gfp_mask(void); diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index bb7f309..305f23c 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -22,7 +22,7 @@ * * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024) * - bit 26 is the NMI_MASK - * - bit 28 is the PREEMPT_ACTIVE flag + * - bit 27 is the PREEMPT_ACTIVE flag * * PREEMPT_MASK: 0x000000ff * SOFTIRQ_MASK: 0x0000ff00 diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 774fa47..ef788b5 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -39,10 +39,17 @@ extern unsigned long totalhigh_pages; void kmap_flush_unused(void); +struct page *kmap_to_page(void *addr); + #else /* CONFIG_HIGHMEM */ static inline unsigned int nr_free_highpages(void) { return 0; } +static inline struct page *kmap_to_page(void *addr) +{ + return virt_to_page(addr); +} + #define totalhigh_pages 0UL #ifndef ARCH_HAS_KMAP diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d5d6bbe..2251648 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -4,9 +4,11 @@ #include <linux/mm_types.h> #include <linux/fs.h> #include <linux/hugetlb_inline.h> +#include <linux/cgroup.h> struct ctl_table; struct user_struct; +struct mmu_gather; #ifdef CONFIG_HUGETLB_PAGE @@ -20,6 +22,11 @@ struct hugepage_subpool { long max_hpages, used_hpages; }; +extern spinlock_t hugetlb_lock; +extern int hugetlb_max_hstate __read_mostly; +#define for_each_hstate(h) \ + for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++) + struct hugepage_subpool *hugepage_new_subpool(long nr_blocks); void hugepage_put_subpool(struct hugepage_subpool *spool); @@ -40,9 +47,14 @@ int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int, unsigned int flags); void unmap_hugepage_range(struct vm_area_struct *, - unsigned long, unsigned long, struct page *); -void __unmap_hugepage_range(struct vm_area_struct *, - unsigned long, unsigned long, struct page *); + unsigned long, unsigned long, struct page *); +void __unmap_hugepage_range_final(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page); +void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page); int hugetlb_prefault(struct address_space *, struct vm_area_struct *); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(int, char *); @@ -98,7 +110,6 @@ static inline unsigned long hugetlb_total_pages(void) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) #define hugetlb_prefault(mapping, vma) ({ BUG(); 0; }) -#define unmap_hugepage_range(vma, start, end, page) BUG() static inline void hugetlb_report_meminfo(struct seq_file *m) { } @@ -112,13 +123,31 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; }) #define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; }) #define huge_pte_offset(mm, address) 0 -#define dequeue_hwpoisoned_huge_page(page) 0 +static inline int dequeue_hwpoisoned_huge_page(struct page *page) +{ + return 0; +} + static inline void copy_huge_page(struct page *dst, struct page *src) { } #define hugetlb_change_protection(vma, address, end, newprot) +static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, struct page *ref_page) +{ + BUG(); +} + +static inline void __unmap_hugepage_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start, + unsigned long end, struct page *ref_page) +{ + BUG(); +} + #endif /* !CONFIG_HUGETLB_PAGE */ #define HUGETLB_ANON_FILE "anon_hugepage" @@ -199,10 +228,15 @@ struct hstate { unsigned long resv_huge_pages; unsigned long surplus_huge_pages; unsigned long nr_overcommit_huge_pages; + struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; +#ifdef CONFIG_CGROUP_HUGETLB + /* cgroup control files */ + struct cftype cgroup_files[5]; +#endif char name[HSTATE_NAME_LEN]; }; @@ -302,6 +336,11 @@ static inline unsigned hstate_index_to_shift(unsigned index) return hstates[index].order + PAGE_SHIFT; } +static inline int hstate_index(struct hstate *h) +{ + return h - hstates; +} + #else struct hstate {}; #define alloc_huge_page_node(h, nid) NULL @@ -320,6 +359,7 @@ static inline unsigned int pages_per_huge_page(struct hstate *h) return 1; } #define hstate_index_to_shift(index) 0 +#define hstate_index(h) 0 #endif #endif /* _LINUX_HUGETLB_H */ diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h new file mode 100644 index 0000000..d73878c --- /dev/null +++ b/include/linux/hugetlb_cgroup.h @@ -0,0 +1,126 @@ +/* + * Copyright IBM Corporation, 2012 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + * + */ + +#ifndef _LINUX_HUGETLB_CGROUP_H +#define _LINUX_HUGETLB_CGROUP_H + +#include <linux/res_counter.h> + +struct hugetlb_cgroup; +/* + * Minimum page order trackable by hugetlb cgroup. + * At least 3 pages are necessary for all the tracking information. + */ +#define HUGETLB_CGROUP_MIN_ORDER 2 + +#ifdef CONFIG_CGROUP_HUGETLB + +static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) +{ + VM_BUG_ON(!PageHuge(page)); + + if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) + return NULL; + return (struct hugetlb_cgroup *)page[2].lru.next; +} + +static inline +int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) +{ + VM_BUG_ON(!PageHuge(page)); + + if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) + return -1; + page[2].lru.next = (void *)h_cg; + return 0; +} + +static inline bool hugetlb_cgroup_disabled(void) +{ + if (hugetlb_subsys.disabled) + return true; + return false; +} + +extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup **ptr); +extern void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg, + struct page *page); +extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, + struct page *page); +extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg); +extern int hugetlb_cgroup_file_init(int idx) __init; +extern void hugetlb_cgroup_migrate(struct page *oldhpage, + struct page *newhpage); + +#else +static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) +{ + return NULL; +} + +static inline +int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg) +{ + return 0; +} + +static inline bool hugetlb_cgroup_disabled(void) +{ + return true; +} + +static inline int +hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup **ptr) +{ + return 0; +} + +static inline void +hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg, + struct page *page) +{ + return; +} + +static inline void +hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, struct page *page) +{ + return; +} + +static inline void +hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages, + struct hugetlb_cgroup *h_cg) +{ + return; +} + +static inline int __init hugetlb_cgroup_file_init(int idx) +{ + return 0; +} + +static inline void hugetlb_cgroup_migrate(struct page *oldhpage, + struct page *newhpage) +{ + return; +} + +#endif /* CONFIG_MEM_RES_CTLR_HUGETLB */ +#endif diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 6960fc1..aa2e167 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -96,21 +96,6 @@ static inline void team_netpoll_send_skb(struct team_port *port, } #endif -static inline int team_dev_queue_xmit(struct team *team, struct team_port *port, - struct sk_buff *skb) -{ - BUILD_BUG_ON(sizeof(skb->queue_mapping) != - sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping)); - skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); - - skb->dev = port->dev; - if (unlikely(netpoll_tx_running(port->dev))) { - team_netpoll_send_skb(port, skb); - return 0; - } - return dev_queue_xmit(skb); -} - struct team_mode_ops { int (*init)(struct team *team); void (*exit)(struct team *team); @@ -200,6 +185,21 @@ struct team { long mode_priv[TEAM_MODE_PRIV_LONGS]; }; +static inline int team_dev_queue_xmit(struct team *team, struct team_port *port, + struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(skb->queue_mapping) != + sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping)); + skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); + + skb->dev = port->dev; + if (unlikely(netpoll_tx_running(team->dev))) { + team_netpoll_send_skb(port, skb); + return 0; + } + return dev_queue_xmit(skb); +} + static inline struct hlist_head *team_port_index_hash(struct team *team, int port_index) { diff --git a/include/linux/iio/frequency/adf4350.h b/include/linux/iio/frequency/adf4350.h index b76b4a8..be91f34 100644 --- a/include/linux/iio/frequency/adf4350.h +++ b/include/linux/iio/frequency/adf4350.h @@ -87,6 +87,8 @@ #define ADF4350_MAX_BANDSEL_CLK 125000 /* Hz */ #define ADF4350_MAX_FREQ_REFIN 250000000 /* Hz */ #define ADF4350_MAX_MODULUS 4095 +#define ADF4350_MAX_R_CNT 1023 + /** * struct adf4350_platform_data - platform specific information diff --git a/include/linux/input/eeti_ts.h b/include/linux/input/eeti_ts.h index f875b31..16625d7 100644 --- a/include/linux/input/eeti_ts.h +++ b/include/linux/input/eeti_ts.h @@ -2,6 +2,7 @@ #define LINUX_INPUT_EETI_TS_H struct eeti_ts_platform_data { + int irq_gpio; unsigned int irq_active_high; }; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index e68a8e5..c5f856a 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -42,7 +42,6 @@ * * IRQF_DISABLED - keep irqs disabled when calling the action handler. * DEPRECATED. This flag is a NOOP and scheduled to be removed - * IRQF_SAMPLE_RANDOM - irq is used to feed the random generator * IRQF_SHARED - allow sharing the irq among several devices * IRQF_PROBE_SHARED - set by callers when they expect sharing mismatches to occur * IRQF_TIMER - Flag to mark this interrupt as timer interrupt @@ -61,7 +60,6 @@ * resume time. */ #define IRQF_DISABLED 0x00000020 -#define IRQF_SAMPLE_RANDOM 0x00000040 #define IRQF_SHARED 0x00000080 #define IRQF_PROBE_SHARED 0x00000100 #define __IRQF_TIMER 0x00000200 diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 54d6d69..7e83370 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -20,6 +20,7 @@ #define __LINUX_IOMMU_H #include <linux/errno.h> +#include <linux/types.h> #define IOMMU_READ (1) #define IOMMU_WRITE (2) @@ -30,6 +31,7 @@ struct iommu_group; struct bus_type; struct device; struct iommu_domain; +struct notifier_block; /* iommu fault flags */ #define IOMMU_FAULT_READ 0x0 diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 379e433..879db26 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -369,6 +369,7 @@ struct ipv6_pinfo { __u8 rcv_tclass; __u32 dst_cookie; + __u32 rx_dst_cookie; struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; diff --git a/include/linux/irq.h b/include/linux/irq.h index 553fb66..216b0ba 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -349,6 +349,7 @@ enum { IRQCHIP_MASK_ON_SUSPEND = (1 << 2), IRQCHIP_ONOFFLINE_ENABLED = (1 << 3), IRQCHIP_SKIP_SET_WAKE = (1 << 4), + IRQCHIP_ONESHOT_SAFE = (1 << 5), }; /* This include will go away once we isolated irq_desc usage to core code */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index f1e2527..9a323d1 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -39,7 +39,6 @@ struct module; */ struct irq_desc { struct irq_data irq_data; - struct timer_rand_state *timer_rand_state; unsigned int __percpu *kstat_irqs; irq_flow_handler_t handle_irq; #ifdef CONFIG_IRQ_PREFLOW_FASTEOI diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 5abb533..0d5b17b 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -112,6 +112,11 @@ struct irq_domain { }; #ifdef CONFIG_IRQ_DOMAIN +struct irq_domain *irq_domain_add_simple(struct device_node *of_node, + unsigned int size, + unsigned int first_irq, + const struct irq_domain_ops *ops, + void *host_data); struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, unsigned int size, unsigned int first_irq, @@ -144,16 +149,31 @@ static inline struct irq_domain *irq_domain_add_legacy_isa( extern void irq_domain_remove(struct irq_domain *host); +extern int irq_domain_associate_many(struct irq_domain *domain, + unsigned int irq_base, + irq_hw_number_t hwirq_base, int count); +static inline int irq_domain_associate(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + return irq_domain_associate_many(domain, irq, hwirq, 1); +} + extern unsigned int irq_create_mapping(struct irq_domain *host, irq_hw_number_t hwirq); extern void irq_dispose_mapping(unsigned int virq); extern unsigned int irq_find_mapping(struct irq_domain *host, irq_hw_number_t hwirq); extern unsigned int irq_create_direct_mapping(struct irq_domain *host); -extern void irq_radix_revmap_insert(struct irq_domain *host, unsigned int virq, - irq_hw_number_t hwirq); -extern unsigned int irq_radix_revmap_lookup(struct irq_domain *host, - irq_hw_number_t hwirq); +extern int irq_create_strict_mappings(struct irq_domain *domain, + unsigned int irq_base, + irq_hw_number_t hwirq_base, int count); + +static inline int irq_create_identity_mapping(struct irq_domain *host, + irq_hw_number_t hwirq) +{ + return irq_create_strict_mappings(host, hwirq, hwirq, 1); +} + extern unsigned int irq_linear_revmap(struct irq_domain *host, irq_hw_number_t hwirq); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index f334c7f..3efc43f 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1125,6 +1125,7 @@ extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); +extern void jbd2_journal_update_sb_errno(journal_t *); extern void jbd2_journal_update_sb_log_tail (journal_t *, tid_t, unsigned long, int); extern void __jbd2_journal_abort_hard (journal_t *); diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 265e2c3..8268054 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -39,9 +39,6 @@ # error Invalid value of HZ. #endif -/* LATCH is used in the interval timer and ftape setup. */ -#define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ) /* For divider */ - /* Suppose we want to divide two numbers NOM and DEN: NOM/DEN, then we can * improve accuracy by shifting LSH bits, hence calculating: * (NOM << LSH) / DEN @@ -54,18 +51,30 @@ #define SH_DIV(NOM,DEN,LSH) ( (((NOM) / (DEN)) << (LSH)) \ + ((((NOM) % (DEN)) << (LSH)) + (DEN) / 2) / (DEN)) -/* HZ is the requested value. ACTHZ is actual HZ ("<< 8" is for accuracy) */ -#define ACTHZ (SH_DIV (CLOCK_TICK_RATE, LATCH, 8)) +#ifdef CLOCK_TICK_RATE +/* LATCH is used in the interval timer and ftape setup. */ +# define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ) /* For divider */ + +/* + * HZ is the requested value. However the CLOCK_TICK_RATE may not allow + * for exactly HZ. So SHIFTED_HZ is high res HZ ("<< 8" is for accuracy) + */ +# define SHIFTED_HZ (SH_DIV(CLOCK_TICK_RATE, LATCH, 8)) +#else +# define SHIFTED_HZ (HZ << 8) +#endif -/* TICK_NSEC is the time between ticks in nsec assuming real ACTHZ */ -#define TICK_NSEC (SH_DIV (1000000UL * 1000, ACTHZ, 8)) +/* TICK_NSEC is the time between ticks in nsec assuming SHIFTED_HZ */ +#define TICK_NSEC (SH_DIV(1000000UL * 1000, SHIFTED_HZ, 8)) /* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ #define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) -/* TICK_USEC_TO_NSEC is the time between ticks in nsec assuming real ACTHZ and */ -/* a value TUSEC for TICK_USEC (can be set bij adjtimex) */ -#define TICK_USEC_TO_NSEC(TUSEC) (SH_DIV (TUSEC * USER_HZ * 1000, ACTHZ, 8)) +/* + * TICK_USEC_TO_NSEC is the time between ticks in nsec assuming SHIFTED_HZ and + * a value TUSEC for TICK_USEC (can be set bij adjtimex) + */ +#define TICK_USEC_TO_NSEC(TUSEC) (SH_DIV(TUSEC * USER_HZ * 1000, SHIFTED_HZ, 8)) /* some arch's have a small-data section that can be accessed register-relative * but that can only take up to, say, 4-byte variables. jiffies being part of diff --git a/include/linux/kdb.h b/include/linux/kdb.h index 0647258..42d9e86 100644 --- a/include/linux/kdb.h +++ b/include/linux/kdb.h @@ -75,8 +75,6 @@ extern const char *kdb_diemsg; #define KDB_FLAG_CATASTROPHIC (1 << 1) /* A catastrophic event has occurred */ #define KDB_FLAG_CMD_INTERRUPT (1 << 2) /* Previous command was interrupted */ #define KDB_FLAG_NOIPI (1 << 3) /* Do not send IPIs */ -#define KDB_FLAG_ONLY_DO_DUMP (1 << 4) /* Only do a dump, used when - * kdb is off */ #define KDB_FLAG_NO_CONSOLE (1 << 5) /* No console is available, * kdb is disabled */ #define KDB_FLAG_NO_VT_CONSOLE (1 << 6) /* No VT console is available, do diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 83e7ba9..8d9489f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -38,7 +38,7 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG /* * All "charge" functions with gfp_mask should use GFP_KERNEL or * (gfp_mask & GFP_RECLAIM_MASK). In current implementatin, memcg doesn't @@ -72,8 +72,6 @@ extern void mem_cgroup_uncharge_end(void); extern void mem_cgroup_uncharge_page(struct page *page); extern void mem_cgroup_uncharge_cache_page(struct page *page); -extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, - int order); bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg, struct mem_cgroup *memcg); int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg); @@ -100,9 +98,9 @@ int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); -extern int -mem_cgroup_prepare_migration(struct page *page, - struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask); +extern void +mem_cgroup_prepare_migration(struct page *page, struct page *newpage, + struct mem_cgroup **memcgp); extern void mem_cgroup_end_migration(struct mem_cgroup *memcg, struct page *oldpage, struct page *newpage, bool migration_ok); @@ -124,7 +122,7 @@ extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, extern void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP extern int do_swap_account; #endif @@ -182,7 +180,6 @@ static inline void mem_cgroup_dec_page_stat(struct page *page, unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, unsigned long *total_scanned); -u64 mem_cgroup_get_limit(struct mem_cgroup *memcg); void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -193,7 +190,7 @@ void mem_cgroup_split_huge_fixup(struct page *head); bool mem_cgroup_bad_page_check(struct page *page); void mem_cgroup_print_bad_page(struct page *page); #endif -#else /* CONFIG_CGROUP_MEM_RES_CTLR */ +#else /* CONFIG_MEMCG */ struct mem_cgroup; static inline int mem_cgroup_newpage_charge(struct page *page, @@ -279,11 +276,10 @@ static inline struct cgroup_subsys_state return NULL; } -static inline int +static inline void mem_cgroup_prepare_migration(struct page *page, struct page *newpage, - struct mem_cgroup **memcgp, gfp_t gfp_mask) + struct mem_cgroup **memcgp) { - return 0; } static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg, @@ -366,12 +362,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, return 0; } -static inline -u64 mem_cgroup_get_limit(struct mem_cgroup *memcg) -{ - return 0; -} - static inline void mem_cgroup_split_huge_fixup(struct page *head) { } @@ -384,9 +374,9 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage, struct page *newpage) { } -#endif /* CONFIG_CGROUP_MEM_RES_CTLR */ +#endif /* CONFIG_MEMCG */ -#if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM) +#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM) static inline bool mem_cgroup_bad_page_check(struct page *page) { @@ -406,7 +396,7 @@ enum { }; struct sock; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM void sock_update_memcg(struct sock *sk); void sock_release_memcg(struct sock *sk); #else @@ -416,6 +406,6 @@ static inline void sock_update_memcg(struct sock *sk) static inline void sock_release_memcg(struct sock *sk) { } -#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */ +#endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/mempool.h b/include/linux/mempool.h index 7c08052..39ed62a 100644 --- a/include/linux/mempool.h +++ b/include/linux/mempool.h @@ -26,7 +26,8 @@ typedef struct mempool_s { extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, - mempool_free_t *free_fn, void *pool_data, int nid); + mempool_free_t *free_fn, void *pool_data, + gfp_t gfp_mask, int nid); extern int mempool_resize(mempool_t *pool, int new_min_nr, gfp_t gfp_mask); extern void mempool_destroy(mempool_t *pool); diff --git a/include/linux/mfd/ezx-pcap.h b/include/linux/mfd/ezx-pcap.h index 40c37216..32a1b5c 100644 --- a/include/linux/mfd/ezx-pcap.h +++ b/include/linux/mfd/ezx-pcap.h @@ -16,6 +16,7 @@ struct pcap_subdev { struct pcap_platform_data { unsigned int irq_base; unsigned int config; + int gpio; void (*init) (void *); /* board specific init */ int num_subdevs; struct pcap_subdev *subdevs; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 855c337..ce7e667 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -15,7 +15,7 @@ extern int migrate_page(struct address_space *, extern int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, enum migrate_mode mode); -extern int migrate_huge_pages(struct list_head *l, new_page_t x, +extern int migrate_huge_page(struct page *, new_page_t x, unsigned long private, bool offlining, enum migrate_mode mode); @@ -36,7 +36,7 @@ static inline void putback_lru_pages(struct list_head *l) {} static inline int migrate_pages(struct list_head *l, new_page_t x, unsigned long private, bool offlining, enum migrate_mode mode) { return -ENOSYS; } -static inline int migrate_huge_pages(struct list_head *l, new_page_t x, +static inline int migrate_huge_page(struct page *page, new_page_t x, unsigned long private, bool offlining, enum migrate_mode mode) { return -ENOSYS; } diff --git a/include/linux/mm.h b/include/linux/mm.h index f9f279c..311be90 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -805,6 +805,17 @@ static inline void *page_rmapping(struct page *page) return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS); } +extern struct address_space *__page_file_mapping(struct page *); + +static inline +struct address_space *page_file_mapping(struct page *page) +{ + if (unlikely(PageSwapCache(page))) + return __page_file_mapping(page); + + return page->mapping; +} + static inline int PageAnon(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; @@ -821,6 +832,20 @@ static inline pgoff_t page_index(struct page *page) return page->index; } +extern pgoff_t __page_file_index(struct page *page); + +/* + * Return the file index of the page. Regular pagecache pages use ->index + * whereas swapcache pages use swp_offset(->private) + */ +static inline pgoff_t page_file_index(struct page *page) +{ + if (unlikely(PageSwapCache(page))) + return __page_file_index(page); + + return page->index; +} + /* * Return true if this page is mapped into pagetables. */ @@ -994,6 +1019,10 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, struct page **pages, struct vm_area_struct **vmas); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); +struct kvec; +int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, + struct page **pages); +int get_kernel_page(unsigned long start, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); @@ -1331,6 +1360,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...); extern void setup_per_cpu_pageset(void); extern void zone_pcp_update(struct zone *zone); +extern void zone_pcp_reset(struct zone *zone); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; @@ -1411,6 +1441,7 @@ extern void truncate_inode_pages_range(struct address_space *, /* generic vm_area_ops exported for stackable file systems */ extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); +extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); /* mm/page-writeback.c */ int write_one_page(struct page *page, int wait); @@ -1528,6 +1559,7 @@ void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long); static inline void vm_stat_account(struct mm_struct *mm, unsigned long flags, struct file *file, long pages) { + mm->total_vm += pages; } #endif /* CONFIG_PROC_FS */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 074eb98..bf78672 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -54,6 +54,15 @@ struct page { union { pgoff_t index; /* Our offset within mapping. */ void *freelist; /* slub/slob first free object */ + bool pfmemalloc; /* If set by the page allocator, + * ALLOC_NO_WATERMARKS was set + * and the low watermark was not + * met implying that the system + * is under some pressure. The + * caller should try ensure + * this page is only used to + * free other pages. + */ }; union { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 458988b..2daa54f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -201,7 +201,7 @@ struct zone_reclaim_stat { struct lruvec { struct list_head lists[NR_LRU_LISTS]; struct zone_reclaim_stat reclaim_stat; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG struct zone *zone; #endif }; @@ -209,7 +209,6 @@ struct lruvec { /* Mask used at gathering information at once (see memcontrol.c) */ #define LRU_ALL_FILE (BIT(LRU_INACTIVE_FILE) | BIT(LRU_ACTIVE_FILE)) #define LRU_ALL_ANON (BIT(LRU_INACTIVE_ANON) | BIT(LRU_ACTIVE_ANON)) -#define LRU_ALL_EVICTABLE (LRU_ALL_FILE | LRU_ALL_ANON) #define LRU_ALL ((1 << NR_LRU_LISTS) - 1) /* Isolate clean file */ @@ -369,6 +368,10 @@ struct zone { */ spinlock_t lock; int all_unreclaimable; /* All pages pinned */ +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* pfn where the last incremental compaction isolated free pages */ + unsigned long compact_cached_free_pfn; +#endif #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; @@ -475,6 +478,14 @@ struct zone { * rarely used fields: */ const char *name; +#ifdef CONFIG_MEMORY_ISOLATION + /* + * the number of MIGRATE_ISOLATE *pageblock*. + * We need this for free page counting. Look at zone_watermark_ok_safe. + * It's protected by zone->lock + */ + int nr_pageblock_isolate; +#endif } ____cacheline_internodealigned_in_smp; typedef enum { @@ -671,7 +682,7 @@ typedef struct pglist_data { int nr_zones; #ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ struct page *node_mem_map; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG struct page_cgroup *node_page_cgroup; #endif #endif @@ -694,6 +705,7 @@ typedef struct pglist_data { range, including holes */ int node_id; wait_queue_head_t kswapd_wait; + wait_queue_head_t pfmemalloc_wait; struct task_struct *kswapd; /* Protected by lock_memory_hotplug() */ int kswapd_max_order; enum zone_type classzone_idx; @@ -718,7 +730,7 @@ typedef struct pglist_data { #include <linux/memory_hotplug.h> extern struct mutex zonelists_mutex; -void build_all_zonelists(void *data); +void build_all_zonelists(pg_data_t *pgdat, struct zone *zone); void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx); bool zone_watermark_ok(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags); @@ -736,7 +748,7 @@ extern void lruvec_init(struct lruvec *lruvec, struct zone *zone); static inline struct zone *lruvec_zone(struct lruvec *lruvec) { -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG return lruvec->zone; #else return container_of(lruvec, struct zone, lruvec); @@ -773,7 +785,7 @@ extern int movable_zone; static inline int zone_movable_is_highmem(void) { -#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE) +#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) return movable_zone == ZONE_HIGHMEM; #else return 0; @@ -1052,7 +1064,7 @@ struct mem_section { /* See declaration of similar field in struct zone */ unsigned long *pageblock_flags; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG /* * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use * section. (see memcontrol.h/page_cgroup.h about this.) diff --git a/include/linux/namei.h b/include/linux/namei.h index d2ef8b3..4bf19d8 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -67,6 +67,7 @@ extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, int); extern struct dentry *user_path_create(int, const char __user *, struct path *, int); +extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index eb06e58..59dc05f3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -953,7 +953,8 @@ struct net_device_ops { #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); int (*ndo_netpoll_setup)(struct net_device *dev, - struct netpoll_info *info); + struct netpoll_info *info, + gfp_t gfp); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, @@ -1300,6 +1301,8 @@ struct net_device { /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; +#define GSO_MAX_SEGS 65535 + u16 gso_max_segs; #ifdef CONFIG_DCB /* Data Center Bridging netlink ops */ @@ -1519,6 +1522,8 @@ struct packet_type { struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); + bool (*id_match)(struct packet_type *ptype, + struct sock *sk); void *af_packet_priv; struct list_head list; }; diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index 0dfc8b7..89f2a62 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -164,7 +164,7 @@ extern int ct_sip_parse_address_param(const struct nf_conn *ct, const char *dptr unsigned int dataoff, unsigned int datalen, const char *name, unsigned int *matchoff, unsigned int *matchlen, - union nf_inet_addr *addr); + union nf_inet_addr *addr, bool delim); extern int ct_sip_parse_numerical_param(const struct nf_conn *ct, const char *dptr, unsigned int off, unsigned int datalen, const char *name, diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index 28f5389..66d5379 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -23,6 +23,7 @@ struct netpoll { u8 remote_mac[ETH_ALEN]; struct list_head rx; /* rx_np list element */ + struct rcu_head rcu; }; struct netpoll_info { @@ -38,28 +39,40 @@ struct netpoll_info { struct delayed_work tx_work; struct netpoll *netpoll; + struct rcu_head rcu; }; void netpoll_send_udp(struct netpoll *np, const char *msg, int len); void netpoll_print_options(struct netpoll *np); int netpoll_parse_options(struct netpoll *np, char *opt); -int __netpoll_setup(struct netpoll *np, struct net_device *ndev); +int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp); int netpoll_setup(struct netpoll *np); int netpoll_trap(void); void netpoll_set_trap(int trap); void __netpoll_cleanup(struct netpoll *np); +void __netpoll_free_rcu(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); -int __netpoll_rx(struct sk_buff *skb); +int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo); void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, struct net_device *dev); static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) { + unsigned long flags; + local_irq_save(flags); netpoll_send_skb_on_dev(np, skb, np->dev); + local_irq_restore(flags); } #ifdef CONFIG_NETPOLL +static inline bool netpoll_rx_on(struct sk_buff *skb) +{ + struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo); + + return npinfo && (!list_empty(&npinfo->rx_np) || npinfo->rx_flags); +} + static inline bool netpoll_rx(struct sk_buff *skb) { struct netpoll_info *npinfo; @@ -67,14 +80,14 @@ static inline bool netpoll_rx(struct sk_buff *skb) bool ret = false; local_irq_save(flags); - npinfo = rcu_dereference_bh(skb->dev->npinfo); - if (!npinfo || (list_empty(&npinfo->rx_np) && !npinfo->rx_flags)) + if (!netpoll_rx_on(skb)) goto out; + npinfo = rcu_dereference_bh(skb->dev->npinfo); spin_lock(&npinfo->rx_lock); /* check rx_flags again with the lock held */ - if (npinfo->rx_flags && __netpoll_rx(skb)) + if (npinfo->rx_flags && __netpoll_rx(skb, npinfo)) ret = true; spin_unlock(&npinfo->rx_lock); @@ -83,13 +96,6 @@ out: return ret; } -static inline int netpoll_rx_on(struct sk_buff *skb) -{ - struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo); - - return npinfo && (!list_empty(&npinfo->rx_np) || npinfo->rx_flags); -} - static inline int netpoll_receive_skb(struct sk_buff *skb) { if (!list_empty(&skb->dev->napi_list)) @@ -119,7 +125,7 @@ static inline void netpoll_poll_unlock(void *have) } } -static inline int netpoll_tx_running(struct net_device *dev) +static inline bool netpoll_tx_running(struct net_device *dev) { return irqs_disabled(); } @@ -127,11 +133,11 @@ static inline int netpoll_tx_running(struct net_device *dev) #else static inline bool netpoll_rx(struct sk_buff *skb) { - return 0; + return false; } -static inline int netpoll_rx_on(struct sk_buff *skb) +static inline bool netpoll_rx_on(struct sk_buff *skb) { - return 0; + return false; } static inline int netpoll_receive_skb(struct sk_buff *skb) { @@ -147,9 +153,9 @@ static inline void netpoll_poll_unlock(void *have) static inline void netpoll_netdev_init(struct net_device *dev) { } -static inline int netpoll_tx_running(struct net_device *dev) +static inline bool netpoll_tx_running(struct net_device *dev) { - return 0; + return false; } #endif diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 2889877..1f8fc7f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -473,10 +473,10 @@ extern ssize_t nfs_direct_IO(int, struct kiocb *, const struct iovec *, loff_t, unsigned long); extern ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, - loff_t pos); + loff_t pos, bool uio); extern ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, - loff_t pos); + loff_t pos, bool uio); /* * linux/fs/nfs/dir.c diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h index ce4743a..fa63048f 100644 --- a/include/linux/nfsd/nfsfh.h +++ b/include/linux/nfsd/nfsfh.h @@ -143,6 +143,7 @@ typedef struct svc_fh { int fh_maxsize; /* max size for fh_handle */ unsigned char fh_locked; /* inode locked by us */ + unsigned char fh_want_write; /* remount protection taken */ #ifdef CONFIG_NFSD_V3 unsigned char fh_post_saved; /* post-op attrs saved */ diff --git a/include/linux/of.h b/include/linux/of.h index 42c2a58..1b11632 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -21,6 +21,7 @@ #include <linux/kref.h> #include <linux/mod_devicetable.h> #include <linux/spinlock.h> +#include <linux/topology.h> #include <asm/byteorder.h> #include <asm/errno.h> @@ -158,11 +159,6 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #define OF_BAD_ADDR ((u64)-1) -#ifndef of_node_to_nid -static inline int of_node_to_nid(struct device_node *np) { return -1; } -#define of_node_to_nid of_node_to_nid -#endif - static inline const char* of_node_full_name(struct device_node *np) { return np ? np->full_name : "<no-node>"; @@ -194,10 +190,17 @@ extern struct device_node *of_get_parent(const struct device_node *node); extern struct device_node *of_get_next_parent(struct device_node *node); extern struct device_node *of_get_next_child(const struct device_node *node, struct device_node *prev); +extern struct device_node *of_get_next_available_child( + const struct device_node *node, struct device_node *prev); + #define for_each_child_of_node(parent, child) \ for (child = of_get_next_child(parent, NULL); child != NULL; \ child = of_get_next_child(parent, child)) +#define for_each_available_child_of_node(parent, child) \ + for (child = of_get_next_available_child(parent, NULL); child != NULL; \ + child = of_get_next_available_child(parent, child)) + static inline int of_get_child_count(const struct device_node *np) { struct device_node *child; @@ -427,6 +430,15 @@ static inline int of_machine_is_compatible(const char *compat) while (0) #endif /* CONFIG_OF */ +#ifndef of_node_to_nid +static inline int of_node_to_nid(struct device_node *np) +{ + return numa_node_id(); +} + +#define of_node_to_nid of_node_to_nid +#endif + /** * of_property_read_bool - Findfrom a property * @np: device node from which the property value is to be read. diff --git a/include/linux/olpc-ec.h b/include/linux/olpc-ec.h new file mode 100644 index 0000000..5bb6e76 --- /dev/null +++ b/include/linux/olpc-ec.h @@ -0,0 +1,41 @@ +#ifndef _LINUX_OLPC_EC_H +#define _LINUX_OLPC_EC_H + +/* XO-1 EC commands */ +#define EC_FIRMWARE_REV 0x08 +#define EC_WRITE_SCI_MASK 0x1b +#define EC_WAKE_UP_WLAN 0x24 +#define EC_WLAN_LEAVE_RESET 0x25 +#define EC_READ_EB_MODE 0x2a +#define EC_SET_SCI_INHIBIT 0x32 +#define EC_SET_SCI_INHIBIT_RELEASE 0x34 +#define EC_WLAN_ENTER_RESET 0x35 +#define EC_WRITE_EXT_SCI_MASK 0x38 +#define EC_SCI_QUERY 0x84 +#define EC_EXT_SCI_QUERY 0x85 + +struct platform_device; + +struct olpc_ec_driver { + int (*probe)(struct platform_device *); + int (*suspend)(struct platform_device *); + int (*resume)(struct platform_device *); + + int (*ec_cmd)(u8, u8 *, size_t, u8 *, size_t, void *); +}; + +#ifdef CONFIG_OLPC + +extern void olpc_ec_driver_register(struct olpc_ec_driver *drv, void *arg); + +extern int olpc_ec_cmd(u8 cmd, u8 *inbuf, size_t inlen, u8 *outbuf, + size_t outlen); + +#else + +static inline int olpc_ec_cmd(u8 cmd, u8 *inbuf, size_t inlen, u8 *outbuf, + size_t outlen) { return -ENODEV; } + +#endif /* CONFIG_OLPC */ + +#endif /* _LINUX_OLPC_EC_H */ diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h new file mode 100644 index 0000000..eb475a8 --- /dev/null +++ b/include/linux/omap-dma.h @@ -0,0 +1,22 @@ +/* + * OMAP DMA Engine support + * + * 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_OMAP_DMA_H +#define __LINUX_OMAP_DMA_H + +struct dma_chan; + +#if defined(CONFIG_DMA_OMAP) || defined(CONFIG_DMA_OMAP_MODULE) +bool omap_dma_filter_fn(struct dma_chan *, void *); +#else +static inline bool omap_dma_filter_fn(struct dma_chan *c, void *d) +{ + return false; +} +#endif + +#endif diff --git a/include/linux/oom.h b/include/linux/oom.h index e4c29bc..49a3031 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -40,15 +40,36 @@ enum oom_constraint { CONSTRAINT_MEMCG, }; +enum oom_scan_t { + OOM_SCAN_OK, /* scan thread and find its badness */ + OOM_SCAN_CONTINUE, /* do not consider thread for oom kill */ + OOM_SCAN_ABORT, /* abort the iteration and return */ + OOM_SCAN_SELECT, /* always select this thread first */ +}; + extern void compare_swap_oom_score_adj(int old_val, int new_val); extern int test_set_oom_score_adj(int new_val); extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); +extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, + unsigned int points, unsigned long totalpages, + struct mem_cgroup *memcg, nodemask_t *nodemask, + const char *message); + extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); +extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, + int order, const nodemask_t *nodemask); + +extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task, + unsigned long totalpages, const nodemask_t *nodemask, + bool force_kill); +extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, + int order); + extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *mask, bool force_kill); extern int register_oom_notifier(struct notifier_block *nb); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index c88d2a9..b5d1384 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -7,6 +7,7 @@ #include <linux/types.h> #include <linux/bug.h> +#include <linux/mmdebug.h> #ifndef __GENERATING_BOUNDS_H #include <linux/mm_types.h> #include <generated/bounds.h> @@ -453,6 +454,34 @@ static inline int PageTransTail(struct page *page) } #endif +/* + * If network-based swap is enabled, sl*b must keep track of whether pages + * were allocated from pfmemalloc reserves. + */ +static inline int PageSlabPfmemalloc(struct page *page) +{ + VM_BUG_ON(!PageSlab(page)); + return PageActive(page); +} + +static inline void SetPageSlabPfmemalloc(struct page *page) +{ + VM_BUG_ON(!PageSlab(page)); + SetPageActive(page); +} + +static inline void __ClearPageSlabPfmemalloc(struct page *page) +{ + VM_BUG_ON(!PageSlab(page)); + __ClearPageActive(page); +} + +static inline void ClearPageSlabPfmemalloc(struct page *page) +{ + VM_BUG_ON(!PageSlab(page)); + ClearPageActive(page); +} + #ifdef CONFIG_MMU #define __PG_MLOCKED (1 << PG_mlocked) #else diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 3bdcab3..105077a 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -1,6 +1,11 @@ #ifndef __LINUX_PAGEISOLATION_H #define __LINUX_PAGEISOLATION_H + +bool has_unmovable_pages(struct zone *zone, struct page *page, int count); +void set_pageblock_migratetype(struct page *page, int migratetype); +int move_freepages_block(struct zone *zone, struct page *page, + int migratetype); /* * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE. * If specified range includes migrate types other than MOVABLE or CMA, @@ -10,7 +15,7 @@ * free all pages in the range. test_page_isolated() can be used for * test it. */ -extern int +int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned migratetype); @@ -18,7 +23,7 @@ start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. * target range is [start_pfn, end_pfn) */ -extern int +int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, unsigned migratetype); @@ -30,8 +35,8 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn); /* * Internal functions. Changes pageblock's migrate type. */ -extern int set_migratetype_isolate(struct page *page); -extern void unset_migratetype_isolate(struct page *page, unsigned migratetype); +int set_migratetype_isolate(struct page *page); +void unset_migratetype_isolate(struct page *page, unsigned migratetype); #endif diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index a88cdba..777a524 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -12,7 +12,7 @@ enum { #ifndef __GENERATING_BOUNDS_H #include <generated/bounds.h> -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG #include <linux/bit_spinlock.h> /* @@ -82,7 +82,7 @@ static inline void unlock_page_cgroup(struct page_cgroup *pc) bit_spin_unlock(PCG_LOCK, &pc->flags); } -#else /* CONFIG_CGROUP_MEM_RES_CTLR */ +#else /* CONFIG_MEMCG */ struct page_cgroup; static inline void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat) @@ -102,11 +102,11 @@ static inline void __init page_cgroup_init_flatmem(void) { } -#endif /* CONFIG_CGROUP_MEM_RES_CTLR */ +#endif /* CONFIG_MEMCG */ #include <linux/swap.h> -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent, unsigned short old, unsigned short new); extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id); @@ -138,7 +138,7 @@ static inline void swap_cgroup_swapoff(int type) return; } -#endif /* CONFIG_CGROUP_MEM_RES_CTLR_SWAP */ +#endif /* CONFIG_MEMCG_SWAP */ #endif /* !__GENERATING_BOUNDS_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7cfad3b..e42c762 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -286,6 +286,11 @@ static inline loff_t page_offset(struct page *page) return ((loff_t)page->index) << PAGE_CACHE_SHIFT; } +static inline loff_t page_file_offset(struct page *page) +{ + return ((loff_t)page_file_index(page)) << PAGE_CACHE_SHIFT; +} + extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 76c5c8b..7602ccb 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1272,7 +1272,8 @@ static inline bool perf_paranoid_kernel(void) extern void perf_event_init(void); extern void perf_tp_event(u64 addr, u64 count, void *record, int entry_size, struct pt_regs *regs, - struct hlist_head *head, int rctx); + struct hlist_head *head, int rctx, + struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags diff --git a/include/linux/pinctrl/consumer.h b/include/linux/pinctrl/consumer.h index 6dd96fb..e9b7f43 100644 --- a/include/linux/pinctrl/consumer.h +++ b/include/linux/pinctrl/consumer.h @@ -20,6 +20,7 @@ /* This struct is private to the core and should be regarded as a cookie */ struct pinctrl; struct pinctrl_state; +struct device; #ifdef CONFIG_PINCTRL diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index e11d1c0..ad1a427 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -160,4 +160,6 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); long pipe_fcntl(struct file *, unsigned int, unsigned long arg); struct pipe_inode_info *get_pipe_info(struct file *file); +int create_pipe_files(struct file **, int); + #endif diff --git a/include/linux/random.h b/include/linux/random.h index 8f74538..ac621ce 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -48,13 +48,13 @@ struct rnd_state { #ifdef __KERNEL__ -extern void rand_initialize_irq(int irq); - +extern void add_device_randomness(const void *, unsigned int); extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); -extern void add_interrupt_randomness(int irq); +extern void add_interrupt_randomness(int irq, int irq_flags); extern void get_random_bytes(void *buf, int nbytes); +extern void get_random_bytes_arch(void *buf, int nbytes); void generate_random_uuid(unsigned char uuid_out[16]); #ifndef MODULE diff --git a/include/linux/sched.h b/include/linux/sched.h index 68dcffa..b8c8664 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -334,14 +334,6 @@ static inline void lockup_detector_init(void) } #endif -#if defined(CONFIG_LOCKUP_DETECTOR) && defined(CONFIG_SUSPEND) -void lockup_detector_bootcpu_resume(void); -#else -static inline void lockup_detector_bootcpu_resume(void) -{ -} -#endif - #ifdef CONFIG_DETECT_HUNG_TASK extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_check_count; @@ -1584,7 +1576,7 @@ struct task_struct { /* bitmask and counter of trace recursion */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */ +#ifdef CONFIG_MEMCG /* memcg uses this to do batch job */ struct memcg_batch_info { int do_batch; /* incremented when batch uncharge started */ struct mem_cgroup *memcg; /* target memcg of uncharge */ @@ -1894,6 +1886,13 @@ static inline void rcu_copy_process(struct task_struct *p) #endif +static inline void tsk_restore_flags(struct task_struct *task, + unsigned long orig_flags, unsigned long flags) +{ + task->flags &= ~flags; + task->flags |= orig_flags & flags; +} + #ifdef CONFIG_SMP extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); diff --git a/include/linux/security.h b/include/linux/security.h index 4e5a73c..3dea6a9 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1242,8 +1242,6 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * Check that the @parent process has sufficient permission to trace the * current process before allowing the current process to present itself * to the @parent process for tracing. - * The parent process will still have to undergo the ptrace_access_check - * checks before it is allowed to trace this one. * @parent contains the task_struct structure for debugger process. * Return 0 if permission is granted. * @capget: diff --git a/include/linux/shdma-base.h b/include/linux/shdma-base.h index 93f9821..a3728bf 100644 --- a/include/linux/shdma-base.h +++ b/include/linux/shdma-base.h @@ -50,6 +50,7 @@ struct shdma_desc { struct list_head node; struct dma_async_tx_descriptor async_tx; enum dma_transfer_direction direction; + size_t partial; dma_cookie_t cookie; int chunks; int mark; @@ -98,6 +99,7 @@ struct shdma_ops { void (*start_xfer)(struct shdma_chan *, struct shdma_desc *); struct shdma_desc *(*embedded_desc)(void *, int); bool (*chan_irq)(struct shdma_chan *, int); + size_t (*get_partial)(struct shdma_chan *, struct shdma_desc *); }; struct shdma_dev { diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 07ceb97..ac6b8ee 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -20,7 +20,6 @@ struct shrink_control { * 'nr_to_scan' entries and attempt to free them up. It should return * the number of objects which remain in the cache. If it returns -1, it means * it cannot do any scanning at this time (eg. there is a risk of deadlock). - * The callback must not return -1 if nr_to_scan is zero. * * The 'gfpmask' refers to the allocation we are currently trying to * fulfil. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d205c4b..7632c87 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -462,6 +462,7 @@ struct sk_buff { #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif + __u8 pfmemalloc:1; __u8 ooo_okay:1; __u8 l4_rxhash:1; __u8 wifi_acked_valid:1; @@ -502,6 +503,15 @@ struct sk_buff { #include <linux/slab.h> +#define SKB_ALLOC_FCLONE 0x01 +#define SKB_ALLOC_RX 0x02 + +/* Returns true if the skb was allocated from PFMEMALLOC reserves */ +static inline bool skb_pfmemalloc(const struct sk_buff *skb) +{ + return unlikely(skb->pfmemalloc); +} + /* * skb might have a dst pointer attached, refcounted or not. * _skb_refdst low order bit is set if refcount was _not_ taken @@ -565,7 +575,7 @@ extern bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize); extern struct sk_buff *__alloc_skb(unsigned int size, - gfp_t priority, int fclone, int node); + gfp_t priority, int flags, int node); extern struct sk_buff *build_skb(void *data, unsigned int frag_size); static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) @@ -576,7 +586,7 @@ static inline struct sk_buff *alloc_skb(unsigned int size, static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { - return __alloc_skb(size, priority, 1, NUMA_NO_NODE); + return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } extern void skb_recycle(struct sk_buff *skb); @@ -1237,6 +1247,17 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + /* + * Propagate page->pfmemalloc to the skb if we can. The problem is + * that not all callers have unique ownership of the page. If + * pfmemalloc is set, we check the mapping as a mapping implies + * page->index is set (index and pfmemalloc share space). + * If it's a valid mapping, we cannot use page->pfmemalloc but we + * do not lose pfmemalloc information as the pages would not be + * allocated using __GFP_MEMALLOC. + */ + if (page->pfmemalloc && !page->mapping) + skb->pfmemalloc = true; frag->page.p = page; frag->page_offset = off; skb_frag_size_set(frag, size); @@ -1753,6 +1774,61 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } +/* + * __skb_alloc_page - allocate pages for ps-rx on a skb and preserve pfmemalloc data + * @gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX + * @skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used + * @order: size of the allocation + * + * Allocate a new page. + * + * %NULL is returned if there is no free memory. +*/ +static inline struct page *__skb_alloc_pages(gfp_t gfp_mask, + struct sk_buff *skb, + unsigned int order) +{ + struct page *page; + + gfp_mask |= __GFP_COLD; + + if (!(gfp_mask & __GFP_NOMEMALLOC)) + gfp_mask |= __GFP_MEMALLOC; + + page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); + if (skb && page && page->pfmemalloc) + skb->pfmemalloc = true; + + return page; +} + +/** + * __skb_alloc_page - allocate a page for ps-rx for a given skb and preserve pfmemalloc data + * @gfp_mask: alloc_pages_node mask. Set __GFP_NOMEMALLOC if not for network packet RX + * @skb: skb to set pfmemalloc on if __GFP_MEMALLOC is used + * + * Allocate a new page. + * + * %NULL is returned if there is no free memory. + */ +static inline struct page *__skb_alloc_page(gfp_t gfp_mask, + struct sk_buff *skb) +{ + return __skb_alloc_pages(gfp_mask, skb, 0); +} + +/** + * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page + * @page: The page that was allocated from skb_alloc_page + * @skb: The skb that may need pfmemalloc set + */ +static inline void skb_propagate_pfmemalloc(struct page *page, + struct sk_buff *skb) +{ + if (page && page->pfmemalloc) + skb->pfmemalloc = true; +} + /** * skb_frag_page - retrieve the page refered to by a paged fragment * @frag: the paged fragment diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 77d278d..cff40aa 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -174,6 +174,8 @@ struct rpc_xprt { unsigned long state; /* transport state */ unsigned char shutdown : 1, /* being shut down */ resvport : 1; /* use a reserved port */ + unsigned int swapper; /* we're swapping over this + transport */ unsigned int bind_index; /* bind function index */ /* @@ -316,6 +318,7 @@ void xprt_release_rqst_cong(struct rpc_task *task); void xprt_disconnect_done(struct rpc_xprt *xprt); void xprt_force_disconnect(struct rpc_xprt *xprt); void xprt_conditional_disconnect(struct rpc_xprt *xprt, unsigned int cookie); +int xs_swapper(struct rpc_xprt *xprt, int enable); /* * Reserved bit positions in xprt->state diff --git a/include/linux/swap.h b/include/linux/swap.h index c84ec68..388e706 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -151,6 +151,7 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ + SWP_FILE = (1 << 7), /* set after swap_activate success */ /* add others here before... */ SWP_SCANNING = (1 << 8), /* refcount in scan_swap_map */ }; @@ -301,7 +302,7 @@ static inline void scan_unevictable_unregister_node(struct node *node) extern int kswapd_run(int nid); extern void kswapd_stop(int nid); -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG extern int mem_cgroup_swappiness(struct mem_cgroup *mem); #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) @@ -309,7 +310,7 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) return vm_swappiness; } #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#ifdef CONFIG_MEMCG_SWAP extern void mem_cgroup_uncharge_swap(swp_entry_t ent); #else static inline void mem_cgroup_uncharge_swap(swp_entry_t ent) @@ -320,8 +321,14 @@ static inline void mem_cgroup_uncharge_swap(swp_entry_t ent) /* linux/mm/page_io.c */ extern int swap_readpage(struct page *); extern int swap_writepage(struct page *page, struct writeback_control *wbc); +extern int swap_set_page_dirty(struct page *page); extern void end_swap_bio_read(struct bio *bio, int err); +int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, + unsigned long nr_pages, sector_t start_block); +int generic_swapfile_activate(struct swap_info_struct *, struct file *, + sector_t *); + /* linux/mm/swap_state.c */ extern struct address_space swapper_space; #define total_swapcache_pages swapper_space.nrpages @@ -356,11 +363,12 @@ extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); extern int page_swapcount(struct page *); +extern struct swap_info_struct *page_swap_info(struct page *); extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; -#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#ifdef CONFIG_MEMCG extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); #else diff --git a/include/linux/timex.h b/include/linux/timex.h index 99bc88b..7c5ceb2 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -232,7 +232,7 @@ struct timex { * estimated error = NTP dispersion. */ extern unsigned long tick_usec; /* USER_HZ period (usec) */ -extern unsigned long tick_nsec; /* ACTHZ period (nsec) */ +extern unsigned long tick_nsec; /* SHIFTED_HZ period (nsec) */ extern void ntp_init(void); extern void ntp_clear(void); diff --git a/include/linux/topology.h b/include/linux/topology.h index e91cd43..fec12d6 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -164,6 +164,7 @@ int arch_update_cpu_topology(void); | 0*SD_SHARE_CPUPOWER \ | 0*SD_SHARE_PKG_RESOURCES \ | 0*SD_SERIALIZE \ + | 1*SD_PREFER_SIBLING \ , \ .last_balance = jiffies, \ .balance_interval = 1, \ diff --git a/include/linux/vfio.h b/include/linux/vfio.h new file mode 100644 index 0000000..0a4f180 --- /dev/null +++ b/include/linux/vfio.h @@ -0,0 +1,445 @@ +/* + * VFIO API definition + * + * Copyright (C) 2012 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson <alex.williamson@redhat.com> + * + * 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 VFIO_H +#define VFIO_H + +#include <linux/types.h> +#include <linux/ioctl.h> + +#define VFIO_API_VERSION 0 + +#ifdef __KERNEL__ /* Internal VFIO-core/bus driver API */ + +#include <linux/iommu.h> +#include <linux/mm.h> + +/** + * struct vfio_device_ops - VFIO bus driver device callbacks + * + * @open: Called when userspace creates new file descriptor for device + * @release: Called when userspace releases file descriptor for device + * @read: Perform read(2) on device file descriptor + * @write: Perform write(2) on device file descriptor + * @ioctl: Perform ioctl(2) on device file descriptor, supporting VFIO_DEVICE_* + * operations documented below + * @mmap: Perform mmap(2) on a region of the device file descriptor + */ +struct vfio_device_ops { + char *name; + int (*open)(void *device_data); + void (*release)(void *device_data); + ssize_t (*read)(void *device_data, char __user *buf, + size_t count, loff_t *ppos); + ssize_t (*write)(void *device_data, const char __user *buf, + size_t count, loff_t *size); + long (*ioctl)(void *device_data, unsigned int cmd, + unsigned long arg); + int (*mmap)(void *device_data, struct vm_area_struct *vma); +}; + +extern int vfio_add_group_dev(struct device *dev, + const struct vfio_device_ops *ops, + void *device_data); + +extern void *vfio_del_group_dev(struct device *dev); + +/** + * struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks + */ +struct vfio_iommu_driver_ops { + char *name; + struct module *owner; + void *(*open)(unsigned long arg); + void (*release)(void *iommu_data); + ssize_t (*read)(void *iommu_data, char __user *buf, + size_t count, loff_t *ppos); + ssize_t (*write)(void *iommu_data, const char __user *buf, + size_t count, loff_t *size); + long (*ioctl)(void *iommu_data, unsigned int cmd, + unsigned long arg); + int (*mmap)(void *iommu_data, struct vm_area_struct *vma); + int (*attach_group)(void *iommu_data, + struct iommu_group *group); + void (*detach_group)(void *iommu_data, + struct iommu_group *group); + +}; + +extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); + +extern void vfio_unregister_iommu_driver( + const struct vfio_iommu_driver_ops *ops); + +/** + * offsetofend(TYPE, MEMBER) + * + * @TYPE: The type of the structure + * @MEMBER: The member within the structure to get the end offset of + * + * Simple helper macro for dealing with variable sized structures passed + * from user space. This allows us to easily determine if the provided + * structure is sized to include various fields. + */ +#define offsetofend(TYPE, MEMBER) ({ \ + TYPE tmp; \ + offsetof(TYPE, MEMBER) + sizeof(tmp.MEMBER); }) \ + +#endif /* __KERNEL__ */ + +/* Kernel & User level defines for VFIO IOCTLs. */ + +/* Extensions */ + +#define VFIO_TYPE1_IOMMU 1 + +/* + * The IOCTL interface is designed for extensibility by embedding the + * structure length (argsz) and flags into structures passed between + * kernel and userspace. We therefore use the _IO() macro for these + * defines to avoid implicitly embedding a size into the ioctl request. + * As structure fields are added, argsz will increase to match and flag + * bits will be defined to indicate additional fields with valid data. + * It's *always* the caller's responsibility to indicate the size of + * the structure passed by setting argsz appropriately. + */ + +#define VFIO_TYPE (';') +#define VFIO_BASE 100 + +/* -------- IOCTLs for VFIO file descriptor (/dev/vfio/vfio) -------- */ + +/** + * VFIO_GET_API_VERSION - _IO(VFIO_TYPE, VFIO_BASE + 0) + * + * Report the version of the VFIO API. This allows us to bump the entire + * API version should we later need to add or change features in incompatible + * ways. + * Return: VFIO_API_VERSION + * Availability: Always + */ +#define VFIO_GET_API_VERSION _IO(VFIO_TYPE, VFIO_BASE + 0) + +/** + * VFIO_CHECK_EXTENSION - _IOW(VFIO_TYPE, VFIO_BASE + 1, __u32) + * + * Check whether an extension is supported. + * Return: 0 if not supported, 1 (or some other positive integer) if supported. + * Availability: Always + */ +#define VFIO_CHECK_EXTENSION _IO(VFIO_TYPE, VFIO_BASE + 1) + +/** + * VFIO_SET_IOMMU - _IOW(VFIO_TYPE, VFIO_BASE + 2, __s32) + * + * Set the iommu to the given type. The type must be supported by an + * iommu driver as verified by calling CHECK_EXTENSION using the same + * type. A group must be set to this file descriptor before this + * ioctl is available. The IOMMU interfaces enabled by this call are + * specific to the value set. + * Return: 0 on success, -errno on failure + * Availability: When VFIO group attached + */ +#define VFIO_SET_IOMMU _IO(VFIO_TYPE, VFIO_BASE + 2) + +/* -------- IOCTLs for GROUP file descriptors (/dev/vfio/$GROUP) -------- */ + +/** + * VFIO_GROUP_GET_STATUS - _IOR(VFIO_TYPE, VFIO_BASE + 3, + * struct vfio_group_status) + * + * Retrieve information about the group. Fills in provided + * struct vfio_group_info. Caller sets argsz. + * Return: 0 on succes, -errno on failure. + * Availability: Always + */ +struct vfio_group_status { + __u32 argsz; + __u32 flags; +#define VFIO_GROUP_FLAGS_VIABLE (1 << 0) +#define VFIO_GROUP_FLAGS_CONTAINER_SET (1 << 1) +}; +#define VFIO_GROUP_GET_STATUS _IO(VFIO_TYPE, VFIO_BASE + 3) + +/** + * VFIO_GROUP_SET_CONTAINER - _IOW(VFIO_TYPE, VFIO_BASE + 4, __s32) + * + * Set the container for the VFIO group to the open VFIO file + * descriptor provided. Groups may only belong to a single + * container. Containers may, at their discretion, support multiple + * groups. Only when a container is set are all of the interfaces + * of the VFIO file descriptor and the VFIO group file descriptor + * available to the user. + * Return: 0 on success, -errno on failure. + * Availability: Always + */ +#define VFIO_GROUP_SET_CONTAINER _IO(VFIO_TYPE, VFIO_BASE + 4) + +/** + * VFIO_GROUP_UNSET_CONTAINER - _IO(VFIO_TYPE, VFIO_BASE + 5) + * + * Remove the group from the attached container. This is the + * opposite of the SET_CONTAINER call and returns the group to + * an initial state. All device file descriptors must be released + * prior to calling this interface. When removing the last group + * from a container, the IOMMU will be disabled and all state lost, + * effectively also returning the VFIO file descriptor to an initial + * state. + * Return: 0 on success, -errno on failure. + * Availability: When attached to container + */ +#define VFIO_GROUP_UNSET_CONTAINER _IO(VFIO_TYPE, VFIO_BASE + 5) + +/** + * VFIO_GROUP_GET_DEVICE_FD - _IOW(VFIO_TYPE, VFIO_BASE + 6, char) + * + * Return a new file descriptor for the device object described by + * the provided string. The string should match a device listed in + * the devices subdirectory of the IOMMU group sysfs entry. The + * group containing the device must already be added to this context. + * Return: new file descriptor on success, -errno on failure. + * Availability: When attached to container + */ +#define VFIO_GROUP_GET_DEVICE_FD _IO(VFIO_TYPE, VFIO_BASE + 6) + +/* --------------- IOCTLs for DEVICE file descriptors --------------- */ + +/** + * VFIO_DEVICE_GET_INFO - _IOR(VFIO_TYPE, VFIO_BASE + 7, + * struct vfio_device_info) + * + * Retrieve information about the device. Fills in provided + * struct vfio_device_info. Caller sets argsz. + * Return: 0 on success, -errno on failure. + */ +struct vfio_device_info { + __u32 argsz; + __u32 flags; +#define VFIO_DEVICE_FLAGS_RESET (1 << 0) /* Device supports reset */ +#define VFIO_DEVICE_FLAGS_PCI (1 << 1) /* vfio-pci device */ + __u32 num_regions; /* Max region index + 1 */ + __u32 num_irqs; /* Max IRQ index + 1 */ +}; +#define VFIO_DEVICE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 7) + +/** + * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8, + * struct vfio_region_info) + * + * Retrieve information about a device region. Caller provides + * struct vfio_region_info with index value set. Caller sets argsz. + * Implementation of region mapping is bus driver specific. This is + * intended to describe MMIO, I/O port, as well as bus specific + * regions (ex. PCI config space). Zero sized regions may be used + * to describe unimplemented regions (ex. unimplemented PCI BARs). + * Return: 0 on success, -errno on failure. + */ +struct vfio_region_info { + __u32 argsz; + __u32 flags; +#define VFIO_REGION_INFO_FLAG_READ (1 << 0) /* Region supports read */ +#define VFIO_REGION_INFO_FLAG_WRITE (1 << 1) /* Region supports write */ +#define VFIO_REGION_INFO_FLAG_MMAP (1 << 2) /* Region supports mmap */ + __u32 index; /* Region index */ + __u32 resv; /* Reserved for alignment */ + __u64 size; /* Region size (bytes) */ + __u64 offset; /* Region offset from start of device fd */ +}; +#define VFIO_DEVICE_GET_REGION_INFO _IO(VFIO_TYPE, VFIO_BASE + 8) + +/** + * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9, + * struct vfio_irq_info) + * + * Retrieve information about a device IRQ. Caller provides + * struct vfio_irq_info with index value set. Caller sets argsz. + * Implementation of IRQ mapping is bus driver specific. Indexes + * using multiple IRQs are primarily intended to support MSI-like + * interrupt blocks. Zero count irq blocks may be used to describe + * unimplemented interrupt types. + * + * The EVENTFD flag indicates the interrupt index supports eventfd based + * signaling. + * + * The MASKABLE flags indicates the index supports MASK and UNMASK + * actions described below. + * + * AUTOMASKED indicates that after signaling, the interrupt line is + * automatically masked by VFIO and the user needs to unmask the line + * to receive new interrupts. This is primarily intended to distinguish + * level triggered interrupts. + * + * The NORESIZE flag indicates that the interrupt lines within the index + * are setup as a set and new subindexes cannot be enabled without first + * disabling the entire index. This is used for interrupts like PCI MSI + * and MSI-X where the driver may only use a subset of the available + * indexes, but VFIO needs to enable a specific number of vectors + * upfront. In the case of MSI-X, where the user can enable MSI-X and + * then add and unmask vectors, it's up to userspace to make the decision + * whether to allocate the maximum supported number of vectors or tear + * down setup and incrementally increase the vectors as each is enabled. + */ +struct vfio_irq_info { + __u32 argsz; + __u32 flags; +#define VFIO_IRQ_INFO_EVENTFD (1 << 0) +#define VFIO_IRQ_INFO_MASKABLE (1 << 1) +#define VFIO_IRQ_INFO_AUTOMASKED (1 << 2) +#define VFIO_IRQ_INFO_NORESIZE (1 << 3) + __u32 index; /* IRQ index */ + __u32 count; /* Number of IRQs within this index */ +}; +#define VFIO_DEVICE_GET_IRQ_INFO _IO(VFIO_TYPE, VFIO_BASE + 9) + +/** + * VFIO_DEVICE_SET_IRQS - _IOW(VFIO_TYPE, VFIO_BASE + 10, struct vfio_irq_set) + * + * Set signaling, masking, and unmasking of interrupts. Caller provides + * struct vfio_irq_set with all fields set. 'start' and 'count' indicate + * the range of subindexes being specified. + * + * The DATA flags specify the type of data provided. If DATA_NONE, the + * operation performs the specified action immediately on the specified + * interrupt(s). For example, to unmask AUTOMASKED interrupt [0,0]: + * flags = (DATA_NONE|ACTION_UNMASK), index = 0, start = 0, count = 1. + * + * DATA_BOOL allows sparse support for the same on arrays of interrupts. + * For example, to mask interrupts [0,1] and [0,3] (but not [0,2]): + * flags = (DATA_BOOL|ACTION_MASK), index = 0, start = 1, count = 3, + * data = {1,0,1} + * + * DATA_EVENTFD binds the specified ACTION to the provided __s32 eventfd. + * A value of -1 can be used to either de-assign interrupts if already + * assigned or skip un-assigned interrupts. For example, to set an eventfd + * to be trigger for interrupts [0,0] and [0,2]: + * flags = (DATA_EVENTFD|ACTION_TRIGGER), index = 0, start = 0, count = 3, + * data = {fd1, -1, fd2} + * If index [0,1] is previously set, two count = 1 ioctls calls would be + * required to set [0,0] and [0,2] without changing [0,1]. + * + * Once a signaling mechanism is set, DATA_BOOL or DATA_NONE can be used + * with ACTION_TRIGGER to perform kernel level interrupt loopback testing + * from userspace (ie. simulate hardware triggering). + * + * Setting of an event triggering mechanism to userspace for ACTION_TRIGGER + * enables the interrupt index for the device. Individual subindex interrupts + * can be disabled using the -1 value for DATA_EVENTFD or the index can be + * disabled as a whole with: flags = (DATA_NONE|ACTION_TRIGGER), count = 0. + * + * Note that ACTION_[UN]MASK specify user->kernel signaling (irqfds) while + * ACTION_TRIGGER specifies kernel->user signaling. + */ +struct vfio_irq_set { + __u32 argsz; + __u32 flags; +#define VFIO_IRQ_SET_DATA_NONE (1 << 0) /* Data not present */ +#define VFIO_IRQ_SET_DATA_BOOL (1 << 1) /* Data is bool (u8) */ +#define VFIO_IRQ_SET_DATA_EVENTFD (1 << 2) /* Data is eventfd (s32) */ +#define VFIO_IRQ_SET_ACTION_MASK (1 << 3) /* Mask interrupt */ +#define VFIO_IRQ_SET_ACTION_UNMASK (1 << 4) /* Unmask interrupt */ +#define VFIO_IRQ_SET_ACTION_TRIGGER (1 << 5) /* Trigger interrupt */ + __u32 index; + __u32 start; + __u32 count; + __u8 data[]; +}; +#define VFIO_DEVICE_SET_IRQS _IO(VFIO_TYPE, VFIO_BASE + 10) + +#define VFIO_IRQ_SET_DATA_TYPE_MASK (VFIO_IRQ_SET_DATA_NONE | \ + VFIO_IRQ_SET_DATA_BOOL | \ + VFIO_IRQ_SET_DATA_EVENTFD) +#define VFIO_IRQ_SET_ACTION_TYPE_MASK (VFIO_IRQ_SET_ACTION_MASK | \ + VFIO_IRQ_SET_ACTION_UNMASK | \ + VFIO_IRQ_SET_ACTION_TRIGGER) +/** + * VFIO_DEVICE_RESET - _IO(VFIO_TYPE, VFIO_BASE + 11) + * + * Reset a device. + */ +#define VFIO_DEVICE_RESET _IO(VFIO_TYPE, VFIO_BASE + 11) + +/* + * The VFIO-PCI bus driver makes use of the following fixed region and + * IRQ index mapping. Unimplemented regions return a size of zero. + * Unimplemented IRQ types return a count of zero. + */ + +enum { + VFIO_PCI_BAR0_REGION_INDEX, + VFIO_PCI_BAR1_REGION_INDEX, + VFIO_PCI_BAR2_REGION_INDEX, + VFIO_PCI_BAR3_REGION_INDEX, + VFIO_PCI_BAR4_REGION_INDEX, + VFIO_PCI_BAR5_REGION_INDEX, + VFIO_PCI_ROM_REGION_INDEX, + VFIO_PCI_CONFIG_REGION_INDEX, + VFIO_PCI_NUM_REGIONS +}; + +enum { + VFIO_PCI_INTX_IRQ_INDEX, + VFIO_PCI_MSI_IRQ_INDEX, + VFIO_PCI_MSIX_IRQ_INDEX, + VFIO_PCI_NUM_IRQS +}; + +/* -------- API for Type1 VFIO IOMMU -------- */ + +/** + * VFIO_IOMMU_GET_INFO - _IOR(VFIO_TYPE, VFIO_BASE + 12, struct vfio_iommu_info) + * + * Retrieve information about the IOMMU object. Fills in provided + * struct vfio_iommu_info. Caller sets argsz. + * + * XXX Should we do these by CHECK_EXTENSION too? + */ +struct vfio_iommu_type1_info { + __u32 argsz; + __u32 flags; +#define VFIO_IOMMU_INFO_PGSIZES (1 << 0) /* supported page sizes info */ + __u64 iova_pgsizes; /* Bitmap of supported page sizes */ +}; + +#define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12) + +/** + * VFIO_IOMMU_MAP_DMA - _IOW(VFIO_TYPE, VFIO_BASE + 13, struct vfio_dma_map) + * + * Map process virtual addresses to IO virtual addresses using the + * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required. + */ +struct vfio_iommu_type1_dma_map { + __u32 argsz; + __u32 flags; +#define VFIO_DMA_MAP_FLAG_READ (1 << 0) /* readable from device */ +#define VFIO_DMA_MAP_FLAG_WRITE (1 << 1) /* writable from device */ + __u64 vaddr; /* Process virtual address */ + __u64 iova; /* IO virtual address */ + __u64 size; /* Size of mapping (bytes) */ +}; + +#define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13) + +/** + * VFIO_IOMMU_UNMAP_DMA - _IOW(VFIO_TYPE, VFIO_BASE + 14, struct vfio_dma_unmap) + * + * Unmap IO virtual addresses using the provided struct vfio_dma_unmap. + * Caller sets argsz. + */ +struct vfio_iommu_type1_dma_unmap { + __u32 argsz; + __u32 flags; + __u64 iova; /* IO virtual address */ + __u64 size; /* Size of mapping (bytes) */ +}; + +#define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14) + +#endif /* VFIO_H */ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 06f8e38..57f7b10 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -30,6 +30,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, FOR_ALL_ZONES(PGSTEAL_DIRECT), FOR_ALL_ZONES(PGSCAN_KSWAPD), FOR_ALL_ZONES(PGSCAN_DIRECT), + PGSCAN_DIRECT_THROTTLE, #ifdef CONFIG_NUMA PGSCAN_ZONE_RECLAIM_FAILED, #endif diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 65efb92..ad2cfd5 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -179,11 +179,6 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp); #define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d) #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d)) -static inline void zap_zone_vm_stats(struct zone *zone) -{ - memset(zone->vm_stat, 0, sizeof(zone->vm_stat)); -} - extern void inc_zone_state(struct zone *, enum zone_stat_item); #ifdef CONFIG_SMP diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 6d0a0fc..50c3e8f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -104,7 +104,6 @@ static inline void wait_on_inode(struct inode *inode) wait_on_bit(&inode->i_state, __I_NEW, inode_wait, TASK_UNINTERRUPTIBLE); } - /* * mm/page-writeback.c */ @@ -189,9 +188,4 @@ void tag_pages_for_writeback(struct address_space *mapping, void account_page_redirty(struct page *page); -/* pdflush.c */ -extern int nr_pdflush_threads; /* Global so it can be exported to sysctl - read-only. */ - - #endif /* WRITEBACK_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 493fa0c..3d254e1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -96,6 +96,7 @@ enum ieee80211_band { * is not permitted. * @IEEE80211_CHAN_NO_HT40MINUS: extension channel below this channel * is not permitted. + * @IEEE80211_CHAN_NO_OFDM: OFDM is not allowed on this channel. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = 1<<0, @@ -104,6 +105,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_RADAR = 1<<3, IEEE80211_CHAN_NO_HT40PLUS = 1<<4, IEEE80211_CHAN_NO_HT40MINUS = 1<<5, + IEEE80211_CHAN_NO_OFDM = 1<<6, }; #define IEEE80211_CHAN_NO_HT40 \ diff --git a/include/net/codel.h b/include/net/codel.h index 550debf..389cf62 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -305,6 +305,8 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch, } } } else if (drop) { + u32 delta; + if (params->ecn && INET_ECN_set_ce(skb)) { stats->ecn_mark++; } else { @@ -320,9 +322,11 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch, * assume that the drop rate that controlled the queue on the * last cycle is a good starting point to control it now. */ - if (codel_time_before(now - vars->drop_next, + delta = vars->count - vars->lastcount; + if (delta > 1 && + codel_time_before(now - vars->drop_next, 16 * params->interval)) { - vars->count = (vars->count - vars->lastcount) | 1; + vars->count = delta; /* we dont care if rec_inv_sqrt approximation * is not very precise : * Next Newton steps will correct it quadratically. diff --git a/include/net/dst.h b/include/net/dst.h index baf5978..621e351 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -110,7 +110,7 @@ struct dst_entry { }; extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); -extern const u32 dst_default_metrics[RTAX_MAX]; +extern const u32 dst_default_metrics[]; #define DST_METRICS_READ_ONLY 0x1UL #define __DST_METRICS_PTR(Y) \ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 5ee66f5..ba1d361 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -39,6 +39,7 @@ struct inet_connection_sock_af_ops { int (*queue_xmit)(struct sk_buff *skb, struct flowi *fl); void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); + void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb); int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, struct request_sock *req, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 83b567f..613cfa4 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -249,13 +249,4 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) return flags; } -static inline void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) -{ - struct dst_entry *dst = skb_dst(skb); - - dst_hold(dst); - sk->sk_rx_dst = dst; - inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; -} - #endif /* _INET_SOCK_H */ diff --git a/include/net/ip.h b/include/net/ip.h index bd5e444..5a5d84d 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -120,7 +120,7 @@ extern struct sk_buff *__ip_make_skb(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork); -extern int ip_send_skb(struct sk_buff *skb); +extern int ip_send_skb(struct net *net, struct sk_buff *skb); extern int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4); extern void ip_flush_pending_frames(struct sock *sk); extern struct sk_buff *ip_make_skb(struct sock *sk, diff --git a/include/net/llc.h b/include/net/llc.h index 226c846..f2d0fc5 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -133,7 +133,7 @@ extern int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, extern void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); extern void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); -extern int llc_station_init(void); +extern void llc_station_init(void); extern void llc_station_exit(void); #ifdef CONFIG_PROC_FS diff --git a/include/net/scm.h b/include/net/scm.h index 079d788..7dc0854 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -70,9 +70,11 @@ static __inline__ void scm_destroy(struct scm_cookie *scm) } static __inline__ int scm_send(struct socket *sock, struct msghdr *msg, - struct scm_cookie *scm) + struct scm_cookie *scm, bool forcecreds) { memset(scm, 0, sizeof(*scm)); + if (forcecreds) + scm_set_cred(scm, task_tgid(current), current_cred()); unix_get_peersec_dgram(sock, scm); if (msg->msg_controllen <= 0) return 0; diff --git a/include/net/sock.h b/include/net/sock.h index e067f8c..72132ae 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -218,6 +218,7 @@ struct cg_proto; * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build + * @sk_gso_max_segs: Maximum number of GSO segments * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held * @sk_callback_lock: used with the callbacks in the end of this struct @@ -338,6 +339,7 @@ struct sock { netdev_features_t sk_route_nocaps; int sk_gso_type; unsigned int sk_gso_max_size; + u16 sk_gso_max_segs; int sk_rcvlowat; unsigned long sk_lingertime; struct sk_buff_head sk_error_queue; @@ -621,6 +623,7 @@ enum sock_flags { SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */ SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */ SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */ + SOCK_MEMALLOC, /* VM depends on this socket for swapping */ SOCK_TIMESTAMPING_TX_HARDWARE, /* %SOF_TIMESTAMPING_TX_HARDWARE */ SOCK_TIMESTAMPING_TX_SOFTWARE, /* %SOF_TIMESTAMPING_TX_SOFTWARE */ SOCK_TIMESTAMPING_RX_HARDWARE, /* %SOF_TIMESTAMPING_RX_HARDWARE */ @@ -658,6 +661,26 @@ static inline bool sock_flag(const struct sock *sk, enum sock_flags flag) return test_bit(flag, &sk->sk_flags); } +#ifdef CONFIG_NET +extern struct static_key memalloc_socks; +static inline int sk_memalloc_socks(void) +{ + return static_key_false(&memalloc_socks); +} +#else + +static inline int sk_memalloc_socks(void) +{ + return 0; +} + +#endif + +static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask) +{ + return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC); +} + static inline void sk_acceptq_removed(struct sock *sk) { sk->sk_ack_backlog--; @@ -733,8 +756,13 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s return 0; } +extern int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); + static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + return __sk_backlog_rcv(sk, skb); + return sk->sk_backlog_rcv(sk, skb); } @@ -798,6 +826,8 @@ extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p); extern void sk_stream_wait_close(struct sock *sk, long timeo_p); extern int sk_stream_error(struct sock *sk, int flags, int err); extern void sk_stream_kill_queues(struct sock *sk); +extern void sk_set_memalloc(struct sock *sk); +extern void sk_clear_memalloc(struct sock *sk); extern int sk_wait_data(struct sock *sk, long *timeo); @@ -913,7 +943,7 @@ struct proto { #ifdef SOCK_REFCNT_DEBUG atomic_t socks; #endif -#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM +#ifdef CONFIG_MEMCG_KMEM /* * cgroup specific init/deinit functions. Called once for all * protocols that implement it, from cgroups populate function. @@ -994,7 +1024,7 @@ inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ -#if defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) && defined(CONFIG_NET) +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_NET) extern struct static_key memcg_socket_limit_enabled; static inline struct cg_proto *parent_cg_proto(struct proto *proto, struct cg_proto *cg_proto) @@ -1301,12 +1331,14 @@ static inline bool sk_wmem_schedule(struct sock *sk, int size) __sk_mem_schedule(sk, size, SK_MEM_SEND); } -static inline bool sk_rmem_schedule(struct sock *sk, int size) +static inline bool +sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, unsigned int size) { if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_RECV); + return size<= sk->sk_forward_alloc || + __sk_mem_schedule(sk, size, SK_MEM_RECV) || + skb_pfmemalloc(skb); } static inline void sk_mem_reclaim(struct sock *sk) diff --git a/include/net/tcp.h b/include/net/tcp.h index e19124b..1f000ff 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -464,6 +464,7 @@ extern int tcp_disconnect(struct sock *sk, int flags); void tcp_connect_init(struct sock *sk); void tcp_finish_connect(struct sock *sk, struct sk_buff *skb); int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size); +void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb); /* From syncookies.c */ extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS]; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d9509eb..976a81a 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -213,6 +213,9 @@ struct xfrm_state { struct xfrm_lifetime_cur curlft; struct tasklet_hrtimer mtimer; + /* used to fix curlft->add_time when changing date */ + long saved_tmo; + /* Last used time */ unsigned long lastused; @@ -238,6 +241,7 @@ static inline struct net *xs_net(struct xfrm_state *x) /* xflags - make enum if more show up */ #define XFRM_TIME_DEFER 1 +#define XFRM_SOFT_EXPIRE 2 enum { XFRM_STATE_VOID, @@ -288,6 +292,8 @@ struct xfrm_policy_afinfo { struct flowi *fl, int reverse); int (*get_tos)(const struct flowi *fl); + void (*init_dst)(struct net *net, + struct xfrm_dst *dst); int (*init_path)(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len); diff --git a/include/sound/es1688.h b/include/sound/es1688.h index 3ec7ecb..f752dd3 100644 --- a/include/sound/es1688.h +++ b/include/sound/es1688.h @@ -29,6 +29,7 @@ #define ES1688_HW_AUTO 0x0000 #define ES1688_HW_688 0x0001 #define ES1688_HW_1688 0x0002 +#define ES1688_HW_UNDEF 0x0003 struct snd_es1688 { unsigned long port; /* port of ESS chip */ diff --git a/include/sound/pcm.h b/include/sound/pcm.h index c75c0d1..cdca2ab 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -1075,7 +1075,8 @@ static inline void snd_pcm_limit_isa_dma_size(int dma, size_t *max) const char *snd_pcm_format_name(snd_pcm_format_t format); /** - * Get a string naming the direction of a stream + * snd_pcm_stream_str - Get a string naming the direction of a stream + * @substream: the pcm substream instance */ static inline const char *snd_pcm_stream_str(struct snd_pcm_substream *substream) { diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h index 9fe3a36..d6fd8e5 100644 --- a/include/trace/events/gfpflags.h +++ b/include/trace/events/gfpflags.h @@ -30,6 +30,7 @@ {(unsigned long)__GFP_COMP, "GFP_COMP"}, \ {(unsigned long)__GFP_ZERO, "GFP_ZERO"}, \ {(unsigned long)__GFP_NOMEMALLOC, "GFP_NOMEMALLOC"}, \ + {(unsigned long)__GFP_MEMALLOC, "GFP_MEMALLOC"}, \ {(unsigned long)__GFP_HARDWALL, "GFP_HARDWALL"}, \ {(unsigned long)__GFP_THISNODE, "GFP_THISNODE"}, \ {(unsigned long)__GFP_RECLAIMABLE, "GFP_RECLAIMABLE"}, \ diff --git a/include/trace/events/random.h b/include/trace/events/random.h new file mode 100644 index 0000000..422df19 --- /dev/null +++ b/include/trace/events/random.h @@ -0,0 +1,134 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM random + +#if !defined(_TRACE_RANDOM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_RANDOM_H + +#include <linux/writeback.h> +#include <linux/tracepoint.h> + +DECLARE_EVENT_CLASS(random__mix_pool_bytes, + TP_PROTO(const char *pool_name, int bytes, unsigned long IP), + + TP_ARGS(pool_name, bytes, IP), + + TP_STRUCT__entry( + __field( const char *, pool_name ) + __field( int, bytes ) + __field(unsigned long, IP ) + ), + + TP_fast_assign( + __entry->pool_name = pool_name; + __entry->bytes = bytes; + __entry->IP = IP; + ), + + TP_printk("%s pool: bytes %d caller %pF", + __entry->pool_name, __entry->bytes, (void *)__entry->IP) +); + +DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes, + TP_PROTO(const char *pool_name, int bytes, unsigned long IP), + + TP_ARGS(pool_name, bytes, IP) +); + +DEFINE_EVENT(random__mix_pool_bytes, mix_pool_bytes_nolock, + TP_PROTO(const char *pool_name, int bytes, unsigned long IP), + + TP_ARGS(pool_name, bytes, IP) +); + +TRACE_EVENT(credit_entropy_bits, + TP_PROTO(const char *pool_name, int bits, int entropy_count, + int entropy_total, unsigned long IP), + + TP_ARGS(pool_name, bits, entropy_count, entropy_total, IP), + + TP_STRUCT__entry( + __field( const char *, pool_name ) + __field( int, bits ) + __field( int, entropy_count ) + __field( int, entropy_total ) + __field(unsigned long, IP ) + ), + + TP_fast_assign( + __entry->pool_name = pool_name; + __entry->bits = bits; + __entry->entropy_count = entropy_count; + __entry->entropy_total = entropy_total; + __entry->IP = IP; + ), + + TP_printk("%s pool: bits %d entropy_count %d entropy_total %d " + "caller %pF", __entry->pool_name, __entry->bits, + __entry->entropy_count, __entry->entropy_total, + (void *)__entry->IP) +); + +TRACE_EVENT(get_random_bytes, + TP_PROTO(int nbytes, unsigned long IP), + + TP_ARGS(nbytes, IP), + + TP_STRUCT__entry( + __field( int, nbytes ) + __field(unsigned long, IP ) + ), + + TP_fast_assign( + __entry->nbytes = nbytes; + __entry->IP = IP; + ), + + TP_printk("nbytes %d caller %pF", __entry->nbytes, (void *)__entry->IP) +); + +DECLARE_EVENT_CLASS(random__extract_entropy, + TP_PROTO(const char *pool_name, int nbytes, int entropy_count, + unsigned long IP), + + TP_ARGS(pool_name, nbytes, entropy_count, IP), + + TP_STRUCT__entry( + __field( const char *, pool_name ) + __field( int, nbytes ) + __field( int, entropy_count ) + __field(unsigned long, IP ) + ), + + TP_fast_assign( + __entry->pool_name = pool_name; + __entry->nbytes = nbytes; + __entry->entropy_count = entropy_count; + __entry->IP = IP; + ), + + TP_printk("%s pool: nbytes %d entropy_count %d caller %pF", + __entry->pool_name, __entry->nbytes, __entry->entropy_count, + (void *)__entry->IP) +); + + +DEFINE_EVENT(random__extract_entropy, extract_entropy, + TP_PROTO(const char *pool_name, int nbytes, int entropy_count, + unsigned long IP), + + TP_ARGS(pool_name, nbytes, entropy_count, IP) +); + +DEFINE_EVENT(random__extract_entropy, extract_entropy_user, + TP_PROTO(const char *pool_name, int nbytes, int entropy_count, + unsigned long IP), + + TP_ARGS(pool_name, nbytes, entropy_count, IP) +); + + + +#endif /* _TRACE_RANDOM_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index ea7a203..5a8671e 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -73,6 +73,9 @@ DECLARE_EVENT_CLASS(sched_wakeup_template, __entry->prio = p->prio; __entry->success = success; __entry->target_cpu = task_cpu(p); + ) + TP_perf_assign( + __perf_task(p); ), TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d", @@ -325,6 +328,7 @@ DECLARE_EVENT_CLASS(sched_stat_template, ) TP_perf_assign( __perf_count(delay); + __perf_task(tsk); ), TP_printk("comm=%s pid=%d delay=%Lu [ns]", diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h index c6bc2fa..a763888 100644 --- a/include/trace/ftrace.h +++ b/include/trace/ftrace.h @@ -712,6 +712,9 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call #undef __perf_count #define __perf_count(c) __count = (c) +#undef __perf_task +#define __perf_task(t) __task = (t) + #undef TP_perf_assign #define TP_perf_assign(args...) args @@ -725,6 +728,7 @@ perf_trace_##call(void *__data, proto) \ struct ftrace_raw_##call *entry; \ struct pt_regs __regs; \ u64 __addr = 0, __count = 1; \ + struct task_struct *__task = NULL; \ struct hlist_head *head; \ int __entry_size; \ int __data_size; \ @@ -752,7 +756,7 @@ perf_trace_##call(void *__data, proto) \ \ head = this_cpu_ptr(event_call->perf_events); \ perf_trace_buf_submit(entry, __entry_size, rctx, __addr, \ - __count, &__regs, head); \ + __count, &__regs, head, __task); \ } /* diff --git a/include/video/da8xx-fb.h b/include/video/da8xx-fb.h index 89d43b3..5a0e4f9 100644 --- a/include/video/da8xx-fb.h +++ b/include/video/da8xx-fb.h @@ -82,6 +82,9 @@ struct lcd_ctrl_config { /* Raster Data Order Select: 1=Most-to-least 0=Least-to-most */ unsigned char raster_order; + + /* DMA FIFO threshold */ + int fifo_th; }; struct lcd_sync_arg { diff --git a/include/video/omapdss.h b/include/video/omapdss.h index c8e59b4..a6267a2 100644 --- a/include/video/omapdss.h +++ b/include/video/omapdss.h @@ -48,6 +48,10 @@ #define DISPC_IRQ_FRAMEDONEWB (1 << 23) #define DISPC_IRQ_FRAMEDONETV (1 << 24) #define DISPC_IRQ_WBBUFFEROVERFLOW (1 << 25) +#define DISPC_IRQ_FRAMEDONE3 (1 << 26) +#define DISPC_IRQ_VSYNC3 (1 << 27) +#define DISPC_IRQ_ACBIAS_COUNT_STAT3 (1 << 28) +#define DISPC_IRQ_SYNC_LOST3 (1 << 29) struct omap_dss_device; struct omap_overlay_manager; @@ -75,6 +79,7 @@ enum omap_channel { OMAP_DSS_CHANNEL_LCD = 0, OMAP_DSS_CHANNEL_DIGIT = 1, OMAP_DSS_CHANNEL_LCD2 = 2, + OMAP_DSS_CHANNEL_LCD3 = 3, }; enum omap_color_mode { @@ -99,11 +104,6 @@ enum omap_color_mode { OMAP_DSS_COLOR_XRGB16_1555 = 1 << 18, /* xRGB16 - 1555 */ }; -enum omap_lcd_display_type { - OMAP_DSS_LCD_DISPLAY_STN, - OMAP_DSS_LCD_DISPLAY_TFT, -}; - enum omap_dss_load_mode { OMAP_DSS_LOAD_CLUT_AND_FRAME = 0, OMAP_DSS_LOAD_CLUT_ONLY = 1, @@ -121,15 +121,15 @@ enum omap_rfbi_te_mode { OMAP_DSS_RFBI_TE_MODE_2 = 2, }; -enum omap_panel_config { - OMAP_DSS_LCD_IVS = 1<<0, - OMAP_DSS_LCD_IHS = 1<<1, - OMAP_DSS_LCD_IPC = 1<<2, - OMAP_DSS_LCD_IEO = 1<<3, - OMAP_DSS_LCD_RF = 1<<4, - OMAP_DSS_LCD_ONOFF = 1<<5, +enum omap_dss_signal_level { + OMAPDSS_SIG_ACTIVE_HIGH = 0, + OMAPDSS_SIG_ACTIVE_LOW = 1, +}; - OMAP_DSS_LCD_TFT = 1<<20, +enum omap_dss_signal_edge { + OMAPDSS_DRIVE_SIG_OPPOSITE_EDGES, + OMAPDSS_DRIVE_SIG_RISING_EDGE, + OMAPDSS_DRIVE_SIG_FALLING_EDGE, }; enum omap_dss_venc_type { @@ -167,13 +167,6 @@ enum omap_dss_audio_state { OMAP_DSS_AUDIO_PLAYING, }; -/* XXX perhaps this should be removed */ -enum omap_dss_overlay_managers { - OMAP_DSS_OVL_MGR_LCD, - OMAP_DSS_OVL_MGR_TV, - OMAP_DSS_OVL_MGR_LCD2, -}; - enum omap_dss_rotation_type { OMAP_DSS_ROT_DMA = 1 << 0, OMAP_DSS_ROT_VRFB = 1 << 1, @@ -268,9 +261,6 @@ struct omap_dss_dsi_videomode_data { int hfp_blanking_mode; /* Video port sync events */ - int vp_de_pol; - int vp_hsync_pol; - int vp_vsync_pol; bool vp_vsync_end; bool vp_hsync_end; @@ -346,6 +336,19 @@ struct omap_video_timings { u16 vfp; /* Vertical front porch */ /* Unit: line clocks */ u16 vbp; /* Vertical back porch */ + + /* Vsync logic level */ + enum omap_dss_signal_level vsync_level; + /* Hsync logic level */ + enum omap_dss_signal_level hsync_level; + /* Interlaced or Progressive timings */ + bool interlace; + /* Pixel clock edge to drive LCD data */ + enum omap_dss_signal_edge data_pclk_edge; + /* Data enable logic level */ + enum omap_dss_signal_level de_level; + /* Pixel clock edges to drive HSYNC and VSYNC signals */ + enum omap_dss_signal_edge sync_pclk_edge; }; #ifdef CONFIG_OMAP2_DSS_VENC @@ -559,8 +562,6 @@ struct omap_dss_device { /* Unit: line clocks */ int acb; /* ac-bias pin frequency */ - enum omap_panel_config config; - enum omap_dss_dsi_pixel_format dsi_pix_fmt; enum omap_dss_dsi_mode dsi_mode; struct omap_dss_dsi_videomode_data dsi_vm_data; diff --git a/include/video/sh_mobile_lcdc.h b/include/video/sh_mobile_lcdc.h index 7571b27..ff43ffc 100644 --- a/include/video/sh_mobile_lcdc.h +++ b/include/video/sh_mobile_lcdc.h @@ -166,6 +166,12 @@ struct sh_mobile_lcdc_bl_info { int (*get_brightness)(void); }; +struct sh_mobile_lcdc_overlay_cfg { + int fourcc; + unsigned int max_xres; + unsigned int max_yres; +}; + struct sh_mobile_lcdc_chan_cfg { int chan; int fourcc; @@ -186,6 +192,7 @@ struct sh_mobile_lcdc_chan_cfg { struct sh_mobile_lcdc_info { int clock_source; struct sh_mobile_lcdc_chan_cfg ch[2]; + struct sh_mobile_lcdc_overlay_cfg overlays[4]; struct sh_mobile_meram_info *meram_dev; }; diff --git a/include/video/sh_mobile_meram.h b/include/video/sh_mobile_meram.h index 29b2fd3..062e6e7 100644 --- a/include/video/sh_mobile_meram.h +++ b/include/video/sh_mobile_meram.h @@ -15,7 +15,6 @@ enum { struct sh_mobile_meram_priv; -struct sh_mobile_meram_ops; /* * struct sh_mobile_meram_info - MERAM platform data @@ -24,7 +23,6 @@ struct sh_mobile_meram_ops; struct sh_mobile_meram_info { int addr_mode; u32 reserved_icbs; - struct sh_mobile_meram_ops *ops; struct sh_mobile_meram_priv *priv; struct platform_device *pdev; }; @@ -38,26 +36,59 @@ struct sh_mobile_meram_cfg { struct sh_mobile_meram_icb_cfg icb[2]; }; -struct module; -struct sh_mobile_meram_ops { - struct module *module; - /* register usage of meram */ - void *(*meram_register)(struct sh_mobile_meram_info *meram_dev, - const struct sh_mobile_meram_cfg *cfg, - unsigned int xres, unsigned int yres, - unsigned int pixelformat, - unsigned int *pitch); - - /* unregister usage of meram */ - void (*meram_unregister)(struct sh_mobile_meram_info *meram_dev, - void *data); - - /* update meram settings */ - void (*meram_update)(struct sh_mobile_meram_info *meram_dev, void *data, +#if defined(CONFIG_FB_SH_MOBILE_MERAM) || \ + defined(CONFIG_FB_SH_MOBILE_MERAM_MODULE) +unsigned long sh_mobile_meram_alloc(struct sh_mobile_meram_info *meram_dev, + size_t size); +void sh_mobile_meram_free(struct sh_mobile_meram_info *meram_dev, + unsigned long mem, size_t size); +void *sh_mobile_meram_cache_alloc(struct sh_mobile_meram_info *dev, + const struct sh_mobile_meram_cfg *cfg, + unsigned int xres, unsigned int yres, + unsigned int pixelformat, + unsigned int *pitch); +void sh_mobile_meram_cache_free(struct sh_mobile_meram_info *dev, void *data); +void sh_mobile_meram_cache_update(struct sh_mobile_meram_info *dev, void *data, + unsigned long base_addr_y, + unsigned long base_addr_c, + unsigned long *icb_addr_y, + unsigned long *icb_addr_c); +#else +static inline unsigned long +sh_mobile_meram_alloc(struct sh_mobile_meram_info *meram_dev, size_t size) +{ + return 0; +} + +static inline void +sh_mobile_meram_free(struct sh_mobile_meram_info *meram_dev, + unsigned long mem, size_t size) +{ +} + +static inline void * +sh_mobile_meram_cache_alloc(struct sh_mobile_meram_info *dev, + const struct sh_mobile_meram_cfg *cfg, + unsigned int xres, unsigned int yres, + unsigned int pixelformat, + unsigned int *pitch) +{ + return ERR_PTR(-ENODEV); +} + +static inline void +sh_mobile_meram_cache_free(struct sh_mobile_meram_info *dev, void *data) +{ +} + +static inline void +sh_mobile_meram_cache_update(struct sh_mobile_meram_info *dev, void *data, unsigned long base_addr_y, unsigned long base_addr_c, unsigned long *icb_addr_y, - unsigned long *icb_addr_c); -}; + unsigned long *icb_addr_c) +{ +} +#endif #endif /* __VIDEO_SH_MOBILE_MERAM_H__ */ |